WO2022135089A1 - Wifi channel allocation method and device - Google Patents
Wifi channel allocation method and device Download PDFInfo
- Publication number
- WO2022135089A1 WO2022135089A1 PCT/CN2021/134858 CN2021134858W WO2022135089A1 WO 2022135089 A1 WO2022135089 A1 WO 2022135089A1 CN 2021134858 W CN2021134858 W CN 2021134858W WO 2022135089 A1 WO2022135089 A1 WO 2022135089A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- data transmission
- electronic terminal
- priority
- internet access
- time period
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 230000005540 biological transmission Effects 0.000 claims description 137
- 230000008569 process Effects 0.000 claims description 12
- 230000006870 function Effects 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 10
- 238000004422 calculation algorithm Methods 0.000 claims description 5
- 230000003321 amplification Effects 0.000 claims description 2
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 2
- 230000009467 reduction Effects 0.000 claims description 2
- 238000010187 selection method Methods 0.000 claims 1
- 238000004364 calculation method Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W72/00—Local resource management
- H04W72/50—Allocation or scheduling criteria for wireless resources
- H04W72/56—Allocation or scheduling criteria for wireless resources based on priority criteria
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W72/00—Local resource management
- H04W72/04—Wireless resource allocation
- H04W72/044—Wireless resource allocation based on the type of the allocated resource
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W72/00—Local resource management
- H04W72/50—Allocation or scheduling criteria for wireless resources
- H04W72/53—Allocation or scheduling criteria for wireless resources based on regulatory allocation policies
Definitions
- the present disclosure generally relates to the field of WIFI technology, and more particularly, to a WIFI channel allocation method and device.
- a home-based local area network there may be multiple electronic terminals connected to the wireless network at the same time. If there are too many electronic terminals or the data transmission volume of the electronic terminals is too large, even if a routing system that supports WIFI6 is used, there may be problems due to the channel Distribution problems occur when poor signal occurs.
- the present disclosure relates to a WIFI channel allocation method, which includes:
- a corresponding WIFI sub-channel is allocated to the electronic terminal.
- the present disclosure relates to a WIFI channel allocation device, comprising:
- a time period determination module configured to determine a priori Internet access time period corresponding to the Internet access request when receiving an Internet access request from any electronic terminal;
- a first priority determining module configured to determine a first priority of the electronic terminal corresponding to the a priori Internet access time period of the electronic terminal according to the prior Internet access time period of the electronic terminal;
- a second priority determining module configured to determine a second priority corresponding to the electronic terminal according to the category to which the electronic terminal belongs;
- a total priority determination module which determines the total priority of the electronic terminal according to the first priority and the second priority of the electronic terminal
- the sub-channel allocation module is configured to allocate a corresponding WIFI sub-channel to the electronic terminal according to the total priority.
- the present disclosure relates to a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, when the processor executes the computer program, the WIFI channel allocation method of the present disclosure is implemented .
- the present disclosure relates to a computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor to execute the WIFI channel allocation method of the present disclosure.
- the WIFI channel allocation method of the present disclosure determines the total priority according to the first priority corresponding to the electronic terminal in the corresponding prior Internet access time period and the second priority corresponding to the category to which it belongs, and then according to the total priority
- the stage allocates sub-channels for electronic terminals. Since the first priority reflects the usage rule of the electronic terminal in the corresponding prior Internet access time period, it is a dynamic factor, while the second priority reflects the characteristics of the electronic terminal itself, which is a fixed factor. It can be seen that the total priority can be determined from Overall, it reflects the priority of the electronic terminal in the corresponding prior Internet access time period, which makes the classification of sub-channels more reasonable and optimized, thereby improving the communication speed of the electronic terminal and improving the problem of poor wireless signals.
- FIG. 1 is a schematic flowchart of a WIFI channel allocation method according to an embodiment of the present disclosure.
- FIG. 2 is a structural block diagram of a WIFI channel allocation apparatus provided by an embodiment of the present disclosure.
- FIG. 1 is a WIFI channel allocation method provided by the present disclosure. As shown in FIG. 1 , the method includes the following steps:
- S140 determine the total priority of the electronic terminal according to the first priority and the second priority of the electronic terminal.
- S150 Allocate a corresponding WIFI sub-channel to the electronic terminal according to the total priority.
- electronic terminals include, but are not limited to, mobile phones, tablet computers, notebook computers, desktop computers, smart refrigerators, smart TVs, smart humidifiers, smart cleaning robots, and other household devices that can be connected to a wireless network.
- information such as the identity identifier of the electronic terminal can be obtained in the Internet access request, and which electronic terminal needs to access the Internet can be known according to the identity identifier.
- the a priori surfing time period is the time period to which the time point when the surfing request is received belongs. In a day, you can set multiple prior Internet access time periods, for example, 6:00-8:00, 8:00-11:00 in the morning, 11:00-13:00, 13:00-16:30 in the noon, 16:30-19:00, 19:00-22:00, etc. in the evening.
- the prior Internet access time period may be manually set in advance, or may be obtained by clustering with a clustering algorithm in a subsequent step. If the moment when the Internet access request is received is within a certain a priori Internet access time period, the Internet access request corresponds to the a priori Internet access time period.
- different electronic terminals have different priorities at different time periods. For example, in the time periods of 6:00-8:00 in the morning, 11:00-13:00 in the noon, and 16:30-19:00 in the evening, the priority of the electronic terminal in the kitchen will be higher. The priority of electronic terminals mainly configured for work on notebooks and desktop computers will be higher. From 19:00 to 22:00 in the evening, the priority of electronic terminals mainly configured for entertainment, such as televisions and mobile phones, will be higher.
- multiple first priorities may be set, and one first priority may be set for each type of electronic terminal in each prior Internet access time period. From 19:00 to 22:00 in the evening, the first priority of the TV is the highest, followed by the mobile phone, and the first priority of the other electronic terminals is lower than the first priority of the TV and the mobile phone. It can be seen that the first priority is determined according to the frequency of use of the electronic terminal in different time periods. The higher the frequency of use of the electronic terminal in a certain time period, the higher the first priority. Use the rule to set the first priority in each prior Internet access time period. If the usage rule of the electronic terminal changes within a certain prior Internet access time period, the corresponding first priority will also change. It can be seen that the first priority may be dynamically changed.
- the belonging category can be categorized from multiple dimensions, eg, portability, functionality, and the like.
- the notebook is a portable device, and the notebook can be used to handle related work, so the second priority of the notebook can be set to the highest, followed by mobile phones, TVs, refrigerators, etc. from high to low.
- the second priority is According to the determination of the electronic terminal itself, if the classification standard is uniform and unchanged, the second priority of the electronic terminal is fixed.
- both the usage rule of the electronic terminal in the corresponding prior Internet access time period and the characteristics of the electronic terminal itself are considered, that is, dynamic factors are taken into account, and the Considering the fixed factor, the priority status of the electronic terminal in the corresponding prior Internet access time period can be generally reflected according to the total priority.
- the higher the total priority of an electronic terminal in an a priori surfing time period the more preferentially the sub-channel may be allocated for the electronic terminal in the a priori surfing time period.
- the total priority can be calculated in various ways, for example, the total priority can be calculated using the following first formula, where the first formula includes:
- G is the total priority
- ⁇ are balance parameters
- g 1 is the first priority
- g 2 is the second priority
- the balance parameter is the parameter that balances the two priorities, for example, The inverse of the number of the first priority may be taken, and ⁇ may be the inverse of the number of the second priority.
- the total number of first priorities is 3 and the total number of second priorities is 4, then is 1/3, ⁇ is 1/4, if the first priority obtained through the above steps is 3 (the lowest first priority) and the second priority is 2, then G is 4 at this time, and it can be seen that the total The priority is also lower. If the first priority is 1 (the highest first priority) and the second priority is 1 (the highest second priority), then G is 1, and the total priority is the highest at this time.
- the overall priority is set to three levels, and the WIFI channels can be divided into six.
- the priority of the TV is the highest, followed by the mobile phone, and the total priority of the other electronic terminals is the lowest.
- the 1st to 3rd subchannels can be allocated to the television, the 4th to 5th subchannels can be allocated to the mobile phone, and the 6th subchannel can be allocated to other electronic terminals.
- the methods provided by the embodiments of the present disclosure may further include:
- S160 Determine, according to the pre-trained prediction model, the total amount of predicted data transmission of the electronic terminal within the prior Internet access time period.
- step S150 may include:
- S152 Allocate a corresponding WIFI sub-channel to the electronic terminal according to the total priority and the predicted data transmission component.
- the total amount of predicted data transmission is the sum of the predicted data transmission amount of the electronic terminal in a prior Internet access time period.
- step S160 may be performed at any time after step S110 and before step S150.
- the prediction model is obtained by training data in a preset historical period, the preset historical period includes a first historical sub-period and a second historical sub-period, and the first historical sub-period is earlier than the second historical sub-period Period, for example, the first historical sub-period is the day before yesterday, and the second historical sub-period is yesterday.
- the data of the day before yesterday is used to predict the data of yesterday, and the model is adjusted according to the prediction result of yesterday and the real data of yesterday to obtain a prediction model, and then Yesterday's real data can be fed into this forecasting model, and today's forecast can be output.
- the a priori Internet access time period is from 19:00 to 22:00 in the evening, and 22:00 is the end time of the a priori Internet access time period.
- the predicted data transmission component is the data transmission amount of the TV between 8:00 and 22:00. For example, if the total amount of predicted data transmission of TV from 19:00 to 22:00 obtained by the prediction model is M, the predicted data transmission component of TV from 8:00 to 22:00 is 2M/3.
- the predicted data transmission component is a predicted value of the data transmission amount for a future time period (the time when the Internet access request is received to the end time of the a priori Internet time period to which it belongs).
- the predicted data transmission component when assigning sub-channels, not only the total priority but also the predicted data transmission component is considered, wherein the total priority reflects the historical usage pattern and its own characteristics of the electronic terminal, and the predicted data transmission component reflects It is the predicted value of the data transmission amount in the future time period, which makes the allocation of sub-channels more reasonable.
- step S152 may include the following steps:
- S152b Adjust the initial sub-channel according to the predicted data transmission component to obtain a target sub-channel, and if the predicted data transmission component is greater than the transmission amount threshold component, perform adjacent amplification on the initial sub-channel to obtain the target sub-channel, otherwise, perform proximity reduction on the initial sub-channel to obtain the target sub-channel;
- the ratio of the transmission volume threshold component to the transmission volume threshold is equal to the ratio of the predicted data transmission component to the total predicted data transmission, and the transmission volume threshold component is the component of the transmission volume threshold.
- the total priority G is 1, and the subchannels corresponding to this total priority are the 1st to 4th subchannels, that is, the initial subchannels are the 1st to 4th subchannels; the total priority G is 4, Then the subchannel corresponding to this total priority is the tenth subchannel, and the initial subchannel is the tenth subchannel.
- the ratio of the traffic threshold component to the traffic threshold is equal to the ratio of the predicted data traffic component to the total predicted data traffic, the traffic threshold component being the component of the traffic threshold, It is calculated similarly to the predicted data transfer component.
- the transmission volume threshold corresponding to the prior Internet access time period from 19:00 to 22:00 is set as k, and the transmission volume threshold component between 8:00 and 22:00 is 2k/3.
- the total priority G when G is 1, if the corresponding predicted data transmission component is less than the transmission volume threshold component, the 1st to 3rd subchannels are used as the target subchannels, that is, the 4th subchannel. Let it be used by other electronic terminals or be vacant.
- G if the corresponding predicted data transmission component is greater than the transmission amount threshold component, the 9th and 10th subchannels are used as target subchannels, that is, the 9th subchannel is added. If the ninth sub-channel is simultaneously used by another electronic terminal, the ninth channel is multiplexed for the two electronic terminals.
- the pre-training process of the predictive model may include:
- the historical period is preset, the past week. Each day can be divided into 12 Internet time periods. During each Internet access time period, each electronic terminal can perform multiple data transmissions with the routing device, so multiple pieces of data transmission information will be generated, and each piece of data transmission information will include the transmitted content and content-related information. (For example, the data transmission amount corresponding to the piece of data transmission information), etc.
- a K-means clustering algorithm is used to cluster 12 time periods online to obtain 6 a priori time periods for Internet access.
- this step is a process of constructing a training sample set: marking the corresponding data transmission amount for each piece of data transmission information, and using the data transmission information marked with the data transmission amount as a training sample.
- the process of performing model training according to the machine learning algorithm and the training sample set is a process of setting and adjusting various parameters in the model. After each parameter is adjusted, a loss function is calculated, and the model is again adjusted according to the loss value. The parameters are adjusted until the loss value calculated according to the loss function is within a certain error range.
- a second formula is used to calculate the loss of the training samples, and the second formula includes:
- L is the total loss of the prediction model corresponding to each prior online time period of each electronic module
- ⁇ and ⁇ are preset balance parameters
- N cls is the positive sample in all training samples required to train the prediction model.
- the number of , L cls ( ) is the first loss function
- y 1i is the pre-labeled data transfer amount for the ith positive sample
- N reg is the number of negative samples in all training samples required to train the prediction model
- L reg ( ) is the second loss function
- y 2i is the pre-labeled data transmission amount of the ith negative sample
- y * is the ratio of the total amount of predicted data transmission output by the prediction model to the number of all training samples.
- the first loss function and the second loss function are different functions. Since positive and negative samples have different effects on training, different loss functions are used.
- ⁇ and ⁇ are preset balance parameters, the sum of ⁇ and ⁇ is 1, and the values can be set as required.
- the second formula includes two parts: the loss value of positive samples and the loss value of negative samples. Therefore, when using the second formula for loss calculation, it is necessary to classify the positive and negative samples in the training sample set.
- the classification process of negative samples can include:
- S042 select a first data transmission amount R1, a second data transmission amount R2, and a third data transmission amount R3 from the transmission amount sequence, where the first data transmission amount is a 1/4 position in the transmission amount sequence
- the second data transmission amount is the data transmission amount at the 1/2 position in the transmission amount sequence
- the third data transmission amount is the data at the 3/4 position in the transmission amount sequence.
- the smart TV has 500 training samples in the prior Internet access time period from 19:00 to 22:00, and the data transmission amount marked by each of the 500 training samples is large or small. At this time According to the order of data transmission volume from small to large, a data transmission volume sequence corresponding to the prior Internet access time period of the smart TV from 19:00 to 22:00 is obtained.
- the positive sample interval set in this way is fixed, and the calculation method is simple and convenient, However, it cannot be changed according to the situation of the transmission amount sequence.
- the following third formula can also be used to calculate the positive sample interval H, and the third formula includes:
- E() is the mean function
- R1 is the first data transmission amount
- R2 is the second data transmission amount
- R3 is the third data transmission amount
- Adjust the parameter for the interval width less than or equal to 1.
- the positive sample interval can be adjusted, The larger the interval, the wider the interval. The smaller the interval, the narrower the interval.
- the size can be set according to experience, of course, it can also be determined by the following methods:
- Set interval width adjustment parameters Gradually increase from 0, when At least 90% of the data transmission volume added to the transmission volume sequence falls within the preset interval inside, stop increasing, set the It is selected and used to calculate the third formula, where ⁇ is the standard deviation of the transmission quantity sequence.
- the 125th data transmission volume is selected as the first data transmission volume R1
- the 250th data transmission volume is selected as the first data transmission volume R1.
- the second data transmission amount R2 select the 375th data transmission amount as the second data transmission amount R3, R1 is 100
- R2 is 135, R3 is 150
- the positive sample interval calculated according to the third formula is [55, 195], so as long as the data transmission amount of the training sample is greater than or equal to 45 and less than or equal to 195, the training sample is considered to be a positive sample, otherwise the training sample is negative sample.
- the data transmission volume of a positive sample of an electronic terminal in an a priori surfing time period is within a large probability range of the data transmission volume of the electronic terminal in the a priori surfing time period.
- a negative sample is not an abnormal sample, and a negative sample is also a normal sample, but the data transmission volume of the negative sample is outside the high probability range of the data transmission volume of the electronic terminal in the prior Internet access time period.
- the data transmission volume within the high probability range accounts for a relatively large proportion
- the data transmission volume outside the high probability range accounts for a relatively small proportion. Therefore, here Distinguish the two, and then calculate the loss of positive samples and the loss of negative samples respectively. Based on the settings of ⁇ and ⁇ , the proportion of positive samples and the proportion of negative samples can be further adjusted to obtain a more reasonable prediction model.
- the total priority is determined according to the first priority corresponding to the electronic terminal in the corresponding prior Internet access time period and the second priority corresponding to the category to which it belongs, and then the electronic terminal is allocated a sub-channel according to the total priority. . Since the first priority reflects the usage rule of the electronic terminal in the corresponding prior Internet access time period, it is a dynamic factor, while the second priority reflects the characteristics of the electronic terminal itself, which is a fixed factor. It can be seen that the total priority can be determined from Overall, it reflects the priority of the electronic terminal in the corresponding prior Internet access time period, which makes the classification of sub-channels more reasonable and optimized, thereby improving the communication speed of the electronic terminal and improving the problem of poor wireless signals.
- the WIFI channel allocation device includes:
- the time period determination module 110 is configured to, when receiving an Internet access request from any electronic terminal, determine the prior Internet access time period corresponding to the Internet access request;
- the first priority determination module 120 is configured to determine the first priority of the electronic terminal corresponding to the prior Internet access time period of the electronic terminal according to the prior Internet access time period of the electronic terminal;
- the second priority determining module 130 is configured to determine the second priority corresponding to the electronic terminal according to the category to which the electronic terminal belongs;
- an overall priority determination module 140 for determining an overall priority of the electronic terminal according to the first priority and the second priority of the electronic terminal.
- the sub-channel allocation module 150 is configured to allocate a corresponding WIFI sub-channel to the electronic terminal according to the total priority.
- the present disclosure also relates to computer equipment, including a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor implementing the WIFI channel allocation method of the present disclosure when the processor executes the computer program.
- the present disclosure also relates to a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, implements the WIFI channel allocation method of the present disclosure.
- any reference to a memory, storage, database, or other medium used in the various examples provided in this disclosure may include non-volatile and/or volatile memory.
- Nonvolatile memory may include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory.
- Volatile memory may include random access memory (RAM) or external cache memory.
- RAM is available in various forms such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous chain Road (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.
- SRAM static RAM
- DRAM dynamic RAM
- SDRAM synchronous DRAM
- DDRSDRAM double data rate SDRAM
- ESDRAM enhanced SDRAM
- SLDRAM synchronous chain Road (Synchlink) DRAM
- SLDRAM synchronous chain Road (Synchlink) DRAM
- Rambus direct RAM
- DRAM direct memory bus dynamic RAM
- RDRAM memory bus dynamic RAM
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
Disclosed are a WIFI channel allocation method and device. The method comprises: when an Internet access request of any electronic terminal is received, determining a prior Internet access time period corresponding to the Internet access request; determining a first priority of the electronic terminal corresponding to the prior Internet access time period; determining a second priority corresponding to the electronic terminal; determining a total priority of the electronic terminal; and allocating a corresponding WIFI sub-channel for the electronic terminal.
Description
相关申请的引用Citations to Related Applications
本公开要求于2020年12月25日向中国人民共和国国家知识产权局提交的申请号为202011563246.1,发明名称为“WIFI信道分配方法及设备”的发明专利申请的全部权益,并通过引用的方式将其全部内容并入本公开。This disclosure claims all rights and interests of the invention patent application with the application number 202011563246.1 and the invention title "WIFI channel allocation method and device" submitted to the State Intellectual Property Office of the People's Republic of China on December 25, 2020, which is incorporated by reference. The entire contents are incorporated into this disclosure.
领域field
本公开大体上涉及WIFI技术领域,更具体地涉及WIFI信道分配方法及设备。The present disclosure generally relates to the field of WIFI technology, and more particularly, to a WIFI channel allocation method and device.
背景background
在以家庭为单位的局域网内,可能会有多个电子终端同时连接无线网络,若电子终端过多或者电子终端的数据传输量过大,即便是采用支持WIFI6的路由***,也有可能会因为信道分配问题而出现信号不佳的情况出现。In a home-based local area network, there may be multiple electronic terminals connected to the wireless network at the same time. If there are too many electronic terminals or the data transmission volume of the electronic terminals is too large, even if a routing system that supports WIFI6 is used, there may be problems due to the channel Distribution problems occur when poor signal occurs.
概述Overview
第一方面,本公开涉及WIFI信道分配方法,其包括:In a first aspect, the present disclosure relates to a WIFI channel allocation method, which includes:
在接收到任一电子终端的上网请求时,确定所述上网请求对应的先验上网时间段;When receiving an Internet access request from any electronic terminal, determining a prior Internet access time period corresponding to the Internet access request;
根据所述电子终端的先验上网时间段,确定所述电子终端在所述先验上网时间段对应的第一优先级;determining the first priority of the electronic terminal corresponding to the prior Internet access time period of the electronic terminal according to the prior Internet access time period of the electronic terminal;
根据所述电子终端的所属类别,确定所述电子终端对应的第二优先级;determining a second priority corresponding to the electronic terminal according to the category to which the electronic terminal belongs;
根据所述电子终端的所述第一优先级和所述第二优先级,确定所述电子终端的总优先级;以及determining an overall priority of the electronic terminal according to the first priority and the second priority of the electronic terminal; and
根据所述总优先级,为所述电子终端分配对应的WIFI子信道。According to the total priority, a corresponding WIFI sub-channel is allocated to the electronic terminal.
第二方面,本公开涉及WIFI信道分配装置,其包括:In a second aspect, the present disclosure relates to a WIFI channel allocation device, comprising:
时间段确定模块,配置为在接收到任一电子终端的上网请求时, 确定所述上网请求对应的先验上网时间段;a time period determination module, configured to determine a priori Internet access time period corresponding to the Internet access request when receiving an Internet access request from any electronic terminal;
第一优先级确定模块,配置为根据所述电子终端的先验上网时间段,确定所述电子终端在所述先验上网时间段对应的第一优先级;a first priority determining module, configured to determine a first priority of the electronic terminal corresponding to the a priori Internet access time period of the electronic terminal according to the prior Internet access time period of the electronic terminal;
第二优先级确定模块,配置为根据所述电子终端的所属类别,确定所述电子终端对应的第二优先级;A second priority determining module, configured to determine a second priority corresponding to the electronic terminal according to the category to which the electronic terminal belongs;
总优先级确定模块,根据所述电子终端的所述第一优先级和所述第二优先级,确定所述电子终端的总优先级;以及a total priority determination module, which determines the total priority of the electronic terminal according to the first priority and the second priority of the electronic terminal; and
子信道分配模块,配置为根据所述总优先级,为所述电子终端分配对应的WIFI子信道。The sub-channel allocation module is configured to allocate a corresponding WIFI sub-channel to the electronic terminal according to the total priority.
第三方面,本公开涉及计算机设备,其包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序,所述处理器执行所述计算机程序时实现本公开的WIFI信道分配方法。In a third aspect, the present disclosure relates to a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, when the processor executes the computer program, the WIFI channel allocation method of the present disclosure is implemented .
第四方面,本公开涉及计算机可读存储介质,其上存储有计算机程序,所述计算机程序被处理器执行本公开的WIFI信道分配方法。In a fourth aspect, the present disclosure relates to a computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor to execute the WIFI channel allocation method of the present disclosure.
在某些实施方案中,本公开的WIFI信道分配方法,根据电子终端在对应先验上网时间段对应的第一优先级和所属类别对应的第二优先级来确定总优先级,进而依据总优先级为电子终端分配子信道。由于第一优先级反映的是电子终端在对应先验上网时间段内的使用规律,属于动态因素,而第二优先级反映的是电子终端本身的特点,属于固定因素,可见总优先级可以从整体上反映电子终端在对应先验上网时间段的优先级情况,使得子信道的分类更加合理、优化,进而提供了电子终端的通信速度,改善了无线信号不佳的问题。In some embodiments, the WIFI channel allocation method of the present disclosure determines the total priority according to the first priority corresponding to the electronic terminal in the corresponding prior Internet access time period and the second priority corresponding to the category to which it belongs, and then according to the total priority The stage allocates sub-channels for electronic terminals. Since the first priority reflects the usage rule of the electronic terminal in the corresponding prior Internet access time period, it is a dynamic factor, while the second priority reflects the characteristics of the electronic terminal itself, which is a fixed factor. It can be seen that the total priority can be determined from Overall, it reflects the priority of the electronic terminal in the corresponding prior Internet access time period, which makes the classification of sub-channels more reasonable and optimized, thereby improving the communication speed of the electronic terminal and improving the problem of poor wireless signals.
附图简要说明Brief Description of Drawings
此处的附图被并入说明书中并构成本说明书的一部分,示出了符合本公开的实施例,并与说明书一起配置为解释本公开的原理。The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure, and together with the description, serve to explain the principles of the disclosure.
为了更清楚地说明本公开的技术方案,下面将对本公开所需要使用的附图作简单地介绍,显而易见地,对于本领域普通技术人员而言,在不付出创造性劳动性的前提下,还可以根据这些附图获得其他的附图。In order to illustrate the technical solutions of the present disclosure more clearly, the accompanying drawings required for the present disclosure will be briefly introduced below. Obviously, for those of ordinary skill in the art, without any creative effort, the Additional drawings are obtained from these drawings.
图1为本公开一实施例提供的WIFI信道分配方法的流程示意图;以及FIG. 1 is a schematic flowchart of a WIFI channel allocation method according to an embodiment of the present disclosure; and
图2为本公开一实施例提供的WIFI信道分配装置的结构框图。FIG. 2 is a structural block diagram of a WIFI channel allocation apparatus provided by an embodiment of the present disclosure.
详述detail
为使本公开实施例的目的、技术方案和优点更加清楚,下面将结合本公开实施例中的附图,对本公开实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例是本公开的一部分实施例,而不是全部的实施例。基于本公开中的实施例,本领域普通技术人员在没有做出创造性劳动的前提下所获得的所有其他实施例,都属于本公开保护的范围。In order to make the purposes, technical solutions and advantages of the embodiments of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be described clearly and completely below with reference to the accompanying drawings in the embodiments of the present disclosure. Obviously, the described embodiments These are some, but not all, embodiments of the present disclosure. Based on the embodiments in the present disclosure, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present disclosure.
图1为本公开提供的WIFI信道分配方法,如图1所示,该方法包括如下步骤:FIG. 1 is a WIFI channel allocation method provided by the present disclosure. As shown in FIG. 1 , the method includes the following steps:
S110,在接收到任一电子终端的上网请求时,确定所述上网请求对应的先验上网时间段;S110, when receiving an Internet access request from any electronic terminal, determine a prior Internet access time period corresponding to the Internet access request;
S120,根据所述电子终端的先验上网时间段,确定所述电子终端在所述先验上网时间段对应的第一优先级;S120, determining a first priority of the electronic terminal corresponding to the prior Internet access time period of the electronic terminal according to the prior Internet access time period;
S130,根据所述电子终端的所属类别,确定所述电子终端对应的第二优先级;S130, determining a second priority corresponding to the electronic terminal according to the category to which the electronic terminal belongs;
S140,根据所述电子终端的所述第一优先级和所述第二优先级,确定所述电子终端的总优先级;以及S140, determine the total priority of the electronic terminal according to the first priority and the second priority of the electronic terminal; and
S150,根据所述总优先级,为所述电子终端分配对应的WIFI子信道。S150: Allocate a corresponding WIFI sub-channel to the electronic terminal according to the total priority.
在某些实施方案中,电子终端包括但不限于手机、平板电脑、笔记本电脑、台式电脑、智能冰箱、智能电视、智能加湿器、智能扫地机器人等任何可以连接无线网络的家庭设备。In some embodiments, electronic terminals include, but are not limited to, mobile phones, tablet computers, notebook computers, desktop computers, smart refrigerators, smart TVs, smart humidifiers, smart cleaning robots, and other household devices that can be connected to a wireless network.
在某些实施方案中,在接收到一个上网请求时,在上网请求中可以得到电子终端的身份标识等信息,根据身份标识可以知道是哪一个电子终端需要上网。In some embodiments, when an Internet access request is received, information such as the identity identifier of the electronic terminal can be obtained in the Internet access request, and which electronic terminal needs to access the Internet can be known according to the identity identifier.
在某些实施方案中,先验上网时间段,是接收到上网请求的时间 点所属的时间段。在一天中,可以设置多个先验上网时间段,例如,早晨6:00~8:00、8:00~11:00,中午11:00~13:00、13:00~16:30,晚上16:30~19:00、19:00~22:00等。这里先验上网时间段可以是预先人工设置,也可以是后续步骤中通过聚类算法聚类得到。若接收到上网请求的时刻在某个先验上网时间段内,则该上网请求对应该先验上网时间段。In some embodiments, the a priori surfing time period is the time period to which the time point when the surfing request is received belongs. In a day, you can set multiple prior Internet access time periods, for example, 6:00-8:00, 8:00-11:00 in the morning, 11:00-13:00, 13:00-16:30 in the noon, 16:30-19:00, 19:00-22:00, etc. in the evening. Here, the prior Internet access time period may be manually set in advance, or may be obtained by clustering with a clustering algorithm in a subsequent step. If the moment when the Internet access request is received is within a certain a priori Internet access time period, the Internet access request corresponds to the a priori Internet access time period.
在某些实施方案中,不同的电子终端,在不同的时间段,具有不同的优先级。例如,在早晨6:00~8:00、中午11:00~13:00、晚上16:30~19:00这些时间段,厨房的电子终端的优先级会较高,在白天的其他时段,笔记本、台式电脑主要配置为工作的电子终端的优先级会较高,在晚上19:00~22:00,电视、手机等主要配置为娱乐的电子终端的优先级会较高。In some embodiments, different electronic terminals have different priorities at different time periods. For example, in the time periods of 6:00-8:00 in the morning, 11:00-13:00 in the noon, and 16:30-19:00 in the evening, the priority of the electronic terminal in the kitchen will be higher. The priority of electronic terminals mainly configured for work on notebooks and desktop computers will be higher. From 19:00 to 22:00 in the evening, the priority of electronic terminals mainly configured for entertainment, such as televisions and mobile phones, will be higher.
在某些实施方案中,第一优先级可以设置为多个,针对每一种电子终端在每一个先验上网时间段设置一个第一优先级。在晚上19:00~22:00,电视的第一优先级最高,其次是手机,而其余电子终端的第一优先级低于电视和手机的第一优先级。可见,第一优先级是根据电子终端在不同时间段的使用频率等因此确定的,电子终端在某一时间段的使用频率越高,其第一优先级越高,因此可以根据电子终端的历史使用规律,为其设置在每一个先验上网时间段的第一优先级。若电子终端在某个先验上网时间段内的使用规律发生变化,则对应的第一优先级也会有变化,可见第一优先级可以是动态变化的。In some embodiments, multiple first priorities may be set, and one first priority may be set for each type of electronic terminal in each prior Internet access time period. From 19:00 to 22:00 in the evening, the first priority of the TV is the highest, followed by the mobile phone, and the first priority of the other electronic terminals is lower than the first priority of the TV and the mobile phone. It can be seen that the first priority is determined according to the frequency of use of the electronic terminal in different time periods. The higher the frequency of use of the electronic terminal in a certain time period, the higher the first priority. Use the rule to set the first priority in each prior Internet access time period. If the usage rule of the electronic terminal changes within a certain prior Internet access time period, the corresponding first priority will also change. It can be seen that the first priority may be dynamically changed.
在某些实施方案中,所属类别可以从多个维度进行分类,例如,便携性、功能性等。笔记本是便携式的设备,而且利用笔记本可以处理相关工作,因此可以将笔记本的第二优先级设置为最高,其次从高到低可以是手机、电视、冰箱等。In some embodiments, the belonging category can be categorized from multiple dimensions, eg, portability, functionality, and the like. The notebook is a portable device, and the notebook can be used to handle related work, so the second priority of the notebook can be set to the highest, followed by mobile phones, TVs, refrigerators, etc. from high to low.
在某些实施方案中,在接收到上网请求时,从上网请求中可以得到是哪一电子终端需要上网,进而根据该电子终端的类别,确定对应的第二优先级,可见第二优先级是根据电子终端本身确定的,若分类标准统一不变,则电子终端的第二优先级就是固定的。In some embodiments, when an Internet access request is received, which electronic terminal needs to access the Internet can be obtained from the Internet access request, and then a corresponding second priority is determined according to the type of the electronic terminal. It can be seen that the second priority is According to the determination of the electronic terminal itself, if the classification standard is uniform and unchanged, the second priority of the electronic terminal is fixed.
在某些实施方案中,在确定电子终端的总优先级时,即考虑到了 电子终端在对应先验上网时间段内的使用规律,也考虑到电子终端本身的特点,即考虑到了动态因素,也考虑到了固定因素,因此根据总优先级可以从总体上反映电子终端在对应先验上网时间段的优先级情况。In some embodiments, when determining the overall priority of the electronic terminal, both the usage rule of the electronic terminal in the corresponding prior Internet access time period and the characteristics of the electronic terminal itself are considered, that is, dynamic factors are taken into account, and the Considering the fixed factor, the priority status of the electronic terminal in the corresponding prior Internet access time period can be generally reflected according to the total priority.
在某些实施方案中,一个电子终端在一个先验上网时间段的总优先级越高,可以越优先为该电子终端在该先验上网时间段分配子信道。In some embodiments, the higher the total priority of an electronic terminal in an a priori surfing time period, the more preferentially the sub-channel may be allocated for the electronic terminal in the a priori surfing time period.
在某些实施方案中,可以采用多种方式计算总优先级,例如采用如下第一公式计算总优先级,所述第一公式包括:In some embodiments, the total priority can be calculated in various ways, for example, the total priority can be calculated using the following first formula, where the first formula includes:
式中,G为所述总优先级,
和γ为平衡参数,g
1为所述第一优先级,g
2为所述第二优先级。其中平衡参数为平衡两个优先级的参数,例如,
可以取第一优先级的数量的倒数,γ可以取第二优先级的数量的倒数。
where G is the total priority, and γ are balance parameters, g 1 is the first priority, and g 2 is the second priority. where the balance parameter is the parameter that balances the two priorities, for example, The inverse of the number of the first priority may be taken, and γ may be the inverse of the number of the second priority.
在某些实施方案中,第一优先级的总数量为3,第二优先级的总数量为4,则
为1/3,γ为1/4,若经过上述步骤得到的第一优先级为3(最低的第一优先级),第二优先级为2,则此时G为4,可见此时总优先级也比较低。若第一优先级为1(最高的第一优先级),第二优先级为1(最高的第二优先级),则G为1,此时总优先级为最高。
In some embodiments, the total number of first priorities is 3 and the total number of second priorities is 4, then is 1/3, γ is 1/4, if the first priority obtained through the above steps is 3 (the lowest first priority) and the second priority is 2, then G is 4 at this time, and it can be seen that the total The priority is also lower. If the first priority is 1 (the highest first priority) and the second priority is 1 (the highest second priority), then G is 1, and the total priority is the highest at this time.
这里对总优先级的数量没有限制,若某一个总优先级距离总优先级1(最高的总优先级)越远,则该总优先级越低。There is no limit to the number of total priorities. If a certain total priority is farther from the total priority 1 (the highest total priority), the lower the total priority.
在某些实施方案中,总优先级设置有三个等级,WIFI信道可以分为6个。通过上述步骤的计算,可得在晚上19:00~22:00,电视的优先级最高,其次是手机,其余电子终端的总优先级最低。此时,可以将第1~3个子信道分配给电视,第4~5个子信道分配给手机,第6个子信道分配给其余电子终端。In some embodiments, the overall priority is set to three levels, and the WIFI channels can be divided into six. Through the calculation of the above steps, it can be obtained that between 19:00 and 22:00 in the evening, the priority of the TV is the highest, followed by the mobile phone, and the total priority of the other electronic terminals is the lowest. At this time, the 1st to 3rd subchannels can be allocated to the television, the 4th to 5th subchannels can be allocated to the mobile phone, and the 6th subchannel can be allocated to other electronic terminals.
在某些实施方案中,本公开实施例提供的方法还可以包括:In certain embodiments, the methods provided by the embodiments of the present disclosure may further include:
S160,根据预先训练的预测模型,确定所述电子终端在所述先验上网时间段内的预测数据传输总量。S160: Determine, according to the pre-trained prediction model, the total amount of predicted data transmission of the electronic terminal within the prior Internet access time period.
在某些实施方案中,步骤S150可以包括:In some embodiments, step S150 may include:
S151,根据所述预测数据传输总量,确定电子设备从接收到上网请求的时刻到所述先验上网时间段的终点时刻的预测数据传输分量;以及S151, according to the total amount of predicted data transmission, determine the predicted data transmission component of the electronic device from the moment of receiving the Internet access request to the end time of the prior Internet access time period; and
S152,根据所述总优先级和所述预测数据传输分量,为所述电子终端分配对应的WIFI子信道。S152: Allocate a corresponding WIFI sub-channel to the electronic terminal according to the total priority and the predicted data transmission component.
预测数据传输总量为所述电子终端在一个先验上网时间段内的预测数据传输量的总和。The total amount of predicted data transmission is the sum of the predicted data transmission amount of the electronic terminal in a prior Internet access time period.
上述步骤S160可以步骤S110之后且步骤S150之前的任意时间执行。The above step S160 may be performed at any time after step S110 and before step S150.
在某些实施方案中,预测模型是用预设历史时期内的数据进行训练得到,预设历史时期包括第一历史子时期和第二历史子时期,第一历史子时期早于第二历史子时期,例如第一历史子时期为前天,第二历史子时期为昨天,用前天的数据预测昨天的数据,根据对昨天的预测结果和昨天的真实数据进行模型调整,得到一个预测模型,然后便可以将昨天的真实数据输入这一预测模型,便可以输出今天的预测结果。In some embodiments, the prediction model is obtained by training data in a preset historical period, the preset historical period includes a first historical sub-period and a second historical sub-period, and the first historical sub-period is earlier than the second historical sub-period Period, for example, the first historical sub-period is the day before yesterday, and the second historical sub-period is yesterday. The data of the day before yesterday is used to predict the data of yesterday, and the model is adjusted according to the prediction result of yesterday and the real data of yesterday to obtain a prediction model, and then Yesterday's real data can be fed into this forecasting model, and today's forecast can be output.
在某些实施方案中,先验上网时间段为晚上19:00~22:00,22:00为先验上网时间段的终点时刻,若接收到电视发送来的上网请求的时刻为8:00,则预测数据传输分量为电视在8:00~22:00之间的数据传输量。例如,通过预测模型得到的电视在19:00~22:00的预测数据传输总量为M,则电视在8:00~22:00之间的预测数据传输分量为2M/3。In some embodiments, the a priori Internet access time period is from 19:00 to 22:00 in the evening, and 22:00 is the end time of the a priori Internet access time period. , the predicted data transmission component is the data transmission amount of the TV between 8:00 and 22:00. For example, if the total amount of predicted data transmission of TV from 19:00 to 22:00 obtained by the prediction model is M, the predicted data transmission component of TV from 8:00 to 22:00 is 2M/3.
在某些实施方案中,预测数据传输分量是对未来时间段(接收到上网请求的时刻到所属先验上网时间段的终点时刻)的数据传输量的预测值。In some embodiments, the predicted data transmission component is a predicted value of the data transmission amount for a future time period (the time when the Internet access request is received to the end time of the a priori Internet time period to which it belongs).
在某些实施方案中,在分配子信道时,不仅考虑到总优先级,也考虑到预测数据传输分量,其中总优先级反映的是电子终端的历史使用规律和本身特点,预测数据传输分量反映的是对未来时间段的数据传输量的预测值,使得子信道的分配更加合理。In some embodiments, when assigning sub-channels, not only the total priority but also the predicted data transmission component is considered, wherein the total priority reflects the historical usage pattern and its own characteristics of the electronic terminal, and the predicted data transmission component reflects It is the predicted value of the data transmission amount in the future time period, which makes the allocation of sub-channels more reasonable.
在某些实施方案中,步骤S152可以包括如下步骤:In some embodiments, step S152 may include the following steps:
S151a,根据所述总优先级,确定所述电子终端的初始子信道;以 及S151a, determining the initial sub-channel of the electronic terminal according to the total priority; and
S152b,根据所述预测数据传输分量,对所述初始子信道进行调整,得到目标子信道,若所述预测数据传输分量大于传输量阈值分量,则对初始子信道进行邻近扩增,得到所述目标子信道,否则,对初始子信道进行邻近缩减,得到所述目标子信道;S152b: Adjust the initial sub-channel according to the predicted data transmission component to obtain a target sub-channel, and if the predicted data transmission component is greater than the transmission amount threshold component, perform adjacent amplification on the initial sub-channel to obtain the target sub-channel, otherwise, perform proximity reduction on the initial sub-channel to obtain the target sub-channel;
其中,所述传输量阈值分量与所述传输量阈值的比值等于所述预测数据传输分量与所述预测数据传输总量的比值,传输量阈值分量是传输量阈值的分量。The ratio of the transmission volume threshold component to the transmission volume threshold is equal to the ratio of the predicted data transmission component to the total predicted data transmission, and the transmission volume threshold component is the component of the transmission volume threshold.
在某些实施方案中,总优先级G为1,这一总优先级对应的子信道为第1~4个子信道,即初始子信道为第1~4个子信道;总优先级G为4,则这一总优先级对应的子信道为第10个子信道,则初始子信道为第10个子信道。In some embodiments, the total priority G is 1, and the subchannels corresponding to this total priority are the 1st to 4th subchannels, that is, the initial subchannels are the 1st to 4th subchannels; the total priority G is 4, Then the subchannel corresponding to this total priority is the tenth subchannel, and the initial subchannel is the tenth subchannel.
在某些实施方案中,所述传输量阈值分量与所述传输量阈值的比值等于所述预测数据传输分量与所述预测数据传输总量的比值,传输量阈值分量是传输量阈值的分量,其计算方式类似于预测数据传输分量。将先验上网时间段19:00~22:00对应的传输量阈值设置为k,在8:00~22:00之间的传输量阈值分量为2k/3。In certain embodiments, the ratio of the traffic threshold component to the traffic threshold is equal to the ratio of the predicted data traffic component to the total predicted data traffic, the traffic threshold component being the component of the traffic threshold, It is calculated similarly to the predicted data transfer component. The transmission volume threshold corresponding to the prior Internet access time period from 19:00 to 22:00 is set as k, and the transmission volume threshold component between 8:00 and 22:00 is 2k/3.
仍以总优先级G为1和4为例,当G为1时,若对应的预测数据传输分量小于传输量阈值分量,则将第1~3个子信道作为目标子信道,即将第4个子信道让给其他的电子终端使用或空置。当G为4时,若对应的预测数据传输分量大于传输量阈值分量,则将第9和10个子信道作为目标子信道,即增加第9个子信道。若此时第9子信道同时被另一个电子终端使用,则第9信道为这两个电子终端复用。Still taking the total priority G as 1 and 4 as an example, when G is 1, if the corresponding predicted data transmission component is less than the transmission volume threshold component, the 1st to 3rd subchannels are used as the target subchannels, that is, the 4th subchannel. Let it be used by other electronic terminals or be vacant. When G is 4, if the corresponding predicted data transmission component is greater than the transmission amount threshold component, the 9th and 10th subchannels are used as target subchannels, that is, the 9th subchannel is added. If the ninth sub-channel is simultaneously used by another electronic terminal, the ninth channel is multiplexed for the two electronic terminals.
在某些实施方案中,预测模型的预先训练过程可以包括:In some embodiments, the pre-training process of the predictive model may include:
S010,获取家庭组网内各个电子终端的历史上网信息,所述历史上网信息包括各个终端在预设历史时期内的各个上网时间段和每一个上网时间段内的各条数据传输信息;S010, obtaining historical Internet access information of each electronic terminal in the home network, where the historical Internet access information includes each Internet access time period of each terminal in a preset historical period and each piece of data transmission information in each Internet access time period;
S020,采用预设聚类算法,对每一个电子终端的各个上网时间段进行聚类,得到每一个电子终端的多个先验上网时间段;S020, using a preset clustering algorithm to cluster each Internet access time period of each electronic terminal to obtain a plurality of prior Internet access time periods of each electronic terminal;
S030,标记每一个先验上网时间段中每一条数据传输信息的数据 传输量,将每一个先验上网时间段中标记有数据传输量的每一条数据传输信息作为一个训练样本,构建训练样本集;S030, mark the data transmission amount of each piece of data transmission information in each prior Internet access time period, and use each piece of data transmission information marked with the data transmission amount in each prior Internet Internet time period as a training sample to construct a training sample set ;
S040,根据所述训练样本集进行模型训练,得到所述预测模型。S040, perform model training according to the training sample set to obtain the prediction model.
在某些实施方案中,预设历史时期,过去的一个星期。可以将每一天划分为12个上网时间段。在每一个上网时间段内,每一个电子终端可以与路由设备之间进行多次数据传输,因此会产生多条数据传输信息,每一条数据传输信息中会包含传输的内容、与内容相关的信息(例如,该条数据传输信息对应的数据传输量)等。In some embodiments, the historical period is preset, the past week. Each day can be divided into 12 Internet time periods. During each Internet access time period, each electronic terminal can perform multiple data transmissions with the routing device, so multiple pieces of data transmission information will be generated, and each piece of data transmission information will include the transmitted content and content-related information. (For example, the data transmission amount corresponding to the piece of data transmission information), etc.
在某些实施方案中,采用K均值聚类算法,将12个上网时间段进行聚类,得到6个先验上网时间段。In some embodiments, a K-means clustering algorithm is used to cluster 12 time periods online to obtain 6 a priori time periods for Internet access.
在某些实施方案中,该步骤是构建训练样本集的过程:对每一条数据传输信息标记对应的数据传输量,将标记有数据传输量的数据传输信息作为一条训练样本。In some embodiments, this step is a process of constructing a training sample set: marking the corresponding data transmission amount for each piece of data transmission information, and using the data transmission information marked with the data transmission amount as a training sample.
在某些实施方案中,依据机器学习算法和训练样本集进行模型训练的过程是对模型中的各个参数进行设置调整的过程,在每一调整参数后,计算损失函数,根据损失值再次对模型参数进行调整,直至依据损失函数计算出来的损失值在一定的误差范围内。In some embodiments, the process of performing model training according to the machine learning algorithm and the training sample set is a process of setting and adjusting various parameters in the model. After each parameter is adjusted, a loss function is calculated, and the model is again adjusted according to the loss value. The parameters are adjusted until the loss value calculated according to the loss function is within a certain error range.
在某些实施方案中,步骤S040中在所述预测模型的训练过程中采用第二公式对训练样本进行损失计算,所述第二公式包括:In some embodiments, in step S040, in the training process of the prediction model, a second formula is used to calculate the loss of the training samples, and the second formula includes:
式中,L为每一个电子模块的每一个先验上网时间段对应的预测模型的总损失,α和β为预设平衡参数,N
cls是训练所述预测模型所需的所有训练样本中正样本的数量,L
cls()为第一损失函数,y
1i是为第i个正样本预先标记的数据传输量,N
reg为训练所述预测模型所需的所有训练样本中负样本的数量,L
reg()为第二损失函数,y
2i为第i个负样本预先标记的数据传输量,y
*为所述预测模型输出的预测数据传输总量与所述所有训练样本的数量的比值。
In the formula, L is the total loss of the prediction model corresponding to each prior online time period of each electronic module, α and β are preset balance parameters, and N cls is the positive sample in all training samples required to train the prediction model. The number of , L cls ( ) is the first loss function, y 1i is the pre-labeled data transfer amount for the ith positive sample, N reg is the number of negative samples in all training samples required to train the prediction model, L reg ( ) is the second loss function, y 2i is the pre-labeled data transmission amount of the ith negative sample, and y * is the ratio of the total amount of predicted data transmission output by the prediction model to the number of all training samples.
在某些实施方案中,第一损失函数和第二损失函数为不同的函数,由于正负样本对训练所产生的影响不同,因此采用不同的损失函数。In some embodiments, the first loss function and the second loss function are different functions. Since positive and negative samples have different effects on training, different loss functions are used.
在某些实施方案中,α和β为预设平衡参数,α与β的和为1,取值可以根据需要设置。In some embodiments, α and β are preset balance parameters, the sum of α and β is 1, and the values can be set as required.
在某些实施方案中,第二公式包括两部分:正样本的损失值和负样本的损失值,因此在利用第二公式进行损失计算时,需要对训练样本集中的正负样本进行分类,正负样本的分类过程可以包括:In some embodiments, the second formula includes two parts: the loss value of positive samples and the loss value of negative samples. Therefore, when using the second formula for loss calculation, it is necessary to classify the positive and negative samples in the training sample set. The classification process of negative samples can include:
S041,针对每一个电子终端的每一个先验上网时间段内的所有训练样本,按照预先标记的数据传输量从低到高进行排序,得到每一个先验上网时间段对应的传输量序列;S041, for all training samples in each prior Internet access time period of each electronic terminal, sort according to the pre-marked data transmission volume from low to high, and obtain a transmission volume sequence corresponding to each a priori Internet access time segment;
S042,从所述传输量序列中选取第一数据传输量R1、第二数据传输量R2和第三数据传输量R3,所述第一数据传输量为所述传输量序列中1/4位置处的数据传输量,所述第二数据传输量为所述传输量序列中1/2位置处的数据传输量,所述第三数据传输量为所述传输量序列中3/4位置处的数据传输量;S042, select a first data transmission amount R1, a second data transmission amount R2, and a third data transmission amount R3 from the transmission amount sequence, where the first data transmission amount is a 1/4 position in the transmission amount sequence The second data transmission amount is the data transmission amount at the 1/2 position in the transmission amount sequence, and the third data transmission amount is the data at the 3/4 position in the transmission amount sequence. transmission volume;
S043,根据所述第一数据传输量、所述第二数据量和所述第三数据传输量,设置每一个电子终端的每一个先验上网时间段对应的正样本区间;以及S043, according to the first data transmission amount, the second data transmission amount and the third data transmission amount, set a positive sample interval corresponding to each a priori Internet access time period of each electronic terminal; and
S044,判断每一个电子终端的每一个先验上网时间段对应的每一个训练样本预先标记的数据传输量是否落在正样本区间内;若是,则该训练样本为正样本;否则,该训练样本为负样本。S044, judging whether the pre-marked data transmission amount of each training sample corresponding to each a priori online time period of each electronic terminal falls within the positive sample interval; if so, the training sample is a positive sample; otherwise, the training sample is a negative sample.
在某些实施方案中,智能电视在19:00~22:00这一先验上网时间段内的500条训练样本,这500条训练样本各自所标记的数据传输量有大有小,此时按照数据传输量从小到大的顺序进行排序,得到智能电视在19:00~22:00这一先验上网时间段对应的一个数据传输量序列。In some embodiments, the smart TV has 500 training samples in the prior Internet access time period from 19:00 to 22:00, and the data transmission amount marked by each of the 500 training samples is large or small. At this time According to the order of data transmission volume from small to large, a data transmission volume sequence corresponding to the prior Internet access time period of the smart TV from 19:00 to 22:00 is obtained.
在某些实施方案中,正样本区间的设置方式有多种,[2R1-R3,2R3-R1],这里没有用到R2,这种方式设置的正样本区间是固定的,计算方法简单方便,但是不能根据传输量序列的情况而改变。也可以采用如下第三公式计算正样本区间H,第三公式包括:In some embodiments, there are multiple ways to set the positive sample interval, [2R1-R3, 2R3-R1], R2 is not used here, the positive sample interval set in this way is fixed, and the calculation method is simple and convenient, However, it cannot be changed according to the situation of the transmission amount sequence. The following third formula can also be used to calculate the positive sample interval H, and the third formula includes:
式中,E()为均值函数,R1为所述第一数据传输量,R2为所述第二数据传输量,R3为所述第三数据传输量,
为区间宽度调节参数,
小于等于1。
In the formula, E() is the mean function, R1 is the first data transmission amount, R2 is the second data transmission amount, R3 is the third data transmission amount, Adjust the parameter for the interval width, less than or equal to 1.
在第三公式中,通过
可以对正样本区间进行调整,
越大,区间越宽,
越小,区间越窄。
的大小可以根据经验设置,当然也可以采用如下方法确定:
In the third formula, by The positive sample interval can be adjusted, The larger the interval, the wider the interval. The smaller the interval, the narrower the interval. The size can be set according to experience, of course, it can also be determined by the following methods:
设置区间宽度调节参数
从0开始逐步增加,当
增加到所述传输量序列中至少90%的数据传输量落在预设区间
内时,
停止增加,将此时的
选取出来用于计算第三公式,其中,δ为所述传输量序列的标准差。
Set interval width adjustment parameters Gradually increase from 0, when At least 90% of the data transmission volume added to the transmission volume sequence falls within the preset interval inside, stop increasing, set the It is selected and used to calculate the third formula, where δ is the standard deviation of the transmission quantity sequence.
在某些实施方案中,当到所述传输量序列中至少90%的数据传输量落在预设区间
内时,根据此时的
计算出来的正样本区间H不会过宽,也不会过窄。
In some embodiments, when at least 90% of the data transfers in the sequence of transfers fall within a preset interval time, according to the time The calculated positive sample interval H is neither too wide nor too narrow.
仍以智能电视在19:00~22:00这一先验上网时间段对应的数据传输量序列为例,假设选取第125个数据传输量作为第一数据传输量R1,选取第250个数据传输量作为第二数据传输量R2,选取第375个数据传输量作为第二数据传输量R3,R1为100,R2为135,R3为150,
取0.9,则依据第三公式计算得到的正样本区间为[55,195],因此只要训练样本的数据传输量大于等于45且小于等于195,就认为训练样本为正样本,否则训练样本为负样本。
Still taking the data transmission volume sequence corresponding to the prior Internet access time period of smart TV from 19:00 to 22:00 as an example, it is assumed that the 125th data transmission volume is selected as the first data transmission volume R1, and the 250th data transmission volume is selected as the first data transmission volume R1. As the second data transmission amount R2, select the 375th data transmission amount as the second data transmission amount R3, R1 is 100, R2 is 135, R3 is 150, Taking 0.9, the positive sample interval calculated according to the third formula is [55, 195], so as long as the data transmission amount of the training sample is greater than or equal to 45 and less than or equal to 195, the training sample is considered to be a positive sample, otherwise the training sample is negative sample.
在某些实施方案中,一个电子终端在一个先验上网时间段中的正样本的数据传输量在该电子终端在该先验上网时间段的数据传输量的大概率范围内。这里需要注意的是负样本并不是异常样本,负样本也是正常样本,只不过负样本的数据传输量在该电子终端在该先验上网时间段的数据传输量的大概率范围之外。而在对一个先验上网时间段对应的预测数据传输总量进行预测时,大概率范围内的数据传输量占的比重比较大,而大概率范围外的数据传输量占的比较小,因此这里将两者区分开来,进而分别计算正样本的损失和负样本的损失,基于设置α和β,从而进一步调整正样本的比重和负样本的比重,进而得到更加合理的预测模型。In some embodiments, the data transmission volume of a positive sample of an electronic terminal in an a priori surfing time period is within a large probability range of the data transmission volume of the electronic terminal in the a priori surfing time period. It should be noted here that a negative sample is not an abnormal sample, and a negative sample is also a normal sample, but the data transmission volume of the negative sample is outside the high probability range of the data transmission volume of the electronic terminal in the prior Internet access time period. When predicting the total amount of predicted data transmission corresponding to a prior Internet access time period, the data transmission volume within the high probability range accounts for a relatively large proportion, while the data transmission volume outside the high probability range accounts for a relatively small proportion. Therefore, here Distinguish the two, and then calculate the loss of positive samples and the loss of negative samples respectively. Based on the settings of α and β, the proportion of positive samples and the proportion of negative samples can be further adjusted to obtain a more reasonable prediction model.
本公开实施例提供的方法,根据电子终端在对应先验上网时间段对应的第一优先级和所属类别对应的第二优先级来确定总优先级,进 而依据总优先级为电子终端分配子信道。由于第一优先级反映的是电子终端在对应先验上网时间段内的使用规律,属于动态因素,而第二优先级反映的是电子终端本身的特点,属于固定因素,可见总优先级可以从整体上反映电子终端在对应先验上网时间段的优先级情况,使得子信道的分类更加合理、优化,进而提供了电子终端的通信速度,改善了无线信号不佳的问题。In the method provided by the embodiment of the present disclosure, the total priority is determined according to the first priority corresponding to the electronic terminal in the corresponding prior Internet access time period and the second priority corresponding to the category to which it belongs, and then the electronic terminal is allocated a sub-channel according to the total priority. . Since the first priority reflects the usage rule of the electronic terminal in the corresponding prior Internet access time period, it is a dynamic factor, while the second priority reflects the characteristics of the electronic terminal itself, which is a fixed factor. It can be seen that the total priority can be determined from Overall, it reflects the priority of the electronic terminal in the corresponding prior Internet access time period, which makes the classification of sub-channels more reasonable and optimized, thereby improving the communication speed of the electronic terminal and improving the problem of poor wireless signals.
如图2所示,本公开实施例提供的WIFI信道分配装置,其包括:As shown in FIG. 2 , the WIFI channel allocation device provided by the embodiment of the present disclosure includes:
时间段确定模块110,配置为在接收到任一电子终端的上网请求时,确定所述上网请求对应的先验上网时间段;The time period determination module 110 is configured to, when receiving an Internet access request from any electronic terminal, determine the prior Internet access time period corresponding to the Internet access request;
第一优先级确定模块120,配置为根据所述电子终端的先验上网时间段,确定所述电子终端在所述先验上网时间段对应的第一优先级;The first priority determination module 120 is configured to determine the first priority of the electronic terminal corresponding to the prior Internet access time period of the electronic terminal according to the prior Internet access time period of the electronic terminal;
第二优先级确定模块130,配置为根据所述电子终端的所属类别,确定所述电子终端对应的第二优先级;The second priority determining module 130 is configured to determine the second priority corresponding to the electronic terminal according to the category to which the electronic terminal belongs;
总优先级确定模块140,根据所述电子终端的所述第一优先级和所述第二优先级,确定所述电子终端的总优先级;以及an overall priority determination module 140, for determining an overall priority of the electronic terminal according to the first priority and the second priority of the electronic terminal; and
子信道分配模块150,配置为根据所述总优先级,为所述电子终端分配对应的WIFI子信道。The sub-channel allocation module 150 is configured to allocate a corresponding WIFI sub-channel to the electronic terminal according to the total priority.
本公开还涉及计算机设备,包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序,所述处理器执行所述计算机程序时实现本公开的WIFI信道分配方法。The present disclosure also relates to computer equipment, including a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor implementing the WIFI channel allocation method of the present disclosure when the processor executes the computer program.
本公开还涉及计算机可读存储介质,其上存储有计算机程序,所述计算机程序被处理器执行时实现本公开的WIFI信道分配方法。The present disclosure also relates to a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, implements the WIFI channel allocation method of the present disclosure.
在某些实施方案中,本公开实施例提供的装置、计算机设备、计算机可读存储介质,有关内容的解释、举例、有益效果等部分可以参考上述方法中的相应部分,此处不再赘述。In some embodiments, for the apparatus, computer equipment, and computer-readable storage medium provided by the embodiments of the present disclosure, for the explanation, examples, and beneficial effects of the content, reference may be made to the corresponding part of the above method, and details are not repeated here.
在某些实施方案中,本公开所提供的各实施例中所使用的对存储器、存储、数据库或其它介质的任何引用,均可包括非易失性和/或易失性存储器。非易失性存储器可包括只读存储器(ROM)、可编程ROM(PROM)、电可编程ROM(EPROM)、电可擦除可编程ROM(EEPROM)或闪存。易失性存储器可包括随机存取存储器(RAM) 或者外部高速缓冲存储器。作为说明而非局限,RAM以多种形式可得,诸如静态RAM(SRAM)、动态RAM(DRAM)、同步DRAM(SDRAM)、双数据率SDRAM(DDRSDRAM)、增强型SDRAM(ESDRAM)、同步链路(Synchlink)DRAM(SLDRAM)、存储器总线(Rambus)直接RAM(RDRAM)、直接存储器总线动态RAM(DRDRAM)、以及存储器总线动态RAM(RDRAM)等。In certain embodiments, any reference to a memory, storage, database, or other medium used in the various examples provided in this disclosure may include non-volatile and/or volatile memory. Nonvolatile memory may include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous chain Road (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.
需要说明的是,在本文中,术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含,从而使得包括一系列要素的过程、方法、物品或者装置不仅包括那些要素,而且还包括没有明确列出的其他要素,或者是还包括为这种过程、方法、物品或者装置所固有的要素。在没有更多限制的情况下,由语句“包括一个……”限定的要素,并不排除在包括该要素的过程、方法、物品或者装置中还存在另外的相同要素。It should be noted that, herein, the terms "comprising", "comprising" or any other variation thereof are intended to encompass non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements, It also includes other elements not expressly listed or inherent to such a process, method, article or apparatus. Without further limitation, an element qualified by the phrase "comprising a..." does not preclude the presence of additional identical elements in a process, method, article or apparatus that includes the element.
上述本公开实施例序号仅仅为了描述,不代表实施例的优劣。The above-mentioned serial numbers of the embodiments of the present disclosure are only for description, and do not represent the advantages or disadvantages of the embodiments.
通过以上的实施方式的描述,本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现,当然也可以通过硬件,但很多情况下前者是更佳的实施方式。基于这样的理解,本公开的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来,该计算机软件产品存储在一个存储介质(如ROM/RAM、磁碟、光盘)中,包括若干指令用以使得一台终端(可以是手机,计算机,服务器,空调器,或者网络设备等)执行本公开各个实施例所述的方法。From the description of the above embodiments, those skilled in the art can clearly understand that the method of the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is better implementation. Based on this understanding, the technical solutions of the present disclosure essentially or the parts that contribute to the prior art can be embodied in the form of software products, and the computer software products are stored in a storage medium (such as ROM/RAM, magnetic disk, CD-ROM), including several instructions to make a terminal (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) execute the methods described in the various embodiments of the present disclosure.
上面结合附图对本公开的实施例进行了描述,但是本公开并不局限于上述的具体实施方式,上述的具体实施方式仅仅是示意性的,而不是限制性的,本领域的普通技术人员在本公开的启示下,在不脱离本公开宗旨和权利要求所保护的范围情况下,还可做出很多形式,这些均属于本公开的保护之内。The embodiments of the present disclosure have been described above in conjunction with the accompanying drawings, but the present disclosure is not limited to the above-mentioned specific embodiments, which are merely illustrative rather than restrictive. Under the inspiration of the present disclosure, many forms can be made without departing from the scope of the present disclosure and the protection scope of the claims, which all fall within the protection of the present disclosure.
Claims (10)
- WIFI信道分配方法,其包括:A WIFI channel allocation method, which includes:在接收到任一电子终端的上网请求时,确定所述上网请求对应的先验上网时间段;When receiving an Internet access request from any electronic terminal, determining a prior Internet access time period corresponding to the Internet access request;根据所述电子终端的先验上网时间段,确定所述电子终端在所述先验上网时间段对应的第一优先级;determining the first priority of the electronic terminal corresponding to the prior Internet access time period of the electronic terminal according to the prior Internet access time period of the electronic terminal;根据所述电子终端的所属类别,确定所述电子终端对应的第二优先级;determining a second priority corresponding to the electronic terminal according to the category to which the electronic terminal belongs;根据所述电子终端的所述第一优先级和所述第二优先级,确定所述电子终端的总优先级;以及determining an overall priority of the electronic terminal according to the first priority and the second priority of the electronic terminal; and根据所述总优先级,为所述电子终端分配对应的WIFI子信道。According to the total priority, a corresponding WIFI sub-channel is allocated to the electronic terminal.
- 如权利要求1所述的方法,其中,采用第一公式计算所述总优先级,所述第一公式包括:The method of claim 1, wherein the overall priority is calculated using a first formula, the first formula comprising:式中,G为所述总优先级,g 1为所述第一优先级,g 2为所述第二优先级, 和γ为平衡参数, 取第一优先级的数量的倒数,γ取第二优先级的数量的倒数。 In the formula, G is the total priority, g 1 is the first priority, g 2 is the second priority, and γ are the equilibrium parameters, Take the reciprocal of the number of the first priority, and γ to take the reciprocal of the number of the second priority.
- 如权利要求1或2所述的方法,其还包括:根据预先训练的预测模型,确定所述电子终端在所述先验上网时间段的预测数据传输总量;以及The method according to claim 1 or 2, further comprising: determining, according to a pre-trained prediction model, the total amount of predicted data transmission of the electronic terminal in the prior Internet access time period; and所述根据所述总优先级,为所述电子终端分配对应的WIFI子信道,包括:The assigning a corresponding WIFI sub-channel to the electronic terminal according to the total priority includes:根据所述预测数据传输总量,确定电子设备从接收到上网请求的时刻到所述先验上网时间段的终点时刻的预测数据传输分量;以及According to the total amount of predicted data transmission, determine the predicted data transmission component of the electronic device from the moment of receiving the Internet access request to the end time of the prior Internet access time period; and根据所述总优先级和所述预测数据传输分量,为所述电子终端分配对应的WIFI子信道。According to the total priority and the predicted data transmission component, a corresponding WIFI sub-channel is allocated to the electronic terminal.
- 如权利要求3所述的方法,其中,所述根据所述总优先级和所述预测数据传输分量,为所述电子终端分配对应的WIFI子信道,包括:The method according to claim 3, wherein the assigning the corresponding WIFI sub-channel to the electronic terminal according to the total priority and the predicted data transmission component comprises:根据所述总优先级,确定所述电子终端的初始子信道;以及determining an initial sub-channel for the electronic terminal based on the overall priority; and根据所述预测数据传输分量,对所述初始子信道进行调整,得到目标子信道,若所述预测数据传输分量大于传输量阈值分量,则对初始子信道进行邻近扩增,得到所述目标子信道,否则,对初始子信道进行邻近缩减,得到所述目标子信道;According to the predicted data transmission component, the initial sub-channel is adjusted to obtain the target sub-channel. If the predicted data transmission component is greater than the transmission amount threshold component, adjacent amplification is performed on the initial sub-channel to obtain the target sub-channel. channel, otherwise, perform proximity reduction on the initial sub-channel to obtain the target sub-channel;其中,所述传输量阈值分量为传输量阈值的分量,所述传输量阈值分量与所述传输量阈值的比值等于所述预测数据传输分量与所述预测数据传输总量的比值。The transmission volume threshold component is a transmission volume threshold component, and the ratio of the transmission volume threshold component to the transmission volume threshold is equal to the ratio of the predicted data transmission component to the predicted data transmission total.
- 如权利要求3或4所述的方法,其中,所述预测模型的预先训练过程包括:The method of claim 3 or 4, wherein the pre-training process of the prediction model comprises:获取家庭组网内各个电子终端的历史上网信息,所述历史上网信息包括各个终端在预设历史时期内的各个上网时间段和每一个上网时间段内的各条数据传输信息;Obtaining the historical Internet access information of each electronic terminal in the home network, the historical Internet access information includes each Internet access time period of each terminal within a preset historical period and each piece of data transmission information within each Internet access time period;采用预设聚类算法,对每一个电子终端的各个上网时间段进行聚类,得到每一个电子终端的多个先验上网时间段;Using a preset clustering algorithm, cluster each Internet access time period of each electronic terminal to obtain a plurality of prior Internet access time periods of each electronic terminal;标记每一个先验上网时间段中每一条数据传输信息的数据传输量,将每一个先验上网时间段中标记有数据传输量的每一条数据传输信息作为一个训练样本,构建训练样本集;以及Marking the data transmission amount of each piece of data transmission information in each prior Internet access time period, and using each piece of data transmission information marked with the data transmission amount in each prior Internet Internet time period as a training sample to construct a training sample set; and根据所述训练样本集进行模型训练,得到所述预测模型。Perform model training according to the training sample set to obtain the prediction model.
- 如权利要求5所述的方法,其中,在根据所述训练样本集进行模型训练的过程中,采用第二公式对训练样本进行损失计算,所述第二公式包括:The method according to claim 5, wherein, in the process of model training according to the training sample set, a second formula is used to calculate the loss of the training samples, and the second formula includes:式中,L为每一个电子模块的每一个先验上网时间段对应的预测模型的总损失,α和β为预设平衡参数,N cls是训练所述预测模型所需的所 有训练样本中正样本的数量,L cls()为第一损失函数,y 1i是为第i个正样本预先标记的数据传输量,N reg为训练所述预测模型所需的所有训练样本中负样本的数量,L reg()为第二损失函数,y 2i为第i个负样本预先标记的数据传输量,y *为所述预测模型输出的预测数据传输总量与所述所有训练样本的数量的比值。 In the formula, L is the total loss of the prediction model corresponding to each prior online time period of each electronic module, α and β are preset balance parameters, and N cls is the positive sample in all training samples required to train the prediction model. The number of , L cls ( ) is the first loss function, y 1i is the pre-labeled data transfer amount for the ith positive sample, N reg is the number of negative samples in all training samples required to train the prediction model, L reg ( ) is the second loss function, y 2i is the pre-labeled data transmission amount of the ith negative sample, and y * is the ratio of the total amount of predicted data transmission output by the prediction model to the number of all training samples.
- 如权利要求6所述的方法,其中,所述正样本和所述负样本的分类过程包括:The method of claim 6, wherein the process of classifying the positive samples and the negative samples comprises:针对每一个电子终端的每一个先验上网时间段内的所有训练样本,按照预先标记的数据传输量从低到高进行排序,得到每一个先验上网时间段对应的传输量序列;For all training samples in each prior Internet access time period of each electronic terminal, sort the data transmission volume from low to high according to the pre-marking, and obtain the transmission volume sequence corresponding to each a priori Internet access time segment;从所述传输量序列中选取第一数据传输量、第二数据传输量和第三数据传输量,所述第一数据传输量为所述传输量序列中1/4位置处的数据传输量,所述第二数据传输量为所述传输量序列中1/2位置处的数据传输量,所述第三数据传输量为所述传输量序列中3/4位置处的数据传输量;The first data transmission amount, the second data transmission amount and the third data transmission amount are selected from the transmission amount sequence, and the first data transmission amount is the data transmission amount at the 1/4 position in the transmission amount sequence, The second data transmission volume is the data transmission volume at the 1/2 position in the transmission volume sequence, and the third data transmission volume is the data transmission volume at the 3/4 position in the transmission volume sequence;根据所述第一数据传输量、所述第二数据传输量和所述第三数据传输量,设置每一个电子终端的每一个先验上网时间段对应的正样本区间;以及According to the first data transmission amount, the second data transmission amount and the third data transmission amount, setting a positive sample interval corresponding to each a priori Internet access time period of each electronic terminal; and判断每一个电子终端的每一个先验上网时间段对应的每一个训练样本预先标记的数据传输量是否落在正样本区间内;若是,则该训练样本为正样本;否则,该训练样本为负样本。Determine whether the pre-marked data transmission amount of each training sample corresponding to each prior Internet access time period of each electronic terminal falls within the positive sample interval; if so, the training sample is a positive sample; otherwise, the training sample is negative sample.
- 如权利要求7所述的方法,其中,采用第三公式求计算所述正样本区间H,所述第三公式包括:The method according to claim 7, wherein the positive sample interval H is calculated using a third formula, and the third formula comprises:
- 如权利要求8所述的方法,其中,所述区间宽度调节参数的选 取方法包括:The method of claim 8, wherein the selection method of the interval width adjustment parameter comprises:设置区间宽度调节参数 从0开始逐步增加,当 增加到所述传输量序列中至少90%的数据传输量落在预设区间 内时, 停止增加,将此时的 选取出来用于计算第三公式,其中,δ为所述传输量序列的标准差。 Set interval width adjustment parameters Gradually increase from 0, when At least 90% of the data transmission volume added to the transmission volume sequence falls within the preset interval inside, stop increasing, set the It is selected and used to calculate the third formula, where δ is the standard deviation of the transmission quantity sequence.
- 计算机设备,包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序,其中,所述处理器执行所述计算机程序时实现权利要求1至9中任一权利要求所述方法。Computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any one of claims 1 to 9 when executing the computer program .
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011563246.1A CN112738895B (en) | 2020-12-25 | 2020-12-25 | WIFI channel allocation method and device |
CN202011563246.1 | 2020-12-25 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2022135089A1 true WO2022135089A1 (en) | 2022-06-30 |
Family
ID=75616221
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2021/134858 WO2022135089A1 (en) | 2020-12-25 | 2021-12-01 | Wifi channel allocation method and device |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN112738895B (en) |
WO (1) | WO2022135089A1 (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116981018A (en) * | 2023-09-25 | 2023-10-31 | 杭州斯诺康技术有限公司 | Method for automatically connecting intelligent equipment with router |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115175272B (en) * | 2022-06-06 | 2023-05-26 | 烽火通信科技股份有限公司 | Wireless terminal networking method and device based on family multi-WIFI |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1409937A (en) * | 1999-12-15 | 2003-04-09 | 诺基亚公司 | Dynamic channel allocation method based on priority |
CN110352584A (en) * | 2016-12-28 | 2019-10-18 | 谷歌有限责任公司 | Across the automatic priority ranking of the equipment flow of local network |
EP3706402A1 (en) * | 2019-03-04 | 2020-09-09 | Avaya Inc. | Priority reconnection of dropped nodes from a network |
CN111776896A (en) * | 2019-11-18 | 2020-10-16 | 北京京东尚科信息技术有限公司 | Elevator dispatching method and device |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106126597A (en) * | 2016-06-20 | 2016-11-16 | 乐视控股(北京)有限公司 | User property Forecasting Methodology and device |
CN111010695A (en) * | 2019-12-12 | 2020-04-14 | 国网新疆电力有限公司信息通信公司 | Channel allocation method based on channel idle time prediction |
-
2020
- 2020-12-25 CN CN202011563246.1A patent/CN112738895B/en active Active
-
2021
- 2021-12-01 WO PCT/CN2021/134858 patent/WO2022135089A1/en active Application Filing
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1409937A (en) * | 1999-12-15 | 2003-04-09 | 诺基亚公司 | Dynamic channel allocation method based on priority |
CN110352584A (en) * | 2016-12-28 | 2019-10-18 | 谷歌有限责任公司 | Across the automatic priority ranking of the equipment flow of local network |
EP3706402A1 (en) * | 2019-03-04 | 2020-09-09 | Avaya Inc. | Priority reconnection of dropped nodes from a network |
CN111776896A (en) * | 2019-11-18 | 2020-10-16 | 北京京东尚科信息技术有限公司 | Elevator dispatching method and device |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116981018A (en) * | 2023-09-25 | 2023-10-31 | 杭州斯诺康技术有限公司 | Method for automatically connecting intelligent equipment with router |
CN116981018B (en) * | 2023-09-25 | 2024-02-13 | 杭州斯诺康技术有限公司 | Method for automatically connecting intelligent equipment with router |
Also Published As
Publication number | Publication date |
---|---|
CN112738895A (en) | 2021-04-30 |
CN112738895B (en) | 2022-10-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2022135089A1 (en) | Wifi channel allocation method and device | |
Sun et al. | Multi-objective optimization of resource scheduling in fog computing using an improved NSGA-II | |
CN108449286B (en) | Network bandwidth resource allocation method and device | |
WO2022095620A1 (en) | Smart power grid-based heterogeneous network access selection method and related device | |
US9747201B2 (en) | Methods and systems for managing memory allocation | |
EP2822236B1 (en) | Network bandwidth distribution method and terminal | |
US20160359725A1 (en) | Method and System to Represent the Impact of Load Variation on Service Outage Over Multiple Links | |
US20050193113A1 (en) | Server allocation control method | |
US10579422B2 (en) | Latency-managed task processing | |
CN109144730B (en) | Task unloading method and device under small cell | |
CN110380881B (en) | Network capacity expansion prediction method and device | |
CN111752706B (en) | Resource allocation method, device and storage medium | |
CN112579194A (en) | Block chain consensus task unloading method and device based on time delay and transaction throughput | |
Wang et al. | Data analysis on video streaming QoE over mobile networks | |
CN112383485B (en) | Network congestion control method and device | |
CN110582072A (en) | Fuzzy matching-based resource allocation method and device in cellular internet of vehicles | |
US10390364B2 (en) | Apparatus and method for dynamically controlling spectrum access | |
CN107948084B (en) | Current limiting method and device | |
CN112668877A (en) | Thing resource information distribution method and system combining federal learning and reinforcement learning | |
Zhao et al. | Performance analysis and optimization for cognitive radio networks with classified secondary users and impatient packets | |
CN113438098B (en) | Time delay sensitive virtual network mapping method and device in cloud data center | |
CN111124439A (en) | Intelligent dynamic unloading algorithm with cloud edge cooperation | |
CN111278039B (en) | User perception suppression identification method, device, equipment and medium | |
CN116128132A (en) | Power consumption prediction method, device, equipment and medium | |
CN113297152B (en) | Method and device for updating cache of edge server of power internet of things |
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: 21909087 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 21909087 Country of ref document: EP Kind code of ref document: A1 |