CN109658187A - Recommend method, apparatus, storage medium and the electronic equipment of cloud service provider - Google Patents
Recommend method, apparatus, storage medium and the electronic equipment of cloud service provider Download PDFInfo
- Publication number
- CN109658187A CN109658187A CN201811534355.3A CN201811534355A CN109658187A CN 109658187 A CN109658187 A CN 109658187A CN 201811534355 A CN201811534355 A CN 201811534355A CN 109658187 A CN109658187 A CN 109658187A
- Authority
- CN
- China
- Prior art keywords
- cloud service
- service provider
- recommended
- index
- target
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
This disclosure relates to a kind of method, apparatus, storage medium and electronic equipment for recommending cloud service provider, cloud service demand information is obtained first, wherein, the cloud service demand information may include the cloud service index of user's input, then the cloud service provider information of cloud service provider to be recommended is obtained, and according to the cloud service index and the cloud service provider information, from the cloud service provider to be recommended, it determines target cloud service provider, and recommends the target cloud service provider.
Description
Technical field
This disclosure relates to cloud service provider recommend field, and in particular, to it is a kind of recommend cloud service provider method, apparatus, deposit
Storage media and electronic equipment.
Background technique
Cloud computing is as a kind of novel IT technology, it is possible to provide ubiquitous, the on-demand calculating money for obtaining, freely configuring
Source has many advantages, such as elastic flexible, raising resource utilization, save the cost, currently, cloud computing has been widely used for political affairs
Mansion, enterprise operation system in.More cloud services are generally used based on the considerations of strategy, business or cost, the user of cloud service
Quotient, since different cloud service provider scales, the grade of service, service ability, service price are different, and different business systems
It unites different to computing capability, disk I/O, network I/O etc. demand, therefore, how to select suitable cloud service provider and match
Appropriate service configuration is set, and then improves resource utilization to greatest extent, ensures business SLA, effectively controls cost, needs one kind
Effective technological means.
In actual conditions, user selects the cloud service provider needs of operation system are various to consider, such as takes to service provider
Business ability is considered, and is considered to cost, operation system characteristic, in the related technology to the service performance of cloud service provider and
Service ability is evaluated, but does not consider the actual demand of subscriber service system, therefore, to the evaluation result of cloud service provider
It is suitble to the reference value of the target cloud service provider of oneself smaller user's selection, while is also required to user oneself and searching the target cloud
Service provider, so that the efficiency of user's selection target cloud service provider can be reduced.
Summary of the invention
The disclosure provides a kind of method, apparatus, storage medium and electronic equipment for recommending cloud service provider.
In a first aspect, providing a kind of method for recommending cloud service provider, which comprises cloud service demand information is obtained,
The cloud service demand information includes the cloud service index of user's input；Obtain the cloud service provider information of cloud service provider to be recommended；
According to the cloud service index and the cloud service provider information from the cloud service provider to be recommended, target cloud service provider is determined；
Recommend the target cloud service provider.
Optionally, it is described according to the cloud service index and the cloud service provider information from the cloud service provider to be recommended
In, determine that target cloud service provider includes: to obtain cloud service provider recommended models；The cloud service index and the cloud service provider are believed
The input as the cloud service provider recommended models is ceased, the corresponding recommendation of each cloud service provider to be recommended is obtained；According to each
The corresponding recommendation of the cloud service provider to be recommended determines the target cloud service provider from the cloud service provider to be recommended.
Optionally, the cloud service index includes rigid index and flexible index；By the cloud service index and described
Input of the cloud service provider information as the cloud service provider recommended models each of obtains the corresponding recommendation of cloud service provider to be recommended
Before, the method also includes: obtain the cloud service label of each cloud service index；According to the rigid index and the cloud
Service labels determine alternative cloud service provider from the cloud service provider to be recommended；Described in being determined from the cloud service provider information
The corresponding alternative cloud service provider information of alternative cloud service provider；It is described using the cloud service index and the cloud service provider information as
The input of the cloud service provider recommended models, each of obtaining the corresponding recommendation of cloud service provider to be recommended includes: to take the cloud
Input of the index and the alternative cloud service provider information of being engaged in as the cloud service provider recommended models, obtains the alternative cloud service
The corresponding recommendation of quotient；It is described according to the corresponding recommendation of each cloud service provider to be recommended from the cloud service provider to be recommended
In, determine that the target cloud service provider includes: according to the corresponding recommendation of the alternative cloud service provider from the alternative cloud service
The target cloud service provider is determined in quotient.
Optionally, after the determining target cloud service provider, the method also includes: determine the target cloud service provider pair
The target cloud service provider information answered；According to the target cloud service provider information training cloud service provider recommended models, obtain more
Cloud service provider recommended models after new.
Second aspect provides a kind of device for recommending cloud service provider, and described device includes: the first acquisition module, for obtaining
Cloud service demand information is taken, the cloud service demand information includes the cloud service index of user's input；Second obtains module, is used for
Obtain the cloud service provider information of cloud service provider to be recommended；First determining module, for according to the cloud service index and the cloud
Service provider's information determines target cloud service provider from the cloud service provider to be recommended；Recommending module, for recommending the target cloud
Service provider.
Optionally, first determining module is for obtaining cloud service provider recommended models；By the cloud service index and institute
Input of the cloud service provider information as the cloud service provider recommended models is stated, the corresponding recommendation of each cloud service provider to be recommended is obtained
Degree；Described in from the cloud service provider to be recommended, being determined according to the corresponding recommendation of each cloud service provider to be recommended
Target cloud service provider.
Optionally, the cloud service index includes rigid index and flexible index；Described device further include: third obtains mould
Block, for obtaining the cloud service label of each cloud service index；Second determining module, for according to the rigid index and
The cloud service label determines alternative cloud service provider from the cloud service provider to be recommended；Third determining module is used for from described
The corresponding alternative cloud service provider information of the alternative cloud service provider is determined in cloud service provider information；First determining module is used
In using the cloud service index and the alternative cloud service provider information as the input of the cloud service provider recommended models, institute is obtained
State the corresponding recommendation of alternative cloud service provider；According to the corresponding recommendation of the alternative cloud service provider from the alternative cloud service provider
The middle determination target cloud service provider.
Optionally, described device further include: the 4th determining module, for determining the corresponding target of the target cloud service provider
Cloud service provider information；Model modification module, for recommending mould according to the target cloud service provider information training cloud service provider
Type obtains updated cloud service provider recommended models.
The third aspect provides a kind of computer readable storage medium, is stored thereon with computer program, and the program is processed
The step of disclosure first aspect the method is realized when device executes.
Fourth aspect provides a kind of electronic equipment, comprising: memory is stored thereon with computer program；Processor is used
In executing the computer program in the memory, the step of to realize disclosure first aspect the method.
Through the above technical solutions, obtaining cloud service demand information, the cloud service demand information includes what user inputted
Cloud service index；Obtain the cloud service provider information of cloud service provider to be recommended；According to the cloud service index and the cloud service provider
Information determines target cloud service provider from the cloud service provider to be recommended；Recommend the target cloud service provider, in this way, according to
The target cloud service provider that the cloud service demand information of family input is recommended, is more able to satisfy the practical business demand of user,
It also avoids user oneself and searches the complicated processes of the target cloud service provider, to improve user's selection target cloud service provider
Efficiency, and then improve the experience of user.
Other feature and advantage of the disclosure will the following detailed description will be given in the detailed implementation section.
Detailed description of the invention
Attached drawing is and to constitute part of specification for providing further understanding of the disclosure, with following tool
Body embodiment is used to explain the disclosure together, but does not constitute the limitation to the disclosure.In the accompanying drawings:
Fig. 1 is the flow chart of the method for the first recommendation cloud service provider shown according to an exemplary embodiment；
Fig. 2 is the flow chart of the method for second of recommendation cloud service provider shown according to an exemplary embodiment；
Fig. 3 is that shown according to an exemplary embodiment the third recommends the flow chart of the method for cloud service provider；
Fig. 4 is the block diagram of the device of the first recommendation cloud service provider shown according to an exemplary embodiment；
Fig. 5 is the block diagram of the device of second of recommendation cloud service provider shown according to an exemplary embodiment；
Fig. 6 is that shown according to an exemplary embodiment the third recommends the block diagram of the device of cloud service provider；
Fig. 7 is the structural block diagram of a kind of electronic equipment shown according to an exemplary embodiment.
Specific embodiment
It is described in detail below in conjunction with specific embodiment of the attached drawing to the disclosure.It should be understood that this place is retouched
The specific embodiment stated is only used for describing and explaining the disclosure, is not limited to the disclosure.
The disclosure provides a kind of method, apparatus, storage medium and electronic equipment for recommending cloud service provider, inputs industry in user
When the cloud service demand information of business system, available cloud service demand information of cloud service provider recommender system, wherein cloud clothes
Business demand information may include the cloud service index of user's input, then obtain the cloud service provider information of cloud service provider to be recommended,
According to the cloud service index and the cloud service provider information from the cloud service provider to be recommended, target cloud service provider is determined, and recommend
The target cloud service provider, in this way, according to the target cloud service provider that the cloud service demand information that user inputs is recommended, more
It is able to satisfy the practical business demand of user, user oneself is also avoided and searches the complicated processes of the target cloud service provider, to mention
The high efficiency of user's selection target cloud service provider, and then improve the experience of user.
The specific embodiment of the disclosure is described in detail with reference to the accompanying drawing.
Fig. 1 is a kind of flow chart of method for recommending cloud service provider shown according to an exemplary embodiment, such as Fig. 1 institute
Show, method includes the following steps:
S101, obtains cloud service demand information, which includes the cloud service index of user's input.
Wherein, which may include the achievement data for meeting the cloud service of subscriber service system actual demand,
For example, the cloud service index may include CPU number, memory size, disk size, read-write operation number (Input/ per second
Output Operations Per Second, IOPS), storage classification, the data such as Price Range.
In one possible implementation, user can be by cloud service provider from service door (such as website, cloud service
Quotient's application software etc.) the cloud service index is inputted, for example, the cloud can be inputted from the application list that service door provides at this
Service indication.
S102 obtains the cloud service provider information of cloud service provider to be recommended.
Wherein, which may include indicating the data of cloud service provider service quality, for example, cloud service provider is gone through
History SLA (Service-Level Agreement, service-level agreement) data (can use third party appraisal agency or monitoring
Tool acquires cloud service provider history SLA data), meanwhile, which can also include user according to cloud service
Actually use the user's evaluation historical data after situation is evaluated and user's purchase history data, personal preference history number
According to etc. related datas.
S103 determines target cloud according to the cloud service index and the cloud service provider information from the cloud service provider to be recommended
Service provider.
Wherein, which may include rigid index and flexible index, it is contemplated that the operation system of different user
It is also not identical to the actual demand of cloud service, for example, whether the service quality that most of user may more value cloud service provider is full
The actual demand of oneself operation system of foot, and whether the service price for further accounting for cloud service provider meets oneself cost and wants
Ask, at this point, user can by the cloud service index relevant to service quality (such as CPU number, IOPS data etc.) of input with
And the Price Range that cloud service provider need to meet is set as the rigid index that target cloud service provider must satisfy, by disk size, cloud
Other cloud service setup measures such as service provider's service ratings are the flexible index preferably met.
It should be noted that in one possible implementation, the cloud clothes that each needs is filled on application list
Have in business index rigid index and flexible index mark (for example, in the graphic interface from service door, can will be hard
Property index be labeled as " must satisfy " flexible index perhaps " essential " be labeled as to " preferably meeting " or " optional "), Yong Huke
To be rigid index or flexible index according to each single item cloud service index of the actual demand of oneself operation system setting input,
So that cloud service provider recommender system can (rigid index or flexibility refer to according to the Criterion Attribute of the cloud service index of user setting
Mark) quickly user is helped to find the target cloud service provider for meeting user demand.
In this step, it can be realized by any one mode in following two mode.
Mode one obtains cloud service provider recommended models；It is taken using the cloud service index and the cloud service provider information as the cloud
The input for quotient's recommended models of being engaged in each of obtains the corresponding recommendation of cloud service provider to be recommended；According to each cloud service to be recommended
The corresponding recommendation of quotient determines the target cloud service provider from the cloud service provider to be recommended.
In addition, improve to reduce the computation complexity of cloud service provider recommended models and recommend efficiency, it can be with employing mode two
Determine the target cloud service provider.
Mode two, the cloud service label for obtaining each cloud service index；According to the hardness index and the cloud service label,
Alternative cloud service provider is determined from cloud service provider to be recommended；Determine that the alternative cloud service provider is corresponding from the cloud service provider information
Alternative cloud service provider information；Obtain cloud service provider recommended models, using the cloud service index and the alternative cloud service provider information as
The input of the cloud service provider recommended models, the corresponding recommendation of the alternative cloud service provider obtained；According to the alternative cloud service provider pair
The recommendation answered determines the target cloud service provider from the alternative cloud service provider.
Wherein, which may include logistic regression (Logistic Regression, LR) model,
It should be noted that the cloud service provider recommended models can be pre- based on experience value when carrying out the recommendation of cloud service provider for the first time
If recommended models, when the recommendation of multiple cloud service provider has been carried out, the cloud service provider recommended models be according to reality
The target cloud service provider of recommendation carries out the recommended models obtained after feedback training.
In addition, the cloud service label may include that cloud service provider recommender system takes the cloud that user inputs according to preset rules
The feature tag of business index automatic marking, which also may include the spy that system manager rule of thumb marks manually
Label is levied, for example, the cloud service label may include general-purpose computations type, CPU intensive type, memory-intensive, big data type, high IO
It handles up type, GPU accelerating type etc..
In one possible implementation, for system in automatic marking feature tag, which may include root
The CPU memory size mark in cloud service index for inputting user according to the ratio of the total memory of CPU memory size Zhan of user's input
Note is general-purpose computations type or CPU intensive type, for example, when CPU memory size occupies the 1/4 of total memory, it can be defeated by user
The CPU memory size entered is labeled as general-purpose computations type, when CPU memory size occupies the 1/2 of total memory, user can be inputted
CPU memory size be labeled as CPU intensive type, in addition, the preset rules can also include according to user input IOPS data
Size cloud service index that user is inputted in IOPS data be labeled, for example, when the IOPS data of user's input are big
When 2000, the IOPS that user inputs can be labeled as high IO and handled up type, is merely illustrative herein, the disclosure does not make this
It limits.
It should be noted that cloud service provider to be recommended can be preset according to when carrying out label for labelling to cloud service index
Regular same rule, carries out the mark of feature tag in advance, in this way, according to the hardness index and the cloud service label, from
In cloud service provider to be recommended determine alternative cloud service provider when, can by the corresponding cloud service label of the hardness index with each wait push away
It recommends the cloud service provider label that cloud service provider marks in advance to be compared, and the cloud service provider to be recommended for meeting the hardness index is true
It is set to the alternative cloud service provider, the cloud service provider to be recommended for being unsatisfactory for the hardness index is eliminated, to reduces subsequent cloud
The computation complexity of service provider's recommended models, provides computational efficiency.
In addition, after obtaining the corresponding recommendation of the alternative cloud service provider, sequence that can be descending according to recommendation
The alternative cloud service provider is ranked up, in this way, according to the corresponding recommendation of the alternative cloud service provider from the alternative cloud service
When determining the target cloud service provider in quotient, facilitate user or system manager can be according to the ranking results, and combine user
The cloud service demand information of input determines the target cloud service provider.
S104 recommends the target cloud service provider.
In one possible implementation, after determining the target cloud service provider, cloud service provider recommender system can be certainly
It moves and opens the cloud service related service that the target cloud service provider provides for user.
It can be used as a kind of reference factor when recommendation to the evaluation of cloud service provider in view of the user of cloud service, but different
For user under different times or different application scene, the evaluation to cloud service and cloud service provider is dynamic change, therefore, it is necessary to
Cloud service provider recommended models can carry out self study, so as to continue to optimize the model parameter of cloud service provider recommended models, into
And the accuracy for improving model recommendation after determining target cloud service provider, can determine this in one possible implementation
The corresponding target cloud service provider information of target cloud service provider；Then according to target cloud service provider information training, the cloud service provider is pushed away
Model is recommended, updated cloud service provider recommended models are obtained, in this way, when getting the cloud service index that user re-enters,
The target cloud service provider for meeting the new business demand of user can be determined according to the updated cloud service provider recommended models, thus
Improve the accuracy that cloud service provider is recommended.
Using the above method, according to the target cloud service provider that the cloud service demand information that user inputs is recommended,
It is more able to satisfy the practical business demand of user, also avoids the complicated processes that user oneself searches the target cloud service provider, thus
The efficiency of user's selection target cloud service provider is improved, and then improves the experience of user.
Fig. 2 is a kind of flow chart of method for recommending cloud service provider shown according to an exemplary embodiment, such as Fig. 2 institute
Show, method includes the following steps:
S201, obtains cloud service demand information, which includes the cloud service index of user's input.
Wherein, which may include the achievement data for meeting the cloud service of subscriber service system actual demand,
For example, the cloud service index may include CPU number, memory size, disk size, read-write operation number per second (IOPS), deposit
Store up the data such as classification, Price Range.
In one possible implementation, user can be by cloud service provider from service door (such as website, cloud service
Quotient's application software etc.) the cloud service index is inputted, for example, the cloud can be inputted from the application list that service door provides at this
Service indication.
S202 obtains the cloud service provider information of cloud service provider to be recommended.
Wherein, which may include indicating the data of cloud service provider service quality, for example, cloud service provider is gone through
History SLA (service-level agreement) data (can use third party appraisal agency or monitoring tools acquire cloud service provider history SLA
Data), meanwhile, which can also include the use after user evaluates according to the actual use situation of cloud service
The related datas such as family evaluation history data and user's purchase history data, personal preference historical data.
S203 obtains cloud service provider recommended models.
Wherein, which may include Logic Regression Models.
It should be noted that the cloud service provider recommended models can be basis when carrying out the recommendation of cloud service provider for the first time
The preset recommended models of empirical value, when the recommendation of multiple cloud service provider has been carried out, which is
The recommended models obtained after feedback training are carried out according to the target cloud service provider of actual recommendation.
Specifically, the available following formula after being solved to the Logic Regression Models:
Wherein, X=(X1, X2 ..., Xk) indicates the input of the Logic Regression Models, and θ indicates the Logic Regression Models
Model parameter (regression coefficient that can also be referred to as model), Y are the output of the Logic Regression Models, it is generally the case that this is patrolled
The value for collecting the output Y of regression model can be 0 or 1, and P (Y=1 | X；θ) indicate that in the input of the Logic Regression Models be X, mould
Shape parameter be θ under conditions of, model export Y=1 probability, in the present embodiment, X be user input cloud service index with
And the cloud service provider information of each cloud service provider to be recommended, θ (wherein, θ=(θ 1, θ 2 ..., θ k)) can indicate each cloud service
Index and the corresponding weight parameter of the corresponding each cloud service provider information of a cloud service provider to be recommended, Y=1 can be indicated
" recommendation ", Y=0 can indicate " not recommending ".
S204 is obtained using the cloud service index and the cloud service provider information as the input of the cloud service provider recommended models
The corresponding recommendation of each cloud service provider to be recommended.
Specifically, after by the cloud service index and the cloud service provider information input cloud service provider recommended models, according to
The corresponding recommendation probability of the available each cloud service provider to be recommended of formula (1), since the numberical range of probability value is 0 to 1, this
When, for that in one possible implementation, the corresponding recommendation probability of each cloud service provider to be recommended can be multiplied convenient for calculating
With 100, the recommendation of cloud service provider to be recommended each of is then obtained between 0 to 100, it should be noted that, the recommendation
Degree also may include the corresponding recommendation probability of each cloud service provider to be recommended, at this point it is possible to the conversion without numerical value, the disclosure
This is not construed as limiting.
Illustratively, currently there are tri- cloud service providers to be recommended of A, B, C, by the cloud service index of user's input and cloud to be recommended
After the cloud service provider information input Logic Regression Models of service provider A, the recommendation probability for obtaining cloud service provider A to be recommended is 0.55,
After the cloud service index of user's input and the cloud service provider information input Logic Regression Models of cloud service provider B to be recommended, obtain
The recommendation probability of cloud service provider B to be recommended is 0.78, and the cloud of the cloud service index of user's input and cloud service provider C to be recommended is taken
Be engaged in quotient's information input Logic Regression Models after, obtain cloud service provider C to be recommended recommendation probability be 0.93, at this point it is possible to by A,
B, the corresponding recommendation probability of C tri- cloud service providers to be recommended is multiplied by 100, so as to obtain tri- clouds to be recommended of A, B, C
The recommendation of service provider is respectively 55,78 and 93, and above-mentioned example is merely illustrative, and the disclosure is not construed as limiting this.
S205 determines mesh according to the corresponding recommendation of each cloud service provider to be recommended from the cloud service provider to be recommended
Mark cloud service provider.
After obtaining the corresponding recommendation of each cloud service provider to be recommended, sequence that can be descending according to recommendation
The cloud service provider to be recommended is ranked up, in this way, to be recommended from this according to the corresponding recommendation of the cloud service provider to be recommended
When determining the target cloud service provider in cloud service provider, facilitate user or system manager can be according to the ranking results, and tie
The cloud service demand information for sharing family input determines the target cloud service provider.
Illustratively, continue to be illustrated by taking tri- cloud service providers to be recommended of A, B, C as an example, after executing S204, can obtain
Recommendation to tri- cloud service providers to be recommended of A, B, C is respectively 55,78 and 93, in this way, can according to recommendation by greatly to
Small sequence is ranked up the cloud service provider to be recommended, which is cloud service provider C to be recommended, cloud service to be recommended
Quotient B, cloud service provider A to be recommended, at this point, user or system manager can select recommendation highest according to the ranking results
Cloud service provider C to be recommended as the target cloud service provider, certainly, user or administrator can also be according to the cloud services of input
Demand information and ranking results selection are more able to satisfy the target cloud service provider of user's practical business demand, although for example, to
The recommendation of cloud service provider C is recommended to be higher than cloud service provider B to be recommended, but the service price of cloud service provider B to be recommended and user
The Price Range of input is closer, at this point, at this point, consider cost factor, user or system manager also can choose to
Recommend cloud service provider B as the target cloud service provider, is merely illustrative herein, the disclosure is not construed as limiting this.
S206 recommends the target cloud service provider.
In one possible implementation, after determining the target cloud service provider, cloud service provider recommender system can be certainly
It moves and opens the cloud service related service that the target cloud service provider provides for user.
It can be used as a kind of reference factor when recommendation to the evaluation of cloud service provider in view of the user of cloud service, but different
For user under different times or different application scene, the evaluation to cloud service and cloud service provider is dynamic change, therefore, it is necessary to
Cloud service provider recommended models can carry out self study, so as to continue to optimize the model parameter of cloud service provider recommended models, into
And improve the accuracy of model recommendation.
In one possible implementation, after determining target cloud service provider, the target cloud service provider pair can be determined
The target cloud service provider information answered；Then it according to the target cloud service provider information training cloud service provider recommended models, obtains more
Cloud service provider recommended models after new, in this way, when getting the cloud service index that user re-enters, can be according to update after
The cloud service provider recommended models determine and meet the target cloud service provider of the new business demand of user, pushed away to improve cloud service provider
The accuracy recommended.
It should be noted that the Logic Regression Models training process belongs to the training for having supervision, for purposes of illustration only, the model
Training data can be expressed as (S, T) and S=(S1, S2 ...), T=(T1, T2 ...), wherein S can indicate user
The cloud service index of input and the target cloud service provider information of target cloud service provider, T can indicate the target cloud service provider
Recommend probability (the as desired output of model), it, should after carrying out cloud service provider recommendation every time and obtaining the target cloud service provider
The available update of the training data of model, for example, when recommending for the first time and obtaining the target cloud service provider 1, the training number
According to for (S1, T1), wherein S1 is the cloud service index and the corresponding target cloud of target cloud service provider 1 of user's input for the first time
Service provider's information 1, T1 are the corresponding recommendation probability of target cloud service provider 1, are recommending for the second time and are obtaining the target cloud service
When quotient 2, which isWherein, S2 is second of cloud service index inputted of user and mesh
The corresponding target cloud service provider information 2 of cloud service provider 2 is marked, T2 is the corresponding recommendation probability of target cloud service provider 2, with such
It pushes away, the training data of the cloud service provider recommended models can be updated according to newest obtained target cloud service provider, and according to newest
Training data model is trained, the model parameter after being optimized, so that obtaining updated cloud service provider recommends mould
Type.
In one possible implementation, the cloud service provider recommended models can be instructed using gradient descent method
Practice, specific training step can refer to associated description in the prior art, and the disclosure does not repeat this.
Using the above method, according to the target cloud service provider that the cloud service demand information that user inputs is recommended,
It is more able to satisfy the practical business demand of user, also avoids the complicated processes that user oneself searches the target cloud service provider, thus
The efficiency of user's selection target cloud service provider is improved, and then improves the experience of user.
In addition, in the disclosure, for the computation complexity for reducing cloud service provider recommended models, improving and recommending efficiency, may be used also
To carry out the recommendation of cloud service provider using specific embodiment shown in Fig. 3.
Fig. 3 is a kind of flow chart of method for recommending cloud service provider shown according to an exemplary embodiment, such as Fig. 3 institute
Show, method includes the following steps:
S301, obtains cloud service demand information, which includes the cloud service index of user's input, the cloud
Service indication includes rigid index and flexible index.
Wherein, which may include the achievement data for meeting the cloud service of subscriber service system actual demand,
For example, the cloud service index may include CPU number, memory size, disk size, read-write operation number per second (IOPS), deposit
Store up classification, the data such as Price Range, in one possible implementation, user can be by cloud service provider from service door
(such as website, cloud service provider application software) inputs the cloud service index, for example, can be in the application provided from service door
The cloud service index is inputted on list.
Furthermore, it is contemplated that the operation system of different user is not also identical to the actual demand of cloud service, for example, most of use
Whether the service quality that family may more value cloud service provider meets the actual demand of oneself operation system, and further accounts for cloud clothes
Whether the service price of business quotient meets the cost requirement of oneself, at this point, user can be by the cloud relevant to service quality of input
The Price Range that service indication (such as CPU number, IOPS data etc.) and cloud service provider need to meet is set as target cloud service
Other cloud service setup measures such as disk size, cloud service provider service ratings are preferably full by the rigid index that quotient must satisfy
The flexible index of foot.
It should be noted that in one possible implementation, the cloud clothes that each needs is filled on application list
Have in business index rigid index and flexible index mark (for example, in the graphic interface from service door, can will be hard
Property index be labeled as " must satisfy " flexible index perhaps " essential " be labeled as to " preferably meeting " or " optional "), Yong Huke
To be rigid index or flexible index according to each single item cloud service index of the actual demand of oneself operation system setting input,
So that cloud service provider recommender system can (rigid index or flexibility refer to according to the Criterion Attribute of the cloud service index of user setting
Mark) quickly user is helped to find the target cloud service provider for meeting user demand.
S302 obtains the cloud service provider information and cloud service provider recommended models of cloud service provider to be recommended.
Wherein, which may include indicating the data of cloud service provider service quality, for example, cloud service provider is gone through
History SLA (service-level agreement) data (can use third party appraisal agency or monitoring tools acquire cloud service provider history SLA
Data), meanwhile, which can also include the use after user evaluates according to the actual use situation of cloud service
Related datas, the cloud service provider such as family evaluation history data and user's purchase history data, personal preference historical data are recommended
Model may include Logic Regression Models.
It should be noted that the cloud service provider recommended models can be basis when carrying out the recommendation of cloud service provider for the first time
The preset recommended models of empirical value, when the recommendation of multiple cloud service provider has been carried out, which is
The recommended models obtained after feedback training are carried out according to the target cloud service provider of actual recommendation.
Specifically, the available following formula after being solved to the Logic Regression Models:
Wherein, X=(X1, X2 ..., Xk) indicates the input of the Logic Regression Models, and θ indicates the Logic Regression Models
Model parameter (regression coefficient that can also be referred to as model), Y are the output of the Logic Regression Models, it is generally the case that this is patrolled
The value for collecting the output Y of regression model can be 0 or 1, and P (Y=1 | X；θ) indicate that in the input of the Logic Regression Models be X, mould
Shape parameter be θ under conditions of, model export Y=1 probability, in the present embodiment, X be user input cloud service index with
And the cloud service provider information of each alternative cloud service provider, θ (wherein, θ=(θ 1, θ 2 ..., θ k)) can indicate that each cloud service refers to
It is marked with and the corresponding weight parameter of the corresponding each cloud service provider information of an alternative cloud service provider, Y=1 can indicate " to push away
Recommend ", Y=0 can indicate " not recommending ".
S303 obtains the cloud service label of each cloud service index.
Wherein, which may include that cloud service provider recommender system takes the cloud that user inputs according to preset rules
The feature tag of business index automatic marking, which also may include the spy that system manager rule of thumb marks manually
Label is levied, for example, the cloud service label may include general-purpose computations type, CPU intensive type, memory-intensive, big data type, high IO
It handles up type, GPU accelerating type etc..
In one possible implementation, for system in automatic marking feature tag, which may include root
The CPU memory size mark in cloud service index for inputting user according to the ratio of the total memory of CPU memory size Zhan of user's input
Note is general-purpose computations type or CPU intensive type, for example, when CPU memory size occupies the 1/4 of total memory, it can be defeated by user
The CPU memory size entered is labeled as general-purpose computations type, when CPU memory size occupies the 1/2 of total memory, user can be inputted
CPU memory size be labeled as CPU intensive type, in addition, the preset rules can also include according to user input IOPS data
Size cloud service index that user is inputted in IOPS data be labeled, for example, when the IOPS data of user's input are big
When 2000, the IOPS that user inputs can be labeled as high IO and handled up type, is merely illustrative herein, the disclosure does not make this
It limits.
S304 determines alternative cloud service provider according to the hardness index and the cloud service label from cloud service provider to be recommended.
It should be noted that cloud service provider to be recommended can be preset according to when carrying out label for labelling to cloud service index
Regular same rule, carries out the mark of feature tag in advance, in this way, according to the hardness index and the cloud service label, from
In cloud service provider to be recommended determine alternative cloud service provider when, can by the corresponding cloud service label of the hardness index with each wait push away
It recommends the cloud service provider label that cloud service provider marks in advance to be compared, and the cloud service provider to be recommended for meeting the hardness index is true
It is set to the alternative cloud service provider, the cloud service provider to be recommended for being unsatisfactory for the hardness index is eliminated, to reduces subsequent cloud
The computation complexity of service recommendation model, provides computational efficiency.
S305 determines the corresponding alternative cloud service provider information of the alternative cloud service provider from the cloud service provider information.
S306, using the cloud service index and the alternative cloud service provider information as the input of the cloud service provider recommended models,
The corresponding recommendation of the alternative cloud service provider.
Specifically, after by the cloud service index and the alternative cloud service provider information input cloud service provider recommended models,
According to the corresponding recommendation probability of the available each alternative cloud service provider of formula (1), since the numberical range of probability value is 0 to 1,
At this point, in one possible implementation, the corresponding recommendation probability of each alternative cloud service provider can be multiplied for convenient for calculating
With 100, the recommendation of alternative cloud service provider each of is then obtained between 0 to 100, it should be noted that, the recommendation
It also may include the corresponding recommendation probability of each alternative cloud service provider, at this point it is possible to the conversion without numerical value, the disclosure is to this
It is not construed as limiting.
Illustratively, currently there are tri- alternative cloud service providers of D, E, F, the cloud service index and alternative cloud service that user is inputted
After the alternative cloud service provider information input Logic Regression Models of quotient D, the recommendation probability for obtaining alternative cloud service provider D is 0.87, will
After the cloud service index of user's input and the cloud service provider information input Logic Regression Models of alternative cloud service provider E, obtain alternative
The recommendation probability of cloud service provider E is 0.76, by the cloud service provider information of the cloud service index of user's input and alternative cloud service provider F
After input logic regression model, the recommendation probability for obtaining alternative cloud service provider F is 0.95, at this point it is possible to alternative by D, E, F tri-
The corresponding recommendation probability of cloud service provider is multiplied by 100, so as to obtain the recommendation point of D, E, F tri- alternative cloud service providers
Not Wei 87,76 and 95, above-mentioned example is merely illustrative, and the disclosure is not construed as limiting this.
S307 determines the target cloud service according to the corresponding recommendation of the alternative cloud service provider from the alternative cloud service provider
Quotient.
It, can be standby to this according to the descending sequence of recommendation after obtaining the corresponding recommendation of the alternative cloud service provider
Select cloud service provider to be ranked up, in this way, according to the corresponding recommendation of the alternative cloud service provider from the alternative cloud service provider really
When the fixed target cloud service provider, facilitate user or system manager can be according to the ranking results, and combine user's input
Cloud service demand information determines the target cloud service provider.
Illustratively, continue to be illustrated by taking D, E, F tri- alternative cloud service providers as an example, it is available after executing S306
D, the recommendation of E, F tri- alternative cloud service providers is respectively 87,76 and 95, in this way, can be descending according to recommendation
Sequence is ranked up the alternative cloud service provider, which is alternative cloud service provider F, alternative cloud service provider D, alternative cloud
Service provider E, at this point, user or system manager can select the highest alternative cloud service of recommendation according to the ranking results
Quotient F is as the target cloud service provider, and certainly, user or administrator can also be according to the cloud service demand informations of input and should
Ranking results select the target cloud service provider for being more able to satisfy user's practical business demand, although for example, alternative cloud service provider F's pushes away
Degree of recommending is higher than alternative cloud service provider D, but the Price Range that the service price of alternative cloud service provider D and user input is closer,
At this point, considering cost factor, user or system manager also can choose alternative cloud service provider D as the target cloud service
Quotient is merely illustrative herein, and the disclosure is not construed as limiting this.
S308 recommends the target cloud service provider.
In one possible implementation, after determining the target cloud service provider, cloud service provider recommender system can be certainly
It moves and opens the cloud service related service that the target cloud service provider provides for user.
It can be used as a kind of reference factor when recommendation to the evaluation of cloud service provider in view of the user of cloud service, but different
For user under different times or different application scene, the evaluation to cloud service and cloud service provider is dynamic change, therefore, it is necessary to
Cloud service provider recommended models can carry out self study, so as to continue to optimize the model parameter of cloud service provider recommended models, into
And the accuracy for improving model recommendation after determining target cloud service provider, can determine this in one possible implementation
The corresponding target cloud service provider information of target cloud service provider；Then according to target cloud service provider information training, the cloud service provider is pushed away
Model is recommended, updated cloud service provider recommended models are obtained, in this way, when getting the cloud service index that user re-enters,
The target cloud service provider for meeting the new business demand of user can be determined according to the updated cloud service provider recommended models, thus
Improve the accuracy that cloud service provider is recommended.
It should be noted that the Logic Regression Models training process belongs to the training for having supervision, for purposes of illustration only, the model
Training data can be expressed as (S, T) and S=(S1, S2 ...), T=(T1, T2 ...), wherein S can indicate user
The cloud service index of input and the target cloud service provider information of target cloud service provider, T can indicate the target cloud service provider
Recommend probability (the as desired output of model), it, should after carrying out cloud service provider recommendation every time and obtaining the target cloud service provider
The available update of the training data of model, for example, when recommending for the first time and obtaining the target cloud service provider 1, the training number
According to for (S1, T1), wherein S1 is the cloud service index and the corresponding target cloud of target cloud service provider 1 of user's input for the first time
Service provider's information 1, T1 are the corresponding recommendation probability of target cloud service provider 1, are recommending for the second time and are obtaining the target cloud service
When quotient 2, which isWherein, S2 is second of cloud service index inputted of user and mesh
The corresponding target cloud service provider information 2 of cloud service provider 2 is marked, T2 is the corresponding recommendation probability of target cloud service provider 2, with such
It pushes away, the training data of the cloud service provider recommended models can be updated according to newest obtained target cloud service provider, and according to newest
Training data model is trained, the model parameter after being optimized, so that obtaining updated cloud service provider recommends mould
Type.
In one possible implementation, the cloud service provider recommended models can be instructed using gradient descent method
Practice, specific training step can refer to associated description in the prior art, and the disclosure does not repeat this.
Using the above method, according to the target cloud service provider that the cloud service demand information that user inputs is recommended,
It is more able to satisfy the practical business demand of user, also avoids the complicated processes that user oneself searches the target cloud service provider, thus
The efficiency of user's selection target cloud service provider is improved, and then improves the experience of user.
Fig. 4 is a kind of block diagram of device for recommending cloud service provider shown according to an exemplary embodiment, as shown in figure 4,
The device includes:
First obtains module 401, and for obtaining cloud service demand information, which includes what user inputted
Cloud service index；
Second obtains module 402, for obtaining the cloud service provider information of cloud service provider to be recommended；
First determining module 403, for according to the cloud service index and the cloud service provider information from the cloud service to be recommended
Shang Zhong determines target cloud service provider；
Recommending module 404, for recommending the target cloud service provider.
Optionally, first determining module 403 is for obtaining cloud service provider recommended models；By the cloud service index and the cloud
Input of service provider's information as the cloud service provider recommended models obtains the corresponding recommendation of each cloud service provider to be recommended；With
In from the cloud service provider to be recommended, determining the target cloud service according to the corresponding recommendation of each cloud service provider to be recommended
Quotient.
Optionally, Fig. 5 is the block diagram for implementing a kind of device of the recommendation cloud service provider exemplified according to Fig.4, wherein
The cloud service index may include rigid index and flexible index；As shown in figure 5, the device further include:
Third obtains module 405, for obtaining the cloud service label of each cloud service index；
Second determining module 406 is used for according to the hardness index and the cloud service label, from the cloud service provider to be recommended
Determine alternative cloud service provider；
Third determining module 407, for determining the corresponding alternative cloud of the alternative cloud service provider from the cloud service provider information
Service provider's information；
First determining module 403, for using the cloud service index and the alternative cloud service provider information as the cloud service
The input of quotient's recommended models obtains the corresponding recommendation of the alternative cloud service provider；According to the corresponding recommendation of the alternative cloud service provider
Degree determines the target cloud service provider from the alternative cloud service provider.
Optionally, Fig. 6 is the block diagram for implementing a kind of device of the recommendation cloud service provider exemplified according to Fig.4, such as Fig. 6
It is shown, the device further include:
4th determining module 408, for determining the corresponding target cloud service provider information of the target cloud service provider；
Model modification module 409, for obtaining according to the target cloud service provider information training cloud service provider recommended models
Updated cloud service provider recommended models.
About the device in above-described embodiment, wherein modules execute the concrete mode of operation in related this method
Embodiment in be described in detail, no detailed explanation will be given here.
Using above-mentioned apparatus, according to the target cloud service provider that the cloud service demand information that user inputs is recommended,
It is more able to satisfy the practical business demand of user, also avoids the complicated processes that user oneself searches the target cloud service provider, thus
The efficiency of user's selection target cloud service provider is improved, and then improves the experience of user.
Fig. 7 is the block diagram of a kind of electronic equipment 700 shown according to an exemplary embodiment.As shown in fig. 7, the electronics is set
Standby 700 may include: processor 701, memory 702.The electronic equipment 700 can also include multimedia component 703, input/
Export one or more of (I/O) interface 704 and communication component 705.
Wherein, processor 701 is used to control the integrated operation of the electronic equipment 700, to complete above-mentioned recommendation cloud service
All or part of the steps in the method for quotient.Memory 702 is for storing various types of data to support in the electronic equipment
700 operation, these data for example may include any application or method for operating on the electronic equipment 700
Instruction and the relevant data of application program, such as contact data, the message of transmitting-receiving, picture, audio, video etc..This is deposited
Reservoir 702 can realize by any kind of volatibility or non-volatile memory device or their combination, for example, it is static with
Machine accesses memory (Static Random Access Memory, abbreviation SRAM), electrically erasable programmable read-only memory
(Electrically Erasable Programmable Read-Only Memory, abbreviation EEPROM), erasable programmable
Read-only memory (Erasable Programmable Read-Only Memory, abbreviation EPROM), programmable read only memory
(Programmable Read-Only Memory, abbreviation PROM), and read-only memory (Read-Only Memory, referred to as
ROM), magnetic memory, flash memory, disk or CD.Multimedia component 703 may include screen and audio component.Wherein
Screen for example can be touch screen, and audio component is used for output and/or input audio signal.For example, audio component may include
One microphone, microphone is for receiving external audio signal.The received audio signal can be further stored in storage
Device 702 is sent by communication component 705.Audio component further includes at least one loudspeaker, is used for output audio signal.I/O
Interface 704 provides interface between processor 701 and other interface modules, other above-mentioned interface modules can be keyboard, mouse,
Button etc..These buttons can be virtual push button or entity button.Communication component 705 is for the electronic equipment 700 and other
Wired or wireless communication is carried out between equipment.Wireless communication, such as Wi-Fi, bluetooth, near-field communication (Near Field
Communication, abbreviation NFC), 2G, 3G, 4G, NB-IOT, eMTC or other 5G etc. or they one or more of
Combination, it is not limited here.Therefore the corresponding communication component 707 may include: Wi-Fi module, bluetooth module, NFC mould
Block etc..
In one exemplary embodiment, electronic equipment 700 can be by one or more application specific integrated circuit
(Application Specific Integrated Circuit, abbreviation ASIC), digital signal processor (Digital
Signal Processor, abbreviation DSP), digital signal processing appts (Digital Signal Processing Device,
Abbreviation DSPD), programmable logic device (Programmable Logic Device, abbreviation PLD), field programmable gate array
(Field Programmable Gate Array, abbreviation FPGA), controller, microcontroller, microprocessor or other electronics member
Part realization, the method for executing above-mentioned recommendation cloud service provider.
In a further exemplary embodiment, a kind of computer readable storage medium including program instruction is additionally provided, it should
The step of method of above-mentioned recommendation cloud service provider is realized when program instruction is executed by processor.For example, this computer-readable is deposited
Storage media can be the above-mentioned memory 702 including program instruction, and above procedure instruction can be by the processor of electronic equipment 700
701 methods executed to complete above-mentioned recommendation cloud service provider.
The preferred embodiment of the disclosure is described in detail in conjunction with attached drawing above, still, the disclosure is not limited to above-mentioned reality
The detail in mode is applied, in the range of the technology design of the disclosure, a variety of letters can be carried out to the technical solution of the disclosure
Monotropic type, these simple variants belong to the protection scope of the disclosure.
It is further to note that specific technical features described in the above specific embodiments, in not lance
In the case where shield, can be combined in any appropriate way, in order to avoid unnecessary repetition, the disclosure to it is various can
No further explanation will be given for the combination of energy.
In addition, any combination can also be carried out between a variety of different embodiments of the disclosure, as long as it is without prejudice to originally
Disclosed thought equally should be considered as disclosure disclosure of that.
Claims (10)
1. a kind of method for recommending cloud service provider, which is characterized in that the described method includes:
Cloud service demand information is obtained, the cloud service demand information includes the cloud service index of user's input；
Obtain the cloud service provider information of cloud service provider to be recommended；
According to the cloud service index and the cloud service provider information from the cloud service provider to be recommended, target cloud service is determined
Quotient；
Recommend the target cloud service provider.
2. the method according to claim 1, wherein described according to the cloud service index and the cloud service provider
Information determines that target cloud service provider includes: from the cloud service provider to be recommended
Obtain cloud service provider recommended models；
Using the cloud service index and the cloud service provider information as the input of the cloud service provider recommended models, obtain each
The corresponding recommendation of cloud service provider to be recommended；
According to the corresponding recommendation of each cloud service provider to be recommended from the cloud service provider to be recommended, the target is determined
Cloud service provider.
3. according to the method described in claim 2, it is characterized in that, the cloud service index includes that rigid index and flexibility refer to
Mark；Using the cloud service index and the cloud service provider information as the input of the cloud service provider recommended models, what is obtained is every
Before the corresponding recommendation of a cloud service provider to be recommended, the method also includes:
Obtain the cloud service label of each cloud service index；
According to the rigid index and the cloud service label, alternative cloud service provider is determined from the cloud service provider to be recommended；
The corresponding alternative cloud service provider information of the alternative cloud service provider is determined from the cloud service provider information；
It is described using the cloud service index and the cloud service provider information as the input of the cloud service provider recommended models, obtain
The corresponding recommendation of each cloud service provider to be recommended includes:
Using the cloud service index and the alternative cloud service provider information as the input of the cloud service provider recommended models, obtain
The corresponding recommendation of the alternative cloud service provider；
It is described according to the corresponding recommendation of each cloud service provider to be recommended from the cloud service provider to be recommended, determine described in
Target cloud service provider includes:
The target cloud service provider is determined from the alternative cloud service provider according to the corresponding recommendation of the alternative cloud service provider.
4. according to the method in claim 2 or 3, which is characterized in that after the determining target cloud service provider, the method
Further include:
Determine the corresponding target cloud service provider information of the target cloud service provider；
According to the target cloud service provider information training cloud service provider recommended models, obtains updated cloud service provider and recommend
Model.
5. a kind of device for recommending cloud service provider, which is characterized in that described device includes:
First obtains module, and for obtaining cloud service demand information, the cloud service demand information includes the cloud clothes of user's input
Business index；
Second obtains module, for obtaining the cloud service provider information of cloud service provider to be recommended；
First determining module, for according to the cloud service index and the cloud service provider information from the cloud service provider to be recommended
In, determine target cloud service provider；
Recommending module, for recommending the target cloud service provider.
6. device according to claim 5, which is characterized in that first determining module is for obtaining cloud service provider recommendation
Model；Using the cloud service index and the cloud service provider information as the input of the cloud service provider recommended models, obtain every
The corresponding recommendation of a cloud service provider to be recommended；For according to the corresponding recommendation of each cloud service provider to be recommended from described
In cloud service provider to be recommended, the target cloud service provider is determined.
7. device according to claim 6, which is characterized in that the cloud service index includes that rigid index and flexibility refer to
Mark；Described device further include:
Third obtains module, for obtaining the cloud service label of each cloud service index；
Second determining module is used for according to the rigid index and the cloud service label, from the cloud service provider to be recommended
Determine alternative cloud service provider；
Third determining module, for determining the corresponding alternative cloud service of the alternative cloud service provider from the cloud service provider information
Quotient's information；
First determining module, for using the cloud service index and the alternative cloud service provider information as the cloud service
The input of quotient's recommended models obtains the corresponding recommendation of the alternative cloud service provider；It is corresponding according to the alternative cloud service provider
Recommendation determines the target cloud service provider from the alternative cloud service provider.
8. device according to claim 6 or 7, which is characterized in that described device further include:
4th determining module, for determining the corresponding target cloud service provider information of the target cloud service provider；
Model modification module, for obtaining more according to the target cloud service provider information training cloud service provider recommended models
Cloud service provider recommended models after new.
9. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is held by processor
The step of any one of claim 1-4 the method is realized when row.
10. a kind of electronic equipment characterized by comprising
Memory is stored thereon with computer program；
Processor, for executing the computer program in the memory, to realize described in any one of claim 1-4
The step of method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811534355.3A CN109658187A (en) | 2018-12-14 | 2018-12-14 | Recommend method, apparatus, storage medium and the electronic equipment of cloud service provider |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811534355.3A CN109658187A (en) | 2018-12-14 | 2018-12-14 | Recommend method, apparatus, storage medium and the electronic equipment of cloud service provider |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109658187A true CN109658187A (en) | 2019-04-19 |
Family
ID=66114152
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811534355.3A Pending CN109658187A (en) | 2018-12-14 | 2018-12-14 | Recommend method, apparatus, storage medium and the electronic equipment of cloud service provider |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109658187A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110719325A (en) * | 2019-09-30 | 2020-01-21 | 恩亿科(北京)数据科技有限公司 | Method and device for responding to user request |
| CN115438270A (en) * | 2022-10-26 | 2022-12-06 | 深圳市信润富联数字科技有限公司 | Intelligent equipment information recommendation method, device, equipment and storage medium |
| WO2023226963A1 (en) * | 2022-05-27 | 2023-11-30 | 华为技术有限公司 | Cloud resource recommendation method and related device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102523247A (en) * | 2011-11-24 | 2012-06-27 | 合肥工业大学 | Cloud service recommendation method and device based on multi-attribute matching |
| CN106204087A (en) * | 2015-05-06 | 2016-12-07 | 北京派择网络科技有限公司 | For the method and apparatus selecting advertising media |
| CN107491992A (en) * | 2017-08-25 | 2017-12-19 | 哈尔滨工业大学（威海） | A kind of intelligent Service proposed algorithm based on cloud computing |
-
2018
- 2018-12-14 CN CN201811534355.3A patent/CN109658187A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102523247A (en) * | 2011-11-24 | 2012-06-27 | 合肥工业大学 | Cloud service recommendation method and device based on multi-attribute matching |
| CN106204087A (en) * | 2015-05-06 | 2016-12-07 | 北京派择网络科技有限公司 | For the method and apparatus selecting advertising media |
| CN107491992A (en) * | 2017-08-25 | 2017-12-19 | 哈尔滨工业大学（威海） | A kind of intelligent Service proposed algorithm based on cloud computing |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110719325A (en) * | 2019-09-30 | 2020-01-21 | 恩亿科(北京)数据科技有限公司 | Method and device for responding to user request |
| WO2023226963A1 (en) * | 2022-05-27 | 2023-11-30 | 华为技术有限公司 | Cloud resource recommendation method and related device |
| CN115438270A (en) * | 2022-10-26 | 2022-12-06 | 深圳市信润富联数字科技有限公司 | Intelligent equipment information recommendation method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20200258006A1 (en) | Prediction method, terminal, and server | |
| US10474957B2 (en) | Method and apparatus for forecasting characteristic information change | |
| Ying et al. | Bi-objective reentrant hybrid flowshop scheduling: an iterated Pareto greedy algorithm | |
| KR102125119B1 (en) | Data handling method and device | |
| US11748452B2 (en) | Method for data processing by performing different non-linear combination processing | |
| CN109658187A (en) | Recommend method, apparatus, storage medium and the electronic equipment of cloud service provider | |
| CN110162292A (en) | Voice broadcast method and device | |
| JPWO2010010654A1 (en) | Usage estimation device | |
| CN109274987A (en) | A kind of video collection sort method, server and readable storage medium storing program for executing | |
| CN111078997B (en) | Information recommendation method and device | |
| CN110866625A (en) | Promotion index information generation method and device | |
| Wang et al. | Province-level estimation of waste mobile phones in China and location planning of recycling centers | |
| CN110456921A (en) | Predict the method and device of user's keyboard operation behavior | |
| US10474688B2 (en) | System and method to recommend a bundle of items based on item/user tagging and co-install graph | |
| CN111522840B (en) | Label configuration method, device, equipment and computer readable storage medium | |
| CN113077321A (en) | Article recommendation method and device, electronic equipment and storage medium | |
| Byrd et al. | An active-set algorithm for nonlinear programming using parametric linear programming | |
| WO2021042541A1 (en) | Shopping guide method and apparatus in new retail model, device and storage medium | |
| CN116485391A (en) | Payment recommendation processing method and device | |
| CN110717095A (en) | Service item pushing method and device | |
| CN109785037A (en) | Resource trusteeship service method, electronic device and computer readable storage medium | |
| JP2012014441A (en) | Server for recommending application to user and method | |
| CN111612548B (en) | Information acquisition method, information acquisition device, computer equipment and readable storage medium | |
| CN113760550A (en) | Resource allocation method and resource allocation device | |
| CN112560938A (en) | Model training method and device and computer 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: 20190419 |