CN108280188A - Intelligence inspection business platform based on big data - Google Patents
Intelligence inspection business platform based on big data Download PDFInfo
- Publication number
- CN108280188A CN108280188A CN201810067741.XA CN201810067741A CN108280188A CN 108280188 A CN108280188 A CN 108280188A CN 201810067741 A CN201810067741 A CN 201810067741A CN 108280188 A CN108280188 A CN 108280188A
- Authority
- CN
- China
- Prior art keywords
- document
- unit
- voice
- big data
- voice messaging
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3343—Query execution using phonetics
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; 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 OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L21/00—Processing of the speech or voice signal to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
- G10L21/0208—Noise filtering
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Business, Economics & Management (AREA)
- Acoustics & Sound (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- Human Computer Interaction (AREA)
- General Health & Medical Sciences (AREA)
- Multimedia (AREA)
- General Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Human Resources & Organizations (AREA)
- Quality & Reliability (AREA)
- Signal Processing (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The intelligence based on big data that the present invention provides a kind of examining business platform, including:Document big data unit, for storing and the relevant document information of case;Voice collecting unit, the voice messaging for acquiring case trial scene;Intelligent language and characters converting unit, for being converted into word according to voice messaging.This platform greatly improves the speech discrimination accuracy at trial scene, is conducive to improve trial efficiency.
Description
Technical field
The invention belongs to law big data processing technology fields, and in particular to a kind of intelligence inspection business based on big data is flat
Platform.
Background technology
With the continuous development of information technology, justice system also proposed increasingly higher demands to automated process.Method
All kinds of case information of institute's trial have been enough to constitute the pending data in big data meaning.Through retrieval, in the prior art Shen
Number please providing a kind of criminal case for CN201710426297.1, intelligently auxiliary is handled a case method, is suitable for public security subsystem, inspection
It examines subsystem and law court's subsystem provides auxiliary of handling a case, the public security subsystem, procuratorial work subsystem and method subsystem are equal
With server communication, include the following steps:
Step 21, one or more of case of public security subsystem pair instrument of evidence carry out evidence collection, typing and
Verification;
Step 22, public security subsystem obtains the pending request instruction of input, and is judged according to the check results of the instrument of evidence
Whether the requirement that proposes pending request is met, if so, sending out pending request to procuratorial work subsystem by server;
Step 23, procuratorial work subsystem obtains the instrument of evidence and its check results of the public security subsystem to the case;
Step 24, procuratorial work subsystem carries out chain of evidence examination to the instrument of evidence of the case;
Step 25, procuratorial work subsystem obtains the examination result that sends out inputted and instructs, and according to the chain of evidence of the instrument of evidence
Examination result judges whether to meet the requirement for sending out examination result, if so, by server to public security subsystem or method courtyard
System sends out examination result.
However, existing case big data processing system still needs the related information retrieval capability of internet information
It improves.In the prior art, more and more sound and perfect with the law of country, the legal consciousness of people increasingly improves, judicial
The quantity of class case is also more and more.And people are when handling a case, also habitually go to search relevant case into
Row reference, so as to involved by case itself case point and relevant law more know and understand.However, being looked into for existing case
For asking or retrieving, people are generally widely to be inquired by universal search engine, and the inquiry of this inquiry mode is accurate
True rate is relatively low, generally requires people and carries out just inquiring useful reference case after largely screening.In addition, people can be with
It is inquired or is retrieved by the dedicated system of judicial department, the universal search engine and this dedicated query mode compares
It says, accuracy rate increases, but it is either in formality, or in mode of operation, all comparatively laborious, can not spirit
Living is retrieved suitable for civil, also, conventional judicial class case retrieval, is also commonly based on the full-text search of keyword
System is realized, and this retrieval can only directly retrieve related keyword whether occur, also relatively low in accuracy rate.
Invention content
In order to improve the automatization level of justice system case examination, the present invention provides a kind of intelligence based on big data
Inspection business platform, including:
Document big data unit, for storing and the relevant document information of case;
Voice collecting unit, the voice messaging for acquiring case trial scene;
Intelligent voice-text conversion unit, for being converted into word according to voice messaging.
Further, the intelligent voice-text conversion unit includes:
Document selection unit, for choosing document according to the voice messaging;
Document markup unit, for marking the document according to the voice messaging;
Hearing process confirmation unit confirms document for generating hearing process according to the voice messaging.
Further, the voice collecting unit is multichannel voice collecting unit.
Further, the multichannel voice collecting unit includes the more of speech signal analysis unit and distributed setting
A microphone.
Further, the document selection unit includes document title determination unit, for generating text according to voice messaging
Word, and document is chosen from the document big data unit according to the corresponding document title of word.
Further, the document markup unit is used to the word being added to the document.
Further, the document big data unit is relationship type document big data unit.
Further, the hearing process confirmation unit includes:
Document establishes unit, confirms document for establishing hearing process;
Content generation unit confirms document for the document and the word to be added to the hearing process.
Further, the document title determination unit includes:
S (w) is speech signal energy spectral density function, cnFor cepstrum coefficient, pass through cnCepstrum distance l, which can be obtained, is:
N is microphone number, and d is that each microphone position is poor relative to the criterion distance of trial judge position, and wherein N (n) is institute
The noise signal in voice messaging is stated, S (n) is the voice signal for removing the voice messaging after noise;pi(k) be based on cepstrum away from
From speech frequency component,
Short-time average energies of the voice signal x (n) of microphone n at the n moment be:
For Hamming window functions;
To the p of each microphone compositioni(k) matrix, the matrix and E are formednCharacteristic value be multiplied, acquire covariance matrix G;
Characteristic value A is sought to matrix G, and then obtains adjusting signal for the cepstrum of each microphone
Technical scheme of the present invention has the following advantages:
The intelligence inspection business platform based on big data of the live noise of trial can farthest be reduced by realizing, by this
Platform, the noise during word can be converted into voice effectively to be reduced, according to test, HMM compared with the prior art
It identifies that validity is higher by 70% or more to voice-character recognition technology of equal models, therefore is highly suitable for other than court
Any place carries out providing stable and reliable text conversion when case trial, greatly improves in trial efficiency.
Description of the drawings
Fig. 1 shows platform composition frame chart according to a preferred embodiment of the invention.
Specific implementation mode
As shown in Figure 1, a kind of intelligence inspection business platform based on big data, including:
Document big data unit, for storing and the relevant document information of case;
Voice collecting unit, the voice messaging for acquiring case trial scene;
Intelligent voice-text conversion unit, for being converted into word according to voice messaging.
It is described intelligence voice-text conversion unit include:
Document selection unit, for choosing document according to the voice messaging;
Document markup unit, for marking the document according to the voice messaging;
Hearing process confirmation unit confirms document for generating hearing process according to the voice messaging.
The voice collecting unit is multichannel voice collecting unit.
The multichannel voice collecting unit includes speech signal analysis unit and multiple microphones of distributed setting.
The document selection unit includes document title determination unit, is used for according to voice messaging generation word, and according to
The corresponding document title of word chooses document from the document big data unit.
The document markup unit is used to the word being added to the document.
The document big data unit is relationship type document big data unit.
The hearing process confirmation unit includes:
Document establishes unit, confirms document for establishing hearing process;
Content generation unit confirms document for the document and the word to be added to the hearing process.
The document title determination unit includes:
S (w) is speech signal energy spectral density function, cnFor cepstrum coefficient, pass through cnCepstrum distance l, which can be obtained, is:
N is microphone number, and d is that each microphone position is poor relative to the criterion distance of trial judge position, and wherein N (n) is institute
The noise signal in voice messaging is stated, S (n) is the voice signal for removing the voice messaging after noise;pi(k) be based on cepstrum away from
From speech frequency component,
Short-time average energies of the voice signal x (n) of microphone n at the n moment be:
For Hamming window functions;
To the p of each microphone compositioni(k) matrix, the matrix and E are formednCharacteristic value be multiplied, acquire covariance matrix G;
Characteristic value A is sought to matrix G, and then obtains adjusting signal for the cepstrum of each microphone
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all essences in the present invention
All any modification, equivalent and improvement etc., should all be included in the protection scope of the present invention made by within refreshing and principle.
Claims (9)
1. a kind of intelligence inspection business platform based on big data, which is characterized in that including:
Document big data unit, for storing and the relevant document information of case;
Voice collecting unit, the voice messaging for acquiring case trial scene;
Intelligent voice-text conversion unit, for being converted into word according to voice messaging.
2. system according to claim 1, which is characterized in that it is described intelligence voice-text conversion unit include:
Document selection unit, for choosing document according to the voice messaging;
Document markup unit, for marking the document according to the voice messaging;
Hearing process confirmation unit confirms document for generating hearing process according to the voice messaging.
3. system according to claim 2, which is characterized in that the voice collecting unit is multichannel voice collecting list
Member.
4. system according to claim 3, which is characterized in that the multichannel voice collecting unit includes at voice messaging
Manage unit and multiple microphones of distributed setting.
5. system according to claim 2, which is characterized in that the document selection unit includes that document title determines list
Member for generating word according to voice messaging, and is selected according to the corresponding document title of word from the document big data unit
Take document.
6. system according to claim 2, which is characterized in that the document markup unit is for the word to be added to
The document.
7. system according to claim 2, which is characterized in that the document big data unit is relationship type document big data
Unit.
8. system according to claim 2, which is characterized in that the hearing process confirmation unit includes:
Document establishes unit, confirms document for establishing hearing process;
Content generation unit confirms document for the document and the word to be added to the hearing process.
9. system according to claim 2, which is characterized in that the document title determination unit includes:S (w) is voice
Signal energy spectral density function, cnFor cepstrum coefficient, pass through cnCepstrum distance l, which can be obtained, is:
N is microphone number, and d is that each microphone position is poor relative to the criterion distance of trial judge position, and wherein N (n) is institute's predicate
Noise signal in message breath, S (n) are the voice signal for removing the voice messaging after noise;pi(k) it is based on cepstrum distance
Speech frequency component,
Short-time average energies of the voice signal x (n) of microphone n at the n moment be:
For Hamming window functions;
To the p of each microphone compositioni(k) matrix, the matrix and E are formednCharacteristic value be multiplied, acquire covariance matrix G;
Characteristic value A is sought to matrix G, and then obtains adjusting signal for the cepstrum of each microphone
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810067741.XA CN108280188A (en) | 2018-01-24 | 2018-01-24 | Intelligence inspection business platform based on big data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810067741.XA CN108280188A (en) | 2018-01-24 | 2018-01-24 | Intelligence inspection business platform based on big data |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108280188A true CN108280188A (en) | 2018-07-13 |
Family
ID=62804926
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810067741.XA Pending CN108280188A (en) | 2018-01-24 | 2018-01-24 | Intelligence inspection business platform based on big data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108280188A (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101301240A (en) * | 2008-05-21 | 2008-11-12 | 清华大学深圳研究生院 | Electric cochlea Chinese fixed electric stimulation amplitude changing pattern in vitro voice processing equipment |
US20090276216A1 (en) * | 2008-05-02 | 2009-11-05 | International Business Machines Corporation | Method and system for robust pattern matching in continuous speech |
US20100030559A1 (en) * | 2001-03-02 | 2010-02-04 | Mindspeed Technologies, Inc. | System and method for an endpoint detection of speech for improved speech recognition in noisy environments |
CN102254558A (en) * | 2011-07-01 | 2011-11-23 | 重庆邮电大学 | Control method of intelligent wheel chair voice recognition based on end point detection |
CN106326640A (en) * | 2016-08-12 | 2017-01-11 | 上海交通大学医学院附属瑞金医院卢湾分院 | Medical speech control system and control method thereof |
-
2018
- 2018-01-24 CN CN201810067741.XA patent/CN108280188A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100030559A1 (en) * | 2001-03-02 | 2010-02-04 | Mindspeed Technologies, Inc. | System and method for an endpoint detection of speech for improved speech recognition in noisy environments |
US20090276216A1 (en) * | 2008-05-02 | 2009-11-05 | International Business Machines Corporation | Method and system for robust pattern matching in continuous speech |
CN101301240A (en) * | 2008-05-21 | 2008-11-12 | 清华大学深圳研究生院 | Electric cochlea Chinese fixed electric stimulation amplitude changing pattern in vitro voice processing equipment |
CN102254558A (en) * | 2011-07-01 | 2011-11-23 | 重庆邮电大学 | Control method of intelligent wheel chair voice recognition based on end point detection |
CN106326640A (en) * | 2016-08-12 | 2017-01-11 | 上海交通大学医学院附属瑞金医院卢湾分院 | Medical speech control system and control method thereof |
Non-Patent Citations (2)
Title |
---|
张丽艳 等: "一种适用于混响环境的麦克风阵列语音增强方法", 《信号处理》 * |
王金甲: "噪声环境下鲁棒性文本自由说话人辨认系统的研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2020228173A1 (en) | Illegal speech detection method, apparatus and device and computer-readable storage medium | |
US8793130B2 (en) | Confidence measure generation for speech related searching | |
CN108197282B (en) | File data classification method and device, terminal, server and storage medium | |
US8135579B2 (en) | Method of analyzing conversational transcripts | |
CN1270361A (en) | Method and device for audio information searching by content and loudspeaker information | |
KR101178068B1 (en) | Text category classification apparatus and its method | |
CN101447188B (en) | Digital voice print identification system and validation and identification method | |
US20080133235A1 (en) | Method to train the language model of a speech recognition system to convert and index voicemails on a search engine | |
CN112530408A (en) | Method, apparatus, electronic device, and medium for recognizing speech | |
WO2016119604A1 (en) | Voice information search method and apparatus, and server | |
CN112818109B (en) | Intelligent reply method, medium, device and computing equipment for mail | |
CN116665676B (en) | Semantic recognition method for intelligent voice outbound system | |
Nandwana et al. | Analysis of Critical Metadata Factors for the Calibration of Speaker Recognition Systems. | |
CN116150651A (en) | AI-based depth synthesis detection method and system | |
CN114399379A (en) | Artificial intelligence-based collection behavior recognition method, device, equipment and medium | |
CN106095799A (en) | The storage of a kind of voice, search method and device | |
CN111209367A (en) | Information searching method, information searching device, electronic equipment and storage medium | |
US9047872B1 (en) | Automatic speech recognition tuning management | |
CN116484052B (en) | Educational resource sharing system based on big data | |
US7340398B2 (en) | Selective sampling for sound signal classification | |
CN108280188A (en) | Intelligence inspection business platform based on big data | |
CN108182570A (en) | A kind of case wisdom auditing system | |
CN108269205A (en) | A kind of electronic data identification systems using cloud platform | |
CN114449105A (en) | Voice-based electric power customer service telephone traffic quality inspection system | |
US20210249036A1 (en) | Virtual counseling system and counseling method using the same |
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: 20180713 |
|
RJ01 | Rejection of invention patent application after publication |