CN109671436A - The method of intelligent sound identification address book contact name - Google Patents

The method of intelligent sound identification address book contact name Download PDF

Info

Publication number
CN109671436A
CN109671436A CN201811495648.5A CN201811495648A CN109671436A CN 109671436 A CN109671436 A CN 109671436A CN 201811495648 A CN201811495648 A CN 201811495648A CN 109671436 A CN109671436 A CN 109671436A
Authority
CN
China
Prior art keywords
address book
phonetic
contact
name
search
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
Application number
CN201811495648.5A
Other languages
Chinese (zh)
Inventor
陈包容
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Individual
Original Assignee
Individual
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Individual filed Critical Individual
Priority to CN201811495648.5A priority Critical patent/CN109671436A/en
Publication of CN109671436A publication Critical patent/CN109671436A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10LSPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00Speech recognition
    • G10L15/26Speech to text systems
    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10LSPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00Speech recognition
    • G10L15/22Procedures used during a speech recognition process, e.g. man-machine dialogue
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04MTELEPHONIC COMMUNICATION
    • H04M1/00Substation equipment, e.g. for use by subscribers
    • H04M1/26Devices for calling a subscriber
    • H04M1/27Devices whereby a plurality of signals may be stored simultaneously
    • H04M1/274Devices whereby a plurality of signals may be stored simultaneously with provision for storing more than one subscriber number at a time, e.g. using toothed disc
    • H04M1/2745Devices whereby a plurality of signals may be stored simultaneously with provision for storing more than one subscriber number at a time, e.g. using toothed disc using static electronic memories, e.g. chips
    • H04M1/27467Methods of retrieving data
    • H04M1/2748Methods of retrieving data by matching character strings
    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10LSPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00Speech recognition
    • G10L15/22Procedures used during a speech recognition process, e.g. man-machine dialogue
    • G10L2015/223Execution procedure of a spoken command
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04MTELEPHONIC COMMUNICATION
    • H04M2250/00Details of telephonic subscriber devices
    • H04M2250/74Details of telephonic subscriber devices with voice recognition means

Landscapes

  • Engineering & Computer Science (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Machine Translation (AREA)

Abstract

The invention discloses the methods of intelligent sound identification address book contact name, including following main steps: step 1: creation private database, database includes creation address book contact phonetic library and creation phonetic search address book contact ordering method;Step 2: user searches for contact person by verbal instructions, smart machine converts verbal instructions, is converted into textual form, obtains corresponding text search results;Step 3: text search results are converted into phonetic, the address book contact phonetic library in comparison database obtains corresponding contact person's search result.Compared with the name phonetic that the present invention facilitates voice to input is compared with associated databases, it is easy-to-look-up to arrive corresponding contact person, when encountering the multiple contact persons of unisonance, it can preferably be distinguished, contact person can be quickly searched, the time spent by artificial search is reduced, improves speech recognition name rate, speech recognition errors rate is reduced, to improve the experience of user.

Description

The method of intelligent sound identification address book contact name
Technical field
The present invention relates to technical field of voice recognition, the specially method of intelligent sound identification address book contact name.
Background technique
Speech recognition technology is also referred to as automatic speech recognition, and target is the vocabulary Content Transformation in the voice by the mankind For computer-readable input.
Field involved in speech recognition technology includes signal processing, pattern-recognition, probability theory and information theory, sound generating mechanism With hearing mechanism, artificial intelligence etc..
With on the intelligent terminals such as mobile phone speech voice input function it is universal, user uses voice on the intelligent terminals such as mobile phone The demand of input is more and more, and especially by the contact person in phonetic search address list, utilization rate is higher and higher.
However the method for existing voice search address book contact, it is not high enough that there are accuracys rate, user speech search experience Bad problem.
Summary of the invention
The present invention provides the method for intelligent sound identification address book contact name, has more preferably intelligent search and contact The advantages of people, it is not accurate enough to solve existing address list phonetic search contact identification, causes identification to be easy to happen mistake, makes At the bad problem of user speech search experience.
The invention provides the following technical scheme: the method for intelligent sound identification address book contact name, including following masters Step:
Step 1: creation private database, database includes creation address book contact phonetic library and creation phonetic search Address book contact ordering method;
Step 2: user searches for contact person by verbal instructions, smart machine is converted into converting after speech recognition Textual form, to obtain corresponding text search results;
Step 3: text search results are converted into phonetic, the address book contact phonetic library in comparison database, thus Obtain corresponding contact person's search result;
Step 4: being based on phonetic search address book contact ordering method, multiple phonetic search contact person results are carried out Intelligent sequencing, to conveniently obtain the contact person of verbal instructions meaning.
Preferred technical solution, creation address book contact phonetic library are first extracted address book contact name and are used to Phonetic library is created, which further comprises:
Summarize all names of address list, for creating name text phonetic library;
Summarize all names of address list, creation name pinyin compares rule base.
Preferred technical solution, the creation phonetic search address book contact ordering method, first creates address book ordering Rule, which further comprises:
Creation is grouped the ordering rule of display contact person according to address list;
Create the ordering rule according to communication contact person communication frequency.
Preferred technical solution, the comparison in the third step obtain search result the following steps are included:
The phonetic of text search results is matched with name pinyin comparison rule base, obtains corresponding by the first step With angle value;
Second step, by judging matching angle value;
Third step, when matching angle value is greater than the set value, it is possible that multiple results or single as a result, multiple when occurring When as a result, main four step of step the is leapt to, when there is single result, phonetic search is confirmed as and is calculated as a result, terminating;
4th step judges the matching angle value again;
5th step, when matching angle value is greater than the set value, it is possible that multiple results or single as a result, multiple when occurring When as a result, main four step of step the is leapt to, when there is single result, phonetic search is confirmed as and is calculated as a result, terminating;
6th step is defaulted as not searching corresponding contact person when matching angle value lower than setting value, automatic to terminate meter It calculates.
Preferred technical solution, the intelligent sequencing rule further progress of the 4th step, which extends, includes:
The ordering rule sequence of display contact person is grouped according to address list;
It is sorted according to the ordering rule of address book contact communication frequency;
By artificial intelligence mode, ranking results sequence is automatically generated.
Preferred technical solution, the comparison rule of the phonetic comparison rule base, which extend, includes:
Being considered as identical alphabetical library includes:
f≈h;
N ≈ l, such as: Hunan ≈ Forlan;
r≈l;
z≈zh;
C≈ch;
S≈sh;
an≈ang;
en≈eng;
in≈ing;
ian≈iang;
uan≈uang;
User can add new same letter data manually.
Preferred technical solution, the setting of the matching angle value are considered as when matching angle value reaches presetting matching value Successful match.
The present invention have it is following the utility model has the advantages that
The method that the intelligent sound identifies address book contact name, the name phonetic and corresponding data for facilitating voice to input Library, which compares, compares, easy-to-look-up to arrive corresponding contact person, when encountering the multiple contact persons of unisonance, can preferably carry out area Not, contact person can be quickly searched, the time spent by artificial search is reduced, improves speech recognition name rate, reduce voice Error rate is identified, to improve the experience of user.
Detailed description of the invention
Fig. 1 is speech recognition flow chart of the present invention;
Fig. 2 is database sharing figure of the present invention;
Fig. 3 is speech recognition process decision chart of the present invention;
Fig. 4 is contact person of the present invention sequence familygram.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other Embodiment shall fall within the protection scope of the present invention.
Referring to Fig. 1, the method for intelligent sound identification address book contact name, including following main steps:
Step 1: creation private database, database includes creation address book contact phonetic library and creation phonetic search Address book contact ordering method;
Step 2: user searches for contact person by verbal instructions, smart machine is converted into converting after speech recognition Textual form, to obtain corresponding text search results;
Step 3: text search results are converted into phonetic, the address book contact phonetic library in comparison database, thus Obtain corresponding contact person's search result;
Step 4: being based on phonetic search address book contact ordering method, multiple phonetic search contact person results are carried out Intelligent sequencing, to conveniently obtain the contact person of verbal instructions meaning.
Fig. 1 and 2 is please referred to, address book contact phonetic library is created, address book contact name is first extracted and is used to create spelling Sound library, which further comprises:
Summarize all names of address list, for creating name text phonetic library, by the creation in name text phonetic library, Data inside the name pinyin for facilitating voice to convert and the phonetic library compare between carrying out, easy-to-look-up to suitable connection People;
Summarize all names of address list, creation name pinyin compares rule base, compares rule base by phonetic and conveniently mentions For comparison rule, the phonetic of voice converting text is facilitated to be compared with the name pinyin in rule base, to obtain corresponding With angle value, it is worth corresponding query result by matching degree, facilitates the operation for completing next step;
The comparison rule of phonetic comparison rule base, which extend, includes:
Being considered as identical alphabetical library includes:
f≈h;
N ≈ l, such as: Hunan ≈ Forlan;
r≈l;
z≈zh;
C≈ch;
S≈sh;
an≈ang;
en≈eng;
in≈ing;
ian≈iang;
uan≈uang;
User can add new same letter data manually.
Phonetic search address book contact ordering method is created, address book ordering rule, address book ordering rule are first created Then further comprise:
Creation according to address list be grouped display contact person ordering rule, such as: the rule can be household → colleague → Friend → classmate;
The ordering rule according to communication contact person communication frequency is created, which may is that
[from high to low] option
[from low to high] option
[only calculating the telephonic communication frequency] option
[only calculating the message communication frequency] option
Other options.
By the setting of rule base, the sequence of search contact person is conveniently obtained, facilitates carry out Effective selection, facilitates similar The lower user's screening of rate is gone down, and most matched user is lifted to extreme higher position.
Please refer to Fig. 1 and 3, the comparison in third step obtain search result the following steps are included:
The phonetic of text search results is matched with name pinyin comparison rule base, obtains corresponding by the first step With angle value;
Second step matches the setting of angle value, when matching angle value reaches presetting by judging matching angle value When with value, it is considered as successful match;
Third step, when matching angle value is greater than the set value, it is possible that multiple results or single as a result, multiple when occurring When as a result, main four step of step the is leapt to, when there is single result, phonetic search is confirmed as and is calculated as a result, terminating;
4th step judges the matching angle value again;
5th step, when matching angle value is greater than the set value, it is possible that multiple results or single as a result, multiple when occurring When as a result, main four step of step the is leapt to, when there is single result, phonetic search is confirmed as and is calculated as a result, terminating;
6th step is defaulted as not searching corresponding contact person when matching angle value lower than setting value, automatic to terminate meter It calculates.
Fig. 1 and 4 are please referred to, the intelligent sequencing rule further progress extension of the 4th step includes:
The ordering rule sequence of display contact person is grouped according to address list;
It is sorted according to the ordering rule of address book contact communication frequency;
By artificial intelligence mode, automatic production scheduling sort result.
It should be noted that, in this document, relational terms such as first and second and the like are used merely to a reality Body or operation are distinguished with another entity or operation, are deposited without necessarily requiring or implying between these entities or operation In any actual relationship or order or sequence.Moreover, the terms "include", "comprise" or its any other variant are intended to Non-exclusive inclusion, so that the process, method, article or equipment including a series of elements is not only wanted including those Element, but also including other elements that are not explicitly listed, or further include for this process, method, article or equipment Intrinsic element.
It although an embodiment of the present invention has been shown and described, for the ordinary skill in the art, can be with A variety of variations, modification, replacement can be carried out to these embodiments without departing from the principles and spirit of the present invention by understanding And modification, the scope of the present invention is defined by the appended.

Claims (7)

1. the method for intelligent sound identification address book contact name, which is characterized in that including following main steps:
Step 1: creation private database, database includes creation address book contact phonetic library and creation phonetic search communication Record contact sequencing method;
Step 2: user searches for contact person by verbal instructions, smart machine is converted into text to converting after speech recognition Form, to obtain corresponding text search results;
Step 3: text search results are converted into phonetic, the address book contact phonetic library in comparison database, to obtain Corresponding contact person's search result;
Step 4: being based on phonetic search address book contact ordering method, intelligence is carried out to multiple phonetic search contact person results Sequence, to conveniently obtain the contact person of verbal instructions meaning.
2. the method for intelligent sound identification address book contact name according to claim 1, it is characterised in that: the wound Address book contact phonetic library is built, address book contact name is first extracted and is used to create phonetic library, which further comprises:
Summarize all names of address list, for creating name text phonetic library;
Summarize all names of address list, creation name pinyin compares rule base.
3. the method for intelligent sound identification address book contact name according to claim 1, it is characterised in that: the wound Phonetic search address book contact ordering method is built, address book ordering rule is first created, address book ordering rule is further wrapped It includes:
Creation is grouped the ordering rule of display contact person according to address list;
Create the ordering rule according to communication contact person communication frequency.
4. the method for intelligent sound according to claim 1 identification address book contact name, it is characterised in that: described the Comparison in three steps obtain search result the following steps are included:
The phonetic of text search results is matched with name pinyin comparison rule base, obtains corresponding matching degree by the first step Value;
Second step, by judging matching angle value;
Third step, when matching angle value is greater than the set value, it is possible that multiple results or single as a result, when there are multiple results When, main four step of step the is leapt to, when there is single result, phonetic search is confirmed as and is calculated as a result, terminating;
4th step judges the matching angle value again;
5th step, when matching angle value is greater than the set value, it is possible that multiple results or single as a result, when there are multiple results When, main four step of step the is leapt to, when there is single result, phonetic search is confirmed as and is calculated as a result, terminating;
6th step is defaulted as not searching corresponding contact person when matching angle value lower than setting value, and automatic terminate calculates.
5. the method for intelligent sound according to claim 1 identification address book contact name, it is characterised in that: described the The intelligent sequencing rule further progress of four steps extends
The ordering rule sequence of display contact person is grouped according to address list;
It is sorted according to the ordering rule of address book contact communication frequency;
By artificial intelligence mode, ranking results sequence is automatically generated.
6. the method for intelligent sound identification address book contact name according to claim 2, it is characterised in that: the spelling The comparison rule of sound comparison rule base, which extend, includes:
Being considered as identical alphabetical library includes:
f≈h;
N ≈ l, such as: Hunan ≈ Forlan;
r≈l;
z≈zh;
C≈ch;
S≈sh;
an≈ang;
en≈eng;
in≈ing;
ian≈iang;
uan≈uang;
User can add new same letter data manually.
7. the method for intelligent sound identification address book contact name according to claim 4, it is characterised in that: described Setting with angle value is considered as successful match when matching angle value reaches presetting matching value.
CN201811495648.5A 2018-12-07 2018-12-07 The method of intelligent sound identification address book contact name Pending CN109671436A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811495648.5A CN109671436A (en) 2018-12-07 2018-12-07 The method of intelligent sound identification address book contact name

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811495648.5A CN109671436A (en) 2018-12-07 2018-12-07 The method of intelligent sound identification address book contact name

Publications (1)

Publication Number Publication Date
CN109671436A true CN109671436A (en) 2019-04-23

Family

ID=66144220

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811495648.5A Pending CN109671436A (en) 2018-12-07 2018-12-07 The method of intelligent sound identification address book contact name

Country Status (1)

Country Link
CN (1) CN109671436A (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112153206A (en) * 2020-09-23 2020-12-29 北京百度网讯科技有限公司 Contact person matching method and device, electronic equipment and storage medium
CN112364212A (en) * 2020-11-04 2021-02-12 北京致远互联软件股份有限公司 Voice name recognition method based on approximate voice recognition
CN112581954A (en) * 2020-12-01 2021-03-30 杭州九阳小家电有限公司 High-matching voice interaction method and intelligent equipment
CN113094470A (en) * 2021-04-08 2021-07-09 蔡堃 Text searching method and system

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101330687A (en) * 2008-06-10 2008-12-24 中兴通讯股份有限公司 Method for matching numbers according to call frequency and mobile phone
CN102148886A (en) * 2010-02-09 2011-08-10 北京数字天域科技有限责任公司 Method for sorting contact list in mobile phone address book
CN102946463A (en) * 2012-11-01 2013-02-27 广东欧珀移动通信有限公司 Classification method and system for address list
CN104238991A (en) * 2013-06-21 2014-12-24 腾讯科技(深圳)有限公司 Voice input matching method and voice input matching device
CN105187656A (en) * 2015-09-23 2015-12-23 百度在线网络技术(北京)有限公司 Address list contact person matching method and device
CN105489220A (en) * 2015-11-26 2016-04-13 小米科技有限责任公司 Method and device for recognizing speech
CN105721651A (en) * 2016-01-19 2016-06-29 海信集团有限公司 Voice dialing method and device
CN107707745A (en) * 2017-09-25 2018-02-16 百度在线网络技术(北京)有限公司 Method and apparatus for extracting information

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101330687A (en) * 2008-06-10 2008-12-24 中兴通讯股份有限公司 Method for matching numbers according to call frequency and mobile phone
CN102148886A (en) * 2010-02-09 2011-08-10 北京数字天域科技有限责任公司 Method for sorting contact list in mobile phone address book
CN102946463A (en) * 2012-11-01 2013-02-27 广东欧珀移动通信有限公司 Classification method and system for address list
CN104238991A (en) * 2013-06-21 2014-12-24 腾讯科技(深圳)有限公司 Voice input matching method and voice input matching device
CN105187656A (en) * 2015-09-23 2015-12-23 百度在线网络技术(北京)有限公司 Address list contact person matching method and device
CN105489220A (en) * 2015-11-26 2016-04-13 小米科技有限责任公司 Method and device for recognizing speech
CN105721651A (en) * 2016-01-19 2016-06-29 海信集团有限公司 Voice dialing method and device
CN107707745A (en) * 2017-09-25 2018-02-16 百度在线网络技术(北京)有限公司 Method and apparatus for extracting information

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112153206A (en) * 2020-09-23 2020-12-29 北京百度网讯科技有限公司 Contact person matching method and device, electronic equipment and storage medium
CN112153206B (en) * 2020-09-23 2022-08-09 阿波罗智联(北京)科技有限公司 Contact person matching method and device, electronic equipment and storage medium
CN112364212A (en) * 2020-11-04 2021-02-12 北京致远互联软件股份有限公司 Voice name recognition method based on approximate voice recognition
CN112581954A (en) * 2020-12-01 2021-03-30 杭州九阳小家电有限公司 High-matching voice interaction method and intelligent equipment
CN112581954B (en) * 2020-12-01 2023-08-04 杭州九阳小家电有限公司 High-matching voice interaction method and intelligent device
CN113094470A (en) * 2021-04-08 2021-07-09 蔡堃 Text searching method and system
CN113094470B (en) * 2021-04-08 2022-05-24 蔡堃 Text searching method and system

Similar Documents

Publication Publication Date Title
CN109671436A (en) The method of intelligent sound identification address book contact name
EP1585030B1 (en) Automatic Capitalization Through User Modeling
CN106407178B (en) A kind of session abstraction generating method, device, server apparatus and terminal device
CN108564953B (en) Punctuation processing method and device for voice recognition text
CN103456297B (en) A kind of method and apparatus of speech recognition match
CN100578539C (en) Automatic question-answering method and system
CN102867512A (en) Method and device for recognizing natural speech
CN105354199B (en) A kind of recognition methods of entity meaning and system based on scene information
US20040163035A1 (en) Method for automatic and semi-automatic classification and clustering of non-deterministic texts
CN110020422A (en) The determination method, apparatus and server of Feature Words
CN110147421B (en) Target entity linking method, device, equipment and storage medium
CN109918485A (en) The method and device of speech recognition vegetable, storage medium, electronic device
CN102867511A (en) Method and device for recognizing natural speech
CN109815310B (en) Voice processing method, device, storage medium and terminal
CN100504857C (en) Method and apparatus for document filtering capable of efficiently extracting document matching to searcher's intention using learning data
CN106383836A (en) Ascribing actionable attributes to data describing personal identity
CN106205613B (en) A kind of navigation audio recognition method and system
JP2018501540A (en) Stopword identification method and apparatus
US20040006460A1 (en) System and method for problem solution support, and medium storing a program therefor
CN108803890A (en) A kind of input method, input unit and the device for input
CN108536680A (en) A kind of acquisition methods and device of house property information
CN109284362B (en) Content retrieval method and system
CN110265019A (en) A kind of method and speech robot people's system of speech recognition
CN106844734B (en) Method for automatically generating session reply content
CN110196635B (en) Gesture input method based on wearable equipment

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20190423