CN115392592A - Storage product parameter configuration recommendation method, device, equipment and medium - Google Patents
Storage product parameter configuration recommendation method, device, equipment and medium Download PDFInfo
- Publication number
- CN115392592A CN115392592A CN202211306930.0A CN202211306930A CN115392592A CN 115392592 A CN115392592 A CN 115392592A CN 202211306930 A CN202211306930 A CN 202211306930A CN 115392592 A CN115392592 A CN 115392592A
- Authority
- CN
- China
- Prior art keywords
- product
- index
- performance
- configuration value
- performance 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.)
- Granted
Links
Images
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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Educational Administration (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application discloses a method, a device, equipment and a medium for recommending storage product parameter configuration, which are applied to the technical field of storage product configuration and comprise the following steps: acquiring all index parameters of a stored product and a configuration value set of each index parameter; acquiring full performance data of the storage product based on the configuration value sets of all index parameters; the total performance data comprises all configuration value combinations corresponding to all the index parameters and product performance values corresponding to each configuration value combination; determining association rules of index parameter configuration value combinations and product performance values based on the full-scale performance data; the index parameter configuration value combination comprises configuration values of a plurality of index parameters in all the index parameters; and when the product performance value required by the user is obtained, outputting a recommended index parameter configuration value combination corresponding to the product performance value based on the association rule. The influence of subjective factors can be avoided, and the reliability of recommending the stored product parameter configuration is improved.
Description
Technical Field
The present application relates to the field of storage product configuration technologies, and in particular, to a method, an apparatus, a device, and a medium for recommending storage product parameter configuration.
Background
In the context of current big data, more and more manufacturers provide various tools for system performance evaluation, performance prediction and the like, and the tools are processes from parameter configuration to performance prediction. With the performance evaluation system, when a front-line engineer communicates with a client, the engineer can evaluate performance data under different configurations for the engineer and the client to refer to according to user configuration requirements, but in some cases, the engineer only needs product performance data under the condition that the client does not know specific parameter configuration and parameter weight influence, so the engineer usually carries out product parameter configuration recommendation to the client according to self experience and the output of a prediction tool.
Disclosure of Invention
In view of this, an object of the present application is to provide a method, an apparatus, a device and a medium for recommending storage product parameter configuration, which can avoid the influence of subjective factors, thereby improving the reliability of recommending storage product parameter configuration. The specific scheme is as follows:
in a first aspect, the present application discloses a method for recommending storage product parameter configuration, comprising:
acquiring all index parameters of a stored product and a configuration value set of each index parameter;
acquiring the full performance data of the storage product based on the configuration value set of all the index parameters; the full performance data comprises all configuration value combinations corresponding to all index parameters and product performance values corresponding to each configuration value combination;
determining association rules of index parameter configuration value combinations and product performance values based on the full-scale performance data; the index parameter configuration value combination comprises configuration values of a plurality of index parameters in all the index parameters;
and when the product performance value required by the user is obtained, outputting a recommended index parameter configuration value combination corresponding to the product performance value based on the association rule.
Optionally, the method further includes:
acquiring a performance prediction model;
correspondingly, the acquiring the full performance data of the storage product based on the configuration value set of all the index parameters includes:
traversing the configuration value sets of all the index parameters to obtain all configuration value combinations corresponding to all the index parameters;
and acquiring the full performance data of the storage product by using the performance prediction model and based on all the configuration value combinations.
Optionally, the obtaining a performance prediction model includes:
acquiring basic performance data; the basic performance data comprises common configuration value combinations of all the index parameters and product performance values obtained by performing performance tests on the storage products by utilizing each common configuration value combination;
and training the basic performance data based on a preset classifier to obtain the performance prediction evaluation model.
Optionally, the obtaining of the full performance data of the storage product based on the all configuration value combinations by using the performance prediction model includes:
determining an unused configuration value combination from all the configuration value combinations;
predicting product performance values corresponding to the non-use configuration value combinations by using the performance prediction model;
and determining the full performance data of the storage product based on the basic performance data and the product performance value corresponding to the unusual configuration value combination.
Optionally, the method further includes:
and constructing a classifier based on a particle swarm algorithm to obtain the preset classifier.
Optionally, the method further includes:
and when a change event of the basic performance data is monitored, updating the full-scale performance data based on the change event.
Optionally, the method further includes:
determining key index parameters from all the index parameters;
correspondingly, the index parameter configuration value combination comprises the configuration value of the key index parameter.
Optionally, the determining, based on the full performance data, an association rule between an index parameter configuration value combination and a product performance value includes:
and running a preset association rule algorithm based on the full performance data, and starting iteration by using a frequent item set consisting of the key index parameters to obtain an association rule of the index parameter configuration value combination and the product performance value.
Optionally, the determining key index parameters from all the index parameters includes:
acquiring the parameter weight corresponding to each index parameter in all the index parameters;
and determining the index parameters with the parameter weight larger than a preset weight threshold value as key index parameters.
Optionally, the obtaining the parameter weight corresponding to each index parameter in all the index parameters includes:
acquiring basic performance data; the basic performance data comprises common configuration value combinations of all the index parameters and product performance values obtained by performing performance tests on the storage products by using each common configuration value combination;
and training the basic performance data based on a preset classifier to obtain the parameter weight corresponding to each index parameter.
Optionally, before determining the association rule between the index parameter configuration value combination and the product performance value based on the full performance data, the method further includes:
and carrying out segmentation processing on the product performance values in the full-scale performance data so as to process the product performance values into preset values corresponding to the corresponding data segments.
Optionally, the determining of the association rule between the index parameter configuration value combination and the product performance value based on the full performance data includes:
determining association rules of index parameter configuration value combinations and product performance values under different confidence degrees based on the full performance data;
correspondingly, outputting a recommended index parameter configuration value combination corresponding to the product performance value based on the association rule includes:
and acquiring the confidence required by the user, and outputting the recommended index parameter configuration value combination corresponding to the product performance value under the confidence based on the association rule.
In a second aspect, the present application discloses a stored product parameter configuration recommendation device, comprising:
the parameter and value set acquisition module is used for acquiring all index parameters of the stored product and a configuration value set of each index parameter;
a full performance data acquisition module, configured to acquire full performance data of the storage product based on the configuration value sets of all the index parameters; the full performance data comprises all configuration value combinations corresponding to all index parameters and product performance values corresponding to each configuration value combination;
the association rule determining module is used for determining association rules of index parameter configuration value combinations and product performance values based on the full-scale performance data; the index parameter configuration value combination comprises configuration values of a plurality of index parameters in all the index parameters;
and the parameter configuration recommending module is used for outputting a recommended index parameter configuration value combination corresponding to the product performance value based on the association rule when the product performance value required by the user is obtained.
In a third aspect, the present application discloses an electronic device comprising a memory and a processor, wherein:
the memory is used for storing a computer program;
the processor is configured to execute the computer program to implement the aforementioned recommendation method for parameter configuration of storage products.
In a fourth aspect, the present application discloses a computer readable storage medium for storing a computer program, wherein the computer program, when executed by a processor, implements the aforementioned method for recommending storage product parameter configuration.
As can be seen, the method includes the steps of firstly obtaining all index parameters of a storage product and a configuration value set of each index parameter, and then obtaining full performance data of the storage product based on the configuration value sets of all index parameters; the total performance data comprises all configuration value combinations corresponding to all index parameters and product performance values corresponding to each configuration value combination, association rules of the index parameter configuration value combinations and the product performance values are determined based on the total performance data, the index parameter configuration value combinations comprise configuration values of a plurality of index parameters in all the index parameters, and when the product performance values required by users are obtained, recommended index parameter configuration value combinations corresponding to the product performance values are output based on the association rules. That is, according to the method and the device, the full performance data of the storage product is obtained based on the configuration value set of all the index parameters of the storage product, association rules of the parameter configuration value combination and the product performance value are mined based on the full performance data, and when the product performance value required by a user is obtained, the corresponding recommended index parameter configuration value combination is output based on the association rules, so that the influence of subjective factors can be avoided, and the reliability of parameter configuration recommendation of the storage product is improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the embodiments or the prior art descriptions will be briefly described below, it is obvious that the drawings in the following description are only the embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a flowchart of a recommendation method for storing product parameter configuration disclosed in an embodiment of the present application;
FIG. 2 is a flowchart of a specific storage product parameter configuration recommendation method disclosed in an embodiment of the present application;
FIG. 3 is a schematic structural diagram of a device for recommending storage product parameter configuration according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of an electronic device disclosed in an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
At present, when a front-line engineer communicates with a client, the engineer can evaluate performance data under different configurations for the engineer and the client to refer to, but under some conditions, the client only requires product performance data under the condition that the client does not know specific parameter configuration and parameter weight influence, so that the engineer often carries out product parameter configuration recommendation to the client according to own experience and the output of a prediction tool, the recommendation mode has a large component in subjectivity, certain theoretical basis is not provided, uncertainty is easily increased, and the parameter configuration which is easy to recommend is not the optimal configuration. Therefore, the stored product parameter configuration recommendation scheme is provided, the influence of subjective factors can be avoided, and the reliability of stored product parameter configuration recommendation is improved.
Referring to fig. 1, the embodiment of the present application discloses a method for recommending storage product parameter configuration, including:
step S11: and acquiring all index parameters of the stored product and a configuration value set of each index parameter.
All index parameters of the storage product comprise hard disk types, hard disk capacities and the like, each index parameter has a corresponding configuration value set, for example, the configuration value set of the hard disk types can be (solid state disk, mechanical hard disk) \8230, the configuration value set of the hard disk capacities can be (500G, 1T \8230).
Step S12: acquiring the full performance data of the storage product based on the configuration value sets of all the index parameters; and the full performance data comprises all configuration value combinations corresponding to all index parameters and product performance values corresponding to each configuration value combination.
In one embodiment, a performance prediction model may be obtained, and the specific steps include:
step 00: acquiring basic performance data; the basic performance data comprises the common configuration value combinations of all the index parameters and product performance values obtained by performing performance tests on the storage products by using each common configuration value combination.
Step 01: and training the basic performance data based on a preset classifier to obtain the performance prediction evaluation model.
In an embodiment, a classifier may be constructed based on a particle swarm algorithm, so as to obtain the preset classifier.
In addition, the configuration value set of all the index parameters can be traversed to obtain all configuration value combinations corresponding to all the index parameters; and acquiring the full performance data of the storage product by using the performance prediction model and based on all the configuration value combinations. All configuration value combinations obtained through traversal can be stored in a matrix. Specifically, the enumerated value set (i.e., the configured value set) of each index parameter may be identified and set, a loop iteration is performed starting with the current index parameter, the subsequent index parameters are sequentially iterated, and all the configured value combinations of the current iteration are output.
Further, the embodiment of the present application may determine an unused configuration value combination from all the configuration value combinations; predicting product performance values corresponding to the non-use configuration value combinations by using the performance prediction model; and determining the total performance data of the stored product based on the basic performance data and the product performance value corresponding to the unusual configuration value combination. That is, if the product performance value is included in the basic performance data, the product performance value in the basic performance data is used, and if the product performance value is not included in the basic performance data, the model prediction is used.
For example, all the index parameters include parameters a, B, and C, the configuration value set of a is { a1, a2, and a3}, the configuration value set of B is { B1, B2, and B3}, and the configuration value set of C is { C1, C2, and C3}, so as to obtain a total parameter value combination, where the common configuration value combinations include: { a1, b1, c1}, { a1, b1, c2}, etc., { a3, b3, c3}, etc., are combined with the extraordinary arrangement values, and for { a3, b3, c3}, the corresponding product performance values are predicted by using the performance prediction model.
In one embodiment, when a change event is monitored for the base performance data, the full-scale performance data is updated based on the change event. For example, an engineer finds that there is a deviation in a performance value of a common configuration value combination in the basic performance data, and may modify the performance value to trigger a change event of the basic performance data. In another embodiment, the full-scale performance data may also be manually updated. Further, local update may be performed, or all updates may be performed by one key.
Step S13: determining association rules of index parameter configuration value combinations and product performance values based on the full-scale performance data; the index parameter configuration value combination comprises configuration values of a plurality of index parameters in all the index parameters.
In one embodiment, a key index parameter may be determined from all the index parameters; correspondingly, the index parameter configuration value combination comprises the configuration value of the key index parameter. Thus, the recommended index parameter configuration value combination also contains the configuration value of the key index parameter. The determining of the key index parameter from all the index parameters may specifically include the following steps:
step 10: acquiring the parameter weight corresponding to each index parameter in all the index parameters;
in one embodiment, base performance data may be obtained; the basic performance data comprises common configuration value combinations of all the index parameters and product performance values obtained by performing performance tests on the storage products by utilizing each common configuration value combination; and training the basic performance data based on a preset classifier to obtain the parameter weight corresponding to each index parameter. That is, in the embodiment of the present application, the basic performance data may be trained based on a preset classifier, so as to obtain a performance prediction model and a parameter weight corresponding to each index parameter.
Step 11: and determining the index parameters with the parameter weight larger than the preset weight threshold value as key index parameters.
Further, in the embodiment of the present application, a preset association rule algorithm may be run based on the full performance data, and iteration is started with a frequent item set composed of the key index parameters, so as to obtain an association rule between the index parameter configuration value combination and the product performance value. In one embodiment, the predetermined association rule algorithm is Apriori algorithm.
Step S14: and when the product performance value required by the user is obtained, outputting a recommended index parameter configuration value combination corresponding to the product performance value based on the association rule.
In an implementation manner, in the embodiment of the present application, association rules of index parameter configuration value combinations and product performance values under different confidence levels may be determined based on the full performance data;
further, the embodiment of the application can obtain the confidence required by the user, and output the recommended index parameter configuration value combination corresponding to the product performance value under the confidence based on the association rule.
In addition, in the embodiment of the present application, before determining the association rule between the index parameter configuration value combination and the product performance value based on the full-scale performance data, the product performance value in the full-scale performance data may be processed in a segmented manner, so as to process the product performance value into the preset value corresponding to the corresponding data segment. For example, the performance value is 10001, the corresponding data segment is 10000 to 10999, and the preset value is 10k. Correspondingly, in the embodiment of the application, when the product performance value required by the user is obtained, the product performance value is firstly subjected to segmentation processing to be processed into the preset value corresponding to the corresponding data segment, and then the recommended index parameter configuration value combination corresponding to the preset value is output based on the association rule.
As can be seen, in the embodiment of the present application, all the index parameters of the storage product and the configuration value set of each index parameter are obtained first, and then the full-scale performance data of the storage product is obtained based on the configuration value sets of all the index parameters; the full performance data comprises all configuration value combinations corresponding to all index parameters and product performance values corresponding to each configuration value combination, association rules of the index parameter configuration value combinations and the product performance values are determined based on the full performance data, the index parameter configuration value combinations comprise configuration values of a plurality of index parameters in all the index parameters, and when a product performance value required by a user is obtained, recommended index parameter configuration value combinations corresponding to the product performance value are output based on the association rules. That is, in the embodiment of the present application, the full-scale performance data of the storage product is obtained based on the configuration value set of all the index parameters of the storage product, the association rule between the parameter configuration value combination and the product performance value is mined based on the full-scale performance data, and when the product performance value required by the user is obtained, the corresponding recommended index parameter configuration value combination is output based on the association rule, so that the influence of the subjective factor can be avoided, and the reliability of the parameter configuration recommendation of the storage product is improved.
For example, referring to fig. 2, fig. 2 is a flowchart of a specific method for recommending storage product parameter configuration disclosed in an embodiment of the present application. The method mainly comprises the following steps:
step one, acquiring a performance prediction model and parameter weight of an index parameter: 1. inputting: training sample data, namely acquired basic performance data; 2. iterative optimization: training sample data by using a classifier; 3. and (3) outputting: the performance prediction model and the parameter weight corresponding to the index parameter; the main idea of the application of the algorithm is as follows: the index parameter comprises a plurality of variables (each variable is a configuration value) so as toV i The ith variable representing the index parameter, namely the speed of the particles, N is the number of the variables, t is the current iteration times, omega is the inertia weight,V i (t + 1) is the position of the ith variable of the indicator parameter in the t +1 th iteration, and rand () represents obedience to uniform distribution [0,1 ]]Random number in between，C 1 And C 2 Sequentially represents an individual learning factor and a social learning factor,p i (t) the individual optimum value searched for the ith particle so far, g the global optimum value searched for all particles so far by iteration,x i (t) is the position of the ith particle in the tth iteration, and iteration and updating are carried out through the following formula:
generating a full index set, namely all configuration value combinations corresponding to all index parameters: acquiring all current index parameters; acquiring a value set corresponding to each index parameter; and traversing to generate a full index set: and traversing the value sets of the index parameters in sequence, and iteratively outputting a full index configuration matrix which is recorded as a full index set.
Step three, generating full performance data: 1. inputting: a full scale index parameter; 2. iteration: and traversing each configuration value combination of the total index parameters in sequence, and calling the performance prediction model output in the first step to complete performance data prediction to obtain a product performance value. 3. And (3) outputting: and (4) full performance data (which is different from basic data and is independently persisted, so that the data can be updated conveniently). The full-scale performance data updating mechanism comprises the following two mechanisms: 1) Monitoring a basic data change event, and automatically updating the full performance data; 2) And a manual updating mode is used for carrying out local updating or one-key total updating according to the index parameter configuration.
Step four, preprocessing the full performance data: and (3) performing segmentation processing on the performance data to enable the performance data to meet the data requirement of the algorithm: the actually measured and evaluated performance data can be various data, can have decimal data or accurate to single-digit data, so that the performance data needs to be segmented firstly, and can be classified.
Step five, determining key index combination: acquiring the parameter weight omega of the index parameter output in the first step, setting a weight threshold value, identifying the index parameter of which the parameter weight omega is greater than the set weight threshold value as a key index parameter, and then taking the key index parameter as a frequent item set applied by the association rule algorithm in the later study, starting iteration from the frequent item set of the key index, wherein the association rule algorithm does not need to start iteration from one item set, so that the iteration times are reduced, and the mining algorithm is improved.
Step six, applying an association rule algorithm: inputting: the full performance data after data preprocessing and the set confidence coefficient; using Apriori algorithm to output association rules meeting confidence, wherein the algorithm mainly comprises the following cores:
let I = { I 1 ，I 2 ，…，I m Is a set of items, m is the number of items, where I i Representing the ith item, corresponding to an index parameter, transaction T i A subset of the representation I, corresponding to the configuration value combination of the index parameters; the association rule is in the form of X->Y, wherein X and Y are referred to as the predecessor and successor of the association rule, respectively, wherein the association rule XY, with support and confidence, is as follows:
in the using process of the algorithm, all index parameters meeting the weight threshold are identified as key index parameter combinations and used as K item sets, wherein K is the number of the key index parameters, and frequent item sets are searched for iteratively from the K item sets. Setting the configuration value combination of the index parameters as X, setting the performance value Y, setting the confidence coefficient, and outputting the association rule of the index configuration value combination meeting the conditions. In addition, in the using process of the algorithm, the confidence coefficient can be set iteratively, and association rules under different confidence coefficients are output, so that more comprehensive recommended parameter configuration can be provided;
and finally, preprocessing and classifying data according to the set specific performance value (namely the performance value required by the user), and outputting the configuration value combination of the index parameters by combining the output association rule and different confidence degrees for the user to select and refer.
That is, the method includes the steps that index parameters are configured firstly, basic performance data of a stored product are collected, then training, learning and iterative optimization are conducted on the basic performance data through a particle swarm optimization algorithm, and parameter weights and performance prediction models corresponding to the index parameters are output; secondly, generating new full index parameter configuration through an algorithm according to the index parameters, and calling the new full index parameter configuration as full index data; thirdly, using a performance prediction model, taking the full index data as input, calling a performance evaluation model, and generating performance data corresponding to all parameter indexes under the full index data, which is called as full performance data; fourthly, carrying out data preprocessing on the full-scale performance data to enable the full-scale performance data to meet the input of an association rule algorithm, and analyzing and mining an association rule hidden in the data by using the association rule algorithm; and finally, according to the association rule, the reliable recommendation of the index parameters is completed by combining the performance value required by the user, and a good foundation is laid for better market promotion of the product.
Therefore, recommendation index parameter configuration can be obtained through the performance value, not only can performance evaluation prediction from collected basic performance data be completed, but also the comprehensiveness of parameter configuration of the recommendation algorithm is ensured by generating the totality of performance index data, so that reliable recommendation from the performance data to the product configuration of a client is met to the maximum extent when a first-line engineer popularizes products in the market, and reliable basis is provided for popularization of the products.
Referring to fig. 3, an embodiment of the present application discloses a device for recommending storage product parameter configuration, including:
a parameter and value set acquisition module 11, configured to acquire all index parameters of a storage product and a configuration value set of each index parameter;
a full performance data obtaining module 12, configured to obtain full performance data of the storage product based on the configuration value sets of all the index parameters; the full performance data comprises all configuration value combinations corresponding to all index parameters and product performance values corresponding to each configuration value combination;
an association rule determining module 13, configured to determine an association rule between an index parameter configuration value combination and a product performance value based on the full performance data; the index parameter configuration value combination comprises configuration values of a plurality of index parameters in all the index parameters;
and the parameter configuration recommending module 14 is configured to, when the product performance value required by the user is obtained, output a recommended index parameter configuration value combination corresponding to the product performance value based on the association rule.
As can be seen, in the embodiment of the present application, all the index parameters of the storage product and the configuration value set of each index parameter are obtained first, and then the full-scale performance data of the storage product is obtained based on the configuration value sets of all the index parameters; the total performance data comprises all configuration value combinations corresponding to all index parameters and product performance values corresponding to each configuration value combination, association rules of the index parameter configuration value combinations and the product performance values are determined based on the total performance data, the index parameter configuration value combinations comprise configuration values of a plurality of index parameters in all the index parameters, and when the product performance values required by users are obtained, recommended index parameter configuration value combinations corresponding to the product performance values are output based on the association rules. That is, in the embodiment of the present application, the full-scale performance data of the storage product is obtained based on the configuration value set of all the index parameters of the storage product, the association rule between the parameter configuration value combination and the product performance value is mined based on the full-scale performance data, and when the product performance value required by the user is obtained, the corresponding recommended index parameter configuration value combination is output based on the association rule, so that the influence of the subjective factor can be avoided, and the reliability of the parameter configuration recommendation of the storage product is improved.
Further, the device also comprises a performance prediction model obtaining module, which is used for obtaining a performance prediction model;
accordingly, the full performance data obtaining module 12 includes:
a total configuration value combination obtaining submodule, configured to traverse the configuration value sets of all the index parameters, to obtain total configuration value combinations corresponding to all the index parameters;
and the total performance data sub-acquisition module is used for acquiring the total performance data of the storage product based on all the configuration value combinations by utilizing the performance prediction model.
In a specific embodiment, all the configuration value combination acquisition sub-modules are specifically used for acquiring basic performance data; the basic performance data comprises common configuration value combinations of all the index parameters and product performance values obtained by performing performance tests on the storage products by utilizing each common configuration value combination; and training the basic performance data based on a preset classifier to obtain the performance prediction evaluation model.
In a specific embodiment, the full performance data sub-obtaining module is specifically configured to:
determining an unused configuration value combination from all the configuration value combinations;
predicting the product performance value corresponding to the unusual configuration value combination by using the performance prediction model;
and determining the full performance data of the storage product based on the basic performance data and the product performance value corresponding to the unusual configuration value combination.
Further, the apparatus further comprises: and the preset classifier building module is used for building a classifier based on a particle swarm algorithm to obtain the preset classifier.
And the device also comprises a full-volume performance data updating module, which is used for updating the full-volume performance data based on the change event when the change event of the basic performance data is monitored.
Further, the apparatus further comprises:
a key index parameter determination module, configured to determine a key index parameter from all the index parameters;
correspondingly, the index parameter configuration value combination comprises the configuration value of the key index parameter.
And the association rule determining module 13 is specifically configured to run a preset association rule algorithm based on the full performance data, and start iteration with a frequent item set composed of the key index parameters to obtain the association rule between the index parameter configuration value combination and the product performance value.
In an embodiment, the key index parameter determining module is specifically configured to obtain a parameter weight corresponding to each index parameter in all the index parameters; and determining the index parameters with the parameter weight larger than the preset weight threshold value as key index parameters.
Wherein the obtaining of the parameter weight corresponding to each index parameter in all the index parameters includes: acquiring basic performance data; the basic performance data comprises common configuration value combinations of all the index parameters and product performance values obtained by performing performance tests on the storage products by using each common configuration value combination; and training the basic performance data based on a preset classifier to obtain the parameter weight corresponding to each index parameter.
In addition, the device further comprises a full capacity performance data preprocessing module, which is used for performing segmentation processing on the product performance value in the full capacity performance data before determining the association rule of the index parameter configuration value combination and the product performance value based on the full capacity performance data, so as to process the product performance value into a preset value corresponding to the corresponding data segment.
In an embodiment, the association rule determining module 13 is specifically configured to determine, based on the full performance data, an association rule between an index parameter configuration value combination and a product performance value at different confidence degrees;
correspondingly, the parameter configuration recommending module 14 is specifically configured to obtain a confidence level required by the user, and output a recommended index parameter configuration value combination corresponding to the product performance value under the confidence level based on the association rule.
Referring to fig. 4, an embodiment of the present application discloses an electronic device 20, which includes a processor 21 and a memory 22; wherein, the memory 22 is used for saving computer programs; the processor 21 is configured to execute the computer program to implement the following steps:
acquiring all index parameters of a stored product and a configuration value set of each index parameter; acquiring the full performance data of the storage product based on the configuration value sets of all the index parameters; the full performance data comprises all configuration value combinations corresponding to all index parameters and product performance values corresponding to each configuration value combination; determining association rules of index parameter configuration value combinations and product performance values based on the full performance data; the index parameter configuration value combination comprises configuration values of a plurality of index parameters in all the index parameters; and when the product performance value required by the user is obtained, outputting a recommended index parameter configuration value combination corresponding to the product performance value based on the association rule.
As can be seen, in the embodiment of the present application, all the index parameters of the storage product and the configuration value set of each index parameter are obtained first, and then the full-scale performance data of the storage product is obtained based on the configuration value sets of all the index parameters; the full performance data comprises all configuration value combinations corresponding to all index parameters and product performance values corresponding to each configuration value combination, association rules of the index parameter configuration value combinations and the product performance values are determined based on the full performance data, the index parameter configuration value combinations comprise configuration values of a plurality of index parameters in all the index parameters, and when a product performance value required by a user is obtained, recommended index parameter configuration value combinations corresponding to the product performance value are output based on the association rules. That is, in the embodiment of the present application, the full-scale performance data of the storage product is obtained based on the configuration value set of all the index parameters of the storage product, the association rule between the parameter configuration value combination and the product performance value is mined based on the full-scale performance data, and when the product performance value required by the user is obtained, the corresponding recommended index parameter configuration value combination is output based on the association rule, so that the influence of the subjective factor can be avoided, and the reliability of the parameter configuration recommendation of the storage product is improved.
In this embodiment, when the processor 21 executes the computer subprogram stored in the memory 22, the following steps may be specifically implemented: acquiring a performance prediction model; traversing the configuration value sets of all the index parameters to obtain all configuration value combinations corresponding to all the index parameters; and acquiring the full performance data of the storage product by using the performance prediction model and based on all the configuration value combinations.
In this embodiment, when the processor 21 executes the computer subprogram stored in the memory 22, the following steps may be specifically implemented: acquiring basic performance data; the basic performance data comprises common configuration value combinations of all the index parameters and product performance values obtained by performing performance tests on the storage products by utilizing each common configuration value combination; and training the basic performance data based on a preset classifier to obtain the performance prediction evaluation model.
In this embodiment, when the processor 21 executes the computer subprogram stored in the memory 22, the following steps may be specifically implemented: determining an unused configuration value combination from all the configuration value combinations; predicting the product performance value corresponding to the unusual configuration value combination by using the performance prediction model; and determining the full performance data of the storage product based on the basic performance data and the product performance value corresponding to the unusual configuration value combination.
In this embodiment, when the processor 21 executes the computer subprogram stored in the memory 22, the following steps may be specifically implemented: and constructing a classifier based on a particle swarm algorithm to obtain the preset classifier.
In this embodiment, when the processor 21 executes the computer subprogram stored in the memory 22, the following steps may be specifically implemented: and when a change event of the basic performance data is monitored, updating the full-scale performance data based on the change event.
In this embodiment, when the processor 21 executes the computer subprogram stored in the memory 22, the following steps may be specifically implemented: determining key index parameters from all the index parameters; correspondingly, the index parameter configuration value combination comprises the configuration value of the key index parameter.
In this embodiment, when the processor 21 executes the computer subprogram stored in the memory 22, the following steps may be specifically implemented: and running a preset association rule algorithm based on the full performance data, and starting iteration by using a frequent item set consisting of the key index parameters to obtain an association rule of the index parameter configuration value combination and the product performance value.
In this embodiment, when the processor 21 executes the computer subprogram stored in the memory 22, the following steps may be specifically implemented: acquiring the parameter weight corresponding to each index parameter in all the index parameters; and determining the index parameters with the parameter weight larger than the preset weight threshold value as key index parameters.
In this embodiment, when the processor 21 executes the computer subprogram stored in the memory 22, the following steps may be specifically implemented: acquiring basic performance data; the basic performance data comprises common configuration value combinations of all the index parameters and product performance values obtained by performing performance tests on the storage products by utilizing each common configuration value combination; and training the basic performance data based on a preset classifier to obtain the parameter weight corresponding to each index parameter.
In this embodiment, when the processor 21 executes the computer subprogram stored in the memory 22, the following steps may be specifically implemented: and carrying out segmentation processing on the product performance values in the full-scale performance data so as to process the product performance values into preset values corresponding to the corresponding data segments.
In this embodiment, when the processor 21 executes the computer subprogram stored in the memory 22, the following steps may be specifically implemented: determining association rules of index parameter configuration value combinations and product performance values under different confidence degrees based on the full performance data; and obtaining the confidence required by the user, and outputting the recommended index parameter configuration value combination corresponding to the product performance value under the confidence based on the association rule.
The memory 22 is used as a carrier for resource storage, and may be a read-only memory, a random access memory, a magnetic disk, or an optical disk, and the storage manner may be a transient storage manner or a permanent storage manner.
In addition, the electronic device 20 further includes a power supply 23, a communication interface 24, an input-output interface 25, and a communication bus 26; the power supply 23 is configured to provide an operating voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and an external device, and a communication protocol followed by the communication interface is any communication protocol applicable to the technical solution of the present application, and is not specifically limited herein; the input/output interface 25 is configured to acquire external input data or output data to the outside, and a specific interface type thereof may be selected according to specific application requirements, which is not specifically limited herein.
Further, an embodiment of the present application discloses a computer readable storage medium for storing a computer program, wherein the computer program, when executed by a processor, implements the following steps:
acquiring all index parameters of a stored product and a configuration value set of each index parameter; acquiring the full performance data of the storage product based on the configuration value set of all the index parameters; the full performance data comprises all configuration value combinations corresponding to all index parameters and product performance values corresponding to each configuration value combination; determining association rules of index parameter configuration value combinations and product performance values based on the full-scale performance data; the index parameter configuration value combination comprises configuration values of a plurality of index parameters in all the index parameters; and when the product performance value required by the user is obtained, outputting a recommended index parameter configuration value combination corresponding to the product performance value based on the association rule.
As can be seen, in the embodiment of the present application, all the index parameters of the storage product and the configuration value set of each index parameter are obtained first, and then the full-scale performance data of the storage product is obtained based on the configuration value sets of all the index parameters; the total performance data comprises all configuration value combinations corresponding to all index parameters and product performance values corresponding to each configuration value combination, association rules of the index parameter configuration value combinations and the product performance values are determined based on the total performance data, the index parameter configuration value combinations comprise configuration values of a plurality of index parameters in all the index parameters, and when the product performance values required by users are obtained, recommended index parameter configuration value combinations corresponding to the product performance values are output based on the association rules. That is, in the embodiment of the present application, the full-scale performance data of the storage product is obtained based on the configuration value set of all the index parameters of the storage product, the association rule between the parameter configuration value combination and the product performance value is mined based on the full-scale performance data, and when the product performance value required by the user is obtained, the corresponding recommended index parameter configuration value combination is output based on the association rule, so that the influence of the subjective factor can be avoided, and the reliability of the parameter configuration recommendation of the storage product is improved.
In this embodiment, when the computer subprogram stored in the computer-readable storage medium is executed by the processor, the following steps may be specifically implemented: acquiring a performance prediction model; traversing the configuration value sets of all the index parameters to obtain all configuration value combinations corresponding to all the index parameters; and acquiring the full performance data of the storage product by using the performance prediction model and based on all the configuration value combinations.
In this embodiment, when the computer subprogram stored in the computer-readable storage medium is executed by the processor, the following steps may be specifically implemented: acquiring basic performance data; the basic performance data comprises common configuration value combinations of all the index parameters and product performance values obtained by performing performance tests on the storage products by utilizing each common configuration value combination; and training the basic performance data based on a preset classifier to obtain the performance prediction evaluation model.
In this embodiment, when the computer subprogram stored in the computer-readable storage medium is executed by the processor, the following steps may be specifically implemented: determining an unused configuration value combination from all the configuration value combinations; predicting product performance values corresponding to the non-use configuration value combinations by using the performance prediction model; and determining the full performance data of the storage product based on the basic performance data and the product performance value corresponding to the unusual configuration value combination.
In this embodiment, when the processor executes the computer subprogram stored in the computer readable storage medium, the following steps may be specifically implemented: and constructing a classifier based on a particle swarm algorithm to obtain the preset classifier.
In this embodiment, when the computer subprogram stored in the computer-readable storage medium is executed by the processor, the following steps may be specifically implemented: and when a change event of the basic performance data is monitored, updating the full-scale performance data based on the change event.
In this embodiment, when the computer subprogram stored in the computer-readable storage medium is executed by the processor, the following steps may be specifically implemented: determining key index parameters from all the index parameters; correspondingly, the index parameter configuration value combination comprises the configuration value of the key index parameter.
In this embodiment, when the processor executes the computer subprogram stored in the computer readable storage medium, the following steps may be specifically implemented: and running a preset association rule algorithm based on the full performance data, and starting iteration by using a frequent item set consisting of the key index parameters to obtain an association rule of the index parameter configuration value combination and the product performance value.
In this embodiment, when the computer subprogram stored in the computer-readable storage medium is executed by the processor, the following steps may be specifically implemented: acquiring the parameter weight corresponding to each index parameter in all the index parameters; and determining the index parameters with the parameter weight larger than a preset weight threshold value as key index parameters.
In this embodiment, when the computer subprogram stored in the computer-readable storage medium is executed by the processor, the following steps may be specifically implemented: acquiring basic performance data; the basic performance data comprises common configuration value combinations of all the index parameters and product performance values obtained by performing performance tests on the storage products by utilizing each common configuration value combination; and training the basic performance data based on a preset classifier to obtain the parameter weight corresponding to each index parameter.
In this embodiment, when the computer subprogram stored in the computer-readable storage medium is executed by the processor, the following steps may be specifically implemented: and performing segmentation processing on the product performance value in the full-scale performance data so as to process the product performance value into a preset value corresponding to the corresponding data segment.
In this embodiment, when the processor executes the computer subprogram stored in the computer readable storage medium, the following steps may be specifically implemented: determining association rules of index parameter configuration value combinations and product performance values under different confidence degrees based on the full performance data; and acquiring the confidence required by the user, and outputting the recommended index parameter configuration value combination corresponding to the product performance value under the confidence based on the association rule.
The embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same or similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The above detailed description is given to a method, an apparatus, a device, and a medium for recommending storage product parameter configuration, and specific examples are applied herein to explain the principles and embodiments of the present application, and the descriptions of the above embodiments are only used to help understand the method and the core idea of the present application; meanwhile, for a person skilled in the art, according to the idea of the present application, the specific implementation manner and the application scope may be changed, and in summary, the content of the present specification should not be construed as a limitation to the present application.
Claims (15)
1. A method for recommending stored product parameter configuration, comprising:
acquiring all index parameters of a stored product and a configuration value set of each index parameter;
acquiring the full performance data of the storage product based on the configuration value sets of all the index parameters; the full performance data comprises all configuration value combinations corresponding to all index parameters and product performance values corresponding to each configuration value combination;
determining association rules of index parameter configuration value combinations and product performance values based on the full performance data; the index parameter configuration value combination comprises configuration values of a plurality of index parameters in all the index parameters;
and when the product performance value required by the user is obtained, outputting a recommended index parameter configuration value combination corresponding to the product performance value based on the association rule.
2. The method of claim 1, further comprising:
acquiring a performance prediction model;
correspondingly, the acquiring the full performance data of the storage product based on the configuration value set of all the index parameters includes:
traversing the configuration value sets of all the index parameters to obtain all configuration value combinations corresponding to all the index parameters;
and acquiring the full performance data of the storage product by using the performance prediction model and based on all the configuration value combinations.
3. The method of claim 2, wherein the obtaining a performance prediction model comprises:
acquiring basic performance data; the basic performance data comprises common configuration value combinations of all the index parameters and product performance values obtained by performing performance tests on the storage products by utilizing each common configuration value combination;
and training the basic performance data based on a preset classifier to obtain the performance prediction evaluation model.
4. The method according to claim 3, wherein the obtaining of the full performance data of the storage product based on the all configuration value combinations by using the performance prediction model comprises:
determining an unused configuration value combination from all the configuration value combinations;
predicting product performance values corresponding to the non-use configuration value combinations by using the performance prediction model;
and determining the total performance data of the stored product based on the basic performance data and the product performance value corresponding to the unusual configuration value combination.
5. The stored product parameter configuration recommendation method of claim 3, further comprising:
and constructing a classifier based on a particle swarm algorithm to obtain the preset classifier.
6. The stored product parameter configuration recommendation method of claim 3, further comprising:
and when a change event of the basic performance data is monitored, updating the full-scale performance data based on the change event.
7. The stored product parameter configuration recommendation method of claim 1, further comprising:
determining key index parameters from all the index parameters;
correspondingly, the index parameter configuration value combination comprises the configuration value of the key index parameter.
8. The method of claim 7, wherein the determining the association rule between the combination of index parameter configuration values and the product performance values based on the full-scale performance data comprises:
and running a preset association rule algorithm based on the full performance data, and starting iteration by using a frequent item set consisting of the key index parameters to obtain an association rule of the index parameter configuration value combination and the product performance value.
9. The method for recommending storage product parameter configuration according to claim 7, wherein said determining key index parameters from said all index parameters comprises:
acquiring the parameter weight corresponding to each index parameter in all the index parameters;
and determining the index parameters with the parameter weight larger than a preset weight threshold value as key index parameters.
10. The method of claim 9, wherein the obtaining the parameter weight corresponding to each index parameter of the index parameters comprises:
acquiring basic performance data; the basic performance data comprises common configuration value combinations of all the index parameters and product performance values obtained by performing performance tests on the storage products by using each common configuration value combination;
and training the basic performance data based on a preset classifier to obtain the parameter weight corresponding to each index parameter.
11. The method of claim 1, wherein before determining the association rule between the combination of index parameter configuration values and the product performance value based on the full-scale performance data, the method further comprises:
and performing segmentation processing on the product performance value in the full-scale performance data so as to process the product performance value into a preset value corresponding to the corresponding data segment.
12. The method for recommending storage product parameter configuration according to any of claims 1 to 11, wherein said determining the association rule of the index parameter configuration value combination and the product performance value based on the full-scale performance data comprises:
determining association rules of index parameter configuration value combinations and product performance values under different confidence degrees based on the full performance data;
correspondingly, outputting a recommended index parameter configuration value combination corresponding to the product performance value based on the association rule includes:
and acquiring the confidence required by the user, and outputting the recommended index parameter configuration value combination corresponding to the product performance value under the confidence based on the association rule.
13. A stored product parameter configuration recommendation device, comprising:
the parameter and value set acquisition module is used for acquiring all index parameters of the stored product and a configuration value set of each index parameter;
a full performance data acquisition module, configured to acquire full performance data of the storage product based on the configuration value sets of all the index parameters; the full performance data comprises all configuration value combinations corresponding to all index parameters and product performance values corresponding to each configuration value combination;
the association rule determining module is used for determining an association rule of the index parameter configuration value combination and the product performance value based on the full performance data; the index parameter configuration value combination comprises configuration values of a plurality of index parameters in all the index parameters;
and the parameter configuration recommending module is used for outputting a recommended index parameter configuration value combination corresponding to the product performance value based on the association rule when the product performance value required by the user is obtained.
14. An electronic device comprising a memory and a processor, wherein:
the memory is used for storing a computer program;
the processor for executing the computer program to implement the stored product parameter configuration recommendation method of any of claims 1-12.
15. A computer-readable storage medium for storing a computer program, wherein the computer program when executed by a processor implements the stored product parameter configuration recommendation method of any of claims 1 to 12.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211306930.0A CN115392592B (en) | 2022-10-25 | 2022-10-25 | Storage product parameter configuration recommendation method, device, equipment and medium |
| PCT/CN2023/078505 WO2024087428A1 (en) | 2022-10-25 | 2023-02-27 | Parameter configuration recommendation method and apparatus for memory product, and device and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211306930.0A CN115392592B (en) | 2022-10-25 | 2022-10-25 | Storage product parameter configuration recommendation method, device, equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115392592A true CN115392592A (en) | 2022-11-25 |
| CN115392592B CN115392592B (en) | 2023-03-24 |
Family
ID=84127866
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211306930.0A Active CN115392592B (en) | 2022-10-25 | 2022-10-25 | Storage product parameter configuration recommendation method, device, equipment and medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN115392592B (en) |
| WO (1) | WO2024087428A1 (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116401468A (en) * | 2023-04-17 | 2023-07-07 | 哈尔滨工业大学 | Intelligent recommendation system and method based on product concept design characteristic combination |
| WO2024087428A1 (en) * | 2022-10-25 | 2024-05-02 | 浪潮电子信息产业股份有限公司 | Parameter configuration recommendation method and apparatus for memory product, and device and medium |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111190801A (en) * | 2019-12-19 | 2020-05-22 | 广州华多网络科技有限公司 | Recommendation system testing method and device and electronic equipment |
| CN111459542A (en) * | 2020-04-09 | 2020-07-28 | 成都安易迅科技有限公司 | Method, device and system for determining recommended configuration index, storage medium and equipment |
| WO2021000244A1 (en) * | 2019-07-02 | 2021-01-07 | Alibaba Group Holding Limited | Hyperparameter recommendation for machine learning method |
| CN112256209A (en) * | 2020-11-03 | 2021-01-22 | 国电南瑞科技股份有限公司 | Parameter configuration optimization method and optimization system of cloud storage system |
| CN112418978A (en) * | 2020-11-17 | 2021-02-26 | 中国平安财产保险股份有限公司 | Product recommendation method, device, equipment and medium |
| CN113254472A (en) * | 2021-06-17 | 2021-08-13 | 浙江大华技术股份有限公司 | Parameter configuration method, device, equipment and readable storage medium |
| CN113569151A (en) * | 2021-09-18 | 2021-10-29 | 平安科技（深圳）有限公司 | Data recommendation method, device, equipment and medium based on artificial intelligence |
| CN113590576A (en) * | 2021-02-05 | 2021-11-02 | 华中科技大学 | Database parameter adjusting method and device, storage medium and electronic equipment |
| CN114118433A (en) * | 2020-08-26 | 2022-03-01 | 华为技术有限公司 | Recommendation method and device for configuration parameters of equipment |
| CN114356893A (en) * | 2022-01-11 | 2022-04-15 | 平安科技（深圳）有限公司 | Metadata tuning method, device, equipment and storage medium based on machine learning |
| CN114461905A (en) * | 2022-01-04 | 2022-05-10 | 网易传媒科技（北京）有限公司 | Parameter adjusting method and device, recommendation system, electronic device and storage medium |
| CN114610234A (en) * | 2022-02-28 | 2022-06-10 | 浪潮电子信息产业股份有限公司 | Storage system parameter recommendation method and related device |
| CN115062480A (en) * | 2022-04-20 | 2022-09-16 | 希望知舟技术(深圳)有限公司 | Method for recommending production process parameters, and related apparatus and program medium |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10361925B1 (en) * | 2016-06-23 | 2019-07-23 | Nutanix, Inc. | Storage infrastructure scenario planning |
| CN109635006A (en) * | 2018-12-17 | 2019-04-16 | 山大地纬软件股份有限公司 | Social security business association rule digging and recommendation apparatus and method based on Apriori |
| CN115129572B (en) * | 2022-07-29 | 2024-06-28 | 苏州浪潮智能科技有限公司 | Performance test method, device, equipment and medium |
| CN115392592B (en) * | 2022-10-25 | 2023-03-24 | 浪潮电子信息产业股份有限公司 | Storage product parameter configuration recommendation method, device, equipment and medium |
-
2022
- 2022-10-25 CN CN202211306930.0A patent/CN115392592B/en active Active
-
2023
- 2023-02-27 WO PCT/CN2023/078505 patent/WO2024087428A1/en unknown
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021000244A1 (en) * | 2019-07-02 | 2021-01-07 | Alibaba Group Holding Limited | Hyperparameter recommendation for machine learning method |
| CN111190801A (en) * | 2019-12-19 | 2020-05-22 | 广州华多网络科技有限公司 | Recommendation system testing method and device and electronic equipment |
| CN111459542A (en) * | 2020-04-09 | 2020-07-28 | 成都安易迅科技有限公司 | Method, device and system for determining recommended configuration index, storage medium and equipment |
| CN114118433A (en) * | 2020-08-26 | 2022-03-01 | 华为技术有限公司 | Recommendation method and device for configuration parameters of equipment |
| CN112256209A (en) * | 2020-11-03 | 2021-01-22 | 国电南瑞科技股份有限公司 | Parameter configuration optimization method and optimization system of cloud storage system |
| CN112418978A (en) * | 2020-11-17 | 2021-02-26 | 中国平安财产保险股份有限公司 | Product recommendation method, device, equipment and medium |
| CN113590576A (en) * | 2021-02-05 | 2021-11-02 | 华中科技大学 | Database parameter adjusting method and device, storage medium and electronic equipment |
| CN113254472A (en) * | 2021-06-17 | 2021-08-13 | 浙江大华技术股份有限公司 | Parameter configuration method, device, equipment and readable storage medium |
| CN113569151A (en) * | 2021-09-18 | 2021-10-29 | 平安科技（深圳）有限公司 | Data recommendation method, device, equipment and medium based on artificial intelligence |
| CN114461905A (en) * | 2022-01-04 | 2022-05-10 | 网易传媒科技（北京）有限公司 | Parameter adjusting method and device, recommendation system, electronic device and storage medium |
| CN114356893A (en) * | 2022-01-11 | 2022-04-15 | 平安科技（深圳）有限公司 | Metadata tuning method, device, equipment and storage medium based on machine learning |
| CN114610234A (en) * | 2022-02-28 | 2022-06-10 | 浪潮电子信息产业股份有限公司 | Storage system parameter recommendation method and related device |
| CN115062480A (en) * | 2022-04-20 | 2022-09-16 | 希望知舟技术(深圳)有限公司 | Method for recommending production process parameters, and related apparatus and program medium |
Non-Patent Citations (6)
| Title |
|---|
| MAIRIELI SANTOS WESSEL: "Tweaking Association Rules to Optimize Software Change Recommendations", 《PROCEEDINGS OF THE XXXI BRAZILIAN SYMPOSIUM ON SOFTWARE ENGINEERING》 * |
| 余鹏程等: "基于属性规则与关联规则的推荐模型设计", 《电子科技》 * |
| 吴宾等: "联合正则化的矩阵分解推荐算法", 《软件学报》 * |
| 张华欣: "基于大数据的混合Top-N推荐算法研究", 《中国优秀硕士学位论文全文数据库 (信息科技辑)》 * |
| 贾晓光: "基于Spark的并行化协同深度推荐模型", 《计算机工程与应用》 * |
| 面向数据分析的探索式服务组合推荐技术研究: "面向数据分析的探索式服务组合推荐技术研究", 《中国优秀硕士学位论文全文数据库 (信息科技辑)》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2024087428A1 (en) * | 2022-10-25 | 2024-05-02 | 浪潮电子信息产业股份有限公司 | Parameter configuration recommendation method and apparatus for memory product, and device and medium |
| CN116401468A (en) * | 2023-04-17 | 2023-07-07 | 哈尔滨工业大学 | Intelligent recommendation system and method based on product concept design characteristic combination |
| CN116401468B (en) * | 2023-04-17 | 2023-12-19 | 哈尔滨工业大学 | Intelligent recommendation system and method based on product concept design characteristic combination |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2024087428A1 (en) | 2024-05-02 |
| CN115392592B (en) | 2023-03-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115392592B (en) | Storage product parameter configuration recommendation method, device, equipment and medium | |
| CN109818961B (en) | Network intrusion detection method, device and equipment | |
| CN112907026A (en) | Comprehensive evaluation method based on editable mesh index system | |
| CN111025041A (en) | Electric vehicle charging pile monitoring method and system, computer equipment and medium | |
| CN112884569A (en) | Credit assessment model training method, device and equipment | |
| CN110321458B (en) | Data flow analysis method and device based on control flow graph | |
| JP7173234B2 (en) | Methods, apparatus, devices and storage media used for information processing | |
| LU505740B1 (en) | Data monitoring method and system | |
| CN117763316A (en) | High-dimensional data dimension reduction method and dimension reduction system based on machine learning | |
| Kusa et al. | Vombat: A tool for visualising evaluation measure behaviour in high-recall search tasks | |
| CN111949530A (en) | Test result prediction method and device, computer equipment and storage medium | |
| JP2018190129A (en) | Determination device, analysis system, determination method and determination program | |
| CN111008119A (en) | Method, device, equipment and medium for updating hard disk prediction model | |
| CN116502234A (en) | Vulnerability value dynamic evaluation method and device based on decision tree | |
| CN115454466A (en) | Method, apparatus, device and medium for automatic updating of machine learning model | |
| US11762562B2 (en) | Performance analysis apparatus and performance analysis method | |
| CN111461344B (en) | Automatic generation method, system, equipment and medium for high-order features | |
| CN114610590A (en) | Method, device and equipment for determining operation time length and storage medium | |
| CN109436980B (en) | Method and system for detecting state of elevator component | |
| CN113610225A (en) | Quality evaluation model training method and device, electronic equipment and storage medium | |
| CN113312027A (en) | Industrial system development method, electronic device, and storage medium | |
| CN111026661A (en) | Method and system for comprehensively testing usability of software | |
| CN115859768B (en) | Method and device for predicting work piece finishing time of dynamic assembly workshop | |
| CN115473232B (en) | Load parameter adjusting method, system, equipment and storage medium | |
| CN114254764B (en) | Feedback-based machine learning model searching method, system, equipment and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |