WO2015184733A1 - 一种帧聚合方法及电子设备 - Google Patents
一种帧聚合方法及电子设备 Download PDFInfo
- Publication number
- WO2015184733A1 WO2015184733A1 PCT/CN2014/090728 CN2014090728W WO2015184733A1 WO 2015184733 A1 WO2015184733 A1 WO 2015184733A1 CN 2014090728 W CN2014090728 W CN 2014090728W WO 2015184733 A1 WO2015184733 A1 WO 2015184733A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- operator
- information
- state
- parameter
- electronic device
- Prior art date
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/16—Threshold monitoring
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
- H04L43/0823—Errors, e.g. transmission errors
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L5/00—Arrangements affording multiple use of the transmission path
- H04L5/003—Arrangements for allocating sub-channels of the transmission path
- H04L5/0053—Allocation of signaling, i.e. of overhead other than pilot signals
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/08—Testing, supervising or monitoring using real traffic
Definitions
- the present invention relates to control technologies for electronic devices in the field of mobile communications, and in particular, to a frame aggregation method and an electronic device.
- a method of determining whether to use a frame aggregation technique or frame aggregation to determine a frame length is generally based on the quality of a wireless channel.
- the frame aggregation technology can effectively improve the throughput of the LAN.
- the frame aggregation technology is not used or only the short aggregation frame is used, which can reduce the impact of retransmission on the system throughput. .
- the above discriminating method does not distinguish the characteristics of the device adopting the frame aggregation technology, that is, the device is a handheld wireless terminal and a wireless access device without user participation. In this way, the accuracy and effectiveness of the obtained channel state information cannot be guaranteed, which may affect the accuracy of determining whether to adopt the frame aggregation technique.
- an object of the present invention is to provide a frame aggregation method and an electronic device.
- An embodiment of the present invention provides a frame aggregation method, where the method includes:
- the calculation result is obtained according to the state information of the wireless channel and the state information of the operator, and when the calculation result satisfies the first condition, frame aggregation is performed.
- the status information of the wireless channel includes at least one of the following: a data error rate, a packet loss rate, a number of retransmissions, and a wireless signal strength.
- the method further includes: setting a status parameter corresponding to the operator.
- the state parameter corresponding to the operator includes: a model
- the method for establishing the model includes: collecting sensing parameters in a specified duration, converting the sensing parameters into change information of N states corresponding to an operator, and training the change information of the N states as an input parameter.
- the model is trained by taking the state corresponding to the operator as an output result.
- the satisfying the first condition includes: when the calculation result reaches a preset threshold, the first condition is met.
- An embodiment of the present invention further provides an electronic device, where the electronic device includes:
- An information acquiring module configured to acquire state information of a wireless channel, and acquire state information of the operator according to the preset state parameter
- a decision module configured to calculate, according to status information of the wireless channel and state information of the operator, a calculation result
- the adjustment module is configured to perform frame aggregation when the calculation result satisfies the first condition.
- the status information of the wireless channel includes at least one of the following: a data error rate, a packet loss rate, a number of retransmissions, and a wireless signal strength.
- the information acquiring module is further configured to set a state parameter corresponding to the operator.
- the information acquiring module is further configured to use the pre-stored model as a state parameter corresponding to the operator;
- the method for establishing the model includes: converting the sensing parameter into the change information of the N states corresponding to the operator according to the sensor collecting the sensing parameter in the specified duration, and using the change information of the N state as the input parameter The training is performed, and the state corresponding to the operator is used as an output result to train the model.
- the determining module is further configured to determine that the first condition is met when the calculation result reaches a preset threshold.
- the frame aggregation method and the electronic device provided by the embodiments of the present invention can perform calculation according to the state of the wireless channel and the state of the operator, and determine whether to perform frame aggregation according to the calculation result, so that it is possible to accurately determine whether it is necessary to perform Frame aggregation, which can further ensure the frame transmission quality of electronic devices.
- FIG. 1 is a schematic flowchart 1 of a frame aggregation method provided by the present invention.
- FIG. 2 is a schematic diagram of various sensors provided in an electronic device
- FIG. 3 is a schematic flowchart of a frame aggregation method provided by the present invention.
- FIG. 4 is a schematic structural diagram of a frame structure in a frame aggregation technique
- FIG. 5 is a schematic structural diagram of an electronic device according to the present invention.
- the frame aggregation method provided by the embodiment of the present invention, as shown in FIG. 1 includes:
- Step 101 Acquire status information of a wireless channel.
- Step 102 Obtain state information of the operator according to the preset state parameter.
- Step 103 Calculate the calculation result according to the state information of the wireless channel and the state information of the operator, and perform frame aggregation when the calculation result satisfies the first condition.
- the sequence of the foregoing step 101 and the step 102 may be performed at the same time, or the step 101 may be performed first, and the step 101 is not performed.
- the status information of the wireless channel includes at least one of the following: a data error rate, a packet loss rate, a number of retransmissions, and a wireless signal strength.
- the threshold when the value is greater than the preset, it indicates that its channel state is poor; otherwise, it indicates that its channel state is good.
- wireless signal strength when its value is greater than a preset threshold, it indicates that its channel state is good; conversely, it indicates that its channel state is poor.
- the acquisition of the state of the wireless channel may be: for closed-loop transmission, the transmitting end may acquire wireless channel state information even if there is a delay, an error, or the like.
- the sender cannot obtain information such as data error rate, packet loss rate, and wireless signal strength through feedback from the receiver.
- the heuristic algorithm can be used to infer the channel state by information such as the number of retransmissions. When the channel cannot obtain any channel status information, the default channel status is "poor".
- the state information of the operator may be the mood state of the operator, or may be the operating environment state of the operator, etc.; the same identifier may also be used for characterization, for example, when the state is divided into two levels, that is, when the difference is good, It can be characterized by "1", and the difference is represented by "0"; or when the state is divided into three grades, that is, good, medium, and poor, it can be characterized by "11", and "01” is characterized by "00". Poor representation.
- the method may further include: setting a state parameter corresponding to the operator.
- the state parameter corresponding to the operator may include: a model; the training method of the model may include: converting the sensing parameter into a change of the N states corresponding to the operator according to the sensor collecting the sensing parameter in the specified duration Information, training the change information of the N states as an input parameter, and using the state corresponding to the operator as an output result, training the model;
- the senor may include a compass, a camera, a gyroscope and a light sensor, a Global Positioning System (GPS), and a pressure sensing device as shown in FIG. 2 . , temperature sensor, acceleration sensor, etc.
- GPS Global Positioning System
- the change information of the N states may be: change information of the emoticon such as facial expression emotion recognition; change information of the sound, such as speech emotion recognition, semantic emotion recognition, central nervous signal emotion recognition, autonomic signal signal emotion recognition, etc. ;, position change information, action change information, temperature change information, etc.
- the change information of the emoji can be obtained by collecting the emoji input by the user when using various chat softwares; the acquired sound can be collected through the microphone, and then analyzing the change information such as the strength and frequency of the sound sent by the user; acquiring the position or action
- the data may be passed through a gyroscope, or a GPS, or an acceleration sensor, etc.; the temperature of the operator may be obtained by a temperature sensor, and then the temperature change information may be analyzed.
- the methods for obtaining corresponding information by using various sensors are all prior art, and are not described herein.
- training the change information of the N states as an input parameter may be selecting only one state change information, for example, a typical parameter may be used to obtain a certain emotion using a single parameter, such as using facial expression parameters to determine emotions, When this parameter is not applicable, the multi-parameter method can be combined to judge the user's emotions.
- the operator's mood state is described, and after collecting the mood related information of the user for a period of time by the sensor, it can be quantized into numerical information that can be processed by the program (such as 0, 1, or in a certain range of values). Within the discrete values), using this information as a sample, a classification model (ie, a user mood state model) is generated using a two-class classification method in machine learning (such as the Bayesian classification method). Through the model, mood state recognition and recognition can be performed on newly collected user mood information.
- a classification model ie, a user mood state model
- machine learning such as the Bayesian classification method
- the voice, expression, and different characteristics may be expressed when the user changes in different emotions, and the machine learning may be through machine learning training by extracting user feature data in a certain state. Identify a certain percentage of user-character emotions. Such as a user's emotions, such as anger, the tone of the spectrum has its characteristics, expressions It has its characteristics, and its feature is used as a feature quantity input classifier to achieve a certain degree of emotion recognition.
- the classifier is a machine learning program, which is essentially a mathematical model. According to the different models, there are many branches, including: Bayes classifier, BP neural network classifier, decision tree algorithm, SVM (support vector machine) algorithm, etc.
- the calculation formula can be:
- X1, X2...Xn respectively represent physiological characteristics of different users, and may represent multiple emotional feature parameters, including but not limited to parameters herein, and may also include other parameters, using different emotional feature parameters, and applying comprehensive judgment to obtain the final emotional information of the user. .
- the satisfying the first condition includes: when the calculation result reaches a preset threshold, satisfying the first condition;
- Ag_condition channel_stat ⁇ usr_mode; where the parameter ag_condition indicates an aggregation condition, which takes values of "1" and "0".
- Step 301 The wireless mobile terminal collects state information of the wireless channel.
- Step 302 The wireless mobile terminal collects various status information of the operator by using the sensor, and after the collected information is processed, uses the status parameter to calculate the status information of the operator.
- Step 303 Calculate a frame aggregation condition according to the state information of the wireless channel and the state information of the operator.
- Step 304 Determine whether the first condition is met. If the calculated result is "1", it indicates that the first condition is met, and frame aggregation is performed; otherwise, no operation is performed.
- the frame aggregation includes: A-MSDU and A-MPDU.
- the A-MSDU technology is on the top of the MAC layer, which aggregates multiple MSDUs into one MPDU.
- the A-MPDU technology aggregates multiple MPDUs into one PSDU at the bottom of the MAC layer, and the MPDUs therein may include aggregated A-MSDUs.
- the electronic device provided by the embodiment of the present invention, as shown in FIG. 5, includes:
- the information acquiring module 51 is configured to acquire state information of the wireless channel, and acquire state information of the operator according to the preset state parameter;
- the determining module 52 is configured to calculate, according to the state information of the wireless channel and the state information of the operator, a calculation result
- the adjusting module 53 is configured to perform frame aggregation when the calculation result satisfies the first condition.
- the status information of the wireless channel includes at least one of the following: a data error rate, a packet loss rate, a number of retransmissions, and a wireless signal strength.
- the information acquiring module 51 can be used for closed loop transmission, and the transmitting end can acquire wireless channel state information even if there is a delay, an error, or the like.
- the sender cannot obtain information such as data error rate, packet loss rate, and wireless signal strength through feedback from the receiver.
- the heuristic algorithm can be used to infer the channel state by information such as the number of retransmissions. When the channel cannot obtain any channel status information, the default channel status is "poor".
- the state information of the operator may be the mood state of the operator, or may be the operating environment state of the operator, etc.; the same identifier may also be used for characterization, for example, when the state is divided into two levels, that is, when the difference is good, It can be characterized by "1", and the difference is represented by "0"; or when the state is divided into three grades, that is, good, medium, and poor, it can be characterized by "11", and "01” is characterized by "00". Poor representation.
- the information obtaining module 51 can be configured to set a state parameter corresponding to the operator.
- the state parameter corresponding to the operator may include: a model; the training method of the model may include: converting the sensing parameter into a change of the N states corresponding to the operator according to the sensor collecting the sensing parameter in the specified duration Information, training the change information of the N states as an input parameter, and using the state corresponding to the operator as an output result, training the model;
- the change information of the N states may be: change information of an emoticon, information of a sound, change information of a position, motion change information, and the like.
- the change information of the emoji can be obtained by collecting the emoji input by the user when using various chat softwares; the acquired sound can be collected through the microphone, and then analyzing the strength, speed, and the like of the sound sent by the user; acquiring the position or the action, etc. Can be passed through the gyroscope.
- a single parameter can be used to obtain a certain emotion, such as using facial expression parameters to judge emotions. When this parameter is not applicable, the multi-parameter method can be combined to determine the user's emotion.
- the sensor After the sensor collects the mood related information of the user for a period of time, it is quantized into numerical information that can be processed by the program (such as 0, 1, or discrete values within a certain range of values), and the information is taken as a sample.
- a two-class classification method in machine learning (such as the Bayesian classification method) generates a classification model (ie, a user mood state model). Through the model, The mood state recognition and recognition can be performed on the newly collected user mood information.
- the operator's state information is to represent the operator's emotions
- different characteristics can be expressed when the user's different emotions change, the voice and the expression, and the machine learning is performed by extracting the user characteristic data in a certain state and learning through the machine learning.
- the classifier is a machine learning program, which is essentially a mathematical model. According to the different models, there are many branches, including: Bayes classifier, BP neural network classifier, decision tree algorithm, SVM (support vector machine) algorithm, etc.
- the calculation formula can be:
- X1, X2...Xn respectively represent physiological characteristics of different users, and may represent multiple emotional feature parameters, including but not limited to parameters herein, and may also include other parameters, using different emotional feature parameters, and applying comprehensive judgment to obtain the final emotional information of the user. .
- the satisfying the first condition includes: when the calculation result reaches a preset threshold, satisfying the first condition;
- Ag_condition channel_stat ⁇ usr_mode; where the parameter ag_condition indicates an aggregation condition, which takes values of "1" and "0".
- embodiments of the present invention can be provided as a method, system, or computer program product. Accordingly, the present invention can take the form of a hardware embodiment, a software embodiment, or a combination of software and hardware. Moreover, the present invention may employ computer-usable storage media (including but not limited to disks) in one or more of the computer-usable program code embodied therein. A form of computer program product embodied on a memory and optical storage, etc.).
- the computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture comprising the instruction device.
- the apparatus implements the functions specified in one or more blocks of a flow or a flow and/or block diagram of the flowchart.
- These computer program instructions can also be loaded onto a computer or other programmable data processing device such that a series of operational steps are performed on a computer or other programmable device to produce computer-implemented processing for execution on a computer or other programmable device.
- the instructions provide steps for implementing the functions specified in one or more of the flow or in a block or blocks of a flow diagram.
- the present invention discloses a frame aggregation method and an electronic device, which acquires state information of a wireless channel, acquires state information of the operator according to a preset state parameter, and obtains state information of the wireless channel and state information of the operator according to the state information of the wireless channel. , frame aggregation. In this way, it is possible to accurately determine whether or not frame aggregation is required, thereby further securing the frame of the electronic device. Transmission quality.
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Environmental & Geological Engineering (AREA)
- Mobile Radio Communication Systems (AREA)
- Quality & Reliability (AREA)
Abstract
Description
Claims (10)
- 一种帧聚合方法,所述方法包括:获取无线信道的状态信息;根据预设的状态参数,获取操作者的状态信息;根据所述无线信道的状态信息以及所述操作者的状态信息进行计算得到计算结果,当计算结果满足第一条件时,进行帧聚合。
- 根据权利要求1所述的方法,其中,所述无线信道的状态信息包括以下至少一种:数据错误率、丢包率、重传次数、无线信号强度。
- 根据权利要求1或2所述的方法,其中,所述方法还包括:设置操作者对应的状态参数。
- 根据权利要求3所述的方法,其中,所述操作者对应的状态参数包括:模型;所述模型的建立方法包括:收集指定时长中的传感参数,将所述传感参数转换为操作者对应的N种状态的变化信息,将所述N种状态的变化信息作为输入参数进行训练,将操作者对应的状态作为输出结果,对模型进行训练。
- 根据权利要求3所述的方法,其中,所述满足第一条件包括:当所述计算结果达到预设的阈值时,满足第一条件。
- 一种电子设备,所述电子设备包括:信息获取模块,配置为获取无线信道的状态信息;根据预设的状态参数,获取操作者的状态信息;决策模块,配置为根据所述无线信道的状态信息以及所述操作者的状态信息进行计算得到计算结果;调整模块,配置为当计算结果满足第一条件时,进行帧聚合。
- 根据权利要求6所述的电子设备,其中,所述无线信道的状态信 息包括以下至少一种:数据错误率、丢包率、重传次数、无线信号强度。
- 根据权利要求7所述的电子设备,其中,所述信息获取模块,配置为设置操作者对应的状态参数。
- 根据权利要求8所述的电子设备,其中,所述信息获取模块,配置为将预存的模型作为所述操作者对应的状态参数;所述模型的建立方法包括:根据传感器收集指定时长中的传感参数,将所述传感参数转换为操作者对应的N种状态的变化信息,将所述N种状态的变化信息作为输入参数进行训练,将操作者对应的状态作为输出结果,对模型进行训练。
- 根据权利要求9所述的电子设备,其中,所述决策模块,配置为当所述计算结果达到预设的阈值时,确定满足第一条件。
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020167033862A KR101962393B1 (ko) | 2014-06-03 | 2014-11-10 | 프레임 집적 방법 및 전자 설비 |
US15/315,722 US10178013B2 (en) | 2014-06-03 | 2014-11-10 | Frame aggregation method and electronic device |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410243093.0A CN105141401B (zh) | 2014-06-03 | 2014-06-03 | 一种帧聚合方法及电子设备 |
CN201410243093.0 | 2014-06-03 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2015184733A1 true WO2015184733A1 (zh) | 2015-12-10 |
Family
ID=54726624
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2014/090728 WO2015184733A1 (zh) | 2014-06-03 | 2014-11-10 | 一种帧聚合方法及电子设备 |
Country Status (4)
Country | Link |
---|---|
US (1) | US10178013B2 (zh) |
KR (1) | KR101962393B1 (zh) |
CN (1) | CN105141401B (zh) |
WO (1) | WO2015184733A1 (zh) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101662546A (zh) * | 2009-09-16 | 2010-03-03 | 中兴通讯股份有限公司 | 情绪监控的方法及装置 |
CN102355324A (zh) * | 2011-08-10 | 2012-02-15 | 中国联合网络通信集团有限公司 | 帧聚合控制方法、装置和系统 |
CN102668490A (zh) * | 2009-09-04 | 2012-09-12 | 索尼公司 | 无线通信装置和无线通信方法 |
CN103348730A (zh) * | 2011-02-10 | 2013-10-09 | 英派尔科技开发有限公司 | 语音服务的体验质量测量 |
Family Cites Families (24)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050095569A1 (en) * | 2003-10-29 | 2005-05-05 | Patricia Franklin | Integrated multi-tiered simulation, mentoring and collaboration E-learning platform and its software |
US7983203B2 (en) * | 2004-07-22 | 2011-07-19 | Nokia Corporation | System and method for improved power efficiency in a shared resource network |
JP4440037B2 (ja) * | 2004-08-11 | 2010-03-24 | 株式会社東芝 | 通信装置及び通信方法 |
US8204005B2 (en) * | 2006-03-09 | 2012-06-19 | Intel Corporation | Wireless communication device and method for dynamic bidirectional aggregation of MAC frames with delayed channel access in a wireless network |
JP4127710B2 (ja) * | 2006-05-30 | 2008-07-30 | 株式会社東芝 | 無線通信装置及び送信制御方法 |
KR100878755B1 (ko) * | 2007-02-08 | 2009-01-14 | 한국과학기술원 | 무선인지 기반 이동통신시스템 및 이동통신 무선접속 방법 |
GB2449252B (en) * | 2007-05-14 | 2012-05-16 | Toshiba Res Europ Ltd | Multichannel MAC in wireless networks |
US8280885B2 (en) * | 2007-10-29 | 2012-10-02 | Cornell University | System and method for automatically summarizing fine-grained opinions in digital text |
US8559306B2 (en) * | 2008-02-13 | 2013-10-15 | Cisco Technology, Inc. | End-to-end packet aggregation in mesh networks |
CN101662417B (zh) * | 2008-08-26 | 2011-12-21 | 华为技术有限公司 | 多业务适配和承载的方法及设备 |
WO2010137777A1 (en) * | 2009-05-28 | 2010-12-02 | Lg Electronics Inc. | Apparatus and method for determination of frame structure for reducing interference in frequency reuse system using cognitive radio |
US8509193B2 (en) * | 2009-07-21 | 2013-08-13 | Microsoft Corporation | Packet aggregation |
US8447875B2 (en) * | 2010-03-10 | 2013-05-21 | Thomson Licensing | Unified cache and peer-to-peer method and apparatus for streaming media in wireless mesh networks |
JP2012070090A (ja) * | 2010-09-21 | 2012-04-05 | Toshiba Corp | 無線通信装置 |
KR20140001930A (ko) | 2010-11-17 | 2014-01-07 | 어펙티바,아이엔씨. | 소셜 네트워크를 통한 정서의 공유 |
US8665843B2 (en) * | 2010-12-23 | 2014-03-04 | Intel Corporation | Single MPDU frame signaling |
US9007362B2 (en) * | 2011-01-14 | 2015-04-14 | Brian Mark Shuster | Adaptable generation of virtual environment frames |
US9276832B2 (en) * | 2011-03-20 | 2016-03-01 | King Abdullah University Of Science And Technology | Buffer sizing for multi-hop networks |
US20140146736A1 (en) * | 2012-11-28 | 2014-05-29 | Electronics And Telecommunications Research Institute | Method of grouping stations in multi-transmission |
US9736859B2 (en) * | 2012-11-28 | 2017-08-15 | Samsung Electronics Co., Ltd. | Method and apparatus for providing voice service in wireless local area network |
US9823330B2 (en) * | 2013-05-03 | 2017-11-21 | Cisco Technology, Inc. | Angle of arrival location sensing with antenna array |
US9378576B2 (en) * | 2013-06-07 | 2016-06-28 | Faceshift Ag | Online modeling for real-time facial animation |
US20170324518A1 (en) * | 2014-12-12 | 2017-11-09 | Intel Corporation | An adaptive block ack mechanism for a-mdpu |
US10575310B2 (en) * | 2016-03-22 | 2020-02-25 | Netgear, Inc. | Wireless communication in an environment with electronic interference |
-
2014
- 2014-06-03 CN CN201410243093.0A patent/CN105141401B/zh not_active Expired - Fee Related
- 2014-11-10 WO PCT/CN2014/090728 patent/WO2015184733A1/zh active Application Filing
- 2014-11-10 KR KR1020167033862A patent/KR101962393B1/ko active IP Right Grant
- 2014-11-10 US US15/315,722 patent/US10178013B2/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102668490A (zh) * | 2009-09-04 | 2012-09-12 | 索尼公司 | 无线通信装置和无线通信方法 |
CN101662546A (zh) * | 2009-09-16 | 2010-03-03 | 中兴通讯股份有限公司 | 情绪监控的方法及装置 |
CN103348730A (zh) * | 2011-02-10 | 2013-10-09 | 英派尔科技开发有限公司 | 语音服务的体验质量测量 |
CN102355324A (zh) * | 2011-08-10 | 2012-02-15 | 中国联合网络通信集团有限公司 | 帧聚合控制方法、装置和系统 |
Also Published As
Publication number | Publication date |
---|---|
KR101962393B1 (ko) | 2019-03-26 |
CN105141401A (zh) | 2015-12-09 |
KR20170010780A (ko) | 2017-02-01 |
CN105141401B (zh) | 2019-04-12 |
US20170093680A1 (en) | 2017-03-30 |
US10178013B2 (en) | 2019-01-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11408629B2 (en) | Artificial intelligence device | |
US10552738B2 (en) | Adaptive channel coding using machine-learned models | |
CN106796753B (zh) | 用于物联网领域的多传感器变化检测 | |
CN109412900B (zh) | 一种网络状态识别的方法、模型训练的方法及装置 | |
CN107004409A (zh) | 利用运行范围归一化的神经网络语音活动检测 | |
US11411850B2 (en) | Traffic analysis apparatus, method, and program | |
US10586543B2 (en) | Sound capturing and identifying devices | |
KR101753509B1 (ko) | 소셜 그래프들, 스피치 모델들, 및 사용자 콘텍스트를 통해 모바일 디바이스 사용자에 근접한 사람들을 식별하는 것 | |
US20180213339A1 (en) | Adapting hearing aids to different environments | |
US20160149547A1 (en) | Automated audio adjustment | |
CN111667818B (zh) | 一种训练唤醒模型的方法及装置 | |
CN104538041A (zh) | 异常声音检测方法及系统 | |
WO2019240845A1 (en) | Sound-based call-quality detector | |
US20190131948A1 (en) | Audio loudness control method and system based on signal analysis and deep learning | |
CN113422751A (zh) | 基于在线强化学习的流媒体处理方法、装置及电子设备 | |
CN107529209A (zh) | 控制wifi热点省电的方法及其装置 | |
WO2015184733A1 (zh) | 一种帧聚合方法及电子设备 | |
CN109451522A (zh) | 一种面向蓝牙网关的流量预测方法及装置 | |
CN115104099A (zh) | 用于服务器与用户设备之间的交互式和隐私保护通信的方法和装置 | |
CN112884142B (zh) | 神经网络训练、目标检测方法、装置、设备、存储介质 | |
US20170309154A1 (en) | Speech therapeutic devices and methods | |
CN108826595A (zh) | 一种空气净化器的控制方法及系统 | |
US9391459B2 (en) | Mesh delivery system | |
Bardalai et al. | Throughput prediction in smart healthcare network using machine learning approaches | |
US11445286B1 (en) | Wireless connection management |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 14893858 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 15315722 Country of ref document: US |
|
ENP | Entry into the national phase |
Ref document number: 20167033862 Country of ref document: KR Kind code of ref document: A |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 14893858 Country of ref document: EP Kind code of ref document: A1 |