CN109767818A - A kind of customization medical treatment is answerred questions interrogation guidance system - Google Patents
A kind of customization medical treatment is answerred questions interrogation guidance system Download PDFInfo
- Publication number
- CN109767818A CN109767818A CN201811610325.6A CN201811610325A CN109767818A CN 109767818 A CN109767818 A CN 109767818A CN 201811610325 A CN201811610325 A CN 201811610325A CN 109767818 A CN109767818 A CN 109767818A
- Authority
- CN
- China
- Prior art keywords
- module
- interrogation
- questions
- client
- sentence
- 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
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
It answers questions interrogation guidance system the present invention provides a kind of customization medical treatment, is applied to hospital, including module of answering questions, interrogation module, warm field module, cover electric module, invite module.When work, it obtains client and inputs sentence, the system is using question sentence identification technology, name entity recognition techniques and intention assessment parsing sentence, when sentence is question sentence, module of answering questions described in starting, when the sentence is non-question sentence, start the interrogation module, it is intended to by identification client, interrogation is carried out to client, client is positioned and is classified;Described to start the electric module of warm field module, set when with customer communication and invite module, answer questions, field is warmed up in interrogation, and set electricity combines with effectively tissue is invited.
Description
Technical field
The present invention relates to artificial intelligence customer service technical field more particularly to a kind of customization medical treatment answer questions interrogation guidance system.
Background technique
With the development of NLP technology, the intelligent customer service system based on automatic question answering is more and more, but current intelligence visitor
Clothes are most of, and there are following two defects:
One, duplicate question and answer can only be solved the problems, such as, cannot accomplish the demand according to different clients, quickly make client's needs
Customization version chat robots.Current chat robots or be exactly the simple chat system towards general-purpose knowledge bases, such as
Siri, small ice of Microsoft etc.;It is exactly the question answering system of the similar expert system towards vertical field, such as IBM waston,
But both robots are not able to satisfy business application at present, provide because commercial customer service system does not require nothing more than to customer issue
Answer questions, by taking medical field as an example, it is also necessary to accomplish accurate interrogation according to the case where client, it is most important that extract the connection of client
It is mode and accomplishes that client is guided to carry out institute's observation, improves conversion ratio.
Two, current intelligent customer service system accomplishes to be answerred questions according to the different demands of each hospital well not yet, interrogation,
Warm field (asking personal information), set electricity are invited progress effectively tissue and are combined, accomplish that fast custom meets Different hospital requirement
Chat robots.
Summary of the invention
The present invention answers questions interrogation guidance system in order to solve the above technical problems, providing a kind of customization medical treatment, is applied to cure
Institute, including module of answering questions, interrogation module, warm field module, cover electric module, invite module, will answer questions, interrogation, warm up field, set electricity and invite
About effective knot of tissue is altogether;
The module of answering questions: the dialog history data provided in conjunction with hospital extract knowledge question from dialog history data
Dialogue, forms the knowledge base of answering questions of hospital;Identify what new client proposed by FAQ text similarity measurement algorithm and question sentence identification technology
Problem, answer questions described in matching the problems in knowledge base, and the corresponding answer of feedback.The key technology that the module relates generally to includes
FAQ is extracted and cleaning, the cluster-based storage of data and retrieval, the key technologies such as FAQ text similarity measurement algorithm and question sentence identification.
The interrogation module: the entity information that client proposes, such as medical project are identified by name entity recognition techniques
Information, medical location information, inquire the entity information by medical knowledge map, provide corresponding interrogation.The doctor
Map of gaining knowledge includes entity name and corresponding informance in medicine.
The warm field module: acquisition client personal information;
The set electricity module: setting covers electric trigger, and trigger condition is preset session operational scenarios, passes through intention assessment and life
Name entity recognition techniques identify the session operational scenarios, and when triggering the set electricity trigger, the system is to customer inquiries correspondent party
Formula;
The module of inviting: trigger is invited in setting, and trigger condition is preset session operational scenarios, passes through intention assessment and life
Name entity recognition techniques identify the session operational scenarios, and when inviting trigger described in triggering, the system is issued to client and invited.
When work, obtains client and input sentence, the system is using question sentence identification technology, name entity recognition techniques and meaning
Figure discriminance analysis sentence, when sentence is question sentence, module of answering questions described in starting, when the sentence is non-question sentence, described in starting
Interrogation module is intended to by identification client, is carried out interrogation to client, is positioned and classify to client;Meanwhile it described being handed over client
When stream, start warm field module, cover electric module and invite module.
Further, the module of answering questions extracts knowledge question dialogue using FAQ extraction algorithm from dialog history data.
Further, the module of answering questions is by the knowledge base deposit cluster of answering questions, and passes through ElasticSearch and phase
It answers questions knowledge base like described in degree algorithm accesses.
Further, when the entity information is multiple, the association of entity information is carried out by the medical knowledge map,
It carries out knowledge reasoning and provides corresponding interrogation in conjunction with multiple entity informations.
Further, art is set by hospital if the warm field module queries customer information, and different hospital's settings is not
Together, including within a preset time, when client does not answer, next client is accessed.
Further, the trigger condition of the set electricity trigger, triggering frequency and set telephony are set by hospital, different
The difference of hospital's setting, the trigger condition includes customer inquiries price.
Further, the trigger condition for inviting trigger, triggering frequency and invite words art set by hospital, it is different
The difference of hospital's setting, the trigger condition include that dialogue number reaches preset times.
By the above-mentioned description of this invention it is found that compared to the prior art, customization medical treatment of the invention is answerred questions interrogation guidance
System will effectively answer questions, interrogation, warm up field, and set electricity is invited modules and organically combined, is truly realized and fully understands client
The problem of problem, corresponding client, answers questions and interrogation, and carries out warm field according to hospital requirements, and set electricity is invited, to greatest extent
Client's conversion ratio is improved, simultaneously as having accomplished the removing between modules, can accomplish art if different hospital's answers
It is customized by each hospital oneself, realizes that Different hospital is able to carry out fast custom and meets art if oneself requirement, show that hospital is only
Special style, rather than machine-made conversational style.
Detailed description of the invention
The drawings described herein are used to provide a further understanding of the present invention, constitutes a part of the invention, this hair
Bright illustrative embodiments and their description are used to explain the present invention, and are not constituted improper limitations of the present invention.
Wherein:
Fig. 1 is a kind of operation schematic diagram of the medical interrogation guidance system of answering questions of customization of the present invention.
Specific embodiment
In order to be clearer and more clear technical problems, technical solutions and advantages to be solved, tie below
Drawings and examples are closed, the present invention will be described in further detail.It should be appreciated that specific embodiment described herein is only used
To explain the present invention, it is not intended to limit the present invention.
A kind of customization medical treatment is answerred questions interrogation guidance system, and hospital, including module of answering questions, interrogation module, warm field mould are applied to
Block covers electric module, invites module, will answer questions, interrogation, warm field, covers electricity and invites and effectively organizes to combine.
Wherein, the key technology that the module of answering questions relates generally to include FAQ extract and cleaning, the cluster-based storage of data and
Retrieval, the key technologies such as FAQ text similarity measurement algorithm and question sentence identification, in conjunction with the dialog history data that hospital provides, using FAQ
Extraction algorithm extracts knowledge question dialogue from dialog history data, forms the knowledge base of answering questions of hospital, and described answer questions is known
Know inventory and enter cluster, and passes through knowledge base of answering questions described in ElasticSearch and similarity algorithm access.When work, pass through FAQ
Text similarity measurement algorithm and question sentence identification technology identify the problem of new client proposes, the problems in knowledge base of answering questions described in matching,
And the corresponding answer of feedback.
The interrogation module identifies the entity information that client proposes, such as medical project letter by name entity recognition techniques
Breath, medical location information, such as rhinitis, by the medical knowledge map pair for including entity name and corresponding informance in medicine
The entity information is inquired, and corresponding interrogation is provided.When the entity information is multiple, for example, upper half sentence is to identify item
Mesh augmentation rhinoplasty, lower half sentence identify prosthese, and the association of entity information is carried out by the medical knowledge map, carry out knowledge reasoning,
Inferring content that the client to be seeked advice from is prosthese augmentation rhinoplasty, without that should rest on topic in prosthese introduction or other grand
In nose scheme.
The warm field module is for acquiring client personal information, the age including user, height and weight etc..The warm field mould
Art is set by hospital if block inquiry customer information, the difference of different hospital's settings, including within a preset time, client does not have
When answer, next client is accessed.
The set electricity module: setting covers electric trigger, and trigger condition is preset session operational scenarios, passes through intention assessment and life
Name entity recognition techniques identify the session operational scenarios, and when triggering the set electricity trigger, the system is to customer inquiries correspondent party
Formula, including phone, mailbox, wechat, QQ etc..Trigger condition, triggering frequency and the set telephony of the set electricity trigger are by hospital
Setting, the difference of different hospital's settings, the trigger condition includes customer inquiries price.
The module of inviting: trigger is invited in setting, and trigger condition is preset session operational scenarios, passes through intention assessment and life
Name entity recognition techniques identify the session operational scenarios, and when inviting trigger described in triggering, the system is issued to client and invited.Institute
It states the trigger condition for inviting trigger, triggering frequency and invites words art and set by hospital, the difference of different hospital's settings is described
Trigger condition includes that dialogue number reaches preset times.
Referring to Fig. 1, obtaining client when work and inputting sentence, the system is known using question sentence identification technology, name entity
Other technology and intention assessment parsing sentence, when sentence is question sentence, module of answering questions described in starting is opened when sentence is non-question sentence
The interrogation module is moved, is intended to by identification client, interrogation is carried out to client, client is positioned and is classified;Meanwhile it is described with
When customer communication, start warm field module, cover electricity module and invite module, effectively combine and answer questions, field is warmed up in interrogation, and set is electric and invites
Modules.
The present invention is exemplarily described above in conjunction with attached drawing, it is clear that the present invention implements not by aforesaid way
Limitation, as long as the improvement for the various unsubstantialities that the inventive concept and technical scheme of the present invention carry out is used, or without changing
It is within the scope of the present invention into the conception and technical scheme of the invention are directly applied to other occasions.
Claims (7)
1. a kind of customization medical treatment is answerred questions, interrogation guides system, is applied to hospital, which is characterized in that including module of answering questions, interrogation mould
Block, covers electric module, invites module warm field module, will answer questions, interrogation, warm field, covers electricity and invites and effectively organizes to combine;
The module of answering questions: the dialog history data provided in conjunction with hospital extract knowledge question dialogue from dialog history data,
Form the knowledge base of answering questions of hospital;The problem of new client proposes is identified by FAQ text similarity measurement algorithm and question sentence identification technology,
It answers questions described in matching the problems in knowledge base, and the corresponding answer of feedback;
The interrogation module: the entity information that client proposes is identified by name entity recognition techniques, passes through medical knowledge map
The entity information is inquired, corresponding interrogation is provided;
The warm field module: acquisition client personal information;
The set electricity module: setting covers electric trigger, and trigger condition is preset session operational scenarios, real by intention assessment and name
Body identification technology identifies the session operational scenarios, and when triggering the set electricity trigger, the system is to customer inquiries contact method;Institute
State and invite module: trigger is invited in setting, and trigger condition is preset session operational scenarios, passes through intention assessment and name Entity recognition
Technology identifies the session operational scenarios, and when inviting trigger described in triggering, the system is issued to client and invited;
When work, obtains client and input sentence, the system is using question sentence identification technology, name entity recognition techniques and is intended to know
Other parsing sentence, when sentence is question sentence, module of answering questions described in starting starts the interrogation when the sentence is non-question sentence
Module is intended to by identification client, is carried out interrogation to client, is positioned and classify to client;It is described when with customer communication, starting
Warm field module covers electric module and invites module.
2. a kind of customization medical treatment according to claim 1 is answerred questions, interrogation guides system, which is characterized in that the module of answering questions
Knowledge question dialogue is extracted from dialog history data using FAQ extraction algorithm.
3. a kind of customization medical treatment according to claim 1 is answerred questions, interrogation guides system, which is characterized in that the module of answering questions
By the knowledge base deposit cluster of answering questions, and pass through knowledge base of answering questions described in ElasticSearch and similarity algorithm access.
4. a kind of customization medical treatment according to claim 1 is answerred questions, interrogation guides system, which is characterized in that when the entity is believed
When ceasing multiple, provides and accordingly ask in conjunction with multiple entity informations by the association that the medical knowledge map carries out entity information
It examines.
5. a kind of customization medical treatment according to claim 1 is answerred questions, interrogation guides system, which is characterized in that the warm field module
Art is set by hospital if inquiry customer information, including within a preset time, when client does not answer, accesses next client.
6. a kind of customization medical treatment according to claim 1 is answerred questions, interrogation guides system, which is characterized in that the set electricity triggering
Trigger condition, triggering frequency and the set telephony of device are set by hospital, and the trigger condition includes customer inquiries price.
7. a kind of customization medical treatment according to claim 1 is answerred questions, interrogation guides system, which is characterized in that described to invite triggering
It the trigger condition of device, triggering frequency and invites words art and is set by hospital, the trigger condition includes that dialogue number reaches default time
Number.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811610325.6A CN109767818A (en) | 2018-12-27 | 2018-12-27 | A kind of customization medical treatment is answerred questions interrogation guidance system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811610325.6A CN109767818A (en) | 2018-12-27 | 2018-12-27 | A kind of customization medical treatment is answerred questions interrogation guidance system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109767818A true CN109767818A (en) | 2019-05-17 |
Family
ID=66451024
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811610325.6A Pending CN109767818A (en) | 2018-12-27 | 2018-12-27 | A kind of customization medical treatment is answerred questions interrogation guidance system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109767818A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111063429A (en) * | 2019-10-25 | 2020-04-24 | 中国科学院自动化研究所 | Medical consultation method, device, equipment and computer-readable storage medium |
CN113360625A (en) * | 2021-07-02 | 2021-09-07 | 北京容联七陌科技有限公司 | Intelligent dialogue marketing customer acquisition method and system based on NLP |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104731895A (en) * | 2015-03-18 | 2015-06-24 | 北京京东尚科信息技术有限公司 | Auto-answer method and device |
CN107133349A (en) * | 2017-05-24 | 2017-09-05 | 北京无忧创新科技有限公司 | One kind dialogue robot system |
CN107247868A (en) * | 2017-05-18 | 2017-10-13 | 深思考人工智能机器人科技(北京)有限公司 | A kind of artificial intelligence aids in interrogation system |
CN107480450A (en) * | 2017-08-15 | 2017-12-15 | 京东方科技集团股份有限公司 | A kind of intelligence point examines method and system |
CN107562788A (en) * | 2017-07-28 | 2018-01-09 | 深圳前海微众银行股份有限公司 | Exchange method, device and computer-readable recording medium |
CN107943998A (en) * | 2017-12-05 | 2018-04-20 | 竹间智能科技(上海)有限公司 | A kind of human-machine conversation control system and method for knowledge based collection of illustrative plates |
CN107992543A (en) * | 2017-11-27 | 2018-05-04 | 上海智臻智能网络科技股份有限公司 | Question and answer exchange method and device, computer equipment and computer-readable recording medium |
CN108920603A (en) * | 2018-06-28 | 2018-11-30 | 厦门快商通信息技术有限公司 | A kind of customer service bootstrap technique based on customer service machine mould |
CN108984655A (en) * | 2018-06-28 | 2018-12-11 | 厦门快商通信息技术有限公司 | A kind of customer service robot intelligent customer service bootstrap technique |
-
2018
- 2018-12-27 CN CN201811610325.6A patent/CN109767818A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104731895A (en) * | 2015-03-18 | 2015-06-24 | 北京京东尚科信息技术有限公司 | Auto-answer method and device |
CN107247868A (en) * | 2017-05-18 | 2017-10-13 | 深思考人工智能机器人科技(北京)有限公司 | A kind of artificial intelligence aids in interrogation system |
CN107133349A (en) * | 2017-05-24 | 2017-09-05 | 北京无忧创新科技有限公司 | One kind dialogue robot system |
CN107562788A (en) * | 2017-07-28 | 2018-01-09 | 深圳前海微众银行股份有限公司 | Exchange method, device and computer-readable recording medium |
CN107480450A (en) * | 2017-08-15 | 2017-12-15 | 京东方科技集团股份有限公司 | A kind of intelligence point examines method and system |
CN107992543A (en) * | 2017-11-27 | 2018-05-04 | 上海智臻智能网络科技股份有限公司 | Question and answer exchange method and device, computer equipment and computer-readable recording medium |
CN107943998A (en) * | 2017-12-05 | 2018-04-20 | 竹间智能科技(上海)有限公司 | A kind of human-machine conversation control system and method for knowledge based collection of illustrative plates |
CN108920603A (en) * | 2018-06-28 | 2018-11-30 | 厦门快商通信息技术有限公司 | A kind of customer service bootstrap technique based on customer service machine mould |
CN108984655A (en) * | 2018-06-28 | 2018-12-11 | 厦门快商通信息技术有限公司 | A kind of customer service robot intelligent customer service bootstrap technique |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111063429A (en) * | 2019-10-25 | 2020-04-24 | 中国科学院自动化研究所 | Medical consultation method, device, equipment and computer-readable storage medium |
CN113360625A (en) * | 2021-07-02 | 2021-09-07 | 北京容联七陌科技有限公司 | Intelligent dialogue marketing customer acquisition method and system based on NLP |
CN113360625B (en) * | 2021-07-02 | 2022-01-04 | 北京容联七陌科技有限公司 | Intelligent dialogue marketing customer acquisition method and system based on NLP |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107247868B (en) | Artificial intelligence auxiliary inquiry system | |
CN108984655B (en) | Intelligent customer service guiding method for customer service robot | |
CN110335595A (en) | Slotting based on speech recognition asks dialogue method, device and storage medium | |
CN109460457A (en) | Text sentence similarity calculating method, intelligent government affairs auxiliary answer system and its working method | |
US20210350209A1 (en) | Intent and context-aware dialogue based virtual assistance | |
CN112035640A (en) | Refined question-answering method based on intelligent question-answering robot, storage medium and intelligent equipment | |
KR101901920B1 (en) | System and method for providing reverse scripting service between speaking and text for ai deep learning | |
CN109767818A (en) | A kind of customization medical treatment is answerred questions interrogation guidance system | |
CN109065052A (en) | A kind of speech robot people | |
CN114187988A (en) | Data processing method, device, system and storage medium | |
CN110569344B (en) | Method and device for determining standard question corresponding to dialogue text | |
CN107562911A (en) | More wheel interaction probabilistic model training methods and auto-answer method | |
CN108920603B (en) | Customer service guiding method based on customer service machine model | |
CN109325780A (en) | A kind of exchange method of the intelligent customer service system in E-Governance Oriented field | |
CN109977204A (en) | A kind of intelligent Answer System and method in knowledge based library | |
Morik | User models and conversational settings: Modeling the user’s wants | |
Jung Lee | An empirical analysis of the relationship between emotional intelligence and emotion work: An examination of public service employees | |
KR20110060039A (en) | Communication robot and controlling method therof | |
CN115661907A (en) | Biological feature recognition method and system | |
CN106503189A (en) | search system optimization method and device based on artificial intelligence | |
Akor et al. | Functions of interpersonal communication in rendering reference services in two University libraries in Nigeria | |
CN114999676A (en) | Method, system, apparatus and medium for automatically replying to medical consultation | |
CN111161733A (en) | Control method and device for intelligent voice service | |
Cooke | Self-efficacious subjects: Rosa on alienation and its antithesis | |
CN116052646B (en) | Speech recognition method, device, storage medium and computer equipment |
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 |
Application publication date: 20190517 |
|
RJ01 | Rejection of invention patent application after publication |