[go: up one dir, main page]
More Web Proxy on the site http://driver.im/

CN113434645A - Financial product intelligence customer service system - Google Patents

Financial product intelligence customer service system Download PDF

Info

Publication number
CN113434645A
CN113434645A CN202110577859.9A CN202110577859A CN113434645A CN 113434645 A CN113434645 A CN 113434645A CN 202110577859 A CN202110577859 A CN 202110577859A CN 113434645 A CN113434645 A CN 113434645A
Authority
CN
China
Prior art keywords
financial
customer service
intelligent
knowledge map
intelligent customer
Prior art date
Legal status (The legal status 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 status listed.)
Pending
Application number
CN202110577859.9A
Other languages
Chinese (zh)
Inventor
孙琪
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai Shengtong Information Technology Co ltd
Original Assignee
Shanghai Shengtong Information Technology Co ltd
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 Shanghai Shengtong Information Technology Co ltd filed Critical Shanghai Shengtong Information Technology Co ltd
Priority to CN202110577859.9A priority Critical patent/CN113434645A/en
Publication of CN113434645A publication Critical patent/CN113434645A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33Querying
    • G06F16/332Query formulation
    • G06F16/3329Natural language query formulation or dialogue systems
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33Querying
    • G06F16/3331Query processing
    • G06F16/334Query execution
    • G06F16/3344Query execution using natural language analysis
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/36Creation of semantic tools, e.g. ontology or thesauri
    • G06F16/367Ontology
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00Handling natural language data
    • G06F40/30Semantic analysis
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q30/00Commerce
    • G06Q30/01Customer relationship services
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q40/00Finance; Insurance; Tax strategies; Processing of corporate or income taxes

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Computational Linguistics (AREA)
  • Business, Economics & Management (AREA)
  • Artificial Intelligence (AREA)
  • Databases & Information Systems (AREA)
  • Data Mining & Analysis (AREA)
  • General Business, Economics & Management (AREA)
  • Strategic Management (AREA)
  • Accounting & Taxation (AREA)
  • Mathematical Physics (AREA)
  • Marketing (AREA)
  • Finance (AREA)
  • Economics (AREA)
  • Development Economics (AREA)
  • Technology Law (AREA)
  • Animal Behavior & Ethology (AREA)
  • Human Computer Interaction (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • General Health & Medical Sciences (AREA)
  • Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)

Abstract

The invention relates to an intelligent customer service system for financial products, which is used for promoting the innovation of financial services and improving the operation efficiency. An intelligent customer service system for financial products comprises functional modules of a financial knowledge map, intelligent question answering, semantic understanding work of the system, information extraction, information retrieval and the like. Firstly, a financial knowledge map is established, which mainly comprises a financial knowledge corpus and a user inquiry data set, and is constructed by experts and scholars in the field, wherein the content of the financial knowledge map comprises question and answer information required by customer service, a plurality of preprocessed customer service historical chat sentences, a plurality of financial data and internal relations among the financial data and the customer service historical chat sentences. Secondly, the corresponding business module is identified and matched by the linguistic data asked by the user, and then retrieval analysis is carried out. Compared with the prior art, the method and the system have the advantages that the intelligent customer service is used for shunting part of the artificial telephone traffic, multi-line question answering and 24-hour uninterrupted service are supported, the accuracy, efficiency and user experience of the system can be effectively improved, and the intelligence and high efficiency degree of various products in the financial industry are improved.

Description

Financial product intelligence customer service system
Technical Field
The invention relates to an intelligent customer service system, in particular to an intelligent customer service system for financial products.
Background
In recent years, with the rapid development of technologies such as big data and artificial intelligence, various industries are undergoing major changes. Among them, the financial field, as one of the most important forces in innovation and reform, puts higher demands and expectations on intelligence and efficiency. Meanwhile, with the continuous development of social economy, the living standard of people is gradually improved, and people have greater demands on products or services in a plurality of financial fields, so that an intelligent customer service system is provided for better reducing labor cost and improving operation efficiency.
An important link in the intelligent customer service system is an intelligent question-and-answer functional module, which extracts feature information through semantic understanding analysis based on the processing result of user query, finds answers in a corpus and returns the answers to the user. In the prior art, an intelligent customer service system mainly performs similarity matching through single sentences for extracting feature keywords and a corpus and obtains answers after retrieval and analysis, but because more and more services and services are provided for financial products at present, the single matching cannot meet the requirement of accuracy, and the matched result is probably not the result required by a user. And as the number of users and services is continuously increased, the traditional intelligent customer service can only solve some simple problems, most users still need to rely on manual customer service, and thus queuing phenomenon is inevitably generated, and the experience of the users is reduced.
In view of the above problems, although intelligent customer service techniques for financial products have been performed well in practice, further improvements are still required.
Disclosure of Invention
In order to solve the problems, the invention relates to an intelligent customer service system of financial products, which is used for promoting the innovation of financial services and improving the operation efficiency. Compared with the prior art, the method and the system have the advantages that internal relation between financial knowledge and data can be mined by using the financial knowledge map, and the accuracy of the intelligent customer service system is improved. Meanwhile, the intelligent customer service can shunt partial artificial telephone traffic, give consideration to multi-line question answering and provide 24-hour uninterrupted service, and can effectively improve the efficiency and user experience of the system, thereby improving the intelligence and high efficiency degree of various products in the financial industry.
The purpose of the invention is realized by the following technical scheme: the invention comprises functional modules of financial knowledge mapping, intelligent question answering, system carrying semantic understanding work, information extraction, information retrieval and the like. Firstly, a financial knowledge map is established, which mainly comprises a financial knowledge corpus and a user inquiry data set, and is constructed by experts and scholars in the field, wherein the content of the financial knowledge map comprises question and answer information required by customer service, a plurality of preprocessed customer service historical chat sentences, a plurality of financial data and internal relations among the financial data and the customer service historical chat sentences. Secondly, the corresponding business module is identified and matched according to the intention of the linguistic data asked by the user, and then retrieval analysis is carried out.
The intelligent customer service system for financial products comprises a schematic diagram of functional modules.
As a preferable scheme of the invention, the financial knowledge graph is established on a knowledge system constructed by experts in the field, and the financial knowledge graph mainly comprises data acquisition and analysis, knowledge graph storage and the like.
As a preferred scheme of the present invention, the intelligent question-answering function module mainly processes a question of a user and answer results returned later. And processing the question of the user, sending the processing result to a system working module for receiving semantic understanding, and processing the answer result sent back and then sending the answer result to the user.
As a preferred scheme of the present invention, the system supporting semantic understanding work module is to perform semantic understanding on the processing result of the intelligent question and answer module, because the questions in the financial field can be matched and answered only by the keywords, but the logical analysis is performed through the semantic understanding of the context, and the analyzed result is sent to the information extraction module.
As a preferred scheme of the present invention, the information extraction module extracts effective information from the result of the analysis performed by the system supporting semantic understanding work module, identifies and matches the corresponding service type, and then sends the effective information and the corresponding service type to the information retrieval module.
As a preferred scheme of the present invention, the information retrieval module retrieves and compares the effective information sent by the information extraction module with respect to the corresponding service type and the content in the knowledge graph, and sends the result to the intelligent question-answering function module after finding the most correct answer, and the module sends the answer to the user.
Drawings
FIG. 1 is a functional block diagram of the present invention.
Detailed Description
The invention will be further described with reference to the accompanying figure 1: in order to make the objects, technical solutions and advantages of the present invention more comprehensible, the present invention is further described with reference to the following specific embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Furthermore, in the following detailed description of the present invention, certain specific details are set forth in order to provide a better understanding of the present invention. It will be fully understood by those skilled in the art that the invention may be practiced without these specific details.
This implementation example provides an intelligent customer service system for financial products: the current intelligent customer service system mainly carries out similarity matching through single sentences for extracting characteristic keywords and a corpus, and obtains answers after retrieval and analysis. And as the number of users and services is continuously increased, the traditional intelligent customer service can only solve some simple problems, most users still need to rely on manual customer service, and thus queuing phenomenon is inevitably generated, and the experience of the users is reduced.
The financial knowledge map is established on a knowledge system constructed by experts in the field, and mainly comprises data acquisition and analysis, knowledge map storage and the like. The intelligent question-answering function module is mainly used for processing the questions of the user and answer results returned later. And processing the question of the user, sending the processing result to a system working module for receiving semantic understanding, and processing the answer result sent back and then sending the answer result to the user. The system supporting semantic understanding work module is used for carrying out semantic understanding on the processing result of the intelligent question-answering module, and the problem in the financial field can be matched and answered only by the aid of keywords, logic analysis is carried out through context semantic understanding, and the analyzed result is sent to the information extraction module. The information extraction module extracts effective information from the result of the analysis of the system carried semantic understanding work module, identifies and matches the corresponding service type, and then sends the effective information to the information retrieval module. The information retrieval module retrieves and compares the effective information sent by the information extraction module aiming at the corresponding service type and the content in the knowledge graph, and sends the result to the intelligent question-answering function module after finding the most correct answer, and the module sends the answer to the user.
The financial knowledge map can mine the internal relation among knowledge under the background of financial knowledge, is enriched and perfected through a knowledge system constructed by experts and scholars in the financial field, can be collated according to historical sentences inquired by a user, and can be continuously updated and perfected along with the feedback of the user and the current financial situation in the using process.
The intelligent question-answering module mainly processes the questions of the users and returns the final result to the intelligent question-answering module, so that the intelligent question-answering module can process the questions of a plurality of users in a multi-line mode, meanwhile, uninterrupted service can be carried out for 24 hours, and the service efficiency is improved. The module sends the result processed by the user to the system semantic understanding work module or returns the final result to the user.
The system supporting semantic understanding work module is mainly used for carrying out semantic understanding on a processing result, although effective information in a sentence asked by a user can be successfully compared in a later link, the effective information may not be an answer required by the user, the problem in the financial field can be matched and answered only by keywords, logic analysis is carried out through context semantic understanding, the user semantic is deeply understood through analysis, and then the analyzed result is sent to the information extraction module.
The information extraction module extracts effective information from the result of the system carrying the semantic understanding work module, omits some information which is contained in the user's question and has no influence on the semantic understanding, compares the information with the business category in the financial knowledge map, identifies the corresponding business type, and sends the effective information and the corresponding business type to the information retrieval module.
The information retrieval module retrieves and compares the effective information and the corresponding service type sent by the information extraction module with the content under the corresponding service category in the knowledge graph, and sends the result to the intelligent question-answering function module after finding the most correct answer, and the module sends the answer to the user.
By adopting the technical scheme, the invention provides multi-line 24-hour intelligent question and answer service for users through the financial knowledge map, the intelligent question and answer, the system carrying semantic understanding work, the information extraction, the information retrieval and other functional modules, thereby reducing the pressure of manual service and the operation cost. And through the fusion of the financial knowledge map and the intelligent customer service, the advantages of the financial knowledge map and the intelligent customer service can be better played, the internal relation behind the information can be deeply mined, the accuracy and the reliability of the intelligent customer service system are improved, and the experience of a user is enhanced.
In summary, the above summary of the present invention and the technical solutions are further described in detail with reference to the specific embodiments, and it should not be construed that the specific embodiments of the present invention are limited to these descriptions. Modifications and equivalents of the disclosed embodiments, as well as improvements made to the techniques of the present invention, will be apparent to those skilled in the art, and are intended to be included within the scope of the present invention without departing from the spirit and principles of the invention.

Claims (3)

1. The invention relates to an intelligent customer service system of financial products, which aims to promote the innovation of financial services and improve the operation efficiency.
2. The intelligent customer service system of financial products as claimed in claim 1, comprising functional modules of financial knowledge map, intelligent question answering, system receiving semantic understanding, information extraction, information retrieval, etc., firstly establishing financial knowledge map, mainly comprising financial knowledge corpus and user inquiry data set, constructed by expert scholars in the field, the content of which has question answering information required for customer service, some preprocessed customer service historical chat sentences, some financial data and the internal relation between them, secondly identifying intention and matching corresponding business module by the corpus questioned by users, and then carrying out retrieval analysis.
3. The intelligent customer service system of financial products as claimed in claim 1, wherein a multi-line and 24-hour intelligent question-answering service is provided for users, the pressure of manual service and the operation cost are reduced, and through the fusion of the financial knowledge map and the intelligent customer service, the advantages of the financial knowledge map and the intelligent customer service can be better played, the internal relation behind information can be deeply mined, the accuracy and reliability of the intelligent customer service system are improved, and the experience of users is enhanced.
CN202110577859.9A 2021-05-26 2021-05-26 Financial product intelligence customer service system Pending CN113434645A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110577859.9A CN113434645A (en) 2021-05-26 2021-05-26 Financial product intelligence customer service system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110577859.9A CN113434645A (en) 2021-05-26 2021-05-26 Financial product intelligence customer service system

Publications (1)

Publication Number Publication Date
CN113434645A true CN113434645A (en) 2021-09-24

Family

ID=77803013

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110577859.9A Pending CN113434645A (en) 2021-05-26 2021-05-26 Financial product intelligence customer service system

Country Status (1)

Country Link
CN (1) CN113434645A (en)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107958091A (en) * 2017-12-28 2018-04-24 北京贝塔智投科技有限公司 A kind of NLP artificial intelligence approaches and interactive system based on financial vertical knowledge mapping
CN110162611A (en) * 2019-04-23 2019-08-23 苏宁易购集团股份有限公司 A kind of intelligent customer service answer method and system
CN111309877A (en) * 2018-12-12 2020-06-19 北京文因互联科技有限公司 Intelligent question-answering method and system based on knowledge graph

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107958091A (en) * 2017-12-28 2018-04-24 北京贝塔智投科技有限公司 A kind of NLP artificial intelligence approaches and interactive system based on financial vertical knowledge mapping
CN111309877A (en) * 2018-12-12 2020-06-19 北京文因互联科技有限公司 Intelligent question-answering method and system based on knowledge graph
CN110162611A (en) * 2019-04-23 2019-08-23 苏宁易购集团股份有限公司 A kind of intelligent customer service answer method and system

Similar Documents

Publication Publication Date Title
CN110162611B (en) Intelligent customer service response method and system
CN105138652B (en) A kind of enterprise's incidence relation recognition methods and system
CN113505586A (en) Seat-assisted question-answering method and system integrating semantic classification and knowledge graph
CN112035640A (en) Refined question-answering method based on intelligent question-answering robot, storage medium and intelligent equipment
CN110175229B (en) Method and system for on-line training based on natural language
CN109508367A (en) Automatically extract the method, on-line intelligence customer service system and electronic equipment of question and answer corpus
CN110727776A (en) Automobile question-answer interaction system and method based on artificial intelligence
CN114969297A (en) Method for analyzing power customer appeal relevancy
CN112035655A (en) Bank human resource system and working method
CN113434645A (en) Financial product intelligence customer service system
CN110321414A (en) A kind of artificial intelligence counseling services method and system based on deep learning
CN112988704A (en) AI consultation database cluster building method and system
CN113987151A (en) Intelligent customer service reply method and device
CN115114493A (en) Intelligent question-answering system implementation method and device based on question matching
CN111159383A (en) Legal opinion book generation system based on target object
CN111125368A (en) Legal opinion book generation method based on target object
CN112417113A (en) Intelligent question-answering method and system based on voice recognition technology
CN114580407A (en) Intelligent consulting method and system for industry recruitment in park based on maximum entropy
CN115408504A (en) Intelligent question-answering robot system in specific field
CN114186048A (en) Question-answer replying method and device based on artificial intelligence, computer equipment and medium
CN112866491A (en) Multi-meaning intelligent question-answering method based on specific field
CN115048513B (en) Knowledge base construction system based on natural language recognition customer service robot
CN110166640B (en) System and method for establishing call center general information model
CN115455159A (en) Method for carrying out on-line question-answering question matching based on cosine similarity of improved word frequency
Nusheva THE CHALLENGES FACING THE BULGARIAN DIASPORA IN THE BALKAN COUNTRIES FOR THE PRESERVATION OF NATIONAL IDENTITY

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination