CN109951859B - Wireless network connection recommendation method and device, electronic equipment and readable medium - Google Patents
Wireless network connection recommendation method and device, electronic equipment and readable medium Download PDFInfo
- Publication number
- CN109951859B CN109951859B CN201910226151.1A CN201910226151A CN109951859B CN 109951859 B CN109951859 B CN 109951859B CN 201910226151 A CN201910226151 A CN 201910226151A CN 109951859 B CN109951859 B CN 109951859B
- Authority
- CN
- China
- Prior art keywords
- attribute
- scores
- wireless network
- wireless networks
- connection
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Landscapes
- Mobile Radio Communication Systems (AREA)
Abstract
The disclosure relates to a wireless network connection recommendation method and device, electronic equipment and a computer readable medium. The method comprises the following steps: acquiring network information of a plurality of wireless networks according to a user instruction, wherein the network information comprises network identifiers and signal intensity; determining a plurality of attribute scores for the plurality of wireless networks based on the network identification; determining a plurality of environmental scores for the plurality of wireless networks based on the signal strengths; determining a plurality of connection quality scores for the plurality of wireless networks from the plurality of attribute scores and the plurality of environmental scores; and making a wireless network connection recommendation based on the plurality of connection quality scores. The wireless network connection recommendation method, the wireless network connection recommendation device, the electronic equipment and the computer readable medium can recommend available wireless network resources with high success rate and high internet access rate for the user.
Description
Technical Field
The present disclosure relates to the field of computer information processing, and in particular, to a wireless network connection recommendation method and apparatus, an electronic device, and a computer-readable medium.
Background
With the popularization and abundance of network resources, users have more and more demands on the network, and the wireless network has wide user demand space because the wireless network is not limited by space and region in the using process. Currently, when a user needs to use wireless network resources at any place, a device detects and simultaneously searches for a large amount of wireless network resources. How to quickly and accurately determine an available wireless network resource from a large amount of wireless network resources and obtain high-quality network services is a problem to be solved at present.
Therefore, a new wireless network connection recommendation method, apparatus, electronic device and computer readable medium are needed.
The above information disclosed in this background section is only for enhancement of understanding of the background of the disclosure and therefore it may contain information that does not constitute prior art that is already known to a person of ordinary skill in the art.
Disclosure of Invention
In view of the above, the present disclosure provides a method and an apparatus for recommending wireless network connection, an electronic device, and a computer readable medium, which can recommend available wireless network resources with high success rate and high internet access rate for a user.
Additional features and advantages of the disclosure will be set forth in the detailed description which follows, or in part will be obvious from the description, or may be learned by practice of the disclosure.
According to an aspect of the present disclosure, a method for recommending wireless network connection is provided, the method including: acquiring network information of a plurality of wireless networks according to a user instruction, wherein the network information comprises network identifiers and signal intensity; determining a plurality of attribute scores for the plurality of wireless networks based on the network identification; determining a plurality of environmental scores for the plurality of wireless networks based on the signal strengths; determining a plurality of connection quality scores for the plurality of wireless networks from the plurality of attribute scores and the plurality of environmental scores; and making a wireless network connection recommendation based on the plurality of connection quality scores.
In an exemplary embodiment of the disclosure, determining a plurality of attribute scores for the plurality of wireless networks based on the network identification comprises: determining a plurality of attribute scores for the plurality of wireless networks through an online dataset based on the network identification; and determining a plurality of attribute scores for the plurality of wireless networks through an offline dataset based on the network identification.
In an exemplary embodiment of the present disclosure, determining a plurality of attribute scores for the plurality of wireless networks through an online dataset based on the network identification further comprises: and acquiring the online data set based on network information and attribute grading models of a plurality of wireless networks.
In an exemplary embodiment of the present disclosure, further comprising: acquiring basic attribute logs and connection behavior logs of a plurality of wireless networks; allocating basic attribute logs corresponding to the plurality of wireless networks into a positive sample set and a negative sample set based on the connection behavior log; and training a machine learning model through the set of positive samples and the set of negative samples to determine the attribute scoring model.
In an exemplary embodiment of the present disclosure, assigning the basic attribute logs corresponding to the plurality of wireless networks to a positive sample set and a negative sample set based on the connection behavior log comprises: acquiring the connection success rate and the internet access rate in the connection behavior log; and distributing the basic attribute logs corresponding to the wireless networks to a positive sample set and a negative sample set through the connection success rate and the internet access rate.
In an exemplary embodiment of the present disclosure, training a machine learning model to determine the attribute scoring model by the set of positive samples and the set of negative samples comprises: determining a model structure and a model depth of a random forest model; using a kini coefficient as a loss function of the random forest model; and inputting the positive sample set and the negative sample set into the set random forest model for training to determine the attribute scoring model.
In an exemplary embodiment of the present disclosure, the obtaining the online data set based on a network information and attribute scoring model of a plurality of wireless networks comprises: extracting a multi-dimensional characteristic data set from a basic attribute log and a connection behavior log of a wireless network; inputting a plurality of multi-dimensional feature data sets corresponding to a plurality of wireless networks into the attribute scoring model to obtain a plurality of initial scores; comparing the plurality of initial scores with predetermined scores to generate a plurality of attribute scores; and generating the online data set through the network identifications of the plurality of wireless networks and the attribute scores corresponding to the network identifications.
In an exemplary embodiment of the present disclosure, before comparing the plurality of initial scores with the predetermined scores to generate the plurality of attribute scores, further comprises: carrying out generalized power transformation processing on the plurality of initial scores to generate a plurality of target scores; calculating a mean and a variance of the plurality of target scores; and generating the predetermined scoring interval by the mean and the variance.
In an exemplary embodiment of the present disclosure, determining a plurality of connection quality scores for the plurality of wireless networks from the plurality of attribute scores and the plurality of environmental scores comprises: determining an attribute scoring weight and an environment scoring weight based on the historical attribute score and the historical environment score; and determining a plurality of connection quality scores for the plurality of wireless networks from the plurality of attribute scores, the attribute score weights, and the plurality of environmental scores, the environmental score weights.
In an exemplary embodiment of the present disclosure, determining the attribute scoring weights and the environmental scoring weights based on the historical attribute scores and the historical environmental scores comprises: determining an attribute scoring weight and an environment scoring weight based on a gray testing mode, historical attribute scoring and historical environment scoring; and determining an attribute scoring weight and an environment scoring weight based on the logistic regression mode and the historical attribute scoring and the historical environment scoring.
In an exemplary embodiment of the present disclosure, a wireless network connection recommendation apparatus is provided, the apparatus including: the network information module is used for acquiring network information of a plurality of wireless networks according to a user instruction, wherein the network information comprises network identifiers and signal intensity; an attribute scoring module to determine a plurality of attribute scores for the plurality of wireless networks based on the network identification; an environmental scoring module to determine a plurality of environmental scores for the plurality of wireless networks based on the signal strength; a quality scoring module to determine a plurality of connection quality scores for the plurality of wireless networks from the plurality of attribute scores and the plurality of environmental scores; and the connection recommending module is used for recommending wireless network connection based on the plurality of connection quality scores.
According to an aspect of the present disclosure, an electronic device is provided, the electronic device including: one or more processors; storage means for storing one or more programs; when executed by one or more processors, cause the one or more processors to implement a method as above.
According to an aspect of the disclosure, a computer-readable medium is proposed, on which a computer program is stored, which program, when being executed by a processor, carries out the method as above.
According to the wireless network connection recommendation method, the wireless network connection recommendation device, the electronic equipment and the computer readable medium, the wireless network connection quality score is determined through the attribute score and the signal score of the wireless network, and the available wireless network resources with high success rate and high internet access rate can be recommended for the user in a network recommendation mode for the user based on the connection quality score.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The above and other objects, features and advantages of the present disclosure will become more apparent by describing in detail exemplary embodiments thereof with reference to the attached drawings. The drawings described below are merely some embodiments of the present disclosure, and other drawings may be derived from those drawings by those of ordinary skill in the art without inventive effort.
Fig. 1 is a system scenario block diagram illustrating a wireless network connection recommendation method and apparatus according to an example embodiment.
Fig. 2 is a block diagram illustrating an application scenario of a wireless network connection recommendation method and apparatus according to an exemplary embodiment.
Fig. 3 is a flow chart illustrating a method of wireless network connection recommendation in accordance with an example embodiment.
Fig. 4 is a flowchart illustrating a wireless network connection recommendation method according to another example embodiment.
Fig. 5 is a diagram illustrating a wireless network connection recommendation method according to another example embodiment.
Fig. 6 is a flow chart illustrating a method of wireless network connection recommendation in accordance with another example embodiment.
Fig. 7 is a block diagram illustrating a wireless network connection recommendation apparatus according to an example embodiment.
FIG. 8 is a block diagram illustrating an electronic device in accordance with an example embodiment.
FIG. 9 is a schematic diagram illustrating a computer-readable storage medium according to an example embodiment.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art. The same reference numerals denote the same or similar parts in the drawings, and thus, a repetitive description thereof will be omitted.
Furthermore, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the disclosure. One skilled in the relevant art will recognize, however, that the subject matter of the present disclosure can be practiced without one or more of the specific details, or with other methods, components, devices, steps, and so forth. In other instances, well-known methods, devices, implementations, or operations have not been shown or described in detail to avoid obscuring aspects of the disclosure.
The block diagrams shown in the figures are functional entities only and do not necessarily correspond to physically separate entities. I.e. these functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor means and/or microcontroller means.
The flow charts shown in the drawings are merely illustrative and do not necessarily include all of the contents and operations/steps, nor do they necessarily have to be performed in the order described. For example, some operations/steps may be decomposed, and some operations/steps may be combined or partially combined, so that the actual execution sequence may be changed according to the actual situation.
It will be understood that, although the terms first, second, third, etc. may be used herein to describe various components, these components should not be limited by these terms. These terms are used to distinguish one element from another. Thus, a first component discussed below may be termed a second component without departing from the teachings of the disclosed concept. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
It is to be understood by those skilled in the art that the drawings are merely schematic representations of exemplary embodiments, and that the blocks or processes shown in the drawings are not necessarily required to practice the present disclosure and are, therefore, not intended to limit the scope of the present disclosure.
Fig. 1 is a system scenario block diagram illustrating a wireless network connection recommendation method and apparatus according to an example embodiment.
As shown in fig. 1, the system architecture 100 may include user devices 101, 102, 103, a network 104 and a server 105, network devices 106, 107, 108. The network 104 is used to provide a medium for communication links between the user devices 101, 102, 103 and the server 105, network devices 106, 107, 108. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
A user may use the user devices 101, 102, 103 to interact with the server 105 over the network 104 to receive or send messages or the like. The user devices 101, 102, 103 may have installed thereon various communication client applications, such as shopping-like applications, web browser applications, search-like applications, instant messaging tools, mailbox clients, social platform software, and the like. More specifically, in the embodiments of the present disclosure, a user may be assisted in performing a wireless network connection operation through a predetermined APP application.
The user devices 101, 102, 103 may be various electronic devices having display screens and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.
The network devices 106, 107, 108 are devices that can provide wireless network connection, and after the user connects with the network devices 106, 107, 108 through the user devices 101, 102, 103, the network data transmission operation can be performed through the network devices 106, 107, 108.
The user equipment 101, 102, 103 may for example obtain network information of the network devices 106, 107, 108, the network information comprising network identification and signal strength; the user devices 101, 102, 103 may determine a plurality of attribute scores for the network devices 106, 107, 108, e.g., based on the network identification; the user devices 101, 102, 103 may determine a plurality of environmental scores for the network devices 106, 107, 108, e.g., based on the signal strengths; the user device 101, 102, 103 may determine a plurality of connection quality scores for the network device 106, 107, 108, e.g., by the plurality of attribute scores and the plurality of environment scores; the user devices 101, 102, 103 may make wireless network connection recommendations, for example, based on the plurality of connection quality scores.
The server 105 may be a server providing various services, such as a background server that processes connection requests submitted by users via the user devices 101, 102, 103. The server 105 may perform processing such as analysis on network performance of the network devices 106, 107, 108, and feed back a processing result to the user device.
The server 105 may obtain network information of a plurality of wireless networks, for example, according to a user instruction, the network information including network identification and signal strength; the server 105 may determine a plurality of attribute scores for the network devices 106, 107, 108, e.g., based on the network identification; the server 105 may determine a plurality of environmental scores for the network devices 106, 107, 108, e.g., based on the signal strengths; the server 105 may determine a plurality of connection quality scores for the network devices 106, 107, 108, e.g., by the plurality of attribute scores and the plurality of environmental scores; the server 105 may make a wireless network connection recommendation, for example, based on the plurality of connection quality scores.
The server 105 may be a server of one entity, and may also be composed of a plurality of servers, for example, it should be noted that the wireless network connection recommendation method provided by the embodiment of the present disclosure may be executed by the server 105 and/or the user equipment 101, 102, 103, and accordingly, the wireless network connection recommendation apparatus may be disposed in the server 105 and/or the user equipment 101, 102, 103.
According to the wireless network connection recommendation method and device, the wireless network connection quality score is determined through the attribute score and the signal score of the wireless network, and the network recommendation mode is performed for the user based on the connection quality score, so that the available wireless network resources with high success rate and high internet access rate can be recommended for the user.
Fig. 2 is a block diagram illustrating an application scenario of a wireless network connection recommendation method and apparatus according to an exemplary embodiment. In the embodiment of the disclosure, the user can be assisted in wireless network (WiFi) connection operation through a predetermined APP application. As shown in fig. 2, when a user wants to obtain wireless network resources for wireless network connection, an attempt is made by the user equipment to connect to the network using a predetermined APP application. The user requests wireless network connection through the APP, and the user equipment identifies the plurality of wireless network devices. The user equipment can obtain the connection quality scores of the wireless network equipment by adopting different strategies according to the network connection state of the current equipment per se, and the connection quality scores are displayed to the user in a sequencing mode according to the connection quality score grades corresponding to the wireless equipment.
In the embodiment of the present disclosure, the connection quality corresponding to the wireless device may be defined as the capability of each wireless device to be successfully connected by the user's attempt.
After the recommendation of wireless network connection is made, the user can click to connect WiFi according to a preset wireless network equipment list provided by APP. According to the method and the device, the connection quality of the wireless network equipment is graded, and the arrangement sequence of the wireless network equipment list in the preset APP display interface is changed, so that the best connectable wireless network is recommended to the user, the use experience of the user is improved, and the retention of the user is increased.
Fig. 3 is a flow chart illustrating a method of wireless network connection recommendation in accordance with an example embodiment. The wireless network connection recommendation method 30 includes at least steps S302 to S310.
As shown in fig. 3, in S302, network information of a plurality of wireless networks is obtained according to a user instruction, and the network information includes network identifiers and signal strengths. As shown in fig. 2, the user may send a predetermined instruction, for example, on a predetermined APP, which may be to request a wireless network connection from a wireless network device in the vicinity of the user.
In one embodiment, network information for a plurality of wireless networks in the vicinity of the user may be obtained according to the user instruction. The network identifier in the network information may be a hardware number, a physical address, or the like of the wireless device, and may uniquely determine the identifier of the wireless device, and the signal strength in the network information is the current wireless signal strength of the wireless device.
In S304, a plurality of attribute scores for the plurality of wireless networks are determined based on the network identifications.
In one embodiment, determining a plurality of attribute scores for the plurality of wireless networks based on the network identification comprises: determining a plurality of attribute scores for the plurality of wireless networks through an online dataset based on the network identification. For example, when the user equipment has a network connection state, the user equipment initiates a request to the background server, and obtains attribute scores corresponding to a plurality of wireless networks through the online data set at the server.
In one embodiment, obtaining the online data set based on a network information and attribute scoring model for a plurality of wireless networks comprises: extracting a multi-dimensional characteristic data set from a basic attribute log and a connection behavior log of a wireless network; inputting a plurality of multi-dimensional feature data sets corresponding to a plurality of wireless networks into the attribute scoring model to obtain a plurality of initial scores; comparing the plurality of initial scores with predetermined scores to generate a plurality of attribute scores; and generating the online data set through the network identifications of the plurality of wireless networks and the attribute scores corresponding to the network identifications. The process of acquiring the online data set will be described in detail in the embodiment corresponding to fig. 6.
Wherein, still include: and acquiring the online data set based on network information and attribute grading models of a plurality of wireless networks. The obtaining process of the scoring model will be described in detail in the embodiment corresponding to fig. 4.
In one embodiment, determining a plurality of attribute scores for the plurality of wireless networks based on the network identification comprises: determining a plurality of attribute scores for the plurality of wireless networks through an offline dataset based on the network identification. For example, when the user equipment has no network connection state, the offline data set can be used for identification, the current multiple wireless network devices are matched with the wireless network devices in the offline data set, after matching, the attribute scores given by the background in the offline packet can be used, and if not matching, the wireless device can be set with a default score value.
In the embodiment of the disclosure, the online data set and the offline data set can be wireless network attribute scores calculated by the same method; the online data set contains an offline data set, which may be, for example, information such as wireless network attribute scores, etc., that are present in small and relatively high frequency in the online data set, and which may be consolidated in the user device.
More specifically, when the user is in a network connection state, the user equipment can be connected to the online data set through the network and get the attribute score of the wireless network; when the user is in a wireless network connection state, the user equipment cannot be connected with the online data set, and only the offline data set can be matched from the mobile phone storage of the user equipment, so that the attribute score of the wireless network is obtained.
In S306, a plurality of environmental scores for the plurality of wireless networks are determined based on the signal strengths. The connection environment of the wireless network equipment is complex and variable, and the connection quality of the wireless network equipment is mainly influenced by the current signal level of the wireless network equipment and other transient changes. The method is limited by the instantaneous information acquisition limit of the wireless network equipment, the response speed requirement of a client and the like in the current log table, and the instantaneous signal score of the wireless network equipment in the current environment is calculated by taking the current signal value of the wireless network equipment as the connection environment characteristic of the wireless network equipment. May for example be: and evenly dividing the instantaneous signal value of the wireless network equipment from 0 to 100 points to 6 points, and obtaining a signal score of 1 to 6 points as an environment score of the wireless network equipment in the current environment.
In S308, a plurality of connection quality scores for the plurality of wireless networks is determined from the plurality of attribute scores and the plurality of environment scores. Attribute scoring weights and environmental scoring weights may be determined, for example, based on historical attribute scores and historical environmental scores; and determining a plurality of connection quality scores for the plurality of wireless networks from the plurality of attribute scores, the attribute score weights, and the plurality of environmental scores, the environmental score weights.
In one embodiment, determining the attribute scoring weights and the environmental scoring weights based on the historical attribute scores and the historical environmental scores comprises: determining an attribute scoring weight and an environment scoring weight based on a gray testing mode, historical attribute scoring and historical environment scoring; and determining an attribute scoring weight and an environment scoring weight based on the logistic regression mode and the historical attribute scoring and the historical environment scoring.
The quality of the wireless device connection is affected by the current connection environment, in addition to the long-term property of the wireless device. Therefore, in order to fully consider the factors of the two aspects, the wireless network device attribute score and the wireless network device environment score of the background are combined to give a final wireless network device connection quality grade, and recommended connection is carried out in a preset APP.
In one embodiment, a set of weighted values corresponding to the attribute scores of the background server and the current environment scores of the wireless network devices received by the user equipment terminal respectively may be empirically given, and then a large number of attest gray tests are performed to select the optimal weighted proportion.
In one embodiment, the weights may also be selected by a logistic regression model to give a final wireless network device connection quality score.
In one embodiment, in the environment scoring calculation of the wireless network device of the user equipment part, when other instantaneous environment characteristics, such as current routing request access and other information acquisition are completed, a new model can be constructed for scoring according to the online environment requirements.
In one embodiment, more specifically, a weight value of 0.3-0.5 is assigned to the attribute score and a weight value of 0.5-0.7 is assigned to the environment score, and the connection quality score is calculated.
In S310, a wireless network connection recommendation is made based on the plurality of connection quality scores. The plurality of wireless network devices can be sequentially arranged from high to low according to the connection quality scores corresponding to the plurality of wireless network devices so as to recommend connection.
According to the wireless network connection recommendation method, an algorithm for determining the wireless network device connection quality score is generated according to the characteristics of the wireless network device connection quality, the algorithm can be executed by a background server and a user equipment terminal, and the background server part can be a wireless network device attribute score model and an attribute score and environment score weight calculation model which are constructed according to the long-term attribute characteristics of the wireless network device.
On the user equipment side, a small-sized calculation model of the current environment score of the wireless network equipment can be constructed. The wireless network connection recommendation method comprehensively considers long-term and static attributes and connection characteristics of wireless network equipment and instantaneous environment characteristics under current connection, obtains the most reasonable wireless network equipment connection quality score grade by adopting the optimal weighting proportion, thereby determining the display sequence of a wireless network equipment list at a user equipment end and preferentially displaying the high-quality connectable wireless network equipment obtained by calculation.
It should be clearly understood that this disclosure describes how to make and use particular examples, but the principles of this disclosure are not limited to any details of these examples. Rather, these principles can be applied to many other embodiments based on the teachings of the present disclosure.
Fig. 4 is a flowchart illustrating a wireless network connection recommendation method according to another example embodiment. The flow shown in fig. 4 is a detailed description of "obtaining the online data set based on the network information and attribute scoring models of multiple wireless networks".
As shown in fig. 4, in S402, a basic attribute log and a connection behavior log of a plurality of wireless networks are acquired. The attribute scoring model of the wireless network device may be obtained by the following steps. Firstly, training sample construction needs to meet the differentiability of positive and negative samples, the trainable capacity of the samples, the diversity and sufficiency of the behavior characteristics of the samples and the like. In order to achieve the above characteristics, the present disclosure obtains a plurality of basic attribute logs and connection behavior logs of a wireless network, and analyzes the connection behavior logs of the wireless network device.
In S404, basic attribute logs corresponding to the plurality of wireless networks are allocated into a positive sample set and a negative sample set based on the connection behavior log. For example, the connection success rate and the internet access rate in the connection behavior log are obtained; and distributing the basic attribute logs corresponding to the wireless networks to a positive sample set and a negative sample set through the connection success rate and the internet access rate.
In the wireless network device connection quality scoring problem, the wireless network device with high connection power can be used as a positive sample, and the wireless network device with low connection success rate can be used as a negative sample. As shown in fig. 5 (a), in order to make the positive and negative samples more distinctive and representative, positive samples and negative samples with a power greater than 0.9 and less than 0.2 may be defined. Meanwhile, as the wireless network device is not necessarily capable of surfing the internet after successful connection, in order to search for a higher-quality wireless network device, the internet access rate is also introduced in the disclosure, as shown in (b) in fig. 2, the wireless network device with the internet access rate higher than 0.7 is regarded as a high-quality wireless network device, and the wireless network device with the internet access rate lower than 0.1 is regarded as a low-quality wireless network device.
After the training samples are determined, in order to obtain the characteristics which can fully embody the connection quality of the wireless network equipment, 58-dimensional characteristics can be obtained by extracting and converting from the basic attribute log of the wireless network equipment and the connection behavior log of the wireless network equipment. In the basic attribute log of the wireless network equipment, the fixed and unchangeable attribute characteristics of the wireless network equipment, such as the type of the wireless network equipment, the business circle attribute, the channel attribute, the password attribute and the like, can be extracted.
The wireless network device type mainly refers to whether the wireless network device belongs to an authentication type wireless network device, an open type wireless network device, a private wireless network device, a wireless network device encryption type and the like.
The attributes of the wireless network equipment business district mainly comprise the city where the wireless network equipment is located, the living standard grade of the city, whether the city is a popular city or not, whether the business district is a popular business district or not and the like. The channel attribute of the wireless network equipment is mainly considered from the aspects of signals and routing, and channel information, routing brands, routing signals and other information of the wireless network equipment are introduced.
The wireless network equipment password attribute mainly comprises the number of wireless network equipment passwords, the password cycle conversion rate, the password month conversion rate, the password year conversion rate and the like.
In the wireless network device connection behavior log, the connection time of the wireless network device and the connection success and failure rate of the wireless network device can be started. In the aspect of connection time consumption, in addition to extracting the time consumed for connecting the wireless network equipment, the time consumed for connecting the wireless network equipment can be scored according to the connection time of the wireless network equipment and the basic properties of the wireless network equipment to serve as a new characteristic. In the aspect of the success and failure rate of wireless network equipment connection, the brand connection success rate and the failure rate can be respectively selected; the wireless network equipment becomes power and failure rate through connection in the housekeeper; the success rate and the failure rate of the connection of the large disk; the success rate and the failure rate of business circle connection; weekly connection success rate and failure rate; monthly connection success rate, failure rate; and an hour-wise concatenation success rate score, etc.
In one embodiment, 58-dimensional features that substantially represent the quality of a wireless network device connection are extracted from the wireless network device connection behavior log and the wireless network device base attribute log table. The long-term attribute values fully show the fixed attribute information of the wireless network equipment, so that the connection quality of the wireless network equipment is comprehensively evaluated.
In S406, a machine learning model is trained on the positive sample set and the negative sample set to determine the attribute scoring model. Can include the following steps: determining a model structure and a model depth of a random forest model; using a kini coefficient as a loss function of the random forest model; and inputting the positive sample set and the negative sample set into the set random forest model for training to determine the attribute scoring model.
In one embodiment, data training may be performed, for example, by a random forest in a machine learning model, which is a common method in machine learning and improves prediction accuracy without significantly increasing the amount of computation. Meanwhile, the random forest is insensitive to multivariate linearity, the result is more stable to missing data and unbalanced data, the effect of thousands of interpretation variables can be well predicted, and the random forest is known as one of the best current algorithms. Therefore, the invention adopts the random forest as the basic classification model of the quality score model of the wireless network equipment and classifies the wireless network equipment according to the static attribute of the wireless network equipment. In the experiment, 100 trees can be constructed by using the kini coefficient as a loss function, and the maximum depth of the tree is set to be 8. Experiments show that the model can well distinguish high-quality and low-quality wireless network equipment, and the accuracy is up to more than 92%. Other machine learning methods or other parameter settings in the random forest algorithm may also be used for data training, which is not limited in this application.
According to the wireless network connection recommendation method, the network access rate of the wireless network equipment is introduced in the positive and negative sample construction process in the machine learning process, the definition of poor wireless network equipment is expanded while high-quality wireless network equipment is increased, and therefore training samples are increased and the diversity of sample behaviors is enriched.
Fig. 6 is a flow chart illustrating a method of wireless network connection recommendation in accordance with another example embodiment. The flow shown in fig. 6 is a detailed description of "acquiring the online data set based on the network information and attribute scoring models of multiple wireless networks".
In S602, a multidimensional feature data set is extracted from the basic attribute log and the connection behavior log of the wireless network. The multi-dimensional feature data set may be, for example, the 58-dimensional feature data set listed in fig. 4.
In S604, the multidimensional feature data sets corresponding to the wireless networks are input into the attribute scoring model, and a plurality of initial scores are obtained.
In S606, the plurality of initial scores are compared with predetermined scores to generate a plurality of attribute scores.
In S608, the online data set is generated by network identifications of a plurality of wireless networks and attribute scores corresponding thereto.
In order to have a more accurate score for the connection quality of the wireless network equipment, the score can be divided according to the probability output by the model. The normal distribution is the most common distribution in nature, and in order to make the scoring more reasonable, the scoring system can be made to conform to the normal distribution. The Box-Cox transform is a data transform commonly used in statistical modeling, and is often used in cases where continuous response variables do not satisfy a normal distribution. The correlation between the unobservable error and the predictive variable can be reduced to a certain extent by data after Box-Cox transformation.
In one embodiment, the continuous probability output of the attribute scoring model can be discretized after Box-Cox transformation, and the attribute scoring value after Box-Cox transformation is divided into 6 segments by using the mean (mu) and the variance (sigma) of the normal distribution: the radio network devices may be sorted by the score of 1-6 corresponding to the radio network device quality score of (-infinity, (. mu. + 2. sigma.), (μ. + 2. mu. + σ ], (. mu. + σ.), (μ. + 2. mu. + σ.), (μ. +. mu.), (μ. +. mu.,. mu.),. mu. ], respectively.
According to the wireless network connection recommendation method, in the process of predicting probability discretization, Box-Cox transformation is introduced, the output distribution of the binary model based on the self attribute of the wireless network equipment is firstly converted into normal distribution, and then fraction segmentation is carried out, so that more reasonable quality fraction is obtained.
The wireless network equipment connection environment changes in a complex and various mode, noise is easily introduced by directly combining the attributes of the wireless network equipment with the mode of constructing the model, and the influence of the attributes of the wireless network equipment on the connection quality of the wireless network equipment is reduced, so that the accuracy of the wireless network equipment connection quality scoring is influenced.
According to the wireless network connection recommendation method, aiming at an algorithm for scoring the connection quality of the wireless network equipment, the algorithm separates the attribute characteristics of the wireless network equipment and the connection environment characteristics, and respectively establishes a model at a background server and a user equipment end, wherein the background server can be used for calculating the long-term and static attribute score of the wireless network equipment; the user equipment side can be used for calculating the environmental score of the wireless network equipment in the current environment. And finally, carrying out weighted average on the scores of the two parts to obtain the most reasonable wireless network device connection quality score grade, and recommending a plurality of wireless network devices according to the score grade in a preset APP. The wireless network connection recommendation method not only avoids the problem of noise possibly introduced by the connection environment, but also comprehensively considers all factors influencing the connection quality of the wireless network equipment, and obtains a reasonable wireless network equipment connection quality score.
Those skilled in the art will appreciate that all or part of the steps implementing the above embodiments are implemented as computer programs executed by a CPU. When executed by the CPU, performs the functions defined by the above-described methods provided by the present disclosure. The program may be stored in a computer readable storage medium, which may be a read-only memory, a magnetic or optical disk, or the like.
Furthermore, it should be noted that the above-mentioned figures are only schematic illustrations of the processes involved in the methods according to exemplary embodiments of the present disclosure, and are not intended to be limiting. It will be readily understood that the processes shown in the above figures are not intended to indicate or limit the chronological order of the processes. In addition, it is also readily understood that these processes may be performed synchronously or asynchronously, e.g., in multiple modules.
The following are embodiments of the disclosed apparatus that may be used to perform embodiments of the disclosed methods. For details not disclosed in the embodiments of the apparatus of the present disclosure, refer to the embodiments of the method of the present disclosure.
Fig. 7 is a block diagram illustrating a wireless network connection recommendation apparatus according to an example embodiment. The wireless network connection recommending apparatus 70 includes: a network information module 702, an attribute scoring module 704, an environment scoring module 706, a quality scoring module 708, and a connection recommendation module 710.
The network information module 702 is configured to obtain network information of multiple wireless networks according to a user instruction, where the network information includes a network identifier and a signal strength; the user may send a predetermined instruction, for example, on a predetermined APP, which may be to request a wireless network connection from a wireless network device in the vicinity of the user.
An attribute scoring module 704 for determining a plurality of attribute scores for the plurality of wireless networks based on the network identification; the method comprises the following steps: determining a plurality of attribute scores for the plurality of wireless networks through an online dataset based on the network identification; determining a plurality of attribute scores for the plurality of wireless networks through an offline dataset based on the network identification.
An environmental scoring module 706 is configured to determine a plurality of environmental scores for the plurality of wireless networks based on the signal strengths; the connection environment of the wireless network equipment is complex and variable, and the connection quality of the wireless network equipment is mainly influenced by the current signal level of the wireless network equipment and other transient changes. The current signal value of the wireless network equipment can be adopted as the connection environment characteristic of the wireless network equipment to calculate the instantaneous signal score of the wireless network equipment in the current environment, and the instantaneous signal score is calculated by limiting the instantaneous information acquisition limit of the wireless network equipment in the current log table, the response speed requirement of a client and the like. May for example be: and evenly dividing the instantaneous signal value of the wireless network equipment from 0 to 100 points to 6 points, and obtaining a signal score of 1 to 6 points as an environment score of the wireless network equipment in the current environment.
A quality scoring module 708 for determining a plurality of connection quality scores for the plurality of wireless networks from the plurality of attribute scores and the plurality of environmental scores; attribute scoring weights and environmental scoring weights may be determined, for example, based on historical attribute scores and historical environmental scores; and determining a plurality of connection quality scores for the plurality of wireless networks from the plurality of attribute scores, the attribute score weights, and the plurality of environmental scores, the environmental score weights.
The connection recommendation module 710 is configured to make a wireless network connection recommendation based on the plurality of connection quality scores. The plurality of wireless network devices can be sequentially arranged from high to low according to the connection quality scores corresponding to the plurality of wireless network devices so as to recommend connection.
According to the wireless network connection recommending device, an algorithm for determining the wireless network equipment connection quality score is generated according to the characteristics of the wireless network equipment connection quality, the algorithm can be executed by a background server and a user equipment terminal, and the background server part can be used for constructing a wireless network equipment attribute score model and an attribute score and environment score weight calculation model according to the long-term attribute characteristics of the wireless network equipment.
On the user equipment side, a small-sized calculation model of the current environment score of the wireless network equipment can be constructed. The wireless network connection recommending device comprehensively considers long-term and static attributes and connection characteristics of the wireless network equipment and instantaneous environment characteristics under current connection, and obtains the most reasonable wireless network equipment connection quality score grade by adopting the optimal weighting proportion, so that the display sequence of the wireless network equipment list at the user equipment end is determined, and the calculated high-quality connectable wireless network equipment is preferentially displayed.
FIG. 8 is a block diagram illustrating an electronic device in accordance with an example embodiment.
An electronic device 800 according to this embodiment of the disclosure is described below with reference to fig. 8. The electronic device 800 shown in fig. 8 is only an example and should not bring any limitations to the functionality and scope of use of the embodiments of the present disclosure.
As shown in fig. 8, electronic device 800 is in the form of a general purpose computing device. The components of the electronic device 800 may include, but are not limited to: at least one processing unit 810, at least one memory unit 820, a bus 830 connecting the various system components (including the memory unit 820 and the processing unit 810), a display unit 840, and the like.
Wherein the storage unit stores program code executable by the processing unit 810 to cause the processing unit 810 to perform steps according to various exemplary embodiments of the present disclosure described in the electronic prescription flow processing method section described above in this specification. For example, the processing unit 810 may perform the steps as shown in fig. 3, 4, 6.
The memory unit 820 may include readable media in the form of volatile memory units such as a random access memory unit (RAM)8201 and/or a cache memory unit 8202, and may further include a read only memory unit (ROM) 8203.
The memory unit 820 may also include a program/utility 8204 having a set (at least one) of program modules 8205, such program modules 8205 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may comprise an implementation of a network environment.
The electronic device 800 may also communicate with one or more external devices 800' (e.g., keyboard, pointing device, bluetooth device, etc.), with one or more devices that enable a user to interact with the electronic device 200, and/or with any devices (e.g., router, modem, etc.) that enable the electronic device 800 to communicate with one or more other computing devices. Such communication may occur via input/output (I/O) interfaces 850. Also, the electronic device 800 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the internet) via the network adapter 860. The network adapter 860 may communicate with other modules of the electronic device 800 via the bus 830. It should be appreciated that although not shown, other hardware and/or software modules may be used in conjunction with the electronic device 800, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.
Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (which may be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which may be a personal computer, a server, or a network device, etc.) to execute the above method according to the embodiments of the present disclosure.
Fig. 9 schematically illustrates a computer-readable storage medium in an exemplary embodiment of the disclosure.
Referring to fig. 9, a program product 900 for implementing the above method according to an embodiment of the present disclosure is described, which may employ a portable compact disc read only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. However, the program product of the present disclosure is not limited thereto, and in this document, a readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
The computer readable storage medium may include a propagated data signal with readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A readable storage medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Program code for carrying out operations for the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider).
The computer readable medium carries one or more programs which, when executed by a device, cause the computer readable medium to perform the functions of: acquiring network information of a plurality of wireless networks according to a user instruction, wherein the network information comprises network identifiers and signal intensity; determining a plurality of attribute scores for the plurality of wireless networks based on the network identification; determining a plurality of environmental scores for the plurality of wireless networks based on the signal strengths; determining a plurality of connection quality scores for the plurality of wireless networks from the plurality of attribute scores and the plurality of environmental scores; and making a wireless network connection recommendation based on the plurality of connection quality scores.
Those skilled in the art will appreciate that the modules described above may be distributed in the apparatus according to the description of the embodiments, or may be modified accordingly in one or more apparatuses unique from the embodiments. The modules of the above embodiments may be combined into one module, or further split into multiple sub-modules.
Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (which may be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which may be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the embodiments of the present disclosure.
In addition, the structures, the proportions, the sizes, and the like shown in the drawings of the present specification are only used for matching with the contents disclosed in the specification, so as to be understood and read by those skilled in the art, and are not used for limiting the limit conditions which the present disclosure can implement, so that the present disclosure has no technical essence, and any modification of the structures, the change of the proportion relation, or the adjustment of the sizes, should still fall within the scope which the technical contents disclosed in the present disclosure can cover without affecting the technical effects which the present disclosure can produce and the purposes which can be achieved. In addition, the terms "above", "first", "second" and "a" as used in the present specification are for the sake of clarity only, and are not intended to limit the scope of the present disclosure, and changes or modifications of the relative relationship may be made without substantial changes in the technical content.
Claims (13)
1. A wireless network connection recommendation method, comprising:
acquiring network information of a plurality of wireless networks according to a user instruction, wherein the network information comprises network identifiers and signal intensity;
determining a plurality of attribute scores for the plurality of wireless networks based on the network identification;
determining a plurality of environmental scores for the plurality of wireless networks based on the signal strengths;
determining a plurality of connection quality scores for the plurality of wireless networks from the plurality of attribute scores and the plurality of environmental scores; and
performing wireless network connection recommendation based on the plurality of connection quality scores;
the method for determining the attribute score comprises the following steps:
carrying out Box-Cox transformation on continuous probability output of an attribute scoring model based on the network identification;
segmenting the numerical value subjected to Box-Cox transformation into a plurality of fraction segments by using the mean value and the variance of normal distribution;
a discretized attribute score corresponding to the fractional segment is determined.
2. The method of claim 1, wherein determining a plurality of attribute scores for the plurality of wireless networks based on the network identification comprises:
determining a plurality of attribute scores for the plurality of wireless networks through an online dataset based on the network identification; and
determining a plurality of attribute scores for the plurality of wireless networks through an offline dataset based on the network identification.
3. The method of claim 2, wherein determining a plurality of attribute scores for the plurality of wireless networks through an online dataset based on the network identification further comprises:
and acquiring the online data set based on network information and attribute grading models of a plurality of wireless networks.
4. The method of claim 3, further comprising:
acquiring basic attribute logs and connection behavior logs of a plurality of wireless networks;
allocating basic attribute logs corresponding to the plurality of wireless networks into a positive sample set and a negative sample set based on the connection behavior log; and
training a machine learning model through the set of positive samples and the set of negative samples to determine the attribute scoring model.
5. The method of claim 4, wherein assigning the base attribute logs corresponding to the plurality of wireless networks into a positive sample set and a negative sample set based on the connection behavior log comprises:
acquiring the connection success rate and the internet access rate in the connection behavior log; and
and distributing basic attribute logs corresponding to the plurality of wireless networks into a positive sample set and a negative sample set through the connection power and the internet access rate.
6. The method of claim 4, wherein training a machine learning model to determine the attribute scoring model by the set of positive samples and the set of negative samples comprises:
determining a model structure and a model depth of a random forest model;
using a kini coefficient as a loss function of the random forest model; and
and inputting the positive sample set and the negative sample set into the set random forest model for training to determine the attribute scoring model.
7. The method of claim 3, wherein obtaining the online data set based on a network information and attribute scoring model for a plurality of wireless networks comprises:
extracting a multi-dimensional characteristic data set from a basic attribute log and a connection behavior log of a wireless network;
inputting a plurality of multi-dimensional feature data sets corresponding to a plurality of wireless networks into the attribute scoring model to obtain a plurality of initial scores;
comparing the plurality of initial scores with predetermined scores to generate a plurality of attribute scores; and
and generating the online data set through the network identifications of the plurality of wireless networks and the attribute scores corresponding to the network identifications.
8. The method of claim 7, wherein prior to comparing the plurality of initial scores to the predetermined scores to generate a plurality of attribute scores, further comprises:
carrying out generalized power transformation processing on the plurality of initial scores to generate a plurality of target scores;
calculating a mean and a variance of the plurality of target scores; and
generating the predetermined scoring interval from the mean and the variance.
9. The method of claim 1, wherein determining a plurality of connection quality scores for the plurality of wireless networks from the plurality of attribute scores and the plurality of environmental scores comprises:
determining an attribute scoring weight and an environment scoring weight based on the historical attribute score and the historical environment score; and
determining a plurality of connection quality scores for the plurality of wireless networks from the plurality of attribute scores, the attribute score weights, and the plurality of environmental scores, the environmental score weights.
10. The method of claim 9, wherein determining attribute scoring weights and environmental scoring weights based on historical attribute scores and historical environmental scores comprises:
determining an attribute scoring weight and an environment scoring weight based on a gray testing mode, historical attribute scoring and historical environment scoring; and
and determining an attribute scoring weight and an environment scoring weight based on the logistic regression mode and the historical attribute scoring and the historical environment scoring.
11. A wireless network connection recommendation device, comprising:
the network information module is used for acquiring network information of a plurality of wireless networks according to a user instruction, wherein the network information comprises network identifiers and signal intensity;
an attribute scoring module to determine a plurality of attribute scores for the plurality of wireless networks based on the network identification;
an environmental scoring module to determine a plurality of environmental scores for the plurality of wireless networks based on the signal strength;
a quality scoring module to determine a plurality of connection quality scores for the plurality of wireless networks from the plurality of attribute scores and the plurality of environmental scores; and
the connection recommending module is used for recommending wireless network connection based on the plurality of connection quality scores;
the attribute scoring module is further to:
carrying out Box-Cox transformation on continuous probability output of an attribute scoring model based on the network identification;
segmenting the numerical value subjected to Box-Cox transformation into a plurality of fraction segments by using the mean value and the variance of normal distribution;
a discretized attribute score corresponding to the fractional segment is determined.
12. An electronic device, comprising:
one or more processors;
storage means for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-10.
13. A computer-readable medium, on which a computer program is stored, which, when being executed by a processor, carries out the method according to any one of claims 1-10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910226151.1A CN109951859B (en) | 2019-03-25 | 2019-03-25 | Wireless network connection recommendation method and device, electronic equipment and readable medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910226151.1A CN109951859B (en) | 2019-03-25 | 2019-03-25 | Wireless network connection recommendation method and device, electronic equipment and readable medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109951859A CN109951859A (en) | 2019-06-28 |
| CN109951859B true CN109951859B (en) | 2021-08-20 |
Family
ID=67011470
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910226151.1A Active CN109951859B (en) | 2019-03-25 | 2019-03-25 | Wireless network connection recommendation method and device, electronic equipment and readable medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109951859B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112260862A (en) * | 2020-10-13 | 2021-01-22 | 北京锐安科技有限公司 | Network data quality determination method and device, electronic equipment and storage medium |
| CN114584607B (en) * | 2022-05-05 | 2022-09-13 | 云南电网有限责任公司 | Communication connection establishing method and device, electronic equipment and readable storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2005062658A1 (en) * | 2003-12-15 | 2005-07-07 | Intel Corporation (A Corporation Of Delaware) | Handoff apparatus, systems, and methods |
| CN103262632A (en) * | 2010-06-04 | 2013-08-21 | 得克萨斯系统大学评议会 | Wireless communication method, system and computer program product |
| CN103874132A (en) * | 2014-03-25 | 2014-06-18 | 北京工业大学 | Heterogeneous wireless network access selection method based on users |
| CN104301925A (en) * | 2014-10-22 | 2015-01-21 | 福建富士通信息软件有限公司 | Wireless WIFI network quality analysis evaluation method |
| CN106488539A (en) * | 2015-09-02 | 2017-03-08 | 腾讯科技（深圳）有限公司 | The processing method of WiFi resource and system in terminal |
| CN107563645A (en) * | 2017-09-04 | 2018-01-09 | 杭州云算信达数据技术有限公司 | A kind of Financial Risk Analysis method based on big data |
-
2019
- 2019-03-25 CN CN201910226151.1A patent/CN109951859B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2005062658A1 (en) * | 2003-12-15 | 2005-07-07 | Intel Corporation (A Corporation Of Delaware) | Handoff apparatus, systems, and methods |
| CN103262632A (en) * | 2010-06-04 | 2013-08-21 | 得克萨斯系统大学评议会 | Wireless communication method, system and computer program product |
| CN103874132A (en) * | 2014-03-25 | 2014-06-18 | 北京工业大学 | Heterogeneous wireless network access selection method based on users |
| CN104301925A (en) * | 2014-10-22 | 2015-01-21 | 福建富士通信息软件有限公司 | Wireless WIFI network quality analysis evaluation method |
| CN106488539A (en) * | 2015-09-02 | 2017-03-08 | 腾讯科技（深圳）有限公司 | The processing method of WiFi resource and system in terminal |
| CN107563645A (en) * | 2017-09-04 | 2018-01-09 | 杭州云算信达数据技术有限公司 | A kind of Financial Risk Analysis method based on big data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109951859A (en) | 2019-06-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112528025A (en) | Text clustering method, device and equipment based on density and storage medium | |
| CN110111139B (en) | Behavior prediction model generation method and device, electronic equipment and readable medium | |
| CN110059172B (en) | Method and device for recommending answers based on natural language understanding | |
| CN107392259B (en) | Method and device for constructing unbalanced sample classification model | |
| CN106844550B (en) | Virtualization platform operation recommendation method and device | |
| CN111967543A (en) | User resource quota determining method and device and electronic equipment | |
| US20180349476A1 (en) | Evaluating theses using tree structures | |
| CN109951859B (en) | Wireless network connection recommendation method and device, electronic equipment and readable medium | |
| CN111582341A (en) | User abnormal operation prediction method and device | |
| CN111210332A (en) | Method and device for generating post-loan management strategy and electronic equipment | |
| CN111191677B (en) | User characteristic data generation method and device and electronic equipment | |
| CN115619448A (en) | User loss prediction method and device, computer equipment and storage medium | |
| CN113298360B (en) | Risk control method, device and system for resource allocation | |
| CN111582649B (en) | Risk assessment method and device based on user APP single-heat coding and electronic equipment | |
| US10460276B2 (en) | Predictive model search by communicating comparative strength | |
| CN117217812A (en) | User behavior prediction method and device, computer equipment and storage medium | |
| CN113568739B (en) | User resource quota allocation method and device and electronic equipment | |
| CN111435381A (en) | Request distribution method and device | |
| CN112527851B (en) | User characteristic data screening method and device and electronic equipment | |
| CN114925275A (en) | Product recommendation method and device, computer equipment and storage medium | |
| CN110852078A (en) | Method and device for generating title | |
| CN113612777A (en) | Training method, traffic classification method, device, electronic device and storage medium | |
| CN112069807A (en) | Text data theme extraction method and device, computer equipment and storage medium | |
| CN111582648A (en) | User policy generation method and device and electronic equipment | |
| CN114862214B (en) | Quantitative evaluation method and device for inter-enterprise intentional collaboration |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |