CN107506372A - A kind of automatic conversation switching method of robot customer service under mixed type session - Google Patents
A kind of automatic conversation switching method of robot customer service under mixed type session Download PDFInfo
- Publication number
- CN107506372A CN107506372A CN201710560942.9A CN201710560942A CN107506372A CN 107506372 A CN107506372 A CN 107506372A CN 201710560942 A CN201710560942 A CN 201710560942A CN 107506372 A CN107506372 A CN 107506372A
- Authority
- CN
- China
- Prior art keywords
- customer service
- user
- answer
- artificial
- message
- 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
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)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention provides a kind of automatic conversation switching method of robot customer service under mixed type session, belongs to Computer Applied Technology field.The present invention comprises the following steps：User conversation request is received, creates session；Type of message is analyzed, message is pre-processed, type of message inquiry information needed is obtained from knowledge base；Judge that can robot customer service answer, if it can, client is replied, if not, the actively session request of triggering or passive triggering and artificial customer service；Judge whether artificial customer service receives, if it is, artificial customer service and user conversation, if not, robot customer service continuation and user conversation, until conversation end.Beneficial effects of the present invention are：By the way that type of message is classified, and build various knowledge bases, corresponding knowledge base is retrieved based on type of message, improve the accuracy rate of problem analysis；The efficiency of artificial customer service and robot customer service switching is improved, drastically increases the satisfaction of Consumer's Experience.
Description
Technical field
The present invention relates to Computer Applied Technology field, more particularly to a kind of robot customer service is under mixed type session
Automatic conversation switching method.
Background technology
In recent years, with Internet technology development and ecommerce popularization, and enterprise portfolio itself and business
The increase of complexity, user also gradually increase to the demand of website customer service, the customer service system such as intelligent customer service, robot customer service
System is developed rapidly, gradually popularized.Robot customer service system is based on natural language processing technique, Knowledge Base Techniques etc., towards
Industry, field application, at present, customer service robot system, which has become, to be linked up and exchanges more and more important between enterprise and user
Technological means.Meanwhile also reduce artificial customer service cost for enterprise, improve customer service quality and efficiency.
At present, most of intelligent customer service system is problematic in that at intelligent aspect：
1) dialogue mode is fixed, and Consumer's Experience is undesirable；
2) artificial customer service is low with robot customer service switching efficiency；
3) using the method for simple keyword match, the higher question and answer queue of matching degree is provided the user, is entered for user
One step selects.This method causes the question and answer that system provides to that with certain limitation, can not parse synonym or similar
The problem of semantic.
The content of the invention
To solve the problems of the prior art, it is automatic under mixed type session that the present invention provides a kind of robot customer service
Conversation switching method.
The present invention comprises the following steps：
S1：User conversation request is received, creates session；
S2：Type of message is analyzed, message is pre-processed, obtains from knowledge base and believes needed for type of message inquiry
Breath；
S3：Judge that can robot customer service answer, if it can, reply client, if not, actively triggering or passive triggering with
The session request of artificial customer service；
S4：Judge whether artificial customer service receives, if it is, artificial customer service and user conversation, if not, robot customer service after
Continuous and user conversation, until conversation end.
The present invention is further improved, and in step s 2, the type of message includes：General question and answer, service question and answer,
Constraints question and answer, natural language interactivity question and answer, the message Preprocessing Algorithm includes participle, synonym is replaced, pronoun
Replace, grammer completion.
The present invention is further improved, and inquiring about required necessary information includes：General question and answer are it is desirable that origination message
Vocabulary after participle；Service question and answer are it is desirable that vocabulary after being segmented to the pretreated message of message；Constraints
Property question and answer are it is desirable that the triple query statement being made up of special word, special word attribute；Natural language interactivity question and answer need
Be website service project special word and its attribute composition triple query statement,
Wherein, the special word is the vocabulary to be acquired a special sense in knowledge base, comprising and be not limited to noun, verb, shape
Hold word；The special word attribute is the attribute vocabulary specified by the special word in knowledge base, comprising and be not limited to code, price,
Transaction value；The triple refers to the question and answer query specification being made up of three special word, attribute, value elements, the special word and category
Property quantity be more than 1.
The present invention is further improved, and the construction method of the knowledge base comprises the following steps：
A：Start, read configuration file；
B：Each epitope of knowledge base is obtained to put；
C：Obtain the special word row and attribute column of restrictive table in knowledge base table；
D：The synonym of extended attribute vocabulary；
E：The table content of three elements is respectively stored into different data structures, terminated.
The present invention is further improved, and in step s3, robot customer service knowledge based storehouse, is carried out using term vector model
Vocabulary or statement matching, if coupling number is less than the threshold value of setting, the session request of artificial customer service is triggered,
If contact staff is online, the customer side of contact staff is reminded, and prompts this session please in request message
What the customer service of Seeking Truth robot was initiated, and show the Message Record that the robot customer service that the user proposes can not answer；If
Contact staff is not online, and robot customer service then can not answer this problem to user prompting.
The present invention is further improved, if the quantity of artificial customer service is multiple, according to the user of artificial customer service
Quantity carries out dynamic and intelligent and distributes the user.
The present invention is further improved, and in step s3, passive triggering is that user actively please with artificial customer service initiation session
Ask, if artificial customer service is online, the customer side of artificial customer service is reminded, and it is that user actively initiates to prompt this session request
, if artificial customer service is not online, robot customer service reminds the user contact staff not online.
The present invention is further improved, in step s 4, after artificial customer service receives session request, if not selecting catcher to use
Family, then the session of the user and the robot customer service can only be watched, it is impossible to intervened；It is if described artificial
Customer service selection catcher user, then artificial customer service conversates with user is connected.
The present invention is further improved, and artificial customer service and robot customer service can not provide the user customer service simultaneously,
Artificial customer service conversates with user be connected during, the robot customer service then stops conversating with the user.
The present invention is further improved, and the mode that artificial customer service disconnects session connection with user includes：The user leaves
Customer service interface or artificial customer service disconnection and the session connection of user, after artificial customer service disconnects with user conversation, the machine
Device people customer service then continues to conversate with user to be connected, until user leaves.
Compared with prior art, the beneficial effects of the invention are as follows：By the way that type of message is classified, and build and various know
Know storehouse, corresponding knowledge base is retrieved based on type of message, the accuracy rate of problem analysis is improved, by under mixed type session
Semi-automatic session switching, the efficiency of artificial customer service and robot customer service switching is improved, drastically increases the satisfaction of Consumer's Experience
Degree.
Brief description of the drawings
Fig. 1 is the inventive method flow chart；
Fig. 2 is one embodiment of the invention detail flowchart；
Fig. 3 is the construction method flow chart of the respective knowledge base information of the present invention；
Fig. 4 is an embodiment process chart of constraints question and answer of the present invention；
Fig. 5 is an embodiment process chart of the general question and answer of the present invention and service question and answer；
Fig. 6 is an embodiment process chart of natural language interactivity question and answer of the present invention；
Fig. 7 and Fig. 8 is the artificial customer service session surface chart of triggering；
Fig. 9 is the more artificial customer service surface charts of multi-user's triggering；
Figure 10 is one embodiment of the invention customer service robot chat record 1；
Figure 11 is one embodiment of the invention customer service robot chat record 2；
Figure 12 is one embodiment of the invention customer service robot chat record 3；
Figure 13 is one embodiment of the invention customer service robot chat record 4；
Figure 14 is one embodiment of the invention customer service robot chat record 5；
Figure 15 is one embodiment of the invention customer service robot chat record 6.
Embodiment
The present invention is described in further details with reference to the accompanying drawings and examples.
As depicted in figs. 1 and 2, the automatic conversation switching method of the present invention comprises the following steps：
Step S1：User conversation request is received, creates session.
After creating session, wait user to put question to, then carry out 30 seconds heartbeat detections, system starts countdown, if the time
Arrive, then judge whether user leaves, if it is, terminating dialogue, preserve chat record.If not, judging whether user proposes to ask
Topic, if it is, customer problem is received, if not, continuing waiting for user's enquirement.
Step S2：Type of message is analyzed, message is pre-processed, is obtained from knowledge base needed for type of message inquiry
Information.
Type of message in this example includes：General question and answer, service question and answer, constraints question and answer, natural language are handed over
Mutual property question and answer.
Wherein, general question and answer are the question-response forms unrelated with context and web site contents.Such as：" hello ",
" what you cry ", " what you both know about " etc., as shown in Figure 10.
Service question and answer are the general question and answer related to web site contents.Such as：" what financier is ", " what VIP has
Benefit ", " how could turning into financier " etc..As shown in figures 11-13.
Constraints question and answer are handled based on Heterogeneous Information, and the context-free with service content restriction relation is asked
Answer, as shown in figure 14.
Natural language interactivity question and answer are based on the interactive context-sensitive question and answer handled naturally, as shown in figure 15.
After type of message is got, question sentence is pre-processed first, the algorithm of message pretreatment include participle,
Synonym replacement, pronoun replacement, grammer completion etc..After question sentence type identification, different types of question sentence uses different places
Reason method.For general question sentence, the vocabulary after original question sentence is segmented is as Query Information；Service question sentence, it will pre-process
Participle vocabulary afterwards is as Query Information；Constraints question sentence, generate special word, attribute, value triple query statement；It is natural
Language interactivity question sentence, the special word and its attribute of website service project are extracted, generate triple query statement.
Wherein, the special word is the vocabulary to be acquired a special sense in knowledge base, comprising and be not limited to noun, verb, shape
Hold word；The special word attribute is the attribute vocabulary specified by the special word in knowledge base, comprising and be not limited to code, price,
Transaction value；The triple refers to the question and answer query specification being made up of three special word, attribute, value elements, the special word and category
The quantity of property includes but is not limited to 1.
As shown in figure 3, for different type of messages, there are its each self-corresponding knowledge base, the structure side of this example knowledge base
Method comprises the following steps：
A：Start, read configuration file；
B：Each epitope of knowledge base is obtained to put；
C：Obtain the special word row and attribute column of restrictive table in knowledge base table；
D：The synonym of extended attribute vocabulary；
E：The table content of three elements is respectively stored into different data structures, terminated.
The Query Information obtained in this example more than is retrieved to knowledge base, including the inspection based on data base querying
The sentence matching of rope, word-based vector model, the matching result for being up to confidence threshold value return to user.
As shown in figure 4, the processing method in this example for constraints question and answer is：
S201：Start, obtain user message, and carry out stop words, go additional character, symbol is unitized to wait pretreatment work
Make；
S202：Judge whether it is the natural language processing question and answer related to product, if it is, being interacted into natural language
Property module, step S208 is then performed, if not, performing step S203；
S203：Judge to whether there is special word in message, if it is, step S204 is performed, if not, judging whether
Any property value, if not, memory module content is removed, into general question and answer and service question and answer module, if it is, judging
Whether the special word of the attribute there is in memory module, if not, memory module content is removed, into general question and answer kimonos
Business property question and answer module, if it is, performing step S205；
S204：The attribute word that the special word can reply is judged whether, if it is, step S205 is performed, if not,
Judge whether the special word of the attribute in memory module be present, if not, memory module content is removed, into general question and answer
With service question and answer module, if it is, performing step S205；
S205：Composition search triple；
S206：Utilize ternary group searching answer；
S207：Into constraints question and answer module；
S208：Answer is returned into user, terminated.
As shown in figure 5, it is for the processing method of general question and answer and service question and answer in this example：
Start, user's raw information is not gone to the pretreatment of stop words；
Matched with the question and answer in everyday knowledge storehouse, then matching fraction is classified by every 0.05, wherein, 1
For matching completely, the problem of obtaining largest score list；
Then, the raw information of user is carried out to the pretreatment of stop words, the synonym that will appear from replaces with and website
Related vocabulary, is then matched with the question and answer in service knowledge base；
Next, often matching one, the matching fraction unification of service question and answer is just raised 0.1, then according to every 0.05
Classified, obtain group big fraction the problem of list, judge whether largest score reaches the threshold value 0.6 of setting, if it is, taking phase
User is returned to like a certain reply in degree highest that class problem, if not, being asked to artificial customer service active triggering session, knot
Beam.
As shown in fig. 6, it is to the processing method of natural language interactivity question and answer in this example：
S211：Start, problem is subjected to stop words and handled, the message on product class is determined whether, if it is, holding
Row step S213, if not, performing step S212；
S212：Judge whether it is the secondary enquirement based on last time natural language processing question and answer, if it is, performing step
S213, if not, returning to a upper module, terminate；
S213：According to acquiescence built-in properties composition triple；
S214：Answer is searched for from knowledge base, is then returned to user, is terminated.
Step S3：Judge that can robot customer service answer, if it can, client is replied, if not, actively triggering or passive tactile
Hair and the session request of artificial customer service.
Actively triggering is the session request of robot triggering, robot customer service knowledge based storehouse, is entered using term vector model
Row vocabulary or statement matching, if coupling number is less than the threshold value of setting, the session request of artificial customer service is triggered,
If contact staff is online, the customer side of contact staff is reminded, and prompts this session please in request message
What the customer service of Seeking Truth robot was initiated, and show the Message Record that the robot customer service that the user proposes can not answer；If
Contact staff is not online, and robot customer service then can not answer this problem to user prompting.
As shown in figure 9, answer can not be retrieved in existing knowledge storehouse by working as robot customer service, then artificial customer service mould is switched to
Formula.When multi-user triggers more customer services simultaneously, system can carry out dynamic and intelligent distribution according to the queuing situation of artificial customer service, carry
The operating efficiency of high artificial customer service.
Passive triggering is that user actively initiates a session request with artificial customer service, if artificial customer service is online, artificial customer service
Customer side is reminded, and it is that user actively initiates to prompt this session request, if artificial customer service is not online, robot visitor
Clothes remind the user contact staff not online.
Step S4：Judge whether artificial customer service receives, if it is, artificial customer service and user conversation, if not, robot is objective
Clothes continue and user conversation, until conversation end.Each robot terminates to talk with user, or artificial customer service terminates with user
Dialogue, system can automatically save chat record into database.
As shown in Figure 7 and Figure 8, after artificial customer service receives session request, pop-up prompting is received, " use is taken over if clicked on
Family ", then it is user service to be switched to artificial customer service, after having serviced, clicks on " terminating catcher ", then automatically switches to robot visitor
Take as user service.If disagreeing switching, ignore.If not selecting to take over user, can only to the user and
The session of the robot customer service is watched, it is impossible to is intervened；If the artificial customer service selection catcher user, people
Work customer service conversates with user to be connected.
Artificial customer service and robot customer service can not provide the user customer service, artificial customer service and user simultaneously in this example
Conversate during connection, the robot customer service then stops conversating with the user.
The mode that artificial customer service disconnects session connection with user includes：The user leaves customer service interface or artificial visitor
Clothes disconnect the session connection with user, and after artificial customer service disconnects with user conversation, the robot customer service then continues and user
Conversate connection, until user leaves.
The present invention by the way that type of message is classified, and build various knowledge bases, based on type of message to corresponding knowledge
Storehouse is retrieved, and improves the accuracy rate of problem analysis, is switched by semi-automatic session under mixed type session, is improved artificial customer service
With the efficiency of robot customer service switching, the satisfaction of Consumer's Experience is drastically increased.
Embodiment described above is the better embodiment of the present invention, not limits the specific of the present invention with this
Practical range, the scope of the present invention includes being not limited to present embodiment, all equal according to the equivalence changes of the invention made
Within the scope of the present invention.
Claims (10)
1. automatic conversation switching method of a kind of robot customer service under mixed type session, it is characterised in that including following step
Suddenly：
S1：User conversation request is received, creates session；
S2：Type of message is analyzed, message is pre-processed, type of message inquiry information needed is obtained from knowledge base；
S3：Judge that can robot customer service answer, if it can, reply client, if not, actively triggering or passive triggering with it is artificial
The session request of customer service；
S4：Judge whether artificial customer service receives, if it is, artificial customer service and user conversation, if not, robot customer service continue with
User conversation, until conversation end.
2. automatic conversation switching method according to claim 1, it is characterised in that：In step s 2, the type of message
Including：General question and answer, service question and answer, constraints question and answer, natural language interactivity question and answer, the message pretreatment are calculated
Method includes participle, synonym is replaced, pronoun is replaced, grammer completion.
3. automatic conversation switching method according to claim 2, it is characterised in that：Necessary information needed for inquiry includes：
General question and answer it is desirable that origination message participle after vocabulary；
Service question and answer are it is desirable that vocabulary after being segmented to the pretreated message of message；
Constraints question and answer are it is desirable that the triple query statement being made up of special word, special word attribute；
Natural language interactivity question and answer are it is desirable that the ternary group polling language of special word and its attribute composition of website service project
Sentence,
Wherein,
The special word is the vocabulary to be acquired a special sense in knowledge base, comprising and be not limited to noun, verb, adjective；It is described
Special word attribute is the attribute vocabulary specified by the special word in knowledge base, comprising and be not limited to code, price, transaction value；Institute
State triple and refer to the question and answer query specification being made up of three special word, attribute, value elements, the quantity of the special word and attribute is
More than 1.
4. automatic conversation switching method according to claim 3, it is characterised in that：The construction method of the knowledge base includes
Following steps：
A：Start, read configuration file；
B：Each epitope of knowledge base is obtained to put；
C：Obtain the special word row and attribute column of restrictive table in knowledge base table；
D：The synonym of extended attribute vocabulary；
E：The table content of three elements is respectively stored into different data structures, terminated.
5. automatic conversation switching method according to claim 4, it is characterised in that：In step s3, robot customer service base
In knowledge base, vocabulary or statement matching are carried out using term vector model, if coupling number is less than the threshold value of setting, triggering is artificial
The session request of customer service,
If contact staff is online, the customer side of contact staff is reminded, and prompts in request message this session request to be
What robot customer service was initiated, and show the Message Record that the robot customer service that the user proposes can not answer；If customer service
Personnel are not online, and robot customer service then can not answer this problem to user prompting.
6. automatic conversation switching method according to claim 5, it is characterised in that：If the quantity of artificial customer service is more
It is individual, then dynamic and intelligent is carried out according to the number of users of artificial customer service and distribute the user.
7. automatic conversation switching method according to claim 1, it is characterised in that：In step s3, passive triggering is to use
Householder is dynamic to be initiated a session request with artificial customer service, if artificial customer service is online, the customer side of artificial customer service is reminded, and is prompted
This session request is that user actively initiates, if artificial customer service is not online, the user contact staff is reminded in robot customer service
It is not online.
8. automatic conversation switching method according to claim 7, it is characterised in that：In step s 4, artificial customer service receives
After session request, if not selecting to take over user, the session of the user and the robot customer service can only be watched,
It can not be intervened；If the artificial customer service selection catcher user, artificial customer service conversates with user to be connected.
9. automatic conversation switching method according to claim 8, it is characterised in that：Artificial customer service and robot customer service can not
It is enough to provide the user customer service simultaneously, artificial customer service conversates with user be connected during, the robot customer service then stops
Conversated with the user.
10. automatic conversation switching method according to claim 9, it is characterised in that：Artificial customer service disconnects session with user
The mode of connection includes：The user leaves customer service interface or artificial customer service disconnection and the session connection of user, artificial visitor
After clothes disconnect with user conversation, the robot customer service then continues to conversate with user to be connected, until user leaves.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710560942.9A CN107506372A (en) | 2017-07-11 | 2017-07-11 | A kind of automatic conversation switching method of robot customer service under mixed type session |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710560942.9A CN107506372A (en) | 2017-07-11 | 2017-07-11 | A kind of automatic conversation switching method of robot customer service under mixed type session |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107506372A true CN107506372A (en) | 2017-12-22 |
Family
ID=60678945
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710560942.9A Pending CN107506372A (en) | 2017-07-11 | 2017-07-11 | A kind of automatic conversation switching method of robot customer service under mixed type session |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107506372A (en) |
Cited By (37)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108304933A (en) * | 2018-01-29 | 2018-07-20 | 北京师范大学 | A kind of complementing method and complementing device of knowledge base |
| CN108418981A (en) * | 2018-03-16 | 2018-08-17 | 苏州思必驰信息科技有限公司 | The method and device of dialogue service is provided for client |
| CN108777751A (en) * | 2018-06-07 | 2018-11-09 | 上海航动科技有限公司 | A kind of call center system and its voice interactive method, device and equipment |
| CN108900726A (en) * | 2018-06-28 | 2018-11-27 | 北京首汽智行科技有限公司 | Artificial customer service forwarding method based on speech robot people |
| CN109033342A (en) * | 2018-07-24 | 2018-12-18 | 北京京东尚科信息技术有限公司 | Applied to the service providing method of service system, device and service model |
| CN109333542A (en) * | 2018-08-16 | 2019-02-15 | 北京云迹科技有限公司 | Robot voice exchange method and system |
| CN109544183A (en) * | 2018-11-27 | 2019-03-29 | 网宿科技股份有限公司 | A kind of business consultation method and device |
| CN110020873A (en) * | 2019-03-12 | 2019-07-16 | 平安科技（深圳）有限公司 | Artificial customer service switching method, relevant apparatus, equipment and computer-readable medium |
| CN110035187A (en) * | 2019-04-16 | 2019-07-19 | 浙江百应科技有限公司 | A method of realizing AI and operator attendance seamless switching in the phone |
| CN110047473A (en) * | 2019-04-19 | 2019-07-23 | 交通银行股份有限公司太平洋信用卡中心 | A kind of man-machine collaboration exchange method and system |
| CN110149450A (en) * | 2019-05-22 | 2019-08-20 | 欧冶云商股份有限公司 | Intelligent customer service answer method and system |
| CN110171005A (en) * | 2019-06-10 | 2019-08-27 | 杭州任你说智能科技有限公司 | A kind of tourism robot system based on intelligent sound box |
| CN110347808A (en) * | 2019-05-28 | 2019-10-18 | 成都美美臣科技有限公司 | One e-commerce website intelligent robot customer service construction method |
| CN110347460A (en) * | 2019-06-11 | 2019-10-18 | 无线生活（杭州）信息科技有限公司 | Reminding method and device |
| CN110362667A (en) * | 2019-07-12 | 2019-10-22 | 深圳前海微众银行股份有限公司 | Intelligent customer service method, apparatus, equipment and readable storage medium storing program for executing |
| WO2019201202A1 (en) * | 2018-04-16 | 2019-10-24 | 华为技术有限公司 | Call handling method and apparatus, server, storage medium, and system |
| CN110377712A (en) * | 2019-07-12 | 2019-10-25 | 腾讯科技（深圳）有限公司 | A kind of intelligence conversation switching method, device, equipment and storage medium |
| CN110377709A (en) * | 2019-06-03 | 2019-10-25 | 广东幽澜机器人科技有限公司 | A kind of method and device reducing robot customer service O&M complexity |
| CN110570215A (en) * | 2019-09-06 | 2019-12-13 | 北京金融资产交易所有限公司 | Intelligent customer service system |
| CN111046151A (en) * | 2018-10-15 | 2020-04-21 | 腾讯科技（深圳）有限公司 | Message processing method and device |
| TWI698830B (en) * | 2018-01-26 | 2020-07-11 | 香港商阿里巴巴集團服務有限公司 | Method and device for transferring robot customer service to manual customer service, computer equipment and computer readable storage medium |
| CN111654584A (en) * | 2020-06-30 | 2020-09-11 | 浙江百应科技有限公司 | Method and server for automatically matching call center seats based on time rules |
| CN111680141A (en) * | 2020-05-28 | 2020-09-18 | 泰康保险集团股份有限公司 | One-to-many intelligent question answering response method, device, equipment and readable storage medium |
| CN111988476A (en) * | 2020-09-25 | 2020-11-24 | 南京酷朗电子有限公司 | Automatic voice cooperative working method of customer service system |
| CN112037904A (en) * | 2020-08-31 | 2020-12-04 | 康键信息技术（深圳）有限公司 | Online diagnosis and treatment data processing method and device, computer equipment and storage medium |
| CN112286209A (en) * | 2020-11-19 | 2021-01-29 | 深圳壹智云科技有限公司 | Man-machine interaction method and system of mobile robot |
| CN112385191A (en) * | 2018-06-28 | 2021-02-19 | 贝宝公司 | Middle layer messaging system |
| CN112543185A (en) * | 2020-11-23 | 2021-03-23 | 建信金融科技有限责任公司 | Customer service method, device and system |
| CN112766936A (en) * | 2021-03-22 | 2021-05-07 | 中国工商银行股份有限公司 | Intelligent customer service processing method and system |
| CN113065362A (en) * | 2021-03-19 | 2021-07-02 | 联想(北京)有限公司 | Intelligent reply method and device |
| CN113360810A (en) * | 2021-07-02 | 2021-09-07 | 北京容联七陌科技有限公司 | Online customer service active session invitation method |
| CN113468894A (en) * | 2021-07-27 | 2021-10-01 | 泰康保险集团股份有限公司 | Dialogue interaction method and device, electronic equipment and computer-readable storage medium |
| CN113783766A (en) * | 2020-05-29 | 2021-12-10 | 北京沃东天骏信息技术有限公司 | Data processing method, device and storage medium |
| CN113946673A (en) * | 2021-12-20 | 2022-01-18 | 深圳市一号互联科技有限公司 | Semantic-based intelligent customer service routing processing method and device |
| CN114117157A (en) * | 2021-11-19 | 2022-03-01 | 招联消费金融有限公司 | Session processing method, device, computer equipment and storage medium |
| CN117176682A (en) * | 2023-09-25 | 2023-12-05 | 北京拍多多科技有限公司 | Message notification method and system |
| US12001972B2 (en) | 2018-10-31 | 2024-06-04 | Accenture Global Solutions Limited | Semantic inferencing in customer relationship management |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105072173A (en) * | 2015-08-03 | 2015-11-18 | 谌志群 | Customer service method and system for automatically switching between automatic customer service and artificial customer service |
| CN105162688A (en) * | 2015-08-13 | 2015-12-16 | 北京智齿博创科技有限公司 | Method for chatting with online customer service representative |
| CN105592237A (en) * | 2014-10-24 | 2016-05-18 | 中国移动通信集团公司 | Method and apparatus for session switching, and intelligent customer service robot |
| CN106911812A (en) * | 2017-05-05 | 2017-06-30 | 腾讯科技（上海）有限公司 | A kind of processing method of session information, server and computer-readable recording medium |
-
2017
- 2017-07-11 CN CN201710560942.9A patent/CN107506372A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105592237A (en) * | 2014-10-24 | 2016-05-18 | 中国移动通信集团公司 | Method and apparatus for session switching, and intelligent customer service robot |
| CN105072173A (en) * | 2015-08-03 | 2015-11-18 | 谌志群 | Customer service method and system for automatically switching between automatic customer service and artificial customer service |
| CN105162688A (en) * | 2015-08-13 | 2015-12-16 | 北京智齿博创科技有限公司 | Method for chatting with online customer service representative |
| CN106911812A (en) * | 2017-05-05 | 2017-06-30 | 腾讯科技（上海）有限公司 | A kind of processing method of session information, server and computer-readable recording medium |
Cited By (52)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI698830B (en) * | 2018-01-26 | 2020-07-11 | 香港商阿里巴巴集團服務有限公司 | Method and device for transferring robot customer service to manual customer service, computer equipment and computer readable storage medium |
| US10977664B2 (en) | 2018-01-26 | 2021-04-13 | Advanced New Technologies Co., Ltd. | Method and apparatus for transferring from robot customer service to human customer service |
| CN108304933A (en) * | 2018-01-29 | 2018-07-20 | 北京师范大学 | A kind of complementing method and complementing device of knowledge base |
| CN108418981A (en) * | 2018-03-16 | 2018-08-17 | 苏州思必驰信息科技有限公司 | The method and device of dialogue service is provided for client |
| CN108418981B (en) * | 2018-03-16 | 2019-10-29 | 苏州思必驰信息科技有限公司 | The method and device of dialogue service is provided for client |
| CN110392168A (en) * | 2018-04-16 | 2019-10-29 | 华为技术有限公司 | Call processing method, device, server, storage medium and system |
| WO2019201202A1 (en) * | 2018-04-16 | 2019-10-24 | 华为技术有限公司 | Call handling method and apparatus, server, storage medium, and system |
| US11240374B2 (en) | 2018-04-16 | 2022-02-01 | Huawei Technologies Co., Ltd. | Call processing method and apparatus, server, storage medium, and system |
| CN108777751A (en) * | 2018-06-07 | 2018-11-09 | 上海航动科技有限公司 | A kind of call center system and its voice interactive method, device and equipment |
| CN112385191A (en) * | 2018-06-28 | 2021-02-19 | 贝宝公司 | Middle layer messaging system |
| CN108900726A (en) * | 2018-06-28 | 2018-11-27 | 北京首汽智行科技有限公司 | Artificial customer service forwarding method based on speech robot people |
| CN109033342A (en) * | 2018-07-24 | 2018-12-18 | 北京京东尚科信息技术有限公司 | Applied to the service providing method of service system, device and service model |
| CN109033342B (en) * | 2018-07-24 | 2023-01-31 | 北京京东尚科信息技术有限公司 | Service providing method and device applied to service system and service model |
| CN109333542A (en) * | 2018-08-16 | 2019-02-15 | 北京云迹科技有限公司 | Robot voice exchange method and system |
| CN111046151A (en) * | 2018-10-15 | 2020-04-21 | 腾讯科技（深圳）有限公司 | Message processing method and device |
| US12001972B2 (en) | 2018-10-31 | 2024-06-04 | Accenture Global Solutions Limited | Semantic inferencing in customer relationship management |
| CN109544183A (en) * | 2018-11-27 | 2019-03-29 | 网宿科技股份有限公司 | A kind of business consultation method and device |
| CN110020873B (en) * | 2019-03-12 | 2024-06-21 | 平安科技（深圳）有限公司 | Manual customer service switching method, related device, equipment and computer readable medium |
| CN110020873A (en) * | 2019-03-12 | 2019-07-16 | 平安科技（深圳）有限公司 | Artificial customer service switching method, relevant apparatus, equipment and computer-readable medium |
| CN110035187A (en) * | 2019-04-16 | 2019-07-19 | 浙江百应科技有限公司 | A method of realizing AI and operator attendance seamless switching in the phone |
| CN110047473A (en) * | 2019-04-19 | 2019-07-23 | 交通银行股份有限公司太平洋信用卡中心 | A kind of man-machine collaboration exchange method and system |
| CN110149450A (en) * | 2019-05-22 | 2019-08-20 | 欧冶云商股份有限公司 | Intelligent customer service answer method and system |
| CN110347808A (en) * | 2019-05-28 | 2019-10-18 | 成都美美臣科技有限公司 | One e-commerce website intelligent robot customer service construction method |
| CN110377709A (en) * | 2019-06-03 | 2019-10-25 | 广东幽澜机器人科技有限公司 | A kind of method and device reducing robot customer service O&M complexity |
| CN110377709B (en) * | 2019-06-03 | 2021-10-08 | 广东幽澜机器人科技有限公司 | Method and device for reducing complexity of robot customer service operation and maintenance |
| CN110171005A (en) * | 2019-06-10 | 2019-08-27 | 杭州任你说智能科技有限公司 | A kind of tourism robot system based on intelligent sound box |
| CN110347460A (en) * | 2019-06-11 | 2019-10-18 | 无线生活（杭州）信息科技有限公司 | Reminding method and device |
| CN110377712A (en) * | 2019-07-12 | 2019-10-25 | 腾讯科技（深圳）有限公司 | A kind of intelligence conversation switching method, device, equipment and storage medium |
| CN110362667A (en) * | 2019-07-12 | 2019-10-22 | 深圳前海微众银行股份有限公司 | Intelligent customer service method, apparatus, equipment and readable storage medium storing program for executing |
| CN110570215A (en) * | 2019-09-06 | 2019-12-13 | 北京金融资产交易所有限公司 | Intelligent customer service system |
| CN111680141B (en) * | 2020-05-28 | 2023-09-08 | 泰康保险集团股份有限公司 | One-to-many intelligent question-answering response method, device, equipment and readable storage medium |
| CN111680141A (en) * | 2020-05-28 | 2020-09-18 | 泰康保险集团股份有限公司 | One-to-many intelligent question answering response method, device, equipment and readable storage medium |
| CN113783766A (en) * | 2020-05-29 | 2021-12-10 | 北京沃东天骏信息技术有限公司 | Data processing method, device and storage medium |
| CN113783766B (en) * | 2020-05-29 | 2023-08-08 | 北京沃东天骏信息技术有限公司 | Data processing method, device and storage medium |
| CN111654584A (en) * | 2020-06-30 | 2020-09-11 | 浙江百应科技有限公司 | Method and server for automatically matching call center seats based on time rules |
| CN112037904B (en) * | 2020-08-31 | 2023-07-18 | 康键信息技术（深圳）有限公司 | Online diagnosis and treatment data processing method and device, computer equipment and storage medium |
| CN112037904A (en) * | 2020-08-31 | 2020-12-04 | 康键信息技术（深圳）有限公司 | Online diagnosis and treatment data processing method and device, computer equipment and storage medium |
| CN111988476A (en) * | 2020-09-25 | 2020-11-24 | 南京酷朗电子有限公司 | Automatic voice cooperative working method of customer service system |
| CN111988476B (en) * | 2020-09-25 | 2021-03-16 | 南京酷朗电子有限公司 | Automatic voice cooperative working method of customer service system |
| CN112286209A (en) * | 2020-11-19 | 2021-01-29 | 深圳壹智云科技有限公司 | Man-machine interaction method and system of mobile robot |
| CN112543185A (en) * | 2020-11-23 | 2021-03-23 | 建信金融科技有限责任公司 | Customer service method, device and system |
| CN113065362B (en) * | 2021-03-19 | 2024-06-21 | 联想(北京)有限公司 | Intelligent reply method and device |
| CN113065362A (en) * | 2021-03-19 | 2021-07-02 | 联想(北京)有限公司 | Intelligent reply method and device |
| CN112766936A (en) * | 2021-03-22 | 2021-05-07 | 中国工商银行股份有限公司 | Intelligent customer service processing method and system |
| CN113360810A (en) * | 2021-07-02 | 2021-09-07 | 北京容联七陌科技有限公司 | Online customer service active session invitation method |
| CN113468894B (en) * | 2021-07-27 | 2024-03-22 | 泰康保险集团股份有限公司 | Dialogue interaction method and device, electronic equipment and computer readable storage medium |
| CN113468894A (en) * | 2021-07-27 | 2021-10-01 | 泰康保险集团股份有限公司 | Dialogue interaction method and device, electronic equipment and computer-readable storage medium |
| CN114117157B (en) * | 2021-11-19 | 2024-04-09 | 招联消费金融股份有限公司 | Session processing method, apparatus, computer device and storage medium |
| CN114117157A (en) * | 2021-11-19 | 2022-03-01 | 招联消费金融有限公司 | Session processing method, device, computer equipment and storage medium |
| CN113946673A (en) * | 2021-12-20 | 2022-01-18 | 深圳市一号互联科技有限公司 | Semantic-based intelligent customer service routing processing method and device |
| CN117176682A (en) * | 2023-09-25 | 2023-12-05 | 北京拍多多科技有限公司 | Message notification method and system |
| CN117176682B (en) * | 2023-09-25 | 2024-02-02 | 北京拍多多科技有限公司 | Message notification method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107506372A (en) | A kind of automatic conversation switching method of robot customer service under mixed type session | |
| CN107329967B (en) | Question answering system and method based on deep learning | |
| US11200886B2 (en) | System and method for training a virtual agent to identify a user's intent from a conversation | |
| CN105592237B (en) | A kind of method, apparatus and intelligent customer service robot of session switching | |
| CN106790004B (en) | Customer service auxiliary real-time prompt system based on artificial intelligence | |
| US9466294B1 (en) | Dialog management system | |
| US9524291B2 (en) | Visual display of semantic information | |
| US20210406473A1 (en) | System and method for building chatbot providing intelligent conversational service | |
| KR20180058877A (en) | Business support method using a chatting bot | |
| US20130246392A1 (en) | Conversational System and Method of Searching for Information | |
| CN101685454A (en) | Human-computer interactive method and system | |
| CN105513593A (en) | Intelligent human-computer interaction method drove by voice | |
| AU2019219717B2 (en) | System and method for analyzing partial utterances | |
| US20200066259A1 (en) | Intelligence-driven virtual assistant for automated idea documentation | |
| JP5368924B2 (en) | Apparatus and method for progressive development of natural language user interfaces | |
| CN110570215A (en) | Intelligent customer service system | |
| CN110457454A (en) | A kind of dialogue method, server, conversational system and storage medium | |
| CN111858854A (en) | Question-answer matching method based on historical dialogue information and related device | |
| Theosaksomo et al. | Conversational recommender system chatbot based on functional requirement | |
| TW202018529A (en) | System for inquiry service and method thereof | |
| CN111242721B (en) | Voice meal ordering method and device, electronic equipment and storage medium | |
| CN106951470B (en) | A kind of intelligent Answer System based on the retrieval of professional knowledge figure | |
| CN110276639A (en) | A kind of network marketing system and method | |
| KR20220041702A (en) | Artificial intelligence chatbot server | |
| WO2013123853A1 (en) | Man-machine conversation 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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171222 |