CN108280095A - Intelligent virtual customer service system - Google Patents
Intelligent virtual customer service system Download PDFInfo
- Publication number
- CN108280095A CN108280095A CN201710010926.2A CN201710010926A CN108280095A CN 108280095 A CN108280095 A CN 108280095A CN 201710010926 A CN201710010926 A CN 201710010926A CN 108280095 A CN108280095 A CN 108280095A
- Authority
- CN
- China
- Prior art keywords
- customer service
- answer
- question
- customer
- intelligent virtual
- 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
Links
- 238000000034 method Methods 0.000 claims abstract description 35
- 230000004044 response Effects 0.000 claims abstract description 4
- 230000008569 process Effects 0.000 claims description 7
- 238000010801 machine learning Methods 0.000 claims description 5
- 238000004891 communication Methods 0.000 abstract description 3
- 230000007812 deficiency Effects 0.000 abstract description 3
- 230000007306 turnover Effects 0.000 abstract description 3
- 238000013515 script Methods 0.000 abstract description 2
- 238000013135 deep learning Methods 0.000 description 21
- 238000013528 artificial neural network Methods 0.000 description 17
- 238000005516 engineering process Methods 0.000 description 8
- 210000004556 brain Anatomy 0.000 description 5
- 238000012549 training Methods 0.000 description 5
- 238000013473 artificial intelligence Methods 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 4
- 238000011160 research Methods 0.000 description 4
- 238000013136 deep learning model Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000001537 neural effect Effects 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- RPNUMPOLZDHAAY-UHFFFAOYSA-N Diethylenetriamine Chemical compound NCCNCCN RPNUMPOLZDHAAY-UHFFFAOYSA-N 0.000 description 1
- 241000233805 Phoenix Species 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 210000004218 nerve net Anatomy 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- ZRHANBBTXQZFSP-UHFFFAOYSA-M potassium;4-amino-3,5,6-trichloropyridine-2-carboxylate Chemical compound [K+].NC1=C(Cl)C(Cl)=NC(C([O-])=O)=C1Cl ZRHANBBTXQZFSP-UHFFFAOYSA-M 0.000 description 1
- 230000035807 sensation Effects 0.000 description 1
- 238000002945 steepest descent method Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- 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
- G06Q30/01—Customer relationship services
- G06Q30/015—Providing customer assistance, e.g. assisting a customer within a business location or via helpdesk
- G06Q30/016—After-sales
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Mathematical Physics (AREA)
- Development Economics (AREA)
- Tourism & Hospitality (AREA)
- Human Resources & Organizations (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Human Computer Interaction (AREA)
- Primary Health Care (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Machine Translation (AREA)
Abstract
The present invention provides a kind of intelligent virtual customer service system, which is characterized in that including:Basic database stores common customer service question and answer;Common customer service question and answer in the basic database are carried out cutting word by keyword recognition module, and fuzzy matching provides the matching answer of single node question-response suggestiveness;Procedure service module, realization is interacted with the question and answer of customer, according to extracting corresponding answer the problem of customer from basic database, and repositions this position of question and answer node within a context.The intelligent virtual customer service system of the present invention solves existing artificial customer service, it is of high cost, management is difficult, turnover rate is big, and the problem of working time deficiency, the working efficiency for greatly improving customer service truly solves customer service by the communication flow setting of hommization guiding and needs a large amount of work for manually going to solve from consulting to transacting business to a series of scripts such as solution customer complaints.
Description
Technical field
The present invention relates to a kind of intelligent virtual customer service systems, belong to intelligent customer service field.
Background technology
Many studies have shown that in order to learn the complicated function of expression Higher Order Abstract concept, target identification, voice are solved
The relevant task of artificial intelligence such as perception and language understanding needs to introduce deep learning (deeplearning).Deep learning frame
Structure is made of multilayered nonlinear arithmetic element, the input of each lower level exported as higher, can be from a large amount of input numbers
According to the effective character representation of middle study, many structural informations that the high-order learnt include input data in indicating are one kind from
The good method that extracting data indicates can be used in the particular problems such as classification, recurrence and information retrieval.
The concept of deep learning originates from the research of artificial neural network, and the multilayer perceptron of multiple hidden layers is depth
Practise a good example of model.For neural network, depth refers to non-linear fortune in the function that e-learning obtains
Calculate the quantity of combined horizontal.The learning algorithm of Current Situation of Neural Network is the network structure for reduced levels, and this network is claimed
For shallow structure neural network, a such as input layer, a hidden layer and an output layer neural network;It in contrast, will be non-thread
Property the higher network of operation combined horizontal be known as depth structure neural network, such as an input layer, three hidden layers and one output
The neural network of layer.
Deep learning is practised than having superficial knowledge has stronger expression ability, and since the increase of depth makes non convex objective function produce
Raw locally optimal solution is the principal element for causing difficulty of learning.Backpropagation is declined based on partial gradient, random just from some
Initial point brings into operation, and is usually absorbed in local extremum, and deteriorate with the increase of network depth, cannot solve depth knot well
Structure neural network problem.2006, what Hinton et al. was proposed was used for depth trust network (deepbeliefnetwork, DBN)
Unsupervised learning algorithm, solve the problems, such as that deep learning model optimization is difficult.The core for solving DBN methods be it is greedy successively
Pre-training algorithm optimizes the weights of DBN on the time complexity linear with network size and depth, by the problem of solution points
Solution is solved as several simpler subproblems.After being delivered with initiative document, Bengio, Hinton,
The numerous studies personnel such as Jarrett, Larochelle, Lee, Ranza, Salakhutdinov, Taylor and Vincent are to depth
Degree study is conducted extensive research to improve and apply depth learning technology.Bengio and Ranzato et al. propose no prison
Educational inspector practises the idea of each layer of neural network of initialization;Erhan et al. trials understand that unsupervised learning plays deep learning process
The reason of help;The reason of original training process failure of Glorot et al. the depth of investigation artificial neurals.Many is ground
Deep learning and its application in field of signal processing can be devoted to by begging for.Document has carried out deep learning more comprehensive comprehensive
It states, proposes that greedy successively pre-training learning process is used to initialize the parameter of deep learning model based on unsupervised learning technology,
Every layer of neural network is trained to form the expression of input, after unsupervised initialization, each layer neural network of storehouse since bottom
Depth supervision feedforward neural network is converted to, is finely adjusted with gradient decline.Learning method for deep learning is mainly concentrated
In the useful expression of learning data, make in neural network higher level study to feature do not change with the factor of variation, it is right
Sudden change in real data has stronger robustness.Document gives the related art of trained deep learning model, especially
It is limited Boltzmann machine (restricted Boltzmannmachine, RBM), and many is thought from neural metwork training
Method can be used for depth structure neural network learning.Bengio is given in the literature for variety classes depth structure nerve
The instruction of the training method of network.Deep learning method has been employed successfully in text data learning tasks and visual identity
In task.In view of the theory significance and actual application value of deep learning, the country has still been in step to the research of depth structure
Section, the document that this respect has been delivered is relatively fewer and is mostly to lay particular emphasis on application field.Further to further investigate depth
It practises theoretical its application field with expansion and has established certain basis.
Parallel distributed deep learning platform:
1. since the high dimensional data of magnanimity needs the great model of scale matching, model and data can only be distributed
It is stored on a large amount of points likes.
2. in spite of the data of magnanimity, but due to the sparsity of data, over-fitting is still to need asking for vigilant
Topic.
3. parallel distributed deep learning platform pair need simultaneously the scene of dense matrix operation and sparse matrix operation into
Optimization is gone.
Of greatest concern in artificial intelligence field in recent years, non-deep learning does not belong to.From Ji Aofuleixindun in 2006
(Geoffery Hinton) etc. exists《Science》(Science) magazine is delivered that famous paper and is started, the upsurge of deep learning
It is swept across from academia to industrial quarters.In June, 2012,《The New York Times》" Google's brain (Google the Brain) " project of disclosure,
By famous Stanford University machine learning professor Wu Enda (Andrew Ng) and the top expert in the Large Scale Computer System world
Jeff's Dien (Jeff Dean) is jointly leading, and deep neural network is trained with the parallel computing platform of 1.6 ten thousand CPU cores
The machine learning model of (Deep Neural Networks, DNN) obtains immense success in the fields such as voice and image recognition.
Domestic aspect, in January, 2013, Baidu set up deep learning research institute, and company CEO Li Yan are macro to serve as president.It is short
Two years, depth learning technology are applied to the phoenix nest ad system of Baidu, Webpage search, phonetic search, image recognition etc.
Tens products are covered in field.Today, almost each service request of the user on Baidu's platform, all by deep learning system
It is handled.
One of feature of artificial intelligence be study ability, i.e., the performance of system whether can with the accumulation of empirical data and
Constantly promoted.So the arrival in big data epoch provides unprecedented opportunities to the development of artificial intelligence.It is carried on the back in this epoch
Under scape, deep learning is not accidental including the breakthrough acquired by image recognition etc..
1) from the point of view of statistics and calculating, deep learning is particularly suitable for processing big data.
2) deep learning is not a Black smoker.It as probabilistic model, provide it is a set of it is abundant, based on connection master
The modeling language (modeling framework) of justice
3) the almost unique end-to-end machine learning system of deep learning.
Big data technology:
With the arriving of cloud era, big data (Big data) technology is commonly used to describe that a company creates a large amount of non-
Structural data and semi-structured data, these data are downloading to relevant database for meeting overspending time when analyzing
And money.Big data analysis is often linked together with cloud computing, because large data set analysis is needed as MapReduce in real time
The same frame shares out the work to tens of, hundreds of or even thousands of computer.Big data needs special technology, with effectively
The a large amount of tolerance of processing is by the data in the time.Suitable for the technology of big data, including MPP (MPP) data
Library, data mining power grid, distributed file system, distributed data base, cloud computing platform, internet and expansible storage system
System.
BP human brain logic neurals:
BP (Back Propagation) neural network is 1986 by the science headed by Rumelhart and McCelland
Group of family proposes, is a kind of Multi-layered Feedforward Networks trained by Back Propagation Algorithm, is current most widely used nerve net
One of network model.BP networks can learn and store a large amount of input-output mode map relationship, this is described without disclosing in advance
The math equation of kind mapping relations.Its learning rules are to use steepest descent method, and constantly network is adjusted by backpropagation
Weights and threshold value, keep the error sum of squares of network minimum.BP neural network model topology structure include input layer (input),
Hidden layer (hidden layer) and output layer (output layer).
Existing artificial customer service, there is of high cost, management is difficult, and turnover rate is big and the problem of working time deficiency, greatly
The big working efficiency for improving customer service.
Existing virtual customer service system, there is problems with:
1. needing constantly setting keyword, Client Work amount huge heavy
2. account team coupled system work even high-tech JAVA engineer is needed to support
3. deployment is slow, non intelligentization system, completed by conventional code formula, change flow is complicated, reaches the standard grade 6-8 months, configuration
System weight.
4. can not standardize, of high cost, the FAQ that the service that can not be provided for medium-sized and small enterprises can only carry out simple question-response is searched
Cable-styled answer, can not carry out logically flow scheme design, no context contact, stiff experience, can not positive true solution determine user demand.
5. cannot achieve the unified platform, each channel needs to establish single self-control robot and self contained data base.
Invention content
The purpose of the present invention is to provide a kind of intelligent virtual customer service systems, to solve the above problems.
Present invention employs following technical solutions:
A kind of intelligent virtual customer service system, which is characterized in that including:Basic database stores common customer service question and answer;It closes
Common customer service question and answer in the basic database are carried out cutting word by key word identification module, and fuzzy matching provides single node one and asks
One answers suggestiveness matching answer;Procedure service module, realization interacted with the question and answer of customer, according to the problem of customer from basic number
According to extracting corresponding answer in library, and reposition this position of question and answer node within a context.
Further, intelligent virtual customer service system of the invention, can also have the feature that:Wherein, the procedure
Service module uses tree architecture.
Further, intelligent virtual customer service system of the invention, can also have the feature that:When procedure service module
When encountering the problem of existing procedure can not be handled, the artificial customer service of system access, at this time by the question and answer of artificial customer service and customer with text
Font formula preserves, for machine learning.
Further, intelligent virtual customer service system of the invention, can also have the feature that:When needing to introduce new industry
When business, new question and answer are introduced into basic database, keyword module carries out cutting word to new question and answer, and is trained.
Further, intelligent virtual customer service system of the invention, can also have the feature that:Wherein, the procedure
Have in service module and be oriented to arrangement module, the priority of new business keyword is improved, makes it in the question and answer mistake of whole system
The frequency occurred in journey improves.
Further, intelligent virtual customer service system of the invention, can also have the feature that:Wherein, it is taken in procedure
In module of being engaged in, also have and greet module, starts to access in system and talk with, terminate this dialogue, and in dialog procedure, actively
It is played to customer and greets term.
Further, intelligent virtual customer service system of the invention, can also have the feature that:Wherein, the procedure
Question and answer node in service module and dynamic connection to database.
Advantageous effect of the invention
The intelligent virtual customer service system of the present invention solves existing artificial customer service, of high cost, and management is difficult, and turnover rate is big, and
The problem of working time deficiency, greatly improves the working efficiency of customer service, real by the communication flow setting of hommization guiding
Solution customer service needs largely manually to go solution from consulting to transacting business to a series of scripts such as solution customer complaints in meaning
Work, and realize 7*24H*365 seamless link Formula IV P free of discontinuities services be enterprise save expenditure in terms of huge customer service and
Working efficiency is significantly increased, services more clients to improve the business revenue of enterprise.
Description of the drawings
Fig. 1 is the structure diagram of the intelligent virtual customer service system of the present invention;
Fig. 2 is the question and answer relationship flow chart of the intelligent virtual customer service system of the present invention;
Fig. 3 is that the intelligent virtual customer service system of the present invention adds new question and answer and optimizes the flow chart of question and answer.
Specific implementation mode
Illustrate the specific implementation mode of the present invention below in conjunction with attached drawing.
As shown in Figure 1, possessing unique tree architecture realizes the identification of the contexts such as client context, and it can realize the man-machine of smoothness
Communicative mode, which allows client's fundamental sensation not go out, to be linked up with robot.
Bottom is keyword recognition layer, including basic database 11 and keyword recognition module 12, wherein being the big of client
FAQ (frequently asked question and common problem) is measured, by the method for keyword recognition, cutting word is granulated and fuzzy matching provides single node
Question-response suggestiveness matches answer.
The second layer is procedure SOP layers 13, or is voyage service module, according to the conventional normalised customer service flow of industry
And words art, preliminary flow services module is established, and connect dynamic data base in each flow nodes, realizes guiding ditch
Logical scene.
Principle is to simulate the method for thinking of human brain logic, realizes logical formula hierarchy, unique tree architecture so that on
It is hereafter associated with so that client can carry out the usual communication of context in arbitrary scene, and can carry out the transacting business of special scenes.
Utilize tree architecture, the scene of implementation process formula transacting business.According to different clients data or knowledge base selection stream
Journey meets the application target that enterprise is experienced again.
Natural language intelligent interaction simulates the netted chart database of language of human brain, reaches and is nowadays generally difficult to meet
High-tech reasoning from logic, substantially increase language message interaction functional efficiency.
It greets module and stores common greeting, customer is greeted in the respective cases.
As shown in Fig. 2, providing a kind of dialogue using this intelligent virtual customer service system and customer:
Step S1 accesses customer, for example is accessed by network forum or other chat tools,.According to client's
Problem, into corresponding step, if such as customer requirement:I wants to apply for wechat robot.Then enter step S2.
If customer requirement:I mutually learns about wechat robot, then enters step S4.
Step S2, intelligent virtual customer service system are analyzed to obtain the requirement of client:Client wants to apply for that wechat robot, customer service return
It answers:You have opened wechat public's account now
As client answers:Yes, wechat account has been opened.Then enter step S3
Step S3, customer service are responded, and good, that woulds you please first log in the client of your wechat public's account.
Step S4, customer service are responded:Wechat robot can have application in many industries, including pre-sales, after sale etc., it may I ask you
Company be in what industry
Step S5, if customer requirement:Wonder how to allow robot learning.Then enter step S6.
Step S6, customer service are responded:Study preferably use client-side program, but can also by directly with wechat machine
People talks with that him is taught to answer a question.
Step S7 enters step S4 if client can not answer, and briefly introduces wechat robot and proposes that inductivity is asked
Topic.Customer service is responded:Wechat robot can have application in many industries, including pre-sales, after sale etc., the company that may I ask you is assorted
Industry
After step S1, step S4 and step S7, if client requires application wechat in any step, enter step
S2。
The customer service system of the present invention has continuous self-optimization system and flexible improved system:As shown in figure 3,
Customer accesses robot customer platforms one is by web forums etc. by three kinds of forms, one is by wechat,
One is by having APP by oneself.
The step S201 of intelligent customer service is carried out after customer's access system.
If occurring the problem of existing procedure can not be handled in step s 201, S203 is entered step, manually using PC visitors
Family end carries out customer service;Or step S204, manually customer service is carried out using mobile clients such as wechat or APP.
Step S205 carries out step S205 after artificial customer service, and machine learning is right using the question and answer of artificial customer service
Intelligent virtual customer service system is trained.
When either S207 proposes that new marketing plan or business change to generation step S206, step S208 is carried out, into
Enter the operating process of customer service chief inspector, carries out step S209.
Step S209, customer service chief inspector carry out the design of business process improving, are then input in intelligent virtual customer service system,
It is trained.
Step S210, intelligent virtual customer service system analyze the customer action and feedback of existing procedure, result are returned to visitor
Take chief inspector.
It the above is only an example simple examples.
Table 1:The feature difference and advantage of the present invention and other systems:
Advantage of the present invention:
1. it is not necessary that keyword is arranged, a key imports FAQ and can answer.
It is supported without IT professionals 2. corporate client is used
3. deployment is fast, maturing intellectualizing system, reach the standard grade within 3-4 months, system is light, and configuration requirement is simple
4. small cost standardised system can be made, service can be provided using saas patterns as medium-sized and small enterprises
5. simple customer is needed to be arranged, you can complete the customer service flow of various complexity, logicality, experience sense is good, really solution
Certainly user demand.
6. can realize that the unified platform manages by all kinds of means, and sync database.
7. using showing that the present invention saves cost 70% after 10 years costs of system of the present invention and traditional artificial cost calculation
More than.
Claims (7)
1. a kind of intelligent virtual customer service system, which is characterized in that including:
Basic database stores common customer service question and answer;
Common customer service question and answer in the basic database are carried out cutting word by keyword recognition module, and fuzzy matching provides single-unit
Point question-response suggestiveness matches answer;
Procedure service module, realization are interacted with the question and answer of customer, are corresponded to according to being extracted from basic database the problem of customer
Answer, and reposition this position of question and answer node within a context.
2. intelligent virtual customer service system as described in claim 1, it is characterised in that:
Wherein, the procedure service module uses tree architecture.
3. intelligent virtual customer service system as described in claim 1, it is characterised in that:
When procedure service module encounters the problem of existing procedure can not be handled, the artificial customer service of system access at this time will be artificial
The question and answer of customer service and customer are preserved with written form, for machine learning.
4. intelligent virtual customer service system as described in claim 1, it is characterised in that:
When needing to introduce new business, new question and answer are introduced into basic database, keyword module carries out new question and answer
Cutting word, and be trained.
5. intelligent virtual customer service system as claimed in claim 4, it is characterised in that:
Wherein, have in the procedure service module and be oriented to arrangement module, the priority of new business keyword is improved, it is made
The frequency occurred in the question answering process of whole system improves.
6. the micro- customer service system of intelligent virtual as claimed in claim 5, it is characterised in that:
Wherein, in procedure service module, also have and greet module, start to access in system and talk with, terminate this dialogue, with
And in dialog procedure, is actively played to customer and greet term.
7. the micro- customer service system of intelligent virtual as described in claim 1, it is characterised in that:
Wherein, the question and answer node and dynamic connection to database in the procedure service module.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710010926.2A CN108280095A (en) | 2017-01-06 | 2017-01-06 | Intelligent virtual customer service system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710010926.2A CN108280095A (en) | 2017-01-06 | 2017-01-06 | Intelligent virtual customer service system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108280095A true CN108280095A (en) | 2018-07-13 |
Family
ID=62799135
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710010926.2A Pending CN108280095A (en) | 2017-01-06 | 2017-01-06 | Intelligent virtual customer service system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108280095A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111061852A (en) * | 2019-12-13 | 2020-04-24 | 上海中通吉网络技术有限公司 | Data processing method, device and system |
CN111444729A (en) * | 2020-03-02 | 2020-07-24 | 平安国际智慧城市科技股份有限公司 | Information processing method, device, equipment and readable storage medium |
CN115118689A (en) * | 2022-06-30 | 2022-09-27 | 哈尔滨工业大学(威海) | Method for building intelligent customer service marketing robot in specific field |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104809197A (en) * | 2015-04-24 | 2015-07-29 | 同程网络科技股份有限公司 | On-line question and answer method based on intelligent robot |
-
2017
- 2017-01-06 CN CN201710010926.2A patent/CN108280095A/en active Pending
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104809197A (en) * | 2015-04-24 | 2015-07-29 | 同程网络科技股份有限公司 | On-line question and answer method based on intelligent robot |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111061852A (en) * | 2019-12-13 | 2020-04-24 | 上海中通吉网络技术有限公司 | Data processing method, device and system |
CN111444729A (en) * | 2020-03-02 | 2020-07-24 | 平安国际智慧城市科技股份有限公司 | Information processing method, device, equipment and readable storage medium |
CN111444729B (en) * | 2020-03-02 | 2024-05-24 | 平安国际智慧城市科技股份有限公司 | Information processing method, device, equipment and readable storage medium |
CN115118689A (en) * | 2022-06-30 | 2022-09-27 | 哈尔滨工业大学(威海) | Method for building intelligent customer service marketing robot in specific field |
CN115118689B (en) * | 2022-06-30 | 2024-04-23 | 哈尔滨工业大学(威海) | Construction method of intelligent customer service marketing robot in specific field |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Peters et al. | Critical philosophy of the postdigital | |
CN108280521A (en) | Intelligent robot service system | |
CN111444709B (en) | Text classification method, device, storage medium and equipment | |
CN107368468B (en) | Operation and maintenance knowledge map generation method and system | |
CN108536681A (en) | Intelligent answer method, apparatus, equipment and storage medium based on sentiment analysis | |
CN113408284A (en) | Training method and device of text processing model, electronic equipment and storage medium | |
CN114330510A (en) | Model training method and device, electronic equipment and storage medium | |
CN108280095A (en) | Intelligent virtual customer service system | |
Huang et al. | Intangible cultural heritage management using machine learning model: a case study of Northwest Folk Song Huaer | |
Chempavathy et al. | Ai based chatbots using deep neural networks in education | |
Tredinnick | Complexity theory and the web | |
Yu | Analysis of task degree of English learning based on deep learning framework and image target recognition | |
Sirbu et al. | ReaderBench: building comprehensive sociograms of online communities | |
Yadav et al. | An Empirical Study of Design Techniques of Chatbot, a Review | |
CN112966084B (en) | Knowledge graph-based answer query method, device, equipment and storage medium | |
Ding et al. | Constructing a Knowledge Graph for the Chinese Subject Based on Collective Intelligence | |
CN112052320A (en) | Information processing method and device and computer readable storage medium | |
CN113392220A (en) | Knowledge graph generation method and device, computer equipment and storage medium | |
Xie | Evaluation of Multimedia Classroom Teaching Effectiveness Based on RS‐BP Neural Network | |
Chiu et al. | Statistical discourse analysis | |
Ferri et al. | Computational Models of Language Evolution: Challenges and Future Perspectives. | |
Wang et al. | Complex Continuous Action Iterated Dilemma With Incremental Dynamic Model | |
Samad et al. | USE OF MODERN INFORMATION TECHNOLOGY FOR PREFORMING OF OBSERVATION OF SOCIAL PROCESS AT THE UNIVERSITY | |
Aranda-Corral et al. | Simulating language dynamics by means of concept reasoning | |
Reitter et al. | Did social networks shape language evolution? A Multi-Agent Cognitive Simulation |
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 | ||
TA01 | Transfer of patent application right | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20200927 Address after: Room 2087, No. 100, Lane 130, Taopu Road, Putuo District, Shanghai Applicant after: Jingpu (Shanghai) Artificial Intelligence Technology Co.,Ltd. Address before: 226000 Jiangsu city of Nantong province No. 2 Building 1 room 110494 Hyde Applicant before: NANTONG SHIAI INTELLIGENT TECHNOLOGY Co.,Ltd. |
|
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180713 |