CN110096582A - The training method of session robotic in a kind of power business - Google Patents
The training method of session robotic in a kind of power business Download PDFInfo
- Publication number
- CN110096582A CN110096582A CN201910364675.7A CN201910364675A CN110096582A CN 110096582 A CN110096582 A CN 110096582A CN 201910364675 A CN201910364675 A CN 201910364675A CN 110096582 A CN110096582 A CN 110096582A
- Authority
- CN
- China
- Prior art keywords
- session robotic
- session
- question
- robotic
- answer data
- 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
- 238000000034 method Methods 0.000 title claims abstract description 20
- 238000012790 confirmation Methods 0.000 claims abstract description 4
- 239000000284 extract Substances 0.000 claims description 5
- 230000005611 electricity Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Water Supply & Treatment (AREA)
- Databases & Information Systems (AREA)
- Computational Linguistics (AREA)
- Human Computer Interaction (AREA)
- Artificial Intelligence (AREA)
- Public Health (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
The invention discloses a kind of training method of session robotic in power business, include the following steps: that session robotic real-time reception user puts question to;Whether it is effectively to put question to that session robotic judges that user puts question to;If so, session robotic is that user puts question to matching answer data according to entity information;Whether the matched answer data of artificial judgment session robotic are accurate;If so, session robotic confirmation matches the answer data;Session robotic stores matching result;If it is not, being manually then several entity information matching answer data;And execute the step: session robotic stores matching result;By carrying out repetition training, and the method that training result is stored to session robotic, the customer service ability of session robotic is continuously improved, has realized session robotic and constantly learns in human assistance, i.e., using more long, the intelligence of session robotic is higher.
Description
Technical field
The present invention relates to a kind of training methods of session robotic in electric power network technique field more particularly to power business.
Background technique
With the continuous development of electrical network business, power grid provides diversified power business, vast use for power consumer
Every aspect in the life of family all increasingly be unable to do without electrical power services.But due to the particularity of electrical network business, include in question sentence
It is interior differ larger with other field, so that usually people are generally found the identification of robot when using the service of power business
It is not accurate enough, it is easy misrecognition or can not identify, so that the customer service ability of session robotic is excessively low, to user in power grid industry
Inquiry in business handle bring greatly it is constant;Therefore, the customer service ability for how improving session robotic in electrical network business, at
For the problem of current urgent need to resolve.
Summary of the invention
The purpose of the present invention is to provide a kind of training method of session robotic in power business, Lai Tigao electrical network business
The customer service ability of middle session robotic.
To achieve this purpose, the present invention adopts the following technical scheme:
The training method of session robotic, includes the following steps: in a kind of power business
Session robotic real-time reception user puts question to;
Whether it is effectively to put question to that session robotic judges that user puts question to;Wherein, effectively puing question to includes several entity informations;
If so, session robotic is that user puts question to matching answer data according to entity information;
Whether the matched answer data of artificial judgment session robotic are accurate;
If so, session robotic confirmation matches the answer data;
Session robotic stores matching result;Wherein, matching result includes several entity informations, and described in correspondence
The answer data of several entity informations;
If it is not, being manually then several entity information matching answer data;And execute the step: session robotic storage
Deposit matching result.
Optionally, the step: whether it is effectively to put question to that session robotic judges that user puts question to, and is specifically included:
Session robotic is putd question to user and is screened, if several entity informations therein can be extracted, effectively to mention
It asks;Wherein, entity information packet is preset, entity information packet includes several entity informations.
Optionally, the step: before whether the matched answer data of artificial judgment session robotic are accurate, further includes:
Session robotic judge the user put question to whether existing matching result;
If it is not, then executing the step: whether the matched answer data of artificial judgment session robotic are accurate.
Optionally, the step: whether it is before effectively puing question to that session robotic judges that user puts question to, further includes:
Several users are analyzed in advance to put question to, and filter out entity therein.
Optionally, the step: whether it is before effectively puing question to that session robotic judges that user puts question to, further includes:
User is putd question to and carries out intention analysis, using natural language understanding technology, each user's enquirement is extracted and is matched
Intention into current system, and next intention and matching degree will be matched and be shown.
Optionally, the step: whether it is after effectively puing question to that session robotic judges that user puts question to, further includes:
Whether the entity information that artificial judgment session robotic extracts is accurate, if so, session robotic is believed according to entity
Breath is that user puts question to matching answer data;If it is not, entity information is then manually extracted, meanwhile, session robotic is by the entity information
Storage.
Compared with prior art, the embodiment of the present invention has the advantages that
The present invention is continuously improved by carrying out repetition training, and the method that training result is stored to session robotic
The customer service ability of session robotic realizes session robotic and constantly learns in human assistance, that is, uses more long, session robotic
Intelligence it is higher.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention without any creative labor, may be used also for those of ordinary skill in the art
To obtain other attached drawings according to these attached drawings.
Fig. 1 is the flow chart of the training method of session robotic in a kind of power business provided in an embodiment of the present invention.
Specific embodiment
In order to make the invention's purpose, features and advantages of the invention more obvious and easy to understand, below in conjunction with the present invention
Attached drawing in embodiment, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that disclosed below
Embodiment be only a part of the embodiment of the present invention, and not all embodiment.Based on the embodiments of the present invention, this field
Those of ordinary skill's all other embodiment obtained without making creative work, belongs to protection of the present invention
Range.
In the description of the present invention, it is to be understood that, term " on ", "lower", "top", "bottom", "inner", "outside" etc. indicate
Orientation or positional relationship be based on the orientation or positional relationship shown in the drawings, be merely for convenience of description the present invention and simplification retouch
It states, rather than the device or element of indication or suggestion meaning must have a particular orientation, be constructed and operated in a specific orientation,
Therefore it is not considered as limiting the invention.
It should be noted that it can be directly to separately when a component is considered as " connection " another component
One component may be simultaneously present the component being centrally located.When a component is considered as " setting exists " another component,
It, which can be, is set up directly on another component or may be simultaneously present the component being centrally located.
To further illustrate the technical scheme of the present invention below with reference to the accompanying drawings and specific embodiments.
Referring to FIG. 1, in a kind of power business session robotic training method, include the following steps:
Step S101: session robotic real-time reception user puts question to;
Step S102: whether it is effectively to put question to that session robotic judges that user puts question to;Wherein, effectively puing question to includes several realities
Body information, such as city, weather, the electricity charge, month.
It is screened specifically, session robotic puts question to user, useless sentence is filtered out, if can extract therein
Several entity informations, then effectively to put question to, if entity information cannot be extracted, to put question in vain, session robotic can be refused
Comprehend;Wherein, entity information packet is preset, entity information packet includes several entity informations;In the present embodiment, entity information is
In key message included in the enquirement of user, such as " can consult the Shanghai day after tomorrow to me can or can not rain " the words
" day after tomorrow ", " Shanghai ".
Step S103: if user puts question to effectively to put question to, session robotic is that user puts question to matching according to entity information
Answer data.
Step S104: whether the matched answer data of artificial judgment session robotic are accurate.
Step S105: if the matched answer data of session robotic are accurate, session robotic confirmation matches the answer
Data, and execute step S106: session robotic stores matching result.
Specifically, matching result includes several entity informations, and the solution answer of corresponding several entity informations
According to.
Step S107: if the matched answer data inaccuracy of session robotic, is manually several entity informations
With answer data, and execute step S106.
Further, before step S102, further includes: analyze several users in advance and put question to, filter out entity therein;Cause
For all user put question in comprising largely to meaningless session is marked, for example chatting (as hello, thanks), more wheel sessions
Journey content (such as the cell-phone number inputted by robot requirement).By these for being intended to mark meaningless information filtering with entity
Fall, artificial action can be mitigated, promotes artificial working efficiency.
Further, before step S102, further includes: put question to user and carry out intention analysis, utilize natural language understanding
Technology extracts the intention in the be matched to current system of each user's enquirement, and will match the intention and matching degree come
It is shown, for manually marking judgement;In the present embodiment, it is intended that: the main purpose of the way to put questions expression of user such as " is asked
Ask today Beijing weather how " and the intention of " the Shanghai day after tomorrow can be consulted to me to rain " this two ways to put questions be all
" Cha Tianqi ";Intention needs operation personnel to be configured in systems in advance according to service conditions.
Further, after step S102, further includes: whether the entity information that artificial judgment session robotic extracts is quasi-
Really, if so, session robotic puts question to matching answer data according to entity information for user;If it is not, then manually extracting entity letter
Breath, meanwhile, session robotic stores the entity information.
The training method of session robotic in a kind of power business provided in this embodiment, by being carried out to session robotic
Repetition training, and the method that training result is stored, have been continuously improved the customer service ability of session robotic, have realized session machine
People constantly learns in human assistance, i.e., using more long, the intelligence of session robotic is higher.
The above, the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations;Although referring to before
Stating embodiment, invention is explained in detail, those skilled in the art should understand that: it still can be to preceding
Technical solution documented by each embodiment is stated to modify or equivalent replacement of some of the technical features;And these
It modifies or replaces, the spirit and scope for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution.
Claims (6)
1. the training method of session robotic in a kind of power business, which comprises the steps of:
Session robotic real-time reception user puts question to;
Whether it is effectively to put question to that session robotic judges that user puts question to;Wherein, effectively puing question to includes several entity informations;
If so, session robotic is that user puts question to matching answer data according to entity information;
Whether the matched answer data of artificial judgment session robotic are accurate;
If so, session robotic confirmation matches the answer data;
Session robotic stores matching result;Wherein, matching result includes several entity informations, and correspondence is described several
The answer data of entity information;
If it is not, being manually then several entity information matching answer data;And execute the step: session robotic storage
With result.
2. the training method of session robotic in power business according to claim 1, which is characterized in that the step:
Whether it is effectively to put question to that session robotic judges that user puts question to, and is specifically included:
Session robotic is putd question to user and is screened, if several entity informations therein can be extracted, effectively to put question to;Its
In, entity information packet is preset, entity information packet includes several entity informations.
3. the training method of session robotic in power business according to claim 1, which is characterized in that the step:
Before whether the matched answer data of artificial judgment session robotic are accurate, further includes:
Session robotic judge the user put question to whether existing matching result;
If it is not, then executing the step: whether the matched answer data of artificial judgment session robotic are accurate.
4. the training method of session robotic in power business according to claim 1, which is characterized in that the step:
Whether it is before effectively puing question to that session robotic judges that user puts question to, further includes:
Several users are analyzed in advance to put question to, and filter out entity therein.
5. the training method of session robotic in power business according to claim 1, which is characterized in that the step:
Whether it is before effectively puing question to that session robotic judges that user puts question to, further includes:
User is putd question to and carries out intention analysis, using natural language understanding technology, each user is extracted and puts question to be matched to and work as
Intention in preceding system, and next intention and matching degree will be matched and be shown.
6. the training method of session robotic in power business according to claim 1, which is characterized in that the step:
Whether it is after effectively puing question to that session robotic judges that user puts question to, further includes:
Whether the entity information that artificial judgment session robotic extracts is accurate, if so, session robotic is according to entity information
User puts question to matching answer data;If it is not, entity information is then manually extracted, meanwhile, session robotic stores the entity information.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910364675.7A CN110096582A (en) | 2019-04-30 | 2019-04-30 | The training method of session robotic in a kind of power business |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910364675.7A CN110096582A (en) | 2019-04-30 | 2019-04-30 | The training method of session robotic in a kind of power business |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110096582A true CN110096582A (en) | 2019-08-06 |
Family
ID=67446693
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910364675.7A Pending CN110096582A (en) | 2019-04-30 | 2019-04-30 | The training method of session robotic in a kind of power business |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110096582A (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103279528A (en) * | 2013-05-31 | 2013-09-04 | 俞志晨 | Question-answering system and question-answering method based on man-machine integration |
CN105207890A (en) * | 2015-08-24 | 2015-12-30 | 北京智齿博创科技有限公司 | Online customer service method |
CN107220353A (en) * | 2017-06-01 | 2017-09-29 | 深圳追科技有限公司 | A kind of intelligent customer service robot satisfaction automatic evaluation method and system |
CN108073976A (en) * | 2016-11-18 | 2018-05-25 | 科沃斯商用机器人有限公司 | Man-machine interactive system and its man-machine interaction method |
-
2019
- 2019-04-30 CN CN201910364675.7A patent/CN110096582A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103279528A (en) * | 2013-05-31 | 2013-09-04 | 俞志晨 | Question-answering system and question-answering method based on man-machine integration |
CN105207890A (en) * | 2015-08-24 | 2015-12-30 | 北京智齿博创科技有限公司 | Online customer service method |
CN108073976A (en) * | 2016-11-18 | 2018-05-25 | 科沃斯商用机器人有限公司 | Man-machine interactive system and its man-machine interaction method |
CN107220353A (en) * | 2017-06-01 | 2017-09-29 | 深圳追科技有限公司 | A kind of intelligent customer service robot satisfaction automatic evaluation method and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109753560B (en) | Information processing method and device of intelligent question-answering system | |
CN111192060B (en) | Full-channel self-service response implementation method based on power IT service | |
CN110263144A (en) | A kind of answer acquisition methods and device | |
CN105072173A (en) | Customer service method and system for automatically switching between automatic customer service and artificial customer service | |
CN108536770B (en) | Distribution network ring net automatic generation method based on distribution GIS model | |
CN108833722A (en) | Audio recognition method, device, computer equipment and storage medium | |
CN104836925A (en) | Consultation system and method | |
CN108418744A (en) | A kind of electronics seat system for promoting electrical power services quality | |
CN109345072A (en) | Dispatching method for distribution branch line scheduling scenario | |
CN110377908A (en) | Semantic understanding method, apparatus, equipment and readable storage medium storing program for executing | |
CN106097835A (en) | A kind of deaf mute exchanges the method for intelligent assistance system and exchange | |
CN110287305B (en) | Intelligent question-answering management system based on natural language processing | |
CN110472008A (en) | Intelligent interactive method and device | |
CN111291157A (en) | Response method, response device, terminal and storage medium | |
CN110096582A (en) | The training method of session robotic in a kind of power business | |
CN105893494A (en) | Information pushing method and device | |
CN110457588A (en) | A kind of service content display processing method and device | |
CN107145758A (en) | A kind of outgoing method of servicing and device of accompanying and attending to based on domestic robot | |
CN110321414A (en) | A kind of artificial intelligence counseling services method and system based on deep learning | |
CN106657591A (en) | Display method and device for push messages of application programs | |
CN105633970B (en) | Distribution back scheduling control system building method based on major network scheduling system | |
CN106779817A (en) | Intension recognizing method and system based on various dimensions information | |
CN106781796B (en) | Communication protocol training method and system combined with application scene and scene association method | |
CN108965618A (en) | A kind of intelligent voice system | |
CN104158176A (en) | Auxiliary scheduling system for use in electric power system |
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: 20190806 |
|
RJ01 | Rejection of invention patent application after publication |