CN110311943A - The inquiry of data and methods of exhibiting in a kind of electric power enterprise big data platform - Google Patents
The inquiry of data and methods of exhibiting in a kind of electric power enterprise big data platform Download PDFInfo
- Publication number
- CN110311943A CN110311943A CN201910302302.7A CN201910302302A CN110311943A CN 110311943 A CN110311943 A CN 110311943A CN 201910302302 A CN201910302302 A CN 201910302302A CN 110311943 A CN110311943 A CN 110311943A
- Authority
- CN
- China
- Prior art keywords
- data
- inquiry
- big data
- exhibiting
- electric power
- 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 32
- 230000001747 exhibiting effect Effects 0.000 title claims abstract description 19
- 230000003993 interaction Effects 0.000 claims abstract description 32
- 238000012545 processing Methods 0.000 claims abstract description 17
- 238000004458 analytical method Methods 0.000 claims abstract description 16
- 239000000284 extract Substances 0.000 claims abstract description 15
- 238000013500 data storage Methods 0.000 claims abstract description 13
- 238000007405 data analysis Methods 0.000 claims abstract description 10
- 210000000352 storage cell Anatomy 0.000 claims abstract description 10
- 238000004148 unit process Methods 0.000 claims abstract description 4
- 230000006870 function Effects 0.000 claims description 12
- 238000003860 storage Methods 0.000 claims description 7
- 238000012360 testing method Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 5
- 238000010801 machine learning Methods 0.000 claims description 5
- 230000001149 cognitive effect Effects 0.000 claims description 3
- 238000013499 data model Methods 0.000 claims description 3
- VEMKTZHHVJILDY-UHFFFAOYSA-N resmethrin Chemical compound CC1(C)C(C=C(C)C)C1C(=O)OCC1=COC(CC=2C=CC=CC=2)=C1 VEMKTZHHVJILDY-UHFFFAOYSA-N 0.000 claims description 3
- 230000001360 synchronised effect Effects 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 10
- 238000004891 communication Methods 0.000 abstract description 5
- 230000002452 interceptive effect Effects 0.000 abstract description 5
- 230000008569 process Effects 0.000 description 9
- 230000000694 effects Effects 0.000 description 5
- 238000007726 management method Methods 0.000 description 5
- 238000001514 detection method Methods 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 238000010276 construction Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000005538 encapsulation Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 230000035800 maturation Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/08—Speech classification or search
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/28—Constructional details of speech recognition systems
- G10L15/30—Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification techniques
- G10L17/22—Interactive procedures; Man-machine interfaces
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/02—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP]
- H04L67/025—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP] for remote control or remote monitoring of applications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1095—Replication or mirroring of data, e.g. scheduling or transport for data synchronisation between network nodes
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1097—Protocols in which an application is distributed across nodes in the network for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/08—Speech classification or search
- G10L2015/088—Word spotting
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Computational Linguistics (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of inquiry of data in electric power enterprise big data platform and methods of exhibiting, it include data acquisition unit, data storage cell, the data analysis being sequentially connected and processing unit and data applying unit including establishing big data platform, in the big data platform；The natural-sounding order that user issues is obtained using voice collector, and analysis is carried out to the natural-sounding order received and extracts inquiry key message；Inquiry is sent in the data application unit in big data platform with key message using human-computer interaction module, after the data analysis and processing unit processes in big data platform, corresponding data information is obtained from data storage cell, and corresponding query information is returned to human-computer interaction module, the query information of the return is shown by human-computer interaction interface.The present invention makes full use of interactive voice technology, realizes the communication and office cost that user is reduced from the automatic operation for inputting, recognizing execution, efficiently promotes operability.
Description
Technical field
The invention belongs to electric power data processing technology fields, and in particular to data in a kind of electric power enterprise big data platform
Inquiry and methods of exhibiting.
Background technique
Traditional man-machine interaction mode has keyboard, mouse etc., and with the increase of production and operation portfolio, each enterprise is all
It has built a large amount of information system to use for office or business decision, menu mutual mode is using relatively early and use is most wide
General man-machine interaction mode.Its main feature is that user is allowed to select in one group of multiple possible object, various possible selections
Item is displayed on the screen in the form of menu items.With the development of mobile technology, requirement of the enterprise for mobile office is also more next
It is higher, but much it can not can be all presented to mobile terminal in the function items that computer terminal is built, and selected object is limited
System, that is, can be only done scheduled system function, operating speed is slow in big system.Because being limited by screen display space, every width
The menu item number that menu is shown is restricted.Since display menu needs to occupy screen space and display time, to increase and be
System expense.
Under nowadays digital Age, power industry is used as the typical case of capital-intensive and technology-intensive industry, information again
Technology has covered the every field such as capital construction, production, operation, office, management, and not only historical data amount is big, and system Construction is various,
The communication cost of user is larger, and data can will also repeatedly input each operation system sometimes, can also there is system data
Inconsistent situation.Inquiry is undoubtedly to aid in a kind of important way that people are quickly found out required data resource.On the other hand,
With the application of speech recognition technology, speech polling is increasingly becoming one of development trend of mode.
How by way of most directly obtaining information, interactive voice technology is made full use of, designs a can be realized
The robot of interactive voice power industry data reduces the communication and office cost of user, efficiently from inputting, recognizing execution
Promoted operability, it appears especially it is necessary to.
Existing intelligent sound assistant or speech robot people working principle approximately as:
First stage: the process of speech-to-text；Signal source → equipment (capture audio input) → enhancing audio input →
Detection voice → be converted to other forms (such as text)；
Second stage: response process；Handle text (such as handling text with NLP, identification is intended to) → operation response.
In detection voice process, just include whether resolution is voice signal, which can be by specified frequency to mould
Quasi- signal is sampled, and simulation sound wave is converted to numerical data.This process is critically important, if successfully identifies voice.Such as
It is all wrong that fruit, which generates numerical data, then it is wrong certainly that the processing in later period, which responds that,.This is also to influence intelligent sound to help
An important factor for reason or speech robot people's discrimination.
In this process, the technology for speech processes be Voice activity detection (Voice activity detection,
VAD), it is therefore an objective to which detecting voice signal whether there is.VAD technology is mainly used for voice coding and speech recognition.It can simplify
Speech processes, it can also be used to non-speech segments are removed during audio session: it can avoid in IP phone application to mute number
Coding and transmission according to packet are saved and calculate time and bandwidth.
Current some related art schemes have been proposed for data query scheme.For example, Publication No.
The patent of invention of CN104199956A describes and provides a kind of ERP data-voice searching method.However, existing inquiry velocity
Can't be satisfactory to the search efficiency of voice on network, in addition, the management for power industry enterprise big data platform
For, for different types of data in different personnel, different regions suffers from respectively different demand and way to manage, language
Sound inquiry still relies in most cases realizes rights management using the authority management module of big data platform itself, faces
When different user is using inquiry and data function of search, it is necessary to exit the system of active user and allow other people again its
The identity of itself logs in system.This brings great inconvenience to user.Especially log in the keyboards such as mobile phone terminal or
When the customer interface of clicking operation mode inconvenience input, the problem of this poor efficiency is with regard to more obvious.
Summary of the invention
In view of the above-mentioned problems, the present invention proposes the inquiry of data and methods of exhibiting in a kind of electric power enterprise big data platform,
Interactive voice technology is made full use of, the communication for reducing user from the automatic operation for inputting, recognizing execution is realized and is done
Public cost efficiently promotes operability.
It realizes above-mentioned technical purpose, reaches above-mentioned technical effect, the invention is realized by the following technical scheme:
The inquiry of data and methods of exhibiting in a kind of electric power enterprise big data platform, comprising the following steps:
Big data platform is established, includes the data acquisition unit being sequentially connected, data storage list in the big data platform
Member, data analysis and processing unit and data applying unit；
The natural-sounding order that user issues is obtained using the voice collector in human-computer interaction module, and to receiving
Natural-sounding order carries out analysis and extracts inquiry key message；
The data application unit being sent to the inquiry with key message using human-computer interaction module in big data platform
In, via the data analysis in big data platform with after processing unit processes, corresponding data are obtained from data storage cell
Information, and corresponding query information is returned to human-computer interaction module, finally by the human-computer interaction interface in human-computer interaction module
Show the query information of the return.
Preferably, the data application unit provides the interface interacted with human-computer interaction module.
Preferably, the data storage cell is the distributed frame built based on hadoop system.
Preferably, for office administration class data, then the data in RDB database are same in the data acquisition unit
It walks in HDFS, so that HDFS becomes the redundant storage for having backed up partial data；For producing real-time class data, then according to industry
Business scene does corresponding pretreatment, is then written in corresponding data storage later；For video file class data, need
After the Extract stage Loads Image, then according to the recognizer of setting, identify and extract the characteristic information of picture, and by its
Be converted to the data model of business scenario needs.
Preferably, the pretreatment includes duplicate removal, denoising and/or intermediate computations.
Preferably, the data analysis provides every sales data, the statistics of market index and comprehensive function with processing unit
Can, it is also provided as warning data setting and reference data function is provided.
Preferably, speech recognition library is contained in the human-computer interaction module；The described pair of natural-sounding order received
It carries out analysis and extracts inquiry key message, specifically include following sub-step:
Characteristics extraction is carried out to the natural-sounding order received, the characteristic value includes: participle and relationship；
The characteristic value extracted is matched according to the matching criterior of setting with the data in speech recognition library；
Most matched inquiry key message is finally found out from speech recognition library.
It preferably, include reference template in the speech recognition library, the reference template is obtained by machine learning, learned
The habit stage after being handled characteristic parameter, establishes a model for each type of service, saves as template library.
Preferably, in cognitive phase, natural-sounding order generates test template after processing, and by the test module with
Reference template is matched, and will match the highest reference template of score as recognition result.
Preferably, after successful match, alphabetic character crossfire is converted by natural-sounding order, and pass through speech analysis function
It analyzes it, in conjunction with Time Domain Analysis, is divided using time and index, unit name, transactional relationship as independent variable
Analysis correctly judges the starting point of natural-sounding order, extracts inquiry key message.
Compared with prior art, beneficial effects of the present invention:
The inquiry of data and methods of exhibiting, make full use of voice in a kind of electric power enterprise big data platform proposed by the present invention
Interaction technique realizes the communication and office cost for reducing user from the automatic operation for inputting, recognizing execution, efficiently mentions
Lift operations.
Detailed description of the invention
Fig. 1 is the structural schematic diagram of the big data platform of an embodiment of the present invention；
Fig. 2 is the inquiry of data and the data of methods of exhibiting in the electric power enterprise big data platform of an embodiment of the present invention
Flow to schematic diagram；
Fig. 3 (a) is one of human-computer interaction interface display figure of an embodiment of the present invention；
Fig. 3 (b) is that the human-computer interaction interface of an embodiment of the present invention shows the two of figure；
Fig. 3 (c) is that the human-computer interaction interface of an embodiment of the present invention shows the three of figure；
Fig. 3 (d) is that the human-computer interaction interface of an embodiment of the present invention shows the four of figure.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to embodiments, to the present invention
It is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and do not have to
It is of the invention in limiting.
Application principle of the invention is explained in detail with reference to the accompanying drawing.
As shown in Figure 1, the present invention provides a kind of inquiry of data in electric power enterprise big data platform and methods of exhibiting, packet
Include following steps:
Step (1) establishes big data platform, as shown in Figure 1, including that the data being sequentially connected are adopted in the big data platform
Collect unit, data storage cell, data analysis and processing unit and data applying unit；
In a kind of specific embodiment of the embodiment of the present invention, in the data acquisition unit, for office administration class
Data in RDB database are then synchronized in HDFS by data, so that HDFS becomes the redundant storage for having backed up partial data,
In such a scenario, data acquisition is just only one simple synchronous, without executing conversion；For producing real-time class data,
Corresponding pretreatment is then done according to business scenario, the pretreatment includes duplicate removal, denoising and/or intermediate computations, is written again later
To corresponding data storage in, this process is similar to traditional ETL, but it is the processing mode of streaming, and the non-timed batch at
Manage Job；For video file class data, need after the Extract stage Loads Image, then according to the recognizer of setting,
The characteristic information of picture is identified and extracted, and is converted into the data model of business scenario needs, under this scene, number
It is relatively long according to the time-consuming of extraction, it is also desirable to more memory source；
The data storage cell is the distributed frame built based on hadoop system, the number of unified storage management dispersion
According to guaranteeing the storage demand of mass data, support the autobalance of increment dilatation and data, random read-write and addition is supported to write
Operation, effectively solve in the prior art data relatively disperse, be stored in respective service application, do not unify
It converges in one storage medium, so that hindering to realize the problem of cooperateing with interaction, can do with each professional production system for conducting business
To the timeliness of decision data, science, perspective, it is each in the production, business activities of electricity power enterprise really to play data
Effect in link provides the purpose of service for Marketing of Power Market decision；
The data analysis provides every sales data, the statistics of market index and comprehensive function with processing unit, is industry
Business department provides accurate market supply and demand condition information, retail customer and consumer for conditions of demand of industry etc.,
Energy supply and dispensing etc., which are carried out, for sales department provides relatively reliable foundation；It is also provided as warning data setting and ginseng is provided
Data are examined, energy enterprise can analyze sale of electricity and sell heat, power generation etc. according to the data information of offer；In conjunction with above several respects
Analysis, the importance that data analyze work are self-evident；
The data application unit provides the interface interacted with human-computer interaction module, is externally supplied to software to realize
Enterprise, scientific research institution use, and data are standardized encapsulation, are carried out on demand in the case where meeting the needs of each business datum uses
It is open, and gradually the open affiliate numerous to outside uses in the case where experience maturation；
Step (2) obtains the natural-sounding order that user issues using the voice collector in human-computer interaction module, and right
The natural-sounding order received carries out analysis and extracts inquiry key message；
Speech recognition library is contained in the human-computer interaction module；It include reference template in the speech recognition library, it is described
Reference template is obtained by machine learning, in the study stage, after characteristic parameter is handled, is established for each type of service
One model, saves as template library；
In a specific embodiment of the invention, the described pair of natural-sounding order received carries out analyzing to extract looking into
It askes and uses key message, specifically include following sub-step:
Characteristics extraction is carried out to the natural-sounding order received, the characteristic value includes: participle and relationship；For dividing
Word extracts, and in practical applications, to the elements such as unit name and its abbreviation, business tine, such as generated energy, uses machine learning
Method be entered into statistics Words partition system and carry out String matching participle, while identifying some new words using statistical method, i.e.,
Statistical string frequency and String matching are combined, not only played fast, the high-efficient feature of matching participle cutting speed, but also nothing is utilized
The advantages of Dictionary based segment combination context identification new word, automatic disambiguation；Extraction for relationship, it is main using statistics and
The method of machine learning extracts transactional relationship, time, place, index in big data platform；
The characteristic value extracted is matched according to the matching criterior of setting with the data in speech recognition library；
Most matched inquiry key message is finally found out from speech recognition library；
I.e. in cognitive phase, natural-sounding order generates test template after processing, and by the test module and refers to
Template is matched, and will match the highest reference template of score as recognition result；After successful match, by natural-sounding order
Be converted into alphabetic character crossfire, and analyzed it by speech analysis function, in conjunction with Time Domain Analysis, with the time and
Index, unit name, transactional relationship are analyzed as independent variable, are correctly judged the starting point of natural-sounding order, are not being carried on the back
It is correct to distinguish voiceless sound and unvoiced segments in the case where scape noise, extract inquiry key message.
The inquiry is sent to the data in big data platform with key message using human-computer interaction module and answered by step (3)
With in unit, via the data analysis in big data platform with after processing unit processes, obtained from data storage cell corresponding
Data information, and return to corresponding query information to human-computer interaction module, finally by the man-machine friendship in human-computer interaction module
The query information of the mutual interface display return, the system of realizing have the function of " sociable ".
In order to preferably realize that the interactive voice of data in enterprise's big data platform shows, the present invention in devise it is several not
With the displaying interface of triggering, comprising: standby interface, result selection interface, answers correct display interface, answers mistake at hearing interface
Accidentally display interface etc..System carries out the displaying at different interfaces according to different results, referring specifically to Fig. 3.
Only show that inquiry user wishes to learn the example process of the telephone number of * * * below:
It 1, is the standby interface of big data robot " big China 001 " under normal circumstances, as shown in Fig. 3 (a)；
2, user comes in face of " big China 001 ", and user speech is interacted: " big China 001, hello ", robot responds:
" you do not pass through face authentication, please first log in "；User, by identification frame, carries out face typing before interface,
By rear；
3, user wakes up " big China 001 " again, and robot responds: " hello, and may I ask needs, what is helped ", while machine
The state that " in listening " is shown on people's page, as shown in Fig. 3 (b)；
3, user speech proposes: " telephone number of * * * ".After robot identifies this word, consistency operation is carried out, if
There are multiple people for being * *, then all exports the information of * * at foreground interface, voice prompting selects to need the letter of selection user again
Breath, after robot identification, voice, which provides, promises information: " cell-phone number of * * * is * * * * * * * * * * ", foreground is also shown on interface
Successful smiling face, as shown in Fig. 3 (c)；
4, user also wants to again attempt to inquire that the phone of another people, robot do not identify voice messaging correctly, this
When, then interacts unsuccessful, and voice prompting user does not find the content that user wants: " not catching, please change a keyword examination
Examination ", foreground interface then shows unhappy expression, as shown in Fig. 3 (d)；
5, inquiry terminates, and user speech " standby ", robot comes back to the displaying interface of Fig. 3 (a).
Under normal operation, the human-computer interaction based on big data is completely successful.As a result as shown in the table:
The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention.The technology of the industry
Personnel are it should be appreciated that the present invention is not limited to the above embodiments, and the above embodiments and description only describe this
The principle of invention, without departing from the spirit and scope of the present invention, various changes and improvements may be made to the invention, these
Changes and improvements all fall within the protetion scope of the claimed invention.The claimed scope of the invention is by appended claims
And its equivalent thereof.
Claims (10)
1. the inquiry of data and methods of exhibiting in a kind of electric power enterprise big data platform, which comprises the following steps:
Big data platform is established, includes data acquisition unit, data storage cell, the number being sequentially connected in the big data platform
According to analysis and processing unit and data applying unit；
The natural-sounding order that user issues is obtained using the voice collector in human-computer interaction module, and to the nature received
Voice command carries out analysis and extracts inquiry key message；
The inquiry is sent in the data application unit in big data platform with key message using human-computer interaction module, is passed through
By the data analysis in big data platform with after processing unit processes, corresponding data information is obtained from data storage cell,
And corresponding query information is returned to human-computer interaction module, this is shown finally by the human-computer interaction interface in human-computer interaction module
The query information of return.
2. the inquiry of data and methods of exhibiting, feature in a kind of electric power enterprise big data platform according to claim 1
Be: the data application unit provides the interface interacted with human-computer interaction module.
3. the inquiry of data and methods of exhibiting, feature in a kind of electric power enterprise big data platform according to claim 1
Be: the data storage cell is the distributed frame built based on hadoop system.
4. the inquiry of data and methods of exhibiting, feature in a kind of electric power enterprise big data platform according to claim 1
It is: in the data acquisition unit, for office administration class data, then the data in RDB database is synchronized in HDFS,
So that HDFS becomes the redundant storage for having backed up partial data；For producing real-time class data, then correspondence is done according to business scenario
Pretreatment, be then written in the storage of corresponding data later；For video file class data, need to add in the Extract stage
After carrying picture, then according to the recognizer of setting, the characteristic information of picture is identified and extracts, and be converted into business scenario
The data model needed.
5. the inquiry of data and methods of exhibiting, feature in a kind of electric power enterprise big data platform according to claim 4
Be: the pretreatment includes duplicate removal, denoising and/or intermediate computations.
6. the inquiry of data and methods of exhibiting, feature in a kind of electric power enterprise big data platform according to claim 1
Be: the data analysis provides every sales data, the statistics of market index and comprehensive function with processing unit, is also provided as
Warning data setting provides reference data function.
7. the inquiry of data and methods of exhibiting, feature in a kind of electric power enterprise big data platform according to claim 1
It is: contains speech recognition library in the human-computer interaction module；The described pair of natural-sounding order received carries out analysis and mentions
Inquiry key message is taken out, following sub-step is specifically included:
Characteristics extraction is carried out to the natural-sounding order received, the characteristic value includes participle and relationship；
The characteristic value extracted is matched according to the matching criterior of setting with the data in speech recognition library；
Most matched inquiry key message is finally found out from speech recognition library.
8. the inquiry of data and methods of exhibiting, feature in a kind of electric power enterprise big data platform according to claim 7
Be: comprising reference template in the speech recognition library, the reference template is obtained by machine learning, will in the study stage
After characteristic parameter is handled, a model is established for each type of service, saves as template library.
9. the inquiry of data and methods of exhibiting, feature in a kind of electric power enterprise big data platform according to claim 8
Be: in cognitive phase, natural-sounding order generates test template after processing, and by the test module and reference template into
Row matching, will match the highest reference template of score as recognition result.
10. the inquiry of data and methods of exhibiting, feature in a kind of electric power enterprise big data platform according to claim 9
It is: after successful match, converts alphabetic character crossfire for natural-sounding order, and divide it by speech analysis function
Analysis, in conjunction with Time Domain Analysis, is analyzed using time and index, unit name, transactional relationship as independent variable, is correctly judged
The starting point of natural-sounding order extracts inquiry key message.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910302302.7A CN110311943A (en) | 2019-04-16 | 2019-04-16 | The inquiry of data and methods of exhibiting in a kind of electric power enterprise big data platform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910302302.7A CN110311943A (en) | 2019-04-16 | 2019-04-16 | The inquiry of data and methods of exhibiting in a kind of electric power enterprise big data platform |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110311943A true CN110311943A (en) | 2019-10-08 |
Family
ID=68074468
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910302302.7A Pending CN110311943A (en) | 2019-04-16 | 2019-04-16 | The inquiry of data and methods of exhibiting in a kind of electric power enterprise big data platform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110311943A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111176607A (en) * | 2019-12-27 | 2020-05-19 | 国网山东省电力公司临沂供电公司 | Voice interaction system and method based on power business |
| CN117037788A (en) * | 2023-09-11 | 2023-11-10 | 南京申瑞电力电子有限公司 | Control cabinet information display device based on voice control |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103730129A (en) * | 2013-11-18 | 2014-04-16 | 长江大学 | Voice query system for database information query |
| CN108306756A (en) * | 2017-12-21 | 2018-07-20 | 国网北京市电力公司 | One kind being based on electric power data network holography assessment system and its Fault Locating Method |
| US20190019264A1 (en) * | 2017-07-11 | 2019-01-17 | Global Tel*Link Corporation | Family-directed inmate debit account funding |
-
2019
- 2019-04-16 CN CN201910302302.7A patent/CN110311943A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103730129A (en) * | 2013-11-18 | 2014-04-16 | 长江大学 | Voice query system for database information query |
| US20190019264A1 (en) * | 2017-07-11 | 2019-01-17 | Global Tel*Link Corporation | Family-directed inmate debit account funding |
| CN108306756A (en) * | 2017-12-21 | 2018-07-20 | 国网北京市电力公司 | One kind being based on electric power data network holography assessment system and its Fault Locating Method |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111176607A (en) * | 2019-12-27 | 2020-05-19 | 国网山东省电力公司临沂供电公司 | Voice interaction system and method based on power business |
| CN117037788A (en) * | 2023-09-11 | 2023-11-10 | 南京申瑞电力电子有限公司 | Control cabinet information display device based on voice control |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11087094B2 (en) | System and method for generation of conversation graphs | |
| AU2018383615B2 (en) | Systems and methods for chatbot generation | |
| US20190272269A1 (en) | Method and system of classification in a natural language user interface | |
| US20190369958A1 (en) | Method and system for providing interface controls based on voice commands | |
| US11954140B2 (en) | Labeling/names of themes | |
| CN107784033B (en) | Method and device for recommending based on session | |
| US10956480B2 (en) | System and method for generating dialogue graphs | |
| CN106406806A (en) | A control method and device for intelligent apparatuses | |
| CN105657129A (en) | Call information obtaining method and device | |
| WO2020106967A1 (en) | Semantic crm transcripts from mobile communications sessions | |
| US10860566B1 (en) | Themes surfacing for communication data analysis | |
| CN110909165A (en) | Data processing method, device, medium and electronic equipment | |
| CN104462600A (en) | Method and device for achieving automatic classification of calling reasons | |
| US8781880B2 (en) | System, method and apparatus for voice analytics of recorded audio | |
| CN111098312A (en) | Window government affairs service robot | |
| CN113051362A (en) | Data query method and device and server | |
| EP4027335A1 (en) | Speech interaction method and apparatus, device, and computer storage medium | |
| CN110311943A (en) | The inquiry of data and methods of exhibiting in a kind of electric power enterprise big data platform | |
| US11200264B2 (en) | Systems and methods for identifying dynamic types in voice queries | |
| CN114064943A (en) | Conference management method, conference management device, storage medium and electronic equipment | |
| CN111858560A (en) | Financial data automated testing and monitoring system based on data warehouse | |
| WO2002089113A1 (en) | System for generating the grammar of a spoken dialogue system | |
| CN113505293A (en) | Information pushing method and device, electronic equipment and storage medium | |
| WO2020070906A1 (en) | Workshop assistance system and workshop assistance method | |
| CN114462364B (en) | Method and device for inputting information |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191008 |