CN113568741B - Service expansion and contraction method, device, equipment and storage medium of distributed system - Google Patents
Service expansion and contraction method, device, equipment and storage medium of distributed system Download PDFInfo
- Publication number
- CN113568741B CN113568741B CN202110816331.2A CN202110816331A CN113568741B CN 113568741 B CN113568741 B CN 113568741B CN 202110816331 A CN202110816331 A CN 202110816331A CN 113568741 B CN113568741 B CN 113568741B
- Authority
- CN
- China
- Prior art keywords
- hour
- service
- micro
- distributed system
- year
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000008602 contraction Effects 0.000 title claims abstract description 84
- 238000000034 method Methods 0.000 title claims abstract description 55
- 230000008859 change Effects 0.000 claims abstract description 88
- 238000012549 training Methods 0.000 claims abstract description 27
- 230000006870 function Effects 0.000 claims description 42
- 238000004422 calculation algorithm Methods 0.000 claims description 26
- 238000012545 processing Methods 0.000 claims description 10
- 238000004891 communication Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 3
- 230000006835 compression Effects 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- GNFTZDOKVXKIBK-UHFFFAOYSA-N 3-(2-methoxyethoxy)benzohydrazide Chemical compound COCCOC1=CC=CC(C(=O)NN)=C1 GNFTZDOKVXKIBK-UHFFFAOYSA-N 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3003—Monitoring arrangements specially adapted to the computing system or computing system component being monitored
- G06F11/3006—Monitoring arrangements specially adapted to the computing system or computing system component being monitored where the computing system is distributed, e.g. networked systems, clusters, multiprocessor systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Data Mining & Analysis (AREA)
- Quality & Reliability (AREA)
- Mathematical Physics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a service expansion and contraction method, a device, equipment and a computer readable storage medium of a distributed system, wherein the method comprises the following steps: determining a contrast coefficient corresponding to the hour to be predicted based on the historical change trend and the current change trend; determining a micro-service volume mean value corresponding to the hour to be predicted; inputting the request quantity of each hour in the current year in the distributed system into a pre-trained request quantity prediction model for model training to obtain a predicted request quantity; determining the micro-service quantity corresponding to the hour to be predicted based on the predicted request quantity, the comparison coefficient, the micro-service quantity average value, the hour request quantity and the started micro-service quantity; and performing micro-service capacity expansion and contraction operation on the distributed system based on the micro-service quantity. According to the invention, the capacity expansion and contraction of the micro services is carried out on the distributed system by combining the micro service quantity obtained by the historical data prediction, so that the automatic capacity expansion and contraction of the micro services in the distributed system is realized, and the capacity expansion and contraction efficiency and accuracy of the distributed system of the website are improved.
Description
Technical Field
The present invention relates to the field of internet technologies, and in particular, to a service capacity expansion and contraction method, device, equipment and computer readable storage medium for a distributed system.
Background
With the rapid development of internet technology, internet users have greatly increased, and have raised high demands on the performance of websites, and the websites are required to support large-flow access, respond rapidly, and promote good experience of users, especially in various holidays (such as double 11), when users access and request websites in high density and high quantity, the server system of the websites can meet the demands of no downtime, rapid response and the like.
At present, the capacity expansion and contraction mode of the distributed system of the website is to perform manual watch-on at various possible peak access times, monitor the server in cooperation with operation and maintenance, and perform manual capacity expansion and contraction operation when the distributed system needs capacity expansion and contraction. However, a large number of operation and maintenance personnel are required to be hired on duty manually, the expansion and contraction capacity of the system is achieved through an artificial mode of monitoring related data indexes, when the expansion and contraction capacity is triggered, the experience requirements on the operation and maintenance personnel are high, when the operation is tired manually, errors are easy to occur in the expansion and contraction capacity operation, and the efficiency and the accuracy of expanding and contracting capacity of the distributed system of the website are low.
The foregoing is provided merely for the purpose of facilitating understanding of the technical solutions of the present invention and is not intended to represent an admission that the foregoing is prior art.
Disclosure of Invention
The invention mainly aims to provide a service capacity expansion and contraction method, device and equipment of a distributed system and a computer readable storage medium, and aims to solve the technical problems of low capacity expansion and contraction efficiency and low accuracy of the distributed system of the existing website.
In order to achieve the above object, the present invention provides a service expansion and contraction method of a distributed system, where the service expansion and contraction method of the distributed system includes the following steps:
Determining a contrast coefficient corresponding to an hour to be predicted based on a historical change trend corresponding to the number of requests in each hour in each year and a current change trend corresponding to the number of requests in each hour in the current year in a distributed system, wherein the number of requests is the number of requests corresponding to micro-services;
Determining a micro-service average value corresponding to an hour to be predicted by a kernel function average value shift algorithm based on the micro-service number of each hour in a preset year before the current year in the distributed system;
Inputting the request quantity of each hour in the current year in the distributed system into a pre-trained request quantity prediction model for model training to obtain a predicted request quantity corresponding to the hour to be predicted;
acquiring an hour request quantity of a micro service processing request per hour and the current started micro service quantity in a distributed system, and determining the micro service quantity corresponding to the hour to be predicted based on the predicted request quantity, a comparison coefficient, a micro service quantity average value, the hour request quantity and the started micro service quantity;
and executing micro-service capacity expansion and contraction operation on the distributed system based on the micro-service quantity corresponding to the to-be-predicted hour.
Further, the step of determining the contrast coefficient corresponding to the hour to be predicted based on the historical variation trend corresponding to the number of requests of each hour in each year in the distributed system and the current variation trend corresponding to the number of requests of each hour in the current year includes:
determining a historical variation trend corresponding to the number of requests of each hour each year based on the number of requests of each hour in a preset year before the current year;
Determining a current change trend corresponding to the request quantity of each hour in the current year based on the request quantity of each hour in the current year before the current moment;
and determining a contrast coefficient corresponding to the hour to be predicted based on the historical change trend and the current change trend.
Further, the step of determining the historical trend corresponding to the number of requests of each hour each year based on the number of requests of each hour in a preset year before the current year includes:
Determining a first request quantity offset value of each hour in the preset year before the current year through a kernel function mean shift algorithm based on the request quantity of each hour in the preset year before the current year;
determining a first request amount mean value for each hour each year based on the first request amount offset value;
and determining the historical change trend corresponding to the number of requests in each hour each year based on the coordinate curve corresponding to the first request quantity average value.
Further, the step of determining the current change trend corresponding to the request number of each hour in the current year based on the request number of each hour in the current year before the current time includes:
determining a second request quantity offset value of each hour in the current year before the current moment through a kernel function mean shift algorithm based on the request quantity of each hour in the current year before the current moment;
Determining a second request quantity average value of each hour in the current year based on the second request quantity offset value;
And determining the current change trend corresponding to the request quantity of each hour in the current year based on the coordinate curve corresponding to the second request quantity average value.
Further, the step of determining the contrast coefficient corresponding to the hour to be predicted based on the historical variation trend and the current variation trend includes:
acquiring a first change trend corresponding to a target time of each day from the historical change trend, wherein the target time is the time of the hour to be predicted in the current day;
acquiring a second change trend corresponding to the daily target moment from the current change trend;
And determining a contrast coefficient corresponding to the hour to be predicted based on the average value of the first change trend and the average value of the second change trend.
Further, the step of determining the micro-service average value corresponding to the hour to be predicted by the kernel function average value shift algorithm based on the micro-service number of each hour in the preset year before the current year in the distributed system includes:
Determining micro-service quantity offset values of all the hours in the preset year before the current year through a kernel function mean shift algorithm based on the micro-service quantity of all the hours in the preset year before the current year;
Determining a micro-service average value of each hour of each year based on the micro-service offset value of each hour in a preset year before the current year;
And determining the micro-service average value corresponding to the hour to be predicted from the micro-service average value of each hour every year.
Further, before the step of inputting the number of requests of each hour in the current year in the distributed system into the pre-trained request quantity prediction model to perform model training to obtain the predicted request quantity corresponding to the hour to be predicted, the method further includes:
Acquiring first historical request data in a preset year before the current year and a service which is the same as a service scene of the first historical request data, wherein the second historical request data in the preset year before the current year;
based on the first historical request data and the second historical request data, model training is performed on the request quantity prediction model to obtain a pre-trained request quantity prediction model.
In addition, in order to achieve the above object, the present invention further provides a service expansion and contraction device of a distributed system, where the service expansion and contraction device of the distributed system includes:
The first determining module is used for determining a contrast coefficient corresponding to an hour to be predicted based on a historical change trend corresponding to the number of requests in each hour each year and a current change trend corresponding to the number of requests in each hour in the current year in the distributed system, wherein the number of requests is the number of requests corresponding to the micro-service;
The second determining module is used for determining a micro-service average value corresponding to the hour to be predicted through a kernel function average value shift algorithm based on the micro-service number of each hour in a preset year before the current year in the distributed system;
The training module is used for inputting the request quantity of each hour in the current year in the distributed system into a pre-trained request quantity prediction model for model training to obtain a predicted request quantity corresponding to the hour to be predicted;
The acquisition module is used for acquiring the hour request quantity of the micro-service processing request per hour and the current started micro-service quantity in the distributed system, and determining the micro-service quantity corresponding to the hour to be predicted based on the predicted request quantity, the comparison coefficient, the micro-service quantity average value, the hour request quantity and the started micro-service quantity;
and the capacity expansion and contraction module is used for executing micro-service capacity expansion and contraction operation on the distributed system based on the micro-service quantity corresponding to the to-be-predicted hours.
In addition, to achieve the above object, the present invention further provides a service expansion and contraction device of a distributed system, where the service expansion and contraction device of the distributed system includes: the method comprises the steps of a memory, a processor and a service expansion and contraction program of a distributed system, wherein the service expansion and contraction program of the distributed system is stored in the memory and can run on the processor, and the service expansion and contraction program of the distributed system realizes the service expansion and contraction method of the distributed system when being executed by the processor.
In addition, in order to achieve the above object, the present invention further provides a computer readable storage medium, on which a service expansion and contraction program of a distributed system is stored, where the service expansion and contraction program of the distributed system implements the steps of the service expansion and contraction method of the distributed system when being executed by a processor.
According to the method, the contrast coefficient corresponding to the hour to be predicted is determined based on the historical change trend corresponding to the request quantity of each hour in each year and the current change trend corresponding to the request quantity of each hour in the current year in the distributed system, wherein the request quantity is the quantity of requests corresponding to the micro-service; then, based on the micro-service quantity of each hour in the preset year before the current year in the distributed system, determining a micro-service mean value corresponding to the hour to be predicted through a kernel function mean shift algorithm; inputting the request quantity of each hour in the current year in the distributed system into a pre-trained request quantity prediction model for model training to obtain a predicted request quantity corresponding to the hour to be predicted; then, acquiring an hour request quantity of a micro service processing request per hour and the current started micro service quantity in the distributed system, and determining the micro service quantity corresponding to the hour to be predicted based on the predicted request quantity, the comparison coefficient, the micro service quantity average value, the hour request quantity and the started micro service quantity; and finally, performing micro-service capacity expansion and contraction operation on the distributed system based on the micro-service quantity corresponding to the to-be-predicted hour, and performing micro-service capacity expansion and contraction on the distributed system by combining the micro-service quantity predicted by the historical data to realize automatic capacity expansion and contraction of the micro-service in the distributed system, thereby improving the capacity expansion and contraction efficiency and accuracy of the distributed system of the website. Meanwhile, the manual participation is reduced in the micro-service capacity expansion and contraction process, errors caused by human errors in micro-service capacity expansion and contraction can be avoided, the manual pressure can be reduced, and the cost is saved.
Drawings
FIG. 1 is a schematic diagram of a service expansion device of a distributed system in a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a flow chart of a first embodiment of a service capacity expansion method of a distributed system according to the present invention;
fig. 3 is a schematic functional block diagram of a service expansion device of a distributed system according to an embodiment of the invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Referring to fig. 1, fig. 1 is a schematic structural diagram of a service expansion device of a distributed system in a hardware running environment according to an embodiment of the present invention.
The service expansion and contraction device of the distributed system in the embodiment of the invention can be a PC, or can be a mobile terminal device with a display function, such as a smart phone, a tablet personal computer, an electronic book reader, an MP3 (Moving Picture Experts Group Audio Layer III, dynamic image expert compression standard audio layer 3) player, an MP4 (Moving Picture Experts Group Audio Layer IV, dynamic image expert compression standard audio layer 4) player, a portable computer and the like.
As shown in fig. 1, the service expansion device of the distributed system may include: a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, a communication bus 1002. Wherein the communication bus 1002 is used to enable connected communication between these components. The user interface 1003 may include a Display, an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may further include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface). The memory 1005 may be a high-speed RAM memory or a stable memory (non-volatile memory), such as a disk memory. The memory 1005 may also optionally be a storage device separate from the processor 1001 described above.
Optionally, the service expansion device of the distributed system may further include a camera, an RF (Radio Frequency) circuit, a sensor, an audio circuit, a WiFi module, and the like. Among other sensors, such as light sensors, motion sensors, and other sensors. Of course, the service expansion and contraction device of the distributed system may also be configured with other sensors such as a gyroscope, a barometer, a hygrometer, a thermometer, an infrared sensor, and the like, which are not described herein.
Those skilled in the art will appreciate that the terminal structure shown in fig. 1 does not constitute a limitation of the service expansion device of the distributed system, and may include more or fewer components than shown, or may combine certain components, or may be a different arrangement of components.
As shown in fig. 1, an operating system, a network communication module, a user interface module, and a service extension program of a distributed system may be included in a memory 1005, which is a type of computer storage medium.
In the service expansion and contraction device of the distributed system shown in fig. 1, the network interface 1004 is mainly used for connecting a background server and performing data communication with the background server; the user interface 1003 is mainly used for connecting a client (user side) and performing data communication with the client; and the processor 1001 may be used to invoke a service extension program of the distributed system stored in the memory 1005.
In this embodiment, a service expansion device of a distributed system includes: the system comprises a memory 1005, a processor 1001 and a service expansion program of the distributed system which is stored in the memory 1005 and can run on the processor 1001, wherein when the processor 1001 calls the service expansion program of the distributed system stored in the memory 1005, the steps of the service expansion method of the distributed system in the following embodiments are executed.
The invention also provides a service capacity expansion and contraction method of the distributed system, referring to fig. 2, fig. 2 is a flow chart of a first embodiment of the service capacity expansion and contraction method of the distributed system.
In this embodiment, the service expansion and contraction method of the distributed system includes the following steps:
step S101, determining a contrast coefficient corresponding to an hour to be predicted based on a historical change trend corresponding to the number of requests of each hour in each year and a current change trend corresponding to the number of requests of each hour in the current year in a distributed system, wherein the number of requests is the number of requests corresponding to micro-services;
The request of this embodiment is a request for accessing a website of the distributed system, and the historical variation trend corresponding to the number of requests in each hour of each year may be determined according to the number of historical requests in the distributed system at the beginning of each year, where the number of historical requests may include the number of historical requests in the last N years, the number of historical requests is divided into the number of historical requests in each hour, and the historical variation trend corresponding to the number of requests in each hour of each year is determined according to the number of requests in each historical hour. Meanwhile, the current change trend is determined according to the number of requests of each hour in the current year.
And then, calculating a contrast coefficient corresponding to the hour to be predicted according to the historical change trend and the current change trend, specifically, acquiring the historical change trend at the same moment as the hour to be predicted at the historical change trend, acquiring the current change trend at the same moment as the hour to be predicted at the current change trend, and then calculating the contrast coefficient corresponding to the hour to be predicted.
The hour to be predicted may be one hour after the current time.
Step S102, determining a micro-service average value corresponding to an hour to be predicted through a kernel function average value shift algorithm based on the micro-service number of each hour in a preset year before the current year in the distributed system;
in the embodiment, firstly, the micro service quantity of each hour in the preset year before the current year in the distributed system is obtained, and the micro service quantity offset value of each hour in the preset year before the current year is determined through a kernel function mean shift algorithm; and determining a micro-service average value corresponding to the hour to be predicted according to the micro-service offset value of each hour in the preset year before the current year.
Wherein the preset year can be 3 years, 5 years, 10 years, etc.
Step S103, inputting the request quantity of each hour in the current year in the distributed system into a pre-trained request quantity prediction model for model training to obtain a predicted request quantity corresponding to the hour to be predicted;
Before the micro-service capacity expansion operation, the method performs model training on the request quantity prediction model according to first historical request data in a preset year before the current year and the service which is the same as the service scene of the first historical request data, and second historical request data in the preset year before the current year to obtain a pre-trained request quantity prediction model.
In this embodiment, the number of requests of each hour in the current year in the distributed system is obtained, where the number of requests of each hour in the current year is the number of requests of each hour in the current year before the current time in the distributed system, then the number of requests of each hour in the current year is input into a pre-trained request quantity prediction model to perform model training, and after the model training is completed, the output result of the pre-trained request quantity prediction model is used as the prediction request quantity corresponding to the hour to be predicted.
Step S104, acquiring an hour request quantity of a micro service processing request per hour and a current started micro service quantity in the distributed system, and determining the micro service quantity corresponding to the to-be-predicted hour based on the predicted request quantity, the comparison coefficient, the micro service quantity average value, the hour request quantity and the started micro service quantity;
In this embodiment, when the predicted request amount corresponding to the hour to be predicted is obtained, the hour request amount of processing the request per hour of the micro service in the distributed system and the current started micro service amount are obtained, where the hour request amount is the amount of the request that can be processed per hour of each micro service, in general, the amount of the request that can be processed per hour of each micro service may be less, and at this time, the average value of the amounts of the requests that can be processed per hour of all the micro services is taken as the hour request amount.
Then, based on the predicted request quantity, the comparison coefficient, the average value of the micro service quantity, the hour request quantity and the started micro service quantity, determining the micro service quantity corresponding to the hour to be predicted, wherein the formula of the micro service quantity is as follows:
C＝Math.ceil((Pt/Q)*R+Math.floor(Math.abs((Bc/S_AVGs-1)*Bc)))；
wherein the Math.ceil function is an upward rounding function; the floor function is a rounding function; math.abs is absolute function, pt is predicted request quantity, Q is hour request quantity, R is contrast coefficient, bc is started micro-service quantity, and S_ AVGs is micro-service quantity average value.
Step S105, performing a micro service capacity expansion operation on the distributed system based on the micro service number corresponding to the to-be-predicted hour.
In this embodiment, when the number of micro services is obtained, a micro service capacity expansion operation is performed on the distributed system based on the number of micro services corresponding to the hour to be predicted, specifically, a difference between the number of micro services and the number of started micro services is calculated first, if the difference is greater than 0, the micro service capacity expansion operation is performed on the distributed system according to the difference, and if the difference is less than 0, the micro service capacity expansion operation is performed on the distributed system according to the difference, and since each service micro service in the distributed system corresponds to one message queue partition, when the micro service capacity expansion operation is performed, the message queue is increased or decreased and the micro service capacity is expanded.
According to the service expansion and contraction method of the distributed system, the comparison coefficient corresponding to the hour to be predicted is determined based on the historical change trend corresponding to the number of requests in each hour in the distributed system and the current change trend corresponding to the number of requests in each hour in the current year, wherein the number of requests is the number of requests corresponding to the micro-service; then, based on the micro-service quantity of each hour in the preset year before the current year in the distributed system, determining a micro-service mean value corresponding to the hour to be predicted through a kernel function mean shift algorithm; inputting the request quantity of each hour in the current year in the distributed system into a pre-trained request quantity prediction model for model training to obtain a predicted request quantity corresponding to the hour to be predicted; then, acquiring an hour request quantity of a micro service processing request per hour and the current started micro service quantity in the distributed system, and determining the micro service quantity corresponding to the hour to be predicted based on the predicted request quantity, the comparison coefficient, the micro service quantity average value, the hour request quantity and the started micro service quantity; and finally, performing micro-service capacity expansion and contraction operation on the distributed system based on the micro-service quantity corresponding to the to-be-predicted hour, and performing micro-service capacity expansion and contraction on the distributed system by combining the micro-service quantity predicted by the historical data to realize automatic capacity expansion and contraction of the micro-service in the distributed system, thereby improving the capacity expansion and contraction efficiency and accuracy of the distributed system of the website. Meanwhile, the manual participation is reduced in the micro-service capacity expansion and contraction process, errors caused by human errors in micro-service capacity expansion and contraction can be avoided, the manual pressure can be reduced, and the cost is saved.
Based on the first embodiment, a second embodiment of the service expansion and contraction method of the distributed system of the present invention is provided, in this embodiment, step S101 includes:
step S201, based on the request quantity of each hour in the preset year before the current year, determining a historical change trend corresponding to the request quantity of each hour each year;
step S202, determining a current change trend corresponding to the request quantity of each hour in the current year based on the request quantity of each hour in the current year before the current moment;
Step S203, determining a contrast coefficient corresponding to the hour to be predicted based on the historical trend and the current trend.
In this embodiment, the number of requests of each hour in a preset year before the current year in the distributed system is obtained first, where the number of requests may include a historical number of requests of N years before the current year, the historical number of requests is divided into the number of requests of each hour, and then, according to the number of requests of each hour in the current year before the current moment, a current change trend corresponding to the number of requests of each hour in the current year is determined by a kernel function mean shift algorithm.
Specifically, in one embodiment, the step S201 includes:
step a, determining a first request quantity offset value of each hour in a preset year before the current year through a kernel function mean shift algorithm based on the request quantity of each hour in the preset year before the current year;
Step b, determining a first request quantity average value of each hour every year based on the first request quantity offset value;
And c, determining the historical change trend corresponding to the number of requests in each hour each year based on the coordinate curve corresponding to the first request quantity average value.
In this embodiment, the number of requests in each hour in a preset year before the current year is obtained, then, a first request offset value of each hour in the preset year before the current year is determined through a kernel mean shift algorithm, for each request number of hours, a central point center is determined randomly in a space with N data points through the kernel mean shift algorithm, vector values of all points and centers in a circular space with a radius r are calculated, finally, the average value of all vectors in the whole circle is obtained, an offset average value is obtained, the central point center is moved to an offset average value position, the next offset average value is calculated again until the offset average value meets the requirement that the flow peak value is equivalent to the server processing capacity value in a certain period of time, and then, the current offset average value is taken as the first request offset value. Specifically, the formula of the first request amount offset value is:
Wherein Mr (X) is a first request amount offset value, n is X is a center point of the request, X i is a request in a range, n is the number of points, i.e., the number of requests, and r is a radius.
Determining a first request amount mean value for each hour each year based on the first request amount offset value; specifically, splitting the first request quantity offset value to obtain a request quantity offset value of the same hour in a preset year, taking the average value of the request quantity offset values of the same hour in the preset year as a first request quantity average value corresponding to the hour, and further obtaining a first request quantity average value of each hour each year, for example, a i,j is the first request quantity offset value of the j-th hour in the i-th year, j=1, 2, 3, 4 …, j < = 8760; the first request amount average AVG j＝(ai,j+ai+1,j+…+an,j)/n, n being the number of years included in the preset year.
And determining a historical change trend corresponding to the number of requests in each hour each year based on the coordinate curve corresponding to the first request average value, specifically, firstly generating a coordinate curve according to each first request average value and the corresponding hour j, wherein the abscissa of the coordinate curve is the first request average value, then determining a historical change trend corresponding to the number of requests in each hour each year according to the point corresponding to each first request average value in the coordinate curve, for example, for (AVG j, j), determining the corresponding historical change trend through the slope of the point and the adjacent point, for example, taking the average value of the slopes of three points (AVG j-1,j-1)、(AVGj,j)、(AVGj+1, j+1) in the coordinate curve as the corresponding historical change trend of the corresponding hour. The historical change trend can be accurately determined according to the first request amount offset value, and the capacity expansion and contraction efficiency and accuracy of the distributed system are further improved.
And then, acquiring the request quantity of each hour in the current year before the current moment in the distributed system, and determining the current change trend corresponding to the request quantity of each hour in the current year according to the request quantity of each hour in the current year before the current moment. Specifically, in yet another embodiment, the step S202 includes:
Step d, determining a second request quantity offset value of each hour in the current year before the current moment through a kernel function mean shift algorithm based on the request quantity of each hour in the current year before the current moment;
step e, determining a second request quantity average value of each hour in the current year based on the second request quantity offset value;
And f, determining the current change trend corresponding to the request quantity of each hour in the current year based on the coordinate curve corresponding to the second request quantity average value.
In this embodiment, the second request offset value, the second request mean value, and the current variation trend are the same as the calculation methods of the first request offset value, the first request mean value, and the historical variation trend, respectively, and are not described herein again. The current change trend can be accurately determined according to the second request amount offset value, and the capacity expansion and contraction efficiency and accuracy of the distributed system are further improved.
Finally, based on the historical trend and the current trend, a comparison coefficient corresponding to the hour to be predicted is determined, and in particular, in another embodiment, the step S203 includes:
Step g, acquiring a first change trend corresponding to a target time of each day from the historical change trend, wherein the target time is the time of the hour to be predicted on the same day;
step h, acquiring a second change trend corresponding to the daily target moment from the current change trend;
and i, determining a contrast coefficient corresponding to the hour to be predicted based on the average value of the first change trend and the average value of the second change trend.
In this embodiment, the time corresponding to the target time, that is, the time of the hour to be predicted, is determined first, where the target time is the time of the day of the hour to be predicted, specifically, the time of the day of an hour after the current hour, specifically, one of 1, 2,3,4 …, and 24. And then, acquiring a first change trend corresponding to the daily target time from the historical change trend, and acquiring a second change trend corresponding to the daily target time from the current change trend.
And then calculating the average value of the first change trend and the average value of the second change trend, and determining a contrast coefficient corresponding to the hour to be predicted based on the average value of the first change trend and the average value of the second change trend, wherein the contrast coefficient is the average value of the second change trend/the average value of the first change trend. The historical change trend and the current change trend of the current year are determined through the request quantity in the historical data, the micro service quantity can be accurately predicted according to the change trend, and the capacity expansion and contraction efficiency and accuracy of the distributed system are further improved.
According to the service expansion and contraction method of the distributed system, the historical change trend corresponding to the request quantity of each hour every year is determined based on the request quantity of each hour in the preset year before the current year; then, based on the request quantity of each hour in the current year before the current moment, determining the current change trend corresponding to the request quantity of each hour in the current year; and then, based on the historical change trend and the current change trend, determining a contrast coefficient corresponding to the hour to be predicted, and determining the historical change trend and the current change trend of the current year according to the request quantity in the historical data, so that the micro-service quantity can be accurately predicted according to the change trend, and the capacity expansion efficiency and the capacity expansion accuracy of the distributed system are further improved.
Based on the first embodiment, a third embodiment of the service expansion and contraction method of the distributed system of the present invention is provided, in this embodiment, step S102 includes:
Step S301, determining micro-service quantity offset values of all the hours in the preset year before the current year through a kernel function mean shift algorithm based on the micro-service quantity of all the hours in the preset year before the current year;
Step S302, determining the average value of the micro service amount of each hour in each year based on the micro service amount offset value of each hour in the preset year before the current year;
Step S303, determining the micro service volume average value corresponding to the hour to be predicted in the micro service volume average value of each hour every year.
In this embodiment, the micro-service number of each hour in the preset year before the current year is obtained first, and then the micro-service offset value of the micro-service number of each hour in the preset year before the current year is determined through a kernel function mean shift algorithm, where the micro-service offset value is the same as the calculation formula of the first request offset value. When the calculation formula of the first request quantity offset value is applied to the calculation of the micro-service quantity offset value, wherein Mr (X) is the micro-service quantity offset value, n is the center point of the micro-service, X i is the micro-service in the range, n is the number of points, namely the request quantity, and r is the radius.
Then, calculating the average value of the micro service amount of each hour in each year based on the micro service amount offset value of each hour in the preset year before the current year; specifically, splitting the micro-service offset value to obtain a micro-service offset value of the same hour in a preset year, taking the average value of the micro-service offset values of the same hour in the preset year as the micro-service average value corresponding to the hour, and further obtaining the micro-service average value of each hour each year, for example, a i,j is the micro-service offset value of the j-th hour in the i-th year, j=1, 2, 3, 4 …, j < = 8760; the micro-service volume average AVG j＝(ai,j+ai+1,j+…+an,j)/n, n being the number of years the preset year contains.
And finally, determining the micro-service average value corresponding to the hour to be predicted in the micro-service average value of each hour each year. The method comprises the steps of firstly determining the specific time of an hour to be predicted in the current year, for example, the time in each year comprises 1, 2, 3 and 4 … 8760, wherein the specific time is one of the specific times, and then taking the average value of the micro-service volume average values of each hour in each year, wherein the average value of the corresponding time and the specific time is the same as the micro-service volume average value corresponding to the hour to be predicted.
According to the service expansion and contraction method of the distributed system, the micro service quantity offset value of each hour in the preset year before the current year is determined through a kernel function mean shift algorithm based on the micro service quantity of each hour in the preset year before the current year; then, determining the average value of the micro service amount of each hour in each year based on the micro service amount offset value of each hour in the preset year before the current year; and then, determining the micro-service average value corresponding to the hour to be predicted in the micro-service average value of each hour every year, and screening the micro-service average value corresponding to the hour to be predicted from the micro-service average value of each hour obtained by the micro-service number of each hour in the history, so that the micro-service average value can be accurately reached according to the history data, and the capacity expansion efficiency and the capacity expansion accuracy of the distributed system can be further improved.
Based on the foregoing embodiments, a fourth embodiment of a service expansion and contraction method of a distributed system according to the present invention is provided, where in this embodiment, before step S103, the service expansion and contraction method of a distributed system further includes:
Step S401, acquiring first historical request data in a preset year before the current year and second historical request data in the preset year before the current year, wherein the service is the same as a service scene of the first historical request data;
step S402, model training is performed on the request quantity prediction model based on the first historical request data and the second historical request data to obtain a pre-trained request quantity prediction model.
In this embodiment, first historical request data in a preset year before a current year and a service identical to a service scene of the first historical request data are obtained, second historical request data in the preset year before the current year are obtained, then a request quantity prediction model is built according to sample data formed by the first historical request data and the second historical request data, a network comprising L hidden layers is built according to the number of samples in the sample data, each layer comprises 2n units, only one unit is arranged at the last layer of the network and is not activated, the network is a linear layer, and a variable trend loss function is used for compiling the current network to obtain the request quantity prediction model; wherein, L and n can be set reasonably according to the size of the sample data.
Then, based on the first historical request data and the second historical request data, model training is performed on the request quantity prediction model to obtain a pre-trained request quantity prediction model. Specifically, the sample data is divided into r groups of sub-samples, the sample correction variance of the i-th group is Si2, N-r is the degree of freedom, and N is the number of samples in the sample data. Then training the r groups of sub-samples for model training of preset rounds until a pre-trained request quantity prediction model is obtained, sequentially traversing the r groups of sub-samples for model training of each round, inputting a target sub-sample into the request quantity prediction model for model training, wherein the target sub-sample is any group of samples in the currently traversed r groups of sub-samples to obtain a trained request quantity prediction model, then taking the trained request quantity prediction model as the request quantity prediction model, and continuously traversing the r groups of sub-samples until traversing the r groups of sub-samples is completed, so as to obtain the request quantity prediction model and a loss function of the current round, and taking the request quantity prediction model of the current round as the pre-trained request quantity prediction model if the loss function is smaller than a preset loss.
According to the service expansion and contraction method of the distributed system, first historical request data in a preset year before the current year and second historical request data in the preset year before the current year are obtained, and the service is the same as the service scene of the first historical request data; and then, based on the first historical request data and the second historical request data, carrying out model training on the request quantity prediction model to obtain a pre-trained request quantity prediction model, and training the request quantity prediction model through the request data of other businesses with the same business scene by the historical request data of the distributed system, so that the prediction of the pre-trained request quantity prediction model is more accurate and reliable, the whole algorithm is more close to the change trend of the real business, the prediction of the future micro-service capacity is more accurate, and the capacity expansion and contraction efficiency and the accuracy of the distributed system are further improved.
The present invention also provides a service expansion and contraction device of a distributed system, referring to fig. 3, the service expansion and contraction device of the distributed system includes:
a first determining module 10, configured to determine a contrast coefficient corresponding to an hour to be predicted based on a historical variation trend corresponding to a number of requests of each hour each year and a current variation trend corresponding to a number of requests of each hour in a current year in the distributed system, where the number of requests is a number of requests corresponding to a micro service;
A second determining module 20, configured to determine, in the distributed system, a micro-service average value corresponding to an hour to be predicted by a kernel function average value shift algorithm based on the micro-service number of each hour in a preset year before the current year;
The training module 30 is configured to input the number of requests of each hour in the current year in the distributed system into a pre-trained request quantity prediction model to perform model training, so as to obtain a predicted request quantity corresponding to the hour to be predicted;
an obtaining module 40, configured to obtain an hour request amount of a microservice processing request per hour and a current started microservice amount in the distributed system, and determine a microservice amount corresponding to an hour to be predicted based on the predicted request amount, the comparison coefficient, the microservice amount average value, the hour request amount and the started microservice amount;
and the capacity expansion and contraction module 50 is used for executing capacity expansion and contraction operation of micro services on the distributed system based on the micro service quantity corresponding to the to-be-predicted hour.
The method executed by each program unit may refer to each embodiment of the service expansion and contraction method of the distributed system of the present invention, which is not described herein.
The invention also provides a computer readable storage medium.
The computer readable storage medium of the present invention stores a service expansion and contraction program of a distributed system, which when executed by a processor, implements the steps of the service expansion and contraction method of the distributed system as described above.
The method implemented when the service capacity expansion and contraction program of the distributed system running on the processor is executed may refer to various embodiments of the service capacity expansion and contraction method of the distributed system of the present invention, which are not described herein again.
In addition, the embodiment of the invention also provides a computer program product, which comprises a service expansion and contraction program of the distributed system, and the service expansion and contraction program of the distributed system realizes the steps of the service expansion and contraction method of the distributed system when being executed by a processor.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) as described above, comprising instructions for causing a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the method according to the embodiments of the present invention.
The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.
Claims (10)
1. The service expansion and contraction method of the distributed system is characterized by comprising the following steps of:
Determining a contrast coefficient corresponding to an hour to be predicted based on a historical change trend corresponding to the number of requests in each hour in each year and a current change trend corresponding to the number of requests in each hour in the current year in a distributed system, wherein the number of requests is the number of requests corresponding to micro-services;
Determining a micro-service average value corresponding to an hour to be predicted by a kernel function average value shift algorithm based on the micro-service number of each hour in a preset year before the current year in the distributed system;
Inputting the request quantity of each hour in the current year in the distributed system into a pre-trained request quantity prediction model for model training to obtain a predicted request quantity corresponding to the hour to be predicted;
Acquiring an hour request quantity of a micro service processing request per hour and a current started micro service quantity in a distributed system, and determining the micro service quantity corresponding to an hour to be predicted based on the predicted request quantity, a comparison coefficient, a micro service quantity average value, the hour request quantity and the started micro service quantity, wherein the formula of the micro service quantity is as follows: c=math.ceil ((Pt/Q) ×r+math.floor (math.abs ((Bc/s_ AVGs-1) ×bc))), wherein the math.ceil function is an upward rounding function; the floor function is a rounding function; math.abs is an absolute function, pt is a predicted request quantity, Q is an hour request quantity, R is a contrast coefficient, bc is the number of started micro services, and S_ AVGs is a micro-service average value;
And executing micro-service capacity expansion operation on the distributed system based on the micro-service quantity corresponding to the hour to be predicted, wherein the difference value between the micro-service quantity and the started micro-service quantity is calculated, if the difference value is larger than 0, the micro-service capacity expansion operation is executed on the distributed system according to the difference value, and if the difference value is smaller than 0, the micro-service capacity expansion operation is executed on the distributed system according to the difference value.
2. The service expansion and contraction method of a distributed system according to claim 1, wherein the step of determining the contrast coefficient corresponding to the hour to be predicted based on the historical trend corresponding to the number of requests of each hour per year and the current trend corresponding to the number of requests of each hour of the current year in the distributed system comprises:
determining a historical variation trend corresponding to the number of requests of each hour each year based on the number of requests of each hour in a preset year before the current year;
Determining a current change trend corresponding to the request quantity of each hour in the current year based on the request quantity of each hour in the current year before the current moment;
and determining a contrast coefficient corresponding to the hour to be predicted based on the historical change trend and the current change trend.
3. The service extension and contraction method of the distributed system according to claim 2, wherein the step of determining the historical trend corresponding to the number of requests of each hour each year based on the number of requests of each hour in a preset year before the current year includes:
Determining a first request quantity offset value of each hour in the preset year before the current year through a kernel function mean shift algorithm based on the request quantity of each hour in the preset year before the current year;
determining a first request amount mean value for each hour each year based on the first request amount offset value;
and determining the historical change trend corresponding to the number of requests in each hour each year based on the coordinate curve corresponding to the first request quantity average value.
4. The service expansion and contraction method of a distributed system according to claim 2, wherein the step of determining the current trend of change corresponding to the number of requests for each hour in the current year based on the number of requests for each hour in the current year before the current time comprises:
determining a second request quantity offset value of each hour in the current year before the current moment through a kernel function mean shift algorithm based on the request quantity of each hour in the current year before the current moment;
Determining a second request quantity average value of each hour in the current year based on the second request quantity offset value;
And determining the current change trend corresponding to the request quantity of each hour in the current year based on the coordinate curve corresponding to the second request quantity average value.
5. The service expansion and contraction method of the distributed system according to claim 2, wherein the step of determining the contrast coefficient corresponding to the hour to be predicted based on the historical trend of change and the current trend of change includes:
acquiring a first change trend corresponding to a target time of each day from the historical change trend, wherein the target time is the time of the hour to be predicted in the current day;
acquiring a second change trend corresponding to the daily target moment from the current change trend;
And determining a contrast coefficient corresponding to the hour to be predicted based on the average value of the first change trend and the average value of the second change trend.
6. The service scaling method of a distributed system according to claim 1, wherein the step of determining the average value of the micro services corresponding to the hour to be predicted by the kernel function mean shift algorithm based on the number of micro services of each hour in a preset year before the current year in the distributed system comprises:
Determining micro-service quantity offset values of all the hours in the preset year before the current year through a kernel function mean shift algorithm based on the micro-service quantity of all the hours in the preset year before the current year;
Determining a micro-service average value of each hour of each year based on the micro-service offset value of each hour in a preset year before the current year;
And determining the micro-service average value corresponding to the hour to be predicted from the micro-service average value of each hour every year.
7. The service expansion and contraction method of a distributed system according to any one of claims 1 to 6, wherein before the step of inputting the number of requests of each hour in the current year in the distributed system into a pre-trained request amount prediction model to perform model training to obtain a predicted request amount corresponding to the hour to be predicted, the method further comprises:
Acquiring first historical request data in a preset year before the current year and a service which is the same as a service scene of the first historical request data, wherein the second historical request data in the preset year before the current year;
based on the first historical request data and the second historical request data, model training is performed on the request quantity prediction model to obtain a pre-trained request quantity prediction model.
8. A service expansion and contraction device of a distributed system, wherein the service expansion and contraction device of the distributed system comprises:
The first determining module is used for determining a contrast coefficient corresponding to an hour to be predicted based on a historical change trend corresponding to the number of requests in each hour each year and a current change trend corresponding to the number of requests in each hour in the current year in the distributed system, wherein the number of requests is the number of requests corresponding to the micro-service;
The second determining module is used for determining a micro-service average value corresponding to the hour to be predicted through a kernel function average value shift algorithm based on the micro-service number of each hour in a preset year before the current year in the distributed system;
The training module is used for inputting the request quantity of each hour in the current year in the distributed system into a pre-trained request quantity prediction model for model training to obtain a predicted request quantity corresponding to the hour to be predicted;
The acquisition module is used for acquiring the hour request quantity of the micro-service processing request per hour and the current started micro-service quantity in the distributed system, and determining the micro-service quantity corresponding to the hour to be predicted based on the predicted request quantity, the comparison coefficient, the micro-service quantity average value, the hour request quantity and the started micro-service quantity, wherein the formula of the micro-service quantity is as follows: c=math.ceil ((Pt/Q) ×r+math.floor (math.abs ((Bc/s_ AVGs-1) ×bc))), wherein the math.ceil function is an upward rounding function; the floor function is a rounding function; math.abs is an absolute function, pt is a predicted request quantity, Q is an hour request quantity, R is a contrast coefficient, bc is the number of started micro services, and S_ AVGs is a micro-service average value;
and the capacity expansion and contraction module is used for executing the capacity expansion and contraction operation of the micro service on the distributed system based on the micro service quantity corresponding to the to-be-predicted hour, wherein the difference value between the micro service quantity and the started micro service quantity is calculated, if the difference value is larger than 0, the capacity expansion operation of the micro service is executed on the distributed system according to the difference value, and if the difference value is smaller than 0, the capacity expansion operation of the micro service is executed on the distributed system according to the difference value.
9. A service expansion device of a distributed system, wherein the service expansion device of the distributed system comprises: memory, a processor and a service extension program of a distributed system stored on the memory and executable on the processor, which when executed by the processor, implements the steps of the service extension method of a distributed system according to any of claims 1 to 7.
10. A computer readable storage medium, characterized in that it has stored thereon a service extension program of a distributed system, which when executed by a processor implements the steps of the service extension method of a distributed system according to any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110816331.2A CN113568741B (en) | 2021-07-19 | 2021-07-19 | Service expansion and contraction method, device, equipment and storage medium of distributed system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110816331.2A CN113568741B (en) | 2021-07-19 | 2021-07-19 | Service expansion and contraction method, device, equipment and storage medium of distributed system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113568741A CN113568741A (en) | 2021-10-29 |
| CN113568741B true CN113568741B (en) | 2024-05-10 |
Family
ID=78165527
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110816331.2A Active CN113568741B (en) | 2021-07-19 | 2021-07-19 | Service expansion and contraction method, device, equipment and storage medium of distributed system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113568741B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019134623A1 (en) * | 2018-01-02 | 2019-07-11 | ***通信有限公司研究院 | Capacity expansion and reduction method, device, apparatus and computer readable storage medium |
| CN110457287A (en) * | 2019-07-03 | 2019-11-15 | 北京百度网讯科技有限公司 | The scalable content processing method and device of database, computer equipment and readable medium |
| CN112199150A (en) * | 2020-08-13 | 2021-01-08 | 北京航空航天大学 | Online application dynamic capacity expansion and contraction method based on micro-service calling dependency perception |
| CN112559191A (en) * | 2020-12-23 | 2021-03-26 | 平安银行股份有限公司 | Method and device for dynamically deploying GPU (graphics processing Unit) resources and computer equipment |
-
2021
- 2021-07-19 CN CN202110816331.2A patent/CN113568741B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019134623A1 (en) * | 2018-01-02 | 2019-07-11 | ***通信有限公司研究院 | Capacity expansion and reduction method, device, apparatus and computer readable storage medium |
| CN110457287A (en) * | 2019-07-03 | 2019-11-15 | 北京百度网讯科技有限公司 | The scalable content processing method and device of database, computer equipment and readable medium |
| CN112199150A (en) * | 2020-08-13 | 2021-01-08 | 北京航空航天大学 | Online application dynamic capacity expansion and contraction method based on micro-service calling dependency perception |
| CN112559191A (en) * | 2020-12-23 | 2021-03-26 | 平安银行股份有限公司 | Method and device for dynamically deploying GPU (graphics processing Unit) resources and computer equipment |
Non-Patent Citations (1)
| Title |
|---|
| 基于集群的高性能家庭影院认证授权***研究;王木旺;;现代电影技术(06);第6-11页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113568741A (en) | 2021-10-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20150278350A1 (en) | Recommendation System With Dual Collaborative Filter Usage Matrix | |
| CN1477895A (en) | Mobile terminal and its control method | |
| CN111652378B (en) | Learning to select vocabulary for category features | |
| CN111898247B (en) | Landslide displacement prediction method, landslide displacement prediction equipment and storage medium | |
| CN111144584A (en) | Parameter tuning method, device and computer storage medium | |
| CN112632380A (en) | Training method of interest point recommendation model and interest point recommendation method | |
| CN112307243B (en) | Method and apparatus for retrieving images | |
| CN114880310A (en) | User behavior analysis method and device, computer equipment and storage medium | |
| CN112214677A (en) | Interest point recommendation method and device, electronic equipment and storage medium | |
| CN110717405B (en) | Face feature point positioning method, device, medium and electronic equipment | |
| CN110555861B (en) | Optical flow calculation method and device and electronic equipment | |
| CN113886721B (en) | Personalized interest point recommendation method and device, computer equipment and storage medium | |
| CN113568741B (en) | Service expansion and contraction method, device, equipment and storage medium of distributed system | |
| CN116415744B (en) | Power prediction method and device based on deep learning and storage medium | |
| CN114420135A (en) | Attention mechanism-based voiceprint recognition method and device | |
| CN112418442A (en) | Data processing method, device, equipment and storage medium for federal transfer learning | |
| CN110378936B (en) | Optical flow calculation method and device and electronic equipment | |
| CN112381224A (en) | Neural network training method, device, equipment and computer readable storage medium | |
| CN109544241B (en) | Click rate estimation model construction method, click rate estimation method and device | |
| US8639693B1 (en) | Personalized place recommendations using collections of place listings | |
| CN116416818A (en) | Parking space reservation method, device, equipment and computer readable storage medium | |
| CN110969361B (en) | Method, device, equipment and computer readable storage medium for evaluating empty rate | |
| CN112308406B (en) | Data ordering method, device, equipment and computer readable storage medium | |
| CN113283115B (en) | Image model generation method and device and electronic equipment | |
| CN117576099B (en) | Liquid bottle separation detection method and device and computer readable storage medium |
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 |