CN109240875A - A kind of Caton analysis method and system - Google Patents
A kind of Caton analysis method and system Download PDFInfo
- Publication number
- CN109240875A CN109240875A CN201810764779.2A CN201810764779A CN109240875A CN 109240875 A CN109240875 A CN 109240875A CN 201810764779 A CN201810764779 A CN 201810764779A CN 109240875 A CN109240875 A CN 109240875A
- Authority
- CN
- China
- Prior art keywords
- caton
- scene
- probability
- gesture path
- record
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3051—Monitoring arrangements for monitoring the configuration of the computing system or of the computing system component, e.g. monitoring the presence of processing resources, peripherals, I/O links, software programs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
- G06F11/3447—Performance evaluation by modeling
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Biology (AREA)
- Computer Hardware Design (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computing Systems (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The invention discloses a kind of Caton analysis method and systems, which comprises receives the gesture path record that client uploads；By gesture path record input Caton analysis model trained in advance, Caton analysis result is obtained, wherein the Caton analysis result includes the probability of the corresponding each Caton scene of gesture path record；Current Caton scene is obtained based on Caton analysis result.It can accurately judge corresponding Caton scene, to be handled in real time Caton reason, optimization stops loss efficiency.
Description
[technical field]
The present invention relates to Computer Applied Technologies, in particular to Caton analysis method and system.
[background technique]
With the continuous development of smart phone technology, a part indispensable in people's daily life is had become.It is right
The use of smart phone is mainly reflected in the use to various APP.It is not difficult readily understood, good user experience is other all mesh
The key of target basis and quality assurance.For example, the playability of mobile phone games APP is largely determined by Caton.It is sent out by investigation
Existing, with the performance boost of user mobile phone, Caton generates bottleneck in the migration that essence occurs.Its main restricting factor is
By user mobile phone performance, become APP quality itself, building environment, concurrent three dimensions in peak.
Caton detection technique on the common line of industry at present is the great expense incurred for relying on cell phone customer end equipment, passes through length
Connection, a large amount of electricity of consumption user equipment, flow, and will lead to that mobile phone is hot and fee suction, caused by damage and be much larger than
Expected value.
With the change of Caton main restricting factor, the main generation bottleneck of Caton is not in client device, so uncommon
It hopes and relies on monitor client precise positioning Caton problem, be tantamount to climb a tree to seek fish.
Caton monitoring and report in client device, observation point systems such as CPU, RAM of client device nothing more than
Resource.Even if Caton main cause is present in client, these observation points can not accurately early warning problem.For example, IOS Installed System Memory
Occupancy reaches 90% still unusual process, and certain android system EMS memory occupations be more than 80% may Caton.On the market
The Android ROM of mainstream is as many as tens of kinds, and renewal frequency is increasingly come.It may not be fitted comprehensively for every a ROM
Match.Therefore it is difficult to find reliable dimension and threshold values to be monitored early warning to FTP client FTP resource.If long-term rate of false alarm compared with
Height, monitoring equipment can lose due warning meaning, just in case really encountering risk, engineer in the state of numbness, also do by difficulty
The fastest reaction out.
To sum up, it would be highly desirable to which a kind of new line is improved quality monitoring technology, the new business pain spot of reply with a definite target in view.Solve tradition
The not covered dimension of client Caton detection technique institute.
[summary of the invention]
The many aspects of the application provide Caton analysis method, system, equipment and storage medium, can accurately sentence
Disconnected corresponding Caton scene, to be handled in real time Caton reason, optimization stops loss efficiency.
An aspect of of the present present invention provides a kind of Caton analysis method, which comprises
Receive the gesture path record that client uploads；
By gesture path record input Caton analysis model trained in advance, Caton analysis result is obtained, wherein institute
State the probability that Caton analysis result includes the corresponding each Caton scene of gesture path record；
Current Caton scene is obtained based on Caton analysis result.
The aspect and any possible implementation manners as described above, it is further provided a kind of implementation, the Caton point
Analysing model is by being trained to preset neural network.
The aspect and any possible implementation manners as described above, it is further provided a kind of implementation, the Caton point
Analysis model is obtained by the training of following training step:
Using the gesture path being collected under different Caton scenes record and corresponding Caton scene tag as training sample；
Using machine learning method, it is based on the training sample, preset Classification Loss function and back-propagation algorithm pair
The neural network is trained, and obtains Caton analysis model.
The aspect and any possible implementation manners as described above, it is further provided a kind of implementation is based on the card
Analysis result of pausing obtains current Caton scene and includes:
Determine gesture path record be not belonging to Caton scene probability whether be the Caton analysis result maximum
Probability；
If not maximum probability corresponds to the general of each Caton scene from the gesture path then according to the numerical values recited of probability
Probability is chosen in rate, and using the corresponding Caton scene of the probability selected as current Caton scene.
The aspect and any possible implementation manners as described above, it is further provided a kind of implementation, from the gesture
Track corresponds in the probability of each Caton scene and chooses probability further include:
The then sequence descending according to numerical value arranges the probability of the corresponding each Caton scene of gesture path record
Sequence obtains probability sequence；
Preset number probability is chosen since the stem of the probability sequence.
The aspect and any possible implementation manners as described above, it is further provided a kind of implementation, from the gesture
Track corresponds in the probability of each Caton scene and chooses probability further include:
The probability for being not less than probability threshold value is chosen from the probability of the corresponding each Caton scene of gesture path record.
The aspect and any possible implementation manners as described above, it is further provided a kind of implementation, the Caton field
Scape includes:
Weak network interface card scene, CPU intensive scene, APP dodge scape of withdrawing from the arena.
The aspect and any possible implementation manners as described above, it is further provided a kind of implementation, it is described will be different
The gesture path record being collected under Caton scene and corresponding Caton scene tag as training sample include:
Constructing analog Caton scene；
Gesture path record of the user in simulation Caton scene is surveyed in collecting；
The label of Caton scene is corresponded to for collected gesture path recording mark.
Another aspect of the present invention provides a kind of Caton analysis system, the system comprises:
Receiving unit, for receiving the gesture path record of client upload；
Analytical unit obtains Caton point for the Caton analysis model that the input of gesture path record is trained in advance
Analyse result, wherein the Caton analysis result includes the probability of the corresponding each Caton scene of gesture path record；
Output unit, for obtaining current Caton scene based on Caton analysis result.
The aspect and any possible implementation manners as described above, it is further provided a kind of implementation, the Caton point
Analysing model is by being trained to preset neural network.
The aspect and any possible implementation manners as described above, it is further provided a kind of implementation, the system is also
Including training unit, it is used for
Using the gesture path being collected under different Caton scenes record and corresponding Caton scene tag as training sample；
Using machine learning method, it is based on the training sample, preset Classification Loss function and back-propagation algorithm pair
The neural network is trained, and obtains Caton analysis model.
The aspect and any possible implementation manners as described above, it is further provided a kind of implementation, the output are single
Member includes:
Subelement is determined, for determining that the gesture path record is not belonging to whether the probability of Caton scene is the Caton
Analyze the maximum probability of result；
Subelement is generated, is used for if not maximum probability, then corresponding from the gesture path according to the numerical values recited of probability
Probability is chosen in the probability of each Caton scene, and using the corresponding Caton scene of the probability selected as current Caton scene.
The aspect and any possible implementation manners as described above, it is further provided a kind of implementation, generation
Unit is specifically used for:
The then sequence descending according to numerical value arranges the probability of the corresponding each Caton scene of gesture path record
Sequence obtains probability sequence；
Preset number probability is chosen since the stem of the probability sequence.
The aspect and any possible implementation manners as described above, it is further provided a kind of implementation, generation
Unit is specifically used for:
The probability for being not less than probability threshold value is chosen from the probability of the corresponding each Caton scene of gesture path record.
The aspect and any possible implementation manners as described above, it is further provided a kind of implementation, the Caton field
Scape includes:
Weak network interface card scene, CPU intensive scene, APP dodge scape of withdrawing from the arena.
The aspect and any possible implementation manners as described above, it is further provided a kind of implementation, training
Unit is specifically used for:
Constructing analog Caton scene；
Gesture path record of the user in simulation Caton scene is surveyed in collecting；
The label of Caton scene is corresponded to for collected gesture path recording mark.
Another aspect of the present invention, provides a kind of computer equipment, including memory, processor and is stored in the storage
On device and the computer program that can run on the processor, the processor are realized as previously discussed when executing described program
Method.
Another aspect of the present invention provides a kind of computer readable storage medium, is stored thereon with computer program, described
Method as described above is realized when program is executed by processor.
It can be seen that based on above-mentioned introduction using scheme of the present invention, can accurately judge corresponding Caton scene,
To be handled in real time Caton reason, optimization stops loss efficiency.
[Detailed description of the invention]
Fig. 1 is the flow chart of Caton analysis method of the present invention；
Fig. 2 is the structure chart of Caton analysis system of the present invention；
Fig. 3 shows the frame for being suitable for the exemplary computer system/server 012 for being used to realize embodiment of the present invention
Figure.
[specific embodiment]
To keep the purposes, technical schemes and advantages of the embodiment of the present application clearer, below in conjunction with the embodiment of the present application
In attached drawing, the technical scheme in the embodiment of the application is clearly and completely described, it is clear that described embodiment is
Some embodiments of the present application, instead of all the embodiments.Based on the embodiment in the application, those of ordinary skill in the art
Whole other embodiments obtained without creative efforts, shall fall in the protection scope of this application.
Fig. 1 is the flow chart of Caton analysis method embodiment of the present invention, as shown in Figure 1, comprising the following steps:
Step S11, the gesture path record that client uploads is received；
Step S12, the input of gesture path record is trained in advance Caton analysis model, obtains Caton analysis knot
Fruit, wherein the Caton analysis result includes the probability of the corresponding each Caton scene of gesture path record；
Step S13, current Caton scene is obtained based on Caton analysis result.
In a kind of preferred implementation of step S11,
Server receives client install by user mobile phone in real time or the gesture path of user that regularly sends records.
Preferably, the client analyzes targeted APP for the Caton to be carried out, or, the client is only to remember
Record and send the client that user analyzes the Caton to be carried out the gesture path of targeted APP.
Preferably, the gesture path record for the user that client described in the server real-time reception is sent, and to described
Gesture path record is with certain period of time, such as is within 2 minutes one group of carry out cutting.
Preferably, the server receives the client with certain period of time, such as is within 2 minutes the user of one group of transmission
Gesture path record.
Preferably, wherein each period includes a plurality of track.
In a kind of preferred implementation of step S12,
Preferably, gesture path record is pre-processed, for example, every group of gesture path is converted to a N-dimensional
Vector is such as: [D0, D1 ... Dn], wherein D represents a characteristic dimension, including is not limited to: upper sliding operation occurs in this group of gesture
Frequency, downslide operating frequency, clicking operation frequency, long press operation frequency, hand gesture location region (it wants surely as needed, it is common to have
4 point-score of screen, 9 point-scores).The N-dimensional vector is subjected to data normalization processing, each characteristic dimension value is normalized to (0-1)
In section.
By pretreated gesture path record input Caton analysis model trained in advance, Caton analysis knot is obtained
Fruit.
Preferably, the Caton analysis model is by being trained to preset neural network, wherein described
Neural network includes convolutional layer, pond layer, full articulamentum and loss layer, and the neural network includes Bayes, CNN and DNN mind
Through network.
Step A obtains the gesture path record being collected under different Caton scenes and corresponding Caton scene tag conduct
Training sample.
Preferably, modelling structural experiment presets controllable abnormal scene.Such as pass through Ngi nx reverse proxy, construction request
Congestion scene；Smooth network gradual change and weak net scene are simulated by routing speed limit；CPU intensive field is constructed by default floating-point operation
Scape；Abnormal data, which is issued, by cloud constructs controllable crash scene；By special screne actuator in the form of Agent, it is put into survey
Equipment is tried, such as is mounted with the mobile phone of APP to be tested.Can be dynamic, control at any time triggers/closes certain scene.In APP
Interior survey user tries object for appreciation process, does not inform abnormal conditions in advance.In the hope of collecting most true gesture path record, by what is be collected into
Gesture path records the label for stamping corresponding scene automatically.
By automated tag technology, the cost and efficiency of training data can be greatly optimized.
Step B, using the gesture path being collected under different Caton scenes record and corresponding Caton scene tag as instruction
Practice sample；
Preferably, gesture path record is pre-processed, for example, every group of gesture path is converted to a N-dimensional
Vector is such as: [D0, D1 ... Dn], wherein D represents a characteristic dimension, including is not limited to: upper sliding operation occurs in this group of gesture
Frequency, downslide operating frequency, clicking operation frequency, long press operation frequency, hand gesture location region (it wants surely as needed, it is common to have
4 point-score of screen, 9 point-scores).The N-dimensional vector is subjected to data normalization processing, each characteristic dimension value is normalized to (0-1)
In section.
Step C is based on the training sample, preset Classification Loss function and backpropagation using machine learning method
Algorithm is trained the neural network, obtains Caton analysis model.
Preferably, the training sample is inputted into preset neural network, obtains the first identification knot corresponding with the sample
Fruit, above-mentioned actuating station can use preset Classification Loss function to determine mark corresponding to first recognition result and the sample
Difference between label, according to the difference, using preset back-propagation algorithm to the parameter in above-mentioned preset neural network into
Row adjustment.
It should be noted that above-mentioned Classification Loss function can be it is various for classification loss function (such as
HingeLoss function or Softmax Loss function etc.).In the training process, Classification Loss function can be constrained convolution kernel and repair
The mode changed and direction, trained target are to keep the value of Classification Loss function minimum.Thus, the convolutional Neural net obtained after training
Corresponding parameter when being minimum value that the parameter of network is the value of Classification Loss function.
In addition, above-mentioned back-propagation algorithm is alternatively referred to as error backpropagation algorithm or Back Propagation Algorithm.It is reversed to pass
The learning process for broadcasting algorithm is made of forward-propagating process and back-propagation process.In feedforward network, input signal is through inputting
Layer input, is calculated by hidden layer, is exported by output layer.By output valve compared with mark value, if there is error, by error reversely by
It is right to can use gradient descent algorithm (such as stochastic gradient descent algorithm) in this process to input Es-region propagations for output layer
The neuron weight parameter etc. of convolution kernel (such as in convolutional layer) is adjusted.
In a kind of preferred implementation of step S13,
It is preferably based on Caton analysis result and obtains current Caton scene and comprise determining that the gesture path record
Be not belonging to Caton scene probability whether be Caton analysis result maximum probability；If not maximum probability, then according to general
The numerical values recited of rate chooses probability, and the probability pair that will be selected from the probability that the gesture path corresponds to each Caton scene
The Caton scene answered is as current Caton scene.
It may be not limited only to single scene due to the appearance of Caton, but the mixing of multiple scenes；Therefore:
Preferably, probability is chosen from the probability that the gesture path corresponds to each Caton scene further include: then according to numerical value
The probability of the corresponding each Caton scene of gesture path record is ranked up, obtains probability sequence by descending sequence；From
The stem of the probability sequence starts to choose preset number probability.
Preferably, probability is chosen from the probability that the gesture path corresponds to each Caton scene further include: from the gesture
Track record corresponds to the probability chosen in the probability of each Caton scene and be not less than probability threshold value.
In a kind of preferred implementation of the present embodiment,
The server can obtain countermeasure by logic of propositions according to current Caton scene.
Such as receiving current state is Caton, and Caton scene is that CPU intensive scene is fed back to then according to logic of propositions
Load balancing host indicates that new examination plays request and not be connected to the higher host of current CPU usage；Similar also can trigger is moved
State dilatation etc. effectively operates.Perceive and solve at the first time the Caton pain spot of user.
Preferably, the server can recorde the time of origin of the Caton scene, provide with HDFS (Hadoop distribution
Formula file system) be representative asynchronous analysis ability, act on Operation Decision auxiliary.It is triggered using timed task, such as daily
Zero point analyzes previous everyday all data, output analysis result, comprising:
Caton rate-Annual distribution trend, accurately dilatation section period, guarantee user experience can become dynamic storage capacity for guidance
The core inductive component of ability；
Caton rate-Regional Distribution trend instructs precise positioning short slab computer room, in conjunction with unitary variant rule to bad computer room and
Good computer room carries out horizontal ratio analysis, and finally navigating to is CDN, host configuration, the basic optimization Caton rate-APP such as network bandwidth
Distribution trend instructs accurate superseded stability to be in normal distribution end 20% less than the APP or period sexual selection of Caton threshold values
APP, ensure examination play experience maintains higher level
The embodiment according to the present invention can record according to the gesture path of user, extract user by machine learning
Gesture feature can accurately judge corresponding Caton scene, and to be handled in real time Caton reason, optimization stops loss efficiency.
It should be noted that for the various method embodiments described above, for simple description, therefore, it is stated as a series of
Combination of actions, but those skilled in the art should understand that, the application is not limited by the described action sequence because
According to the application, some steps may be performed in other sequences or simultaneously.Secondly, those skilled in the art should also know
It knows, the embodiments described in the specification are all preferred embodiments, related actions and modules not necessarily the application
It is necessary.
The introduction about embodiment of the method above, below by way of Installation practice, to scheme of the present invention carry out into
One step explanation.
Fig. 2 is the structure chart of Caton analysis system embodiment of the present invention, as shown in Figure 2, comprising:
Receiving unit 21, for receiving the gesture path record of client upload；
Analytical unit 22 obtains Caton for the Caton analysis model that the input of gesture path record is trained in advance
Analyze result, wherein the Caton analysis result includes the probability of the corresponding each Caton scene of gesture path record；
Output unit 23, for obtaining current Caton scene based on Caton analysis result.
In a kind of preferred implementation of receiving unit 21,
The receiving unit 21 receives the gesture rail of user that client install by user mobile phone is real-time or regularly sends
Mark record.
Preferably, the client analyzes targeted APP for the Caton to be carried out, or, the client is only to remember
Record and send the client that user analyzes the Caton to be carried out the gesture path of targeted APP.
Preferably, the gesture path record for the user that client described in 21 real-time reception of receiving unit is sent, and it is right
The gesture path record is with certain period of time, such as is within 2 minutes one group of carry out cutting.
Preferably, the receiving unit 21 receives the client with certain period of time, such as is within 2 minutes one group of transmission
The gesture path of user records.
Preferably, wherein each period includes a plurality of track.
In a kind of preferred implementation of analytical unit 22,
Preferably, gesture path record is pre-processed, for example, every group of gesture path is converted to a N-dimensional
Vector is such as: [D0, D1 ... Dn], wherein D represents a characteristic dimension, including is not limited to: upper sliding operation occurs in this group of gesture
Frequency, downslide operating frequency, clicking operation frequency, long press operation frequency, hand gesture location region (it wants surely as needed, it is common to have
4 point-score of screen, 9 point-scores).The N-dimensional vector is subjected to data normalization processing, each characteristic dimension value is normalized to (0-1)
In section.
By pretreated gesture path record input Caton analysis model trained in advance, Caton analysis knot is obtained
Fruit.
Preferably, the system also includes training unit 24, the Caton analysis model be by training unit 24 by pair
What preset neural network was trained, wherein the neural network includes convolutional layer, pond layer, full articulamentum and damage
Layer is lost, the neural network includes Bayes, CNN and DNN neural network.
Step A obtains the gesture path record being collected under different Caton scenes and corresponding Caton scene tag conduct
Training sample.
Preferably, modelling structural experiment presets controllable abnormal scene.Such as by Nginx reverse proxy, construction request is gathered around
Stifled scene；Smooth network gradual change and weak net scene are simulated by routing speed limit；CPU intensive field is constructed by default floating-point operation
Scape；Abnormal data, which is issued, by cloud constructs controllable crash scene；By special screne actuator in the form of Agent, it is put into survey
Equipment is tried, such as is mounted with the mobile phone of APP to be tested.Can be dynamic, control at any time triggers/closes certain scene.In APP
Interior survey user tries object for appreciation process, does not inform abnormal conditions in advance.In the hope of collecting most true gesture path record, by what is be collected into
Gesture path records the label for stamping corresponding scene automatically.
By automated tag technology, the cost and efficiency of training data can be greatly optimized.
Step B, using the gesture path being collected under different Caton scenes record and corresponding Caton scene tag as instruction
Practice sample；
Preferably, gesture path record is pre-processed, for example, every group of gesture path is converted to a N-dimensional
Vector is such as: [D0, D1 ... Dn], wherein D represents a characteristic dimension, including is not limited to: upper sliding operation occurs in this group of gesture
Frequency, downslide operating frequency, clicking operation frequency, long press operation frequency, hand gesture location region (it wants surely as needed, it is common to have
4 point-score of screen, 9 point-scores).The N-dimensional vector is subjected to data normalization processing, each characteristic dimension value is normalized to (0-1)
In section.
Step C is based on the training sample, preset Classification Loss function and backpropagation using machine learning method
Algorithm is trained the neural network, obtains Caton analysis model.
Preferably, the training sample is inputted preset neural network by the analytical unit 22, is obtained and the sample pair
The first recognition result answered, above-mentioned actuating station can use preset Classification Loss function to determine first recognition result and be somebody's turn to do
Difference between label corresponding to sample, according to the difference, using preset back-propagation algorithm to above-mentioned preset nerve
Parameter in network is adjusted.
It should be noted that above-mentioned Classification Loss function can be it is various for classification loss function (such as
HingeLoss function or Softmax Loss function etc.).In the training process, Classification Loss function can be constrained convolution kernel and repair
The mode changed and direction, trained target are to keep the value of Classification Loss function minimum.Thus, the convolutional Neural net obtained after training
Corresponding parameter when being minimum value that the parameter of network is the value of Classification Loss function.
In addition, above-mentioned back-propagation algorithm is alternatively referred to as error backpropagation algorithm or Back Propagation Algorithm.It is reversed to pass
The learning process for broadcasting algorithm is made of forward-propagating process and back-propagation process.In feedforward network, input signal is through inputting
Layer input, is calculated by hidden layer, is exported by output layer.By output valve compared with mark value, if there is error, by error reversely by
It is right to can use gradient descent algorithm (such as stochastic gradient descent algorithm) in this process to input Es-region propagations for output layer
The neuron weight parameter etc. of convolution kernel (such as in convolutional layer) is adjusted.
In a kind of preferred implementation of output unit 23,
Preferably, output unit 23 is based on Caton analysis result and obtains current Caton scene, comprising: determines the hand
Gesture track record be not belonging to Caton scene probability whether be Caton analysis result maximum probability；If not most probably
Rate chooses probability then according to the numerical values recited of probability from the probability that the gesture path corresponds to each Caton scene, and will choose
The corresponding Caton scene of probability out is as current Caton scene.
It may be not limited only to single scene due to the appearance of Caton, but the mixing of multiple scenes；Therefore:
Preferably, probability is chosen from the probability that the gesture path corresponds to each Caton scene further include: then according to numerical value
The probability of the corresponding each Caton scene of gesture path record is ranked up, obtains probability sequence by descending sequence；From
The stem of the probability sequence starts to choose preset number probability.
Preferably, probability is chosen from the probability that the gesture path corresponds to each Caton scene further include: from the gesture
Track record corresponds to the probability chosen in the probability of each Caton scene and be not less than probability threshold value.
In a kind of preferred implementation of the present embodiment,
The server can also include decision package 25, for being obtained according to current Caton scene by logic of propositions
Countermeasure.
Such as receiving current state is Caton, and Caton scene is that CPU intensive scene is fed back to then according to logic of propositions
Load balancing host indicates that new examination plays request and not be connected to the higher host of current CPU usage；Similar also can trigger is moved
State dilatation etc. effectively operates.Perceive and solve at the first time the Caton pain spot of user.
Preferably, the decision package 25 can also record the time of origin of the Caton scene, provide with HDFS
(Hadoop distributed file system) is the asynchronous analysis ability of representative, acts on Operation Decision auxiliary.It is touched using timed task
Hair, such as daily zero point analyze previous everyday all data, output analysis result, comprising:
Caton rate-Annual distribution trend, accurately dilatation section period, guarantee user experience can become dynamic storage capacity for guidance
The core inductive component of ability；
Caton rate-Regional Distribution trend instructs precise positioning short slab computer room, in conjunction with unitary variant rule to bad computer room and
Good computer room carries out horizontal ratio analysis, and finally navigating to is CDN, host configuration, the basic optimization Caton rate-APP such as network bandwidth
Distribution trend instructs accurate superseded stability to be in normal distribution end 20% less than the APP or period sexual selection of Caton threshold values
APP, ensure examination play experience maintains higher level
The embodiment according to the present invention can record according to the gesture path of user, extract user by machine learning
Gesture feature can accurately judge corresponding Caton scene, and to be handled in real time Caton reason, optimization stops loss efficiency.
It is apparent to those skilled in the art that for convenience and simplicity of description, the terminal of the description
It with the specific work process of server, can refer to corresponding processes in the foregoing method embodiment, details are not described herein.
In several embodiments provided herein, it should be understood that disclosed method and apparatus can pass through it
Its mode is realized.For example, the apparatus embodiments described above are merely exemplary, for example, the division of the unit, only
Only a kind of logical function partition, there may be another division manner in actual implementation, such as multiple units or components can be tied
Another system is closed or is desirably integrated into, or some features can be ignored or not executed.Another point, it is shown or discussed
Mutual coupling, direct-coupling or communication connection can be through some interfaces, the INDIRECT COUPLING or logical of device or unit
Letter connection can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
In addition, each functional unit in each embodiment of the application can integrate in a processor, it is also possible to
Each unit physically exists alone, and can also be integrated in one unit with two or more units.The integrated unit
Both it can take the form of hardware realization, can also have been realized in the form of hardware adds SFU software functional unit.
Fig. 3 shows the frame for being suitable for the exemplary computer system/server 012 for being used to realize embodiment of the present invention
Figure.The computer system/server 012 that Fig. 3 is shown is only an example, should not function and use to the embodiment of the present invention
Range band carrys out any restrictions.
As shown in figure 3, computer system/server 012 is showed in the form of universal computing device.Computer system/clothes
The component of business device 012 can include but is not limited to: one or more processor or processor 016, system storage 028,
Connect the bus 018 of different system components (including system storage 028 and processor 016).
Bus 018 indicates one of a few class bus structures or a variety of, including memory bus or Memory Controller,
Peripheral bus, graphics acceleration port, processor or the local bus using any bus structures in a variety of bus structures.It lifts
For example, these architectures include but is not limited to industry standard architecture (ISA) bus, microchannel architecture (MAC)
Bus, enhanced isa bus, Video Electronics Standards Association (VESA) local bus and peripheral component interconnection (PCI) bus.
Computer system/server 012 typically comprises a variety of computer system readable media.These media, which can be, appoints
The usable medium what can be accessed by computer system/server 012, including volatile and non-volatile media, movably
With immovable medium.
System storage 028 may include the computer system readable media of form of volatile memory, such as deposit at random
Access to memory (RAM) 030 and/or cache memory 032.Computer system/server 012 may further include other
Removable/nonremovable, volatile/non-volatile computer system storage medium.Only as an example, storage system 034 can
For reading and writing immovable, non-volatile magnetic media (Fig. 3 do not show, commonly referred to as " hard disk drive ").Although in Fig. 3
It is not shown, the disc driver for reading and writing to removable non-volatile magnetic disk (such as " floppy disk ") can be provided, and to can
The CD drive of mobile anonvolatile optical disk (such as CD-ROM, DVD-ROM or other optical mediums) read-write.In these situations
Under, each driver can be connected by one or more data media interfaces with bus 018.Memory 028 may include
At least one program product, the program product have one group of (for example, at least one) program module, these program modules are configured
To execute the function of various embodiments of the present invention.
Program/utility 040 with one group of (at least one) program module 042, can store in such as memory
In 028, such program module 042 includes --- but being not limited to --- operating system, one or more application program, other
It may include the realization of network environment in program module and program data, each of these examples or certain combination.Journey
Sequence module 042 usually executes function and/or method in embodiment described in the invention.
Computer system/server 012 can also with one or more external equipments 014 (such as keyboard, sensing equipment,
Display 024 etc.) communication, in the present invention, computer system/server 012 is communicated with outside radar equipment, can also be with
One or more equipment that sounder is interacted with the computer system/server 012 communication, and/or with make this
Any equipment that computer system/server 012 can be communicated with one or more of the other calculating equipment (adjust by such as network interface card
Modulator-demodulator etc.) communication.This communication can be carried out by input/output (I/O) interface 022.Also, computer system/
Server 012 can also pass through network adapter 020 and one or more network (such as local area network (LAN), wide area network
(WAN) and/or public network, for example, internet) communication.As shown in figure 3, network adapter 020 passes through bus 018 and computer
Other modules of systems/servers 012 communicate.It should be understood that computer system/service can be combined although being not shown in Fig. 3
Device 012 uses other hardware and/or software module, including but not limited to: microcode, device driver, redundant processor, outside
Disk drive array, RAID system, tape drive and data backup storage system etc..
The program that processor 016 is stored in system storage 028 by operation, thereby executing reality described in the invention
Apply the function and/or method in example.
Above-mentioned computer program can be set in computer storage medium, i.e., the computer storage medium is encoded with
Computer program, the program by one or more computers when being executed, so that one or more computers execute in the present invention
State method flow shown in embodiment and/or device operation.
With time, the development of technology, medium meaning is more and more extensive, and the route of transmission of computer program is no longer limited by
Tangible medium, can also be directly from network downloading etc..It can be using any combination of one or more computer-readable media.
Computer-readable medium can be computer-readable signal media or computer readable storage medium.Computer-readable storage medium
Matter for example may be-but not limited to-system, device or the device of electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, or
Any above combination of person.The more specific example (non exhaustive list) of computer readable storage medium includes: with one
Or the electrical connections of multiple conducting wires, portable computer diskette, hard disk, random access memory (RAM), read-only memory (ROM),
Erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light
Memory device, magnetic memory device or above-mentioned any appropriate combination.In this document, computer readable storage medium can
With to be any include or the tangible medium of storage program, the program can be commanded execution system, device or device use or
Person is in connection.
Computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
Wherein carry computer-readable program code.The data-signal of this propagation can take various forms, including --- but
It is not limited to --- electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be
Any computer-readable medium other than computer readable storage medium, which can send, propagate or
Transmission is for by the use of instruction execution system, device or device or program in connection.
The program code for including on computer-readable medium can transmit with any suitable medium, including --- but it is unlimited
In --- wireless, electric wire, optical cable, RF etc. or above-mentioned any appropriate combination.
The computer for executing operation of the present invention can be write with one or more programming languages or combinations thereof
Program code, described program design language include object oriented program language-such as Java, Smalltalk, C++,
It further include conventional procedural programming language-such as " C " language or similar programming language.Program code can be with
It is fully executed on sounder computer, partly executes on sounder computer, held as an independent software package
Row, partially on sounder computer part on the remote computer execute or completely on a remote computer or server
It executes.In situations involving remote computers, remote computer can pass through the network of any kind --- including local area network
(LAN) or wide area network (WAN) is connected to sounder computer, or, it may be connected to outer computer (such as utilize internet
Service provider is connected by internet).
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of the description,
The specific work process of device and unit, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
In several embodiments provided herein, it should be understood that disclosed method and apparatus can pass through it
Its mode is realized.For example, the apparatus embodiments described above are merely exemplary, for example, the division of the unit, only
Only a kind of logical function partition, there may be another division manner in actual implementation, such as multiple units or components can be tied
Another system is closed or is desirably integrated into, or some features can be ignored or not executed.Another point, it is shown or discussed
Mutual coupling, direct-coupling or communication connection can be through some interfaces, the INDIRECT COUPLING or logical of device or unit
Letter connection can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
In addition, each functional unit in each embodiment of the application can integrate in a processor, it is also possible to
Each unit physically exists alone, and can also be integrated in one unit with two or more units.The integrated unit
Both it can take the form of hardware realization, can also have been realized in the form of hardware adds SFU software functional unit.
Finally, it should be noted that above embodiments are only to illustrate the technical solution of the application, rather than its limitations；Although
The application is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it still may be used
To modify the technical solutions described in the foregoing embodiments or equivalent replacement of some of the technical features；
And these are modified or replaceed, each embodiment technical solution of the application that it does not separate the essence of the corresponding technical solution spirit and
Range.
Claims (18)
1. a kind of Caton analysis method, which is characterized in that the described method includes:
Receive the gesture path record that client uploads；
By gesture path record input Caton analysis model trained in advance, Caton analysis result is obtained, wherein the card
Analysis result of pausing includes the probability of the corresponding each Caton scene of gesture path record；
Current Caton scene is obtained based on Caton analysis result.
2. according to the method described in claim 1, wherein, the Caton analysis model is by carrying out to preset neural network
What training obtained.
3. according to the method described in claim 2, wherein, the Caton analysis model is obtained by the training of following training step
:
Using the gesture path being collected under different Caton scenes record and corresponding Caton scene tag as training sample；
Using machine learning method, based on the training sample, preset Classification Loss function and back-propagation algorithm to described
Neural network is trained, and obtains Caton analysis model.
4. according to the method described in claim 1, wherein, obtaining current Caton scene based on Caton analysis result includes:
Determine gesture path record be not belonging to Caton scene probability whether be the Caton analysis result maximum probability；
If not maximum probability, then according to the numerical values recited of probability, from the probability that the gesture path corresponds to each Caton scene
Probability is chosen, and using the corresponding Caton scene of the probability selected as current Caton scene.
5. according to the method described in claim 4, wherein, being chosen from the probability that the gesture path corresponds to each Caton scene general
Rate further include:
The probability of the corresponding each Caton scene of gesture path record is ranked up by the then sequence descending according to numerical value,
Obtain probability sequence；
Preset number probability is chosen since the stem of the probability sequence.
6. according to the method described in claim 4, wherein, being chosen from the probability that the gesture path corresponds to each Caton scene general
Rate further include:
The probability for being not less than probability threshold value is chosen from the probability of the corresponding each Caton scene of gesture path record.
7. according to the method described in claim 1, wherein, the Caton scene includes:
Weak network interface card scene, CPU intensive scene, APP dodge scape of withdrawing from the arena.
8. according to the method described in claim 3, wherein, it is described by the gesture path being collected under different Caton scenes record and
Corresponding Caton scene tag includes: as training sample
Constructing analog Caton scene；
Gesture path record of the user in simulation Caton scene is surveyed in collecting；
The label of Caton scene is corresponded to for collected gesture path recording mark.
9. a kind of Caton analysis system, which is characterized in that the system comprises:
Receiving unit, for receiving the gesture path record of client upload；
Analytical unit obtains Caton analysis knot for the Caton analysis model that the input of gesture path record is trained in advance
Fruit, wherein the Caton analysis result includes the probability of the corresponding each Caton scene of gesture path record；
Output unit, for obtaining current Caton scene based on Caton analysis result.
10. system according to claim 9, wherein the Caton analysis model be by preset neural network into
Row training obtains.
11. system according to claim 10, wherein the system also includes training units, are used for
Using the gesture path being collected under different Caton scenes record and corresponding Caton scene tag as training sample；
Using machine learning method, based on the training sample, preset Classification Loss function and back-propagation algorithm to described
Neural network is trained, and obtains Caton analysis model.
12. system according to claim 9, wherein the output unit includes:
Determine subelement, whether the probability for determining that the gesture path record is not belonging to Caton scene is the Caton analysis
As a result maximum probability；
Subelement is generated, for if not maximum probability corresponds to each card from the gesture path then according to the numerical values recited of probability
Probability is chosen in the probability for scene of pausing, and using the corresponding Caton scene of the probability selected as current Caton scene.
13. system according to claim 12, wherein the generation subelement is specifically used for:
The probability of the corresponding each Caton scene of gesture path record is ranked up by the then sequence descending according to numerical value,
Obtain probability sequence；
Preset number probability is chosen since the stem of the probability sequence.
14. system according to claim 12, wherein the generation subelement is specifically used for:
The probability for being not less than probability threshold value is chosen from the probability of the corresponding each Caton scene of gesture path record.
15. system according to claim 9, wherein the Caton scene includes:
Weak network interface card scene, CPU intensive scene, APP dodge scape of withdrawing from the arena.
16. according to the method for claim 11, wherein the trained subelement is specifically used for:
Constructing analog Caton scene；
Gesture path record of the user in simulation Caton scene is surveyed in collecting；
The label of Caton scene is corresponded to for collected gesture path recording mark.
17. a kind of computer equipment, including memory, processor and it is stored on the memory and can be on the processor
The computer program of operation, which is characterized in that the processor is realized when executing described program as any in claim 1~8
Method described in.
18. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that described program is processed
Such as method according to any one of claims 1 to 8 is realized when device executes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810764779.2A CN109240875B (en) | 2018-07-12 | 2018-07-12 | Canton analysis method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810764779.2A CN109240875B (en) | 2018-07-12 | 2018-07-12 | Canton analysis method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109240875A true CN109240875A (en) | 2019-01-18 |
| CN109240875B CN109240875B (en) | 2022-05-03 |
Family
ID=65072577
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810764779.2A Active CN109240875B (en) | 2018-07-12 | 2018-07-12 | Canton analysis method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109240875B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109756762A (en) * | 2019-01-29 | 2019-05-14 | 北京奇艺世纪科技有限公司 | A kind of determination method and device of terminal class |
| CN110311806A (en) * | 2019-06-06 | 2019-10-08 | 上海交通大学 | A kind of mobile applications interface operating lag diagnostic method, system and terminal |
| CN110888781A (en) * | 2019-11-21 | 2020-03-17 | 腾讯科技（深圳）有限公司 | Application blockage detection method and detection device |
| CN110908864A (en) * | 2019-11-11 | 2020-03-24 | 腾讯科技（深圳）有限公司 | Equipment blocking processing method, device, equipment and medium |
| CN111260335A (en) * | 2020-02-12 | 2020-06-09 | 上海发才网络信息技术有限公司 | Fission type benefit sharing mode for human resource service promotion |
| CN112445687A (en) * | 2019-08-30 | 2021-03-05 | 深信服科技股份有限公司 | Blocking detection method of computing equipment and related device |
| CN113453076A (en) * | 2020-03-24 | 2021-09-28 | 中国移动通信集团河北有限公司 | User video service quality evaluation method and device, computing equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120037967A1 (en) * | 2010-08-10 | 2012-02-16 | International Business Machines Corporation | Cmos pixel sensor cells with poly spacer transfer gates and methods of manufacture |
| CN104869203A (en) * | 2015-06-18 | 2015-08-26 | 广东欧珀移动通信有限公司 | Unsmooth running testing method and device, and testing equipment |
| CN105260117A (en) * | 2015-09-30 | 2016-01-20 | 小米科技有限责任公司 | Application control method and apparatus |
| CN105389252A (en) * | 2015-10-16 | 2016-03-09 | 华为技术有限公司 | Method and device for feeding back test problem |
| CN105637497A (en) * | 2013-07-12 | 2016-06-01 | 谷歌公司 | Methods and systems for performance monitoring for mobile applications |
| CN106940805A (en) * | 2017-03-06 | 2017-07-11 | 江南大学 | A kind of group behavior analysis method based on mobile phone sensor |
-
2018
- 2018-07-12 CN CN201810764779.2A patent/CN109240875B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120037967A1 (en) * | 2010-08-10 | 2012-02-16 | International Business Machines Corporation | Cmos pixel sensor cells with poly spacer transfer gates and methods of manufacture |
| CN105637497A (en) * | 2013-07-12 | 2016-06-01 | 谷歌公司 | Methods and systems for performance monitoring for mobile applications |
| CN104869203A (en) * | 2015-06-18 | 2015-08-26 | 广东欧珀移动通信有限公司 | Unsmooth running testing method and device, and testing equipment |
| CN105260117A (en) * | 2015-09-30 | 2016-01-20 | 小米科技有限责任公司 | Application control method and apparatus |
| CN105389252A (en) * | 2015-10-16 | 2016-03-09 | 华为技术有限公司 | Method and device for feeding back test problem |
| CN106940805A (en) * | 2017-03-06 | 2017-07-11 | 江南大学 | A kind of group behavior analysis method based on mobile phone sensor |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109756762A (en) * | 2019-01-29 | 2019-05-14 | 北京奇艺世纪科技有限公司 | A kind of determination method and device of terminal class |
| CN109756762B (en) * | 2019-01-29 | 2020-10-02 | 北京奇艺世纪科技有限公司 | Method and device for determining terminal category |
| CN110311806A (en) * | 2019-06-06 | 2019-10-08 | 上海交通大学 | A kind of mobile applications interface operating lag diagnostic method, system and terminal |
| CN112445687A (en) * | 2019-08-30 | 2021-03-05 | 深信服科技股份有限公司 | Blocking detection method of computing equipment and related device |
| CN110908864A (en) * | 2019-11-11 | 2020-03-24 | 腾讯科技（深圳）有限公司 | Equipment blocking processing method, device, equipment and medium |
| CN110908864B (en) * | 2019-11-11 | 2024-05-10 | 腾讯科技（深圳）有限公司 | Equipment jamming processing method, device, equipment and medium |
| CN110888781A (en) * | 2019-11-21 | 2020-03-17 | 腾讯科技（深圳）有限公司 | Application blockage detection method and detection device |
| CN110888781B (en) * | 2019-11-21 | 2021-11-16 | 腾讯科技（深圳）有限公司 | Application blockage detection method and detection device |
| CN111260335A (en) * | 2020-02-12 | 2020-06-09 | 上海发才网络信息技术有限公司 | Fission type benefit sharing mode for human resource service promotion |
| CN113453076A (en) * | 2020-03-24 | 2021-09-28 | 中国移动通信集团河北有限公司 | User video service quality evaluation method and device, computing equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109240875B (en) | 2022-05-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109240875A (en) | A kind of Caton analysis method and system | |
| US10699195B2 (en) | Training of artificial neural networks using safe mutations based on output gradients | |
| US10412105B2 (en) | Automatic detection of network threats based on modeling sequential behavior in network traffic | |
| WO2022111154A1 (en) | Proactive anomaly detection | |
| CN110378544A (en) | A kind of personnel and post matching analysis method, device, equipment and medium | |
| CN108228705A (en) | Automatic object and activity tracking equipment, method and medium in live video feedback | |
| CN106209862A (en) | A kind of steal-number defence implementation method and device | |
| WO2014059183A2 (en) | Methods and automated systems for testing, optimization, and analysis that preserve continuity in identities and status of users who access remote information from different contexts | |
| CN108234472A (en) | Detection method and device, computer equipment and the readable medium of Challenging black hole attack | |
| CN117421684B (en) | Abnormal data monitoring and analyzing method based on data mining and neural network | |
| CN106202489A (en) | A kind of agricultural pest intelligent diagnosis system based on big data | |
| CN115511501A (en) | Data processing method, computer equipment and readable storage medium | |
| CN109362235A (en) | Classify to the affairs at network accessible storage device | |
| CN113190670A (en) | Information display method and system based on big data platform | |
| CN109117352B (en) | Server performance prediction method and device | |
| KR102359090B1 (en) | Method and System for Real-time Abnormal Insider Event Detection on Enterprise Resource Planning System | |
| CN110535850A (en) | Treating method and apparatus, storage medium and the electronic device that account number logs in | |
| CN109255442A (en) | Training method, equipment and the readable medium of control decision module based on artificial intelligence | |
| CN115759748A (en) | Risk detection model generation method and device and risk individual identification method and device | |
| US11640558B2 (en) | Unbalanced sample classification method and apparatus | |
| CN117499821A (en) | Park network management system and method based on optical network technology | |
| CN115935089B (en) | Get-on point recommendation optimization method and system based on RPA technology | |
| CN104317859B (en) | LED display intelligent classification system and method | |
| US11928009B2 (en) | Predicting a root cause of an alert using a recurrent neural network | |
| KR20230138703A (en) | Method and system for generating an event on an object on the screen by recognizing screen information including text and non-text image based on artificial intelligence |
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 |