CN110069600A - Dialogue method and device, computer readable storage medium - Google Patents
Dialogue method and device, computer readable storage medium Download PDFInfo
- Publication number
- CN110069600A CN110069600A CN201910233200.4A CN201910233200A CN110069600A CN 110069600 A CN110069600 A CN 110069600A CN 201910233200 A CN201910233200 A CN 201910233200A CN 110069600 A CN110069600 A CN 110069600A
- Authority
- CN
- China
- Prior art keywords
- client
- node
- dialogue
- art
- directed toward
- 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
- 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
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Mathematical Physics (AREA)
- Human Computer Interaction (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Machine Translation (AREA)
Abstract
A kind of dialogue method and device, computer readable storage medium, the dialogue method include: the dialog text for obtaining client;Semantic analysis is carried out to the dialog text, determines that the semantic of the client is directed toward;It is directed toward according to the semanteme of the client, determines that node corresponding with the semanteme of client direction, the node include transition node and ending node from preset dialogue digraph;Art is exported to the client if the node is corresponded to.Using the above scheme, it can be improved dialogue efficiency.
Description
Technical field
The present embodiments relate to natural language technical fields more particularly to a kind of dialogue method and device, computer can
Read storage medium.
Background technique
With becoming increasingly popular for dialogue robot, speech robot people or text chat machine will use in more and more scenes
Device people substitutes the simple manual service in part, such as customer service and marketing.
To talk with robot usage scenario relatively common at present still to market in customer service, these scenes words art is relatively easy,
Very high design tactics are not often needed.
When talking with robot for complicated scene, there is a problem of that dialogue efficiency is lower.
Summary of the invention
The technical issues of embodiment of the present invention solves is that dialogue efficiency is lower.
In order to solve the above technical problems, it includes: pair for obtaining client that the embodiment of the present invention, which provides a kind of dialogue method,
Talk about text;Semantic analysis is carried out to the dialog text, determines that the semantic of the client is directed toward;Referred to according to the semanteme of the client
To the determining node corresponding with the semanteme of client direction from preset dialogue digraph, the node includes transition segment
Point and ending node;Art is exported to the client if the node is corresponded to.
Optionally, before the dialog text for obtaining client, further includes: obtain the dialogue digraph according to application scenarios
In start node it is corresponding if art, and export to the client.
Optionally, art includes any of the following if the start node is corresponding: client identity verifies words art, business needs
It implores and knows words art, words of greeting art, opening remarks guidance words art.
Optionally, when not found from the dialogue digraph with the semanteme of the client corresponding node of direction, also
Include: obtain it is default if art and export to the client.
Optionally, when not found from the dialogue digraph with the semanteme of the client corresponding node of direction, also
Include: to be directed toward according to the semanteme of the client, corresponding answer is found out from preset answer library, and export to the client.
Optionally, the dialog text to the client carries out semantic analysis, determines that the semantic of the client is directed toward, packet
It includes: extracting the keyword and entity of the dialog text;According to extracted keyword and entity, the language of the client is confirmed
Justice is directed toward.
The embodiment of the present invention also provides a kind of Interface, comprising: acquiring unit, suitable for obtaining the dialog text of client;
Semantic analysis unit is suitable for carrying out semantic analysis to the dialog text, determines that the semantic of the client is directed toward;Determination unit,
Suitable for being directed toward according to the semanteme of the client, determination is corresponding with the semanteme of client direction from preset dialogue digraph
Node, the node include transition node and ending node;Output unit, suitable for corresponding to the node, art is exported to institute
State client.
Optionally, the output unit is further adapted for before the dialog text for obtaining client, obtains institute according to application scenarios
Art if the start node in dialogue digraph corresponds to is stated, and is exported to the client.
Optionally, art includes any of the following if the start node is corresponding: client identity verifies words art, business needs
It implores and knows words art, words of greeting art, opening remarks guidance words art.
Optionally, the output unit is further adapted for working as the semanteme not found from the dialogue digraph with the client
When being directed toward corresponding node, obtains art if presetting and export to the client.
Optionally, the output unit is further adapted for working as the semanteme not found from the dialogue digraph with the client
When being directed toward corresponding node, it is directed toward according to the semanteme of the client, finds out corresponding answer from preset answer library, and export
To the client.
Optionally, the semantic analysis unit, the keyword and entity of the dialog text suitable for extracting the client;Root
According to extracted keyword and entity, confirm that the semantic of the client is directed toward.
The embodiment of the present invention also provides a kind of Interface, including memory and processor, is stored on the memory
The computer instruction that can be run on the processor, the processor execute any of the above-described kind when running the computer instruction
The step of dialogue method.
The embodiment of the present invention also provides a kind of computer readable storage medium, and computer readable storage medium is non-volatile
Storage medium or non-transitory storage media, are stored thereon with computer instruction, and the computer instruction executes above-mentioned when running
A kind of the step of dialogue method.
Compared with prior art, the technical solution of the embodiment of the present invention has the advantages that
It is determining with the client's from preset dialogue digraph according to the corresponding semantic direction of the dialog text of client
Semanteme is directed toward corresponding node, and art if node correspondence is exported to client.Since output to art if client is from pre-
If dialogue digraph in find out, the art process so as to efficiently control the dialogue with client, dialogue digraph institute
Client questions are replied in the range of restriction and are asked a question to client, planless chat is avoided, it is thus possible to improve dialogue effect
Rate.
Detailed description of the invention
Fig. 1 is the flow chart of one of embodiment of the present invention dialogue method;
Fig. 2 is the schematic diagram of one of embodiment of the present invention dialogue digraph;
Fig. 3 is the structural schematic diagram of one of embodiment of the present invention Interface.
Specific embodiment
To talk with robot usage scenario relatively common at present still to market in customer service, these scenes words art is relatively easy,
Very high design tactics are not often needed.When talking with scene of the robot for some complexity, it is lower to there is dialogue efficiency
Problem.
In the embodiment of the present invention, according to the corresponding semantic direction of the dialog text of client, from preset dialogue digraph
Confirm node corresponding with the semanteme of client direction, and art if node correspondence is exported to client.Due to output
It is found out from preset dialogue digraph to art if client, the art stream so as to efficiently control the dialogue with client
Journey replys client questions in dialogue digraph limited range and asks a question to client, avoids planless chat, because
This, can be improved dialogue efficiency.
It is understandable to enable the above-mentioned purpose, feature and beneficial effect of the embodiment of the present invention to become apparent, below with reference to attached
Figure is described in detail specific embodiments of the present invention.
Referring to Fig.1, a kind of flow chart of dialogue method in the embodiment of the present invention is given.It may include steps of:
Step 11, the dialog text of client is obtained.
In specific implementation, in application scenes, client, can be with when seeking advice from using product or for product
It converses with dialogue robot to obtain the information wanted to know about.In other application scenarios, dialogue robot executes one
When a little business, can actively with corresponding trade connection.Text chat interface can be passed through between client and dialogue robot
It engages in the dialogue, can also be engaged in the dialogue by phone.
In embodiments of the present invention, the dialog text of client can be obtained from the dialogue that text chat interface generates;?
Client can be converted into corresponding text with the conversation audio of dialogue robot, and obtain client from the text being converted to
Dialog text.The dialog text of client can be client's answer given aiming at the problem that talking with robot and proposing, can also
Think the problem of client proposes.
Step 12, semantic analysis is carried out to the dialog text, determines that the semantic of the client is directed toward.
In specific implementation, after getting the dialog text of client, the dialog text of client can be carried out semantic
Analysis determines that the semantic of the client is directed toward.In embodiments of the present invention, can extract the keyword in client's dialog text with
And entity, and semantic analysis is carried out to the dialog text of client according to extracted keyword and entity, determine the semanteme of client
It is directed toward.
For example, the problem of dialogue robot are as follows: be the loan of your oneself application? the dialog text of client are as follows: yes, I
It is the loan of application in 2019.Semantic analysis is carried out for the dialog text of client, determining that the semanteme of client is oriented to is client
The loan of my application.
Step 13, it is directed toward according to the semanteme of the client, the determining language with the client from preset dialogue digraph
Justice is directed toward corresponding node.
In specific implementation, for different business demands, dialogue digraph can be preset respectively, it is oriented talking with
Under the guidance of figure, dialogue robot can carry out self-service dialogue with client.
In dialogue digraph, transition node and ending node can be set.Talk with robot in pair with client
It during words, can be directed toward, be found out from preset dialogue digraph opposite with the semantic direction of client according to the semanteme of client
The transition node answered or ending node, wherein when client it is semantic be directed toward corresponding ending node or when detecting it is complete
When at setting task, corresponding ending node in dialogue digraph can be jumped to.
Step 14, art is exported to the client if the node being corresponded to.
In specific implementation, talk with node different in digraph and be corresponding with art if difference.When in dialogue digraph
After finding node corresponding with the semanteme of client direction, art is exported to client if the node found is corresponded to.
It can be by audio side when talking with robot using audible and client's dialogue according to application scenarios difference
Formula is exported art is talked about to client;When talking with robot and being talked with using text mode and client, can by way of text incite somebody to action
Words art is exported to client.
By above scheme it is found that according to the corresponding semantic direction of dialog text of client, from preset dialogue digraph
Confirm node corresponding with the semanteme of client direction, and art if node correspondence is exported to client.Due to output
It is found out from preset dialogue digraph to art if client, the art stream so as to efficiently control the dialogue with client
Journey replys client questions in dialogue digraph limited range and asks a question to client, avoids planless chat, because
This, can be improved dialogue efficiency.
In addition, can clearly know that the dialogue for talking with robot and client is currently at dialogue and has using dialogue digraph
Which node into figure, when there is accident or failure, can be read fastly in dialogue robot and the dialog procedure of client
Orientation problem node simultaneously knows association variation brought by some node variations.
In specific implementation, in order to enable the dialogue of dialogue robot and client are more smooth, purpose is more clear, user's body
It tests more preferably, in embodiments of the present invention, before the dialog text for obtaining client, opening in the available dialogue digraph
Art if beginning node is corresponding, and export to the client.
It in embodiments of the present invention, can be in dialogue digraph for different tasks or different application scenarios
Start node, and the art for the start node of different types of application scenarios setting correspondence are set.
In specific implementation, if start node is corresponding art may include it is following any one: client identity verify words art,
Business demand informs words art, words of greeting art, opening remarks guidance words art.It is understood that may be used also according to practical application request
What other said art is arranged, herein without limitation.
For example, dialogue robot is using the start node pair for talking with digraph in creditor's identity verification application scenarios
Art is that client identity verifies words art if answering.After talking with robot foundation and the communication connection of client, export to client's
Talk about art are as follows: may I ask is Li Si?
In specific implementation, start node can be arranged according to practical application request, it may for some specific scenes
Setting start node is not needed.For example, in the case of can determine that client identity, then it need not be in start node to client's
Identity is verified, and so as to simplify workflow, promotes working efficiency, and avoids causing user discontented because repeating to verify.
In practical applications, since client is in dialog procedure, some not phases with current session theme may be proposed suddenly
The problem of pass, further increases dialogue efficiency, implements in the present invention in order to effectively control conversation process and dialogue trend
It is available default when not found from the dialogue digraph with the semanteme of the client corresponding node of direction in example
If art and export to the client.Export to client it is default if art, dialogue digraph can be revert to for guidance user
Art if middle corresponding node, or art if the unified format of setting.
For example, dialogue robot, which was exported to the problem of client, is: asking when dialogue robot executes credit return visit task
Ask whether you are satisfied with the service for the staff Zhang San that credit operation is handled for you.Client answers: Zhang San's that day recommends for me
What dining room is the dish in a dining room near company all well and good, I forgets dining room name, you are able to tell that I is? talk with machine
People carries out semantic analysis to the dialog text that client answers, and confirms semantic direction, does not find in dialogue digraph and refers to semanteme
To corresponding node, exports art if set unified format: aiming at the problem that you, cannot temporarily be answered accordingly to you
It is multiple, it is sorry.After art if the unified format of output, problem " can also be may I ask you to the work for handling credit operation person for you
Whether the service for making personnel Zhang San is satisfied with " it is exported again to client, to ensure being normally carried out for conversation process.
In order to further promote user experience, when not finding semanteme with the client from the dialogue digraph
When being directed toward corresponding node, it can also be directed toward according to the semanteme of the client, find out corresponding answer from preset answer library,
And it exports to the client.
Referring to Fig. 2, a kind of schematic diagram for talking with digraph in the embodiment of the present invention is given.The shown dialogue of Fig. 2 is oriented
It include start node Q1 in figure;Transition node Q1.1, Q1.2, Q1.1.1, Q2.1, Q2.2, Q2.3, Q2.4, Q1.2;Finish up node
E1,E2,E3,E4.Talk with digraph in directed edge A1.1, A1.2, A1.1.1, A2.1, A2.2, A2.3, A2.4, A3.1,
A3.2, A3.3 are that the semantic of client is directed toward.In practical applications, the number of transition node, oriented based on the difference of application scenarios
Connection whether setting and between transition node and transition node of the number on side, the number for the node that finishes up, start node is closed
System is different.
When being engaged in the dialogue based on dialogue digraph, node is to export to client art in the every wheel dialogue of dialogue robot,
Directed edge between node and node is that semanteme of the client in every wheel dialogue is directed toward, and different semantic are directed toward correspond to different sections
Point, art if the output of different node on behalf dialogues robot is different.
Does is for example, start node Q1 output words art: may I ask Mr. Li Si? client answers: not being.According to the dialogue of client text
This "no", the semantic A1.2 that is directed toward corresponds to transition node Q1.2 in dialogue digraph.Art if Q1.2 is corresponded to: it " conveniently allows
Mr. Li Si receives calls? " it exports to client.Client answers: inconvenient.According to the dialog text " inconvenience " of client, right
It talks about the semantic A3.2 that is directed toward in digraph and corresponds to ending node E2.Art if the node E2 that will finish up is corresponding: " leave you alone, then
See." export to client.
Dialogue method provided in an embodiment of the present invention can be applied to creditor's identity verification, loan is paid a return visit, loan is related
Some business scenarios relevant to credit such as questionnaire survey, consulting in or other and the incoherent business scenario of credit.Root
It can be the corresponding dialogue digraph of task design of setting according to the actual demand of different business scenarios, have in design dialogue
It is designed into dialogue digraph to semanteme direction a possibility that when scheming, as far as possible answer client, and is directed to all possible answer
Corresponding node is designed, and prepares accordingly art, and the variability in view of talking in client's dialog procedure for each node
And flexibility, it would be possible to directed edge can be added between related node.So that talking with robot when talking with client, as far as possible
According to the dialogue paths that provide in dialogue digraph, the progress of the orderly art according to setting node one by one.
For example, referring to Fig. 2, the art if output transition node Q1.1 is corresponding: " may I ask loan is that you apply yourself? "
Later, if client answers: " yes ".Enter transition node Q1.1.1 according to the semantic A1.1.1 that is directed toward of the answer " yes " of client.
Export Q1.1.1 it is corresponding if art " may I ask you is the loan when applied " to client.Client answers: on March 19th, 2019 Shen
Loan please.It is directed toward A2.1 for the semantic of answer " loan filed on March 19th, 2019 " of client, into node Q2.1,
Export art if transition node Q2.1 is corresponded to.
For another example, referring to Fig. 2, the art if output transition node Q1.1 is corresponding: " may I ask loan is what you applied? " it
Afterwards, if client answers: " yes, loan filed on March 19th, 2019 ", for answer " yes, on March 19th, 2019 of client
The loan done " carries out semantic analysis, determines that the corresponding transition node Q2.1 of semantic direction A2.1, output transition node Q2.1 are corresponding
If art.
Better understand and realize that the embodiment of the present invention, the embodiment of the present invention also provide one for the ease of those skilled in the art
Kind Interface.
Referring to Fig. 3, a kind of structural schematic diagram of Interface in the embodiment of the present invention is given.The Interface 30 can
To include: acquiring unit 31, semantic analysis unit 32, determination unit 33 and output unit 34, in which:
Acquiring unit 31, suitable for obtaining the dialog text of client;
Semantic analysis unit 32 carries out semantic analysis suitable for the dialog text to the client, determines the language of the client
Justice is directed toward;
Determination unit 33, suitable for according to the client semanteme be directed toward, from preset dialogue digraph determination with it is described
The semanteme of client is directed toward corresponding node, and the node includes: transition node and ending node;
Output unit 34, suitable for corresponding to the node, art is exported to the client.
In specific implementation, the output unit 34 is further adapted for before the dialog text for obtaining client, according to applied field
Art if the start node that scape obtains in the dialogue digraph corresponds to, and export to the client.
In specific implementation, art includes any of the following if the start node is corresponding: client identity verification words art,
Business demand informs words art, words of greeting art, opening remarks guidance words art.
In specific implementation, the output unit 34 is further adapted for working as and not find and the visitor from the dialogue digraph
When the semanteme at family is directed toward corresponding node, obtains art if presetting and export to the client.
In specific implementation, the output unit 34 is further adapted for working as and not find and the visitor from the dialogue digraph
When the semanteme at family is directed toward corresponding node, it is directed toward according to the semanteme of the client, finds out corresponding answer from preset answer library
Case, and export to the client.
In specific implementation, the semantic analysis unit 32, suitable for extract the client dialog text keyword with
And entity;According to extracted keyword and entity, confirm that the semantic of the client is directed toward.
In specific implementation, the working principle and workflow of the Interface 30, can be with reference to the above-mentioned reality of the present invention
The description in the dialogue method provided in example is applied, details are not described herein again.
The embodiment of the present invention also provides a kind of Interface, including memory and processor, is stored on the memory
The computer instruction that can be run on the processor, the processor, which executes the present invention when running the computer instruction, to be implemented
The step of any of the above-described kind of dialogue method that example provides.
The embodiment of the present invention also provides a kind of computer readable storage medium, and computer readable storage medium is non-volatile
Storage medium or non-transitory storage media, are stored thereon with computer instruction, and the computer instruction executes the present invention when running
The step of any of the above-described kind of dialogue method that embodiment provides.
Those of ordinary skill in the art will appreciate that all or part of the steps in the various methods of above-described embodiment is can
It is completed with instructing relevant hardware by program, which can store in any computer readable storage medium storing program for executing, deposit
Storage media may include: ROM, RAM, disk or CD etc..
Although present disclosure is as above, present invention is not limited to this.Anyone skilled in the art are not departing from this
It in the spirit and scope of invention, can make various changes or modifications, therefore protection scope of the present invention should be with claim institute
Subject to the range of restriction.
Claims (14)
1. a kind of dialogue method characterized by comprising
Obtain the dialog text of client;
Semantic analysis is carried out to the dialog text, determines that the semantic of the client is directed toward;
It is directed toward according to the semanteme of the client, determination is corresponding with the semanteme of client direction from preset dialogue digraph
Node, the node include transition node and ending node;
Art is exported to the client if the node is corresponded to.
2. dialogue method according to claim 1, which is characterized in that before the dialog text for obtaining client, further includes:
Art if the start node in the dialogue digraph corresponds to is obtained according to application scenarios, and is exported to the client.
3. dialogue method according to claim 2, which is characterized in that art includes following if the start node is corresponding
It anticipates one kind:
Client identity verifies words art, business demand informs words art, words of greeting art, opening remarks guidance words art.
4. dialogue method according to claim 1, which is characterized in that when do not found from the dialogue digraph with it is described
When the semanteme of client is directed toward corresponding node, further includes: obtain art if presetting and export to the client.
5. dialogue method according to claim 4, which is characterized in that when do not found from the dialogue digraph with it is described
When the semanteme of client is directed toward corresponding node, further includes: be directed toward according to the semanteme of the client, found out from preset answer library
Corresponding answer, and export to the client.
6. dialogue method according to claim 1, which is characterized in that the dialog text to the client carries out semantic
Analysis determines that the semantic of the client is directed toward, comprising:
Extract the keyword and entity of the dialog text;
According to extracted keyword and entity, confirm that the semantic of the client is directed toward.
7. a kind of Interface characterized by comprising
Acquiring unit, suitable for obtaining the dialog text of client;
Semantic analysis unit is suitable for carrying out semantic analysis to the dialog text, determines that the semantic of the client is directed toward;
Determination unit, it is determining with the client's from preset dialogue digraph suitable for being directed toward according to the semanteme of the client
Semanteme is directed toward corresponding node, and the node includes transition node and ending node;
Output unit, suitable for corresponding to the node, art is exported to the client.
8. Interface according to claim 7, which is characterized in that the output unit is further adapted for obtaining client's
Before dialog text, art if the start node in the dialogue digraph corresponds to is obtained according to application scenarios, and export to institute
State client.
9. Interface according to claim 8, which is characterized in that art includes following if the start node is corresponding
It anticipates one kind:
Client identity verifies words art, business demand informs words art, words of greeting art, opening remarks guidance words art.
10. Interface according to claim 7, which is characterized in that the output unit is further adapted for working as from the dialogue
When do not found in digraph with the semanteme of the client corresponding node of direction, obtains art if presetting and export to the visitor
Family.
11. Interface according to claim 10, which is characterized in that the output unit is further adapted for working as from described right
It does not find when being directed toward corresponding node with the semanteme of the client, is directed toward according to the semanteme of the client, from pre- in words digraph
If answer library in find out corresponding answer, and export to the client.
12. Interface according to claim 7, which is characterized in that the semantic analysis unit is suitable for extracting the visitor
The keyword and entity of the dialog text at family;According to extracted keyword and entity, confirm that the semantic of the client is directed toward.
13. a kind of Interface, including memory and processor, it is stored with and can runs on the processor on the memory
Computer instruction, which is characterized in that perform claim requires any one of 1 to 6 when the processor runs the computer instruction
The step of described dialogue method.
14. a kind of computer readable storage medium, computer readable storage medium is non-volatile memory medium or non-transient deposits
Storage media is stored thereon with computer instruction, which is characterized in that perform claim requires 1 to 6 when the computer instruction is run
The step of dialogue method described in one.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910233200.4A CN110069600A (en) | 2019-03-26 | 2019-03-26 | Dialogue method and device, computer readable storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910233200.4A CN110069600A (en) | 2019-03-26 | 2019-03-26 | Dialogue method and device, computer readable storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110069600A true CN110069600A (en) | 2019-07-30 |
Family
ID=67366766
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910233200.4A Pending CN110069600A (en) | 2019-03-26 | 2019-03-26 | Dialogue method and device, computer readable storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110069600A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111563151A (en) * | 2020-05-07 | 2020-08-21 | 腾讯科技(深圳)有限公司 | Information acquisition method, session configuration device and storage medium |
CN112347237A (en) * | 2020-11-19 | 2021-02-09 | 龙马智芯(珠海横琴)科技有限公司 | Question-answering method and device, server and readable storage medium |
WO2021120563A1 (en) * | 2019-12-20 | 2021-06-24 | 苏宁易购集团股份有限公司 | Method and system for quickly locating problem in chatbot |
CN113256395A (en) * | 2021-06-23 | 2021-08-13 | 中国平安人寿保险股份有限公司 | Product recommendation method, device, equipment and storage medium based on recommendation graph network |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106528613A (en) * | 2016-05-26 | 2017-03-22 | 中科鼎富(北京)科技发展有限公司 | Intelligent question-answer (Q&A) method and device |
CN107239450A (en) * | 2017-06-02 | 2017-10-10 | 上海对岸信息科技有限公司 | Natural language method is handled based on Interaction context |
CN108073587A (en) * | 2016-11-09 | 2018-05-25 | 阿里巴巴集团控股有限公司 | A kind of automatic question-answering method, device and electronic equipment |
-
2019
- 2019-03-26 CN CN201910233200.4A patent/CN110069600A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106528613A (en) * | 2016-05-26 | 2017-03-22 | 中科鼎富(北京)科技发展有限公司 | Intelligent question-answer (Q&A) method and device |
CN108073587A (en) * | 2016-11-09 | 2018-05-25 | 阿里巴巴集团控股有限公司 | A kind of automatic question-answering method, device and electronic equipment |
CN107239450A (en) * | 2017-06-02 | 2017-10-10 | 上海对岸信息科技有限公司 | Natural language method is handled based on Interaction context |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2021120563A1 (en) * | 2019-12-20 | 2021-06-24 | 苏宁易购集团股份有限公司 | Method and system for quickly locating problem in chatbot |
CN111563151A (en) * | 2020-05-07 | 2020-08-21 | 腾讯科技(深圳)有限公司 | Information acquisition method, session configuration device and storage medium |
CN111563151B (en) * | 2020-05-07 | 2024-02-02 | 腾讯科技(深圳)有限公司 | Information acquisition method, session configuration method, device and storage medium |
CN112347237A (en) * | 2020-11-19 | 2021-02-09 | 龙马智芯(珠海横琴)科技有限公司 | Question-answering method and device, server and readable storage medium |
CN113256395A (en) * | 2021-06-23 | 2021-08-13 | 中国平安人寿保险股份有限公司 | Product recommendation method, device, equipment and storage medium based on recommendation graph network |
CN113256395B (en) * | 2021-06-23 | 2023-11-24 | 中国平安人寿保险股份有限公司 | Product recommendation method, device, equipment and storage medium based on recommendation graph network |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110069600A (en) | Dialogue method and device, computer readable storage medium | |
US10554817B1 (en) | Automation of contact workflow and automated service agents in contact center system | |
WO2020210580A1 (en) | Maintaining machine language model state across communications channels | |
AU2019226252A1 (en) | Transactional conversation - based computing system | |
CN108021934B (en) | Method and device for recognizing multiple elements | |
CN109583746B (en) | Method and device for setting routing rule of flow and readable storage medium | |
AU2017251686A1 (en) | Intelligent automated agent for a contact center | |
US9552512B2 (en) | Personalized, automated receptionist | |
WO2016205818A1 (en) | Method and apparatus for managing customer interactions on multiple interaction channels | |
CN108038687B (en) | Transaction method based on voice recognition, server and computer-readable storage medium | |
CN108985358A (en) | Emotion identification method, apparatus, equipment and storage medium | |
US9319527B2 (en) | System and method for providing improved wait time estimates | |
CN109002515A (en) | A kind of method and apparatus of intelligent response | |
CN112840628A (en) | Evidence recording of human-computer interaction communication | |
US10318639B2 (en) | Intelligent action recommendation | |
US8903052B2 (en) | Voice print tagging of interactive voice response sessions | |
CN111597312A (en) | Method and device for generating multi-turn dialogue script | |
US11743378B1 (en) | Intelligent agent assistant for natural language understanding in a customer service system | |
US10354654B2 (en) | Conversation structure analysis | |
CN115129878B (en) | Conversation service execution method, device, storage medium and electronic equipment | |
CN110675867A (en) | Intelligent dialogue method and device, computer equipment and storage medium | |
CN106888446B (en) | Methods, devices and systems for verification information recipient's property right identity | |
KR102196167B1 (en) | Method for evaluating social intelligence and apparatus using the same | |
US20170124518A1 (en) | Facilitating meetings | |
CN111508471B (en) | Speech synthesis method and device, electronic equipment and storage 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 | ||
TA01 | Transfer of patent application right | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20191225 Address after: 200062 floor 6, building 21, No. 958, Zhenbei Road, Putuo District, Shanghai Applicant after: Shanghai qiaopan Technology Co., Ltd Address before: No. 10 and No. 20, Lane 999, Dangui Road, China (Shanghai) Free Trade Pilot Area, Pudong New Area, Shanghai, 200120 Applicant before: SHANGHAI PPDAI FINANCE INFORMATION SERVICE CO., LTD. |
|
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190730 |