CN106790004B - Customer service auxiliary real-time prompt system based on artificial intelligence - Google Patents
Customer service auxiliary real-time prompt system based on artificial intelligence Download PDFInfo
- Publication number
- CN106790004B CN106790004B CN201611142197.8A CN201611142197A CN106790004B CN 106790004 B CN106790004 B CN 106790004B CN 201611142197 A CN201611142197 A CN 201611142197A CN 106790004 B CN106790004 B CN 106790004B
- Authority
- CN
- China
- Prior art keywords
- user
- intention
- module
- data
- communication interface
- 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.)
- Active
Links
Images
Classifications
-
- 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
- H04M3/5141—Details of processing calls and other types of contacts in an unified manner
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/22—Indexing; Data structures therefor; Storage structures
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/08—Network architectures or network communication protocols for network security for authentication of entities
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/14—Session management
-
- 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
- H04M3/5183—Call or contact centers with computer-telephony arrangements
- H04M3/5191—Call or contact centers with computer-telephony arrangements interacting with the Internet
Abstract
The invention provides a customer service auxiliary real-time prompting system based on artificial intelligence, which comprises a database, an intention recognizer, a template generator and communication interfaces, wherein the database, the intention recognizer and the template generator are sequentially connected, and the communication interfaces are respectively connected with a user communication tool, the template generator and the database; the intention recognizer is used for receiving the data sent by the database and recognizing the user session data to generate user intention data; the template generator is used for receiving the user intention data sent by the intention recognizer and generating a template through the user intention data; the communication interface is used for receiving the user session data on the user communication tool and sending the user session data to the database, and is used for receiving the template sent by the template generator and sending the template to the user communication tool. The invention can identify the user session data and automatically generate the template according to the user session data so as to save the session time of the client and the customer service and facilitate the customer service to read the user session data.
Description
Technical Field
The invention relates to the field of computer networks, in particular to a customer service auxiliary real-time prompting system based on artificial intelligence.
Background
With the rapid development of computer technology and network communication technology, the wide application of computer networks in various fields greatly improves the working efficiency of people, and makes the clothes and food activities more convenient. People at both ends of the earth can communicate with each other through the internet, and electronic commerce rises accordingly. In the era of mobile internet, a large number of users use mobile phones to perform information interaction. Traditional customer service can not satisfy the high efficiency of mobile internet era, even if the customer service is on the telephone and computer side every day, the work order can not be processed completely. Therefore, an artificial intelligence-based customer service assistant real-time prompting system is urgently needed to improve the conversation efficiency between the customer and the customer service.
Disclosure of Invention
The invention aims to provide a customer service assistance real-time prompting system based on artificial intelligence, which can identify user session data and automatically generate a template according to the user session data so as to save the session time of a client and customer service and facilitate the customer service to read the user session data.
In order to achieve the aim, the invention provides a customer service auxiliary real-time prompting system based on artificial intelligence, which comprises a database, an intention recognizer, a template generator and communication interfaces, wherein the database, the intention recognizer and the template generator are sequentially connected, and the communication interfaces are respectively connected with a user communication tool, the template generator and the database; the intention recognizer is used for receiving the data sent by the database and recognizing the user session data to generate user intention data; the template generator is used for receiving the user intention data sent by the intention recognizer and generating a template through the user intention data; the communication interface is used for receiving user session data on the user communication tool and sending the user session data to the database, and is used for receiving the template sent by the template generator and sending the template to the user communication tool, wherein the user communication tool comprises a microblog, a WeChat, HTML5, a webpage, communication software and a call center.
As a preferred mode, the invention provides a customer service auxiliary real-time prompt system based on artificial intelligence, wherein a template generator comprises an extraction module and a combination module which are connected with each other; the extraction module is used for receiving the user intention data sent by the intention recognizer, retrieving and matching a preset keyword table through the user intention data to extract keywords in the user intention data, and retrieving and matching a preset service information table through the user intention data to extract service information in the user intention data; the combination module is used for receiving the service information and the keywords and combining the service information and the keywords together according to a combination mode preset by a user to generate a template.
As a preferred mode, the present invention provides a customer service assistance real-time prompt system based on artificial intelligence, wherein the communication interface includes: and the interface calling module is used for calling the communication interface of the user communication tool so as to carry out information interaction.
As a preferred mode, the present invention provides a customer service assistance real-time prompt system based on artificial intelligence, further comprising: and the manual switching module is respectively connected with the intention recognizer and the communication interface and is used for sending a message to the manual customer service through the communication interface when receiving a prompt that the intention recognizer fails to recognize the intention of the user, and reminding the manual customer service to access the user communication tool for conversation so as to answer the question of the client.
As a preferred mode, the invention provides a customer service assistance real-time prompting system based on artificial intelligence, further comprising a real-time monitoring module, including: the retrieval module is connected with the communication interface and used for sending the user ID and the retrieval session request to the corresponding server through the communication interface and receiving the response information of the corresponding server through the communication interface; and the communication module is connected with the retrieval module and used for receiving the response information and receiving the user session data when the response information returns the user session data which agrees to send the corresponding ID.
As a preferred mode, the invention provides a customer service assistance real-time prompting system based on artificial intelligence, which further comprises a history spot check module, and the history spot check module comprises: the timing module is connected with the communication interface and used for interacting with the communication interface of the user communication tool through the communication interface so as to read and store the response time of the customer service; and the counting module is connected with the timing module and used for receiving the response time and respectively counting the average response time of each customer service.
As a preferred mode, the invention provides a customer service auxiliary real-time prompt system based on artificial intelligence, which also comprises a KPI (Key Performance indicator) assessment module connected with a database, and the KPI assessment module comprises: the assessment index calculation module is used for receiving assessment indexes and a preset performance table of the database, matching the preset performance table through the assessment indexes, and converting the assessment indexes into performance indexes and outputting the performance indexes; and the index recording module is used for inputting the assessment indexes to the database and sending the assessment indexes to the assessment index calculating module.
As a preferred mode, the present invention provides a customer service assistance real-time prompt system based on artificial intelligence, further comprising: and the authority verification module is connected with the database and used for verifying the identity information of the user according to the identity information preset in the database.
As a preferred mode, the present invention provides a customer service assistance real-time prompt system based on artificial intelligence, further comprising: and the head portrait matching module is respectively connected with the intention recognizer and the communication interface and is used for interacting with the communication interface of the user communication tool through the communication interface so as to acquire the head portrait information of the user and automatically reading, storing and displaying the head portrait information of the user.
As a preferred mode, the present invention provides a customer service assistance real-time prompt system based on artificial intelligence, further comprising: and the automatic response system is respectively connected with the intention recognizer and the communication interface and is used for receiving the intention data of the user to generate corresponding response information and sending the response information to the communication interface of the user communication tool through the communication interface.
The customer service auxiliary real-time prompt system based on artificial intelligence can improve conversation efficiency between a client and a customer service, automatically generate a template and send the template to the user. The template can clearly list the service information (service theme) to be operated by the client and the keywords of the operation to be carried out, so that the client can conveniently look up the information. The intention recognizer is connected with an automatic response system, the automatic response system is provided with a chat robot and a knowledge base system, 80% of common problems can be solved automatically, and when the trouble problems are met, the manual seat can be accessed to solve at any time.
In addition, the invention supports tens of millions of users to be online at the same time, and the number of the sent messages is over a hundred million, thus the invention is ultra-stable, highly concurrent and highly safe. The invention can be connected with a mobile communication tool, is convenient for a user using a mobile phone to carry out real-time communication, and can be used no matter whether a customer service and a client stand, sit, lie or lie down.
Moreover, the invention also realizes real-time monitoring, historical spot check and KPI check to form omnibearing quality check. The head portrait matching module can provide accurate customer portraits so as to improve the transaction rate.
The communication data access channel is wide, and the communication data from the APP, the microblog, the WeChat, the webpage, the H5 and the call center can be received, so that all customer requirements can be converged into the system for unified processing.
Therefore, the method and the device have important significance for improving conversation efficiency among users.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only used for explaining the concept of the present invention.
FIG. 1 is a schematic block diagram of an artificial intelligence based customer service assistance real-time reminder system of the present invention;
FIG. 2 is a schematic diagram of an artificial intelligence based customer service assistance real-time reminder system according to the present invention;
FIG. 3 is a flowchart of the working steps of the customer service assistance real-time reminder system based on artificial intelligence of the present invention;
FIG. 4 is a flowchart of the steps of the template generator of the customer service assistance real-time reminder system based on artificial intelligence according to the present invention.
Summary of reference numerals:
1. communication interface 2, database 3, intention recognizer
4. Template generator 5, user communication tool 6 and extraction module
7. Combined module 8, interface calling module 9 and manual switching module
10. Real-time monitoring module 11, communication module 12 and retrieval module
13. Historical spot check module 14, timing module 15 and statistic module
16. KPI examination module 17, examination index calculation module 18, index recording module
19. Authority verification module 20, head portrait matching module 21 and automatic response system
Detailed Description
Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings.
The examples described herein are specific embodiments of the present invention, are intended to be illustrative and exemplary in nature, and are not to be construed as limiting the scope of the invention. In addition to the embodiments described herein, those skilled in the art will be able to employ other technical solutions which are obvious based on the disclosure of the claims and the specification of the present application, and these technical solutions include any obvious replacement or modification of the embodiments described herein.
Referring to fig. 1, the customer service assistance real-time prompting system based on artificial intelligence provided by the invention comprises a database 2, an intention identifier 3, a template generator 4 and a communication interface 1, wherein the database 2, the intention identifier 3, the template generator 4 and the communication interface are sequentially connected, and the communication interface 1 is respectively connected with a user communication tool 5, the template generator 4 and the database 2, and the database 2 is used for storing user session data; the intention recognizer 3 is used for receiving the data sent by the database 2 and recognizing the user session data to generate user intention data; the template generator 4 is used for receiving the user intention data sent by the intention recognizer 3 and generating a template by the user intention data; the communication interface 1 is used for receiving user session data on the user communication tool 5 and sending the user session data to the database 2, and is used for receiving the template sent by the template generator 4 and sending the template to the user communication tool 5, wherein the user communication tool 5 comprises a microblog, a WeChat, HTML5, a webpage, communication software and a call center.
Referring to fig. 2, in the present embodiment, the intention recognizer 3 and the template recognizer 4 may be implemented by software programming. The intention recognizer 3 of the invention can automatically generate more accurate descriptor prompts by training a model based on historical dialogue data of past clients and customer service and recognizing the intention of dialogue between two parties. The intent recognizer 3 can train the model by manually noting business information (e.g., business name) based on customer service historical dialogue data. When the intention recognizer 3 recognizes the keyword, the historical question data of customer service may be used as the main research objects, such as "please provide your order number", "what exception occurs to your goods", to perform entity recognition and extraction, and manually confirm "order number", and "goods question" is the keyword of "return goods" service.
The template recognizer 4 can automatically generate a business description sentence containing keywords based on historical dialogue data by a machine learning model.
Specifically, the artificial intelligence algorithm has the following analysis for the user's input:
what kind of questions the user wants to express, what is the most accurate and efficient way to describe? What keywords need to be provided?
Based on the information, the system automatically generates a description template, prompts the description template to a user, fills keywords, selects and confirms the keywords and then sends the keywords to the customer service. The invention can be used for assisting the client conversation and is installed on the intelligent equipment (such as a smart phone and a computer) of the client, and can also be used for assisting the client service conversation and is installed on the intelligent equipment of the client service. In the present embodiment, although the present invention is described as being provided in the client, the present invention is also applicable to the client, and the principle and procedure of installation in the client are the same as those in the client, and the client also has the functions of the presentation session and the support session.
The existing method has the main defect that the corresponding prompt words are searched based on the keywords. If the database does not contain the relevant data of the keyword, the prompt language cannot be found. Or the user says 'where my express delivery arrives', data which is actually relevant, such as 'help me find my express delivery', cannot be matched by the keywords alone.
In the invention, if the customer wants to find the customer service for returning, when the customer inputs 'i want to return' through the user communication tool at the client of the system side, the background artificial intelligence (intention recognizer) of the prompting system analyzes the input to recognize the intention of 'returning', and obtains necessary information (for example, the user session information refers to the problems of order numbers xxxxx and yyyyy) required for applying for returning based on the past dialogue historical data. Then, the template generator can automatically generate a service description text for applying for goods return in real time, such as "my order number xxxxx", i find the problem of yyyyyy after receiving goods, and apply for goods return ", and the user can supplement specific information in the prompt and then give the customer service. Therefore, the communication efficiency of the following clients and customer service is greatly improved by accurately describing the problems and providing necessary information.
For another example, when the customer wants to contact the customer service, for example, the customer wants to buy a Chinese hamburger, and sends a message to the customer service "i wants to order four Chinese hamburgers" through the user communication tool, the intention recognizer of the prompt system automatically receives the user session data of the customer and recognizes the intention of the user. Then, the template generator of the prompt system automatically generates a template according to the user intention data, for example, displaying that "the goods i want to buy are Chinese hamburgers, and the total number is four". In this example, Chinese hamburgers are business information, and four are keywords. The customer service may store the corresponding service information and its corresponding keywords in the prompt system database 2. Also, the intention recognizer can receive a past dialog through the communication interface 1 and analyze keywords according to the past dialog. Therefore, the template generator 4 can automatically generate the template according to the related service information preset by the customer service or according to the historical data of the past conversation, so that the time of the user is saved, and the communication efficiency is improved.
Another disadvantage of the existing method is that the interference of synonyms and negatives cannot be avoided only by keyword search. For example, "i want to buy apple" can point to either the iphone or a fruit. More importantly, the prompt effect is single, only the user can be prompted to point to a high-frequency problem, and the communication between the next customer service and the user cannot be improved or accelerated efficiently.
In the invention, when the server can not identify the user session data of the client, for example, the client sends ' four fruit pies ', the intention identifier 3 finds that only the apple pies and the grape pies are stored in the database 2 by comparing the keyword information in the database 2, the system queries the past user session data, searches for related keywords such as ' strawberry pies ', corrects the searched keywords through historical dialogue data (in the example, the intention identifier 3 identifies that the business information of the strawberry pies, the apple pies and the grape pies is consistent and does not need to correct), if the system can not find other keywords except ' strawberry pies ' in the past user session data, the client is prompted, the goods to be purchased are the apple pies, the grape pies or the strawberry pies, the total number is four ', so that the prompting system can automatically take one action and three actions, the keywords can be extracted from the customer service system database, keywords in the customer's user session data can also be automatically identified and automatically added to the template.
For another example, the client sends "four apples", and the intention identifier 3 finds that only apples and grapes are stored in the database 2 by comparing keyword information in the database 2, the system queries session data of the past user, searches for related keywords such as "apple cell phone", corrects the searched keywords through historical dialogue data (in this example, the intention identifier 3 identifies that business information of the apple cell phone and the grapes in the database is not consistent, so that the intention identifier 3 can judge that the user wants to buy the apple cell phone instead of the apples and the grapes), and if the system cannot find other keywords except "apple cell phone" in the session data of the past user, the client is prompted, and "i want to buy the apples and the grapes, the total number is four".
Referring to fig. 3, the working steps are as follows:
s11 the client sends the user session data to the user communication tool 5. S12 communication interface 1 automatically receives user session data and sends it to database 2. S13 the intention recognizer 3 receives the user session data in the database 2, generates user intention data by recognizing the intention of the user through the user session data, and transmits the user intention data to the template generator 4. S14 the template generator 4 receives the user intention data sent by the intention recognizer 3 and generates a template from the user intention data. S15 the template generator 4 transmits the generated template to the user communication tool 5 through the communication interface 1.
The user need not to ask what kind of product specifically has again like this, only need say rough demand, after user's intention recognizer 3 through communication interface 1 connection user communications tools 5 of suggestion system and discernment user's intention, 4 generation templates of rethread template generator, then send the template to user communications tools 5 through communication interface 1, the user just can know the relevant information of commodity very fast, need not the repeated introduction of customer service, most problems can both be solved through the suggestion system is automatic, need not artifical customer service, therefore conversation efficiency has been improved greatly, and the human cost is saved. The template generated by the prompt system can clearly list the service information to be operated by the client and the keywords of the operation to be carried out, so that the client can conveniently look up the service information. Moreover, the real-time prompting system can be connected with a mobile communication tool, so that a user using a mobile phone can conveniently carry out real-time communication, and the conversation efficiency is improved. The invention can be used no matter whether the customer service and the client stand, sit, lie or lie prone. The invention supports tens of millions of users to be on-line at the same time every day, and the number of the sent messages is over a hundred million, thus the invention is ultra-stable, highly concurrent and highly safe.
The present embodiment further preferably provides a customer service assistance real-time prompting system based on artificial intelligence, wherein the template generator 4 comprises an extraction module 6 and a combination module 7 which are connected with each other; the extraction module 6 is used for receiving the user intention data sent by the intention recognizer 3, retrieving and matching a preset keyword table through the user intention data to extract keywords in the user intention data, and retrieving and matching a preset service information table through the user intention data to extract service information in the user intention data; the combination module 7 is configured to receive the service information and the keywords, and combine the service information and the keywords according to a combination mode preset by a user to generate a template.
In this embodiment, the combining module 7 may combine the keywords according to a preset keyword category and a corresponding priority. For example, the user issues 'four Chinese hamburgers with different thickness' and the intention pattern recognizer 3 analyzes and recognizes the service information and the keywords and then sends the service information and the keywords to the template generator 4 for processing. The template generator determines the keyword priority according to a preset keyword table, for example:
service information: chinese hamburger
The number of keywords: priority is highest keyword taste: the priority is next
The template generated by the template generator 4 is as follows:
i need to order four Chinese hamburgers, which are fat and thin alternately.
Referring to fig. 4, the working steps of the template generator 4 are as follows:
the S21 extraction module 6 extracts a keyword table matching the preset by the user intention data retrieval to extract a keyword in the user intention data. The S22 extraction module 6 sends the keyword to the combination module 7. The S23 combination module 7 receives the user intention data identified by the intention identifier 3, extracts and identifies business information therefrom. S24 the combination module 7 searches the preset keyword and priority table, retrieves the matching keyword to query its corresponding priority. And the S25 combination module 7 automatically combines and generates the template according to the service information and the priority.
Therefore, on one hand, the client can simplify the input information and quickly and automatically generate the template. On the other hand, the customer service can more intuitively and conveniently see the customer demands through the template generated by the system, and the business information and the keywords are automatically classified and recombined, so that the sentences are more smooth and understandable, and the manpower and the time are greatly saved.
The present embodiment further preferably provides a customer service assistance real-time prompting system based on artificial intelligence, wherein the communication interface 1 includes: and the interface calling module 8 is used for calling the communication interface of the user communication tool 5 to perform information interaction.
In this embodiment, the interface calling module 8 can transmit data by wire or wirelessly. The interface calling module 8 is provided with an interface compatible with microblog, WeChat, HTML5, a webpage, communication software and a call center communication protocol, so that the interface calling module can interact with the communication tool. Therefore, the communication data access channel is wide, and the communication data from the APP, the microblog, the WeChat, the webpage, the H5 and the call center can be received, so that all customer requirements can be gathered in the system for uniform processing.
Further preferably, the present embodiment provides a customer service assistance real-time prompting system based on artificial intelligence, further comprising: and the manual switching module 9 is respectively connected with the intention recognizer 3 and the communication interface 1, and is used for sending a message to the manual customer service through the communication interface 1 when receiving a prompt that the intention recognizer 3 fails to recognize the intention of the user, and reminding the manual customer service to access the user communication tool 5 for conversation so as to answer the question of the client.
Therefore, the intention recognizer 3 is connected with the manual switching module 9, when the recognition of the intention of the user fails, the communication interface 1 can send a message to the user communication tool 5 of the manual customer service, and the manual customer service can access to solve the problem at any time.
The present embodiment further preferably provides a customer service assistance real-time prompting system based on artificial intelligence, further including a real-time monitoring module 10 including: a retrieval module 12 connected to the communication interface 1, for sending the user ID and the retrieval session request to the corresponding server through the communication interface 1, for example, sending the retrieval session request to the corresponding server connected to the user communication tool 5, and receiving the response information of the corresponding server through the communication interface 1; the communication module 11, which can be set on the mobile phone of the supervising person, is connected with the retrieval module 12 for receiving the response information, and when the response information returns the user session data agreeing to send the corresponding ID, the supervising person can receive the user session data through the mobile phone. Therefore, the service condition of the customer service can be conveniently checked, and the omnibearing quality inspection is realized.
Further preferably, the present embodiment provides a customer service assistance real-time prompting system based on artificial intelligence, further including a history spot check module 13, including: the timing module 14 is connected with the communication interface 1, and is used for interacting with the communication interface of the user communication tool 5 through the communication interface 1, for example, sending a retrieval session request to a server corresponding to the user communication tool 5 to read the response time of the customer service, receiving the response time through the communication interface 1, and storing the response time to the database 2; and the counting module 15 is connected with the timing module 14 and used for receiving the response time and counting the average response time of each customer service respectively. Therefore, the service condition of the customer service can be conveniently checked, and the omnibearing quality inspection is realized.
The present embodiment further preferably provides a customer service assistance real-time prompting system based on artificial intelligence, further including a KPI assessment module 16 connected to the database 2, including: the assessment index calculation module 17 is used for receiving the assessment indexes and the preset performance table of the database 2, matching the preset performance table through the assessment indexes, and converting the assessment indexes into the performance indexes and outputting the performance indexes; and the index recording module 18 is used for inputting the assessment indexes into the database 2 and sending the assessment indexes to the assessment index calculating module 17. Therefore, the service condition of the customer service can be conveniently checked, and the omnibearing quality inspection is realized.
Thus, the invention realizes real-time monitoring, historical spot check and KPI check through the real-time monitoring module 10, the historical spot check module 13 and the KPI check module 16, and forms omnibearing quality check.
Further preferably, the present embodiment provides a customer service assistance real-time prompting system based on artificial intelligence, further comprising: and the authority verification module 19 is connected with the database 2 and used for verifying the identity information of the user according to the identity information preset in the database 2.
Therefore, the function of the prompting system which can be used by the user can be limited by the system through the authority verification module 19, and the safety of the system is greatly improved.
Further preferably, the present embodiment provides a customer service assistance real-time prompting system based on artificial intelligence, further comprising: the head portrait matching module 20 is respectively connected with the intention recognizer 3 and the communication interface 1, and is used for interacting with the communication interface of the user communication tool 5 through the communication interface 1 to acquire the head portrait information of the user, and automatically reading, storing and displaying the head portrait information of the user.
Therefore, the customer service can provide accurate customer images through the head portrait matching module 20 so as to improve the transaction rate and greatly increase the safety and the convenience of the system.
Further preferably, the present embodiment provides a customer service assistance real-time prompting system based on artificial intelligence, further comprising: and the automatic response system 21 is respectively connected with the intention identifier 3 and the communication interface 1 and is used for receiving the intention data of the user to generate corresponding response information and sending the response information to the communication interface of the user communication tool 5 through the communication interface 1.
In the present embodiment, the automatic response system 21 includes a chat robot and a knowledge base system. Therefore, the intention recognizer 3 is connected with the automatic answering system 21, 80% of common problems can be solved by self, and when the trouble problem is met, the manual seat can be accessed and solved at any time.
It is to be understood that the above-described embodiments of the present invention are merely illustrative of or explaining the principles of the invention and are not to be construed as limiting the invention. Therefore, any modification, equivalent replacement, improvement and the like made without departing from the spirit and scope of the present invention should be included in the protection scope of the present invention. Further, it is intended that the appended claims cover all such variations and modifications as fall within the scope and boundaries of the appended claims or the equivalents of such scope and boundaries.
Claims (5)
1. A customer service auxiliary real-time prompt system based on artificial intelligence comprises a database, an intention recognizer, a template generator and communication interfaces, wherein the database, the intention recognizer and the template generator are sequentially connected with one another, the communication interfaces are respectively connected with a user communication tool, the template generator and the database,
the database is used for storing user session data;
the intention recognizer is used for receiving the data sent by the database and recognizing user session data to generate user intention data;
the template generator is used for receiving the user intention data sent by the intention recognizer and generating a template through the user intention data;
the communication interface is used for receiving user session data on the user communication tool and sending the user session data to the database, and is used for receiving the template sent by the template generator and sending the template to the user communication tool, wherein the user communication tool comprises a microblog, a WeChat, HTML5, a webpage, communication software and a call center;
the intention recognizer is used for recognizing the intention of the conversation between two parties and automatically generating a description language prompt by training a model based on historical conversation data of past customers and customer service; the template recognizer automatically generates a business description sentence containing keywords by a machine learning model based on historical dialogue data;
the intention recognizer can receive the past conversation through the communication interface and analyze keywords according to the past conversation;
the template generator comprises an extraction module and a combination module which are connected with each other;
the extraction module is used for receiving the user intention data sent by the intention recognizer, retrieving and matching a preset keyword table through the user intention data to extract keywords in the user intention data, and retrieving and matching a preset service information table through the user intention data to extract service information in the user intention data;
the combination module is used for receiving the service information and the keywords and combining the service information and the keywords together according to a combination mode preset by a user to generate a template;
the template generator automatically generates a template according to related service information preset by customer service or historical data of past conversations;
still include historical spot check module, include:
the timing module is connected with the communication interface and is used for interacting with the communication interface of the user communication tool through the communication interface so as to read and store the response time of the customer service;
the counting module is connected with the timing module and used for receiving the response time and respectively counting the average response time of each customer service;
the communication interface includes:
the interface calling module is used for calling a communication interface of the user communication tool so as to carry out information interaction;
still include real time monitoring module, include:
the retrieval module is connected with the communication interface and used for sending a client or user ID and a retrieval session request to a corresponding server through the communication interface and receiving response information of the corresponding server through the communication interface;
the communication module is connected with the retrieval module and used for receiving the response information and receiving the user session data when the response information returns the user session data which agrees to send the corresponding ID;
the KPI assessment module connected with the database comprises:
the assessment index calculation module is used for receiving assessment indexes and a preset performance table of the database, matching the preset performance table through the assessment indexes, and converting the assessment indexes into performance indexes and outputting the performance indexes;
and the index recording module is used for inputting the assessment indexes to the database and sending the assessment indexes to the assessment index calculating module.
2. The artificial intelligence based customer service assistance real-time alerting system of claim 1, further comprising:
and the manual switching module is respectively connected with the intention identifier and the communication interface and is used for sending a message to the manual customer service through the communication interface when receiving a prompt that the intention identifier fails to identify the intention of the user, and reminding the manual customer service to access the communication tool of the user for conversation so as to answer the question of the client.
3. The artificial intelligence based customer service assistance real-time alerting system of claim 1, further comprising:
and the authority verification module is connected with the database and used for verifying the identity information of the user according to the identity information preset in the database.
4. The artificial intelligence based customer service assistance real-time alerting system of claim 1, further comprising:
and the head portrait matching module is respectively connected with the intention recognizer and the communication interface and is used for interacting with the communication interface of the user communication tool through the communication interface so as to acquire the head portrait information of the user and automatically reading, storing and displaying the head portrait information of the user.
5. The artificial intelligence based customer service assistance real-time alerting system of claim 1, further comprising:
and the automatic response system is respectively connected with the intention recognizer and the communication interface and is used for receiving the intention data of the user to generate corresponding response information and sending the response information to the communication interface of the user communication tool through the communication interface.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611142197.8A CN106790004B (en) | 2016-12-12 | 2016-12-12 | Customer service auxiliary real-time prompt system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611142197.8A CN106790004B (en) | 2016-12-12 | 2016-12-12 | Customer service auxiliary real-time prompt system based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106790004A CN106790004A (en) | 2017-05-31 |
| CN106790004B true CN106790004B (en) | 2021-02-02 |
Family
ID=58876127
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611142197.8A Active CN106790004B (en) | 2016-12-12 | 2016-12-12 | Customer service auxiliary real-time prompt system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106790004B (en) |
Families Citing this family (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107451274B (en) * | 2017-08-04 | 2020-11-27 | 上海优扬新媒信息技术有限公司 | Method, device and equipment for pushing auxiliary customer service information and storage medium |
| CN107645440A (en) * | 2017-08-18 | 2018-01-30 | 无锡雅座在线科技股份有限公司 | Information push method and device |
| CN107679868B (en) * | 2017-09-15 | 2020-02-21 | 平安科技（深圳）有限公司 | Rights and interests information management method, device and equipment and computer readable storage medium |
| CN108446322B (en) * | 2018-02-10 | 2022-03-25 | 灯塔财经信息有限公司 | Method and device for realizing intelligent question-answering system |
| CN110232573A (en) * | 2018-03-06 | 2019-09-13 | 广州供电局有限公司 | Based on interactive intelligent response system |
| CN108667713A (en) * | 2018-03-16 | 2018-10-16 | 平安科技（深圳）有限公司 | Public platform is attended a banquet overtime based reminding method, device, equipment and storage medium |
| CN108197963A (en) * | 2018-03-28 | 2018-06-22 | 广州市菲玛尔咨询服务有限公司 | A kind of intelligent customer service manages system |
| CN108537644A (en) * | 2018-04-23 | 2018-09-14 | 吉林亿联银行股份有限公司 | A kind of method and apparatus of customer service recommended products |
| CN108833722B (en) * | 2018-05-29 | 2021-05-11 | 平安科技（深圳）有限公司 | Speech recognition method, speech recognition device, computer equipment and storage medium |
| CN108881646B (en) * | 2018-05-30 | 2021-04-02 | 平安科技（深圳）有限公司 | Task tracking method, device, equipment and storage medium of call center |
| CN109710941A (en) * | 2018-12-29 | 2019-05-03 | 上海点融信息科技有限责任公司 | User's intension recognizing method and device based on artificial intelligence |
| CN109889677B (en) * | 2019-01-23 | 2021-01-26 | 广州市聚星源科技有限公司 | Intelligent customer service system with intelligent message processing function |
| CN111405129A (en) * | 2020-03-12 | 2020-07-10 | 中国建设银行股份有限公司 | Intelligent outbound risk monitoring method and device |
| CN112468387A (en) * | 2020-11-25 | 2021-03-09 | 银盛通信有限公司 | Template message sending method, computer equipment and computer storage medium |
| CN112911071B (en) * | 2021-01-15 | 2022-09-06 | 安徽迪科数金科技有限公司 | Auxiliary robot and intelligent auxiliary method |
| CN113393217A (en) * | 2021-07-05 | 2021-09-14 | 携程旅游网络技术（上海）有限公司 | Method, system, electronic device and medium for providing support by customer service assistance panel |
| CN113726964B (en) * | 2021-09-03 | 2023-06-30 | 中国银行股份有限公司 | Outbound processing method and device, storage medium and electronic equipment |
| CN116228252A (en) * | 2023-02-10 | 2023-06-06 | 广东盛迪嘉电子商务股份有限公司 | Background customer service terminal |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102082883A (en) * | 2009-11-27 | 2011-06-01 | 中兴通讯股份有限公司 | Method for customer service system to provide information for customers and customer service system |
| CN102866990A (en) * | 2012-08-20 | 2013-01-09 | 北京搜狗信息服务有限公司 | Thematic conversation method and device |
| CN103078995A (en) * | 2012-12-18 | 2013-05-01 | 苏州思必驰信息科技有限公司 | Customizable individualized response method and system used in mobile terminal |
| CN103198155A (en) * | 2013-04-27 | 2013-07-10 | 俞志晨 | Mobile terminal based smart question answering interaction system and method |
| CN105426436A (en) * | 2015-11-05 | 2016-03-23 | 百度在线网络技术（北京）有限公司 | Artificial intelligent robot based information provision method and apparatus |
| CN105515938A (en) * | 2014-09-24 | 2016-04-20 | 北京三星通信技术研究有限公司 | Communication information generating method and device |
| CN105681609A (en) * | 2014-11-20 | 2016-06-15 | 中兴通讯股份有限公司 | Assistance method and device for service center agent |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106202085B (en) * | 2015-04-30 | 2019-08-20 | 阿里巴巴集团控股有限公司 | The method, apparatus and electronic equipment of information search are carried out according to specific subject |
-
2016
- 2016-12-12 CN CN201611142197.8A patent/CN106790004B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102082883A (en) * | 2009-11-27 | 2011-06-01 | 中兴通讯股份有限公司 | Method for customer service system to provide information for customers and customer service system |
| CN102866990A (en) * | 2012-08-20 | 2013-01-09 | 北京搜狗信息服务有限公司 | Thematic conversation method and device |
| CN103078995A (en) * | 2012-12-18 | 2013-05-01 | 苏州思必驰信息科技有限公司 | Customizable individualized response method and system used in mobile terminal |
| CN103198155A (en) * | 2013-04-27 | 2013-07-10 | 俞志晨 | Mobile terminal based smart question answering interaction system and method |
| CN105515938A (en) * | 2014-09-24 | 2016-04-20 | 北京三星通信技术研究有限公司 | Communication information generating method and device |
| CN105681609A (en) * | 2014-11-20 | 2016-06-15 | 中兴通讯股份有限公司 | Assistance method and device for service center agent |
| CN105426436A (en) * | 2015-11-05 | 2016-03-23 | 百度在线网络技术（北京）有限公司 | Artificial intelligent robot based information provision method and apparatus |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106790004A (en) | 2017-05-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106790004B (en) | Customer service auxiliary real-time prompt system based on artificial intelligence | |
| US10142477B2 (en) | System and method for social message classification based on influence | |
| CN105095272B (en) | Question and answer processing method based on image recognition, apparatus and system | |
| CN107957992B (en) | Automatic processing method and system for user feedback information | |
| US9300482B2 (en) | Cross-channel conversations with context aware transition between channels | |
| CN105631022B (en) | Information processing method and device | |
| CN107153965A (en) | A kind of intelligent customer service solution of multiple terminals | |
| CN107784033B (en) | Method and device for recommending based on session | |
| CN105206269A (en) | Voice processing method and device | |
| CN109189898A (en) | A kind of intelligent response method and system | |
| CA2823835A1 (en) | Voice search and response based on relevancy | |
| CN112131358A (en) | Scene flow structure and intelligent customer service system applied by same | |
| CN110570215A (en) | Intelligent customer service system | |
| WO2020011043A1 (en) | Method, device and system for acquiring logistics object distribution information | |
| CN111429157A (en) | Method, device and equipment for evaluating and processing complaint work order and storage medium | |
| CN112925888A (en) | Method and device for training question-answer response and small sample text matching model | |
| WO2014089539A1 (en) | Cross-channel conversations with context aware transition between channels | |
| CN113051389B (en) | Knowledge pushing method and device | |
| CN110011898A (en) | Answering method, device, storage medium and the computer equipment of Email | |
| CN106791237A (en) | For consumers' opinions processing unit, the system and method for Utilities Electric Co. | |
| JP2014174938A (en) | Help desk support system | |
| US20230342864A1 (en) | System and method for automatically responding to negative content | |
| CN112860873A (en) | Intelligent response method, device and storage medium | |
| CN112163066A (en) | Artificial intelligence model training method, knowledge point pushing method, device and medium | |
| CN111046151A (en) | Message processing method and device |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |