CN106227779A - A kind of man-machine interaction method of customer service system - Google Patents
A kind of man-machine interaction method of customer service system Download PDFInfo
- Publication number
- CN106227779A CN106227779A CN201610565248.1A CN201610565248A CN106227779A CN 106227779 A CN106227779 A CN 106227779A CN 201610565248 A CN201610565248 A CN 201610565248A CN 106227779 A CN106227779 A CN 106227779A
- Authority
- CN
- China
- Prior art keywords
- user
- customer service
- service system
- faq
- man
- 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
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
- G06Q30/015—Providing customer assistance, e.g. assisting a customer within a business location or via helpdesk
- G06Q30/016—After-sales
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Marketing (AREA)
- Human Computer Interaction (AREA)
- General Business, Economics & Management (AREA)
- Finance (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Artificial Intelligence (AREA)
- Strategic Management (AREA)
- Accounting & Taxation (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
The present invention relates to the man-machine interaction method of a kind of customer service system, the method includes: user proposes problem, waits that customer service system is answered a question;Reply answer interface in customer service system, increase the button representing the satisfied and dissatisfied feedback of user, invite user to feed back answering whether to be satisfied with;After user clicks on satisfied or dissatisfied button, customer service system backstage receives feedback, then by another candidate frequently asked questions and corresponding answer FAQ, be again pushed to user;Customer service system replies still can be to user's satisfaction or unsatisfied Evaluation and Selection, and user continues to evaluate;This process repeatedly, terminates circulation after reaching end condition;After termination, if user still evaluates dissatisfied, return again to acquiescence and reply, terminate the understanding to active user's question sentence, guess and answer.The present invention carrys out the interception rate of hoisting machine people's customer service from man-machine interaction angle, and on the one hand this exchange method improves Consumer's Experience, on the one hand can promote interception rate, reduce the cost of artificial customer service.
Description
Technical field
The present invention relates to man-machine interaction method, be specifically related to the man-machine interaction method of a kind of customer service system.
Background technology
Enterprise's customer service is the important means that enterprise carries out network marketing, technical support, after-sale service.Divide according to channel,
Comprise phone customer service, video customer service, IM customer service.Divide according to the carrier of customer service, artificial customer service and customer service system can be divided into
System.Wherein artificial customer service needs substantial amounts of customer service to attend a banquet and complicated calling system, relatively costly.Customer service system is sent out recent years
Exhibition is rapid, bright for FAQ (Frequently Asked Questions, the problem often asked) type answer aspect advantage
Aobvious, the work of artificial customer service can be replaced wholly or in part, a large amount of costs reducing artificial customer service.
Customer service system is not limited to the channel of above-mentioned instant messaging form, in channel forms such as phone customer service and video customer services
In, use the technology such as audio/video coding, decoding, phonetic synthesis, animation compound, customer service system can be applied.
Customer service system common practices is the mode using search.First FAQ storehouse is indexed.Such as to following FAQ storehouse
Question and Answer, through word segmentation processing, builds text index:
Q: what if forget Password?
A: select " ... "-> payment management-> forget payment cipher-> selection bank card in the upper right corner-> fill according to prompting
Relevant information-> reset password.
Q: how new password is set?
A: select " ... the "-> payment management-> amendment payment cipher-> input Old Password-> input new password in the upper right corner i.e.
Can.
Run into user put question to when, user's question sentence is understood, then retrieval obtains FAQ sequence of giving a mark,
FAQ closest to user's question sentence is presented to user at last, at this moment has three kinds of situations and a result:
(1st) plants situation, directly answers user, and answers correct;
(2nd) plants situation, because Query understands unsuccessfully, the most high reason of confidence level of giving a mark, returns the answer of acquiescence;
(3rd) plants situation, directly answers, but erroneous answers.
In general approach, all use the methods such as synonym extension, core word extraction, complete Query and understand and and FAQ
Similarity mode.The most useful sophisticated method, such as LSA (latent semantic analysis), Word2Vec (term vector method), LDA, deep
The machine learning methods such as degree study carry out Query and understand and FAQ Similarity Measure.But due to training sample limited (because
The language of people is very difficult exhaustive), it is the most accurate still can not to accomplish unknown subscriber's question sentence.
Understand due to Query and similarity mode can not reach perfect so that faced by customer service system during unknown subscriber's question sentence,
(2nd), (3) kind situation can exist all the time, and the question sentence of erroneous answers the most also can erroneous answers.Even if use LDA, LSA,
The sophisticated method such as Word2Vec, degree of depth study, limited also by the quantity of the corpus that can obtain, it is impossible to accomplish persistently to learn
Practise.
Replace artificial customer service with machine customer service the most completely, and the effect reaching artificial customer service is also difficult to, typically at machine
The when that device people's customer service can not solving customer problem, can be obvious by order (such as " turning artificial ") or one to user one
Button is switched to the chance of artificial customer service.At this moment machine customer service is taken in artificial customer service, continues answer customer problem.Have one among these
The problem of individual interception rate, i.e. robot customer service can intercept the customer problem of how many ratios, and user has obtained Resolving probiems, no
Artificial customer service can be proceeded to.Intercepting the important indicator of Shuai Shi robot customer service, interception rate is the biggest, the efficiency of robot customer service is described more
High.
Summary of the invention
For solving above-mentioned deficiency of the prior art, it is an object of the invention to provide the man-machine interaction side of a kind of customer service system
Method, this exchange method walks around the optimization of above-mentioned algorithm aspect, carrys out the interception rate of hoisting machine people's customer service from man-machine interaction angle, this
Plant interactive mode and on the one hand improve Consumer's Experience, on the one hand can promote interception rate, reduce the cost of artificial customer service.
It is an object of the invention to use following technical proposals to realize:
The present invention provides the man-machine interaction method of a kind of customer service system, described method to utilize the feedback of user, knows current
Answering and whether solve problem, to an open question, other candidates are answered and are presented to user one by one by customer service system so that user
One corresponding multiple answer of problem, improves problem fix rate;Described method comprises the steps:
(1) user proposes problem, waits that customer service system is answered a question;
(2) reply answer interface in customer service system, increase the button representing the satisfied and dissatisfied feedback of user, invite user
Feed back answering whether to be satisfied with;
(3) after user clicks on satisfied or dissatisfied button, customer service system backstage receives feedback, then by normal for another candidate
See answer FAQ, be again pushed to user;
(4) customer service system replies and still can continue evaluation to user's satisfaction or unsatisfied Evaluation and Selection, user;
(5) this process is repeatedly, terminates circulation after reaching end condition;
(6) after terminating, if user still evaluates dissatisfied, return again to acquiescence and reply, terminate active user's question sentence
Understand, guess and answer.
Further, in described step (2), the button of the satisfied and dissatisfied feedback of described user replaces with praising, step on word,
Or with √, × symbol replace, or with thumb upwards, the downward gesture of thumb replace.
Further, in described step (3), after customer problem is input to customer service system, customer service system backstage is to common
Answer FAQ set is retrieved and sorts;
The frequently asked questions and corresponding answer FAQ of sequence first is returned to user;If the frequently asked questions and corresponding answer FAQ of sequence first is not
Can meet user when answering, it is dissatisfied that user clicks on feedback, then customer service system is by automatic for the frequently asked questions and corresponding answer FAQ of sequence second
It is pushed to user;If feedback is dissatisfied the most again, then the frequently asked questions and corresponding answer FAQ of sequence the 3rd is pushed user;Follow-up
Order pushes successively.
Further, according to marking sequence or described sequence is carried out according to frequently asked questions and corresponding answer FAQ history temperature mode.
Further, in described step (5), described end condition includes: run into that user feedback is satisfied, it is dissatisfied not feed back
Leave, candidate frequently asked questions and corresponding answer FAQ uses up or has reached number of times and limits, then terminate pushing successively;Or ask candidate is common
The key to exercises is answered FAQ and is terminated less than the when of threshold value with user's question sentence degree of association, proceeds to step (6).
Further, described customer service system includes the customer service system of instant messaging channel, phone customer service and video customer service shape
Formula.
Further, described phone customer service uses and adds the realization of telephone key-press way of act, and described video customer service uses and adds
Enter the button on visual interface, or by speech recognition technology and Gesture Recognition, obtain user's interaction feedback, and then optimize
Customer service effect.
In order to some aspects of the embodiment disclosed are had a basic understanding, shown below is simple summary.Should
Summarized section is not extensive overview, is not key/critical component to be determined or the protection domain describing these embodiments.
Its sole purpose is to present some concepts, in this, as the preamble of following detailed description by simple form.
Compared with immediate prior art, the excellent effect that the technical scheme that the present invention provides has is:
(1) promote Consumer's Experience, do not allow user feel frosty.
(2) it is no longer that single guesses user view, repeatedly guesses user view so that problem fix rate is greatly improved.Special
It not that the intention being difficult to the question sentence with technological means solution understands.
(3) scheme that candidate's answer pushes successively can improve problem fix rate;
(4) present invention understands for convenience, uses the robot customer service of instant messaging channel, but is not limiting as this side
Case is applied to other channel forms such as phone customer service, video customer service.As long as adding telephone key-press behavior, adding on visual interface
Button, or by the technology such as speech recognition, gesture identification, equally can obtain user's interaction feedback, and then optimize customer service effect
Really.
(5) it is that effect optimization have accumulated a large amount of forward sample and negative sense sample.
For above-mentioned and relevant purpose, one or more embodiments include will be explained in below and in claim
In the feature that particularly points out.Description below and accompanying drawing describe some illustrative aspects in detail, and its instruction is only
Some modes in the utilizable various modes of principle of each embodiment.Other benefit and novel features will along with under
The detailed description in face is considered in conjunction with the accompanying and becomes obvious, the disclosed embodiments be intended to include all these aspect and they
Equivalent.
Accompanying drawing explanation
Fig. 1 is the schematic diagram of a kind of interactive mode of the specific embodiment that the present invention provides;
Fig. 2 is the schematic diagram one sorted that FAQ set is retrieved and given a mark that the present invention provides;
Fig. 3 is the schematic diagram two sorted that FAQ set is retrieved and given a mark that the present invention provides;
Fig. 4 is the schematic diagram three sorted that FAQ set is retrieved and given a mark that the present invention provides;
Fig. 5 is the overall flow figure of the man-machine interaction method of the customer service system that the present invention provides.
Detailed description of the invention
Below in conjunction with the accompanying drawings the detailed description of the invention of the present invention is described in further detail.
The following description and drawings illustrate specific embodiments of the present invention fully, to enable those skilled in the art to
Put into practice them.Other embodiments can include structure, logic, electric, process and other change.Embodiment
Only represent possible change.Unless explicitly requested, otherwise individually assembly and function are optional, and the order operated is permissible
Change.The part of some embodiments and feature can be included in or replace part and the feature of other embodiments.This
The scope of bright embodiment includes the gamut of claims, and all obtainable equivalent of claims
Thing.In this article, these embodiments of the present invention can be represented by " inventing " individually or generally with term, and this is only
For convenience, and if in fact disclose the invention more than, it is not meant to automatically limit this application in the range of appointing
What single invention or inventive concept.
The present invention proposes the man-machine interaction method of a kind of customer service system, and on the one hand this exchange method improves Consumer's Experience,
On the one hand the lasts optimization of question answering system can be supported.
The present invention provides the man-machine interaction method of a kind of customer service system, described method to utilize the feedback of user, knows current
Answering and whether solve problem, to an open question, other candidates are answered and are presented to user one by one by customer service system so that user
One corresponding multiple answer of problem, improves problem fix rate;Described method comprises the steps:
(1) user proposes problem, waits that customer service system is answered a question;
(2) present invention proposes, reply near answer in customer service, increases and represents user and " be satisfied with " and " being unsatisfied with " feeds back
Whether button, invite user to feed back answering to be satisfied with.User is invited to feed back answering whether to be satisfied with;The present invention program
It is not limited to its form, can replace with words such as<" praising " " stepping on ">, it is also possible to replace with symbols such as " √ " "×".
(3) after user clicks on satisfied or dissatisfied button, customer service system backstage receives feedback, then by normal for another candidate
See answer FAQ, be again pushed to user;
(4) customer service system replies and still can continue evaluation to user's satisfaction or unsatisfied Evaluation and Selection, user;
(5) this process is repeatedly, terminates circulation after reaching end condition;
(6) after terminating, if user still evaluates dissatisfied, return again to acquiescence and reply, terminate active user's question sentence
Understand, guess and answer.
After user clicks on " satisfaction " or " being unsatisfied with ", backstage receives feedback, then answered by another " candidate FAQ ", then
Secondary it is pushed to user.This answer " is satisfied with " Evaluation and Selection of " being unsatisfied with " still can to user, and user can continue to evaluate.This
Process repeatedly can run into user and click on " satisfaction " or do not terminate when clicking on " being unsatisfied with ".If user's point repeatedly
Hit " being unsatisfied with ", can terminate reaching certain number of times upper limit when, it is also possible at " candidate FAQ " and user's question sentence degree of association
Terminate less than the when of certain threshold value.After termination, if user still evaluates " being unsatisfied with ", return again to acquiescence and reply (such as " machine
Device people cannot understand your problem, and you could change a way to put questions."), terminate the understanding of active user's question sentence, guess, answer.
In Fig. 1 example, user asks " password that I disregards ", and " how Modify password " is replied in robot customer service for the first time, nothing
Method solves customer problem.After user clicks on " being unsatisfied with ", robot customer service second time replies and " what if forgets Password?", this time
Answer and can solve the problem that customer problem.Now user clicks on " satisfaction " or does not click on any feedback, and robot thinks that customer problem solves
Certainly.
A kind of interactive mode is, in second time and subsequent represent, " sorry, I guesses that you think in fact to add a prompting
That ask is ' XXXXX ' ".The interactive mode of the present invention, the reminding method comprised, including but not limited to the literary style of above-mentioned prompting,
In general, in step (3), when customer problem is input to robot customer service, the backstage of robot can be to FAQ collection
Conjunction carries out sequence of retrieving and give a mark, as in Figure 2-4.
The FAQ of ranking higher (or marking is higher than certain threshold value) is that candidate answers.Generally, all can be by ranking
The answer of the FAQ of first returns to user.
But general user is to ask a question by colloquial natural language question sentence form, simultaneously because input method error tape
The mistake entered is write so that robot customer service sometimes can not by maximally related FAQ marking the highest, it is possible to come second place even after
Face.Even so, the FAQ that generally dependency is high comes the probability of top and is higher than the FAQs solution that dependency is low
Answer FAQ.
In the present invention, if the FAQ of sequence first answers can not meet user when answering, user clicks on feedback and " is discontented with
Meaning ", then the FAQ of sequence second is answered and is automatically pushed to user by robot customer service.If feedback " being unsatisfied with " the most again, then
The FAQ of sequence the 3rd is pushed user.Follow-up order successively pushes, until user feedback " is satisfied with " or does not feeds back " being unsatisfied with "
Leave or candidate FAQ use up or reached number of times and limits, then terminate pushing successively, return user with acquiescence answer,
Terminate above-mentioned circulation.
(1) place in Fig. 5, ranking results of<User (i), Question (j)>and FAQ being given a mark is stored in User Status storehouse,
And the state having selected FAQ1 is set to Y, other be set to N.
(2) place in Fig. 5, by the FAQ marking sequence of the correspondence<User (i), Question (j)>of storage in User Status storehouse
Result reads, and selects one and does not represents FAQ, and the state of this FAQ is set to Y, writes back User Status storehouse.
(3) place in Fig. 5, is to the continuous circulation of right side flow process in figure.
The present invention understands for convenience, uses the robot customer service of instant messaging channel, but is not limiting as this scheme
It is applied to other channel forms such as phone customer service, video customer service.As long as adding telephone key-press behavior, adding pressing on visual interface
Button, or by the technology such as speech recognition, gesture identification, equally can obtain user's interaction feedback, and then optimize customer service effect.
Above example is only in order to illustrate that technical scheme is not intended to limit, although with reference to above-described embodiment pair
The present invention has been described in detail, and the detailed description of the invention of the present invention still can be entered by those of ordinary skill in the field
Row amendment or equivalent, these are without departing from any amendment of spirit and scope of the invention or equivalent, all in application
Within the claims of the present invention awaited the reply.
Claims (7)
1. the man-machine interaction method of a customer service system, it is characterised in that described method utilizes the feedback of user, knows current returning
Answering and whether solve problem, to an open question, other candidates are answered and are presented to user one by one by customer service system so that Yong Huyi
The corresponding multiple answer of individual problem, improves problem fix rate;Described method comprises the steps:
(1) user proposes problem, waits that customer service system is answered a question;
(2) reply answer interface in customer service system, increase the button representing the satisfied and dissatisfied feedback of user, invite user to returning
Answer whether to be satisfied with and feed back;
(3) after user clicks on satisfied or dissatisfied button, customer service system backstage receives feedback, then ask common for another candidate
FAQ answered in the key to exercises, is again pushed to user;
(4) customer service system replies and still can continue evaluation to user's satisfaction or unsatisfied Evaluation and Selection, user;
(5) this process is repeatedly, terminates circulation after reaching end condition;
(6) after terminating, if user still evaluates dissatisfied, return again to acquiescence and reply, terminate to the understanding of active user's question sentence,
Conjecture and answer.
2. man-machine interaction method as claimed in claim 1, it is characterised in that in described step (2), described user is satisfied and not
The button of satisfactory feedback with praise, step on word replace, or with √, × symbol replacement, or with thumb upwards, thumb downward gesture generation
Replace.
3. man-machine interaction method as claimed in claim 1, it is characterised in that in described step (3), when customer problem is input to
After customer service system, frequently asked questions and corresponding answer FAQ set is retrieved and sorts by customer service system backstage;
The frequently asked questions and corresponding answer FAQ of sequence first is returned to user;If the frequently asked questions and corresponding answer FAQ of sequence first can not expire
When foot user answers, it is dissatisfied that user clicks on feedback, then the frequently asked questions and corresponding answer FAQ of sequence second is pushed by customer service system automatically
To user;If feedback is dissatisfied the most again, then the frequently asked questions and corresponding answer FAQ of sequence the 3rd is pushed user;Follow-up successively
Order pushes.
4. man-machine interaction method as claimed in claim 3, it is characterised in that according to marking sequence or according to frequently asked questions and corresponding answer
FAQ history temperature mode carries out described sequence.
5. man-machine interaction method as claimed in claim 1, it is characterised in that in described step (5), described end condition bag
Include: run into that user feedback is satisfied, do not feed back dissatisfied leave, candidate frequently asked questions and corresponding answer FAQ uses up or has reached number of times limit
System, then terminate pushing successively;Or terminate candidate frequently asked questions and corresponding answer FAQ is less than threshold value with user's question sentence degree of association when,
Proceed to step (6).
6. man-machine interaction method as claimed in claim 1, it is characterised in that described customer service system includes instant messaging channel
Customer service system, phone customer service and video customer service form.
7. man-machine interaction method as claimed in claim 6, it is characterised in that described phone customer service uses and adds telephone key-press row
Realizing for mode, described video customer service uses the button added on visual interface, or by speech recognition technology and gesture identification
Technology, obtains user's interaction feedback, and then optimizes customer service effect.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610565248.1A CN106227779A (en) | 2016-07-18 | 2016-07-18 | A kind of man-machine interaction method of customer service system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610565248.1A CN106227779A (en) | 2016-07-18 | 2016-07-18 | A kind of man-machine interaction method of customer service system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106227779A true CN106227779A (en) | 2016-12-14 |
Family
ID=57530859
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610565248.1A Pending CN106227779A (en) | 2016-07-18 | 2016-07-18 | A kind of man-machine interaction method of customer service system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106227779A (en) |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107862423A (en) * | 2017-06-28 | 2018-03-30 | 陆金所(上海)科技服务有限公司 | System evaluation method, intelligent evaluation system and computer-readable recording medium |
CN108388558A (en) * | 2018-02-07 | 2018-08-10 | 平安普惠企业管理有限公司 | Problem matching process, device, customer service robot and storage medium |
CN108446290A (en) * | 2017-02-16 | 2018-08-24 | 谷歌有限责任公司 | Streaming actual conversation management |
CN108733712A (en) * | 2017-04-21 | 2018-11-02 | 北京京东尚科信息技术有限公司 | A kind of question answering system evaluation method and device |
CN108874995A (en) * | 2018-06-12 | 2018-11-23 | 广东电网有限责任公司 | Method and device for establishing customer service database and electronic equipment |
CN108875055A (en) * | 2018-06-28 | 2018-11-23 | 联想(北京)有限公司 | A kind of answer providing method and equipment |
CN109189881A (en) * | 2018-06-20 | 2019-01-11 | 网宿科技股份有限公司 | Man-machine interaction method and intelligent robot |
CN109712618A (en) * | 2018-12-06 | 2019-05-03 | 珠海格力电器股份有限公司 | Voice service control method and device, storage medium and air conditioner |
CN110232573A (en) * | 2018-03-06 | 2019-09-13 | 广州供电局有限公司 | Based on interactive intelligent response system |
CN111460111A (en) * | 2019-01-22 | 2020-07-28 | 国际商业机器公司 | Evaluating retraining recommendations for automatic conversation services |
CN116434733A (en) * | 2023-04-25 | 2023-07-14 | 深圳市中诺智联科技有限公司 | AI voice interaction processing method for intelligent safety helmet |
CN116975395A (en) * | 2023-09-22 | 2023-10-31 | 安徽淘云科技股份有限公司 | Error feedback data processing method, device, equipment and medium |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101431573A (en) * | 2007-11-08 | 2009-05-13 | 上海赢思软件技术有限公司 | Method and equipment for implementing automatic customer service through human-machine interaction technology |
US20100076998A1 (en) * | 2008-09-11 | 2010-03-25 | Intuit Inc. | Method and system for generating a dynamic help document |
CN102075886A (en) * | 2010-12-15 | 2011-05-25 | 百度在线网络技术(北京)有限公司 | Question-and-answer method and system based on short message |
CN102624675A (en) * | 2011-01-27 | 2012-08-01 | 腾讯科技(深圳)有限公司 | Self-service customer service system and method |
CN103685506A (en) * | 2013-12-10 | 2014-03-26 | 北京奇虎科技有限公司 | Method, client side, server and system for pushing guidance query items |
CN104573000A (en) * | 2015-01-07 | 2015-04-29 | 北京云知声信息技术有限公司 | Sequential learning based automatic questions and answers device and method |
CN104699708A (en) * | 2013-12-09 | 2015-06-10 | ***通信集团北京有限公司 | Self-learning method and device for customer service robot |
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 |
-
2016
- 2016-07-18 CN CN201610565248.1A patent/CN106227779A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101431573A (en) * | 2007-11-08 | 2009-05-13 | 上海赢思软件技术有限公司 | Method and equipment for implementing automatic customer service through human-machine interaction technology |
US20100076998A1 (en) * | 2008-09-11 | 2010-03-25 | Intuit Inc. | Method and system for generating a dynamic help document |
CN102075886A (en) * | 2010-12-15 | 2011-05-25 | 百度在线网络技术(北京)有限公司 | Question-and-answer method and system based on short message |
CN102624675A (en) * | 2011-01-27 | 2012-08-01 | 腾讯科技(深圳)有限公司 | Self-service customer service system and method |
CN104699708A (en) * | 2013-12-09 | 2015-06-10 | ***通信集团北京有限公司 | Self-learning method and device for customer service robot |
CN103685506A (en) * | 2013-12-10 | 2014-03-26 | 北京奇虎科技有限公司 | Method, client side, server and system for pushing guidance query items |
CN104573000A (en) * | 2015-01-07 | 2015-04-29 | 北京云知声信息技术有限公司 | Sequential learning based automatic questions and answers device and method |
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 (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108446290A (en) * | 2017-02-16 | 2018-08-24 | 谷歌有限责任公司 | Streaming actual conversation management |
US11860913B2 (en) | 2017-02-16 | 2024-01-02 | Google Llc | Streaming real-time dialog management |
US11537646B2 (en) | 2017-02-16 | 2022-12-27 | Google Llc | Streaming real-time dialog management |
CN108733712A (en) * | 2017-04-21 | 2018-11-02 | 北京京东尚科信息技术有限公司 | A kind of question answering system evaluation method and device |
CN107862423A (en) * | 2017-06-28 | 2018-03-30 | 陆金所(上海)科技服务有限公司 | System evaluation method, intelligent evaluation system and computer-readable recording medium |
CN108388558B (en) * | 2018-02-07 | 2022-04-19 | 平安普惠企业管理有限公司 | Question matching method and device, customer service robot and storage medium |
CN108388558A (en) * | 2018-02-07 | 2018-08-10 | 平安普惠企业管理有限公司 | Problem matching process, device, customer service robot and storage medium |
CN110232573A (en) * | 2018-03-06 | 2019-09-13 | 广州供电局有限公司 | Based on interactive intelligent response system |
CN108874995A (en) * | 2018-06-12 | 2018-11-23 | 广东电网有限责任公司 | Method and device for establishing customer service database and electronic equipment |
CN109189881A (en) * | 2018-06-20 | 2019-01-11 | 网宿科技股份有限公司 | Man-machine interaction method and intelligent robot |
CN109189881B (en) * | 2018-06-20 | 2021-03-05 | 网宿科技股份有限公司 | Man-machine interaction method and intelligent robot |
CN108875055A (en) * | 2018-06-28 | 2018-11-23 | 联想(北京)有限公司 | A kind of answer providing method and equipment |
CN108875055B (en) * | 2018-06-28 | 2021-12-24 | 联想(北京)有限公司 | Answer providing method and equipment |
CN109712618A (en) * | 2018-12-06 | 2019-05-03 | 珠海格力电器股份有限公司 | Voice service control method and device, storage medium and air conditioner |
CN111460111A (en) * | 2019-01-22 | 2020-07-28 | 国际商业机器公司 | Evaluating retraining recommendations for automatic conversation services |
CN111460111B (en) * | 2019-01-22 | 2024-01-26 | 国际商业机器公司 | Retraining recommendations to evaluate automated dialog services |
CN116434733A (en) * | 2023-04-25 | 2023-07-14 | 深圳市中诺智联科技有限公司 | AI voice interaction processing method for intelligent safety helmet |
CN116434733B (en) * | 2023-04-25 | 2024-06-07 | 深圳市中诺智联科技有限公司 | AI voice interaction processing method for intelligent safety helmet |
CN116975395A (en) * | 2023-09-22 | 2023-10-31 | 安徽淘云科技股份有限公司 | Error feedback data processing method, device, equipment and medium |
CN116975395B (en) * | 2023-09-22 | 2024-01-23 | 安徽淘云科技股份有限公司 | Error feedback data processing method, device, equipment and medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106227779A (en) | A kind of man-machine interaction method of customer service system | |
CN106202159A (en) | A kind of man-machine interaction method of customer service system | |
CN108153780B (en) | Man-machine conversation device and method for realizing man-machine conversation | |
CN111553754B (en) | Updating method and device of behavior prediction system | |
CN105683874B (en) | Method for using emoji for text prediction | |
US20190066031A1 (en) | Automatic Updating Interactive Query Answering and Feature Training Method and System | |
US7218249B2 (en) | Hand-held communication device having navigation key-based predictive text entry | |
CN111949787A (en) | Automatic question-answering method, device, equipment and storage medium based on knowledge graph | |
CN110008322A (en) | Art recommended method and device under more wheel session operational scenarios | |
CN108595519A (en) | Focus incident sorting technique, device and storage medium | |
CN107688605B (en) | Cross-platform data matching process, device, computer equipment and storage medium | |
CN111062220B (en) | End-to-end intention recognition system and method based on memory forgetting device | |
CN106708802A (en) | Information recommendation method and system | |
CN111291172A (en) | Method and device for processing text | |
CN110473537A (en) | Control method, device, equipment and the storage medium of voice technical ability | |
Theosaksomo et al. | Conversational recommender system chatbot based on functional requirement | |
CN117573834B (en) | Multi-robot dialogue method and system for software-oriented instant service platform | |
CN117436679B (en) | Meta-universe resource matching method and system | |
CN109739969A (en) | Answer generation method and intelligent conversational system | |
CN109492085A (en) | Method, apparatus, terminal and storage medium are determined based on the answer of data processing | |
CN115146124A (en) | Question-answering system response method and device, equipment, medium and product thereof | |
CN106095941A (en) | Recommend method and system based on the solution in big data knowledge storehouse | |
CN112463930A (en) | Electric pin AI robot based on artificial intelligence | |
CN113726849A (en) | Sharing method and device for drinking wine making mode and server | |
Alinaghi et al. | A multi-agent question-answering system for e-learning and collaborative learning environment |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20161214 |