CN113408846A - Telephone marketing management method and system based on AI artificial intelligence - Google Patents

Telephone marketing management method and system based on AI artificial intelligence Download PDF

Info

Publication number
CN113408846A
CN113408846A CN202110502998.5A CN202110502998A CN113408846A CN 113408846 A CN113408846 A CN 113408846A CN 202110502998 A CN202110502998 A CN 202110502998A CN 113408846 A CN113408846 A CN 113408846A
Authority
CN
China
Prior art keywords
marketing
client
customer
management system
telephone
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
CN202110502998.5A
Other languages
Chinese (zh)
Inventor
周平世
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.)
Shandong Yuyin Smartfinancial Equipment Co ltd
Original Assignee
Shandong Yuyin Smartfinancial Equipment 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 Shandong Yuyin Smartfinancial Equipment Co ltd filed Critical Shandong Yuyin Smartfinancial Equipment Co ltd
Priority to CN202110502998.5A priority Critical patent/CN113408846A/en
Publication of CN113408846A publication Critical patent/CN113408846A/en
Pending legal-status Critical Current

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
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G06Q10/06311—Scheduling, planning or task assignment for a person or group
    • 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
    • G06Q30/01—Customer relationship services
    • 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
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data
    • 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
    • G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/02—Banking, e.g. interest calculation or account maintenance
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M3/00—Automatic or semi-automatic exchanges
    • H04M3/42—Systems providing special services or facilities to subscribers
    • H04M3/487—Arrangements for providing information services, e.g. recorded voice services or time announcements
    • H04M3/493—Interactive information services, e.g. directory enquiries ; Arrangements therefor, e.g. interactive voice response [IVR] systems or voice portals
    • H04M3/4936—Speech interaction details
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M3/00—Automatic or semi-automatic exchanges
    • H04M3/42—Systems providing special services or facilities to subscribers
    • H04M3/50—Centralised arrangements for answering calls; Centralised arrangements for recording messages for absent or busy subscribers ; Centralised arrangements for recording messages
    • H04M3/51—Centralised call answering arrangements requiring operator intervention, e.g. call or contact centers for telemarketing
    • H04M3/5166—Centralised call answering arrangements requiring operator intervention, e.g. call or contact centers for telemarketing in combination with interactive voice response systems or voice portals, e.g. as front-ends

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Strategic Management (AREA)
  • Finance (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • Marketing (AREA)
  • Human Resources & Organizations (AREA)
  • Economics (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • General Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • Signal Processing (AREA)
  • Game Theory and Decision Science (AREA)
  • Tourism & Hospitality (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Educational Administration (AREA)
  • Human Computer Interaction (AREA)
  • Technology Law (AREA)
  • Data Mining & Analysis (AREA)
  • Telephonic Communication Services (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

A telephone marketing management method and system based on AI artificial intelligence relates to the communication technology field, automatic outbound is carried out by an AI robot, telephone number state is identified by an ASR speech recognition engine, word combination vector is obtained by a dialectical process and a dialogue turn, client intention identification is carried out by an LSTM model, outbound record, result, number state and client intention form a client label, the client label is automatically returned to an artificial customer service for accurate marketing follow-up, the artificial customer service clicks a client number or a 'dialing' button, a mobile phone provided with an intelligent communication terminal embedded telephone marketing system and connected with the client management system or a distributed communication centralized management system or a tablet computer with a mobile communication function realizes automatic synchronous call-out, automatic outbound of the AI robot and artificial cooperative telephone marketing can save the labor cost of client maintenance and marketing acquisition, the working capacity and the efficiency are improved.

Description

Telephone marketing management method and system based on AI artificial intelligence
Technical Field
The invention relates to the technical field of telemarketing, in particular to a telemarketing management method and system based on AI artificial intelligence.
Background
The customer data of bank more and more become the core asset of bank, on the one hand the bank invests in a large amount of resources annually and carries out bank customer data management, build CRM customer management system, data analysis platform, do not have the intelligent instrument of falling to the ground of data marketing to give a ray of staff high-efficient marketing, on the other hand because the management layer lacks unified management instrument, can only rely on a ray of marketing personnel to think about marketing, the marketing task is often not accomplished, the effect of marketing campaign popularization is good or bad the analysis, can not realize the benefit transformation of financial science and technology achievement.
Adopt traditional artifical telemarketing mode, communicate with customer's telephone and lack the supervision and the control of staying trace of process, traditional hand-copy, shoot, cell-phone record, customer information security does not guarantee, can't realize visual accurate marketing and fall to the ground and the closed loop management of website telemarketing, and the business transformation that has not adapted the whole staff marketing, the intelligent transformation upgrading of wisdom finance, science and technology finance. Chinese patent 2017105498303 discloses an enterprise customer marketing intelligent management system based on cloud computing, which gives an intelligent solution for developing marketing and management in marketing mode, reduces the cost of artificial marketing and management, realizes intelligent visual accurate marketing and marketing management, but still depends on artificial development marketing and management, and the working efficiency also has a very large space for promotion.
Disclosure of Invention
The invention aims to provide a telemarketing management method and a telemarketing management system based on AI artificial intelligence, aiming at solving the problems of low efficiency, inconsistent speech and easy complaint of the telemarketing service manually developed in the prior art, and the invention automatically calls out the marketing jobs screened by the job intentions of notification, return visit, satisfaction survey and simple interactive marketing of customers by an AI robot, automatically returns the calling-out results to the artificial customer service to which the calling-out numbers belong, clicks the customer numbers or the dialing buttons by the artificial customer service, realizes automatic calling out by a mobile phone, a telephone or a tablet computer with communication function which is connected with the customer management system or a distributed communication centralized management system and is provided with an intelligent communication terminal embedded telemarketing system, and the AI robot and the artificial customer service work in a cooperative way, realizes the improvement of the precision of the artificial customer service and the improvement of the marketing efficiency of a network point, the labor cost for customer maintenance and customer obtaining marketing is saved.
In order to achieve the technical purpose, the invention provides a telemarketing management method based on AI artificial intelligence, which comprises the following operations:
an AI robot is used for automatic outbound, voice recognition is carried out by connecting a prompt tone or a polyphonic ringtone to the telephone of an operator, and the state of the number is recorded;
when the telephone is connected, word combination vectors are obtained through an ASR speech recognition engine, man-machine interaction is carried out with a client through a conversation turn and a conversation process, and client intention recognition is carried out through an LSTM model;
forming a client label by the outgoing call record, the result, the state, the client intention and the client intention, and automatically pushing the number and the corresponding client label to the corresponding manual client service;
the artificial customer service carries out secondary marketing follow-up according to the customer label, clicks the customer number or a 'dialing' button, is connected with a customer management system or a distributed communication centralized management system, is provided with a mobile phone, a telephone or a tablet computer with a communication function of an intelligent communication terminal embedded telephone marketing system to realize automatic call-out, leaves traces in real time in the marketing communication process, and automatically stores or writes back the communication data to a database or a platform system for recording.
Further, an AI robot is used for automatic outbound, when the telephone is connected, voice recognition is carried out by telephone connection prompt tones or polyphonic ringtone of operators, and the state of the number is recorded;
the AI robot judges whether to recall automatically according to the number state, the number state forms a client label, and the number state label is automatically pushed to the manual customer service;
and the manual customer service performs optimized updating on the customer information data of the mobile phone numbers with vacant numbers, stop numbers and wrong numbers according to the customer number state labels, records the mobile phone numbers which are not connected, and dials again through an AI robot or manually in other time periods.
Further, the word combination vector is formed by splicing the word vector and the word vector recognized by the ASR speech recognition engine.
Further, the method also comprises the step that the AI robot outbound result is automatically transferred to manual follow-up marketing.
Further, the method further comprises visualizing the whole marketing process, including marketing data visualization, marketing process visualization, result visualization, marketing progress visualization and monitoring management visualization.
Further, the method further comprises:
setting a server, a mobile phone, an intelligent telephone or a tablet personal computer with a communication function for business processing, file management and record storage, and carrying out information acquisition, call recording, storage and automatic dialing outbound on marketing big data;
the business server is connected with the client relation management system, the central database, the AI robot and the connection distributed communication centralized management system, the file server is connected with the client relation management system or the central database, the connection AI robot and the connection distributed communication centralized management system, and the recording server is connected with the client relation management system, the central database, the AI robot and the connection distributed communication centralized management system;
the customer relationship management system and the central database can be replaced by a connection distributed communication centralized management system and a central database, when the enterprise customer relationship management system is richer than a functional module of the distributed communication centralized management system, the distributed communication centralized management system can be used as a submodule of the enterprise customer relationship management system and used for calling automatic outbound of embedded equipment of the intelligent communication terminal embedded telephone marketing system and managing the equipment access quantity and interaction of call information data;
the distributed communication centralized management system is used for managing organizations; the following single or multiple modules may be provided, such as: the system comprises an organization management module, a user management module, a client distribution module, an AI robot management module, an outbound line management module, a call recording module, a dialect knowledge base module, a marketing task list module, a work order counting module, an equipment access authorization module, an equipment query counting module, a marketing report module, a blacklist management module and a short message module;
the business server, the file server and the recording server are connected with the intelligent communication terminal embedded telemarketing system through a network, and the intelligent communication terminal embedded telemarketing system is arranged in the mobile phone, the telephone or the tablet personal computer with the mobile communication function.
An A I artificial intelligence based telemarketing management system, the system comprising:
the number state recognition module is used for carrying out automatic outbound by utilizing the AI robot, carrying out voice recognition by a connection prompt tone or a ring tone of an operator and recording the state of the number;
the intention recognition module is used for carrying out man-machine interaction with the client through a conversation turn and a conversation process when the telephone is connected, obtaining word combination vectors through an ASR (asynchronous transcription) speech recognition engine and carrying out client intention recognition through an LSTM (least squares TM) model;
further, the system further comprises:
the label pushing module is used for forming a customer label by the outgoing call record, the result, the number state and the customer intention and automatically pushing the number and the corresponding customer label to the corresponding manual customer service;
and the secondary follow-up module can be integrated in the customer management module or the marketing task list module and is used for performing secondary follow-up on the manual customer service according to the customer label, keeping traces in real time in the marketing communication process, and writing back the communication record, the communication report form, the marketing result, the customer maintenance information and the customer label to a database or a platform system for recording.
Further, the system also comprises an artificial intelligence visualization module which is used for realizing marketing data visualization, marketing process visualization, result visualization, marketing progress visualization and monitoring management visualization.
The effect provided in the summary of the invention is only the effect of the embodiment, not all the effects of the invention, and one of the above technical solutions has the following advantages or beneficial effects:
compared with the prior art, the invention carries out automatic outbound through the AI robot, records the number state through the speech recognition engine, carries out man-machine interaction with the client through the conversation turns and the conversational process, obtains the word combination vector through the ASR speech recognition engine, carries out client intention recognition through the LSTM model, forms the outbound record, the result, the number state and the client intention into the client label, pushes the client label to the corresponding artificial customer service for secondary follow-up, can make up the problems of complicated marketing business, insufficient professional financial management quantity, inconsistent conversational skill and insufficient service capability, hands the AI robot to carry out automatic outbound through the work of simple interaction with the client such as notification, return visit, satisfaction survey, intention screening and the like, automatically returns the outbound result to the artificial customer service to which the outbound number belongs, and manually carries out efficient and accurate follow-up marketing through the outbound result, the method and the system realize the improvement of the working efficiency of the marketing of the network points and save the labor cost of the marketing of the customers. The marketing work of notice, return visit, satisfaction survey and the work intention screening of the simple interactive marketing of the client is handed over to an AI robot for automatic call-out, and the call-out result is automatically returned to an artificial customer service belonging to the call-out number, the artificial customer service clicks the client number or a 'dialing' button, and a mobile phone set provided with an intelligent communication terminal embedded telephone marketing system or a tablet computer with a mobile communication function which is connected with a client management system or a distributed communication centralized management system is connected to realize the automatic call-out,
the AI robot and the artificial customer service work in a cooperative mode, the problems that the efficiency of manually developing the services is low, the dialect is not uniform and the services are easy to complain are solved, the intention customers are screened out through AI intelligence, and then the accuracy of the artificial customer service marketing is improved, the working efficiency of the website marketing is improved, and the labor cost of customer maintenance and customer-obtaining marketing is saved in an intervention marketing mode of a customer manager.
Drawings
Fig. 1 is a flowchart of a telemarketing management method based on AI artificial intelligence provided in an embodiment of the present invention;
fig. 2 is a block diagram of a telemarketing management system based on AI artificial intelligence provided in an embodiment of the present invention.
Fig. 3 is a network diagram of a telemarketing management system based on AI artificial intelligence provided in an embodiment of the present invention.
Detailed Description
In order to clearly explain the technical features of the present invention, the following detailed description of the present invention is provided with reference to the accompanying drawings. The following disclosure provides many different embodiments, or examples, for implementing different features of the invention. To simplify the disclosure of the present invention, the components and arrangements of specific examples are described below. Furthermore, the present invention may repeat reference numerals and/or letters in the various examples. This repetition is for the purpose of simplicity and clarity and does not in itself dictate a relationship between the various embodiments and/or configurations discussed. It should be noted that the components illustrated in the figures are not necessarily drawn to scale. Descriptions of well-known components and processing techniques and procedures are omitted so as to not unnecessarily limit the invention.
The following describes a telemarketing management method and system based on AI artificial intelligence provided by the embodiments of the present invention in detail with reference to the accompanying drawings.
As shown in fig. 1, the present invention discloses a telemarketing management method based on AI artificial intelligence, the method comprising the operations of:
an AI robot is used for automatic outbound, voice recognition is carried out through a switch-on prompt tone of an operator, and the state of a number is recorded;
when the telephone is connected, man-machine interaction is carried out with a client through a conversation turn and a conversation process, word combination vectors are obtained through an ASR speech recognition engine, and client intention recognition is carried out through an LSTM model;
forming a customer label by the outgoing call record, the result, the number state and the customer intention, and automatically pushing the number and the corresponding customer label to the corresponding manual customer service;
and the manual customer service performs secondary follow-up according to the customer label, leaves a trace in real time in the marketing communication process, and writes back the communication record, the communication report, the marketing result, the customer maintenance information and the customer label to the customer relationship management system for recording.
In the embodiment of the invention, an AI robot is added to automatically call out, and the state of the mobile phone number is identified. Through the ASR speech recognition engine, in combination with an on prompt tone or a polyphonic ringtone of an operator in the number on process, such as 'the telephone dialed by you is in a call', 'the telephone dialed by you is turned off', and the like, the state of the calling mobile phone number is recognized. And optimally updating the customer information data for the mobile phone numbers with vacant numbers, stopped numbers and wrong numbers, for example, deleting the numbers, recording the mobile phone numbers which are not connected, and dialing again in other time periods.
When the AI robot calls the mobile phone number to automatically connect the client, the intention of screening the client is realized through the conversation turns and the conversation process, such as intention to the client, transacted client and the like. But the correct understanding of the content spoken by the client is ensured in the process of man-machine interaction, and then the client is correctly screened.
In the embodiment of the invention, the word vectors and the word vectors identified by the ASR speech recognition engine are spliced to form word combination vectors which are used as input data and input into the intention recognition model, and abnormal influence on intention recognition caused by word segmentation errors is reduced on the basis of not losing word characteristics. In the embodiment of the invention, intention recognition is carried out through the LSTM model, and the information of the whole sentence is fused in each hidden layer state in the LSTM model, so that the last hidden layer state is not only used as a model output vector for classification, but also the output of each hidden layer state is comprehensively utilized for classifying each word, and the intention classification result of each word is obtained. A sentence containing m characters is given an encoding expression E and is encoded through LSTM to obtain a hidden layer state:
E＝(e1,e2,e3,...,em)
σ＝sigmoid()
it＝σ(Wxixi+Whiht-1+Wcict-1+bi)
ft＝σ(Wxfxt+Whfht-1+Wcfct-1+bf)
ct＝ftct-1+it tanh(Wxcxt+Whcht-1+bc)
ot＝σ(Wxfxt+Whfht-1+Wcfct-1+bf)
ht＝ot tanh(ct)
wherein i, f, c, o are respectively an input gate, a forgetting gate, a unit vector and an output gate, and the intention classification result of each word is obtained by softmax classification:
yi＝soft max(Whhi)
ot＝arg max(yi)
the intent classification of the entire sentence is determined by voting:
Figure BDA0003057143930000071
where m is the number of words contained in the sentence and n represents the total number of intent tags.
After the intention of the customer is recognized, the relevant data of each number, including outbound records, results, number states, the intention of the customer and the like, are arranged to form a customer label, the number and the corresponding customer label are automatically pushed to the corresponding artificial customer service, and the artificial customer service follows the customer through the outbound results of the AI robot pushed by the system and secondary utilization of intelligent equipment.
And for the robot outbound result, intelligent marketing is carried out through manual customer service. And a business server, a file server, a recording server and a plurality of mobile phones or telephones are arranged to acquire information, record calls, store and dial marketing big data.
The business server is connected with the client management system and the distributed communication centralized management system, the file server is connected with the client management system, the distributed communication centralized management system and the intelligent communication terminal embedded telemarketing system, the recording server is connected with the distributed communication centralized management system and the intelligent communication terminal embedded telemarketing system, and the intelligent communication terminal embedded telemarketing system is arranged in the mobile phone or the telephone or the tablet computer with the communication function.
The client management system is connected with the embedded telephone marketing system of the intelligent communication terminal through the Internet, the embedded telephone marketing system can be replaced by a distributed communication centralized management system under the condition that an enterprise does not have the client management system, the distributed communication centralized management system can become a sub-module of the intelligent telephone marketing management of the enterprise under the condition that the enterprise has the client management system, and the intelligent telephone marketing management system can automatically and accurately identify clients, automatically correspond to marketing personnel, automatically dial calls, synchronize marketing results, display client information, display last contact records of the calls, automatically belong to client managers, upload and retrieve call records, automatically remind the clients, automatically count marketing reports and automatically update functions by dialing the calls through the client management system, can be used for centralized management of all levels of organizations nationwide, province, city and the like, and specially check and count a certain area or field, the system is convenient for handling complaints, work supervision, marketing management, key customer maintenance and authority distribution and use.
The client manager login device uploads a client information importing function through the client management module of the distributed communication centralized management system, manually imports clients in an outbound result of the AI robot, can check automatically received client labels in the marketing task list module, manually clicks a client number or a dialing button by a client service, is connected with a mobile phone, a telephone or a tablet computer with a mobile communication function of the intelligent communication terminal embedded telephone marketing system of the client management system or the distributed communication centralized management system to realize automatic calling,
the embedded telephone marketing system can automatically receive and check the client list in the outbound result of the AI robot by logging in the intelligent communication terminal, click a single client list on the equipment to realize automatic calling of a mobile phone, a telephone or a tablet personal computer with a mobile communication function, fill the marketing result after the telephone marketing with the client is finished, and automatically synchronize the marketing result to the client management system. The details of the call records, including data of call objects, call types, call time, call duration, marketing results and the like, are stored in the file server and the recording server, the call records during call can be played or downloaded on line, the export button at the upper right corner can be clicked, and the call records can be downloaded locally in the form of Excel files.
In the whole marketing process, traces, call records, call reports, marketing results, customer maintenance information and customer labels can be left in real time and are automatically written back to a customer relationship management system, marketing closed loop is realized through man-machine linkage, and the synergistic effect of greater data integration and intercommunication is exerted.
In the whole marketing management process, the whole process artificial intelligence visualization is realized, and the whole process artificial intelligence visualization comprises marketing data visualization, marketing process visualization, result visualization, marketing progress visualization and monitoring management visualization.
Through forming the data label of key information and write back to customer management system, data center, or other platform systems to customer voice call, the AI robot exhales outward and can realize that the robot is automatic to be exhaled outward and select the intention customer, automatic sending marketing SMS confirms telling the customer, and carry out the accurate telemarketing follow-up of secondary high efficiency by artifical customer service, will save customer's marketing time and cost greatly, through system and data integration, the efficient visual accurate marketing of human-computer interaction realization.
As shown in fig. 2, an embodiment of the present invention further discloses an AI artificial intelligence-based telemarketing management system, which includes:
the number state recognition module is used for carrying out automatic outbound by utilizing the AI robot, carrying out voice recognition by a connection prompt tone of an operator and recording the state of the number;
the intention recognition module is used for carrying out man-machine interaction with the client through a conversation turn and a conversation process when the telephone is connected, obtaining word combination vectors through an ASR (asynchronous transcription) speech recognition engine and carrying out client intention recognition through an LSTM (least squares TM) model;
the label pushing module is used for forming a customer label by the outgoing call record, the result, the number state and the customer intention and automatically pushing the number and the corresponding customer label to the corresponding manual customer service;
and the secondary follow-up module can be integrated in the customer management module or the marketing task list module and is used for performing secondary follow-up on the manual customer service according to the customer label, keeping traces in real time in the marketing communication process, and automatically writing back the communication record, the communication report form, the marketing result, the customer maintenance information and the customer label to the customer relationship management system for recording.
And an AI robot is added to automatically call outside and identify the state of the mobile phone number. The ASR speech recognition engine is combined with a call-in prompt tone of an operator in the number call-in process, such as 'the telephone dialed by you is in a call', 'the telephone dialed by you is powered off', 'the number dialed by you is stopped', and the like, so that the state of the mobile phone number in the call is recognized. And optimally updating the customer information data for the mobile phone numbers with vacant numbers, stopped numbers and wrong numbers, recording the mobile phone numbers which are not connected, and dialing again in other time periods.
When the AI robot calls the mobile phone number to automatically connect the client, the intention of screening the client is realized through the conversation turns and the conversation process, such as intention to the client, transacted client and the like. But the correct understanding of the content spoken by the client is ensured in the process of man-machine interaction, and then the client is correctly screened.
In the embodiment of the invention, the word vectors and the word vectors identified by the ASR speech recognition engine are spliced to form word combination vectors which are used as input data and input into the intention recognition model, and abnormal influence on intention recognition caused by word segmentation errors is reduced on the basis of not losing word characteristics. In the embodiment of the invention, intention recognition is carried out through the LSTM model, and the information of the whole sentence is fused in each hidden layer state in the LSTM model, so that the last hidden layer state is not only used as a model output vector for classification, but also the output of each hidden layer state is comprehensively utilized for classifying each word, and the intention classification result of each word is obtained. A sentence containing m characters is given an encoding expression E and is encoded through LSTM to obtain a hidden layer state:
E＝(e1,e2,e3,...,em)
σ＝sigmoid()
it＝σ(Wxixi+Whiht-1+Wcict-1+bi)
ft＝σ(Wxfxt+Whfht-1+Wcfct-1+bf)
ct＝ftct-1+it tanh(Wxcxt+Whcht-1+bc)
ot＝σ(Wxfxt+Whfht-1+Wcfct-1+bf)
ht＝ot tanh(ct)
wherein i, f, c, o are respectively an input gate, a forgetting gate, a unit vector and an output gate, and the intention classification result of each word is obtained by softmax classification:
yi＝soft max(Whhi)
ot＝arg max(yi)
the intent classification of the entire sentence is determined by voting:
Figure BDA0003057143930000101
where m is the number of words contained in the sentence and n represents the total number of intent tags.
After the intention of the customer is recognized, the relevant data of each number, including outbound records, results, number states, the intention of the customer and the like, are arranged, a customer label is formed, the number and the corresponding customer label are automatically pushed to the corresponding artificial customer service, and the artificial customer service carries out secondary utilization of intelligent equipment to efficiently and accurately follow up the customer through the outbound result of the AI robot pushed by the system.
As shown in fig. 3, the present invention discloses a telemarketing management method based on AI artificial intelligence, the method further comprising:
and a business server, a file server, a recording server and a plurality of mobile phones or telephones or tablet computers with communication functions are arranged, and information acquisition, call recording, storage and dialing are carried out on the marketing big data. The business server is connected with the client management system and the distributed communication centralized management system, the file server is connected with the client management system, the distributed communication centralized management system and the intelligent communication terminal embedded telemarketing system, the recording server is connected with the distributed communication centralized management system and the intelligent communication terminal embedded telemarketing system, and the intelligent communication terminal embedded telemarketing system is arranged in the mobile phone or the telephone.
Taking a network telephone as an example, the telephone is used for automatic dialing outbound of manual customer service, the telephone is provided with an intelligent communication terminal embedded telephone marketing system which is butted with a customer management system, a distributed communication centralized management system and a data center of each bank through a network, the telephone can dial the network telephone of SI P protocol by connecting an outbound special line through the network, if a mobile phone card is arranged on the telephone, the telephone can dial a mobile phone by clicking a dialing button behind customer information through a computer logging in the customer management system or the distributed communication centralized management system to realize synchronous automatic dialing of the telephone, or directly and manually clicking the dialing outbound on the telephone, and after the call, a call record, a call report, a marketing result, customer maintenance information and a customer label are automatically written back to a database or a platform system to be recorded, so that intelligent telephone marketing, data processing and the like are realized, The system comprises voice call management, service flow automatic processing, data interaction safety management, visual accurate telemarketing of all employees and landing employee marketing trace management, and can be distributed at multiple points, managed in a remote centralized mode and upgraded remotely.
Telephone sets of the whole country and the whole network can be realized without modification, telemarketing management, voice call management, service flow automatic processing, data interaction safety management, visual accurate telemarketing of all staff and ground-to-ground whole staff marketing trace-remaining management can be carried out under the condition of network line outbound call or mobile network, and remote centralized management and remote upgrading can be realized.
Taking an intelligent fixed telephone as an example, the original PSTN fixed telephone line of an enterprise intranet and a network can be used, telephone dialing of the whole country and the whole network can be realized through the fixed telephone line under the environment of the enterprise intranet without modification, a user management system can be logged in through a computer or a distributed communication centralized management system, a dialing button behind user information can be clicked to realize synchronous automatic dialing of the telephone, manual dialing and calling can be directly performed on the telephone, after the call is finished, call recording, call report forms, marketing results, user maintenance information and user labels are automatically written back to a database or a platform system through the network to be recorded, and intelligent telephone marketing, voice call management, service flow automation processing, safety management of data interaction, visual accurate telephone marketing of all employees and ground whole-person marketing trace remaining management are realized, the system can be distributed and placed at multiple points, managed in a remote centralized mode and upgraded remotely.
The mobile phone or the tablet personal computer is used for manual customer service automatic dialing outbound, the mobile phone or the tablet personal computer is provided with an intelligent communication terminal embedded telemarketing system which can be butted with a customer management system, a distributed communication centralized management system and a data center of each enterprise through a network, telephone dialing can be carried out through the mobile network, synchronous automatic dialing of the mobile phone can be realized by clicking a dialing button behind customer information through logging in the customer management system or the distributed communication centralized management system through the computer, telephone dialing can also be carried out through the mobile network directly on the mobile phone, call data are uploaded to a database and are interacted with the data through the network, after the call is finished, automatic call recording, call report forms, marketing results, customer maintenance information and customer labels are recorded in the database or the platform system through network write-back, and intelligent telemarketing, voice call management, call data processing and the like are realized, The system comprises service management, service flow automatic processing, data interaction safety management, visual accurate telemarketing of all employees and landing employee marketing trace management, and can be distributed at multiple points, managed in a remote centralized mode and upgraded remotely.
The telemarketing management, the voice call management, the service flow automatic processing, the data interaction safety management, the visual accurate telemarketing and the landing whole staff marketing trace management of all the staff can be realized under the condition of mobile network and any place by mobile phones and tablet personal computers in the whole country without modification, and the remote centralized management and the remote upgrading can be realized.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.

Claims (9)

1. A telemarketing management method based on AI artificial intelligence, characterized in that the method comprises the following operations:
an AI robot is used for automatic outbound, when the telephone is connected, an ASR speech recognition engine is used for obtaining word combination vectors, man-machine interaction is carried out with a client through conversation turns and a conversation process, and client intention recognition is carried out through an LSTM model;
forming a customer label by the outgoing call record and the customer intention, and automatically pushing the number and the corresponding customer label to the corresponding manual customer service;
the artificial customer service carries out secondary marketing follow-up according to the customer label, clicks the customer number or a 'dialing' button, is connected with a customer management system or a distributed communication centralized management system, is provided with a mobile phone, a telephone or a tablet computer with a communication function of an intelligent communication terminal embedded telephone marketing system to realize automatic call-out, leaves traces in real time in the marketing communication process, and automatically stores or writes back the communication data to a database or a platform system for recording.
2. The AI artificial intelligence based telemarketing management method of claim 1, wherein an AI robot is used to make an automatic outbound call, and when the call is connected, voice recognition is performed by a call connection prompt tone or a color ring tone of an operator, and the state of the number is recorded;
the AI robot judges whether to recall automatically according to the number state, the number state forms a client label, and the number state label is automatically pushed to the manual customer service;
and the manual customer service records the disconnected mobile phone number according to the customer number state label and dials again through an AI robot or manually in other time periods.
3. The AI artificial intelligence based telemarketing management method of claim 1, wherein the word combination vector is formed by concatenating a word vector and a word vector recognized by an ASR speech recognition engine.
4. The AI artificial intelligence based telemarketing management method of claim 1, further comprising an automatic routing of AI robot outbound results to manual follow-up marketing.
5. The AI artificial intelligence based telemarketing management method of claim 1, further comprising visualizing a marketing overall process, including marketing data visualization, marketing process visualization, result visualization, marketing progress visualization, and monitoring management visualization.
6. The AI artificial intelligence based telemarketing management method of claim 1, further comprising:
setting a server, a mobile phone, a telephone or a tablet computer for business processing, file management and record storage, and carrying out information acquisition, call recording, storage and automatic dialing outbound on marketing big data;
the business server is connected with the client management system, the central database, the AI robot and the connection distributed communication centralized management system, the file server is connected with the client relationship management system, the central database, the connection AI robot and the connection distributed communication centralized management system, and the recording server is connected with the client relationship management system, the central database, the AI robot and the connection distributed communication centralized management system
The business server, the file server and the recording server are connected with the intelligent communication terminal embedded telemarketing system through a network, and the intelligent communication terminal embedded telemarketing system is arranged in the mobile phone, the telephone or the tablet personal computer.
7. An AI artificial intelligence based telemarketing management system, the system comprising:
the number state recognition module is used for carrying out automatic outbound by utilizing the AI robot, carrying out voice recognition by a connection prompt tone of an operator and recording the state of the number;
and the intention recognition module is used for performing man-machine interaction with the client through a conversation turn and a conversation process when the telephone is connected, obtaining word combination vectors through an ASR (asynchronous transcription) speech recognition engine, and performing client intention recognition through an LSTM (least Square TM) model.
8. The AI artificial intelligence based telemarketing management system of claim 7, further comprising:
the label pushing module is used for forming a customer label by the outgoing call record, the result, the number state and the customer intention and automatically pushing the number and the corresponding customer label to the corresponding manual customer service;
and the secondary follow-up module is used for performing secondary follow-up by the manual customer service according to the client label, keeping traces in real time in the marketing communication process, and automatically writing back the communication record, the communication report, the marketing result, the client maintenance information and the client label to the database or the platform system for recording.
9. The AI artificial intelligence based telemarketing management system of claim 6, further comprising an artificial intelligence visualization module for implementing marketing data visualization, marketing process visualization, results visualization, marketing progress visualization, and monitoring management visualization.
CN202110502998.5A 2021-05-10 2021-05-10 Telephone marketing management method and system based on AI artificial intelligence Pending CN113408846A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110502998.5A CN113408846A (en) 2021-05-10 2021-05-10 Telephone marketing management method and system based on AI artificial intelligence

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110502998.5A CN113408846A (en) 2021-05-10 2021-05-10 Telephone marketing management method and system based on AI artificial intelligence

Publications (1)

Publication Number Publication Date
CN113408846A true CN113408846A (en) 2021-09-17

Family

ID=77678089

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110502998.5A Pending CN113408846A (en) 2021-05-10 2021-05-10 Telephone marketing management method and system based on AI artificial intelligence

Country Status (1)

Country Link
CN (1) CN113408846A (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114205467A (en) * 2021-12-09 2022-03-18 广西电网有限责任公司 Intelligent outbound system for power grid customer service work order and use method
CN114757595A (en) * 2022-06-15 2022-07-15 中邮消费金融有限公司 User-defined scheduling strategy-based telemarketing task scheduling method and system
CN115567640A (en) * 2021-12-24 2023-01-03 上海莘启科技有限公司 AI-based intelligent outbound marketing analysis system
CN115994766A (en) * 2022-11-03 2023-04-21 八度云计算(安徽)有限公司 Outbound system for automatically positioning target crowd

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105262881A (en) * 2015-08-28 2016-01-20 北京搜狗科技发展有限公司 Communication control method and electronic equipment
CN107392450A (en) * 2017-07-07 2017-11-24 山东御银智慧金融设备有限公司 Corporate client marketing intellectualized management system based on cloud computing
CN108521525A (en) * 2018-04-03 2018-09-11 南京甄视智能科技有限公司 Intelligent robot customer service marketing method and system based on user tag system
CN110019734A (en) * 2017-12-28 2019-07-16 顺丰科技有限公司 A kind of intention in utterance recognition methods, device, equipment and storage medium

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105262881A (en) * 2015-08-28 2016-01-20 北京搜狗科技发展有限公司 Communication control method and electronic equipment
CN107392450A (en) * 2017-07-07 2017-11-24 山东御银智慧金融设备有限公司 Corporate client marketing intellectualized management system based on cloud computing
CN110019734A (en) * 2017-12-28 2019-07-16 顺丰科技有限公司 A kind of intention in utterance recognition methods, device, equipment and storage medium
CN108521525A (en) * 2018-04-03 2018-09-11 南京甄视智能科技有限公司 Intelligent robot customer service marketing method and system based on user tag system

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
周权 等: ""基于多特征融合的意图识别算法研究"", 《电脑知识与技术》 *

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114205467A (en) * 2021-12-09 2022-03-18 广西电网有限责任公司 Intelligent outbound system for power grid customer service work order and use method
CN115567640A (en) * 2021-12-24 2023-01-03 上海莘启科技有限公司 AI-based intelligent outbound marketing analysis system
CN114757595A (en) * 2022-06-15 2022-07-15 中邮消费金融有限公司 User-defined scheduling strategy-based telemarketing task scheduling method and system
CN115994766A (en) * 2022-11-03 2023-04-21 八度云计算(安徽)有限公司 Outbound system for automatically positioning target crowd
CN115994766B (en) * 2022-11-03 2023-11-07 八度云计算(安徽)有限公司 Outbound system for automatically positioning target crowd

Similar Documents

Publication Publication Date Title
CN113408846A (en) Telephone marketing management method and system based on AI artificial intelligence
CN107392450B (en) Enterprise client marketing intelligent management system based on cloud computing
CN101431573B (en) Method and equipment for implementing automatic customer service through human-machine interaction technology
CN107331383A (en) One kind is based on artificial intelligence telephone outbound system and its implementation
US20100100377A1 (en) Generating and processing forms for receiving speech data
CN103686723A (en) System and method for processing complex SMS (short message service) message of mobile customer hotline SMS messaging service hall
CN106993104A (en) Call processing method, device and terminal
CN109446305A (en) The construction method and system of intelligent tour customer service system
US11659364B2 (en) Method of exposing a received message, user terminal performing the same and computer readable medium for performing the same
Sharp Call center operation: design, operation, and maintenance
CN102904928B (en) The high in the clouds retrieval of service calls and automatic dial method, system and device
CN110677540A (en) Intelligent voice recognition management system for consultation telephone of medical institution
CN114372130A (en) Online customer service system based on intelligent voice question answering
CN110351444A (en) A kind of intelligent sound customer service system
CN110189110A (en) Business Process-oriented autonomous intelligent customer service system and method
US6668056B2 (en) System and method for modeling resources for calls centered in a public switch telephone network
CN111652399A (en) System for realizing non-inductive face-brushing number-taking in face recognition of tax service hall
CN109819124B (en) IVR intelligent service and implementation method thereof
CN114418641A (en) Automatic dispatching method and device for stock customer access work order and electronic equipment
CN102572128A (en) Telephone check-in system
CN107332999A (en) A kind of Stranger Calls number identification method and device
CN115907784A (en) Method and system for identifying and actively early warning and notifying sensitive customers in electric power business hall
CN107580305B (en) Customer member purity analysis method and system
CN116167587A (en) Automatic customer service distribution method and storage system
CN113342987B (en) Composite network construction method of distribution DTU acceptance special corpus

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