CN107835520A - Wifi hotspot connection method, device and storage medium - Google Patents
Wifi hotspot connection method, device and storage medium Download PDFInfo
- Publication number
- CN107835520A CN107835520A CN201710884576.2A CN201710884576A CN107835520A CN 107835520 A CN107835520 A CN 107835520A CN 201710884576 A CN201710884576 A CN 201710884576A CN 107835520 A CN107835520 A CN 107835520A
- Authority
- CN
- China
- Prior art keywords
- wifi hotspot
- scoring
- multiple wifi
- hotspot
- preset time
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/08—Testing, supervising or monitoring using real traffic
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W48/00—Access restriction; Network selection; Access point selection
- H04W48/16—Discovering, processing access restriction or access information
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Mathematical Optimization (AREA)
- Theoretical Computer Science (AREA)
- Pure & Applied Mathematics (AREA)
- Computational Mathematics (AREA)
- Signal Processing (AREA)
- Mathematical Analysis (AREA)
- Computer Networks & Wireless Communication (AREA)
- Evolutionary Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Operations Research (AREA)
- Probability & Statistics with Applications (AREA)
- Bioinformatics & Computational Biology (AREA)
- Algebra (AREA)
- Computer Security & Cryptography (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The invention discloses a kind of wifi hotspot connection method, device and storage medium, this method includes:Historical data of the available multiple wifi hotspots and the multiple wifi hotspot that reception client scan arrives in the first preset time;Every the second preset time, predetermined Logic Regression Models are updated;According to the historical data in the first preset time and the Logic Regression Models after the renewal, the first scoring of the multiple wifi hotspot is calculated;Connection failure number of the multiple wifi hotspot in the 3rd preset time is read, the second scoring of the multiple wifi hotspot is obtained according to predetermined drop power rule;According to the signal intensity of the multiple wifi hotspot and the second height to score, the multiple wifi hotspot is ranked up;And attempt to connect the multiple wifi hotspot successively according to ranking results.The present invention utilizes the historical data of wifi hotspot, selects optimal wifi hotspot for user and carries out attended operation, lifts user's online experience.
Description
Technical field
The present invention relates to field of computer technology, more particularly to a kind of wifi hotspot connection method, electronic installation and calculating
Machine readable storage medium storing program for executing.
Background technology
When mobile terminal starts wireless lan function, the wifi heat scanned can be shown in WLAN interface
Point, user can be connected manually to scanning wifi hotspot, if the wifi hotspot once connected in the focus scanned be present,
Then system can be attached automatically to the wifi hotspot.Wifi hotspot is typically provided with connection password, can prevent loiter network and ensure to lead to
Letter safety.In wifi hotspot connection procedure, for the wifi hotspot provided with password, password need to be inputted.
According to the position of mobile terminal, in the wifi hotspot list scanned, free wifi hotspot may be present, such as:Operation
Business's wifi hotspot (China Mobile, China Telecom, CHINAUNICOM), public wifi, businessman's wifi hotspot etc..User is for scanning
Free wifi hotspot, generally choose at random and connected manually, choose at random cause connection wifi hotspot be not usually
Optimal, connection is also not convenient enough manually, influences user's online experience.Therefore, how handy wifi heat is picked out for user
The automatic connection of point, is a very valuable and urgent problem to be solved.
The content of the invention
The present invention provides a kind of wifi hotspot connection method, electronic installation and computer-readable recording medium, its main mesh
Be, using the historical data of wifi hotspot, calculate the scoring of wifi hotspot using the model of real-time update, selected for user
Optimal wifi hotspot simultaneously carries out attended operation, lifts user's online experience.
To achieve the above object, the present invention provides a kind of wifi hotspot connection method, and this method includes:
Receiving step:The available multiple wifi hotspots and the multiple wifi hotspot that reception client scan arrives are first
Historical data in preset time;
Model modification step:Every the second preset time, using the multiple wifi hotspot in second preset time
Historical data, predetermined Logic Regression Models are updated, by the model file of the Logic Regression Models after renewal
Preserve into memory;
Score step:According to the historical data in the first preset time and the Logic Regression Models after the renewal, calculate
First scoring of the multiple wifi hotspot;
Score set-up procedure:Connection failure number of the multiple wifi hotspot in the 3rd preset time is read, according to
First scoring of the predetermined drop power rule to the multiple wifi hotspot is adjusted, and obtains the multiple wifi hotspot
Second scoring;
Sequence step:According to the signal intensity of the multiple wifi hotspot and the second height to score, to the multiple
Wifi hotspot is ranked up;And
Connection Step:Attempt to connect the multiple wifi hotspot successively according to ranking results.
Preferably, this method is further comprising the steps of:
After client is successfully connected a wifi hotspot in the 4th preset time, whether real the wifi hotspot is detected
It can use, if the wifi hotspot is unavailable, continue to be attached operation to coming the wifi hotspot after the wifi hotspot.
Preferably, the predetermined drop power rule includes:
Read connection failure number of multiple wifi hotspots in the 3rd preset time described in historical data;
When the connection failure number is less than the first predetermined threshold value, retain the first scoring of the multiple wifi hotspot,
The second scoring as the multiple wifi hotspot;
, will be the multiple when the connection failure number is more than the first predetermined threshold value and is less than the second predetermined threshold value
The first coefficient is multiplied by first scoring of wifi hotspot, the second scoring as the multiple wifi hotspot;And
When the connection failure number is more than the second predetermined threshold value, the first scoring of the multiple wifi hotspot is multiplied by
Second coefficient, the second scoring as the multiple wifi hotspot.
Preferably, the sequence step includes:
According to the strong and weak order of the current signal intensity of the multiple wifi hotspot, the multiple wifi hotspot is arranged
Sequence;And
For two or more wifi hotspots of the current signal strength in same signal intensity section, according to described two
Or the sequence of the second scoring of multiple wifi hotspots is ranked up.
Preferably, the scoring step also includes:
To there is no the wifi hotspot of historical data to assign an acquiescence scoring in the multiple wifi hotspot or assigning other
The average mark of second scoring of multiple wifi hotspots.
In addition, to achieve the above object, the present invention also provides a kind of electronic installation, and the electronic installation includes:Memory, place
Device is managed, is stored with wifi hotspot linker on the memory, the wifi hotspot linker is by the computing device
Shi Shixian following steps:
Receiving step:The available multiple wifi hotspots and the multiple wifi hotspot that reception client scan arrives are first
Historical data in preset time;
Model modification step:Every the second preset time, using the multiple wifi hotspot in second preset time
Historical data, predetermined Logic Regression Models are updated, by the model file of the Logic Regression Models after renewal
Preserve into memory;
Score step:According to the historical data in the first preset time and the Logic Regression Models after the renewal, calculate
First scoring of the multiple wifi hotspot;
Score set-up procedure:Connection failure number of the multiple wifi hotspot in the 3rd preset time is read, according to
First scoring of the predetermined drop power rule to the multiple wifi hotspot is adjusted, and obtains the multiple wifi hotspot
Second scoring;
Sequence step:According to the signal intensity of the multiple wifi hotspot and the second height to score, to the multiple
Wifi hotspot is ranked up;And
Connection Step:Attempt to connect the multiple wifi hotspot successively according to ranking results.
Preferably, the wifi hotspot linker by the computing device when also realize following steps:
After client is successfully connected a wifi hotspot in the 4th preset time, whether real the wifi hotspot is detected
It can use, if the wifi hotspot is unavailable, continue to be attached operation to coming the wifi hotspot after the wifi hotspot.
Preferably, the predetermined drop power rule includes:
Read connection failure number of multiple wifi hotspots in the 3rd preset time described in historical data;
When the connection failure number is less than the first predetermined threshold value, retain the first scoring of the multiple wifi hotspot,
The second scoring as the multiple wifi hotspot;
, will be the multiple when the connection failure number is more than the first predetermined threshold value and is less than the second predetermined threshold value
The first coefficient is multiplied by first scoring of wifi hotspot, the second scoring as the multiple wifi hotspot;And
When the connection failure number is more than the second predetermined threshold value, the first scoring of the multiple wifi hotspot is multiplied by
Second coefficient, the second scoring as the multiple wifi hotspot.
Preferably, the sequence step includes:
According to the strong and weak order of the current signal intensity of the multiple wifi hotspot, the multiple wifi hotspot is arranged
Sequence;And
For two or more wifi hotspots of the current signal strength in same signal intensity section, according to described two
Or the sequence of the second scoring of multiple wifi hotspots is ranked up.
Preferably, the scoring step also includes:
To there is no the wifi hotspot of historical data to assign an acquiescence scoring in the multiple wifi hotspot or assigning other
The average mark of second scoring of multiple wifi hotspots.
In addition, to achieve the above object, the present invention also provides a kind of computer-readable recording medium, described computer-readable
Wifi hotspot linker is stored with storage medium, as above institute is realized when the wifi hotspot linker is executed by processor
The step of wifi hotspot connection method stated.
Compared to prior art, wifi hotspot connection method, electronic installation and computer-readable storage proposed by the present invention
Medium, by obtaining the historical data of wifi hotspot, calculate wifi hotspot it is following may successful connection probability, then root successively
Wifi hotspot is ranked up according to wifi hotspot signal intensity, scoring score value, finally selects optimal wifi hotspot simultaneously for user
Operation is attached, lifts user's online experience.
Brief description of the drawings
Fig. 1 is the schematic diagram of electronic installation preferred embodiment of the present invention;
Fig. 2 is the module diagram of wifi hotspot linker preferred embodiment in Fig. 1;
Fig. 3 is the flow chart of wifi hotspot connection method preferred embodiment of the present invention.
The realization, functional characteristics and advantage of the object of the invention will be described further referring to the drawings in conjunction with the embodiments.
Embodiment
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
The present invention provides a kind of electronic installation 1.It is the signal of the preferred embodiment of electronic installation 1 of the present invention shown in reference picture 1
Figure.In the present embodiment, the electronic installation 1 includes memory 11, processor 12, network interface 13 and communication bus 14.
Electronic installation 1 can be that server, smart mobile phone, tablet personal computer, pocket computer, desktop PC etc. have
The terminal device of calculation function, in certain embodiments, the server can be rack-mount server, blade server,
Tower server or Cabinet-type server etc..
Communication bus 14 is used to realize the connection communication between these components.
Memory 11 includes the readable storage medium storing program for executing of at least one type.The readable storage medium storing program for executing of at least one type
Can be such as flash memory, hard disk, multimedia card, the non-volatile memory medium of card-type memory.In certain embodiments, it is described can
Read the internal storage unit that storage medium can be the electronic installation 1, such as the hard disk of the electronic installation 1.In other realities
Apply in example, the readable storage medium storing program for executing can also be the External memory equipment of the electronic installation 1, such as the electronic installation 1
The plug-in type hard disk of upper outfit, intelligent memory card (Smart Media Card, SMC), secure digital (Secure Digital,
SD) block, flash card (Flash Card) etc..
In the present embodiment, the readable storage medium storing program for executing of the memory 11 is generally used for storage and is installed on the electronic installation
1 wifi hotspot linker, the historical data of the wifi hotspot connected in the recent period that client 2 is collected and user, in advance really
Logic Regression Models after set and renewal etc..The memory 11, which can be also used for temporarily storing, to have exported or has incited somebody to action
The data to be exported.
Processor 12 can be in certain embodiments a central processing unit (Central Processing Unit,
CPU), microprocessor or other data processing chips, for the program code or processing data stored in run memory 11, example
Such as perform wifi hotspot linker.
Fig. 1 illustrate only the electronic installation 1 with component 11-14 and wifi hotspot linker 10, it should be understood that
Be, it is not required that implement all components shown, the more or less component of the implementation that can be substituted.
Optionally, the electronic installation 1 can also include user interface, and user interface can include input block such as keyboard
(Keyboard), optional user interface can also include wireline interface, the wave point of standard.
Alternatively, the electronic installation 1 can also include display (Display), can be that LED shows in certain embodiments
Show device, liquid crystal display, touch-control liquid crystal display and OLED (Organic Light-Emitting Diode, You Jifa
Optical diode) touch device etc..Display is used to show the information that handles in an electronic and for showing visual use
Family interface.
Alternatively, the electronic installation 1 can also include camera, RF (Radio Frequency, radio frequency) circuit, sensing
Device, voicefrequency circuit, wifi module etc., will not be repeated here.
In the device embodiment shown in Fig. 1, as being stored with wifi in a kind of memory 11 of computer-readable storage medium
Focus linker 10, processor 12 realize following steps when performing the wifi hotspot linker 10 stored in memory 11:
Receiving step:The available multiple wifi hotspots that scan of client 2 and the multiple wifi hotspot are received the
Historical data in one preset time.
For example, the version of client 2 of wifi hotspot linker is mounted in the client 2 that each user uses (afterwards
Abbreviation APP), client 2 is attached wifi hotspot by the APP and operated.The APP is persistently scanned current by client 2
The available multiple wifi hotspots in position, electronic installation 1 receives multiple wifi hotspots that APP is scanned by client 2, and collects
The historical data for the plurality of wifi hotspot that each user accessed in the first preset time (nearly three months), including:Wifi's
Title, accessed time and duration, mode of operation (successful connection, connection failure, log in successfully, log in unsuccessfully etc.), it is accessed
The frequency, whether operator provide etc..Historical data is uploaded to log server by electronic installation 1, and passes through data warehouse technology
(Extract-Transform-Load, abbreviation ETL) extracts crucial historical data, such as wifi marks, time, position, connection
Operation, online duration, successful connection number, connection failure number, number of retries, log in number of success, log in frequency of failure etc.,
Preserve into memory 11, model modification and scoring operation are carried out for follow-up.
Model modification step:Every the second preset time, using the multiple wifi hotspot in second preset time
Historical data, predetermined Logic Regression Models are updated, by the model file of the Logic Regression Models after renewal
Preserve into memory.
Specifically, the predetermined Logic Regression Models are obtained by way of off-line training:To above-mentioned crucial number
According to being analyzed, from time dimension, operator ,/shared focus dimension, connect/logs in/retried/online duration statistics etc. structure
The aspect of model is made, determines model label;Monthly, day counting user uses the frequency and data volume of wifi hotspot, determines that the time is grown
Spend for the dimension of nearest three months, nearest one week, along with " operator/shared focus ", " connect and/log in/retrying/when surfing the Net
It is long " dimension is combined into series of features, such as nearest Ge Yue operators connect into power, nearest one week wifi hotspot retries
Number etc..Then using nearest trimestral crucial historical data as training set, Random Forest model is trained, used
Preserved in the Logic Regression Models to be scored wifi hotspot, and by the model file of the Logic Regression Models to memory 11
In.Scoring on each wifi hotspot is trained and calculated using it to the model has had the computational methods of maturation,
It will not be repeated here.
It is understood that the advantages of off-line training model is that substantial amounts of historical data, sample are abundant.On-line training
The advantages of model is can to utilize newest data, and model adapts to the change of real time data, in data distribution and history gap
In the case of larger, on-time model is more accurate.In order that the scoring for each wifi hotspot being subsequently calculated is more accurate, every
Second preset time (such as one day) is updated to above-mentioned Logic Regression Models.Make off-line training and on-line training by combining
Two ways, both advantages, the degree of accuracy of lift scheme can be taken, while prevented under thread environment, data volume very little or
Caused by network, system problem the problems such as real-time model renewal failure.
In one embodiment, model training is to use sample data, using optimized algorithm, iterative model parameter
Process.The target of optimized algorithm iterative calculation is so that the loss function value of model is minimum, for Logic Regression Models, Wo Menli
L-BFGS algorithms (Limited-memory Broyden-Fletcher-Goldfarb-Shanno) are used to instruct under thread environment
Practice, obtain parameter sets S0, i.e. offline model results;In thread environment, FTRL-Proximal algorithms (Follow The are used
(Proximally) Regularized Leader), set S0 is as initial value for loading, uses the next wifi reached in real time
The data of focus, are once calculated, and the result of calculating is new set of parameter values S1;The like, then have a number in real time
During according to reaching, using S1 as input, it is newest model that result S2, the last result of calculation Sn, which is calculated,.
Score step:According to the historical data in the first preset time and the Logic Regression Models after the renewal, calculate
First scoring of the multiple wifi hotspot.After multiple wifi hotspots of client 2APP transmissions are received, from memory 11
The middle model file for calling the Logic Regression Models, and transfer from memory 11 in the multiple wifi hotspot three months
Historical data, model is inputted, obtains the first scoring of the multiple wifi hotspot, that is, the multiple wifi hotspot exists
The probability of following possible successful connection.
Score set-up procedure:Connection failure number of the multiple wifi hotspot in the 3rd preset time is read, according to
First scoring of the predetermined drop power rule to the multiple wifi hotspot is adjusted, and obtains the multiple wifi hotspot
Second scoring.In the present embodiment, in order to further ensure that the reliability of the first of above-mentioned multiple wifi hotspots the scoring, according to pre-
The drop power rule first determined, the first scoring to the multiple wifi hotspot are adjusted.The predetermined drop power rule
Including:Read connection failure number of multiple wifi hotspots in the 3rd preset time described in historical data;When the connection
When the frequency of failure is less than the first predetermined threshold value, retain the first scoring of the multiple wifi hotspot, as the multiple wifi heat
Second scoring of point;, will be described more when the connection failure number is more than the first predetermined threshold value and is less than the second predetermined threshold value
The first coefficient is multiplied by first scoring of individual wifi hotspot, the second scoring as the multiple wifi hotspot;And when the connection
When the frequency of failure is more than the second predetermined threshold value, the second coefficient is multiplied by the first scoring of the multiple wifi hotspot, as described
Second scoring of multiple wifi hotspots.
By taking wifi hotspot A, B, C as an example, the first of wifi hotspot A, B, C is respectively:9.0、8.5、9.5.Assuming that the
Three preset times are 30min, and the first predetermined threshold value is 5, and the second predetermined threshold value is 10, and the first coefficient is 0.8, and the second coefficient is
0.4, reading the connection failure number of wifi hotspot A, B, C in 30min is respectively:8th, 3,15, wifi hotspot A is in 30min
Connection failure number be more than first predetermined threshold value and be less than the second predetermined threshold value, therefore the second of wifi hotspot A scores and is
7.2;Connection failure numbers of the wifi hotspot B in 30min is less than first predetermined threshold value, therefore the second of wifi hotspot B comments
It is divided into 8.5;Connection failure numbers of the wifi hotspot C in 30min is more than the second predetermined threshold value, therefore the second of wifi hotspot C comments
It is divided into 3.8.
Specifically, a kind of situation be present, in the multiple wifi hotspot, there is a wifi hotspot there is no historical data, that
The Logic Regression Models can not calculate the first scoring of the wifi hotspot, and can not also calculate the wifi hotspot second is commented
Point, for this kind of wifi hotspot, take default acquiescence scoring or take the second of other multiple wifi hotspots score be averaged
Value, is assigned to this kind of wifi hotspot.Further, when acquiescence scoring with the second of other multiple wifi hotspots score be averaged
When being worth inconsistent, the second scoring as this kind of wifi hotspot that score value is high is taken.
Sequence step:According to the signal intensity of the multiple wifi hotspot and the second height to score, to the multiple
Wifi hotspot is ranked up.
It should be noted that for same wifi hotspot, different clients 2 arrives the wifi in different position scanning
The signal intensity of focus is different, and still, the scoring to the wifi hotspot is consistent, therefore scoring that can not only according to each wifi hotspot
Each wifi hotspot is ranked up, it is also necessary to consider the signal intensity of each wifi hotspot.By taking wifi hotspot A, B, C as an example, according to
Above-mentioned drop power rule obtains the second of wifi hotspot A, B, C and is respectively:7.2nd, 8.5,3.8, the signal of wifi hotspot A, B is strong
Section is spent all between -35dbm~-60dbm, and wifi hotspot C signal intensity section is between -60dbm~-85dbm, specifically
Ground, the sequence step include:
According to the strong and weak order of the current signal intensity of the multiple wifi hotspot, the multiple wifi hotspot is arranged
Sequence (A=B > C);For two or more wifi hotspots of the current signal strength in same signal intensity section, according to described
The sequence of second scoring of two or more wifi hotspots is ranked up (B > A), therefore final ranking results are B, A, C.
Connection Step:Attempt to connect the multiple wifi hotspot successively according to ranking results.According to final ranking results, electricity
Sub-device is attached operation to wifi hotspot B, A, C successively according to wifi hotspot B, A, C order.
Specifically, after client 2 is successfully connected a wifi hotspot in the 4th preset time, the wifi hotspot is detected
Whether really can use, if the wifi hotspot is unavailable, continue to be attached operation to coming the wifi hotspot after the wifi hotspot.
Assuming that the 4th preset time is 10s, when client 2 is successfully connected a wifi hotspot B in 10s, detecting wifi hotspot B is
It is no really available, for example, utilizing " ping " order to check whether wifi hotspot B network connects, analyze and judge wifi hotspot B
With the presence or absence of network failure.It is understood that if wifi hotspot B, Huo Zhejian are connected not successfully more than the 4th preset time 10s
Measure wifi hotspot B and network failure be present, it is unavailable to be interpreted as wifi hotspot B, after continuing to coming the wifi hotspot
Wifi hotspot (A, C) is attached operation.
It should be noted that first preset time~the 4th preset time, default acquiescence score value, predetermined
Parameter, the rule that the needs such as drop power rule are pre-set, user can be adjusted according to actual conditions.
The electronic installation 1 that the present embodiment proposes, by obtaining the historical data of wifi hotspot, real-time update calculates wifi heat
The Logic Regression Models of point scoring, the probability of the following possible successful connection of wifi hotspot is calculated, then successively according to wifi hotspot
Signal intensity, scoring score value are ranked up to wifi hotspot, are finally selected optimal wifi hotspot for user and are attached behaviour
Make, lift user's online experience.
Alternatively, in other embodiments, wifi hotspot linker 10 can also be divided into one or more mould
Block, one or more module are stored in memory 11, and by the place in one or more processors, such as the present embodiment
Manage performed by device 12, to complete the present invention.Module alleged by the present invention is the series of computation machine for referring to complete specific function
Programmed instruction section.
It is the module diagram of wifi hotspot linker 10 in Fig. 1 for example, referring to shown in Fig. 2.In the present embodiment,
Wifi hotspot linker 10 can be divided into:Receiving module 110, update module 120, the first grading module 130, second are commented
Sub-module 140, order module 150 and link block 160.The function or operating procedure that the module 110-160 is realized with
It is similar above, no longer it is described in detail herein, exemplarily, such as wherein:
Receiving module 110, the available multiple wifi hotspots and the multiple wifi heat arrived for receiving client scan
Historical data o'clock in the first preset time;
Update module 120, for every the second preset time, using the multiple wifi hotspot in second preset time
Interior historical data, predetermined Logic Regression Models are updated, by the model text of the Logic Regression Models after renewal
Part is preserved into memory;
First grading module 130, for being returned according to the historical data in the first preset time and the logic after the renewal
Return model, calculate the first scoring of the multiple wifi hotspot;
Second grading module 140, for reading connection failure of the multiple wifi hotspot in the 3rd preset time time
Number, it is adjusted, obtains the multiple according to the first scoring of the predetermined drop power rule to the multiple wifi hotspot
Second scoring of wifi hotspot;
Order module 150, for sequence step:According to the signal intensity of the multiple wifi hotspot and the second height to score
It is low, the multiple wifi hotspot is ranked up;And
Link block 160, for attempting to connect the multiple wifi hotspot successively according to ranking results.
In addition, the present invention also provides a kind of wifi hotspot connection method.Shown in reference picture 3, connect for wifi hotspot of the present invention
Connect the flow chart of method first embodiment.This method can be performed by a device, and the device can be real by software and/or hardware
It is existing.
In the present embodiment, wifi hotspot connection method includes:Step S10, step S20, step S30, step S40, step
Rapid S50 and step S60.
Step S10, the available multiple wifi hotspots and the multiple wifi hotspot that reception client scan arrives are first
Historical data in preset time.
For example, the client release that wifi hotspot linker is mounted in the client that each user uses is (simple afterwards
Claim APP), client is attached wifi hotspot by the APP and operated.The APP is persistently scanned in current location by client
Available multiple wifi hotspots, electronic installation receives multiple wifi hotspots that APP is arrived by client scan, and collects each user
The historical data of the plurality of wifi hotspot accessed in the first preset time (nearly three months), including:Wifi title, quilt
Access time and duration, mode of operation (successful connection, connection failure, log in successfully, log in unsuccessfully etc.), the accessed frequency, be
No operator's offer etc..Historical data is uploaded to log server by electronic installation, and is extracted by data warehouse technology (ETL)
Go out crucial historical data, such as wifi marks, time, position, attended operation, online duration, successful connection number, connection failure time
Number, number of retries, log in number of success, log in frequency of failure etc., preserving into memory, for follow-up progress model modification and commenting
Divide operation.
Step S20, every the second preset time, utilize history of the multiple wifi hotspot in second preset time
Data, predetermined Logic Regression Models are updated, by the model file of the Logic Regression Models after renewal preserve to
In memory.
Specifically, the predetermined Logic Regression Models are obtained by way of off-line training:To above-mentioned crucial number
According to being analyzed, from time dimension, operator ,/shared focus dimension, connect/logs in/retried/online duration statistics etc. structure
The aspect of model is made, determines model label;Monthly, day counting user uses the frequency and data volume of wifi hotspot, determines that the time is grown
Spend for the dimension of nearest three months, nearest one week, along with " operator/shared focus ", " connect and/log in/retrying/when surfing the Net
It is long " dimension is combined into series of features, such as nearest Ge Yue operators connect into power, nearest one week wifi hotspot retries
Number etc..Then using nearest trimestral crucial historical data as training set, Random Forest model is trained, used
Preserved in the Logic Regression Models to be scored wifi hotspot, and by the model file of the Logic Regression Models to memory
In.Scoring on each wifi hotspot is trained and calculated using it to the model has had the computational methods of maturation,
It will not be repeated here.
It is understood that the advantages of off-line training model is that substantial amounts of historical data, sample are abundant.On-line training
The advantages of model is can to utilize newest data, and model adapts to the change of real time data, in data distribution and history gap
In the case of larger, on-time model is more accurate.In order that the scoring for each wifi hotspot being subsequently calculated is more accurate, every
Second preset time (such as one day) is updated to above-mentioned Logic Regression Models.Make off-line training and on-line training by combining
Two ways, both advantages, the degree of accuracy of lift scheme can be taken, while prevented under thread environment, data volume very little or
Caused by network, system problem the problems such as real-time model renewal failure.
In one embodiment, model training is to use sample data, using optimized algorithm, iterative model parameter
Process.The target of optimized algorithm iterative calculation is so that the loss function value of model is minimum, for Logic Regression Models, Wo Menli
L-BFGS Algorithm for Training is used under thread environment, obtains parameter sets S0, i.e. offline model results;In thread environment, use
FTRL-Proximal algorithms, set S0 is as initial value for loading, using the data of the next wifi hotspot reached in real time, enters
Row once calculates, and the result of calculating is new set of parameter values S1;The like, then when thering is real time data to reach, use
For S1 as input, it is newest model that result S2, the last result of calculation Sn, which is calculated,.
Step S30, according to the historical data in the first preset time and the Logic Regression Models after the renewal, calculate institute
State the first scoring of multiple wifi hotspots.After multiple wifi hotspots of client end AP P transmissions are received, called from memory
Historical data in the model file of the Logic Regression Models and the multiple wifi hotspot three months, is inputted model,
The first scoring of the multiple wifi hotspot, that is, the multiple wifi hotspot are obtained in the general of following possible successful connection
Rate.
Step S40, connection failure number of the multiple wifi hotspot in the 3rd preset time is read, according to true in advance
First scoring of the fixed drop power rule to the multiple wifi hotspot is adjusted, and obtain the multiple wifi hotspot second is commented
Point.In the present embodiment, in order to further ensure that the reliability of the first of above-mentioned multiple wifi hotspots the scoring, according to predetermined
Drop power rule, the first of the multiple wifi hotspot the scoring is adjusted.The predetermined drop power rule includes:Read
Take connection failure number of multiple wifi hotspots in the 3rd preset time described in historical data;When the connection failure number
During less than the first predetermined threshold value, retain the multiple wifi hotspot first scoring, second as the multiple wifi hotspot
Scoring;When the connection failure number is more than the first predetermined threshold value and is less than the second predetermined threshold value, by the multiple wifi heat
The first coefficient is multiplied by first scoring of point, the second scoring as the multiple wifi hotspot;And when the connection failure number
During more than the second predetermined threshold value, the second coefficient is multiplied by the first scoring of the multiple wifi hotspot, as the multiple wifi
Second scoring of focus.
By taking wifi hotspot A, B, C as an example, the first of wifi hotspot A, B, C is respectively:9.0、8.5、9.5.Assuming that the
Three preset times are 30min, and the first predetermined threshold value is 5, and the second predetermined threshold value is 10, and the first coefficient is 0.8, and the second coefficient is
0.4, reading the connection failure number of wifi hotspot A, B, C in 30min is respectively:8th, 3,15, wifi hotspot A is in 30min
Connection failure number be more than first predetermined threshold value and be less than the second predetermined threshold value, therefore the second of wifi hotspot A scores and is
7.2;Connection failure numbers of the wifi hotspot B in 30min is less than first predetermined threshold value, therefore the second of wifi hotspot B comments
It is divided into 8.5;Connection failure numbers of the wifi hotspot C in 30min is more than the second predetermined threshold value, therefore the second of wifi hotspot C comments
It is divided into 3.8.
Specifically, a kind of situation be present, in the multiple wifi hotspot, there is a wifi hotspot there is no historical data, that
The Logic Regression Models can not calculate the first scoring of the wifi hotspot, and can not also calculate the wifi hotspot second is commented
Point, for this kind of wifi hotspot, take default acquiescence scoring or take the second of other multiple wifi hotspots score be averaged
Value, is assigned to this kind of wifi hotspot.Further, when acquiescence scoring with the second of other multiple wifi hotspots score be averaged
When being worth inconsistent, the second scoring as this kind of wifi hotspot that score value is high is taken.
Step S50, according to the signal intensity of the multiple wifi hotspot and the second height to score, to the multiple wifi
Focus is ranked up.
It should be noted that for same wifi hotspot, different clients arrives the wifi in different position scanning
The signal intensity of focus is different, and still, the scoring to the wifi hotspot is consistent, therefore scoring that can not only according to each wifi hotspot
Each wifi hotspot is ranked up, it is also necessary to consider the signal intensity of each wifi hotspot.By taking wifi hotspot A, B, C as an example, according to
Above-mentioned drop power rule obtains the second of wifi hotspot A, B, C and is respectively:7.2nd, 8.5,3.8, the signal of wifi hotspot A, B is strong
Section is spent all between -35dbm~-60dbm, and wifi hotspot C signal intensity section is between -60dbm~-85dbm, specifically
Ground, the sequence step include:
According to the strong and weak order of the current signal intensity of the multiple wifi hotspot, the multiple wifi hotspot is arranged
Sequence (A=B > C);For two or more wifi hotspots of the current signal strength in same signal intensity section, according to described
The sequence of second scoring of two or more wifi hotspots is ranked up (B > A), therefore final ranking results are B, A, C.
Step S60, attempt to connect the multiple wifi hotspot successively according to ranking results.According to final ranking results, electricity
Sub-device is attached operation to wifi hotspot B, A, C successively according to wifi hotspot B, A, C order.
Further, after client is successfully connected a wifi hotspot in the 4th preset time, wifi heat is detected
Whether point is really available, if the wifi hotspot is unavailable, continues to be attached behaviour to coming the wifi hotspot after the wifi hotspot
Make.Assuming that the 4th preset time is 10s, when client is successfully connected a wifi hotspot B in 10s, wifi hotspot B is detected
Whether really can use, for example, utilizing " ping " order to check whether wifi hotspot B network connects, analyze and judge wifi heat
Point B whether there is network failure.If it is understood that connect wifi hotspot B not successfully more than the 4th preset time 10s, or
Person detects that wifi hotspot B has network failure, and it is unavailable to be interpreted as wifi hotspot B, after continuing to coming the wifi hotspot
Wifi hotspot (A, C) be attached operation.
It should be noted that first preset time~the 4th preset time, default acquiescence score value, predetermined
Parameter, the rule that the needs such as drop power rule are pre-set, user can be adjusted according to actual conditions.
The wifi hotspot connection method that the present embodiment proposes, by obtaining the historical data of wifi hotspot, real-time update meter
Calculate the Logic Regression Models of wifi hotspot scoring, calculate wifi hotspot it is following may successful connection probability, then basis successively
Wifi hotspot signal intensity, scoring score value are ranked up to wifi hotspot, are finally selected optimal wifi hotspot for user and are gone forward side by side
Row attended operation, lift user's online experience.
In addition, the embodiment of the present invention also proposes a kind of computer-readable recording medium, the computer-readable recording medium
On be stored with wifi hotspot linker, following operation is realized when the wifi hotspot linker is executed by processor:
Receiving step:The available multiple wifi hotspots and the multiple wifi hotspot that reception client scan arrives are first
Historical data in preset time;
Model modification step:Every the second preset time, using the multiple wifi hotspot in second preset time
Historical data, predetermined Logic Regression Models are updated, by the model file of the Logic Regression Models after renewal
Preserve into memory;
Score step:According to the historical data in the first preset time and the Logic Regression Models after the renewal, calculate
First scoring of the multiple wifi hotspot;
Score set-up procedure:Connection failure number of the multiple wifi hotspot in the 3rd preset time is read, according to
First scoring of the predetermined drop power rule to the multiple wifi hotspot is adjusted, and obtains the multiple wifi hotspot
Second scoring;
Sequence step:According to the signal intensity of the multiple wifi hotspot and the second height to score, to the multiple
Wifi hotspot is ranked up;And
Connection Step:Attempt to connect the multiple wifi hotspot successively according to ranking results.
The embodiment of the computer-readable recording medium of the present invention is specific with above-mentioned wifi hotspot connection method
Embodiment is roughly the same, will not be repeated here.
It should be noted that herein, term " comprising ", "comprising" or its any other variant are intended to non-row
His property includes, so that process, device, article or method including a series of elements not only include those key elements, and
And also include the other element being not expressly set out, or also include for this process, device, article or method institute inherently
Key element.In the absence of more restrictions, the key element limited by sentence "including a ...", it is not excluded that including this
Other identical element also be present in the process of key element, device, article or method.
The embodiments of the present invention are for illustration only, do not represent the quality of embodiment.Embodiment party more than
The description of formula, it is required general that those skilled in the art can be understood that above-described embodiment method can add by software
The mode of hardware platform is realized, naturally it is also possible to which by hardware, but the former is more preferably embodiment in many cases.It is based on
Such understanding, the part that technical scheme substantially contributes to prior art in other words can be with software products
Form embody, the computer software product is stored in a storage medium (such as ROM/RAM, magnetic disc, light as described above
Disk) in, including some instructions are make it that a station terminal equipment (can be mobile phone, computer, server, or the network equipment
Deng) perform method described in each embodiment of the present invention.
The preferred embodiments of the present invention are these are only, are not intended to limit the scope of the invention, it is every to utilize this hair
The equivalent structure or equivalent flow conversion that bright specification and accompanying drawing content are made, or directly or indirectly it is used in other related skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of wifi hotspot connection method, applied to electronic installation, the electronic installation passes through the one or more visitors of network connection
Family end, it is characterised in that methods described includes:
Receiving step:The available multiple wifi hotspots and the multiple wifi hotspot that reception client scan arrives are default first
Historical data in time;
Model modification step:Every the second preset time, the multiple wifi hotspot going through in second preset time is utilized
History data, predetermined Logic Regression Models are updated, the model file of the Logic Regression Models after renewal is preserved
Into memory;
Score step:According to the historical data in the first preset time and the Logic Regression Models after the renewal, described in calculating
First scoring of multiple wifi hotspots;
Score set-up procedure:Connection failure number of the multiple wifi hotspot in the 3rd preset time is read, according to advance
First scoring of the drop power rule of determination to the multiple wifi hotspot is adjusted, and obtains the second of the multiple wifi hotspot
Scoring;
Sequence step:According to the signal intensity of the multiple wifi hotspot and the second height to score, to the multiple wifi heat
Point is ranked up;And
Connection Step:Attempt to connect the multiple wifi hotspot successively according to ranking results.
2. wifi hotspot connection method as claimed in claim 1, it is characterised in that this method is further comprising the steps of:
After client is successfully connected a wifi hotspot in the 4th preset time, detect whether the wifi hotspot really may be used
With if the wifi hotspot is unavailable, continuing to be attached operation to coming the wifi hotspot after the wifi hotspot.
3. wifi hotspot connection method according to claim 1, it is characterised in that the predetermined drop power rule bag
Include:
Read connection failure number of multiple wifi hotspots in the 3rd preset time described in historical data;
When the connection failure number is less than the first predetermined threshold value, retain the first scoring of the multiple wifi hotspot, as
Second scoring of the multiple wifi hotspot;
When the connection failure number is more than the first predetermined threshold value and is less than the second predetermined threshold value, by the multiple wifi heat
The first coefficient is multiplied by first scoring of point, as the second scoring of the multiple wifi hotspot, wherein, first predetermined threshold value
Less than the second predetermined threshold value;And
When the connection failure number is more than second predetermined threshold value, the first scoring of the multiple wifi hotspot is multiplied by
Second coefficient, the second scoring as the multiple wifi hotspot.
4. wifi hotspot connection method according to claim 1, it is characterised in that the sequence step includes:
According to the strong and weak order of the current signal intensity of the multiple wifi hotspot, the multiple wifi hotspot is ranked up;
And
For two or more wifi hotspots of the current signal strength in same signal intensity section, according to described two or more
The sequence of second scoring of individual wifi hotspot is ranked up.
5. wifi hotspot connection method as claimed in claim 1, it is characterised in that the scoring step also includes:
To there is no the wifi hotspot of historical data to assign an acquiescence scoring in the multiple wifi hotspot or assigning other multiple
The average mark of second scoring of wifi hotspot.
6. a kind of electronic installation, it is characterised in that the electronic installation includes:Memory, processor, it is stored with the memory
Wifi hotspot linker, following steps are realized when the wifi hotspot linker is by the computing device:
Receiving step:The available multiple wifi hotspots and the multiple wifi hotspot that reception client scan arrives are default first
Historical data in time;
Model modification step:Every the second preset time, the multiple wifi hotspot going through in second preset time is utilized
History data, predetermined Logic Regression Models are updated, the model file of the Logic Regression Models after renewal is preserved
Into memory;
Score step:According to the historical data in the first preset time and the Logic Regression Models after the renewal, described in calculating
First scoring of multiple wifi hotspots;
Score set-up procedure:Connection failure number of the multiple wifi hotspot in the 3rd preset time is read, according to advance
First scoring of the drop power rule of determination to the multiple wifi hotspot is adjusted, and obtains the second of the multiple wifi hotspot
Scoring;
Sequence step:According to the signal intensity of the multiple wifi hotspot and the second height to score, to the multiple wifi heat
Point is ranked up;And
Connection Step:Attempt to connect the multiple wifi hotspot successively according to ranking results.
7. electronic installation according to claim 6, it is characterised in that the wifi hotspot linker is by the processor
Following steps are also realized during execution:
After client is successfully connected a wifi hotspot in the 4th preset time, detect whether the wifi hotspot really may be used
With if the wifi hotspot is unavailable, continuing to be attached operation to coming the wifi hotspot after the wifi hotspot.
8. electronic installation according to claim 6, it is characterised in that the predetermined drop power rule includes:
Read connection failure number of multiple wifi hotspots in the 3rd preset time described in historical data;
When the connection failure number is less than the first predetermined threshold value, retain the first scoring of the multiple wifi hotspot, as
Second scoring of the multiple wifi hotspot;
When the connection failure number is more than the first predetermined threshold value and is less than the second predetermined threshold value, by the multiple wifi heat
The first coefficient is multiplied by first scoring of point, the second scoring as the multiple wifi hotspot;And
When the connection failure number is more than the second predetermined threshold value, the first scoring of the multiple wifi hotspot is multiplied by second
Coefficient, the second scoring as the multiple wifi hotspot.
9. electronic installation according to claim 6, it is characterised in that the sequence step includes:
According to the strong and weak order of the current signal intensity of the multiple wifi hotspot, the multiple wifi hotspot is ranked up;
And
For two or more wifi hotspots of the current signal strength in same signal intensity section, according to described two or more
The sequence of second scoring of individual wifi hotspot is ranked up.
10. a kind of computer-readable recording medium, it is characterised in that wifi heat is stored with the computer-readable recording medium
Point linker, is realized as any one of claim 1 to 5 when the wifi hotspot linker is executed by processor
The step of wifi hotspot connection method.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710884576.2A CN107835520B (en) | 2017-09-26 | 2017-09-26 | Wifi hotspot connection method and device and storage medium |
PCT/CN2018/076180 WO2019061993A1 (en) | 2017-09-26 | 2018-02-10 | Wi-fi hotspot connection method, device and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710884576.2A CN107835520B (en) | 2017-09-26 | 2017-09-26 | Wifi hotspot connection method and device and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107835520A true CN107835520A (en) | 2018-03-23 |
CN107835520B CN107835520B (en) | 2021-01-05 |
Family
ID=61643447
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710884576.2A Active CN107835520B (en) | 2017-09-26 | 2017-09-26 | Wifi hotspot connection method and device and storage medium |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN107835520B (en) |
WO (1) | WO2019061993A1 (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108601040A (en) * | 2018-07-23 | 2018-09-28 | 连尚(新昌)网络科技有限公司 | A kind of wireless access point sort method and equipment |
CN108810916A (en) * | 2018-04-17 | 2018-11-13 | 深圳平安讯科技术有限公司 | Wi-Fi Hotspot recommends method, apparatus and storage medium |
CN108848545A (en) * | 2018-07-02 | 2018-11-20 | 晶晨半导体(上海)股份有限公司 | A kind of method for intelligent connection and system of wireless access point |
CN109195204A (en) * | 2018-11-12 | 2019-01-11 | Oppo广东移动通信有限公司 | Wireless network access method and device, computer-readable medium, communication terminal |
CN110856233A (en) * | 2019-11-14 | 2020-02-28 | Oppo广东移动通信有限公司 | Communication control method and related product |
CN111866994A (en) * | 2020-07-26 | 2020-10-30 | 广云物联网科技(广州)有限公司 | Method and device for rapidly distributing network at hot spot |
CN113810947A (en) * | 2021-10-29 | 2021-12-17 | 中国联合网络通信集团有限公司 | WiFi network quality evaluation method and device, electronic equipment and storage medium |
CN113839820A (en) * | 2021-10-14 | 2021-12-24 | 福建天晴数码有限公司 | Method and system for searching optimal network updating node during service updating |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP2362689A1 (en) * | 2010-02-26 | 2011-08-31 | Research In Motion Limited | Storage of radio information on a removable memory |
CN102907121A (en) * | 2010-05-20 | 2013-01-30 | At&T移动第二有限责任公司 | WI-FI intelligent selection engine |
CN104768156A (en) * | 2015-04-30 | 2015-07-08 | 北京奇虎科技有限公司 | WiFi connection method and device |
CN105376700A (en) * | 2015-11-23 | 2016-03-02 | 努比亚技术有限公司 | An access device and method for a free Wi-Fi network |
CN105657790A (en) * | 2016-03-23 | 2016-06-08 | 深圳优克云联科技有限公司 | Network connecting method, device and system |
-
2017
- 2017-09-26 CN CN201710884576.2A patent/CN107835520B/en active Active
-
2018
- 2018-02-10 WO PCT/CN2018/076180 patent/WO2019061993A1/en active Application Filing
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP2362689A1 (en) * | 2010-02-26 | 2011-08-31 | Research In Motion Limited | Storage of radio information on a removable memory |
CN102907121A (en) * | 2010-05-20 | 2013-01-30 | At&T移动第二有限责任公司 | WI-FI intelligent selection engine |
CN104768156A (en) * | 2015-04-30 | 2015-07-08 | 北京奇虎科技有限公司 | WiFi connection method and device |
CN105376700A (en) * | 2015-11-23 | 2016-03-02 | 努比亚技术有限公司 | An access device and method for a free Wi-Fi network |
CN105657790A (en) * | 2016-03-23 | 2016-06-08 | 深圳优克云联科技有限公司 | Network connecting method, device and system |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108810916A (en) * | 2018-04-17 | 2018-11-13 | 深圳平安讯科技术有限公司 | Wi-Fi Hotspot recommends method, apparatus and storage medium |
CN108810916B (en) * | 2018-04-17 | 2022-08-12 | 深圳平安通信科技有限公司 | Wi-Fi hotspot recommendation method and device and storage medium |
CN108848545A (en) * | 2018-07-02 | 2018-11-20 | 晶晨半导体(上海)股份有限公司 | A kind of method for intelligent connection and system of wireless access point |
CN108601040B (en) * | 2018-07-23 | 2022-03-04 | 上海尚往网络科技有限公司 | Wireless access point ordering method and device |
CN108601040A (en) * | 2018-07-23 | 2018-09-28 | 连尚(新昌)网络科技有限公司 | A kind of wireless access point sort method and equipment |
CN109195204A (en) * | 2018-11-12 | 2019-01-11 | Oppo广东移动通信有限公司 | Wireless network access method and device, computer-readable medium, communication terminal |
CN110856233B (en) * | 2019-11-14 | 2022-04-22 | Oppo广东移动通信有限公司 | Communication control method and related product |
CN110856233A (en) * | 2019-11-14 | 2020-02-28 | Oppo广东移动通信有限公司 | Communication control method and related product |
CN111866994A (en) * | 2020-07-26 | 2020-10-30 | 广云物联网科技(广州)有限公司 | Method and device for rapidly distributing network at hot spot |
CN113839820A (en) * | 2021-10-14 | 2021-12-24 | 福建天晴数码有限公司 | Method and system for searching optimal network updating node during service updating |
CN113839820B (en) * | 2021-10-14 | 2023-08-11 | 福建天晴数码有限公司 | Method and system for searching optimal network updating node during updating service |
CN113810947A (en) * | 2021-10-29 | 2021-12-17 | 中国联合网络通信集团有限公司 | WiFi network quality evaluation method and device, electronic equipment and storage medium |
CN113810947B (en) * | 2021-10-29 | 2023-05-09 | 中国联合网络通信集团有限公司 | WiFi network quality assessment method and device, electronic equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
WO2019061993A1 (en) | 2019-04-04 |
CN107835520B (en) | 2021-01-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107835520A (en) | Wifi hotspot connection method, device and storage medium | |
CN106202117B (en) | Data processing method and device and server | |
CN104966046B (en) | A kind of appraisal procedure of face key point positioning result, and apparatus for evaluating | |
CN103959282A (en) | Selective feedback for text recognition systems | |
CN109509017B (en) | User retention prediction method and device based on big data analysis | |
CN108280115A (en) | Identify the method and device of customer relationship | |
CN110515951B (en) | BOM standardization method and system, electronic device and storage medium | |
CN109146539A (en) | The update method and device of user's portrait | |
CN107886400A (en) | A kind of recipe recommendation method, device and mobile terminal | |
CN107734594A (en) | Personalized wifi hotspot method for pushing, device and storage medium | |
CN107742221A (en) | A kind of processing method of promotion message, device and system | |
CN110969327B (en) | Work order dispatching method, device, system and data processing method | |
CN107809740B (en) | Wi-Fi hotspot deployment optimization method, server and storage medium | |
CN111143543A (en) | Object recommendation method, device, equipment and medium | |
CN108566666A (en) | Wi-Fi Hotspot recommends method, apparatus and storage medium | |
CN110392414B (en) | Wireless network connection method and device, terminal equipment and readable storage medium | |
CN110969240B (en) | Pruning method, device, equipment and medium for deep convolutional neural network | |
US11240777B2 (en) | Device positioning method and apparatus | |
CN108579094A (en) | A kind of user interface detection method and relevant apparatus, system and storage medium | |
CN107204898A (en) | Production test method, system and the storage device of intelligent appliance, mobile terminal | |
CN111625690A (en) | Object recommendation method, device, equipment and medium | |
CN113837793A (en) | Supplier recommendation method and device, storage medium and terminal | |
CN110796096B (en) | Training method, device, equipment and medium for gesture recognition model | |
CN105955507B (en) | A kind of display methods and terminal of soft keyboard | |
CN109033874B (en) | Multi-role login method and system for Android program of digital sea information based on SQlite database |
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 |