KR102203893B1 - System for automating customer management using auto-call based on Artificial Intelligence and method thereof - Google Patents

Abstract

The present invention relates to a customer management automation system through an auto call based on artificial intelligence and a method thereof. That is, the present invention collects auto call records by performing an automated outbound call function according to a script and a DB list provided from a server in a terminal and continues to collect auto call records by performing an automated outbound call function through an updated script and DB list based on a result of analyzing the collected auto call records, and thus the present invention increases the utilization of customer information by additionally collecting information on purchase intention and targets, and automates repetitive tasks using auto-call, so that a business manager can focus on core tasks.

Description

System for automating customer management using auto-call based on Artificial Intelligence and method thereof

The present invention relates to an automated customer management system and method thereof through an artificial intelligence-based auto call, and in particular, collects auto call records by performing an automated outbound call function according to a script and DB list provided from a server in a terminal, Based on the result of analyzing the collected auto call records, the automated outbound call function is executed through the updated script and DB list to continuously collect the auto call records, and the information filtering function and information on the collected auto call records It relates to a customer management automation system and a method thereof through an artificial intelligence-based auto call that provides an extraction function and the like.

The act of marketing over the phone is called telemarketing, and a place equipped with counselors and related facilities is called a call center. It is also called a contact center in terms of consulting not only by phone but also through e-mail and the Internet.

The work in these call centers is classified into in-bound work and out-bound work. Among them, inbound service is a form in which a call center counselor provides services for external calls, faxes, and e-mails, while outbound business is a form of marketing by calling directly to provide information or sell products.

In the outbound call center environment, which is mainly for sales, there are many telemarketers working in the call center office, and all the work is being done, resulting in poor work efficiency.

In addition, in the case of call centers, maximizing the sales performance of the salesperson is the key.For this, it is necessary to secure targeted customers in advance and provide contacts with high purchase intentions to the salesperson, but a method for obtaining such targeted customer information This is inadequate..

Korean Patent Application Publication No. 10-2009-0087938 [Title: System for establishing outbound communication with contacts from the center]

An object of the present invention is to perform an automated outbound call function according to a script and DB list provided from a server in a terminal to collect auto call records, and to update scripts and DB lists based on the results of analyzing the collected auto call records. Automated customer management system through artificial intelligence-based auto call that continuously collects auto call records by performing an automated outbound call function through the system and provides information filtering and information extraction functions for the collected auto call records. And to provide the method.

Another object of the present invention is to collect auto call records by performing an automated outbound call function according to a script and DB list provided from a server in a terminal, and update scripts and DBs based on the results of analyzing the collected auto call records. It is to provide an automated customer management system and method for customer management through auto call based on artificial intelligence that collects auto call records by performing an automated outbound call function through a list.

Another object of the present invention is a customer management automation system through auto call based on artificial intelligence that collects auto call records by performing an automated outbound call function according to a script and DB list in connection with a cloud calling server in a server, and There is a way to provide.

An automated customer management system through an artificial intelligence-based auto call according to an embodiment of the present invention includes a server for transmitting a plurality of scripts and DB lists; And generating the plurality of scripts into a plurality of sound source files through a text-to-speech function, and responding to a plurality of contacts corresponding to a preset ratio among the DB list transmitted from the server using the generated plurality of sound source files. Performs an auto-call function with another terminal to be called, generates an auto-call record with the other terminal according to the progress of the auto-call, and traffic to multiple contacts for multiple scripts composed of multiple survey contents or multiple similar survey contents Based on a number of auto-call records that are the result of distributed processing, A/B test is performed according to preset indicators including at least one of answer conversion rate, sales conversion rate, survey content, time zone, and music source gender, and A/B test In order to optimize the sound source file based on the execution result, the contact information remaining as any one sound source file that is the most efficient as a result of performing an A/B test among the plurality of survey contents or a plurality of sound source files composed of the plurality of similar survey contents A terminal that performs an auto-call function by driving and transmits a plurality of auto-call records, optimized sound source files, and terminal identification information generated according to the auto-call performed on a plurality of contacts included in the DB list to the server. Can include.

As an example related to the present invention, each of the plurality of scripts may be a state in which a plurality of questionnaire contents are combined in a different order according to a purpose, or a state in which each questionnaire content is generated in a similar structure.

As an example related to the present invention, the terminal divides a plurality of contacts corresponding to a preset ratio among the DB list according to the number of the generated plurality of sound source files, and divides the divided one or more contacts into the generated plurality of contacts. Each of the sound source files may be assigned to each of the sound source files, and the auto-call function may be sequentially performed with other terminals corresponding to one or more contacts for each of the plurality of sound source files.

As an example related to the present invention, the auto call record includes a script, a sound source file corresponding to the script, caller information, callee information, call time, recorded file, total call length, location information, and a memo directly inputted by the user by hand. It may include at least one of.

As an example related to the present invention, the server receives the plurality of auto call records, optimized sound source files, and terminal identification information transmitted from the terminal, and filters information on the plurality of auto call records according to an administrator input At least one of a function and an information extraction function may be performed, and at least one of a result of performing an information filtering function and a result of performing an information extraction function may be output.

As an example related to the present invention, the plurality of scripts and the DB list provided from the server are interlocked with the server, and a cloud telephone line is provided from the server in units of call or time, and the server does not have its own terminal. A client that performs an auto call function may be further included by using.

A method for automating customer management through an artificial intelligence-based auto call according to an embodiment of the present invention includes the steps of: by a terminal, generating a plurality of scripts transmitted from a server as a plurality of sound source files through a text-to-speech function; Performing, by the terminal, an auto call function with other terminals corresponding to a plurality of contacts corresponding to a preset ratio among the DB list transmitted from the server by using the generated plurality of sound source files; Generating, by the terminal, an auto call record with the other terminal according to the progress of the auto call; By the terminal, response conversion rate, sales conversion rate, questionnaire content, based on a plurality of auto call records resulting from distributing traffic to a plurality of contacts for a plurality of scripts consisting of a plurality of survey contents or a plurality of similar survey contents, Performing an A/B test according to a preset indicator including at least one of a time zone and a sound source gender; In order to optimize the sound source file based on the result of the A/B test performed by the terminal, the A/B test result is the most efficient among the plurality of sound source files composed of the plurality of questionnaire content or the plurality of similar questionnaire content. Performing an auto call function by driving the remaining contacts to any one sound source file; And transmitting, by the terminal, a plurality of autocall records generated according to an autocall performed on a plurality of contacts included in the DB list, an optimized sound source file, and identification information of the terminal to the server. I can.

As an example related to the present invention, the step of performing an auto-call function with other terminals corresponding to the plurality of contacts includes a plurality of contacts corresponding to a preset ratio among the DB list to the number of the generated plurality of sound source files. The process of dividing along; Allocating the divided one or more contacts to each of the generated plurality of sound source files; And performing an auto-call function sequentially with other terminals corresponding to one or more contacts for each of the plurality of sound source files.

As an example related to the present invention, the step of receiving, by the server, the plurality of auto call records, optimized sound source files, and identification information of the terminal transmitted from the terminal; Performing, by the server, at least one of an information filtering function and an information extraction function for the plurality of auto call records according to an administrator input; And outputting, by the server, at least one of a result of performing an information filtering function and a result of performing an information extraction function.

As an example related to the present invention, providing a cloud telephone line to the client in a call unit or a time unit by the server in connection with the client; And performing an auto call function by the client using the plurality of scripts and the DB list provided from the server, even if the client does not have its own terminal.

The present invention collects auto call records by performing an automated outbound call function according to a script and DB list provided from a server in a terminal, and through an updated script and DB list based on the result of analyzing the collected auto call records. By performing an automated outbound call function to continuously collect auto call records, and by providing information filtering and information extraction functions for the collected auto call records, additional information on purchase intention and target is collected. Accordingly, it has the effect of increasing the utilization of customer information, automating repetitive tasks using auto-call, and allowing salespeople to focus on core tasks.

In addition, the present invention collects auto call records by performing an automated outbound call function according to the script and DB list provided from the server in the terminal, and the updated script and DB list based on the result of analyzing the collected auto call records. Auto call records are collected by performing an automated outbound call function through the system, thereby increasing the reliability of the auto call records collected by collecting auto call records using optimized scripts among multiple scripts, and automating customer information collection. There is an effect that can improve the efficiency.

In addition, the present invention collects auto call records by performing an automated outbound call function according to a script and DB list by interlocking with the cloud calling server in the server, so that the auto call function can be performed even if the client side does not have the terminal itself. There is an effect that can be used.

1 is a block diagram showing the configuration of a customer management automation system through an artificial intelligence-based auto call according to an embodiment of the present invention.
2 is a flowchart illustrating a method for automating customer management through an artificial intelligence-based auto call according to an embodiment of the present invention.

It should be noted that the technical terms used in the present invention are used only to describe specific embodiments, and are not intended to limit the present invention. In addition, the technical terms used in the present invention should be interpreted as generally understood by those of ordinary skill in the technical field to which the present invention belongs, unless otherwise defined in the present invention, and is excessively comprehensive. It should not be construed as a human meaning or an excessively reduced meaning. In addition, when a technical term used in the present invention is an incorrect technical term that does not accurately express the spirit of the present invention, it should be replaced with a technical term that can be correctly understood by those skilled in the art. In addition, general terms used in the present invention should be interpreted as defined in the dictionary or according to the context before and after, and should not be interpreted as an excessively reduced meaning.

In addition, the singular expression used in the present invention includes a plurality of expressions unless the context clearly indicates otherwise. In the present invention, terms such as “consisting of” or “comprising” should not be construed as necessarily including all of the various components or steps described in the invention, and some components or some steps may not be included. It should be construed that it may or may further include additional components or steps.

In addition, terms including ordinal numbers such as first and second used in the present invention may be used to describe the constituent elements, but the constituent elements should not be limited by the terms. The terms are used only for the purpose of distinguishing one component from another. For example, without departing from the scope of the present invention, a first component may be referred to as a second component, and similarly, a second component may be referred to as a first component.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings, but the same or similar components are assigned the same reference numerals regardless of the reference numerals, and redundant descriptions thereof will be omitted.

In addition, in describing the present invention, when it is determined that a detailed description of a related known technology may obscure the subject matter of the present invention, a detailed description thereof will be omitted. In addition, it should be noted that the accompanying drawings are only for easily understanding the spirit of the present invention and should not be construed as limiting the spirit of the present invention by the accompanying drawings.

1 is a block diagram showing the configuration of a customer management automation system 10 through an artificial intelligence-based auto call according to an embodiment of the present invention.

As shown in FIG. 1, the customer management automation system 10 through an artificial intelligence-based auto call is composed of a terminal 100 and a server 200. Not all of the components of the customer management automation system 10 shown in FIG. 1 are essential components, and the customer management automation system 10 may be implemented by more components than the components shown in FIG. 1, The customer management automation system 10 may be implemented with fewer components.

Each of the terminal 100 and the server 200 includes a communication unit (not shown) for performing a communication function with other terminals, a storage unit (not shown) for storing various information and programs (or applications), and various A display unit (not shown) for displaying information and program execution results, an audio output unit (not shown) for outputting audio information corresponding to the various information and program execution results, and controlling various components and functions of each terminal It may include a control unit (not shown) and the like.

The terminal 100 includes a smart phone, a portable terminal, a mobile terminal, a foldable terminal, a personal digital assistant (PDA), and a portable multimedia device (PMP). Player) Terminal, Telematics Terminal, Navigation Terminal, Personal Computer, Notebook Computer, Slate PC, Tablet PC, Ultrabook, Wearable Device (Wearable) Device, for example, including smartwatch, smart glass, HMD (Head Mounted Display), Wibro terminal, Internet Protocol Television (IPTV) terminal, smart TV, digital broadcasting It can be applied to various terminals such as terminals, audio video navigation (AVN) terminals, audio/video (A/V) systems, flexible terminals, digital signage devices, and Internet telephone terminals.

The terminal 100 communicates with the server 200 and the like. In this case, the terminal 100 may be a terminal possessed by a user performing an auto call function using a DB list provided from the server 200.

In addition, the terminal 100 is a user for receiving an auto call function, an auto call record management function, etc. through a dedicated app and/or website provided by the server 200 by interworking with the server 200 Sign up as a member, and register personal information and the like in the server 200. In this case, the personal information includes ID, email address, password (or password), name, gender, date of birth, contact information, address, and the like.

In addition, the terminal 100 may subscribe as a user to the server 200 by using SNS account information or mobile messenger account information to which the user of the terminal 100 has subscribed. Here, the SNS account may be information related to Facebook, Twitter, Kakao Story, Naver, PAYCO, and the like. In addition, the mobile messenger account is information related to KakaoTalk, line, viber, wechat, whatsapp, Telegram, and snapchat. I can.

In addition, when performing the membership registration procedure, the terminal 100 must complete the authentication function through an identity authentication means (eg, mobile phone, credit card, i-PIN, etc.) to normally perform the membership registration procedure for the server 200. Can be completed.

In addition, after membership registration is completed, the terminal 100 corresponds to a dedicated app (or application/application/specific app) provided from the server 200 in order to use the service provided by the server 200. It is installed in the terminal 100. In this case, the dedicated app may be an app for performing an auto call function, an auto call record management function, or the like.

In addition, the terminal 100 executes a dedicated app previously installed in the terminal 100 and displays an app execution result screen according to the execution of the dedicated app. At this time, the app execution result screen includes an auto call menu (or button/item) for performing an auto call function according to the DB list, an auto call record management menu for managing auto call records according to the auto call execution, and the like. . Here, the terminal 100 is a member registered with the server 200 providing the dedicated app, and executes the dedicated app using an ID and password according to membership registration, a barcode or QR code including the ID, etc. By performing a login procedure at the time, one or more functions (eg, auto-call function, auto-call record management function, etc.) of the corresponding dedicated app may be performed.

In addition, the terminal 100 receives a plurality of scripts, DB lists, etc. transmitted from the server 200. At this time, each of the plurality of scripts is a state in which the plurality of questionnaire contents are combined in a different order, or each questionnaire content is created in a similar structure (for example, a state in which words, modifiers, etc. are used differently) (or Combined) state. In addition, the script may be composed of a sales script in a text format, a questionnaire script, etc. according to the above purpose, and may be configured as individual modules for a plurality of survey contents (or sentences).

In addition, the terminal 100 generates (or converts) the plurality of scripts in the form of the received text into a plurality of sound source files through a text to speech (TTS) function.

In an embodiment of the present invention, the terminal 100 generates the script as a sound source file through a text-to-speech function, but is not limited thereto, and the server 200 performs the text-to-speech function. A script may be generated as a sound source file, and the generated sound source file may be transmitted to the terminal 100. In addition, the terminal 100 may receive a plurality of sound source files, the DB list, and the like respectively corresponding to the plurality of scripts transmitted from the server 200.

In addition, the terminal 100 uses another terminal (not shown) corresponding to a plurality of contacts corresponding to a preset ratio (for example, 30%) of the received DB list by using the generated plurality of sound source files. It performs (or proceeds) the auto call (or outbound call/robo call/auto call/RPA(Robotic Process Automation)) function in sequence.

That is, the terminal 100 divides a plurality of contacts corresponding to a preset ratio among the received DB list according to the number of the generated plurality of sound source files, and divides the divided one or more contacts into the generated plurality of Each of the sound source files is assigned (or mapped/matched/set), and the auto-call function is sequentially performed with other terminals corresponding to one or more contacts for each of a plurality of sound source files.

In this way, the terminal 100 may distribute traffic to a plurality of contacts for a plurality of scripts each composed of a plurality of questionnaire contents or a plurality of similar questionnaire contents for an A/B test.

In addition, the terminal 100 generates (or collects) an auto call record with the other terminal according to the progress of the auto call, and stores (or manages) the generated auto call record. Here, the auto call record (or call record) is a script, a sound source file corresponding to the script, caller information, receiver information, call time, a recording file (or a recording file in the form of an audio/sound source), and a total call length (or total Call time), location information, and a memo (or a memo according to the user input) directly input by the user.

In addition, the terminal 100 may perform an outbound call (or auto call) function in the following manner.

That is, firstly, when the terminal 100 is a PC, when the program is executed on the PC, an outbound call is made from a connected Internet phone (for example, a PC and a phone terminal are connected through a LAN line), and the PC The auto call record recorded in may be uploaded to the server 200.

Second, when the terminal 100 is a terminal for outbound business, the other party does not answer the phone with the 070 number or 02 number in many cases. For example, an outbound call is made to (for example, 010 number) (for example, an app automatically acquires mobile phone OS permission and makes a call), and an auto call record recorded in the mobile phone may be uploaded to the server 200.

In this way, when a call event with another terminal (not shown) occurs in the terminal 100, the terminal 100 automatically stores information on the call. In this case, the terminal 100 may be in a state in which recording rights have been obtained in advance. Here, the call information (or call information/auto call record) is meta information, and a script, a sound source file corresponding to the script, caller information, receiver information, call time, recording file (or recording in the form of voice/sound source) File), total call length (or total call time), location information, memo manually entered by the user (or memo according to user input), and the like. In this case, the terminal 100 may calculate (or generate) real-time location information of the terminal 100 through a GPS receiver (not shown) configured in the terminal 100.

In addition, the terminal 100 responds to the plurality of questionnaire content or the plurality of scripts consisting of the plurality of similar questionnaire content, based on a number of auto-call records, which is a result of distributing traffic to a plurality of contacts. A/B test is performed according to various preset indicators including conversion rate, questionnaire content (or module), time zone, and sound source gender.

In addition, in order to optimize the sound source file (or script) based on the result of the A/B test, the terminal 100 may select A/B from among a plurality of sound source files composed of the plurality of questionnaire content or the plurality of similar questionnaire content. As a result of performing the test, the remaining contacts (or at least one remaining contact excluding a plurality of contacts corresponding to the above ratio in the traffic/DB list) are driven into one of the most efficient sound source files to perform the auto call function.

That is, the terminal 100 collects (or accumulates) auto call records (or conversion data) for some of the contacts included in the DB list based on the A/B test result, and then collected. Based on the auto call record (or conversion data/A/B test result), it is possible to perform the auto call function for the remaining contacts by optimizing the sound source file with the best efficiency. At this time, the terminal 100 performs an auto call function again using the most efficient sound source file for the auto call proceeding with a sound source file other than the most efficient sound source file among the plurality of sound source files. You can also create (or collect) call records.

In this way, the terminal 100 may perform an auto-call function sequentially or in a separate ordering according to an action request from the server 200.

In addition, as described above, if an app/program is installed in the terminal 100 owned by the server 200, anyone can conveniently access the service and perform the auto call function.

In addition, the terminal 100 may additionally collect information on a purchase intention and target through an automated call from a contact list (or DB list) provided as an auto call service, and increase efficiency.

In addition, the terminal 100 may automate simple and repetitive tasks, thereby automating or increasing the efficiency of tasks.

That is, the user (or business operator) of the terminal 100 can focus on core tasks and automate repetitive tasks using auto-call.

In the embodiment of the present invention, it is mainly described that the terminal 100 performs an outbound call function, but the present invention is not limited thereto, and the terminal 100 may perform a function corresponding to an inbound call.

That is, the terminal 100 can track even when a customer makes a phone call or transmits a text inbound.

For example, when viewing the missed call history after an outbound call and making an inbound call to the terminal 100 from another terminal possessed by a corresponding customer, the terminal 100 (or the server 200) It is possible to create an auto call record by matching customer information and receiving an answer through a question from the customer in the same way as calling outbound.

For another example, when a response is delivered to the terminal 100 in the form of a text message from another terminal possessed by the customer, the terminal 100 (or the server 200) ), and can proceed with the later process (or question/answer).

That is, when the corresponding customer is absent, the terminal 100 transmits an automated text in the form of a text message to the corresponding other terminal so as to maximize sales performance.

For example, the terminal 100 transmits a text message "Please contact me when a call is available" to the corresponding other terminal. In addition, when the terminal 100 makes a call from another terminal that has confirmed the text message, the terminal 100 matches customer information related to the customer of the other terminal and proceeds to answer a question through an inbound call.

As another example, the terminal 100 transmits a text message saying "If you agree with _____, send 1, and if you want to reject reception, please send 2" to another terminal. In addition, when the terminal 100 transmits a response message from another terminal that has checked the text message, the terminal 100 parses (or parses) the response message and proceeds to the next step according to the parsing result (for example, In case of case, outbound call is made, and in case of 2, it is terminated.

In addition, the terminal 100 may induce payment or use of a service by designing a complex process in advance through an RPA (or robotic process automation) function.

For example, when the terminal 100 makes a call with another terminal with the content of a questionnaire "Would you like to receive a free referral number?", and the other terminal selects an affirmative response, "Agree to automatically provide a recommendation number by text" "Do you do?" is another questionnaire content, and when a call with the other terminal is made and an affirmative response is selected from the other terminal, a preset service content may be additionally provided to the other terminal.

For another example, when the terminal 100 calls another terminal with the content of a questionnaire, "If you input the amount of stock currently investing, we will send you a recommended item every week.", and if you select a positive response from the other terminal, "Investment If you make a call with the other terminal above with another questionnaire content such as "How much is the amount?", and enter the amount on the other terminal (for example, KRW 4 million), other preset service contents (for example, "We will send you this week's spike." ") may be additionally provided to the other terminal.

In addition, the terminal 100 records a plurality of auto-calls generated (or collected) according to auto-calls performed on a plurality of contacts included in the received DB list, and optimized sound source files (or optimized scripts) , And transmits identification information of the terminal 100 to the server 200. Here, the identification information of the terminal 100 includes mobile directory number (MDN), mobile IP, mobile MAC, subscriber identity module (SIM) card unique information, serial number, and the like.

In this way, the terminal 100 communicates using an API (Application Programming Interface) provided by the server 200, and all results are stored (or registered) in the server 200 at a remote location. I can.

In addition, as described above, the terminal 100 may perform an auto call function in various ways through a mobile phone terminal, an Internet phone terminal, or the like.

In the embodiment of the present invention, it is mainly described that the terminal 100 performs an auto call function related to sales, but it is not limited thereto, and the terminal 100 is also used in the field of public opinion survey and consumer survey. Call function can be applied.

As such, the core of the call sensor is a database, and the cost of collecting or purchasing such a database is expensive.

Therefore, if the database is classified by the end of business just because it is rejected once in the customer's response, it is a big loss for a company or a business operator. Accordingly, in the embodiment of the present invention, the old DB (or the DB that has been rejected once) is contacted again (or continuously contacted through a robocall) to change the database to a possible conversion.

In addition, the terminal 100 can efficiently automate repetitive tasks of a business operator using RPA (or auto call/robo call/auto call).

In addition, although the embodiment of the present invention describes that the terminal 100 performs an auto-call function, an auto-call record management function, etc. in the form of a dedicated app, the server 200 is not limited thereto. The auto call function, the auto call record management function, etc. may be performed through a web site provided by ).

The server 200 communicates with the terminal 100 and the like.

In addition, the server 200 performs a membership registration procedure for users such as the terminal 100, etc.

In addition, the server 200 registers personal information related to a user such as the terminal 100. In this case, the server 200 may register (or manage) corresponding personal information in a DB server (not shown).

In addition, the server 200 performs a member management function for users such as the terminal 100.

In addition, the server 200 provides a dedicated app and/or website that provides an auto call function, an auto call record management function, and the like, to the terminal 100 and the like.

In addition, the server 200 provides a bulletin board function for announcements and events.

In addition, the server 200 generates a plurality of scripts composed of a plurality of questionnaire contents (or text/sentence) according to the purpose. At this time, each of the plurality of scripts is a state in which the plurality of questionnaire contents are combined in a different order, or each questionnaire content is created in a similar structure (for example, a state in which words, modifiers, etc. are used differently) (or Combined) state. In addition, the script is composed of a text type sales script, a questionnaire script, etc. according to the above purpose, and a plurality of survey contents (or sentences) are configured in individual modules.

In this way, the server 200 may generate the script by sequentially selecting the plurality of questionnaire content of the module unit as the plurality of questionnaire content is configured in a module unit, and the questionnaire content of the module unit The module can be duplicated, modified, or deleted.

For example, if you want to conduct a survey on car purchase, the server 200 may ask "How much is your budget?", "Domestic/foreign-made?", "Preferred car model?" The script may be generated by modularizing a plurality of survey contents such as, and combining the plurality of survey contents. In this case, the module may be composed of a question (or text) item, an answer item (eg, including items such as text, number, Boolean, select/option, etc.).

In addition, the server 200 transmits the generated plurality of scripts and DB lists to the terminal 100. Here, the DB list may be leads information (or preliminary customer list information/TM target list information) that is DB information on a customer.

In addition, the server 200 receives a plurality of auto call records, optimized sound source files (or optimized scripts), and identification information of the terminal 100 transmitted from the terminal 100.

In addition, the server 200 performs an information filtering function, an information extraction function, etc. for the plurality of auto call records according to an administrator input (or administrator selection/touch/control), and an information filtering function execution result, an information extraction function Output (or display) the execution result, etc.

For example, the information filtering function includes a list of people who answered 2 to question 1 (or content of questionnaire 1), a list of people who hung up on question 2, and the like.

In the embodiment of the present invention, it is described that the terminal 100 performs an A/B test function, but the present invention is not limited thereto, and the server 200 interworks with the terminal 100, and the terminal 100 ) To perform the corresponding A/B test function using a plurality of auto-call records provided from), and to optimize the sound source file (or script) based on the A/B test result, the plurality of survey contents or the plurality of Among a plurality of sound source files composed of similar survey contents of the A/B test result, the contact information remaining as one of the most efficient sound source files (or at least one remaining excluding a number of contacts corresponding to the above ratio in the traffic/DB list) It is also possible to configure to perform an auto call function in the corresponding terminal 100 by driving the contact information of the terminal.

In this way, according to the execution of the A/B test function, various optimizations may be performed according to the business purpose, rather than simply maximizing the number of answers.

For example, if the key question is "How much is your budget?", you may be able to identify the question module with a high budget and make an optimization choice that maximizes the sum of that budget.

In addition, the server 200 can variously grasp the result of script registration or outbound call, and provides an export/import function for this.

That is, the server 200 performs various filtering functions or data export functions for auto call records.

In addition, when the auto call is terminated through the API and a specific event occurs (or when the answer is completed), the server 200 interlocks data to other services through a preset outbound hook API. You may.

In addition, the server 200 manages the auto call record and performs a filtering function. Here, the filtering function is to download the entire outbound call list, download non-responders, download users who answered a specific response (for example, yes or no) to a specific item (for example, item 1), and download other specific items ( For example, it may include downloading a user who answered another specific response (for example, 10 million won or more) to item 3), and downloading a user who satisfies several conditions with OR/AND conditions.

For example, the server 200 records how to make a call to the lead (or one DB) (for example, absent → absent → text received → auto call → answer only up to item 3 and terminate → absent → Auto call → including answering up to question 10) is managed.

In addition, the server 200 interlocks with the terminal 100 to manage all auto-call records, all auto-call recordings, all inbound records, all inbound recordings, and all text message reception/transmission details.

In addition, the server 200 performs a preset action.

That is, the server 200 may select a specific list and execute a desired action through it.

For example, the server 200 interlocks with the terminal 100 to collectively send a text message to a selected specific list.

For another example, the server 200 works with the terminal 100 to automatically target customers who have been absent on a preset date (for example, 1:10:20 pm on June 01, 2020). The auto call function is executed again with

In addition, the server 200 interlocks with a cloud server (or client) (not shown) to provide a cloud phone line to the client in units of call or time, and the corresponding client has its own terminal (or number/device). Even if it is not owned, the auto call function may be used (or executed) using a plurality of scripts and DB lists provided from the server 200. In this case, the server 200 may interwork with the cloud server (or client) through an API, and may request an action.

In addition, when the action is executed (or when the command to run the auto call is transmitted after entering the database and completing the script input), a mobile phone application in a remote location or a PC connected to the Internet phone through the API operates, After phone calls are made sequentially (or in random/optimized order) from a remote location, the server 200 collects the result (or auto call record) through the API.

That is, the user does not need to have a separate terminal, and can use the auto call service by simply accessing and using the server 200 through the web.

In addition, the server 200 calculates a preset reliability for auto-call records according to the corresponding sales survey, public opinion survey, and consumer survey so that the auto call function can be performed in the fields of business survey, public opinion survey, and consumer survey. According to the method, the reliability of the auto call record is calculated.

In addition, the server 200 manages the calculated reliability by interlocking (or mapping/matching) the auto call record.

In addition, the server 200 may provide related information to a company (or corporate server) (not shown) that needs information in the form of SaaS (Software as a Service) or IaaS (Infrastructure as a Service) through Open API. I can.

In other words, the server 200 can link the robocall service by linking with services such as CRM, SalesForce, Google Spreadsheet, and SQL (DB) owned by the administrator, even if the administrator does not have to manually input the DB list or script. I can.

That is, when a specific action occurs, the server 200 may directly transmit data to the CRM through the outbound hook API.

For example, when a response occurs, the server 200 may automatically transmit data to CRM through REST API.

In addition, the server 200 manages all databases (or leads) in CRM (customer relationship management), and filters according to various collected criteria (eg, all outbound call list filters, non-responders Filters, filters for users who responded to specific items, etc.)

In this way, the server 200 may manage, filter, and measure customer information according to a plurality of auto-call records through a CRM solution.

In addition, the server 200 does not simply store customer information (or database), but how many times they have entered the same contact information (leads), and how they did business for such customer information (sales/opportunity), and Based on these achievements, we analyze what kind of results were produced.

In addition, the server 200 is interested in not only the simple quantitative indicators of the auto call record (for example, the number of calls, the number of responses, etc.), but also behavioral data (for example, what description content is mainly stopped, what description content). Including whether or not it is shown), a web front-end technology can be applied.

In addition, the server 200 provides the terminal 100 with an analysis result obtained by analyzing the collected various auto call records.

In addition, the server 200 includes leads information (or prospective customer list information/TM target list information), orders information, team information, analytics information, and other information about the customer. And the like are stored (or managed) in a database (not shown). In this case, the server 200 may access the database through an API gateway (not shown).

In addition, the server 200 may provide a web-based integrated dashboard for managers during sales according to an auto call function.

Here, the integrated dashboard is controlled by the manager, a team/organizational chart management function (including, for example, a salesperson creation function, an authority management function, etc.), a leeds management function (for example, distribution and collection of leeds to individual salesmen) Functions, etc.), order management functions (e.g., the ability to identify sales/conversions of individual sales persons or the whole, send contracts or modify contract information, etc.), analytical management functions (e.g., individual It includes information for performing the business operator, period or total, and the function of managing indicators according to specific conditions).

In this way, the server 200 connects to the database through the API gateway, regardless of the CRM (for example, a number of platforms such as SalesForce, HubSpot, Google Spreadsheet, Excel, etc.) platform (or through an interlocked application). You can connect.

In addition, the terminal 100 may access the database or the server 200 through the API gateway regardless of the CRM platform used by the terminal 100 (or through an interlocked application). In this case, the terminal 100 may access the CRM using access information (eg, including URL, ID, password, etc.).

In addition, the above leads information (or prospective customer list information/TM target list information) is DB information on customers, and is accumulated when a form based on unique information (for example, mobile phone number) is entered. It is in row units.

In addition, the sales process (opportunity) is a unit of sales and represents all details of sales for individual leads.

For example, for the 010-1234-5678 number, 5 opportunities are recorded, such as 1) phone call, 2) call but absent, 3) text message, 4) phone call first inbound, 5) text message for the last contract Can be.

In addition, the sales process may be divided into several categories (eg, text messages, telephone calls, face-to-face (meeting), missed calls, missed calls, paid prospects, paid conversions, rejections, etc.).

In this case, the lead and the sales process may have a 1:N relationship (where N is a natural number).

The orders information (or sales information) is finally converted to sales/order/orders through several sales processes for individual leads (including sales, orders, contracts, etc.) Represents.

The team information represents information for providing a collaboration tool (eg, including chat, bulletin board, etc.) for a team to which a salesperson belongs.

In addition, the analytics information represents information for providing statistical functions for sales (eg, total conversion, conversion by period, conversion rate, settlement amount, salary calculation, confirmation of commission contract information, etc.).

In addition, the sync information is always synchronized (or synchronized) with the server 200 through an API for sales management.

In other words, the information that can be viewed in the mobile app can be viewed (or checked) by accessing the web application (or website) at any time.

In addition, the server 200 provides (or performs) a function of filtering each component.

In addition, the server 200 provides (or performs) a function of specifically checking detailed information for an individual row.

In addition, the server 200 provides (or performs) a function of importing/exporting (Import/Export) in various data formats such as Excel, CSV, and JSON for column*row.

In addition, the server 200 provides (or performs) statistics, visualization functions, and the like.

That is, the server 200 may analyze and check (or grasp) the conversion rate, sales, etc. based on the auto call record related to the customer.

In addition, the server 200 is based on the collected auto-call record, among a plurality of contents stored in a plurality of content management servers (not shown), one or more additional information (or additional content) related to a customer corresponding to the auto call record. //Data), etc. are collected through crawling. In this case, the additional information includes text (or a post registered in the content management server), an image (for example, a form/format such as png, gif, jpg, etc.), a video (for example, asf, avi, mpeg, wmv, etc.). Type/format), upload date and time information of the additional information, link information on which the corresponding content is posted, link information of images/videos included in the additional information for providing thumbnail information, number of followers/subscribers of posting account ID , The number of likes/dislikes/shares of the additional information, the content of the posting comment of the additional information, and the posting hashtag related to the additional information for sorting the additional information.

In addition, the server 200 may perform preprocessing on the collected additional information. In this case, the pretreatment includes a cleaning process and the like. Here, the refining process (or de-noising process) may be a process of removing noise content (or noise data) corresponding to a preset noise from among the collected one or more contents.

In addition, the server 200 uses the collected additional information (or pre-processed additional information) and the collected auto call record to provide customized product information and/or customized service information specific to the customer to the corresponding customer. It may be recommended (or provided) to other terminals 300. At this time, the other terminal 300 may be in a state of consenting to use of customer information (or use of marketing information).

The customer management automation system 10 through an artificial intelligence-based auto call according to an embodiment of the present invention is controlled by the server 200, various information collected by the server 200, and the server 200 It may further include a database (not shown) for storing the result of the analysis performed, and an API gateway (not shown) for providing a connection function with the database.

In addition, the database stores (or manages) various information (or data) necessary to perform an outbound call function or an inbound call function under the control of the server 200.

In addition, the database is composed of sales-related programs such as SalesForce and HubSpot, DBMS (DataBase Management System) such as MySQL, Oracel, Postgresql, etc., Google's SpreadSheet, and MS Office's Excel.

In addition, the API gateway may be a database connector that interlocks with various platforms and makes a single API. At this time, for each platform, an API connector for connecting a database related to the platform may be configured.

That is, the API gateway connects heterogeneous databases through an open API that provides a number of platforms (not shown) to develop 3rd party applications.

In this way, the API gateway may be configured to be able to link not only with CRM operated and managed by the server 200 itself, but also with data such as SalesForce, HubSpot, Google Spreadsheet, and Excel used by many companies.

In addition, since all consistent (or the same) Restful API is provided through the API gateway, all platforms can be supported with a single mobile application code regardless of the platform.

In this way, the terminal performs an automated outbound call function according to the script and DB list provided from the server to collect the auto call record, and through the updated script and DB list based on the result of analyzing the collected auto call record. By performing an automated outbound call function, auto call records can be continuously collected, and information filtering and information extraction functions can be provided for the collected auto call records.

In addition, in this way, the terminal performs an automated outbound call function according to the script and DB list provided from the server to collect the auto call record, and the updated script and DB list based on the result of analyzing the collected auto call record. Through the automated outbound call function, auto call records can be collected.

In addition, in this way, the server interlocks with the cloud calling server to perform an automated outbound call function according to the script and DB list to collect auto call records.

Hereinafter, a method of automating customer management through an artificial intelligence-based auto call according to the present invention will be described in detail with reference to FIGS. 1 to 2.

2 is a flowchart illustrating a method for automating customer management through an artificial intelligence-based auto call according to an embodiment of the present invention.

First, the server 200 generates a plurality of scripts composed of a plurality of survey contents (or text/sentence) according to the purpose. At this time, each of the plurality of scripts is a state in which the plurality of questionnaire contents are combined in a different order, or each questionnaire content is created in a similar structure (for example, a state in which words, modifiers, etc. are used differently) (or Combined) state. In addition, the script is composed of a text type sales script, a questionnaire script, etc. according to the above purpose, and a plurality of survey contents (or sentences) are configured in individual modules.

In this way, the server 200 may generate the script by sequentially selecting the plurality of questionnaire content of the module unit as the plurality of questionnaire content is configured in a module unit, and the questionnaire content of the module unit The module can be duplicated, modified, or deleted.

In addition, the server 200 transmits the generated plurality of scripts and DB lists to the terminal 100. Here, the DB list may be leads information (or preliminary customer list information/TM target list information) that is DB information on a customer.

For example, the server 200 generates first to third scripts using the first to fifth questionnaire content according to the questionnaire script. At this time, the first script is composed of the first questionnaire content, the second questionnaire content, the third questionnaire content, the fourth questionnaire content, and the fifth questionnaire content in order, and the second script is the first It consists of a questionnaire content, the third questionnaire content, the second questionnaire content, the fourth questionnaire content, and the fifth questionnaire content in order, and the third script includes the first questionnaire content, the third questionnaire content, and the The fourth questionnaire content, the second questionnaire content, and the fifth questionnaire content may be in an order.

In addition, the server 200 transmits the generated first to third scripts and a first DB list including the first to 1000th customer contacts to the first terminal 100 (S210).

Thereafter, the terminal 100 receives a plurality of scripts, DB lists, etc. transmitted from the server 200.

In addition, the terminal 100 generates (or converts) the plurality of scripts in the form of the received text into a plurality of sound source files through a text to speech (TTS) function.

For example, the first terminal receives a first script to a third script, a first DB list, etc. transmitted from the server 200.

In addition, the first terminal generates a first sound source file by applying a text-to-speech function to the received first script, and applies a text-to-speech function to the received second script to generate a second sound source file. And generates a third sound source file by applying a text-to-speech function to the received third script (S220).

Thereafter, the terminal 100 uses another terminal (not shown) corresponding to a plurality of contacts corresponding to a preset ratio (for example, 30%) of the received DB list using the generated plurality of sound source files. It performs (or proceeds) the auto call (or outbound call/robo call/auto call/RPA(Robotic Process Automation)) function in sequence.

That is, the terminal 100 divides a plurality of contacts corresponding to a preset ratio among the received DB list according to the number of the generated plurality of sound source files, and divides the divided one or more contacts into the generated plurality of Each of the sound source files is assigned (or mapped/matched/set), and the auto-call function is sequentially performed with other terminals corresponding to one or more contacts for each of a plurality of sound source files.

In this way, the terminal 100 may distribute traffic to a plurality of contacts for a plurality of scripts each composed of a plurality of questionnaire contents or a plurality of similar questionnaire contents for an A/B test.

In addition, the terminal 100 generates (or collects) an auto call record with the other terminal according to the progress of the auto call, and stores (or manages) the generated auto call record. Here, the auto call record (or call record) is a script, a sound source file corresponding to the script, caller information, receiver information, call time, a recording file (or a recording file in the form of an audio/sound source), and a total call length (or total Call time), location information, and a memo (or a memo according to the user input) directly input by the user.

As an example, the first terminal stores first to 300 customer contacts corresponding to a preset ratio of 30% among 1000 customer contacts included in the received first DB list from the generated first sound source file to Divide by 100 according to the number of third sound source files (for example, 3), allocate the divided first to 100th customer contacts to the first sound source file, and the divided 101st customer contact to The 200th customer contact information is allocated to the second sound source file, and the divided 201th customer contact information to the 300th customer contact information is allocated to the third sound source file. In addition, the first terminal performs an auto call function with a customer terminal corresponding to each of the first customer contact to the 100th customer contact by using the first sound source file, and the 101st terminal using the second sound source file Perform an auto call function with a customer terminal corresponding to each of the customer contact information to the 200th customer contact information, and a customer terminal and an auto call function respectively corresponding to the 201 customer contact information to the 300th customer contact information using the third sound source file. Perform.

In addition, the first terminal generates a first auto call record to a 300th auto call record according to the execution of an auto call function with a plurality of customer terminals respectively corresponding to the first to 300 customer contacts (S230) .

Thereafter, the terminal 100 responds to the plurality of questionnaire contents or the plurality of scripts composed of the plurality of similar questionnaire contents, based on a number of auto-call records, which is a result of distributing traffic to a plurality of contacts. A/B test is performed according to various preset indicators including conversion rate, questionnaire content (or module), time zone, and sound source gender.

As an example, the first terminal records a first autocall record to a 100th autocall record related to the first sound source file, a 101th autocall record to a 200th autocall record related to the second sound source file, and the third sound source file. An A/B test is performed according to an indicator including an answer conversion rate, a sales conversion rate, and the like by analyzing the 201th to 300th autocall records related to the file (S240).

Thereafter, in order to optimize the sound source file (or script) based on the results of the A/B test, the terminal 100 may select A/B from among the plurality of survey content or a plurality of sound source files composed of the plurality of similar survey content. As a result of performing the test, the remaining contacts (or at least one remaining contact excluding a plurality of contacts corresponding to the above ratio in the traffic/DB list) are driven into one of the most efficient sound source files to perform the auto call function.

That is, the terminal 100 collects (or accumulates) auto call records (or conversion data) for some of the contacts included in the DB list based on the A/B test result, and then collected. Based on the auto call record (or conversion data/A/B test result), it is possible to perform the auto call function for the remaining contacts by optimizing the sound source file with the best efficiency. At this time, the terminal 100 performs an auto call function again using the most efficient sound source file for the auto call proceeding with a sound source file other than the most efficient sound source file among the plurality of sound source files. You can also create (or collect) call records.

For example, the first terminal is based on the A/B test result, the number of calls of the first sound source file is 100, the number of calls is 10, the number of calls of the second sound source file is 100, and the number of calls is 15, and the third When the number of calls of the sound source file is 100 and the conversion is 9, the second sound source file with the highest conversion rate among the first to third sound source files and the remaining 301th to 1000th customer contacts included in the DB list The auto call function with the corresponding customer terminal is performed, and the 301th autocall record to the 1000th autocall record are respectively generated according to the autocall function execution (S250).

Thereafter, the terminal 100 records a plurality of auto-calls generated (or collected) according to auto-calls performed on a plurality of contacts included in the received DB list, and optimized sound source files (or optimized scripts) , And transmits identification information of the terminal 100 to the server 200. Here, the identification information of the terminal 100 includes MDN, mobile IP, mobile MAC, Sim (subscriber identification module) card unique information, serial number, and the like.

As an example, the first terminal records the first to 1000th autocall generated according to the autocall function performed for the first to 1000th customer contacts included in the first DB list, the optimization The second sound source file (or a second script corresponding to the second sound source file) and identification information of the first terminal are transmitted to the server 200 (S260).

Thereafter, the server 200 receives a plurality of auto call records, optimized sound source files (or optimized scripts), and identification information of the terminal 100 transmitted from the terminal 100.

In addition, the server 200 performs an information filtering function, an information extraction function, etc. for the plurality of auto call records according to an administrator input (or administrator selection/touch/control), and an information filtering function execution result, an information extraction function Output (or display) the execution result, etc.

For example, the server 200 performs recording of a first autocall to a 1000th autocall transmitted from the first terminal, the optimized second sound source file, and identification information of the first terminal.

In addition, the server 200 performs a function of filtering a record in which a call was made according to an administrator input for the received first auto call record to the 1000th auto call record, and the record in which the performed call was made is filtered. The result is displayed (S270).

As described above, the embodiment of the present invention collects auto call records by performing an automated outbound call function according to the script and DB list provided from the server in the terminal, and based on the result of analyzing the collected auto call records. Automatic outbound call function is performed through the updated script and DB list to continuously collect auto call records, and information filtering function and information extraction function are provided for the collected auto call records. By collecting additional information on customer information, the utilization of customer information is increased, repetitive tasks are automated using auto-call, and salespeople can focus on core tasks.

In addition, as described above, the embodiment of the present invention collects auto call records by performing an automated outbound call function according to the script and DB list provided from the server in the terminal, and analyzes the collected auto call records. Based on the updated script and DB list, the auto call record is collected by performing an automated outbound call function, and the auto call record is collected when the auto call record is collected using an optimized script among multiple scripts. And improve the work efficiency of customer information collection automation.

In addition, as described above, the embodiment of the present invention collects auto call records by performing an automated outbound call function according to a script and DB list by interworking with a cloud calling server in the server, You can use the auto call function even if you do not have.

The above contents may be modified and modified without departing from the essential characteristics of the present invention by those of ordinary skill in the technical field to which the present invention belongs. Accordingly, the embodiments disclosed in the present invention are not intended to limit the technical idea of the present invention, but to explain the technical idea, and the scope of the technical idea of the present invention is not limited by these embodiments. The scope of protection of the present invention should be interpreted by the following claims, and all technical ideas within the scope equivalent thereto should be interpreted as being included in the scope of the present invention.

10: Customer management automation system through artificial intelligence-based auto call
100: terminal 200: server

Claims (10)

A server for transmitting a plurality of scripts and DB lists; And
Each of the plurality of scripts is generated as a plurality of sound source files through the text-to-speech function, and corresponding to a plurality of contacts corresponding to a preset ratio among the DB list transmitted from the server using the generated plurality of sound source files. Performs an auto call function with other terminals, generates an auto call record with the other terminal according to the auto call progress, and sends traffic to a plurality of contacts for a plurality of scripts composed of a plurality of survey contents or a plurality of similar survey contents. Based on a number of auto-call records resulting from distributed processing, A/B tests are performed according to preset indicators including at least one of answer conversion rate, sales conversion rate, questionnaire content, time zone, and music source gender, and A/B tests are performed. In order to optimize the sound source file based on the result, one of the sound source files with the highest efficiency as a result of performing an A/B test among the plurality of sound source files composed of the plurality of survey contents or the plurality of similar survey contents, among the DB list Performs an auto-call function for at least one remaining contact, excluding the plurality of contacts, and records a plurality of auto-calls generated according to the auto-calls performed on a plurality of contacts included in the DB list, and an optimized sound source file And a terminal transmitting identification information of the terminal to the server,
The terminal,
Divide a plurality of contacts corresponding to a preset ratio among the DB list according to the number of the generated plurality of sound source files, and allocate the divided one or more contacts to the generated plurality of sound source files for traffic distribution processing And, performing an auto call function sequentially with other terminals corresponding to one or more contacts for each of a plurality of sound source files,
Regarding the auto-call progressed to a sound source file other than the most efficient sound source file among the plurality of sound source files, the auto call function is performed again using the most efficient sound source file to collect auto call records. Customer management automation system through artificial intelligence-based auto call. The method of claim 1,
Each of the plurality of scripts,
A customer management automation system through artificial intelligence-based auto-call, characterized in that a plurality of survey contents are combined in a different order according to the purpose, or each survey contents are created in a similar structure. delete The method of claim 1,
The auto call record,
An artificial intelligence base comprising at least one of a script, a sound source file corresponding to the script, caller information, callee information, call time, recording file, total call length, location information, and a memo manually entered by the user. Customer management automation system through auto call The method of claim 1,
The server,
Receiving the plurality of auto-call records, optimized sound source files, and identification information of the terminal transmitted from the terminal, and performing at least one of an information filtering function and an information extraction function for the plurality of auto-call records according to a manager input And outputting at least one of a result of performing an information filtering function and a result of performing an information extraction function. A customer management automation system through an artificial intelligence-based auto call. The method of claim 1,
Interworking with the server, receiving a cloud phone line from the server in units of call or time, and performing an auto call function using the plurality of scripts and the DB list provided from the server even if they do not have their own terminal. Customer management automation system through artificial intelligence-based auto call, characterized in that it further comprises a client to perform. Generating, by the terminal, a plurality of scripts transmitted from the server into a plurality of sound source files through a text-to-speech function;
Performing, by the terminal, an auto call function with other terminals corresponding to a plurality of contacts corresponding to a preset ratio among the DB list transmitted from the server by using the generated plurality of sound source files;
Generating, by the terminal, an auto call record with the other terminal according to the progress of the auto call;
By the terminal, response conversion rate, sales conversion rate, questionnaire content, based on a plurality of auto call records resulting from distributing traffic to a plurality of contacts for a plurality of scripts consisting of a plurality of survey contents or a plurality of similar survey contents, Performing an A/B test according to a preset indicator including at least one of a time zone and a sound source gender;
In order to optimize the sound source file based on the result of the A/B test performed by the terminal, the A/B test result is the most efficient among the plurality of sound source files composed of the plurality of questionnaire content or the plurality of similar questionnaire content. Performing an auto-call function for at least one remaining contact information excluding the plurality of contact information from the DB list with any one sound source file; And
Transmitting, by the terminal, a plurality of auto-call records, optimized sound source files, and identification information of the terminal, generated according to an auto-call performed on a plurality of contacts included in the DB list, to the server,
The step of performing an auto call function with other terminals corresponding to the plurality of contacts,
Dividing a plurality of contacts corresponding to a preset ratio among the DB list according to the number of the generated plurality of sound source files;
Allocating the divided one or more contacts to the plurality of generated sound source files for traffic distribution processing; And
Including a process of sequentially performing an auto call function with other terminals corresponding to one or more contacts for each of a plurality of sound source files,
The step of performing an auto-call function for at least one remaining contact information excluding the plurality of contacts from the DB list with any one sound source file having the best efficiency as a result of the A/B test,
Regarding the auto-call progressed to a sound source file other than the most efficient sound source file among the plurality of sound source files, the auto call function is performed again using the most efficient sound source file to collect auto call records. How to automate customer management through artificial intelligence-based auto-call. delete The method of claim 7,
Receiving, by the server, the plurality of auto call records, optimized sound source files, and identification information of the terminal transmitted from the terminal;
Performing, by the server, at least one of an information filtering function and an information extraction function for the plurality of auto call records according to an administrator input; And
And outputting at least one of a result of performing an information filtering function and a result of performing an information extraction function, by the server, by the server. The method of claim 7,
Providing, by the server, a cloud telephone line to the client in units of calls or hours in connection with the client; And
By the client, even if it does not have its own terminal, further comprising the step of performing an auto call function using the plurality of scripts and the DB list provided from the server. How to automate customer management through

Images