CN108574595A - A kind of method and apparatus improving service reliability and user experience - Google Patents
A kind of method and apparatus improving service reliability and user experience Download PDFInfo
- Publication number
- CN108574595A CN108574595A CN201710149711.9A CN201710149711A CN108574595A CN 108574595 A CN108574595 A CN 108574595A CN 201710149711 A CN201710149711 A CN 201710149711A CN 108574595 A CN108574595 A CN 108574595A
- Authority
- CN
- China
- Prior art keywords
- exploration
- reply
- instruction
- thread
- replied
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/08—Configuration management of networks or network elements
- H04L41/0803—Configuration setting
- H04L41/0823—Configuration setting characterised by the purposes of a change of settings, e.g. optimising configuration for enhancing reliability
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/08—Configuration management of networks or network elements
- H04L41/0803—Configuration setting
- H04L41/0823—Configuration setting characterised by the purposes of a change of settings, e.g. optimising configuration for enhancing reliability
- H04L41/0836—Configuration setting characterised by the purposes of a change of settings, e.g. optimising configuration for enhancing reliability to enhance reliability, e.g. reduce downtime
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/50—Network service management, e.g. ensuring proper service fulfilment according to agreements
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/50—Network service management, e.g. ensuring proper service fulfilment according to agreements
- H04L41/5061—Network service management, e.g. ensuring proper service fulfilment according to agreements characterised by the interaction between service providers and their network customers, e.g. customer relationship management
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Business, Economics & Management (AREA)
- General Business, Economics & Management (AREA)
- Electrically Operated Instructional Devices (AREA)
- Debugging And Monitoring (AREA)
- Computer And Data Communications (AREA)
Abstract
The present invention provides a kind of method and apparatus improving service reliability and user experience, help to be adaptively adjusted according to different service equipment and network condition and replys stand-by period and instruction transmission number, farthest to utilize the performance of service equipment and network, to improve user experience while ensureing service reliability.The method includes machine learning stage and actual operation phases, it is characterised in that：In the machine learning stage, client sends to service equipment in multiple threads and sounds out data packet, and the thread record for souning out reply for souning out data packet is directed to from the exploration data packet is sent out to the feedback time for souning out reply is received to receiving, the stand-by period will be set for responding to for receiving the most short feedback time for the thread that the exploration is replied；In the actual operation phase, the client waits for the reply of the instruction to being sent out on the single thread according to the reply stand-by period.
Description
Technical field
The present invention relates to computer and software technology field, particularly a kind of raising service reliability and user experience
Method and apparatus.
Background technology
At present in the field of the Internet services, in a network environment due to network or service equipment failure and other reasons and not all
Operation from client can all succeed.To ensure that service equipment is properly received and executes operational order, client is usual
It needs to send identical multiple instruction to an operation.Network environment, used service equipment simultaneously differ, the instruction of transmission
Although number excessively can improve reliability, user experience is also reduced simultaneously；Although and send number of instructions it is very few can
User experience is improved to reply the stand-by period by reduction, but also reduces reliability simultaneously.Service equipment is for coming from visitor
The operation at family end, response speed are determined by the soft hardware performance of its own.In general, the reply stand-by period is longer, operation
The possibility of failure is smaller, i.e., service reliability is higher；Conversely, replying, the stand-by period is shorter, and the possibility of operation failure is bigger,
I.e. service reliability is lower.But the reply stand-by period the long, and user experience will be caused poorer.Which results in user experience and
Service reliability becomes conflict：That is, service reliability may then be sacrificed by improving user experience, improves service reliability and then may be used
User experience can be sacrificed.
Therefore conventionally, as current technology scheme mostly uses UDP (User in network communications
Datagram Protocol, User Datagram Protocol) communication.To improve service reliability, client is usually in single thread
Multiple identical instructions are sent, and wait for the feedback result of corresponding service equipment within a certain period of time.Fig. 1 is in the prior art
Client sends schematic diagram of the instruction to be communicated with service equipment one by one.As shown in Figure 1, client repeatedly sends instruction,
The reply from service equipment is waited for continue if being not received by reply within the short period after each instruction is sent
Instruction is sent, until sending the instruction of predetermined number.Fig. 2 be in the prior art client continuously transmit instruction with service equipment
The schematic diagram communicated.As shown in Fig. 2, client continuous several times send the instruction of predetermined number, then sent out in all instructions
The reply from service equipment is waited in long period after sending.Technical solution in Fig. 1 and Fig. 2 is considered under network environment
UDP transmission unreliability and repeatedly send instruction；In view of service equipment execution operation needs certain time and reply is set
Stand-by period.
From it is above-mentioned in the prior art, it can be found that the prior art has the disadvantage that：It replys the stand-by period and instruction is sent
Number is fixed value, but the soft hardware performance of service equipment is had nothing in common with each other, and used network performance is also not quite similar, therefore
Fixed reply stand-by period and instruction send number can not adapt to different service equipments and network condition completely, can not also know
The optimal value of replying stand-by period and instruction transmission number of the road under different service equipments and network performance, thus can not root
The stand-by period is replied according to the optimal value adjustment under present case and instruction sends number to be carried while ensureing service reliability
High user experience.
Invention content
In view of this, the present invention provides a kind of method and dress improving service reliability and user experience based on machine learning
It sets, helps to be adaptively adjusted according to different service equipment and network condition and reply stand-by period and instruction transmission number,
Farthest to utilize the performance of service equipment and network, to improve user experience while ensureing service reliability.
The present invention is suitable for the Internet services fields such as smart home, and client is adaptively obtained by machine learning strategy and intelligence
The home equipment communication associated reply stand-by period number can be sent with instruction, to be improved while ensureing service reliability
User experience
To achieve the above object, according to an aspect of the invention, there is provided a kind of raising service reliability and user's body
The method tested.
A kind of raising service reliability of the present invention and the method for user experience include machine learning stage and practical operation
Stage, it is characterised in that：In the machine learning stage, client sends to service equipment in multiple threads and sounds out data
Packet, and the thread for receiving the exploration reply for being directed to exploration data packet is recorded from the exploration data packet is sent out to receiving
The feedback time soundd out and replied is stated, will be set for responding to for receiving the most short feedback time for souning out the thread replied
Stand-by period；In the actual operation phase, the client is waited for according to the reply stand-by period in the single line
The reply of the instruction sent out in journey.
Optionally, further include：In the machine learning stage, the client is in multiple threads to the service
Equipment continuously transmits the different exploration data packet of quantity, and records the line to receiving the thread replied of souning out
The number of the exploration data packet in journey, by the minimum exploration number-of-packet in receiving the thread soundd out and replied
Mesh is set as instruction and sends number；In the actual operation phase, the client is in the single thread to the service
Equipment sends the instruction that described instruction sends number.
Optionally, it is characterised in that：If the client described in the actual operation phase does not receive to single described
The reply of the instruction sent out on thread, then the client reenter the machine learning stage, with the determination reply
Stand-by period.
Optionally, it is characterised in that：If the client described in the actual operation phase does not receive to single described
The reply of the instruction sent out on thread, then the client reenter the machine learning stage, to determine described instruction
Send number.
Optionally, it is characterised in that：If do not received in the given time for all exploration data packets sent out
It is replied to the exploration, then determines network or the service equipment failure occur in the machine learning stage.
Optionally, it is characterised in that：The reply stand-by period is determined using the method measured by half, that is, in the machine
Device learns the stage, and the exploration is waited for reply within the predetermined time first, is replied if receiving the exploration, it tries
The exploration is waited for reply in the half the time of the predetermined time, and so on, until when can not receive the exploration reply
In previous trial described reply etc. will be set as receiving most short feedback time described in the thread for souning out reply
Wait for the time.
Optionally, it is characterised in that：Determine that described instruction sends number using the method measured by half, that is, in the machine
Device learns the stage, and the exploration data packet of predetermined number is arranged first in the thread, is replied if receiving the exploration,
The exploration data packet that the half of predetermined number is set in the thread is then attempted, and so on, until institute can not be received
It states to sound out and sets the minimum exploration number of data packets for receiving the thread soundd out and replied in previous trial when replying
It is set to described instruction and sends number.
To achieve the above object, according to another aspect of the present invention, a kind of raising service reliability and user's body are provided
The device tested.
A kind of raising service reliability of the present invention and the device of user experience include machine learning module and practical operation
Module, it is characterised in that：The machine learning module sends to service equipment in multiple threads and sounds out data packet, and to receiving
The thread record replied for the exploration for souning out data packet is from the explorations data packet is sent out to receiving exploration reply
Feedback time, the stand-by period will be set for responding to for receiving the most short feedback time of the thread replied of souning out；
The practical operation module waits for the reply of the instruction to being sent out on the single thread according to the reply stand-by period.
Optionally, further include：The machine learning module continuously transmits in multiple threads to the service equipment
The different exploration data packet of quantity, and the examination in the thread is recorded to the thread for receiving the exploration reply
Minimum exploration number of data packets in receiving the thread soundd out and replied is set as instructing by the number for visiting data packet
Send number；The practical operation module sends described instruction to the service equipment in the single thread and sends number
Instruction.
Optionally, it is characterised in that：If the practical operation module does not receive to being sent out on the single thread
Instruction reply, then the practical operation module notify the machine learning module to redefine the reply stand-by period.
Optionally, it is characterised in that：If the practical operation module does not receive to being sent out on the single thread
Instruction reply, then the practical operation module notify the machine learning module redefine described instruction send number.
Optionally, it is characterised in that：If do not received in the given time for all exploration data packets sent out
It is replied to the exploration, then network or the service equipment failure occurs in the machine learning module determination.
Optionally, it is characterised in that：The reply stand-by period is determined using the method measured by half, that is, the machine
Study module waits for the exploration to reply within the predetermined time first, is replied if receiving the exploration, it tries in institute
Stating in the half the time of predetermined time waits for the exploration to reply, and so on, it will when the exploration is replied until can not receive
In previous trial the reply waiting is set as receiving most short feedback time described in the thread for souning out reply
Time.
Optionally, it is characterised in that：Determine that described instruction sends number using the method measured by half, that is, the machine
The exploration data packet of predetermined number is arranged in study module first in the thread, is replied if receiving the exploration,
The exploration data packet that the half of predetermined number is set in the thread is attempted, and so on, until can not receive described
It sounds out and the minimum exploration number of data packets for receiving the thread soundd out and replied in previous trial is arranged when replying
Number is sent for described instruction.
According to another aspect of the invention, a kind of electronic equipment is provided.
The present invention a kind of electronic equipment include：At least one processor；And at least one processor communication
The memory of connection；Wherein, the memory is stored with the instruction that can be executed by one processor, and described instruction is by institute
It states at least one processor to execute, be improved based on machine learning so that at least one processor execution is provided by the present invention
The method of service reliability and user experience.
In accordance with a further aspect of the present invention, a kind of readable storage medium storing program for executing is provided.
A kind of non-transient computer readable storage medium of the present invention is stored with computer instruction, and the computer instruction is used
The method provided by the present invention for improving service reliability and user experience is executed in making the computer.
According to the technique and scheme of the present invention, the method for service reliability and user experience being improved by using machine learning
And device, it overcomes the fixed reply stand-by period and instruction sends number and can not adapt to different service equipments and network feelings completely
Condition helps to be adaptively adjusted according to different service equipment and network condition and replys stand-by period and instruction transmission number,
Farthest to utilize the performance of service equipment and network, to improve user experience while ensureing service reliability.
Description of the drawings
Attached drawing does not constitute inappropriate limitation of the present invention for more fully understanding the present invention.Wherein：
Fig. 1 is that client sends schematic diagram of the instruction to be communicated with service equipment one by one in the prior art；
Fig. 2 is that client sends schematic diagram of the instruction to be communicated with service equipment one by one in the prior art；
Fig. 3 A are that client according to the ... of the embodiment of the present invention carries out machine learning to obtain reply stand-by period and instruction hair
Send the schematic diagram of number；
Fig. 3 B are that client application according to the ... of the embodiment of the present invention replys the stand-by period and instruction sends number to carry out reality
The schematic diagram of border operation；
Fig. 4 is machine learning stage and the cycle of operation of actual operation phase of client according to the ... of the embodiment of the present invention
Schematic diagram；
Fig. 5 is the schematic diagram that the stand-by period is replied in study according to the ... of the embodiment of the present invention；
Fig. 6 is according to the ... of the embodiment of the present invention due to not learning to judge network or service equipment to the reply stand-by period
The schematic diagram of failure；
Fig. 7 is the schematic diagram that study instruction according to the ... of the embodiment of the present invention sends number；
Fig. 8 is according to the ... of the embodiment of the present invention due to not learning to judge network or service equipment to instruction transmission number
The schematic diagram of failure；
Fig. 9 is the flow chart that client according to the ... of the embodiment of the present invention carries out machine learning and practical operation；
Figure 10 is showing for the device according to the ... of the embodiment of the present invention for realizing the method for improving service reliability and user experience
It is intended to；
Figure 11 is the electronic equipment of the method according to the ... of the embodiment of the present invention realized and improve service reliability and user experience
Hardware architecture diagram.
Specific implementation mode
It explains to the exemplary embodiment of the present invention below in conjunction with attached drawing, including embodiment of the present invention
Various details should think them only exemplary to help understanding.Therefore, those of ordinary skill in the art should recognize
Know, various changes and modifications can be made to embodiment described herein, without departing from scope and spirit of the present invention.
Equally, for clarity and conciseness, the description to known function and structure is omitted in following description.
Relevant main there are two parameters with client practical operation：The instruction for repeating to send is needed to complete an operation
Number, i.e., instruction send number；The time for sending the feedback that service equipment is waited for after instructing, that is, reply the stand-by period.It sends
Number of instructions it is more, receive bigger for the possibility of the feedback of instruction, but the time to be feedback such as need longer, that is, improve
Service reliability and have lost user experience；The number of instructions of transmission is fewer, receives and the possibility of the feedback of instruction is got over
It is small, but the time to be feedback such as need shorter, that is, it improves user experience and has lost service reliability.
In the environment for providing the Internet services, the cycle of operation of client includes two kinds：Machine learning stage and practical behaviour
Make the stage.
Fig. 3 A are that client according to the ... of the embodiment of the present invention carries out machine learning to obtain reply stand-by period and instruction hair
Send the schematic diagram of number.Learnt by network and service by way of enabling multithreading simultaneously in machine learning stage client
The reply stand-by period that equipment performance influences sends number with instruction, wherein has in per thread and realizes exploration and sampling work(
Multiple exploration data packets of energy.It is to improve learning efficiency using the reason of multithreading, so as to shorten the machine learning time.
Fig. 3 B are that client application according to the ... of the embodiment of the present invention replys the stand-by period and instruction sends number to carry out reality
The schematic diagram of border operation.After completing machine learning, the reply stand-by period learnt and instruction are sent number by client
It is applied in the operation to service equipment, will be described in learning to reply used by the embodiment of the present invention in Fig. 5 to Fig. 8
Stand-by period and instruction send the strategy of number.In actual operation phase, client usually requires to enable a thread with to clothes
Equipment of being engaged in sends instruction, and the instruction that setting learns in the thread sends the instruction of number, and according to the reply learnt
Stand-by period waits for the reply from service equipment.
For example, client can one by one send in actual operation phase to service equipment in single thread and learn
Instruction sends the instruction of number, and waits within the reply stand-by period learnt after each transmission instruction and being set from service
Standby reply.Learn to arrive for another example client continuously transmits in single thread to service equipment in actual operation phase
Instruction send number instruction, and after sending all instructions when the reply stand-by period than learning is suitably increased
Interior reply of the waiting from service equipment.
Further, it if occurring operation failure in actual mechanical process, needs to reenter the machine learning stage,
To learn to send number to newest reply stand-by period and instruction, and it is re-applied in new practical operation.
Alternatively, in the machine learning stage the various operations to service equipment can equally be carried out, but client may be because
It is carried out at the same time machine learning and practical operation and pays performance cost.
Fig. 4 is machine learning stage and the cycle of operation of actual operation phase of client according to the ... of the embodiment of the present invention
Schematic diagram.As shown, the cycle of operation of client shows the spy that machine-learning process and actual mechanical process are alternately present
Sign.The reply of the instruction to being sent out is not received in two moment clients of t2 and t4, therefore client judges current reply etc.
It waits for that time and instruction send the behavior pattern that number is not suitable with current network or service equipment, is relearned to start, with
The stand-by period is replied in study and instruction sends number.
Fig. 5 is the schematic diagram according to the ... of the embodiment of the present invention soundd out and reply the stand-by period.Client in multiple threads to
Service equipment, which is sent, sounds out data packet, and sounds out data packet to receiving for souning out data packet from sending out to per thread record
Sound out the feedback time replied.As shown in figure 5, not receiving the feedback from service equipment for thread 1, thread 2；For line
Journey x, from send out thread x to receive for the feedback of thread x time be tx；For thread n, from thread n is sent out to receiving pair
It is t in the time of the feedback of thread nn.When therefore, in the example of hgure 5, for receiving the most short feedback for souning out the thread replied
Between be tx, txThe reply stand-by period as learnt.In addition, when the stand-by period is replied in study, client is in per thread
The exploration data packet of transmission wants enough, to exclude to sound out interference of the number of data packets to learning outcome.
Fig. 6 be it is according to the ... of the embodiment of the present invention due to do not sound out reply the stand-by period and judge network or service equipment
The schematic diagram of failure.As shown in fig. 6, in predetermined time (not shown), all threads are not received from service equipment
Feedback, it is possible to determine that network or service equipment break down, can there is network or service equipment by prompt
The case where failure, informs user.
Fig. 7 is the schematic diagram according to the ... of the embodiment of the present invention soundd out instruction and send number.Similar with Fig. 5, client is more
The different exploration data packet of quantity is continuously transmitted to service equipment in a thread, and the exploration time for souning out data packet is directed to receiving
Multiple thread records the number of the exploration data packet in the thread.As shown in fig. 7, thread 1, thread 2 are not received and are come from
The feedback of service equipment；For thread x, due to receiving the feedback for thread x, so recording it contains X exploration data packet；
For thread n, due to receiving the feedback for thread n, so recording it contains N number of exploration data packet.Therefore, showing in Fig. 7
In example, the minimum exploration number of data packets for the thread replied is soundd out as X for receiving, X is that the instruction learnt sends number.
In addition, when study instructs and sends number, client waits for the time soundd out and replied to want long enough, to exclude the stand-by period to learning
Practise the interference of result.
Fig. 8 be it is according to the ... of the embodiment of the present invention due to do not sound out instruction send number and judge network or service equipment
The schematic diagram of failure.As shown in figure 8, in predetermined time (not shown), no matter in thread containing how many number according to packet, for institute
There is thread not receive the feedback from service equipment, then can determine that network or service equipment break down, can pass through
By network or service equipment, there are the case where failure to inform user for prompt.
The stand-by period is replied furthermore, it is possible to be determined using the method measured by half, that is, in the machine learning stage, is existed first
It waits for the exploration to reply in predetermined time, is replied if receiving exploration, it tries waited in the half the time of predetermined time
It sounds out and replys, and so on, until can not receive and sound out the thread replied will be soundd out for receiving when replying in previous trial
Most short feedback time is set for responding to the stand-by period.Similarly, the method determine instruction measured by half may be used and send number,
That is, in the machine learning stage, the exploration data packet of predetermined number is set first in thread, replys, tastes if receiving exploration
Try in thread be arranged predetermined number half exploration data packet, and so on, until can not receive exploration reply when will before
The minimum exploration number of data packets that the thread for souning out reply is received in secondary trial is set as instruction transmission number.Using measurement by half
Method determine reply the stand-by period and instruction send number, can with faster speed determine reply the stand-by period and instruction send out
Send the optimal value of number.
In addition, to further ensure that reliability of service, in actual operation phase, client can be more than learning
The reply waited in the time of stand-by period to the instruction sent out on single thread is replied, such as in the reply learnt
The reply to the instruction sent out on single thread is waited in 1.1 times of the time of stand-by period.Similarly, in practical operation
Stage, client are sent to service equipment more than the instruction for instructing transmission number learnt in single thread, such as
1.1 times of the instruction that the instruction learnt sends number is sent in single thread to service equipment.
Fig. 9 is the flow chart that client according to the ... of the embodiment of the present invention carries out machine learning and practical operation.In S91,
Client is first begin to carry out machine learning, replys the stand-by period according to Fig. 5 and policy learning shown in Fig. 7 and instruction sends number
Mesh.That is, client, which is sent in multiple threads to service equipment, sounds out data packet, and the exploration for souning out data packet is directed to receiving
The thread record of reply, will be for receiving the line soundd out and replied from exploration data packet is sent out to the feedback time soundd out and replied is received
The most short feedback time of journey is set for responding to the stand-by period.Further, client is continuously sent out in multiple threads to service equipment
The exploration data packet that quantity is different, and the number to receiving the exploration data packet in the thread record thread soundd out and replied are sent, it will
Minimum exploration number of data packets in receiving the thread soundd out and replied is set as instruction and sends number.In S92, if client
End because not receiving the feedback for the exploration data packet sent out in the given time, when so as to cause being that study is waited for reply
Between or instruction send number, then flow enter S94, i.e., there may be networks or service equipment failure to user report for client.
In S92, if client study enters S93, i.e. client entrance to stand-by period or instruction transmission number, flow is replied
Actual operation phase.In S93, client sends to service equipment in a thread and instructs, and is arranged in the thread and is learned
The instruction practised sends the instruction of number, and waits for the reply from service equipment according to the reply stand-by period learnt.
In S94, if client does not receive the reply of the instruction to being sent out on single thread --- there is operation exception,
Client enters S91 and restarts the machine learning stage, and number is sent with determination new reply stand-by period and instruction.
In S94, if it is there is operation exception, client keeps actual operation phase.
Figure 10 is showing for the device according to the ... of the embodiment of the present invention for realizing the method for improving service reliability and user experience
It is intended to.As shown in Figure 10, the client terminal device in the present embodiment includes machine learning module and practical operation module.Machine learning
Module sends to service equipment and sounds out data packet, replys the stand-by period with study and instruction sends number, and will learn
It replys the stand-by period and instruction sends number and sends practical operation module to.Practical operation module will reply stand-by period and instruction
It sends number to be applied to send in actual instruction to service equipment, and when there is operation exception, triggers machine learning module
It relearns and replys stand-by period and instruction transmission number.
According to an embodiment of the invention, the present invention also provides a kind of electronic equipment and a kind of non-transient computer is readable deposits
Storage media.
The present invention electronic equipment include：At least one processor；And connect at least one processor communication
Memory；Wherein, which is stored with the instruction that can be executed by a processor, and the instruction is by least one processor
It executes, so that at least one processor execution is provided by the present invention based on machine learning raising service reliability and user's body
The method tested.
The non-transient computer readable storage medium of the present invention is stored with computer instruction, and the computer instruction is based on making
Calculation machine executes the method provided by the present invention for improving service reliability and user experience based on machine learning.
Figure 11 is the electronic equipment of the method according to the ... of the embodiment of the present invention realized and improve service reliability and user experience
Hardware architecture diagram.As shown in figure 11, which includes：One or more processors 111 and memory 112,
In Figure 11 by taking a processor 111 as an example.Wherein, memory 112 is that non-transient computer provided by the present invention is readable deposits
Storage media.
The electronic equipment of the method for service reliability and user experience is improved based on machine learning to include：Input dress
Set 113 and output device 114.
Processor 111, memory 112, input unit 113 and output device 114 can pass through bus or other modes
It connects, in Figure 11 for being connected by bus.
Memory 112 is used as a kind of non-transient computer readable storage medium, can be used for storing non-transient software program, non-
Transient computer executable program instructions and module, it is such as corresponding with the automatic method of calling distribution in the embodiment of the present invention
Program instruction --- for example, machine learning module shown in Fig. 10 and practical operation module.Processor 111 is stored in by operation
Non-transient software program, instruction and module in memory 112, to execute based on machine learning improve service reliability and
Raising service reliability and use in above method embodiment are realized in the various function application of user experience and data processing
The method of family experience.
Memory 112 may include storing program area and storage data field, wherein storing program area can store operation system
System, the required application program of at least one function；Storage data field can store the reply stand-by period learnt and instruction
Send number etc..In addition, memory 112 may include high-speed random access memory, can also include non-transient memory, example
Such as at least one disk memory, flush memory device or other non-transient solid-state memories.In some embodiments, it stores
It includes the memory remotely located relative to processor 111 that device 112 is optional, these remote memories can be by network connection extremely
The electronic equipment.The example of above-mentioned network include but not limited to internet, intranet, LAN, mobile radio communication and its
Combination.
Input unit 113 can receive such as input in the machine learning stage predetermined time relevant number to be feedback
Word or character information.Output device 114 may include that display screen etc. shows equipment
One or more of modules are stored in memory 112, are executed when by one or more processor 111
When, execute the method for realizing the service reliability and user experience of the raising in above-mentioned any means embodiment.
The said goods can perform the method that the embodiment of the present invention is provided, and has the corresponding function module of execution method and has
Beneficial effect.The not technical detail of detailed description in the present embodiment, reference can be made to the method that the embodiment of the present invention is provided.
Above-mentioned specific implementation mode, does not constitute limiting the scope of the invention.Those skilled in the art should be bright
It is white, design requirement and other factors are depended on, various modifications, combination, sub-portfolio and replacement can occur.It is any
Modifications, equivalent substitutions and improvements made by within the spirit and principles in the present invention etc., should be included in the scope of the present invention
Within.
Claims (16)
1. a kind of method improving service reliability and user experience, including machine learning stage and actual operation phase, special
Sign is：
In the machine learning stage, client sends to service equipment in multiple threads and sounds out data packet, and to receiving needle
To sound out data packet exploration reply the thread record from send out it is described exploration data packet to receive it is described sound out reply
Feedback time will be set for responding to the stand-by period for receiving the most short feedback time for souning out the thread replied；
In the actual operation phase, the client is waited for according to the reply stand-by period to the institute on the single thread
The reply of the instruction sent out.
2. according to the method described in claim 1, further including：
In the machine learning stage, the client continuously transmits quantity not in multiple threads to the service equipment
The same exploration data packet, and the exploration data in the thread are recorded to the thread for receiving the exploration reply
The number of packet sets the minimum exploration number of data packets in receiving the thread soundd out and replied to instruction and sends number
Mesh；
In the actual operation phase, the client sends described instruction hair in the single thread to the service equipment
Send the instruction of number.
3. according to the method described in claim 1, it is characterized in that：
If the client described in the actual operation phase does not receive time of the instruction to being sent out on the single thread
Multiple, then the client reenters the machine learning stage, with the determination reply stand-by period.
4. according to the method described in claim 2, it is characterized in that：
If the client described in the actual operation phase does not receive time of the instruction to being sent out on the single thread
Multiple, then the client reenters the machine learning stage, to determine that described instruction sends number.
5. method according to claim 1 or 2, it is characterised in that：
If not receiving the exploration in the given time for all exploration data packets sent out to reply, described
There is network or the service equipment failure in the determination of machine learning stage.
6. according to the method described in claim 5, it is characterized in that：
The reply stand-by period is determined using the method measured by half, that is, in the machine learning stage, first described pre-
The interior waiting exploration of fixing time is replied, and is replied if receiving the exploration, it tries in the half the time of the predetermined time
It is interior that explorations is waited for reply, and so on, until when can not receive the exploration reply by previous trial for receiving
The most short feedback time for stating the thread for souning out reply is set as the reply stand-by period.
7. according to the method described in claim 5, it is characterized in that：
Determine that described instruction sends number using the method measured by half, that is, in the machine learning stage, first in the line
The exploration data packet of setting predetermined number in journey, is replied, it tries be arranged in the thread if receiving the exploration
The exploration data packet of the half of predetermined number, and so on, until can not receive previous trial when the exploration is replied
In receive it is described sound out reply the thread minimum the explorations number of data packets be set as described instruction transmission number.
8. a kind of device improving service reliability and user experience, described device includes machine learning module and practical operation mould
Block, it is characterised in that：
The machine learning module sends to service equipment in multiple threads and sounds out data packet, and sounds out data to receiving to be directed to
The thread record that the exploration of packet is replied, will from the exploration data packet is sent out to the feedback time soundd out and replied is received
It is set for responding to the stand-by period for receiving the most short feedback time for souning out the thread replied；
The practical operation module is waited for according to the reply stand-by period to the instruction that is sent out on the single thread
It replys.
9. device according to claim 8, further includes：
The machine learning module continuously transmits the different exploration of quantity in multiple threads to the service equipment
Data packet, and to receiving the number soundd out the thread replied and record the exploration data packet in the thread, it will
Minimum exploration number of data packets in receiving the thread soundd out and replied is set as instruction and sends number；
The practical operation module sends the instruction that described instruction sends number in the single thread to the service equipment.
10. device according to claim 8, it is characterised in that：
If the practical operation module does not receive the reply of the instruction to being sent out on the single thread, the reality
Operation module notifies the machine learning module to redefine the reply stand-by period.
11. device according to claim 9, it is characterised in that：
If the practical operation module does not receive the reply of the instruction to being sent out on the single thread, the reality
Operation module notifies the machine learning module to redefine described instruction and send number.
12. device according to claim 8 or claim 9, it is characterised in that：
If not receiving the exploration in the given time for all exploration data packets sent out to reply, the machine
There is network or the service equipment failure in the determination of device study module.
13. device according to claim 12, it is characterised in that：
The reply stand-by period is determined using the method measured by half, that is, the machine learning module is first described predetermined
It waits for the exploration to reply in time, is replied if receiving the exploration, it tries in the half the time of the predetermined time
The exploration is waited for reply, and so on, it will be described for receiving in previous trial when the exploration is replied until can not receive
The most short feedback time for souning out the thread replied is set as the reply stand-by period.
14. device according to claim 12, it is characterised in that：
Determine that described instruction sends number using the method measured by half, that is, the machine learning module is first in the thread
The exploration data packet of interior setting predetermined number, is replied if receiving the exploration, it tries is arranged in the thread pre-
The exploration data packet of fixed number purpose half, and so on, it will be in previous trial when the exploration is replied until can not receive
The minimum exploration number of data packets for receiving the thread soundd out and replied is set as described instruction transmission number.
15. a kind of electronic equipment, which is characterized in that including：
At least one processor；And
The memory being connect at least one processor communication；Wherein,
The memory is stored with the instruction that can be executed by one processor, and described instruction is by least one processing
Device executes, so that at least one processor is able to carry out the method described in any one of claim 1 to 7.
16. a kind of non-transient computer readable storage medium, which is characterized in that the non-transient computer readable storage medium is deposited
Contain computer instruction, the side that the computer instruction is used to that the computer perform claim to be made to require described in any one of 1 to 7
Method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710149711.9A CN108574595B (en) | 2017-03-14 | 2017-03-14 | Method and device for improving service reliability and user experience |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710149711.9A CN108574595B (en) | 2017-03-14 | 2017-03-14 | Method and device for improving service reliability and user experience |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108574595A true CN108574595A (en) | 2018-09-25 |
| CN108574595B CN108574595B (en) | 2021-10-01 |
Family
ID=63578559
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710149711.9A Active CN108574595B (en) | 2017-03-14 | 2017-03-14 | Method and device for improving service reliability and user experience |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108574595B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109921967A (en) * | 2019-03-08 | 2019-06-21 | 美的智慧家居科技有限公司 | Command processing method and system, gateway and computer readable storage medium |
| CN109976168A (en) * | 2019-03-08 | 2019-07-05 | 佛山市云米电器科技有限公司 | A kind of intelligent home furnishing control method and system of decentralization |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2011022920A1 (en) * | 2009-08-28 | 2011-03-03 | 中兴通讯股份有限公司 | Timing method and apparatus for hybrid automatic repeat request |
| CN103795564A (en) * | 2012-10-31 | 2014-05-14 | 三星Sds株式会社 | Terminal and method of monitoring network by using the same |
| CN105024933A (en) * | 2014-04-22 | 2015-11-04 | 腾讯科技（深圳）有限公司 | Request packet sending frequency control method and apparatus |
| CN105491594A (en) * | 2015-11-24 | 2016-04-13 | 小米科技有限责任公司 | Network connection processing method and device |
| CN106487603A (en) * | 2015-08-26 | 2017-03-08 | 阿里巴巴集团控股有限公司 | A kind of response test method and device |
-
2017
- 2017-03-14 CN CN201710149711.9A patent/CN108574595B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2011022920A1 (en) * | 2009-08-28 | 2011-03-03 | 中兴通讯股份有限公司 | Timing method and apparatus for hybrid automatic repeat request |
| CN103795564A (en) * | 2012-10-31 | 2014-05-14 | 三星Sds株式会社 | Terminal and method of monitoring network by using the same |
| CN105024933A (en) * | 2014-04-22 | 2015-11-04 | 腾讯科技（深圳）有限公司 | Request packet sending frequency control method and apparatus |
| CN106487603A (en) * | 2015-08-26 | 2017-03-08 | 阿里巴巴集团控股有限公司 | A kind of response test method and device |
| CN105491594A (en) * | 2015-11-24 | 2016-04-13 | 小米科技有限责任公司 | Network connection processing method and device |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109921967A (en) * | 2019-03-08 | 2019-06-21 | 美的智慧家居科技有限公司 | Command processing method and system, gateway and computer readable storage medium |
| CN109976168A (en) * | 2019-03-08 | 2019-07-05 | 佛山市云米电器科技有限公司 | A kind of intelligent home furnishing control method and system of decentralization |
| CN109921967B (en) * | 2019-03-08 | 2021-05-07 | 美智光电科技股份有限公司 | Instruction processing method and system, gateway device and computer readable storage medium |
| CN109976168B (en) * | 2019-03-08 | 2022-07-08 | 佛山市云米电器科技有限公司 | Decentralized intelligent home control method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108574595B (en) | 2021-10-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109617731A (en) | Adaptive gateway role configuration method and device under a kind of multi-gateway environment | |
| CN106685917A (en) | Method and system for realizing intelligent binding between Internet of Things device and controller | |
| CN109729131A (en) | A kind of processing method of application request, device and router | |
| CN107688502A (en) | Inter-process communication methods and device | |
| CN107526659A (en) | Method and apparatus for standby | |
| CN108900384A (en) | Network flow monitoring method, apparatus and system, computer readable storage medium | |
| CN110401466B (en) | Data transmission method, device and medium based on high-speed signal switching chip | |
| CN104836800B (en) | A kind of method, equipment and the system of service quality control | |
| CN107707370B (en) | Group communication method, server, terminal and computer storage medium | |
| CN108574595A (en) | A kind of method and apparatus improving service reliability and user experience | |
| CN110505640A (en) | The processing method of apparatus bound, apparatus and system, to distribution net equipment and terminal | |
| CN107231398A (en) | Information interacting method and device | |
| CN108366129A (en) | USB data transmission method, device and USB adapter | |
| CN104079398B (en) | A kind of data communications method, apparatus and system | |
| CN104488243B (en) | To the write-access of the variable in server | |
| US8402312B2 (en) | Method and system for testing an application | |
| CN105978970A (en) | Control mode selection method and device | |
| CN109922120A (en) | Improve the method and terminal of DNS availability | |
| Oh et al. | Periodic bandits and wireless network selection | |
| CN109885266A (en) | A kind of method, apparatus, system and the mobile terminal of printer network connection | |
| CN109710908A (en) | Page editing method, system and device | |
| CN106294146B (en) | Parameter replacement test method and device | |
| CN105357243B (en) | A kind of method and apparatus with internet of things equipment remote interaction | |
| US9900399B2 (en) | Method for operating machines and system using the same | |
| CN107592340A (en) | The method and apparatus of remote operation management server |
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 |