CN112699221A - Multi-scene task flow system in intelligent customer service - Google Patents

Multi-scene task flow system in intelligent customer service Download PDF

Info

Publication number
CN112699221A
CN112699221A CN202110018983.1A CN202110018983A CN112699221A CN 112699221 A CN112699221 A CN 112699221A CN 202110018983 A CN202110018983 A CN 202110018983A CN 112699221 A CN112699221 A CN 112699221A
Authority
CN
China
Prior art keywords
scene
module
scenario
intention
switching
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
Application number
CN202110018983.1A
Other languages
Chinese (zh)
Inventor
娄鑫
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Icsoc Beijing Communication Technology Co ltd
Original Assignee
Icsoc Beijing Communication Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Icsoc Beijing Communication Technology Co ltd filed Critical Icsoc Beijing Communication Technology Co ltd
Priority to CN202110018983.1A priority Critical patent/CN112699221A/en
Publication of CN112699221A publication Critical patent/CN112699221A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33Querying
    • G06F16/332Query formulation
    • G06F16/3329Natural language query formulation or dialogue systems
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33Querying
    • G06F16/3331Query processing
    • G06F16/334Query execution
    • G06F16/3344Query execution using natural language analysis
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00Handling natural language data
    • G06F40/20Natural language analysis
    • G06F40/279Recognition of textual entities
    • G06F40/289Phrasal analysis, e.g. finite state techniques or chunking
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00Handling natural language data
    • G06F40/30Semantic analysis

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • General Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Mathematical Physics (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • General Health & Medical Sciences (AREA)
  • Human Computer Interaction (AREA)
  • Machine Translation (AREA)

Abstract

The invention discloses a multi-scene task flow transfer system in intelligent customer service, which comprises: the device comprises an intention identification module, a scene matching module, a scene switching module and a storage module, wherein after the intention identification module identifies conversation intents, corresponding scenes are matched through the scene matching module, the scene switching module is used for switching to the matched scenes, multi-round scene interaction is achieved, and the storage module stores multi-round conversations under each scene, so that scene switching back is facilitated. The invention solves the problem that the matching of the existing man-machine conversation scene cannot be adjusted in time.

Description

Multi-scene task flow system in intelligent customer service
Technical Field
The invention relates to the field of dialog scene matching, in particular to a multi-scene task flow system in intelligent customer service.
Background
The multi-scenario task flow technology is mainly applied to man-machine conversation scenarios under customer service scenarios, conversation can jump from one scenario to another at any time, and the robot can jump according to the scenario change at any time. In a man-machine conversation scene, the thought of a person is changeable, and various questions can be asked at any time, so that if the robot cannot respond to the questions of the person, the robot cannot answer the questions, the effect is poor, and the experience is influenced.
Disclosure of Invention
Therefore, the invention provides a multi-scene task flow system in intelligent customer service, which aims to solve the problem that the existing man-machine conversation scene cannot be adjusted and matched in time.
In order to achieve the above purpose, the invention provides the following technical scheme:
the invention discloses a multi-scene task flow transfer system in intelligent customer service, which comprises: the device comprises an intention identification module, a scene matching module, a scene switching module and a storage module, wherein after the intention identification module identifies conversation intents, corresponding scenes are matched through the scene matching module, the scene switching module is used for switching to the matched scenes, multi-round scene interaction is achieved, and the storage module stores multi-round conversations under each scene, so that scene switching back is facilitated.
Furthermore, the intention recognition module carries out semantic understanding through a mode combining a semantic grammar algorithm and a deep learning multiple algorithms, and recognizes the intention of the user dialogue in the man-machine dialogue.
Further, the scene matching module matches a corresponding scene in the plurality of scenes with answers to the plurality of dialogue questions according to the user intention identified by the intention identification module.
Further, the scene switching module switches the matched scene, and performs multiple rounds of dialogue question answering after switching to the scene matched with the user intention.
Further, when the user performs multi-scene interaction and the problem of non-local scenes occurs, the scene switching module identifies the intention to be matched with other scenes through the intention identification module and utilizes the scene switching module to switch the scenes in time.
Furthermore, the storage module stores each pair of conversation processes, and after the current conversation is finished, the stored context information is acquired and is switched to the last completed scene conversation through the scene switching module.
The invention has the following advantages:
the invention discloses a multi-scene task flow system in intelligent customer service, which can greatly improve the experience of human-computer interaction by means of a scene switching technology and avoid conversation interruption caused by the fact that a user cannot return to a previous conversation scene after a scene is temporarily switched. By storing multiple rounds of conversations, scenes are timely converted, and user experience is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It should be apparent that the drawings in the following description are merely exemplary, and that other embodiments can be derived from the drawings provided by those of ordinary skill in the art without inventive effort.
The structures, ratios, sizes, and the like shown in the present specification are only used for matching with the contents disclosed in the specification, so as to be understood and read by those skilled in the art, and are not used to limit the conditions that the present invention can be implemented, so that the present invention has no technical significance, and any structural modifications, changes in the ratio relationship, or adjustments of the sizes, without affecting the effects and the achievable by the present invention, should still fall within the range that the technical contents disclosed in the present invention can cover.
Fig. 1 is a flowchart of a multi-scenario task flow system in an intelligent customer service according to an embodiment of the present invention;
Detailed Description
The present invention is described in terms of particular embodiments, other advantages and features of the invention will become apparent to those skilled in the art from the following disclosure, and it is to be understood that the described embodiments are merely exemplary of the invention and that it is not intended to limit the invention to the particular embodiments disclosed. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Examples
The embodiment discloses a multi-scene task flow transfer system in intelligent customer service, which comprises: the device comprises an intention identification module, a scene matching module, a scene switching module and a storage module, wherein after the intention identification module identifies conversation intents, corresponding scenes are matched through the scene matching module, the scene switching module is used for switching to the matched scenes, multi-round scene interaction is achieved, and the storage module stores multi-round conversations under each scene, so that scene switching back is facilitated.
The intention recognition module carries out semantic understanding through a mode combining a semantic grammar algorithm and a deep learning multiple algorithms, and recognizes the intention of user conversation in man-machine conversation. And after receiving the actual man-machine conversation sentences, the semantic grammar algorithm module splits the question sentences, matches the split words with words in a database, stores intention analysis of a plurality of conversations in the database, and analyzes the conversation intention according to the matched words. Or automatically recognizing the intention of the sentence text of the newly input man-machine conversation by utilizing a semantic model of a deep learning algorithm.
The scene matching module matches corresponding scenes in the plurality of scenes according to the user intentions identified by the intention identification module, and the corresponding scenes are provided with answers of a plurality of dialogue questions; the scene switching module switches the matched scene to a scene matched with the user intention and then carries out multi-turn dialogue question answering; the storage module stores a plurality of turns of conversations. When a user carries out multi-scene interaction and the problem of non-scene occurs, the scene switching module identifies the intention to be matched with other scenes through the intention identification module and utilizes the scene switching module to switch the scene in time. If the intention of the user can not be matched with the questions in the current multi-turn scenes, other scenes or the questions and answers of the common question items and the answers FAQ corresponding to the questions are continuously matched, and after the matching, the user can directly jump to the past.
And after the current round of conversation is finished, the stored context information is acquired, and the conversation is switched to the last completed scene conversation through the scene switching module, so that the phenomenon that the scene is switched and the former conversation scene is lost is avoided.
The embodiment discloses a multi-scene task circulation system in intelligent customer service, which can greatly improve the experience of human-computer interaction by means of a scene switching technology, and avoids the problem that after a scene is temporarily switched, the user cannot return to the previous conversation scene, so that conversation is interrupted. By storing multiple rounds of conversations, scenes are timely converted, and user experience is improved.
Although the invention has been described in detail above with reference to a general description and specific examples, it will be apparent to one skilled in the art that modifications or improvements may be made thereto based on the invention. Accordingly, such modifications and improvements are intended to be within the scope of the invention as claimed.

Claims (6)

1. A multi-scenario task flow system in intelligent customer service is characterized by comprising: the device comprises an intention identification module, a scene matching module, a scene switching module and a storage module, wherein after the intention identification module identifies conversation intents, corresponding scenes are matched through the scene matching module, the scene switching module is used for switching to the matched scenes, multi-round scene interaction is achieved, and the storage module stores multi-round conversations under each scene, so that scene switching back is facilitated.
2. The system of claim 1, wherein the intent recognition module recognizes intent of user dialog in human-machine dialog by semantic comprehension through a combination of semantic grammar algorithms and deep learning algorithms.
3. The intelligent multi-scenario task flow system of claim 1, wherein the scenario matching module matches a corresponding scenario among a plurality of scenarios according to the user's intention identified by the intention identification module, the corresponding scenario having a plurality of answers to the dialog questions.
4. The multi-scenario task flow-through system in intelligent customer service as claimed in claim 1, wherein the scenario switching module switches the matched scenario to a scenario matching the user's intention, and then performs multiple rounds of dialogue question answering.
5. The system of claim 1, wherein the scene switching module identifies other scenes matching the intention through the intention identification module after a problem other than the scene occurs during the multi-scene interaction of the user, and switches the scene in time through the scene switching module.
6. The system of claim 1, wherein the storage module stores each round of session process, and after the session is completed, the stored context information is obtained and switched to the last completed session by the session switching module.
CN202110018983.1A 2021-01-07 2021-01-07 Multi-scene task flow system in intelligent customer service Pending CN112699221A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110018983.1A CN112699221A (en) 2021-01-07 2021-01-07 Multi-scene task flow system in intelligent customer service

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110018983.1A CN112699221A (en) 2021-01-07 2021-01-07 Multi-scene task flow system in intelligent customer service

Publications (1)

Publication Number Publication Date
CN112699221A true CN112699221A (en) 2021-04-23

Family

ID=75515038

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110018983.1A Pending CN112699221A (en) 2021-01-07 2021-01-07 Multi-scene task flow system in intelligent customer service

Country Status (1)

Country Link
CN (1) CN112699221A (en)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160085762A1 (en) * 2014-09-23 2016-03-24 Smoothweb Technologies Ltd. Multi-Scene Rich Media Content Rendering System
CN110609893A (en) * 2019-09-24 2019-12-24 大众问问(北京)信息科技有限公司 Question-answer interaction method, device, equipment and storage medium in multi-turn conversation scene
CN111049996A (en) * 2019-12-26 2020-04-21 苏州思必驰信息科技有限公司 Multi-scene voice recognition method and device and intelligent customer service system applying same

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160085762A1 (en) * 2014-09-23 2016-03-24 Smoothweb Technologies Ltd. Multi-Scene Rich Media Content Rendering System
CN110609893A (en) * 2019-09-24 2019-12-24 大众问问(北京)信息科技有限公司 Question-answer interaction method, device, equipment and storage medium in multi-turn conversation scene
CN111049996A (en) * 2019-12-26 2020-04-21 苏州思必驰信息科技有限公司 Multi-scene voice recognition method and device and intelligent customer service system applying same

Similar Documents

Publication Publication Date Title
CN107229684B (en) Sentence classification method and system, electronic equipment, refrigerator and storage medium
CN108197191B (en) A kind of scene intention interrupt method of more wheel dialogues
CN104965592A (en) Voice and gesture recognition based multimodal non-touch human-machine interaction method and system
CN110222162A (en) A kind of intelligent answer method based on natural language processing and knowledge mapping
CN108376144B (en) Man-machine multi-round conversation method for automatic scene switching based on deep neural network
CN106847274B (en) Man-machine interaction method and device for intelligent robot
CN111178081B (en) Semantic recognition method, server, electronic device and computer storage medium
US20190333514A1 (en) Method and apparatus for dialoguing based on a mood of a user
CN111816172A (en) Voice response method and device
US20210183388A1 (en) Voice recognition method and device, photographing system, and computer-readable storage medium
CN111768781A (en) Voice interruption processing method and device
CN113342945A (en) Voice session processing method and device
CN106971719A (en) A kind of offline changeable nonspecific sound speech recognition awakening method for waking up word
CN107742516B (en) Intelligent recognition method, robot and computer readable storage medium
CN116797695A (en) Interaction method, system and storage medium of digital person and virtual whiteboard
CN111625629B (en) Task type dialogue robot response method and device, robot and storage medium
CN112699221A (en) Multi-scene task flow system in intelligent customer service
CN112015879B (en) Method and device for realizing man-machine interaction engine based on text structured management
CN109166572A (en) The method and reading machine people that robot is read
CN106910498A (en) The method for improving voice control command word discrimination
CN109960489B (en) Method, device, equipment, medium and question-answering system for generating intelligent question-answering system
CN104281609B (en) Configuration method and device for voice input instruction matching rule
CN111243587A (en) Voice interaction method, device, equipment and storage medium
CN111104504A (en) Natural language processing and knowledge graph based dialogue method
CN116129903A (en) Call audio processing method and device

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination