CN109558674A - Method for Sales Forecast and its model training method, device - Google Patents
Method for Sales Forecast and its model training method, device Download PDFInfo
- Publication number
- CN109558674A CN109558674A CN201811435865.5A CN201811435865A CN109558674A CN 109558674 A CN109558674 A CN 109558674A CN 201811435865 A CN201811435865 A CN 201811435865A CN 109558674 A CN109558674 A CN 109558674A
- Authority
- CN
- China
- Prior art keywords
- training
- data
- model
- sample
- sample data
- 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.)
- Pending
Links
- 238000012549 training Methods 0.000 title claims abstract description 133
- 238000000034 method Methods 0.000 title claims abstract description 53
- 238000004590 computer program Methods 0.000 claims description 9
- 239000011159 matrix material Substances 0.000 claims description 9
- 238000013499 data model Methods 0.000 claims 1
- 230000000712 assembly Effects 0.000 abstract description 8
- 238000000429 assembly Methods 0.000 abstract description 8
- 238000012546 transfer Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 6
- 238000012545 processing Methods 0.000 description 5
- 238000001514 detection method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000003068 static effect Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
Abstract
The invention discloses a kind of Method for Sales Forecast and its model training method, device, computer equipment and storage mediums, and wherein model training method includes: to obtain training sample data;The training sample data are classified according to sample class, form multiple row sample data;The multiple row sample data is distributed to the training pattern being deployed on serverless backup framework by column, is trained by the training pattern, the model after being trained, wherein the training pattern being deployed on serverless backup framework is the model run on single machine.The invention avoids training patterns, and to run resource on single machine limited, the problem of running on distributed type assemblies server, need the significantly algorithmic code of adjusting training model.
Description
Technical field
The present invention relates to depth learning technology fields, and in particular to a kind of Method for Sales Forecast and its model training method, device,
Computer equipment and storage medium.
Background technique
Currently, comparative maturity, these mature training patterns generally operate in all kinds of training patterns of deep learning
On single machine, but the CPU of single machine and memory source are than relatively limited.Due to currently to merchandise sales enterprise (for example, retail convenience shop
Or retail supermarket) acquisition data volume it is bigger, need high configuration to be just able to achieve if using single machine.And if using
Distributed type assemblies server then needs to make many adjustment to the algorithmic code of training pattern itself, considerably increases instruction
The complexity for practicing the algorithm application of model, increases the workload of research staff.
Summary of the invention
The invention solves existing training pattern in the prior art, to run resource on single machine limited, in distributed type assemblies
The problem of being run on server, needing the significantly algorithmic code of adjusting training model, thus provide a kind of Method for Sales Forecast and its
Model training method, device, computer equipment and storage medium.
An aspect of of the present present invention provides a kind of model training method, comprising: obtains training sample data;According to sample
Classification classifies the training sample data, forms multiple row sample data;The multiple row sample data is distributed to by column
The training pattern being deployed on serverless backup framework, is trained by the training pattern, the model after being trained, wherein
The training pattern being deployed on serverless backup framework is the model run on single machine.
Optionally, the training sample data are being classified according to sample class, are being formed after multiple row sample data,
Further include: the multiple row sample data is stored in distributed storage server.
Optionally, the training sample data are classified according to sample class, formed multiple row sample data include: by
The training sample data are packed into data matrix, wherein each column represent a sample class in the data matrix.
Optionally, further includes: according to the corresponding son training mould of sample class building on the serverless backup framework
Type, wherein the corresponding sub- training pattern of each sample class;Wherein, the multiple row sample data is distributed to deployment by column
Training pattern on serverless backup framework includes: that each column sample data is distributed to corresponding sub- instruction according to the sample class
Practice and is trained in model.
Optionally, the training sample data are Sales Volume of Commodity data, and the sample class is merchandise classification, the training
Model is Method for Sales Forecast model.
Another aspect of the present invention provides a kind of Method for Sales Forecast method, comprising: obtains the Sales Volume of Commodity number of preset time
According to;Classify according to merchandise classification to the Sales Volume of Commodity data, forms multiple row Sales Volume of Commodity data;By column by the commodity
Sales volume data are input in the model that the model training method training obtains, and the Sales Volume of Commodity for obtaining each merchandise classification is pre-
Survey result.
Another aspect of the present invention provides a kind of model training apparatus, comprising: sample acquisition module, for obtaining instruction
Practice sample data;Sample classification module forms multiple row sample for the training sample data to be classified according to sample class
Notebook data;Training module, for the multiple row sample data to be distributed to the training mould being deployed on serverless backup framework by column
Type, is trained by the training pattern, the model after being trained, wherein the instruction being deployed on serverless backup framework
Practicing model is the model run on single machine.
Another aspect of the present invention provides a kind of Method for Sales Forecast device, comprising: sales volume data acquisition module, for obtaining
Take the Sales Volume of Commodity data of preset time;Commodity data categorization module is used for according to merchandise classification to the Sales Volume of Commodity data
Classify, forms multiple row Sales Volume of Commodity data;The Sales Volume of Commodity data are input to described by prediction module for by column
In the model that model training method training obtains, the Sales Volume of Commodity prediction result of each merchandise classification is obtained.
Another aspect of the present invention provides a kind of computer equipment and includes memory, processor and be stored in storage
On device and the computer program that can run on a processor, the processor realize the method when executing the computer program
The step of.
Another aspect of the present invention provides a kind of computer readable storage medium, is stored thereon with computer program, institute
State the step of realizing the method when computer program is executed by processor.
In the embodiment of the present invention, by the way that the training pattern that can only be run on single machine is deployed on serverless backup framework,
It that is to say and the code of training pattern and feature are deployed on serverless backup framework, it is only necessary to increase on the code of training pattern
The function of one resource transfer, so that it may in the way of the resource transfer possessed by the serverless backup framework, realize big data quantity
Model training, avoiding training pattern, to run resource on single machine limited, runs, needs big on distributed type assemblies server
The problem of algorithmic code of amplitude adjusting training model.
Detailed description of the invention
It, below will be to specific in order to illustrate more clearly of the specific embodiment of the invention or technical solution in the prior art
Embodiment or attached drawing needed to be used in the description of the prior art be briefly described, it should be apparent that, it is described below
Attached drawing is some embodiments of the present invention, for those of ordinary skill in the art, before not making the creative labor
It puts, is also possible to obtain other drawings based on these drawings.
Fig. 1 is the flow chart of the processing method of learning information in the embodiment of the present invention;
Fig. 2 is the schematic diagram of message queue in the embodiment of the present invention;
Fig. 3 is the schematic diagram of the processing unit of learning information in the embodiment of the present invention;
Fig. 4 is the hardware structural diagram of computer equipment of the embodiment of the present invention;And
Fig. 5 shows the computer equipment with processor and memory.
Specific embodiment
Technical solution of the present invention is clearly and completely described below in conjunction with attached drawing, it is clear that described implementation
Example is a part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, ordinary skill
Personnel's every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
In the description of the present invention, it should be noted that term " first ", " second ", " third " are used for description purposes only,
It is not understood to indicate or imply relative importance.
As long as in addition, the non-structure each other of technical characteristic involved in invention described below different embodiments
It can be combined with each other at conflict.
The embodiment of the invention provides a kind of model training methods, as shown in Figure 1, this method comprises:
Step S101 obtains training sample data.Training sample data may include training data and detection data,
In, training data is trained use for training pattern, and detection data then is used to detect the accuracy of training pattern, to protect
The detection accuracy of model after card training.
Step S102 classifies the training sample data according to sample class, forms multiple row sample data.Specifically
The training sample data can be packed into data matrix by ground, wherein each column represent a sample in the data matrix
This classification.
After the classification, the multiple row sample data is stored in distributed storage server.
The multiple row sample data is distributed to the training pattern being deployed on serverless backup framework by step S103 by column,
It is trained by the training pattern, the model after being trained, wherein the trained mould being deployed on serverless backup framework
Type is the model run on single machine.Wherein, serverless backup framework can refer to the framework calculated using serverless backup, no service
Device calculating is the new paragon of the managed application in the infrastructure without end user management.Serverless backup calculating is a kind of
Cloud service, managed service provider can distribute sufficient resource in real time for you, rather than allow you be in advance dedicated server or
Capacity payment.
In the embodiment of the present invention, by the way that the training pattern that can only be run on single machine is deployed on serverless backup framework,
It that is to say and the code of training pattern and feature are deployed on serverless backup framework, it is only necessary to increase on the code of training pattern
The function of one resource transfer, so that it may in the way of the resource transfer possessed by the serverless backup framework, realize big data quantity
Model training, avoiding training pattern, to run resource on single machine limited, runs, needs big on distributed type assemblies server
The problem of algorithmic code of amplitude adjusting training model.
In the embodiment of the present invention, do not limit the algorithm of any training pattern, if the algorithm of training pattern be it is existing, open
Source, the algorithm that is run on single machine.Optionally, the training sample data of the embodiment of the present invention can be commodity pin
Data are measured, the sample class can be merchandise classification, and the training pattern can be Method for Sales Forecast model.
For Sales Volume of Commodity data, data storage can be carried out by the way of matrix, wherein each column represent a quotient
Category is other, and every a line represents the data of a chronomere.To which each of matrix element represents some chronomere
The sales volume of some commodity.There is the retail convenience shop of 2500 SKU for one, nearly 2 years Sales Volume of Commodity data can be acquired,
Establish the matrix of 730 rows 2500 column, the sales data of 2500 SKU to indicate nearest 2 years.
As an alternative embodiment, serverless backup framework supports the reception data of multi-column version, and to each column
Construct model, therefore, the model training method of the embodiment of the present invention further include: according to the sample on the serverless backup framework
This classification constructs corresponding sub- training pattern, wherein the corresponding sub- training pattern of each sample class.
Correspondingly, the multiple row sample data is distributed to the training pattern packet being deployed on serverless backup framework by column
It includes: each column sample data being distributed in corresponding sub- training pattern according to the sample class and is trained.After training
Sub- training pattern, integration obtain the model after final training.
The embodiment of the invention also provides a kind of Method for Sales Forecast methods, as shown in Fig. 2, this method comprises:
Step S201 obtains the Sales Volume of Commodity data of preset time.
Step S202 classifies to the Sales Volume of Commodity data according to merchandise classification, forms multiple row Sales Volume of Commodity data.
For the classification of Sales Volume of Commodity data can mode identical with above-mentioned training sample data handle.
The Sales Volume of Commodity data are input in the model that model training method training obtains by column, obtain by step S203
To the Sales Volume of Commodity prediction result of each merchandise classification.Wherein model training method is side described in the above embodiment of the present invention
Method is not described herein.
In the embodiment of the present invention, serverless backup frame is equally deployed in using the model that the training of above-mentioned model training method obtains
On structure, it is only necessary to increase the function of a resource transfer on the code of training pattern, so that it may utilize serverless backup framework institute
The resource transfer mode having, realizes the model training of big data quantity, and avoiding training pattern, to run resource on single machine limited,
The problem of being run on distributed type assemblies server, needing the significantly algorithmic code of adjusting training model.
The embodiment of the invention also provides a kind of model training apparatus, as shown in figure 3, the device includes:
Sample acquisition module 31, for obtaining training sample data.
Sample classification module 32 forms multiple row sample for the training sample data to be classified according to sample class
Notebook data.
Training module 33, for the multiple row sample data to be distributed to the training being deployed on serverless backup framework by column
Model, is trained by the training pattern, the model after being trained, wherein is deployed in described on serverless backup framework
Training pattern is the model run on single machine.
In the embodiment of the present invention, by the way that the training pattern that can only be run on single machine is deployed on serverless backup framework,
It that is to say and the code of training pattern and feature are deployed on serverless backup framework, it is only necessary to increase on the code of training pattern
The function of one resource transfer, so that it may in the way of the resource transfer possessed by the serverless backup framework, realize big data quantity
Model training, avoiding training pattern, to run resource on single machine limited, runs, needs big on distributed type assemblies server
The problem of algorithmic code of amplitude adjusting training model.
It specifically describes referring to above method embodiment, which is not described herein again.
The embodiment of the invention also provides a kind of Method for Sales Forecast devices, as shown in figure 4, the device includes:
Sales volume data acquisition module 41, for obtaining the Sales Volume of Commodity data of preset time;
Commodity data categorization module 42 is formed more for classifying according to merchandise classification to the Sales Volume of Commodity data
Column Sales Volume of Commodity data;
Prediction module 43, for the Sales Volume of Commodity data to be input to mould described in any one of claim 1 to 5 by column
In the model that the training of type training method obtains, the Sales Volume of Commodity prediction result of each merchandise classification is obtained.
In the embodiment of the present invention, serverless backup frame is equally deployed in using the model that the training of above-mentioned model training method obtains
On structure, it is only necessary to increase the function of a resource transfer on the code of training pattern, so that it may utilize serverless backup framework institute
The resource transfer mode having, realizes the model training of big data quantity, and avoiding training pattern, to run resource on single machine limited,
The problem of being run on distributed type assemblies server, needing the significantly algorithmic code of adjusting training model.
It specifically describes referring to above method embodiment, which is not described herein again.
The present embodiment also provides a kind of computer equipment, can such as execute the desktop computer of program, rack-mount server,
Blade server, tower server or Cabinet-type server are (including composed by independent server or multiple servers
Server cluster) etc..The computer equipment 20 of the present embodiment includes, but is not limited to: that company can be in communication with each other by system bus
Memory 21, the processor 22 connect, as shown in Figure 5.It should be pointed out that Fig. 5 illustrates only the computer with component 21-22
Equipment 20, it should be understood that being not required for implementing all components shown, the implementation that can be substituted is more or less
Component.
In the present embodiment, memory 21 (i.e. readable storage medium storing program for executing) includes flash memory, hard disk, multimedia card, card-type memory
(for example, SD or DX memory etc.), random access storage device (RAM), static random-access memory (SRAM), read-only memory
(ROM), electrically erasable programmable read-only memory (EEPROM), programmable read only memory (PROM), magnetic storage, magnetic
Disk, CD etc..In some embodiments, memory 21 can be the internal storage unit of computer equipment 20, such as the calculating
The hard disk or memory of machine equipment 20.In further embodiments, memory 21 is also possible to the external storage of computer equipment 20
The plug-in type hard disk being equipped in equipment, such as the computer equipment 20, intelligent memory card (Smart Media Card, SMC), peace
Digital (Secure Digital, SD) card, flash card (Flash Card) etc..Certainly, memory 21 can also both include meter
The internal storage unit for calculating machine equipment 20 also includes its External memory equipment.In the present embodiment, memory 21 is commonly used in storage
Be installed on the operating system and types of applications software of computer equipment 20, for example, above-described embodiment device program code etc..
In addition, memory 21 can be also used for temporarily storing the Various types of data that has exported or will export.
Processor 22 can be in some embodiments central processing unit (Central Processing Unit, CPU),
Controller, microcontroller, microprocessor or other data processing chips.The processor 22 is commonly used in control computer equipment
20 overall operation.In the present embodiment, program code or processing data of the processor 22 for being stored in run memory 21,
The method for realizing above-described embodiment.
The present embodiment also provides a kind of computer readable storage medium, such as flash memory, hard disk, multimedia card, card-type memory
(for example, SD or DX memory etc.), random access storage device (RAM), static random-access memory (SRAM), read-only memory
(ROM), electrically erasable programmable read-only memory (EEPROM), programmable read only memory (PROM), magnetic storage, magnetic
Disk, CD, server, App are stored thereon with computer program, phase are realized when program is executed by processor using store etc.
Answer function.The computer readable storage medium of the present embodiment is used to store the code of the method for above-described embodiment, is held by processor
The method of above-described embodiment is realized when row.
Obviously, the above embodiments are merely examples for clarifying the description, and does not limit the embodiments.It is right
For those of ordinary skill in the art, can also make on the basis of the above description it is other it is various forms of variation or
It changes.There is no necessity and possibility to exhaust all the enbodiments.And it is extended from this it is obvious variation or
It changes among still in the protection scope of the application.
Claims (10)
1. a kind of model training method characterized by comprising
Obtain training sample data;
The training sample data are classified according to sample class, form multiple row sample data;
The multiple row sample data is distributed to the training pattern being deployed on serverless backup framework by column, by the training pattern
It is trained, the model after being trained, wherein the training pattern being deployed on serverless backup framework is to transport on single machine
Capable model.
2. the method according to claim 1, wherein the training sample data are carried out according to sample class
Classification is formed after multiple row sample data, further includes:
The multiple row sample data is stored in distributed storage server.
3. the method according to claim 1, wherein the training sample data are divided according to sample class
Class, forming multiple row sample data includes:
The training sample data are packed into data matrix, wherein each column represent a sample in the data matrix
Classification.
4. the method according to claim 1, wherein further include:
Corresponding sub- training pattern is constructed according to the sample class on the serverless backup framework, wherein each sample class
It Dui Ying not a sub- training pattern;
Wherein, the multiple row sample data is distributed to the training pattern being deployed on serverless backup framework by column includes:
Each column sample data is distributed in corresponding sub- training pattern according to the sample class and is trained.
5. method according to claim 1-4, which is characterized in that the training sample data are Sales Volume of Commodity number
According to the sample class is merchandise classification, and the training pattern is Method for Sales Forecast model.
6. a kind of Method for Sales Forecast method characterized by comprising
Obtain the Sales Volume of Commodity data of preset time;
Classify according to merchandise classification to the Sales Volume of Commodity data, forms multiple row Sales Volume of Commodity data;
The Sales Volume of Commodity data model training method training described in any one of claim 1 to 5 is input to by column to obtain
Model in, obtain the Sales Volume of Commodity prediction result of each merchandise classification.
7. a kind of model training apparatus characterized by comprising
Sample acquisition module, for obtaining training sample data;
Sample classification module forms multiple row sample data for the training sample data to be classified according to sample class;
Training module, for the multiple row sample data to be distributed to the training pattern being deployed on serverless backup framework by column,
It is trained by the training pattern, the model after being trained, wherein the trained mould being deployed on serverless backup framework
Type is the model run on single machine.
8. a kind of Method for Sales Forecast device characterized by comprising
Sales volume data acquisition module, for obtaining the Sales Volume of Commodity data of preset time;
Commodity data categorization module forms multiple row commodity for classifying according to merchandise classification to the Sales Volume of Commodity data
Sales volume data;
Prediction module, for the Sales Volume of Commodity data to be input to model training described in any one of claim 1 to 5 by column
In the model that method training obtains, the Sales Volume of Commodity prediction result of each merchandise classification is obtained.
9. a kind of computer equipment, which is characterized in that including memory, processor and store on a memory and can handle
The computer program run on device, the processor realized when executing the computer program any one of claim 1 to 5 or
The step of claim 6 the method.
10. a kind of computer readable storage medium, is stored thereon with computer program, it is characterised in that: the computer program
The step of any one of claim 1 to 5 or claim 6 the method are realized when being executed by processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811435865.5A CN109558674A (en) | 2018-11-28 | 2018-11-28 | Method for Sales Forecast and its model training method, device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811435865.5A CN109558674A (en) | 2018-11-28 | 2018-11-28 | Method for Sales Forecast and its model training method, device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109558674A true CN109558674A (en) | 2019-04-02 |
Family
ID=65867820
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811435865.5A Pending CN109558674A (en) | 2018-11-28 | 2018-11-28 | Method for Sales Forecast and its model training method, device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109558674A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110135907A (en) * | 2019-05-14 | 2019-08-16 | 网易无尾熊(杭州)科技有限公司 | Method for building up, medium, device and the calculating equipment of Method for Sales Forecast model |
CN110222779A (en) * | 2019-06-11 | 2019-09-10 | 腾讯科技(深圳)有限公司 | Distributed data processing method and system |
CN111178517A (en) * | 2020-01-20 | 2020-05-19 | 上海依图网络科技有限公司 | Model deployment method, system, chip, electronic device and medium |
CN112308205A (en) * | 2020-06-28 | 2021-02-02 | 北京沃东天骏信息技术有限公司 | Model improvement method and device based on pre-training model |
CN113055476A (en) * | 2021-03-12 | 2021-06-29 | 杭州网易再顾科技有限公司 | Cluster type service system, method, medium and computing equipment |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105184313A (en) * | 2015-08-24 | 2015-12-23 | 小米科技有限责任公司 | Classification model construction method and device |
CN105956699A (en) * | 2016-04-29 | 2016-09-21 | 连云港天马网络发展有限公司 | Commodity classification and delivery and sales prediction method based on e-commerce sales data |
CN106204086A (en) * | 2015-05-06 | 2016-12-07 | 阿里巴巴集团控股有限公司 | The method for early warning of Sales Volume of Commodity and device |
CN108133391A (en) * | 2017-12-22 | 2018-06-08 | 联想(北京)有限公司 | Method for Sales Forecast method and server |
CN108573358A (en) * | 2018-05-09 | 2018-09-25 | 平安普惠企业管理有限公司 | A kind of overdue prediction model generation method and terminal device |
CN108845878A (en) * | 2018-05-08 | 2018-11-20 | 南京理工大学 | The big data processing method and processing device calculated based on serverless backup |
-
2018
- 2018-11-28 CN CN201811435865.5A patent/CN109558674A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106204086A (en) * | 2015-05-06 | 2016-12-07 | 阿里巴巴集团控股有限公司 | The method for early warning of Sales Volume of Commodity and device |
CN105184313A (en) * | 2015-08-24 | 2015-12-23 | 小米科技有限责任公司 | Classification model construction method and device |
CN105956699A (en) * | 2016-04-29 | 2016-09-21 | 连云港天马网络发展有限公司 | Commodity classification and delivery and sales prediction method based on e-commerce sales data |
CN108133391A (en) * | 2017-12-22 | 2018-06-08 | 联想(北京)有限公司 | Method for Sales Forecast method and server |
CN108845878A (en) * | 2018-05-08 | 2018-11-20 | 南京理工大学 | The big data processing method and processing device calculated based on serverless backup |
CN108573358A (en) * | 2018-05-09 | 2018-09-25 | 平安普惠企业管理有限公司 | A kind of overdue prediction model generation method and terminal device |
Non-Patent Citations (1)
Title |
---|
日经BP社, 东方出版社 * |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110135907A (en) * | 2019-05-14 | 2019-08-16 | 网易无尾熊(杭州)科技有限公司 | Method for building up, medium, device and the calculating equipment of Method for Sales Forecast model |
CN110222779A (en) * | 2019-06-11 | 2019-09-10 | 腾讯科技(深圳)有限公司 | Distributed data processing method and system |
CN110222779B (en) * | 2019-06-11 | 2023-08-01 | 腾讯科技(深圳)有限公司 | Distributed data processing method and system |
CN111178517A (en) * | 2020-01-20 | 2020-05-19 | 上海依图网络科技有限公司 | Model deployment method, system, chip, electronic device and medium |
CN111178517B (en) * | 2020-01-20 | 2023-12-05 | 上海依图网络科技有限公司 | Model deployment method, system, chip, electronic equipment and medium |
CN112308205A (en) * | 2020-06-28 | 2021-02-02 | 北京沃东天骏信息技术有限公司 | Model improvement method and device based on pre-training model |
CN113055476A (en) * | 2021-03-12 | 2021-06-29 | 杭州网易再顾科技有限公司 | Cluster type service system, method, medium and computing equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109558674A (en) | Method for Sales Forecast and its model training method, device | |
US10498857B2 (en) | System interaction monitoring and component scaling | |
US20150378721A1 (en) | Methods for managing applications using semantic modeling and tagging and devices thereof | |
AU2017254647B2 (en) | Multi-stage network discovery | |
KR20060076164A (en) | Reader application markup language schema | |
CN104838377A (en) | Integrating event processing with map-reduce | |
EP2793175A2 (en) | Optimization utilizing machine learning | |
CN109918437A (en) | Distributed data processing method, apparatus and data assets management system | |
Le et al. | EPC information services with No-SQL datastore for the Internet of Things | |
CN108255628A (en) | A kind of data processing method and device | |
CN106104468A (en) | Dynamically determine the pattern of data process application | |
CN115082247B (en) | System production method, device, equipment, medium and product based on label library | |
CN110727664A (en) | Method and device for executing target operation on public cloud data | |
US9424260B2 (en) | Techniques for data assignment from an external distributed file system to a database management system | |
CN110659760A (en) | Configuration method and system for warehouse storage position | |
CN103530395A (en) | Data tracing method and device | |
CN113076224B (en) | Data backup method, data backup system, electronic device and readable storage medium | |
CN106354435A (en) | Method and device for initializing RAID | |
CN107766530A (en) | A kind of method and its device of gathered data distribution | |
JP2010277571A (en) | Commodity selection system and method, and commodity selection computer program | |
US11281674B2 (en) | Grouping data in a heap using tags | |
CN109961193A (en) | A kind of object-based life cycle management method and device | |
CN106372985A (en) | Order data processing method and device | |
CN110084541B (en) | Method and apparatus for predicting supplier delivery duration | |
CN112131465A (en) | Activity information matching method, device, medium and terminal equipment |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190402 |