CN104732974A - Intelligent recording and recognizing system - Google Patents
Intelligent recording and recognizing system Download PDFInfo
- Publication number
- CN104732974A CN104732974A CN201310710976.3A CN201310710976A CN104732974A CN 104732974 A CN104732974 A CN 104732974A CN 201310710976 A CN201310710976 A CN 201310710976A CN 104732974 A CN104732974 A CN 104732974A
- Authority
- CN
- China
- Prior art keywords
- module
- recording
- user
- voiceprint
- voice
- 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.)
- Granted
Links
Abstract
The invention discloses an intelligent recording and recognizing system. The intelligent recording and recognizing system comprises a recording module, a voiceprint recognizing module, a keyword matching module and a determining module. The recording module is used for performing on-line recording on communication voice of a user to obtain recording information; the voiceprint recognizing module is connected to the recording module and used for performing voiceprint recognizing and file conversion on the recording information to obtain text information; the keyword matching module is connected to the voiceprint recognizing module and used for matching the text information according to preset keywords; the determining module is connected to the keyword matching module and used for determining that the communication voice belongs to standardization voice on the condition of successful matching and determining that the communication voice belongs to non-standardization voice on the condition of failing matching. According to the intelligent recording and recognizing system, the effects of improving the recognizing efficiency and quality of dispatching recording, promoting the safety supervision work efficiency and enhancing the standardability of dispatching ordering are achieved.
Description
Technical field
The present invention relates to field of power communication, in particular to a kind of intelligence recording recognition system.
Background technology
Ordering to record for scheduling and supervise, there is some problems in current safety monitor work.Make us standard works under relying on administrative practice constrained dispatch and arrange full-time staff to listen to sound recordings, cannot meet present situation, such as, the monthly average for certain city electric company is ordered recording 8000, is difficult to accomplish to monitor one by one.And by the mode of artificial sampling observation audiometry, scheduling quality cannot be evaluated fully and effectively, be difficult to guarantee the scheduling term of the proper use of regulation of dispatcher and dispatch command is accurate, errorless.
For the mode of recording of being ordered by artificial sampling observation audiometry in correlation technique, the problem of scheduling quality cannot be evaluated fully and effectively, not yet propose effective solution at present.
Summary of the invention
The invention provides one intelligence recording recognition system, at least to solve in above-mentioned correlation technique the mode of recording of being ordered by artificial sampling observation audiometry, the problem of scheduling quality cannot be evaluated fully and effectively.
According to the present invention, provide a kind of intelligence recording recognition system, comprising: recording module, for carrying out on-line recording to the call voice of user, obtaining recorded message; Voiceprint identification module, is connected to recording module, for carrying out Application on Voiceprint Recognition and file transform to recorded message, obtains text message; Keyword-matching module, is connected to voiceprint identification module, for mating text message according to the key word preset; Confirm module, be connected to keyword-matching module, for when the match is successful, confirm that call voice belongs to standardization voice, when it fails to match, confirm that call voice belongs to non-standardization voice.
Preferably, this system also comprises: authentication module, is connected to recording module, for according to preset the identity of user's Permission Levels information to user differentiate, when differentiate by, determine that the identity of user is legal, otherwise, determine that the identity of user is illegal.
Preferably, voiceprint identification module comprises: Application on Voiceprint Recognition unit, for using the sound-groove model in the sound-groove model storehouse that pre-sets to carry out Application on Voiceprint Recognition to recorded message, obtains the voiceprint after identifying; Converting unit, for converting voiceprint to text message.
Preferably, this system also comprises: prompting module, is connected to confirmation module, for when confirming that module confirms that call voice belongs to non-standardization voice, reminds user's operating specification language to re-start call.
Preferably, user comprises: dispatching the personnel that order or dispatch will the person of making us.
Preferably, when user for scheduling order personnel or scheduling will the person of making us, prompting module reminds scheduling personnel of ordering to re-start to order or remind scheduling the person of making us to re-start and will make.
Preferably, key word comprise following one of at least: order phrase information, user's identity phrase information, request phrase information, recipient's phrase information.
Preferably, order phrase information comprises following crucial phrase one of at least and pulls open, closes; User's identity phrase information comprises following crucial phrase one of at least: the organization of user, the name of user.
Preferably, voiceprint comprises: sound end, word speed, average word speed, abnormal emotion and quiet duration.
Preferably, call voice comprises: online call voice, or on-the-spot call voice.
Pass through the present invention, adopt the supervision area of recording data application speech analysis techniques being applied to grid dispatching center recording system and live recording notes record, voice messaging is converted to the text message of index structure, pass through keyword retrieval, screening, the Treatment Analysis such as business classification, to the mode that dispatching record identifies, solve in correlation technique the mode of recording of being ordered by artificial sampling observation audiometry, the problem of scheduling quality cannot be evaluated fully and effectively, reach the recognition efficiency and quality that improve dispatching record, promote safety monitor work efficiency, the effect of the standardization of ordering is dispatched in strengthening.
Accompanying drawing explanation
Accompanying drawing described herein is used to provide a further understanding of the present invention, and form a application's part, schematic description and description of the present invention, for explaining the present invention, does not form inappropriate limitation of the present invention.In the accompanying drawings:
Fig. 1 is the structured flowchart of the intelligence recording recognition system according to the embodiment of the present invention;
Fig. 2 is the structured flowchart of the preferred intelligence recording recognition system according to the embodiment of the present invention;
Fig. 3 is the workflow schematic diagram of intelligence recording recognition system according to the preferred embodiment of the invention;
Fig. 4 is that intelligence recording recognition system inquires about the schematic diagram of voice of ordering according to the preferred embodiment of the invention;
Fig. 5 is that intelligence records recognition system to the schematic diagram of user's authenticating identity according to the preferred embodiment of the invention;
Fig. 6 is that intelligence recording recognition system is identifying the schematic diagram carrying out speech retrieval in Recording Process according to the preferred embodiment of the invention.
Embodiment
Hereinafter also describe the present invention in detail with reference to accompanying drawing in conjunction with the embodiments.It should be noted that, when not conflicting, the embodiment in the application and the feature in embodiment can combine mutually.
Embodiments provide a kind of intelligence recording recognition system.Fig. 1 is the structured flowchart of the intelligence recording recognition system according to the embodiment of the present invention, and as shown in Figure 1, this intelligence recording recognition system comprises: recording module 10, voiceprint identification module 20, keyword-matching module 30 and confirmation module 40.Wherein:
Recording module 10, for carrying out on-line recording to the call voice of user, obtains recorded message; Voiceprint identification module 20, is connected to recording module 10, for carrying out Application on Voiceprint Recognition and file transform to recorded message, obtains text message; Keyword-matching module 30, is connected to voiceprint identification module 20, for mating text message according to the key word preset; Confirm module 40, be connected to keyword-matching module 30, for when the match is successful, confirm that call voice belongs to standardization voice, when it fails to match, confirm that call voice belongs to non-standardization voice.
Fig. 2 is the structured flowchart of the preferred intelligence recording recognition system according to the embodiment of the present invention, as shown in Figure 2, this preferred intelligence recording recognition system can also comprise: authentication module 50, be connected to recording module 10, for according to preset the identity of user's Permission Levels information to user differentiate, when differentiate by, determine that the identity of user is legal, otherwise, determine that the identity of user is illegal.
In this preferably intelligence recording recognition system, voiceprint identification module 20 can comprise: Application on Voiceprint Recognition unit 22, for using the sound-groove model in the sound-groove model storehouse that pre-sets to carry out Application on Voiceprint Recognition to recorded message, obtains the voiceprint after identifying; Converting unit 24, for converting voiceprint to text message.
Preferably, this preferred intelligence recording recognition system can also comprise: prompting module 60, being connected to and confirming module 40, for when confirming that module 40 confirms that call voice belongs to non-standardization voice, reminding user's operating specification language to re-start call.
In the present embodiment, user can comprise: dispatching the personnel that order or dispatch will the person of making us.
In the present embodiment, when user for scheduling order personnel or scheduling will the person of making us, prompting module reminds scheduling personnel of ordering to re-start to order or remind scheduling the person of making us to re-start and will make.
In the present embodiment, key word can comprise following one of at least: order phrase information, user's identity phrase information, request phrase information, recipient's phrase information.
In the present embodiment, order phrase information can comprise following crucial phrase one of at least and pulls open, closes; User's identity phrase information comprises following crucial phrase one of at least: the organization of user, the name of user.
In the present embodiment, voiceprint can comprise: sound end, word speed, average word speed, abnormal emotion and quiet duration.
In the present embodiment, call voice can comprise: online call voice, or on-the-spot call voice.
Below in conjunction with Fig. 3 to Fig. 6 and preferred embodiment, the intelligence recording recognition system that above-described embodiment provides is further described in more detail and is illustrated.
The intelligence recording recognition system that this preferred embodiment provides is the set of system in conjunction with the regulatory format design of safety supervision department on the basis of existing recording system.The scope that this system can manage can cover management by objective and the evaluation of safety monitor work, order process management and supervision, interpretation of result and examination, error rate statistic and the important step such as to report, the access scope of this system contains the data of existing telephone recording system, the recording file data that the recording substance file of execute-in-place recording pen and next step recording data are synchronously translated online.
Fig. 3 is the workflow schematic diagram of intelligence recording recognition system according to the preferred embodiment of the invention, and as shown in Figure 3, this workflow is implemented mainly through following several stages:
Stage one, first-selected ground, safety monitor department carries out historical data inspection, optimize original workflow, by the intelligence recording recognition system of newly building, sound is utilized to transform the technology of word, by recording of ordering in the past, carry out sort check, recording of ordering, field staff make recording and other daily calling records distinguish again.For recording category division and content are monitored, the efficiency far using intelligence recording recognition system to carry out identifying exceedes traditional artificial cognition.
Through optimization sound-groove model repeatedly, while personnel's input amount is reduced greatly, recording is checked on the quality and is also obviously promoted.By the judgement of crucial phrase, recording is transformed into word and mates line by line with crucial phrase by system automatically, and listening quality is guaranteed, and people listens to the detection leakage phenomenon that fatigue causes to be stopped at all.
Fig. 4 is that intelligence recording recognition system inquiry is according to the preferred embodiment of the invention ordered the schematic diagram of voice, please refer to Fig. 4, after recording recognition technology completes, under make us specification and order also to realize Back-Supervision.By the sound-groove model in system and set crucial phrase, as crucial phrases such as " pull open, close, order, organization, name ", make accurate discriminance analysis and confirm.
In the preferred embodiment, the current check of dispatching record and supervision and check not only the behavior of the person of making us will carry out omnidistance supervision to order personnel and scheduling of scheduling, Fig. 5 is that intelligence records recognition system to the schematic diagram of user's authenticating identity according to the preferred embodiment of the invention, as shown in Figure 5, can simultaneously under make us, the legitimacy of making us identity realizes synchronous supervision, by intelligence recording discriminance analysis system under make us, make us identity and make examination confirmation, the disqualification personnel that take precautions against act as fraudulent substitute for a person, be engaged in unlawful activities, affect power network safety operation.
Stage two, this stage belong to carries out extraction planning, management to the call voice in future, to accomplish real-time online error correction, under make us and will make us utilization scheduling term in once not meet codes and standards, these personnel of system automatic-prompting use specification term again to order maybe will make, and stop habitual violating the regulations from root.Realize rectifying and improving in thing afterwards and correcting in time, change to real-time prompting from inspection afterwards in the past.
Systematic difference realizes comprehensively, overall process, omnibearing supervision management and control, improve power supply enterprise to electric power netting safe running control ability and person works's efficiency.Utilize modern management mode, made the safety and stability of operation of power networks commander link, farthest improved work efficiency and work quality.
In this preferred embodiments, when intelligence recording recognition system mainly comprises the following aspects to the process identified of recording:
1, speech transcription (identification).Speech transcription, refers to and non-structured voice document is converted to structurized text message.This is the Core Feature of speech analysis.
Speech analysis is applied, and the voice after being separated is converted to Chinese phonetic symbol by acoustic model, then by the language model of super large WordNet, phonetic symbol information is identified as content of text.In conjunction with native accent and dispatching of power netwoks term, optimize acoustic model and language model, to promote speech transcription accuracy rate.
2, speech index.Speech index, refers to and the various information comprised in voice is carried out identifying and sorting out, and forms the index facilitating query statistic.
Speech analysis is applied, detect the amplitude of variation such as fundamental frequency, pitch of recording of taking on the telephone, prediction anxious state of mind also locates its positional information, analyzes average word speed and the Speed variation of calling record, detect the mute time etc. of calling record, generate the index file of standard XML format.Index content comprises: the word transcription result of (1) regulation and control personnel's voice and operations staff's voice; (2) if two-channel voice, then channel information (which sound channel keyword is positioned at) is provided; (3) information such as the sound end conversed, word speed, mainly comprise regulation and control personnel and operations staff's beginning and ending time of at every turn speaking separately, word speed (word/second), average word speed (word/second), abnormal emotion, quiet duration etc.
3, speech retrieval.Speech retrieval, refers to the rapid screening of carrying out key word information from index file, returns sound result and carries out programming count.Speech retrieval, supports the functions such as logical combination retrieval, quadratic search.Here for the ease of understanding the process of speech retrieval, can reference diagram 6(Fig. 6 be that intelligence recording recognition system is identifying in Recording Process the schematic diagram carrying out speech retrieval according to the preferred embodiment of the invention).
4, scene cut.Scene cut, refers to and detects the double-talk behavior in calling record, cut and be separated.At present, in dispatching record, the whole dialogues of same sound recordings regulation and control personnel and operations staff.
Speech analysis is applied, and be separated, and then specific aim is monitored respectively scheduling quality and analyzes, with identification problem origination point and problem content by scene cut technology to two side's dialog contexts.Consider from the angle of onsite application, provide conveniently to safety inspection work, improve work efficiency.Consider from marketable value angle, this software can frequently use in the routine work of safety supervision specialty, and the prospect applied in the safety supervision professional work of whole Beijing company is also comparatively extensive.
By the enforcement of this preferred embodiments, following target of the present invention can be realized: 1, realize three liftings: (1) improved efficiency, break the artificial limitation monitored, utilize the round-the-clock characteristic of system, promote and listen to efficiency.(2) increased quality, skips the thinking inertia of human brain, utilizes and translates pattern, do and word for word verify.(3) managerial promotion, improves conventional security supervision supervision work mode, utilizes the rule formulated, and directly to going out graphics data, concerned issue is described.2, key word is set up, strengthening sound-groove model storehouse, jcharge factor and recording quality are promoted again, utilize sound-groove model to carry out specification to order term, while dispatcher orders, system background accomplishes that sorting judges, promote the standardization of term of ordering, in time prompting is provided for nonstandard operation of ordering, ordering, link just at utmost guarantees that quality is correct, utilize intelligence recording recognition technology, changing the passive supervision method of traditional personnel is system initiatively prompt modes, realizes a series of activities such as modernization security control, supervisor, examination simultaneously.3, under quality and efficiency can both obtain the abundant prerequisite ensured, we widen thinking by intelligent communication technology, pass through Application on Voiceprint Recognition, sound wave is adopted to verify for the scheduling personnel of ordering, sound in conjunction with the personnel that ordered in the past gathers, and formulates standard of ordering safely, at utmost promotes the legitimacy of dispatching and ordering, not only ensured electrical network strong safe while, also stride forward to Intelligent Developing Trends.
It should be noted that, above-mentioned modules can be realized by hardware.Such as: a kind of processor, comprise above-mentioned modules, or above-mentioned modules lays respectively in a processor.
In another embodiment, additionally provide a kind of software, this software is for performing the technical scheme described in above-described embodiment and preferred implementation.
In another embodiment, additionally provide a kind of storage medium, store above-mentioned software in this storage medium, this storage medium includes but not limited to: CD, floppy disk, hard disk, scratch pad memory etc.
From above description, can find out, present invention achieves following technique effect: application speech analysis techniques transfers the recording data of grid dispatching center recording system and live recording notes record to index information (text structure), by Treatment Analysis such as keyword retrieval, screening, business classification, qualitative leap has been had to the efficiency of dispatching record identification and quality, have passed through the application in site environment and improve and upgrade, while lifting safety monitor work efficiency, enhance again the standardization of dispatching and ordering.
Obviously, those skilled in the art should be understood that, above-mentioned of the present invention each module or each step can realize with general calculation element, they can concentrate on single calculation element, or be distributed on network that multiple calculation element forms, alternatively, they can realize with the executable program code of calculation element, thus, they can be stored and be performed by calculation element in the storage device, and in some cases, step shown or described by can performing with the order be different from herein, or they are made into each integrated circuit modules respectively, or the multiple module in them or step are made into single integrated circuit module to realize.Like this, the present invention is not restricted to any specific hardware and software combination.
The foregoing is only the preferred embodiments of the present invention, be not limited to the present invention, for a person skilled in the art, the present invention can have various modifications and variations.Within the spirit and principles in the present invention all, any amendment done, equivalent replacement, improvement etc., all should be included within protection scope of the present invention.
Claims (10)
1. an intelligence recording recognition system, is characterized in that, comprising:
Recording module, for carrying out on-line recording to the call voice of user, obtains recorded message;
Voiceprint identification module, is connected to described recording module, for carrying out Application on Voiceprint Recognition and file transform to described recorded message, obtains text message;
Keyword-matching module, is connected to described voiceprint identification module, for mating described text message according to the key word preset;
Confirm module, be connected to described keyword-matching module, for when the match is successful, confirm that described call voice belongs to standardization voice, when it fails to match, confirm that described call voice belongs to non-standardization voice.
2. system according to claim 1, is characterized in that, described system also comprises:
Authentication module, is connected to described recording module, for differentiating according to the identity of user's Permission Levels information to described user preset, when differentiate by, determine that the identity of described user is legal, otherwise, determine that the identity of described user is illegal.
3. system according to claim 1, is characterized in that, described voiceprint identification module comprises:
Application on Voiceprint Recognition unit, for using the sound-groove model in the sound-groove model storehouse that pre-sets to carry out Application on Voiceprint Recognition to described recorded message, obtains the voiceprint after identifying;
Converting unit, for converting described voiceprint to described text message.
4. system according to claim 1, is characterized in that, described system also comprises:
Prompting module, is connected to described confirmation module, for when described confirmation module confirms that described call voice belongs to non-standardization voice, reminds described user's operating specification language to re-start call.
5. system according to claim 4, is characterized in that, described user comprises: dispatching the personnel that order or dispatch will the person of making us.
6. system according to claim 5, it is characterized in that, when described user for scheduling order personnel or scheduling will the person of making us, described prompting module reminds the described scheduling personnel of ordering to re-start to order or remind described scheduling the person of making us to re-start and will make.
7. system according to claim 1, is characterized in that, described key word comprise following one of at least: order phrase information, user's identity phrase information, request phrase information, recipient's phrase information.
8. system according to claim 7, is characterized in that,
Described order phrase information comprises following crucial phrase one of at least and pulls open, closes;
Described user's identity phrase information comprises following crucial phrase one of at least: the organization of user, the name of user.
9. system according to any one of claim 1 to 8, is characterized in that, described voiceprint comprises: sound end, word speed, average word speed, abnormal emotion and quiet duration.
10. system according to any one of claim 1 to 8, is characterized in that, described call voice comprises: online call voice, or on-the-spot call voice.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310710976.3A CN104732974B (en) | 2013-12-19 | 2013-12-19 | Intelligence recording identifying system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310710976.3A CN104732974B (en) | 2013-12-19 | 2013-12-19 | Intelligence recording identifying system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104732974A true CN104732974A (en) | 2015-06-24 |
CN104732974B CN104732974B (en) | 2019-05-24 |
Family
ID=53456813
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201310710976.3A Active CN104732974B (en) | 2013-12-19 | 2013-12-19 | Intelligence recording identifying system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104732974B (en) |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105895132A (en) * | 2016-03-18 | 2016-08-24 | 北京智驾互联信息服务有限公司 | Vehicle-mounted voice recording method, apparatus and system |
CN106254696A (en) * | 2016-08-02 | 2016-12-21 | 北京京东尚科信息技术有限公司 | Outgoing call result determines method, Apparatus and system |
WO2017016449A1 (en) * | 2015-07-24 | 2017-02-02 | 中兴通讯股份有限公司 | Processing method and device for divulgence prevention |
CN107886955A (en) * | 2016-09-29 | 2018-04-06 | 百度在线网络技术(北京)有限公司 | A kind of personal identification method, device and the equipment of voice conversation sample |
CN107886975A (en) * | 2017-11-07 | 2018-04-06 | 广东欧珀移动通信有限公司 | Processing method, device, storage medium and the electronic equipment of audio |
CN109119084A (en) * | 2018-07-13 | 2019-01-01 | 广东电网有限责任公司 | A kind of dispatch call method and system based on speech recognition |
CN109635624A (en) * | 2018-10-15 | 2019-04-16 | 西北铁道电子股份有限公司 | For the hitch of railcar automated driving system, train pipe monitoring method and system |
CN110943536A (en) * | 2019-10-17 | 2020-03-31 | 国网浙江省电力有限公司金华供电公司 | System and method for applying voice recognition to power grid dispatching monitoring |
CN111081245A (en) * | 2019-12-24 | 2020-04-28 | 杭州纪元通信设备有限公司 | Call center menu system based on voice recognition |
CN111092996A (en) * | 2019-10-31 | 2020-05-01 | 国网山东省电力公司信息通信公司 | Centralized scheduling recording system and control method |
CN111128233A (en) * | 2019-10-12 | 2020-05-08 | 中国平安财产保险股份有限公司 | Recording detection method and device, electronic equipment and storage medium |
CN111223496A (en) * | 2020-01-03 | 2020-06-02 | 广东电网有限责任公司 | Voice information classification method and device |
CN111432062A (en) * | 2020-05-12 | 2020-07-17 | 国网天津市电力公司 | Intelligent authentication recording telephone system |
CN112509583A (en) * | 2020-11-27 | 2021-03-16 | 贵州电网有限责任公司 | Auxiliary supervision method and system based on scheduling operation order system |
CN113488061A (en) * | 2021-08-05 | 2021-10-08 | 国网江苏省电力有限公司 | Distribution network dispatcher identity verification method and system based on improved Synth2Aug |
CN114171011A (en) * | 2021-12-25 | 2022-03-11 | 中国人民解放军战略支援部队信息工程大学 | Monophonic voice recognition method and system based on railway scheduling |
CN114239593A (en) * | 2021-12-02 | 2022-03-25 | 国网山东省电力公司信息通信公司 | Scheduling recording intelligent monitoring method and system based on semantic analysis |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101292282A (en) * | 2005-08-29 | 2008-10-22 | 沃伊斯博克斯科技公司 | Mobile systems and methods of supporting natural language human-machine interactions |
JP2010109618A (en) * | 2008-10-29 | 2010-05-13 | Ntt Communications Kk | Authentication device, authentication method, and program |
CN102223367A (en) * | 2011-06-10 | 2011-10-19 | 安徽科大讯飞信息科技股份有限公司 | Method, device and system for accessing website of mobile subscriber |
CN103077721A (en) * | 2012-12-25 | 2013-05-01 | 百度在线网络技术(北京)有限公司 | Voice memorandum method of mobile terminal and mobile terminal |
-
2013
- 2013-12-19 CN CN201310710976.3A patent/CN104732974B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101292282A (en) * | 2005-08-29 | 2008-10-22 | 沃伊斯博克斯科技公司 | Mobile systems and methods of supporting natural language human-machine interactions |
JP2010109618A (en) * | 2008-10-29 | 2010-05-13 | Ntt Communications Kk | Authentication device, authentication method, and program |
CN102223367A (en) * | 2011-06-10 | 2011-10-19 | 安徽科大讯飞信息科技股份有限公司 | Method, device and system for accessing website of mobile subscriber |
CN103077721A (en) * | 2012-12-25 | 2013-05-01 | 百度在线网络技术(北京)有限公司 | Voice memorandum method of mobile terminal and mobile terminal |
Cited By (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2017016449A1 (en) * | 2015-07-24 | 2017-02-02 | 中兴通讯股份有限公司 | Processing method and device for divulgence prevention |
CN105895132A (en) * | 2016-03-18 | 2016-08-24 | 北京智驾互联信息服务有限公司 | Vehicle-mounted voice recording method, apparatus and system |
CN105895132B (en) * | 2016-03-18 | 2019-12-13 | 北京智驾互联信息服务有限公司 | vehicle-mounted voice recording method, device and system |
CN106254696A (en) * | 2016-08-02 | 2016-12-21 | 北京京东尚科信息技术有限公司 | Outgoing call result determines method, Apparatus and system |
CN107886955A (en) * | 2016-09-29 | 2018-04-06 | 百度在线网络技术(北京)有限公司 | A kind of personal identification method, device and the equipment of voice conversation sample |
CN107886975A (en) * | 2017-11-07 | 2018-04-06 | 广东欧珀移动通信有限公司 | Processing method, device, storage medium and the electronic equipment of audio |
CN109119084A (en) * | 2018-07-13 | 2019-01-01 | 广东电网有限责任公司 | A kind of dispatch call method and system based on speech recognition |
CN109635624A (en) * | 2018-10-15 | 2019-04-16 | 西北铁道电子股份有限公司 | For the hitch of railcar automated driving system, train pipe monitoring method and system |
CN111128233A (en) * | 2019-10-12 | 2020-05-08 | 中国平安财产保险股份有限公司 | Recording detection method and device, electronic equipment and storage medium |
CN110943536A (en) * | 2019-10-17 | 2020-03-31 | 国网浙江省电力有限公司金华供电公司 | System and method for applying voice recognition to power grid dispatching monitoring |
CN111092996A (en) * | 2019-10-31 | 2020-05-01 | 国网山东省电力公司信息通信公司 | Centralized scheduling recording system and control method |
CN111081245A (en) * | 2019-12-24 | 2020-04-28 | 杭州纪元通信设备有限公司 | Call center menu system based on voice recognition |
CN111223496A (en) * | 2020-01-03 | 2020-06-02 | 广东电网有限责任公司 | Voice information classification method and device |
CN111432062A (en) * | 2020-05-12 | 2020-07-17 | 国网天津市电力公司 | Intelligent authentication recording telephone system |
CN112509583A (en) * | 2020-11-27 | 2021-03-16 | 贵州电网有限责任公司 | Auxiliary supervision method and system based on scheduling operation order system |
CN112509583B (en) * | 2020-11-27 | 2023-07-18 | 贵州电网有限责任公司 | Auxiliary supervision method and system based on scheduling operation ticket system |
CN113488061A (en) * | 2021-08-05 | 2021-10-08 | 国网江苏省电力有限公司 | Distribution network dispatcher identity verification method and system based on improved Synth2Aug |
CN113488061B (en) * | 2021-08-05 | 2024-02-23 | 国网江苏省电力有限公司 | Distribution network dispatcher identity verification method and system based on improved Synth2Aug |
CN114239593A (en) * | 2021-12-02 | 2022-03-25 | 国网山东省电力公司信息通信公司 | Scheduling recording intelligent monitoring method and system based on semantic analysis |
CN114171011A (en) * | 2021-12-25 | 2022-03-11 | 中国人民解放军战略支援部队信息工程大学 | Monophonic voice recognition method and system based on railway scheduling |
Also Published As
Publication number | Publication date |
---|---|
CN104732974B (en) | 2019-05-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104732974A (en) | Intelligent recording and recognizing system | |
CN110335612A (en) | Minutes generation method, device and storage medium based on speech recognition | |
CN107799120A (en) | Service robot identifies awakening method and device | |
CN103258535A (en) | Identity recognition method and system based on voiceprint recognition | |
US11676576B2 (en) | Organizational-based language model generation | |
WO2020119448A1 (en) | Voice information verification | |
CN110457432A (en) | Interview methods of marking, device, equipment and storage medium | |
CN105975514A (en) | Automatic quality testing method and system | |
CN107093431A (en) | A kind of method and device that quality inspection is carried out to service quality | |
CN101447188B (en) | Digital voice print identification system and validation and identification method | |
CN103530912A (en) | Attendance recording system having emotion identification function, and method thereof | |
CN109192194A (en) | Voice data mask method, device, computer equipment and storage medium | |
CN106356057A (en) | Speech recognition system based on semantic understanding of computer application scenario | |
CN111326153A (en) | Power grid intelligent regulation and control auxiliary robot interaction method based on semantic understanding | |
CN110489527A (en) | Banking intelligent consulting based on interactive voice and handle method and system | |
CN104538034A (en) | Voice recognition method and system | |
CN109887508A (en) | A kind of meeting automatic record method, electronic equipment and storage medium based on vocal print | |
CN102867276A (en) | Interactive control method based on electric power operational system | |
CN108257594A (en) | A kind of conference system and its information processing method | |
US10897368B2 (en) | Integrating an interactive virtual assistant into a meeting environment | |
CN107451131A (en) | A kind of audio recognition method and device | |
CN113140219A (en) | Regulation and control instruction generation method and device, electronic equipment and storage medium | |
CN103812679B (en) | A kind of massive logs statistical analysis system and method | |
WO2022267322A1 (en) | Method and apparatus for generating meeting summary, and terminal device and computer storage medium | |
US9047872B1 (en) | Automatic speech recognition tuning management |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |