WO2022103068A1 - Procédé et dispositif de création de profil de client à base de dialogue en ligne par l'intermédiaire de multiples représentants - Google Patents

Procédé et dispositif de création de profil de client à base de dialogue en ligne par l'intermédiaire de multiples représentants Download PDF

Info

Publication number
WO2022103068A1
WO2022103068A1 PCT/KR2021/015899 KR2021015899W WO2022103068A1 WO 2022103068 A1 WO2022103068 A1 WO 2022103068A1 KR 2021015899 W KR2021015899 W KR 2021015899W WO 2022103068 A1 WO2022103068 A1 WO 2022103068A1
Authority
WO
WIPO (PCT)
Prior art keywords
customer profile
profile
customer
information
domain
Prior art date
Application number
PCT/KR2021/015899
Other languages
English (en)
Korean (ko)
Inventor
정진모
김정준
곽태호
이준섭
박주영
이태춘
박상훈
Original Assignee
주식회사 엔터프라이즈블록체인
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 주식회사 엔터프라이즈블록체인 filed Critical 주식회사 엔터프라이즈블록체인
Publication of WO2022103068A1 publication Critical patent/WO2022103068A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0281—Customer communication at a business location, e.g. providing product or service information, consulting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/30—Semantic analysis
    • G06F40/35—Discourse or dialogue representation

Definitions

  • the present disclosure relates to a method and apparatus for generating a chat-based customer profile, and more particularly, to a method and apparatus for creating a customer profile so that the customer does not re-query the contents previously queried even when chatting through several agents. it's about
  • High-involvement products refer to products that require a lot of prior knowledge or help in decision-making to purchase goods/services.
  • the high-involvement product may be a high-priced product such as financial products, insurance, used cars, and furniture.
  • consumers spend a lot of time and effort to actively search for information and go through a careful decision-making process before purchasing, so they usually purchase face-to-face. proportion is increasing.
  • customers can usually consult with a professional counselor in advance and be connected with a salesperson who concludes a contract for the case.
  • a salesperson who concludes a final contract is connected with a customer through this multi-channel consultation, the customer may experience an unnecessary process of having to deliver the questions/answered information to the salesperson back to the salesperson.
  • multiple counselors may repeatedly ask questions to the customer.
  • An object of the present disclosure is to solve a problem in which, when a user conducts multiple consultations with multiple counselors, multiple counselors repeatedly inquire to customers in order to complete a customer profile.
  • a chat-based customer profile creation method through a plurality of agents, provided by the customer profile creation system.
  • the method of the present disclosure includes generating a profile template database by changing to a general information domain based on customer information required for a product or service; receiving, from the user terminal, at least one first message of a user through a first chat room with a first counselor; extracting first intention data of the corresponding user by analyzing the at least one first message, respectively; generating a first customer profile by matching the first intent data and profile template data; receiving, from the user terminal, at least one second message of the user through a second chat room with a second counselor; extracting corresponding user's second intention data by analyzing the at least one second message, respectively; generating a second customer profile by matching the second intent data and profile template data; and generating a fused customer profile based on the first customer profile and the second customer profile.
  • the method may include encrypting the first customer profile, and using the encrypted information of the second counselor as an encryption key value.
  • the generating a profile template database by changing to a general information domain based on customer information required for a product or service includes: receiving the product or service attribute information; converting the attribute information into a general information domain by natural language processing; and generating a profile template by converting the general information domain into data.
  • the step of receiving the product or service attribute information includes receiving essential information about the product or service explicitly input by the person in charge of the product or service or through chatting in relation to the product or service. It may be essential information calculated based on one piece of information.
  • the step of extracting the corresponding user's first intention data by analyzing each of the at least one first message extracts the user's first intention data based on a natural language processing technique
  • the first intention data may include explicitly input information—the explicitly input information includes a name, age, and address—or implicit information.
  • the step of extracting the user's first intention data based on the natural language processing technique may analyze a user intent to generate a conversation flow and extract data related to the user intent.
  • the generating of the first customer profile by matching the first intention data and the profile template data may include: storing words for each domain; extracting intention words by analyzing the customer intention; measuring a distance between the intention word and a domain word of the profile template; estimating the customer profile domain using the intent word based on the distance value between the intent word and the domain word of the profile Teflin; and generating a customer profile using the intention word selected based on the distance value between the intention word and the domain word of the profile Teflin.
  • the step of generating a fusion customer profile based on the first customer profile and the second customer profile includes generating the first customer profile and the first customer profile based on the customer profile template. and determining whether the domain of the first customer profile and the domain of the second customer profile are similar, and when the domains are similar, generating a fusion customer profile by linking domain information.
  • a computer-readable recording medium including one or more instructions, the one or more instructions, when executed for a computer, can cause the computer to perform any one of the methods described above.
  • a customer profile generating system configured to provide a chat-based customer profile generating service through a plurality of agents.
  • the disclosed system includes a communication module; database; and a customer profile generating module, wherein the communication module is configured to: at least one first message of the user from the user terminal through a first chat room with a first counselor and at least one of the user through a second chat room with a second counselor is configured to receive a second message of, the database is configured to change to a general information domain based on required customer information for a product or service to store a profile template, and the customer profile creation module generates at least one first message, respectively The first intention data of the corresponding user is analyzed and extracted to match the first intention data and profile template data to generate a first customer profile, and the at least one second message is analyzed and the corresponding user's extracting second intent data to create a second customer profile by matching the second intent data and profile template data; and generating a fused customer profile based on the first customer profile and the
  • the customer profile generating module may be further configured to encrypt the first customer profile and the information of the second counselor with an encryption key value.
  • the database may be configured to receive the product or service attribute information, convert the attribute information into a general information domain by natural language processing, and convert the general information domain into data to generate a profile template.
  • the product or service attribute information is based on essential information about a product/service explicitly input by the person in charge of the product or service or information received through chatting in relation to the product or service It may be required information calculated as .
  • the customer profile generating module is configured to extract first intention data of the user based on a natural language processing technique, and the first intention data is information explicitly input - the explicit
  • the information entered as a name, age, and address may include - or implicit information.
  • the customer profile generation module may be configured to analyze a user intent to generate a conversation flow and to extract data related to the user intent.
  • the customer profile generating module stores words for each domain, analyzes the customer intention, extracts the intention word, measures the distance between the intention word and the domain word of the profile template, and the intention
  • the customer profile domain is estimated using the intent word based on the distance value between the word and the domain word of the profile Teflin, and a customer profile using the intent word selected based on the distance value between the intent word and the domain word of the profile Teflin.
  • FIG. 1 is a diagram schematically illustrating a customer profile generation system environment 100 capable of generating a chat-based customer profile according to an embodiment of the present disclosure.
  • FIG. 2 is a functional block diagram schematically illustrating a functional configuration of the profile generating server shown in FIG. 1 according to an embodiment of the present disclosure.
  • FIG. 3 is an operation flowchart illustrating a process of dataizing a profile template based on product/service attributes according to an embodiment of the present disclosure.
  • FIG. 4 is an operation flowchart illustrating a process of analyzing customer intention according to an embodiment of the present disclosure.
  • FIG. 5 is an operation flowchart illustrating a process of generating a customer profile according to an embodiment of the present disclosure.
  • FIG. 6 is an operation flowchart illustrating a process of generating a fusion customer profile according to an embodiment of the present disclosure.
  • a 'module' or 'unit' means a functional part that performs at least one function or operation, and may be implemented as hardware or software, or a combination of hardware and software.
  • the plurality of 'modules' or 'units' may be integrated into at least one software module and implemented by at least one processor, except for 'modules' or 'units' that need to be implemented with specific hardware. there is.
  • the customer profile generation system environment 100 includes a user terminal 110 , agent terminals 120a and 120b , a communication network 130 , and a service server 140 .
  • the user terminal 110 may be any user electronic device having a wired or wireless communication function. It should be noted that each of the user terminals 110 may be, for example, various wired or wireless communication terminals including a smart phone, a tablet PC, a desktop, a laptop, a PDA, a digital TV, and the like, and is not limited to a specific form. In this drawing, only one user terminal is shown, but the present disclosure is not limited thereto. It should be noted that, according to another embodiment of the present disclosure, the system environment 100 may include a greater number of various types of user terminals. According to an embodiment of the present disclosure, the user may conduct a consultation with the counselor terminals 120a and 120b through the server 140 using the user terminal 110 . In an embodiment, the user may conduct a chat-based consultation with the counselor terminals 120a and 120b through the server 140 using the user terminal 110 .
  • the user terminal 110 may communicate with the counselor terminals 120a and 120b, ie, transmit/receive necessary information, through the communication network 130 .
  • the user terminal 110 may receive various types of user inputs such as voice and/or text input, image and/or video input, touch input, and other various control inputs from the outside.
  • various types of user inputs received on the user terminal 110 may be transmitted to the server 140 through the communication network 130 .
  • the user terminal 110 may receive various signals transmitted from the outside (eg, the server 140 ) through the communication network 130 .
  • each of the user terminals 110 through the communication network 130 and the server 140, one or a plurality of conversation sessions provided by one or a plurality of agent terminals (120a, 120b)
  • a real-time chat may be exchanged with one or a plurality of agent terminals 120a and 120b through the established chat session.
  • the counselor terminals 120a and 120b may be any user electronic devices having a wired or wireless communication function. It should be noted that each of the agent terminals 120a and 120b may be various wired or wireless communication terminals including, for example, a smart phone, a tablet PC, a desktop, a laptop, a PDA, a digital TV, and the like, and is not limited to a specific form. In this drawing, only two agent terminals are shown, but the present disclosure is not limited thereto. It should be noted that, according to another embodiment of the present disclosure, the system environment 100 may include a larger number of various types of agent terminals. According to an embodiment of the present disclosure, the counselor may conduct chat-based counseling with the user terminal 110 through the server 140 using the counselor terminals 120a and 120b.
  • the counselor terminals 120a and 120b may communicate with the user terminal 110 through the communication network 130 , ie, transmit/receive necessary information.
  • the agent terminals 120a and 120b receive various types of input from the agent, such as voice and/or text input, image and/or video input, touch input, and other various control inputs from the outside. can do.
  • various types of user inputs received on the counselor terminals 120a and 120b may be transmitted to the server 140 through the communication network 130 .
  • the agent terminals 120a and 120b may receive various signals transmitted from the outside (eg, the server 140 ) through the communication network 130 .
  • each of the agent terminals 120a and 120b may exchange a real-time conversation with one or a plurality of user terminals 110 through the communication network 130 and the server 140 .
  • the communication network 130 may include any wired or wireless communication network, for example, a TCP/IP communication network.
  • the communication network 130 may include, for example, a Wi-Fi network, a LAN network, a WAN network, an Internet network, and the like, and the present disclosure is not limited thereto.
  • the communication network 130 is, for example, Ethernet, GSM, EDGE (Enhanced Data GSM Environment), CDMA, TDMA, OFDM, OFDMA, Bluetooth, VoIP, Wi-MAX, Wibro, and any other various wired lines. Alternatively, it may be implemented using a wireless communication protocol.
  • the service server 140 may communicate with the user terminal 110 through the communication network 130 .
  • the service server 140 for example, according to a request received from the user terminal 110 through the communication network 130, the corresponding user terminal 110 and one or a plurality of other agent terminals ( A conversation session may be established between 120a and 120b), and a real-time conversation may proceed between terminals participating in the corresponding conversation session.
  • the service server 140 may analyze the intention of the customer based on the contents of conversations between the counselor and the customer, and may store and manage characteristic data for each user account.
  • the service server 140 may generate a customer profile template.
  • the customer profile template may be a general domainized data form based on customer information required for a product/service created by a product/service person in charge.
  • the service server 140 may fuse the customer profile information generated in the consultation process with the customer profile information received in the previous consultation step into one customer profile.
  • the service server 140 may encrypt the customer profile generated through the conversation.
  • the user profile generation server 140 includes a profile template generation unit 210 , a customer intent analysis unit 220 , a customer profile generation unit 230 , a customer profile fusion unit 240 , and a processing unit (encryption unit). ) 250 , a communication unit 260 and a storage unit 270 .
  • the customer profile template generating unit 210 may convert the information into a general information domain based on necessary customer information for a product/service created by a product/service person in charge and convert it into data.
  • the transformation to the general information domain may use natural language processing techniques.
  • the customer intention analysis unit 220 may extract the customer's intention based on the contents of the conversation between the counselor and the customer.
  • the process of extracting the customer's intention may select one of general natural language processing methods, and as a result, the customer's intention may be extracted as a word.
  • the customer's intention may include, for example, explicitly input information (age, name, address, etc.) and information displayed in a detour (desiring a product less than 300,000 won).
  • the customer profile generator 230 may match the customer intention data analyzed by the above-described customer intention analysis unit 220 with the profile template.
  • the matching of the customer's intention data with the profile template uses a conventional natural language processing technique, for example, word to vector (Word to Vec), etc., based on the distance between each piece of information.
  • Profiles can be created by mapping with template data.
  • the profile fusion unit 240 may fuse the customer profile information generated in the consultation process with the customer profile information received in the previous consultation step into one customer profile.
  • each profile information can also be integrated based on the customer profile template.
  • the same domain information (counseling information No. 1: Seoul residence, Counseling information No. 2: residence in one room) may be linked and generated.
  • the processing unit 250 may perform various operations while communicating with each component of the server 140 . According to an embodiment of the present disclosure, the processing unit 250 may drive and execute various application programs on the storage unit 270 . According to an embodiment of the present disclosure, if necessary, the processing unit 250 may receive signals and perform appropriate processing on these signals. According to an embodiment of the present disclosure, the processing unit 250 may perform appropriate processing on a signal received from the outside through the communication unit 260 if necessary.
  • the processing unit 250 may encrypt the customer profile generated through the conversation. According to an embodiment, the processing unit 250 may encrypt the customer profile using the information of the salesperson who will conduct the next consultation as a key, and transmit it to the next consultation agent (salesperson). According to an embodiment, the corresponding customer profile information may be decrypted by inputting its own information (encryption key) in the next counselor terminal 120b.
  • the communication unit 260 enables the server 140 to communicate between the user terminal 110 and the counselor terminal 120 through the communication network 130 of FIG. 1 .
  • the communication unit 260 may transmit, for example, an acquired signal to the user terminal 110 and the counselor terminal 120 through the communication network 130 according to a predetermined protocol.
  • the communication unit 260 may include, for example, various signals received from the user terminal 110 and the agent terminal 120 through the communication network 130 , for example, a user message in the form of voice and/or text, or It is possible to receive various control signals and the like, and perform appropriate processing according to a predetermined protocol.
  • the storage unit 270 may be any storage medium in which various programs that can be executed in the server 140, for example, various application programs and related data are stored.
  • the storage unit 270 includes various application programs including, for example, a messenger service providing application by communication with the user terminal 110 or the agent terminal 120, a camera application, a watch application, and the like. Data related to the execution of these programs may be stored.
  • the storage unit 270 may be configured to include various types of volatile or non-volatile memory, such as DRAM, SRAM, DDR RAM, ROM, magnetic disk, optical disk, and flash memory.
  • FIG. 3 is an operation flowchart illustrating a process of converting a profile template into data based on product/service attributes in the customer profile template generator shown in FIG. 2 according to an embodiment of the present disclosure.
  • the customer profile template generator 210 may extract a required customer profile template that is a target for a product/service.
  • the customer profile template generator 210 may receive attribute information of a product/service.
  • the product/service attribute information may be essential information about the product/service explicitly input by the person in charge of the product/service.
  • the attribute information of the product/service may be necessary information calculated based on information received through the user terminal 110 through chatting in relation to the product/service.
  • the customer profile template generator 210 may convert product/service attribute information into general domain information.
  • the conversion of attribute information of goods/services into general domain information may be performed through a natural language processing technique, and since those skilled in the art are well aware of various methods and modifications using the natural language processing technique, the detailed description will be Hereinafter, it will be omitted.
  • step S306 the customer profile template generator 210 may convert the profile template data into data based on the general domain information converted in step S304.
  • the customer profile template generator 210 may convert the information into a general information domain based on necessary customer information for a product/service created by a product/service person in charge and convert it into data.
  • the customer profile template generating unit 210 may create a database by changing the information to a general information domain based on necessary customer information for a product/service created by a product/service person in charge. there is.
  • the customer intention analysis unit 220 may extract the customer's intention based on the contents of the conversation between the counselor and the customer.
  • the process of extracting the customer's intention may select one of general natural language processing methods, and as a result, the customer's intention may be extracted as a word.
  • the customer's intention may include, for example, explicitly input information (age, name, address, etc.) and information displayed in a detour (desiring a product less than 300,000 won).
  • the customer intention analysis unit 220 may receive an input from the user terminal 110 .
  • the customer intention analysis unit 220 may analyze one or more user intents of the received text input based on a learning sentence unit (not shown) to be described later.
  • a user intent may be associated with a series of action(s) that may be understood and performed by the server 140 according to the user intent.
  • the customer intention analyzer 220 may refer to previously identified user intent information when matching the received text input to one or more user intents.
  • the learning sentence unit may include, for example, a predefined ontology model.
  • the ontology model may be expressed, for example, in a hierarchical structure between nodes, where each node is an "intent” node corresponding to the user's intent or a subordinate linked to an "intent” node. It can be one of the "properties” nodes (child “properties” nodes that are linked directly to the "Intent” node, or linked back to the "properties” node of the "Intent” node).
  • an “Intent” node and “attribute” nodes directly or indirectly linked to the “Intent” node may constitute one domain, and the ontology may be composed of a set of domains.
  • the learning sentence unit may be configured to include domains respectively corresponding to all intents.
  • the ontology model may be dynamically changed by adding or deleting nodes, or modifying a relationship between nodes.
  • the customer intention analysis unit 220 may generate a conversation flow by analyzing the user intent.
  • the customer intention analyzer 220 may generate a series of operation flows corresponding thereto according to the analyzed user intent.
  • the customer intention analysis unit 220 may extract data related to the user intent.
  • intent nodes and attribute nodes of each domain in the ontology model may be respectively associated with words and/or phrases related to user intents or attributes corresponding thereto.
  • the learning sentence unit can implement the ontology model in the form of, for example, a vocabulary dictionary (not specifically shown), consisting of nodes in a hierarchical structure and a set of words and/or phrases related to each node.
  • the customer intention analysis unit 220 may determine the user intent based on the ontology model implemented in the form of a vocabulary dictionary as described above.
  • the customer intention analysis unit 220 may determine which nodes in which domain in an ontology model each word in the sequence is associated with, and , a corresponding domain, ie, a user intent, may be determined based on such a determination to extract an intention word.
  • FIG. 5 is an operation flowchart illustrating a process of creating a customer profile by mapping customer intention data and a profile template in the customer profile generator shown in FIG. 2 according to an embodiment of the present disclosure.
  • the customer profile generator 230 may store words for each domain.
  • the customer profile generating unit 230 may receive the intention word extracted by the customer intention analyzing unit 220 .
  • the customer profile generator 230 may measure the distance between the received intention word and the domain word of the profile template.
  • the previously learned Word2Vec table may be used to measure the distance between the received intention word and the domain word of the profile template, but is not limited thereto.
  • the customer profile generator 230 may estimate the customer profile domain using the intention word based on the distance value between the intention word and the domain word of the profile Teflin.
  • the customer profile generator 230 may generate a customer profile using the intention word based on the distance value between the intention word and the domain word of the profile Teflin.
  • the customer profile generator 230 may generate a customer profile by mapping intention data with template data to an area having the shortest distance between pieces of information.
  • FIG. 6 is an operation flowchart illustrating a process of generating a fusion customer profile according to an embodiment of the present disclosure.
  • the customer profile information generated in the first consultation process may be received, and the customer profile information generated in the second consultation step may be fused into one customer profile.
  • Profile information generated in each consultation step may be structured data based on the initial customer profile template. Accordingly, each customer v-profile information generated as a result of each consultation can also be fused based on the customer profile template.
  • a first customer profile may be generated based on the customer profile template.
  • a first customer profile may be generated based on the customer profile template.
  • step S606 it is determined whether the domain of the first customer profile and the domain of the second customer profile are similar, and if the domains are identical or similar, the fusion customer profile can be created by linking with the same domain information. For example, if a customer profile resident in Seoul is created as a result of the first consultation, and a customer profile is created as a residence in one room as a result of the second consultation, the customer profile information will be generated by setting the profile domain as “residence” to (Seoul, one-room).
  • a computer program includes a storage medium readable by a computer processor or the like, such as EPROM, EEPROM, nonvolatile memory such as a flash memory device, a magnetic disk such as an internal hard disk and a removable disk, a magneto-optical disk, and It may be implemented in a form stored in various types of storage media including a CDROM disk and the like.
  • the program code(s) may be implemented in assembly language or machine language. All modifications and variations falling within the true spirit and scope of the present disclosure are intended to be embraced by the following claims.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • General Engineering & Computer Science (AREA)
  • Finance (AREA)
  • Development Economics (AREA)
  • Accounting & Taxation (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Artificial Intelligence (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Health & Medical Sciences (AREA)
  • Game Theory and Decision Science (AREA)
  • Data Mining & Analysis (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Information Transfer Between Computers (AREA)

Abstract

Est divulgué ici un procédé de création de profil de client à base de dialogue en ligne par l'intermédiaire de multiples représentants, lequel procédé est fourni par un système de création de profil de client. Le procédé de la présente divulgation comprend les étapes consistant à : créer une base de données de modèles de profil en passant à un domaine d'informations général sur la base d'informations de client requises pour un produit ou un service ; recevoir, en provenance d'un terminal utilisateur, au moins un premier message d'un utilisateur par l'intermédiaire d'un premier salon de dialogue en ligne avec un premier représentant ; extraire des premières données d'intention de l'utilisateur correspondant par analyse de chacun du ou des premiers messages ; créer un premier profil de client par mise en correspondance des premières données d'intention avec des données de modèle de profil ; recevoir, en provenance du terminal utilisateur, au moins un second message de l'utilisateur par l'intermédiaire d'un second salon de dialogue en ligne avec un second représentant ; extraire des secondes données d'intention de l'utilisateur correspondant par analyse de chacun du ou des seconds messages ; créer un second profil de client par mise en correspondance des secondes données d'intention avec les données de modèle de profil ; et créer un profil de client de fusion sur la base du premier profil de client et du second profil de client.
PCT/KR2021/015899 2020-11-16 2021-11-04 Procédé et dispositif de création de profil de client à base de dialogue en ligne par l'intermédiaire de multiples représentants WO2022103068A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
KR10-2020-0152531 2020-11-16
KR1020200152531A KR102274335B1 (ko) 2020-11-16 2020-11-16 복수의 상담원을 통한 채팅기반 고객 프로파일 생성 방법 및 장치

Publications (1)

Publication Number Publication Date
WO2022103068A1 true WO2022103068A1 (fr) 2022-05-19

Family

ID=76861896

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/KR2021/015899 WO2022103068A1 (fr) 2020-11-16 2021-11-04 Procédé et dispositif de création de profil de client à base de dialogue en ligne par l'intermédiaire de multiples représentants

Country Status (2)

Country Link
KR (1) KR102274335B1 (fr)
WO (1) WO2022103068A1 (fr)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR102274335B1 (ko) * 2020-11-16 2021-07-07 한화생명보험(주) 복수의 상담원을 통한 채팅기반 고객 프로파일 생성 방법 및 장치

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20100128068A (ko) * 2009-05-27 2010-12-07 포항공과대학교 산학협력단 음성 대화 의미처리를 통한 사용자 프로파일 자동 구성 방법 및 장치, 및 그에 따른 콘텐츠 추천 방법 및 장치
KR20180022762A (ko) * 2018-02-26 2018-03-06 오영재 실시간 답변 메시지 생성을 이용한 고객 상담 서비스 제공 방법, 시스템 및 컴퓨터 판독 가능한 기록 매체
KR20180118669A (ko) * 2016-02-10 2018-10-31 니틴 바츠 디지털 커뮤니케이션 네트워크에 기반한 지능형 채팅
KR20190029509A (ko) * 2016-06-13 2019-03-20 푸쉬 인코포레이티드 사용자 프로필에 사용자 정보를 안전하게 저장하기 위한 시스템 및 방법
KR102119404B1 (ko) * 2018-11-28 2020-06-05 주식회사 와이즈넛 복수 챗봇의 협업에 의한 대화형 정보제공 시스템 및 그 방법
KR102274335B1 (ko) * 2020-11-16 2021-07-07 한화생명보험(주) 복수의 상담원을 통한 채팅기반 고객 프로파일 생성 방법 및 장치

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20100128068A (ko) * 2009-05-27 2010-12-07 포항공과대학교 산학협력단 음성 대화 의미처리를 통한 사용자 프로파일 자동 구성 방법 및 장치, 및 그에 따른 콘텐츠 추천 방법 및 장치
KR20180118669A (ko) * 2016-02-10 2018-10-31 니틴 바츠 디지털 커뮤니케이션 네트워크에 기반한 지능형 채팅
KR20190029509A (ko) * 2016-06-13 2019-03-20 푸쉬 인코포레이티드 사용자 프로필에 사용자 정보를 안전하게 저장하기 위한 시스템 및 방법
KR20180022762A (ko) * 2018-02-26 2018-03-06 오영재 실시간 답변 메시지 생성을 이용한 고객 상담 서비스 제공 방법, 시스템 및 컴퓨터 판독 가능한 기록 매체
KR102119404B1 (ko) * 2018-11-28 2020-06-05 주식회사 와이즈넛 복수 챗봇의 협업에 의한 대화형 정보제공 시스템 및 그 방법
KR102274335B1 (ko) * 2020-11-16 2021-07-07 한화생명보험(주) 복수의 상담원을 통한 채팅기반 고객 프로파일 생성 방법 및 장치

Also Published As

Publication number Publication date
KR102274335B1 (ko) 2021-07-07

Similar Documents

Publication Publication Date Title
JP6718828B2 (ja) 情報入力方法および装置
WO2018030672A1 (fr) Procédé et système de consultation d'automatisation de robot pour la consultation avec un client selon un scénario prédéterminé en utilisant un apprentissage automatique
US9015033B2 (en) Method and apparatus for detecting a sentiment of short messages
CN104735480B (zh) 移动终端与电视之间的信息发送方法及系统
US9881011B2 (en) System and method for generating user profiles for human resources
KR101990895B1 (ko) 온라인 게시물 및 댓글 자동 응답용 인공지능 대화형 댓글 제공 시스템
KR20170140877A (ko) 전문가 매칭 시스템을 이용하는 온라인 플랫폼 시스템.
US11282507B1 (en) Contemporaneous machine-learning analysis of audio streams
WO2021010744A1 (fr) Procédé et dispositif d'analyse d'une conversation de vente sur la base de reconnaissance vocale
KR20190058066A (ko) 상담데이터 관리 방법 및 장치
US11050884B2 (en) Intent-driven contact center
WO2022103068A1 (fr) Procédé et dispositif de création de profil de client à base de dialogue en ligne par l'intermédiaire de multiples représentants
CN113076423A (zh) 数据处理方法及装置、数据查询方法及装置
US20240143930A1 (en) Distributed Computing Architecture For Intent Matching
US20190012313A1 (en) Speech converter
WO2015102125A1 (fr) Système et procédé de conversation de texto
JP2004341672A (ja) 情報提示方法及び情報提示装置
WO2021005648A1 (fr) Dispositif, système, procédé et programme de recommandation d'informations
WO2022255850A1 (fr) Système de dialogue en ligne et procédé de fourniture en mesure de prendre en charge une traduction multilingue
US11869511B2 (en) Using speech mannerisms to validate an integrity of a conference participant
JP6913995B1 (ja) 情報処理システム、情報処理方法及びプログラム
CN114943590A (zh) 基于双塔模型的对象推荐方法及装置
CN107316644A (zh) 用于信息交互的方法及装置
TW201306536A (zh) 應用於網路協定語音之多國語音辨識及翻譯幕顯像系統
CN112632241A (zh) 智能会话的方法、装置、设备和计算机可读介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21892236

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 24/10/2023)

122 Ep: pct application non-entry in european phase

Ref document number: 21892236

Country of ref document: EP

Kind code of ref document: A1