CN103220151A - User correlation method based on voice recognition - Google Patents
User correlation method based on voice recognition Download PDFInfo
- Publication number
- CN103220151A CN103220151A CN2013101339441A CN201310133944A CN103220151A CN 103220151 A CN103220151 A CN 103220151A CN 2013101339441 A CN2013101339441 A CN 2013101339441A CN 201310133944 A CN201310133944 A CN 201310133944A CN 103220151 A CN103220151 A CN 103220151A
- Authority
- CN
- China
- Prior art keywords
- group
- terminal
- server
- user
- sound
- 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
Landscapes
- Telephonic Communication Services (AREA)
Abstract
A user correlation method based on voice recognition is based on a system which comprises a server and N terminals, wherein the N terminals are close enough to one another in a physical mode and are respectively provided with voice recording equipment. The method includes the steps of enabling the N terminals to enter a waiting state, turning on all the recording equipment; obtaining, through all the terminals, voice which is sent by a user of any one terminal, and storing the voice as characteristic audio files through all the terminals; sending a characteristic audio file of a terminal A and an account number of the terminal A to the server by the terminal A, requesting for setting up a group; setting up the group which takes the characteristic audio file as a group command; sending characteristic audio files and account numbers of the other terminals to the server through the other terminals, requesting for adding to the group by the other terminals; traversing the group which is sep up through the server, comparing a received characteristic audio file with the group command through the server, adding a user account to the group if the received characteristic audio file coincides with the group command; and setting up the group after repeating N-1 times of the above steps. The user correlation method based on the voice recognition has the advantages of rapidly conducting correlation on a plurality of users which are close to one another in a physical mode, simplifying user operation and adding operation interestingness.
Description
Technical field
The present invention relates to a kind of network user management method, specifically is a kind of user's correlating method based on voice recognition.
Background technology
Now, the mobile Internet development is very fast, and a lot of mobile Internets are used the management that all relates to the network user, particularly various online digital shops and game on line.
In online digital shop, each user has number of the account on server, write down the digital commodities of oneself buying, for security consideration, the user must provide password when accessing to your account internal information and digital commodities, in this case, if the user wishes under the situation of not informing their password very difficult certain digital commodities of sharing oneself with other people.
In game on line, each user has number of the account equally on server, writes down the recreation archives of oneself.When the user wants that when other people formed team and play, must carry out loaded down with trivial details operation: set up team, set team's title and password, each one searched for team respectively, input team's password also adds team.
In order to overcome the above problems, be necessary to invent a kind of user's correlating method, allow the user form group with other people easily, share digital commodities or common recreation.
Summary of the invention
The present invention proposes a kind of user's correlating method based on voice recognition, and this method can allow physically approaching a plurality of users carry out association quickly and easily, forms a group.
This method realizes based on following system:
1, a server and N terminal (N is greater than 1) is arranged in the system, connect by network between server and the terminal, server is judged the identity of institute's connecting terminal by user account.
2, have 1 and to have only 1 terminal be group originator in N terminal, be assumed to be terminal A, other N-1 terminal is a group member.
3, terminal A goes up and uses a user account Connection Service device, and other N-1 terminal used M user account, and (1≤M≤N-1), this M+1 number of the account is different mutually.
4, N terminal is enough approaching physically, and standard is that N terminal user separately can hear the sound that other users send clearly.
5, N terminal all is equipped with sound pick-up outfit.
On basis based on above system, should be as follows based on the idiographic flow that user's correlating method of voice recognition is realized:
Step S1: terminal A enters group and initiates wait state, and other N-1 terminal enters group and adds wait state, after an above N terminal enters wait state, all opens sound pick-up outfit;
Step S2: the user of any one terminal sends a sound, and this sound can be any sound, and the sound pick-up outfit of all terminals obtains this sound, and saves as the characteristic sounds file;
Step S3: terminal A is sent to server with characteristic sounds file and self number of the account, and sends the request of setting up group;
Step S4: after server is received the request of setting up group, set up a G of group, the password of this group is set at the audio files of receiving;
Step S5: characteristic sounds file that other N-1 terminal will obtain separately and number of the account separately are sent to server, and send the request that adds group;
Step S6: server is after receiving that adding group asks, the traversal group that T set up in second before the request of receiving, and the characteristic sounds file received and characteristic sounds file as group's password compared, if comparison result unanimity, then this user account is added group, add group otherwise just refuse this user;
Step S7:, postpone T and attempt once more after second if, then waiting list is put in this request through not finding the group that can add after the traversal;
Step S8: after above step S6 and S7 repeated N-1 time, final group set up, and the user in the group can be according to setting the authority shared resource.
The value of above-mentioned T can set up on their own as required.
For the ease of the sound comparison, follow following flow process when each terminal utilizes sound pick-up outfit to obtain characteristic sounds among the above-mentioned steps S2:
At first obtain 500 milliseconds of voice signals sound as a setting;
The analysis background voice signal obtains the maximum V of background sound intensity, gets V*1.3 as threshold value;
The voice signal that supervision is obtained, when intensity of sound surpassed threshold value, opening entry voice signal, and continue record W second was preserved and as characteristic sounds.The value of W can set up on their own as required.
In order to reduce the operand of audio files comparison, can add the geographical position in addition as auxiliary judgment, in described step S3, terminal A is sent to server with characteristic sounds file, the geographical position of self and self number of the account, and sends the request of setting up group; Among the described step S5, the characteristic sounds file that other N-1 terminal will obtain separately, the geographical position letter of self and number of the account separately are sent to server, and send the request that adds group; Among the step S6, server is after receiving that adding group asks, the traversal group that T set up in second before the request of receiving, the server only request that the geographical position is approaching carries out the comparison of characteristic sounds file, the characteristic sounds file that is about to receive with compare as the characteristic sounds file of group's password, so can significantly reduce the operand of comparison.
The invention has the advantages that: use this user's correlating method, can allow physically approaching a plurality of users carry out association quickly and easily, form a group, simplify user's operation, and it is interesting to have increased operation based on voice recognition.
Embodiment
Embodiment one
This method realizes based on following system:
1, server and 5 terminals are arranged in the system, connect by network between server and the terminal, server is judged the identity of institute's connecting terminal by user account.
2, in 5 terminals 1 terminal being arranged is group originator, is assumed to be terminal A, and other 4 terminals are group member.
3, terminal A goes up and uses a user account Connection Service device, and other 4 terminals are used 4 user accounts, and these 5 numbers of the account are different mutually.
4,4 terminals are enough approaching physically, and standard is that 4 terminal users separately can hear the sound that other users send clearly.
5,4 terminals all are equipped with sound pick-up outfit.
On basis based on above system, should be as follows based on the idiographic flow that user's correlating method of voice recognition is realized:
Step S1: terminal A enters group and initiates wait state, and other 4 terminals enter group and add wait state, after above 5 terminals enter wait state, all open sound pick-up outfit;
Step S2: the user of any one terminal sends a sound, and this sound can be any sound, and the sound pick-up outfit of all terminals obtains this sound, and saves as the characteristic sounds file;
Step S3: terminal A is sent to server with characteristic sounds file and self number of the account, and sends the request of setting up group;
Step S4: after server is received the request of setting up group, set up a G of group, the password of this group is set at the audio files of receiving;
Step S5: characteristic sounds file that other 4 terminals will obtain separately and number of the account separately are sent to server, and send the request that adds group;
Step S6: server is after receiving that adding group asks, traversal is being received the group that asks foundation in preceding 10 seconds, and the characteristic sounds file received and characteristic sounds file as group's password compared, if comparison result unanimity, then this user account is added group, add group otherwise just refuse this user;
Step S7:, postpone to attempt once more after 10 seconds if, then waiting list is put in this request through not finding the group that can add after the traversal;
Step S8: after above step S6 and S7 repeated 4 times, final group set up, and the user in the group can be according to setting the authority shared resource.
Embodiment two
This method realizes based on following system:
1, server and 10 terminals are arranged in the system, connect by network between server and the terminal, server is judged the identity of institute's connecting terminal by user account.
2, in 10 terminals 1 terminal being arranged is group originator, is assumed to be terminal A, and other 9 terminals are group member.
3, terminal A goes up and uses a user account Connection Service device, and other 9 terminals are used 7 user accounts, and these 7 numbers of the account are different mutually.
4,9 terminals are enough approaching physically, and standard is that 9 terminal users separately can hear the sound that other users send clearly.
5,9 terminals all are equipped with sound pick-up outfit.
On basis based on above system, should be as follows based on the idiographic flow that user's correlating method of voice recognition is realized:
Step S1: terminal A enters group and initiates wait state, and other 9 terminals enter group and add wait state, after above 9 terminals enter wait state, all open sound pick-up outfit;
Step S2: the user of any one terminal sends a sound, and this sound can be any sound, and the sound pick-up outfit of all terminals obtains this sound, and saves as the characteristic sounds file;
Step S3: terminal A is sent to server with characteristic sounds file, the geographical position of self and self number of the account, and sends the request of setting up group;
Step S4: after server is received the request of setting up group, set up a G of group, the password of this group is set at the audio files of receiving;
Step S5: characteristic sounds file, the geographical position of self and number of the account separately that other 9 terminals will obtain separately are sent to server, and send the request that adds group;
Step S6: server is after receiving that adding group asks, traversal is being received the group that asks foundation in preceding 15 seconds, and with the immediate characteristic sounds file in the geographical position of receiving with compare as the characteristic sounds file of group's password, if comparison result unanimity, then this user account is added group, add group otherwise just refuse this user;
Step S7:, postpone to attempt once more after 15 seconds if, then waiting list is put in this request through not finding the group that can add after the traversal;
Step S8: after above step S6 and S7 repeated 9 times, final group set up, and the user in the group can be according to setting the authority shared resource.
The above is only for the preferred embodiment of the invention; not in order to restriction the invention; all in the invention spirit and principle within done any modification, be equal to and replace and improvement etc., all should be included within the protection range of the invention.
Claims (3)
1. user's correlating method based on voice recognition, it is characterized in that: this method realizes based on following system:
(1), server and N terminal are arranged in the system, N connects by network between server and the terminal greater than 1, and server is judged the identity of institute's connecting terminal by user account;
(2), have 1 and to have only 1 terminal be group originator in the N terminal, be made as terminal A, other N-1 terminal is a group member;
(3), terminal A go up to use a user account Connection Service device, other N-1 terminal used M user account, 1≤M≤N-1, this M+1 number of the account is difference mutually;
(4), a N terminal is enough approaching physically, standard is that N terminal user separately can hear the sound that other users send clearly;
(5), N terminal all is equipped with sound pick-up outfit;
On basis based on above system, should be as follows based on the idiographic flow that user's correlating method of voice recognition is realized:
Step S1: terminal A enters group and initiates wait state, and other N-1 terminal enters group and adds wait state, after an above N terminal enters wait state, all opens sound pick-up outfit;
Step S2: the user of any one terminal sends a sound, and this sound can be any sound, and the sound pick-up outfit of all terminals obtains this sound, and saves as the characteristic sounds file;
Step S3: terminal A is sent to server with characteristic sounds file and self number of the account, and sends the request of setting up group;
Step S4: after server is received the request of setting up group, set up a G of group, the password of this group is set at the audio files of receiving;
Step S5: characteristic sounds file that other N-1 terminal will obtain separately and number of the account separately are sent to server, and send the request that adds group;
Step S6: server is after receiving that adding group asks, the traversal group that T set up in second before the request of receiving, and the characteristic sounds file received and characteristic sounds file as group's password compared, if comparison result unanimity, then this user account is added group, add group otherwise just refuse this user;
Step S7:, postpone T and attempt once more after second if, then waiting list is put in this request through not finding the group that can add after the traversal;
Step S8: after above step S6 and S7 repeated N-1 time, final group set up, and the user in the group can be according to setting the authority shared resource.
2. a kind of user's correlating method based on voice recognition as claimed in claim 1 is characterized in that: follow following flow process when each terminal utilizes sound pick-up outfit to obtain characteristic sounds among the above-mentioned steps S2:
At first obtain 500 milliseconds of voice signals sound as a setting;
The analysis background voice signal obtains the maximum V of background sound intensity, gets V*1.3 as threshold value;
The voice signal that supervision is obtained, when intensity of sound surpassed threshold value, opening entry voice signal, and continue record W second was preserved and as characteristic sounds.
3. a kind of user's correlating method as claimed in claim 1 or 2 based on voice recognition, it is characterized in that: in described step S3, terminal A is sent to server with characteristic sounds file, the geographical position of self and self number of the account, and sends the request of setting up group; Among the described step S5, the characteristic sounds file that other N-1 terminal will obtain separately, the geographical position letter of self and number of the account separately are sent to server, and send the request that adds group; Among the step S6, server travels through the group that T set up in second before the request of receiving after receiving that adding group asks, and the server only request that the geographical position is approaching carries out the comparison of characteristic sounds file.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2013101339441A CN103220151A (en) | 2013-04-17 | 2013-04-17 | User correlation method based on voice recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2013101339441A CN103220151A (en) | 2013-04-17 | 2013-04-17 | User correlation method based on voice recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103220151A true CN103220151A (en) | 2013-07-24 |
Family
ID=48817640
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2013101339441A Pending CN103220151A (en) | 2013-04-17 | 2013-04-17 | User correlation method based on voice recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103220151A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103561114A (en) * | 2013-11-18 | 2014-02-05 | 广东利为网络科技有限公司 | Method and device for adding friends through acoustic coding and decoding |
| CN103618713A (en) * | 2013-11-26 | 2014-03-05 | 王玉娇 | User relevance method, system and related equipment |
| WO2015043338A1 (en) * | 2013-09-27 | 2015-04-02 | Tencent Technology (Shenzhen) Company Limited | Identify verifying method, account acquiring method, mobile terminal, and storage medium |
| CN104615359A (en) * | 2015-02-13 | 2015-05-13 | 小米科技有限责任公司 | Method and device for performing voice operation on application software |
| CN104657120A (en) * | 2013-11-20 | 2015-05-27 | 联想(北京)有限公司 | Information processing method and electronic device |
| CN105099874A (en) * | 2015-06-24 | 2015-11-25 | 小米科技有限责任公司 | Method and device for group establishment |
| CN105978940A (en) * | 2016-04-26 | 2016-09-28 | 广东小天才科技有限公司 | Friend adding method and system of intelligent wearable device |
| CN106961374A (en) * | 2016-01-08 | 2017-07-18 | 阿里巴巴集团控股有限公司 | The means of communication, communicating terminal and Communications service end |
| CN108134736A (en) * | 2018-01-19 | 2018-06-08 | 腾讯科技(成都)有限公司 | Colonization method and device |
| WO2019134580A1 (en) * | 2018-01-05 | 2019-07-11 | 上海连尚网络科技有限公司 | Method and device for managing game users |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101453285A (en) * | 2007-11-30 | 2009-06-10 | 深圳华为通信技术有限公司 | System and method for viewing program together |
| CN102379103A (en) * | 2009-01-30 | 2012-03-14 | 惠普开发有限公司 | Methods and systems for establishing collaborative communications between devices using ambient audio |
| CN102456346A (en) * | 2010-10-19 | 2012-05-16 | 盛乐信息技术（上海）有限公司 | Concatenated speech detection system and method |
| WO2012121854A1 (en) * | 2011-03-04 | 2012-09-13 | Qualcomm Incorporated | Method and apparatus for grouping client devices based on context similarity |
-
2013
- 2013-04-17 CN CN2013101339441A patent/CN103220151A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101453285A (en) * | 2007-11-30 | 2009-06-10 | 深圳华为通信技术有限公司 | System and method for viewing program together |
| CN102379103A (en) * | 2009-01-30 | 2012-03-14 | 惠普开发有限公司 | Methods and systems for establishing collaborative communications between devices using ambient audio |
| CN102456346A (en) * | 2010-10-19 | 2012-05-16 | 盛乐信息技术（上海）有限公司 | Concatenated speech detection system and method |
| WO2012121854A1 (en) * | 2011-03-04 | 2012-09-13 | Qualcomm Incorporated | Method and apparatus for grouping client devices based on context similarity |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015043338A1 (en) * | 2013-09-27 | 2015-04-02 | Tencent Technology (Shenzhen) Company Limited | Identify verifying method, account acquiring method, mobile terminal, and storage medium |
| CN104518875A (en) * | 2013-09-27 | 2015-04-15 | 深圳市腾讯计算机系统有限公司 | Identity authentication method, account acquisition method and mobile terminal |
| CN104518875B (en) * | 2013-09-27 | 2018-12-11 | 深圳市腾讯计算机系统有限公司 | A kind of method that authentication and account obtain, mobile terminal |
| US9351165B2 (en) | 2013-09-27 | 2016-05-24 | Tencent Technology (Shenzhen) Company Limited | Identity verifying method, account acquiring method, and mobile terminal |
| CN103561114B (en) * | 2013-11-18 | 2017-06-30 | 广东利为网络科技有限公司 | A kind of method and device for being added good friend of utilization acoustic coding decoding |
| CN103561114A (en) * | 2013-11-18 | 2014-02-05 | 广东利为网络科技有限公司 | Method and device for adding friends through acoustic coding and decoding |
| CN104657120A (en) * | 2013-11-20 | 2015-05-27 | 联想(北京)有限公司 | Information processing method and electronic device |
| CN104657120B (en) * | 2013-11-20 | 2018-06-01 | 联想(北京)有限公司 | A kind of information processing method and electronic equipment |
| CN103618713A (en) * | 2013-11-26 | 2014-03-05 | 王玉娇 | User relevance method, system and related equipment |
| CN104615359A (en) * | 2015-02-13 | 2015-05-13 | 小米科技有限责任公司 | Method and device for performing voice operation on application software |
| CN104615359B (en) * | 2015-02-13 | 2018-05-29 | 小米科技有限责任公司 | The method and device of voice operating is carried out to application software |
| CN105099874A (en) * | 2015-06-24 | 2015-11-25 | 小米科技有限责任公司 | Method and device for group establishment |
| CN105099874B (en) * | 2015-06-24 | 2019-02-12 | 小米科技有限责任公司 | Group's method for building up and device |
| CN106961374A (en) * | 2016-01-08 | 2017-07-18 | 阿里巴巴集团控股有限公司 | The means of communication, communicating terminal and Communications service end |
| CN106961374B (en) * | 2016-01-08 | 2020-08-11 | 阿里巴巴集团控股有限公司 | Communication method, communication terminal and communication server |
| CN105978940A (en) * | 2016-04-26 | 2016-09-28 | 广东小天才科技有限公司 | Friend adding method and system of intelligent wearable device |
| CN105978940B (en) * | 2016-04-26 | 2019-04-16 | 广东小天才科技有限公司 | Friend adding method and system of intelligent wearable device |
| WO2019134580A1 (en) * | 2018-01-05 | 2019-07-11 | 上海连尚网络科技有限公司 | Method and device for managing game users |
| CN108134736A (en) * | 2018-01-19 | 2018-06-08 | 腾讯科技(成都)有限公司 | Colonization method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103220151A (en) | User correlation method based on voice recognition | |
| EP4027343B1 (en) | Proximity based temporary audio sharing | |
| WO2020038095A1 (en) | Evidence collection method and system based on blockchain evidence storage | |
| US9374397B2 (en) | Method and system for searching, sensing, discovering, screening, enabling awareness, alerting, sharing, sending, receiving, buying, selling, and otherwise transmitting stories, content, interests, data, goods and services among known and unknown devices in a communication network | |
| CN109088875A (en) | A kind of access authority method of calibration and device | |
| US9516466B2 (en) | Establishing presence by identifying audio sample and position | |
| CN103346897B (en) | A kind of group's Adding Way and relevant device, system | |
| CN103023900B (en) | Identity identifying method based on cloud server end, cloud service system and Cloud Server | |
| CN109313897A (en) | Utilize the communication of multiple virtual assistant services | |
| CN105426744B (en) | A kind of setting method and device of cryptoguard problem | |
| CN110474902B (en) | Account binding method, system, computing device and medium | |
| CN106656958A (en) | Mobile-terminal-based account login method, login apparatus and login system | |
| KR20160090330A (en) | Controlling voice composition in a conference | |
| CN106161406B (en) | The method and apparatus for obtaining user account | |
| CN108573393A (en) | Comment information processing method, device, server and storage medium | |
| CN104935496B (en) | Instant communicating method, system, device and instant communication terminal | |
| CN107979830A (en) | A kind of Bluetooth connecting method, device, equipment and the storage medium of intelligent back vision mirror | |
| CN106533923A (en) | Information processing method and device based on instant messaging software | |
| CN112822161A (en) | Method and equipment for realizing conference message synchronization | |
| US20170163792A1 (en) | METHOD, ELECTRONIC DEVICE and SYSTEM FOR DATA BACK TRANSMISSION AFTER LOSS OF MOBILE TERMINAL | |
| CN102469039A (en) | Intelligent network communication system and method | |
| CN116846610A (en) | Network security threat detection method, device, equipment and medium | |
| CN111916086B (en) | Voice interaction control method, device, computer equipment and storage medium | |
| CN110719195B (en) | Group cooperation sharing system based on digital service community and working method | |
| US20170171330A1 (en) | Method for pushing information and electronic device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20130724 |
|
| RJ01 | Rejection of invention patent application after publication |