CN116502102A - Self-research intelligent product operation system and method for cloud service - Google Patents
Self-research intelligent product operation system and method for cloud service Download PDFInfo
- Publication number
- CN116502102A CN116502102A CN202310762038.1A CN202310762038A CN116502102A CN 116502102 A CN116502102 A CN 116502102A CN 202310762038 A CN202310762038 A CN 202310762038A CN 116502102 A CN116502102 A CN 116502102A
- Authority
- CN
- China
- Prior art keywords
- resource
- design
- service
- cloud service
- user
- 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
- 238000011160 research Methods 0.000 title claims abstract description 26
- 238000000034 method Methods 0.000 title claims abstract description 19
- 238000013461 design Methods 0.000 claims abstract description 202
- 238000011156 evaluation Methods 0.000 claims abstract description 47
- 238000005538 encapsulation Methods 0.000 claims abstract description 11
- 230000003993 interaction Effects 0.000 claims abstract description 6
- 239000013598 vector Substances 0.000 claims description 16
- 230000006978 adaptation Effects 0.000 claims description 10
- 230000003068 static effect Effects 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000012544 monitoring process Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 6
- 239000000284 extract Substances 0.000 claims description 4
- 230000007613 environmental effect Effects 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 230000008447 perception Effects 0.000 claims description 3
- 238000004806 packaging method and process Methods 0.000 claims 1
- 238000004519 manufacturing process Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 201000004569 Blindness Diseases 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000012938 design process Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000005498 polishing Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
-
- 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
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a self-research intelligent product operation system and a self-research intelligent product operation method for cloud service, which are characterized in that a resource type in design resources is acquired, the design resources are accessed according to the resource type, a resource type resource ontology model is constructed, design tasks of the resource ontology model are acquired, the design resources are subjected to service encapsulation to form cloud service, comprehensive performance indexes of the cloud service are identified to obtain a cloud service pool, comprehensive satisfaction of users in the service pool is acquired from target cloud service, a user QoS preference model is constructed, the maximum user QoS preference similarity in the user QoS model is selected to determine the target cloud service, the target cloud service and the design tasks are bound and executed to complete the self-research intelligent product operation of the target cloud service, the design tasks and the service resources are subjected to similarity matching and cloud service quality recommendation are combined to improve the service quality of the cloud service, the interaction condition of users on service evaluation is fused, service description of the resources is realized, and the operation efficiency of the cloud service is improved.
Description
Technical Field
The invention belongs to the technical field of cloud services, and particularly relates to a self-research intelligent product operation system and method for cloud services.
Background
At present, in the process of matching and judging a user task and a service resource, the task description is generally that the task submitted by the user is firstly converted into a standard resource service request description, various information of the task is classified and extracted, parameters such as basic information, input information, output information and the like are analyzed, and then the parameters are matched with corresponding information in the service resource, so that the service searching and matching process is completed, or a cloud database is searched by directly using service resource entries. However, quality of service QoS is an important concept for defining non-functional characteristics of a service, in a cloud manufacturing service, whether the cloud manufacturing service meets own needs is measured based on the quality of service QoS of the cloud manufacturing service, and service types and functions are various, so that classification standards are five-in-eight, different classification results can be generated according to different classification standards, and the originally defined quality of service QoS only includes an index for measuring whether the service meets the non-functionality of a user. Because of the growing cloud service, a user can only judge whether a certain cloud service can meet the own functional requirement through the functional description of a service provider or a platform operator, but cannot judge whether the functional service quality is good or bad, so that the operation efficiency of the cloud service is affected.
Disclosure of Invention
In view of the above, the present invention provides a self-research intelligent product operation system and method for cloud service, which can improve the functional service quality, the accuracy of matching resources and services, and the operation efficiency of cloud service, so as to solve the above technical problems.
In a first aspect, the present invention provides a self-research intelligent product operation system for cloud services, comprising:
the resource acquisition module is used for acquiring the resource type in the design resource, accessing the design resource according to the resource type and constructing a resource ontology model corresponding to the resource type, wherein the resource type comprises a static entity resource and a dynamic capacity resource;
the service building module is used for obtaining the design task of the resource ontology model and carrying out service encapsulation on the design resource to form cloud service, and identifying the comprehensive performance index of the cloud service to obtain a cloud service pool;
the service selection module is used for acquiring the comprehensive satisfaction degree of the users of the service pool from the target cloud service, constructing a user QoS preference model, and selecting the maximum user QoS preference similarity in the user QoS model to determine the target cloud service;
and the service execution module is used for binding and executing the target cloud service and the design task to complete the self-research intelligent product operation of the target cloud service.
As a further preferred aspect of the above technical solution, selecting the maximum user QoS preference similarity in the user QoS model to determine the target cloud service includes:
the Euclidean distance is adopted to calculate the preference similarity of the user, and when the user puts forward or the system senses the service request of the user, the service request semantic is matched with a group of candidate services with the same functionality from the target cloud serviceIf each candidate service contains m QoS attribute values +.>Different QoS attribute values represent the performance requirements of different services, and m attribute values of n services are constructed into one +.>By row vectorsDescribing QoS attribute values corresponding to each service;
each QoS attribute value is weighted, the higher the weight the greater the importance,represents m QoS attribute values +.>The Euclidean distance represents the distance between two points in m-dimensional space, and the QoS attribute value vector of each service is calculated by adopting the weighted Euclidean distance>Distance from user preference QoS attribute value vector aThe expression of the weighted Euclidean distance calculation isMaximum selection of the service with highest similarity S, i.e. +.>Wherein->Representing user QoS preference similarity for the service.
As a further preferred aspect of the above technical solution, obtaining comprehensive satisfaction of users of a service pool from a target cloud service and constructing a user QoS preference model includes:
acquiring a service request, sending the service request to a cloud service adaptation unit and matching corresponding services, wherein the cloud service adaptation unit comprehensively processes the user evaluation information and the context information of the current equipment environment according to the QoS evaluation information stored in a QoS evaluation information table and pushes a cloud service which can meet the personalized preference of the user and accords with the environment context to the user, and the cloud service adaptation unit belongs to a service selection module;
the QoS preference vector is extracted from the previous evaluation information of the user through clustering, the similarity between the service and the QoS preference vector of the user is calculated through weighting Euclidean distance, the context monitoring unit extracts and analyzes the context information of the user equipment to calculate the context matching degree, and the context matching degree is provided for the service meeting the maximum comprehensive evaluation degree, wherein the context monitoring unit belongs to a service selection module.
As a further preferred aspect of the above technical solution, pushing a cloud service capable of meeting user personalized preference and conforming to environmental context to a user includes:
presetting a user behavior matrix as，/>Representing the behavior of user u on service i, in a modelI.e. H is the product of two multidimensional matrices, the transversal quantity H represents the preference degree of the user for each hidden factor, i.e. the evaluation dimension of the service, k represents the number of hidden factors, the column vector F represents the probability distribution of a service on each hidden factor, the user requirement and the service are contacted through the hidden characteristic relation, the information of both the user and the service is fused with the information of the implicit feedback, and the information is mapped to a multidimensional space in a joint way.
As a further preferred aspect of the above technical solution, obtaining a design task of a resource ontology model and performing service encapsulation on design resources to form a cloud service, and identifying a comprehensive performance index of the cloud service to obtain a cloud service pool, including:
the resource ontology model comprises an ontology, a concept and an attribute, wherein the ontology is used for expressing objects of tasks or parameters of the objects, the concept is used for expressing contents related to the objects in a collective manner, the attribute is used for expressing the relationship between the concept or the concept and characters and numerical values, and the expression of the ontology model for designing the resource is constructed by adopting a binary algorithm and is thatWherein R represents an ontology model, and the family represents the whole resource, the individual resource or the resource parameter according to the difference of the representation levels; c represents the concept of ontology, using the set to express design resources or parameter information thereof; />Representing attributes related to concepts in the resource, representing relationships between the concepts;
constructing a multi-granularity and multi-layer design resource ontology model through a binary group algorithm and different concepts and attribute sets, wherein the aggregate expression of an ontology model binary group object is as followsWherein i represents the number of concepts contained in the ontology; />The ith concept representing an ontology，/>Property representing the i-th concept itself in the ontology, < +.>Representing the attribute relationship between the i-th and j-th concepts in the topic.
As a further preferable aspect of the above technical solution, identifying the comprehensive performance index of the cloud service to obtain the cloud service pool includes:
the expression for presetting the comprehensive index CM to reflect the comprehensive performance of different cloud services is thatWherein->Comprehensive performance value of a certain cloud service representing the ith cloud platform,/for>Weight indicating j-th performance index value of cloud service,/->Represents the maximum value of the j-th performance index in all cloud platforms,/for>Representing the minimum value of the jth performance index in all cloud platforms,/for>The j-th performance index value of the cloud service on the i-th cloud platform is represented, N represents the combination of all performance indexes of a certain cloud service participating in calculation, and the j-th performance index value is represented by the combination of +.>Normalized to +.>The larger the value of CM, the better the overall performance of the cloud service.
As a further preferred aspect of the above technical solution, accessing design resources according to a resource type and constructing a resource ontology model corresponding to the resource type includes:
acquiring historical data of design resource completion to establish an evaluation variable of the design resource, wherein the evaluation variable comprises a design maturity coefficient, a design success rate coefficient and a design stability coefficient, the completion condition of the design task reflects the maturity condition of the design resource, and the design maturity coefficient is establishedThe expression of (2) is +.>Wherein M represents the number of times the design resource performs the design task, < ->Representing the number of times a resource has completed a design task, M and +.>All give the initial value to be 1, obtain the coefficient initial value of the design maturity to be 1;
the design times of successfully completing the design task reflect the design capability of the design resource, and a design success rate coefficient is establishedThe expression of (2) is +.>Wherein M represents the number of times the design resource performs a task, < +.>Representing the number of times the resource successfully completes the design task, M and +.>All give the initial value to be 1, get the initial value of the coefficient of success rate of design to be 1;
if the time for completing the design task is closer, the design is representedThe higher the stability of the resource, the greater the probability that the design task can be completed on time when the resource user invokes the resource, and the proportional mean square error is establishedThe expression of (2) isWherein M represents the number of times the design resource performs a task, < >>Indicating the time of use of the resource for the ith execution of the design task,/->Representing the average time spent of m execution of design tasks by a resource, proportional mean square error +.>Reflecting the degree of difference in design when performing multiple design tasks.
As a further preferable mode of the technical scheme, the evaluation variables further comprise experience coefficients, evaluation indexes and cost indexes of the design resources, the total number of the resources participating in the design reflects the experience that the resources can contain, and the expression for establishing the experience coefficients is thatWherein M represents the number of times the designed resource performs the task, and when the resource is called for the first time, an initial value M=1 and an experience coefficient are given to the designed resource>A value of 0 indicates that the design resource does not participate in the design at present;
the expression of the evaluation index E using the average of the quality scores in QoS user evaluation as the design resource isWherein M represents the number of times the design resource performs a task, < +.>Representing an ith user quality rating score for the resource;
the design cost is reflected in both the man-hour cost and the design time, and the expression of the design resource cost index D is established asWherein M represents the number of times the design resource performs a task, < +.>Representing the ith design use of a resource,representing the man-hour price of the ith design of the resource.
As a further preference of the above technical solution, obtaining a resource type in the design resource, accessing the design resource according to the resource type and constructing a resource ontology model corresponding to the resource type, including:
the dynamic capacity resource is accessed, wherein the dynamic capacity resource comprises program type resources and human resources, is accessed in a man-machine interaction mode, is driven by a designer, automatically accesses the program resources by using a fixed input/output interface, and is automatically driven by a system;
and the static entity resources comprise offline resources and mobile equipment, and the required resources are perceived and accessed through human resources to realize offline perception of the resources, so that the non-online management of the resources is completed.
In a second aspect, the present invention also provides a self-research intelligent product operation method for cloud services, including the following steps:
acquiring a resource type in a design resource, accessing the design resource according to the resource type, and constructing a resource ontology model corresponding to the resource type, wherein the resource type comprises a static entity resource and a dynamic capacity resource;
acquiring a design task of a resource ontology model, carrying out service encapsulation on the design resource to form cloud service, and identifying comprehensive performance indexes of the cloud service to obtain a cloud service pool;
acquiring comprehensive user satisfaction of a service pool from the target cloud service, constructing a user QoS preference model, and selecting the maximum user QoS preference similarity in the user QoS model to determine the target cloud service;
and binding and executing the target cloud service and the design task to complete the self-research intelligent product operation of the target cloud service.
The invention provides a self-research intelligent product operation system and a self-research intelligent product operation method for cloud service, which are characterized in that a resource type in design resources is acquired, the design resources are accessed according to the resource type, a resource ontology model corresponding to the resource type is constructed, the design tasks of the resource ontology model are acquired, the design resources are subjected to service encapsulation to form cloud service, the comprehensive performance indexes of the cloud service are identified to obtain a cloud service pool, the comprehensive satisfaction degree of users in the service pool is acquired from target cloud service, a user QoS preference model is constructed, the maximum user QoS preference similarity in the user QoS model is selected to determine target cloud service, the target cloud service and the design tasks are bound and executed to complete the self-research intelligent product operation of the target cloud service, the design tasks and the service resources are subjected to similarity matching and cloud service quality recommendation are combined to improve the service quality of the cloud service, the interaction condition of users on service evaluation is fused, so that the service description of the resources is realized, and the operation efficiency of the cloud service is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a block diagram of a self-developed intelligent product operation system for cloud services according to the present invention;
FIG. 2 is a flow chart of a method of operating a self-polishing intelligent product for cloud services according to the present invention.
Detailed Description
Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative only and are not to be construed as limiting the invention.
Referring to fig. 1, the present invention provides a self-research intelligent product operation system for cloud service, comprising:
the resource acquisition module is used for acquiring the resource type in the design resource, accessing the design resource according to the resource type and constructing a resource ontology model corresponding to the resource type, wherein the resource type comprises a static entity resource and a dynamic capacity resource;
the service building module is used for obtaining the design task of the resource ontology model and carrying out service encapsulation on the design resource to form cloud service, and identifying the comprehensive performance index of the cloud service to obtain a cloud service pool;
the service selection module is used for acquiring the comprehensive satisfaction degree of the users of the service pool from the target cloud service, constructing a user QoS preference model, and selecting the maximum user QoS preference similarity in the user QoS model to determine the target cloud service;
and the service execution module is used for binding and executing the target cloud service and the design task to complete the self-research intelligent product operation of the target cloud service.
In this embodiment, selecting the maximum user QoS preference similarity in the user QoS model to determine the target cloud service includes: the Euclidean distance is adopted to calculate the preference similarity of the user, and when the user puts forward or the system senses the service request of the user, the service request semantic is matched with a group of candidate services with the same functionality from the target cloud serviceIf each candidate service contains m QoS attribute values +.>Different QoS attribute values represent the performance requirements of different services, and m attribute values of n services are constructedBuild a +.>Is>Describing QoS attribute values corresponding to each service; each QoS attribute value is weighted, the higher the weight the greater the importance,represents m QoS attribute values +.>The Euclidean distance represents the distance between two points in m-dimensional space, and the QoS attribute value vector of each service is calculated by adopting the weighted Euclidean distance>Distance +.A from user preference QoS attribute value vector A>The expression of the weighted Euclidean distance calculation isMaximum selection of the service with highest similarity S, i.e. +.>Wherein->Representing user QoS preference similarity for the service.
It should be noted that, the resource requester issues the design task, and according to the requirement of the design task ontology model, the resource requester issues the design task instance, extracts task information and directly performs semantic similarity matching with a single cloud service resource in the cloud service pool, if matching is successful, performs task calling to complete the matching process, otherwise, enters the next matching, and the next matching is the matching of the design task and the historical cloud service combination, which is a cloud service combination that has been successfully matched and successfully called in the early stage, and can quickly search for mature resources meeting the requirement. Searching cloud services in a cloud service pool and constructing a new cloud service combination, if the matching fails, calling a service searching and combining program by a system, searching a proper single cloud service from the cloud service pool and combining the single cloud service into a large-granularity service combination to complete a designed task service, and if the task is successfully matched with resources, calling the service and completing the designed task, if the matching fails, judging whether the task is a feature level element task, if the task is an indecipherable feature level element task, indicating that no related resource in the current cloud service pool can meet the requirements of the designed task, if the matching fails, ending the program, and if the current task is not the element task, entering a next task decomposing program.
It should be understood that the design task issued by the resource user needs to be subjected to the flow decomposition of the interactive product design process, so as to reduce the granularity of the design task, facilitate the searching and matching of the cloud service resource in the cloud manufacturing environment, and reduce the resource management overhead. The service with the maximum user QoS preference similarity is selected, because most users have the limitation on professional knowledge and the blindness on performance requirements, the selection is not necessarily long-term, the effective and optimal selection is realized, the service quality context data of the user equipment is the best data reflecting the current state of the user, the service selection of the user preference is combined with the context matching degree, one service meeting the user preference and meeting the device context is recommended to the user, the context data iterates the requirements of each service, then one service with the highest comprehensive satisfaction degree is selected, namely the service meeting the context matching degree of the device and the user preference similarity to the greatest extent is finally bound with the service, and therefore the operation efficiency of cloud service and the reliability of system operation are improved.
Optionally, obtaining the comprehensive satisfaction of the users of the service pool from the target cloud service and constructing the user QoS preference model comprises the following steps:
acquiring a service request, sending the service request to a cloud service adaptation unit and matching corresponding services, wherein the cloud service adaptation unit comprehensively processes the user evaluation information and the context information of the current equipment environment according to the QoS evaluation information stored in a QoS evaluation information table and pushes a cloud service which can meet the personalized preference of the user and accords with the environment context to the user, and the cloud service adaptation unit belongs to a service selection module;
the QoS preference vector is extracted from the previous evaluation information of the user through clustering, the similarity between the service and the QoS preference vector of the user is calculated through weighting Euclidean distance, the context monitoring unit extracts and analyzes the context information of the user equipment to calculate the context matching degree, and the context matching degree is provided for the service meeting the maximum comprehensive evaluation degree, wherein the context monitoring unit belongs to a service selection module.
In this embodiment, pushing a cloud service that can satisfy the personalized preference of the user and meet the environmental context to the user includes: presetting a user behavior matrix as，/>Representing the behavior of user u on service i, in a modelI.e. H is the product of two multidimensional matrices, the transversal quantity H represents the preference degree of the user for each hidden factor, i.e. the evaluation dimension of the service, k represents the number of hidden factors, the column vector F represents the probability distribution of a service on each hidden factor, the user requirement and the service are contacted through the hidden characteristic relation, the information of both the user and the service is fused with the information of the implicit feedback, and the information is mapped to a multidimensional space in a joint way.
It should be noted that, cloud services pay attention to personal experience of users and dynamic adaptation of the system, and the system is required to actively perceive QoS requirements of users on services and select satisfactory services by using the requirements. Because of lack and limitation of professional awareness, it is difficult for most users to give accurate and detailed QoS requirement information of services in the environment, and it is relatively easy to obtain an overall rating according to the usage experience of the service at ordinary times. The service evaluation is a collection of various service attributes, including service reliability, service performance and the like, and can objectively reflect comprehensive evaluation of various qualities of the service by a user or an organization. Through a QoS preference information learning model of user evaluation, qoS information contained in user service evaluation is adopted to generate user preference constraint information, and different user preference can be obtained by different user evaluation.
Optionally, obtaining a design task of the resource ontology model and carrying out service encapsulation on the design resource to form a cloud service, and identifying a comprehensive performance index of the cloud service to obtain a cloud service pool, including:
the resource ontology model comprises an ontology, a concept and an attribute, wherein the ontology is used for expressing objects of tasks or parameters of the objects, the concept is used for expressing contents related to the objects in a collective manner, the attribute is used for expressing the relationship between the concept or the concept and characters and numerical values, and the expression of the ontology model for designing the resource is constructed by adopting a binary algorithm and is thatWherein R represents an ontology model, and the family represents the whole resource, the individual resource or the resource parameter according to the difference of the representation levels; c represents the concept of ontology, using the set to express design resources or parameter information thereof; />Representing attributes related to concepts in the resource, representing relationships between the concepts;
constructing a multi-granularity and multi-layer design resource ontology model through a binary group algorithm and different concepts and attribute sets, wherein the aggregate expression of an ontology model binary group object is as followsWherein i represents the number of concepts contained in the ontology; />Representing the ith concept of ontology, +.>Representing a bodyProperty of the i-th concept itself, +.>Representing the attribute relationship between the i-th and j-th concepts in the topic.
In this embodiment, when the user selects the cloud service suitable for the user, a large number of individual performance indexes are often too complicated for the user to make a reasonable judgment, so that the comprehensive influence of different indexes on the user's service selection is considered in the performance indexes. Identifying the comprehensive performance index of the cloud service to obtain a cloud service pool, comprising: the expression for presetting the comprehensive index CM to reflect the comprehensive performance of different cloud services is thatWherein->Comprehensive performance value of a certain cloud service representing the ith cloud platform,/for>Weight indicating j-th performance index value of cloud service,/->Represents the maximum value of the j-th performance index in all cloud platforms,/for>Representing the minimum value of the jth performance index in all cloud platforms,/for>The j-th performance index value of the cloud service on the i-th cloud platform is represented, N represents the combination of all performance indexes of a certain cloud service participating in calculation, and the j-th performance index value is represented by the combination of +.>Normalized to +.>Space, the larger the value of CM, cloud clothesThe better the overall performance of the business. The service processing time is selected to represent the recognition speed, the request error rate is used for checking the important index of cloud service availability and stability, the value of the important index is the ratio of the number of failed requests to the total number of user requests, the successful request means that the user sends the recognition request, and the cloud platform can successfully call the corresponding processing recognition program according to the request requirement and return the result to the user.
Optionally, accessing the design resource according to the resource type and constructing a resource ontology model corresponding to the resource type, including:
acquiring historical data of design resource completion to establish an evaluation variable of the design resource, wherein the evaluation variable comprises a design maturity coefficient, a design success rate coefficient and a design stability coefficient, the completion condition of the design task reflects the maturity condition of the design resource, and the design maturity coefficient is establishedThe expression of (2) is +.>Wherein M represents the number of times the design resource performs the design task, < ->Representing the number of times a resource has completed a design task, M and +.>All give the initial value to be 1, obtain the coefficient initial value of the design maturity to be 1;
the design times of successfully completing the design task reflect the design capability of the design resource, and a design success rate coefficient is establishedThe expression of (2) is +.>Wherein M represents the number of times the design resource performs a task, < +.>Representation of the resourceThe number of times the source successfully completes the design task, M and +.>All give the initial value to be 1, get the initial value of the coefficient of success rate of design to be 1;
if the time for completing the design task is closer, the stability of the design resource is higher, the probability that the design task can be completed on time is higher when the resource user invokes the resource, and the proportional mean square error is establishedThe expression of (2) isWherein M represents the number of times the design resource performs a task, < >>Indicating the time of use of the resource for the ith execution of the design task,/->Representing the average time spent of m execution of design tasks by a resource, proportional mean square error +.>Reflecting the degree of difference in design when performing multiple design tasks.
In this embodiment, the evaluation variables further include experience degree coefficient, evaluation index and cost index of the design resource, the total number of times the resource participates in the design reflects experience degree that the resource can contain, and the expression of the experience degree coefficient is established asWherein M represents the number of times the designed resource performs the task, and when the resource is called for the first time, an initial value M=1 and an experience coefficient are given to the designed resource>A value of 0 indicates that the design resource does not participate in the design at present; the expression of the evaluation index E using the average of the quality scores in QoS user evaluation as the design resource is/>Wherein M represents the number of times the design resource performs a task, < +.>Representing an ith user quality rating score for the resource; the design cost is reflected in both the man-hour cost and the design time, and the expression of the design resource cost index D is established as +.>Wherein M represents the number of times the design resource performs a task, < +.>Representing the i-th design time of a resource, < + >>Representing the man-hour price of the ith design of the resource.
It should be noted that, obtaining a resource type in the design resource, accessing the design resource according to the resource type and constructing a resource ontology model corresponding to the resource type, including: the dynamic capacity resource is accessed, wherein the dynamic capacity resource comprises program type resources and human resources, is accessed in a man-machine interaction mode, is driven by a designer, automatically accesses the program resources by using a fixed input/output interface, and is automatically driven by a system; and the static entity resources comprise offline resources and mobile equipment, and the required resources are perceived and accessed through human resources to realize offline perception of the resources, so that the non-online management of the resources is completed. After a certain design activity is performed on the design resource, design history data and user evaluation information are generated in a resource database, and the data are true manifestations of the resource design capability. The method for determining reasonable evaluation variables and extracting information reflecting the resource design capability from mass data is a key for comprehensively evaluating the design resources. The service times, the times of completing design tasks, the times of achieving user acceptance standards, the duration time of each task and other design history data are selected as the basis for establishing evaluation variables, so that the matching accuracy of resources and services is improved.
Referring to fig. 2, the invention further provides a self-research intelligent product operation method for cloud service, comprising the following steps:
s1: acquiring a resource type in a design resource, accessing the design resource according to the resource type, and constructing a resource ontology model corresponding to the resource type, wherein the resource type comprises a static entity resource and a dynamic capacity resource;
s2: acquiring a design task of a resource ontology model, carrying out service encapsulation on the design resource to form cloud service, and identifying comprehensive performance indexes of the cloud service to obtain a cloud service pool;
s3: acquiring comprehensive user satisfaction of a service pool from the target cloud service, constructing a user QoS preference model, and selecting the maximum user QoS preference similarity in the user QoS model to determine the target cloud service;
s4: and binding and executing the target cloud service and the design task to complete the self-research intelligent product operation of the target cloud service.
In this embodiment, a resource type in a design resource is obtained, the design resource is accessed according to the resource type, a resource ontology model corresponding to the resource type is constructed, a design task of the resource ontology model is obtained, the design resource is subjected to service encapsulation to form cloud service, a comprehensive performance index of the cloud service is identified to obtain a cloud service pool, a comprehensive user satisfaction degree of the service pool is obtained from a target cloud service, a user QoS preference model is constructed, the maximum user QoS preference similarity in the user QoS model is selected to determine the target cloud service, the target cloud service and the design task are bound and executed to complete self-research intelligent product operation of the target cloud service, the design task and the service resource are subjected to similarity matching and cloud service quality recommendation are combined to promote service quality of the cloud service, and interaction conditions of users on service evaluation are fused, so that service description of the resource is realized, and meanwhile, operation efficiency of the cloud service is also promoted.
Any particular values in all examples shown and described herein are to be construed as merely illustrative and not a limitation, and thus other examples of exemplary embodiments may have different values.
It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures.
The above examples merely represent a few embodiments of the present invention, which are described in more detail and are not to be construed as limiting the scope of the present invention. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the invention, which are all within the scope of the invention.
Claims (10)
1. A self-research intelligent product operation system for cloud services, comprising:
the resource acquisition module is used for acquiring the resource type in the design resource, accessing the design resource according to the resource type and constructing a resource ontology model corresponding to the resource type, wherein the resource type comprises a static entity resource and a dynamic capacity resource;
the service building module is used for obtaining the design task of the resource ontology model and carrying out service encapsulation on the design resource to form cloud service, and identifying the comprehensive performance index of the cloud service to obtain a cloud service pool;
the service selection module is used for acquiring the comprehensive satisfaction degree of the users of the service pool from the target cloud service, constructing a user QoS preference model, and selecting the maximum user QoS preference similarity in the user QoS model to determine the target cloud service;
and the service execution module is used for binding and executing the target cloud service and the design task to complete the self-research intelligent product operation of the target cloud service.
2. The self-developed intelligent product operation system for cloud services of claim 1, wherein selecting a maximum user QoS preference similarity in a user QoS model to determine a target cloud service comprises:
the Euclidean distance is adopted to calculate the preference similarity of the user, and when the user puts forward or the system senses the service request of the user, the service request semantic is matched with a group of candidate services with the same functionality from the target cloud serviceIf each candidate service contains m QoS attribute values +.>Different QoS attribute values represent the performance requirements of different services, and m attribute values of n services are constructed into one +.>Is>Describing QoS attribute values corresponding to each service;
each QoS attribute value is weighted, the higher the weight the greater the importance,represents m QoS attribute values +.>The Euclidean distance represents the distance between two points in m-dimensional space, and the QoS attribute value vector of each service is calculated by adopting the weighted Euclidean distance>Distance +.A from user preference QoS attribute value vector A>The expression of the weighted Euclidean distance calculation isAccording to the use ofThe user preference selects the service with the highest similarity S, i.e. +.>Wherein->Representing user QoS preference similarity for the service.
3. The self-research intelligent product operation system for cloud services of claim 1, wherein obtaining user integrated satisfaction of a service pool from a target cloud service and constructing a user QoS preference model comprises:
acquiring a service request, sending the service request to a cloud service adaptation unit and matching corresponding services, wherein the cloud service adaptation unit comprehensively processes the user evaluation information and the context information of the current equipment environment according to the QoS evaluation information stored in a QoS evaluation information table and pushes a cloud service which can meet the personalized preference of the user and accords with the environment context to the user, and the cloud service adaptation unit belongs to a service selection module;
the QoS preference vector is extracted from the previous evaluation information of the user through clustering, the similarity between the service and the QoS preference vector of the user is calculated through weighting Euclidean distance, the context monitoring unit extracts and analyzes the context information of the user equipment to calculate the context matching degree, and the context matching degree is provided for the service meeting the maximum comprehensive evaluation degree, wherein the context monitoring unit belongs to a service selection module.
4. The self-research intelligent product operation system for cloud services as claimed in claim 3, wherein pushing a cloud service to the user that satisfies user personalized preferences and meets environmental context comprises:
presetting a user behavior matrix as，/>Representing the behaviour of user u on service i, in model +.>I.e. H is the product of two multidimensional matrices, the transversal quantity H represents the preference degree of the user for each hidden factor, i.e. the evaluation dimension of the service, k represents the number of hidden factors, the column vector F represents the probability distribution of a service on each hidden factor, the user requirement and the service are contacted through the hidden characteristic relation, the information of both the user and the service is fused with the information of the implicit feedback, and the information is mapped to a multidimensional space in a joint way.
5. The system of claim 1, wherein the steps of obtaining the design task of the resource ontology model and performing service packaging on the design resource to form the cloud service, and identifying the comprehensive performance index of the cloud service to obtain the cloud service pool comprise:
the resource ontology model comprises an ontology, a concept and an attribute, wherein the ontology is used for expressing objects of tasks or parameters of the objects, the concept is used for expressing contents related to the objects in a collective manner, the attribute is used for expressing the relationship between the concept or the concept and characters and numerical values, and the expression of the ontology model for designing the resource is constructed by adopting a binary algorithm and is thatWherein R represents an ontology model, and the family represents the whole resource, the individual resource or the resource parameter according to the difference of the representation levels; c represents the concept of ontology, using the set to express design resources or parameter information thereof; />Representing attributes related to concepts in the resource, representing relationships between the concepts;
constructing a multi-granularity and multi-layer design resource ontology model through a binary group algorithm and different concepts and attribute sets, wherein the aggregate expression of an ontology model binary group object is as followsWherein i represents the number of concepts contained in the ontology; />Representing the ith concept of ontology, +.>Property representing the i-th concept itself in the ontology, < +.>Representing the attribute relationship between the i-th and j-th concepts in the topic.
6. The self-research intelligent product operation system for cloud services of claim 5, wherein identifying the comprehensive performance metrics of the cloud services to obtain a cloud service pool comprises:
the expression for presetting the comprehensive index CM to reflect the comprehensive performance of different cloud services is thatWherein->Comprehensive performance value of a certain cloud service representing the ith cloud platform,/for>Weight indicating j-th performance index value of cloud service,/->Represents the maximum value of the j-th performance index in all cloud platforms,/for>Representing the minimum value of the jth performance index in all cloud platforms,/for>The j-th performance index value of the cloud service on the i-th cloud platform is represented, N represents the combination of all performance indexes of a certain cloud service participating in calculation, and the j-th performance index value is represented by the combination of +.>Normalized to +.>The larger the value of CM, the better the overall performance of the cloud service.
7. The system for cloud services as claimed in claim 1, wherein the method for accessing design resources according to resource types and constructing resource ontology models corresponding to the resource types comprises:
acquiring historical data of design resource completion to establish an evaluation variable of the design resource, wherein the evaluation variable comprises a design maturity coefficient, a design success rate coefficient and a design stability coefficient, the completion condition of the design task reflects the maturity condition of the design resource, and the design maturity coefficient is establishedThe expression of (2) is +.>Wherein M represents the number of times the design resource performs the design task, < ->Representing the number of times a resource has completed a design task, M and +.>All give the initial value to be 1, obtain the coefficient initial value of the design maturity to be 1;
the design times of successfully completing the design task reflect the design capability of the design resource, and a design success rate coefficient is establishedThe expression of (2) is +.>Wherein M represents the number of times the design resource performs a task, < +.>Representing the number of times the resource successfully completes the design task, M and +.>All give the initial value to be 1, get the initial value of the coefficient of success rate of design to be 1;
if the time for completing the design task is closer, the stability of the design resource is higher, the probability that the design task can be completed on time is higher when the resource user invokes the resource, and the proportional mean square error is establishedThe expression of (2) isWherein M represents the number of times the design resource performs a task, < >>Indicating the time of use of the resource for the ith execution of the design task,/->Representing the average time spent of m execution of design tasks by a resource, proportional mean square error +.>Reflecting the degree of difference in design when performing multiple design tasks.
8. The self-research intelligent product operation system for cloud services of claim 7, wherein the evaluation variablesThe method also comprises the steps of designing experience coefficients, evaluation indexes and cost indexes of the resources, wherein the total number of the resources participating in the design reflects the experience that the resources can contain, and the expression of the experience coefficients is established asWherein M represents the number of times the designed resource performs the task, and when the resource is called for the first time, an initial value M=1 and an experience coefficient are given to the designed resource>A value of 0 indicates that the design resource does not participate in the design at present;
the expression of the evaluation index E using the average of the quality scores in QoS user evaluation as the design resource isWherein M represents the number of times the design resource performs a task, < +.>Representing an ith user quality rating score for the resource;
the design cost is reflected in both the man-hour cost and the design time, and the expression of the design resource cost index D is established asWherein M represents the number of times the design resource performs a task, < +.>Representing the i-th design time of a resource, < + >>Representing the man-hour price of the ith design of the resource.
9. The system of claim 1, wherein the obtaining the resource type in the design resource, accessing the design resource according to the resource type and constructing the resource ontology model corresponding to the resource type comprises:
the dynamic capacity resource is accessed, wherein the dynamic capacity resource comprises program type resources and human resources, is accessed in a man-machine interaction mode, is driven by a designer, automatically accesses the program resources by using a fixed input/output interface, and is automatically driven by a system;
and the static entity resources comprise offline resources and mobile equipment, and the required resources are perceived and accessed through human resources to realize offline perception of the resources, so that the non-online management of the resources is completed.
10. A self-grinding intelligent product operation method for cloud service according to any one of claims 1-9, characterized by comprising the steps of:
acquiring a resource type in a design resource, accessing the design resource according to the resource type, and constructing a resource ontology model corresponding to the resource type, wherein the resource type comprises a static entity resource and a dynamic capacity resource;
acquiring a design task of a resource ontology model, carrying out service encapsulation on the design resource to form cloud service, and identifying comprehensive performance indexes of the cloud service to obtain a cloud service pool;
acquiring comprehensive user satisfaction of a service pool from the target cloud service, constructing a user QoS preference model, and selecting the maximum user QoS preference similarity in the user QoS model to determine the target cloud service;
and binding and executing the target cloud service and the design task to complete the self-research intelligent product operation of the target cloud service.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310762038.1A CN116502102A (en) | 2023-06-27 | 2023-06-27 | Self-research intelligent product operation system and method for cloud service |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310762038.1A CN116502102A (en) | 2023-06-27 | 2023-06-27 | Self-research intelligent product operation system and method for cloud service |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116502102A true CN116502102A (en) | 2023-07-28 |
Family
ID=87320575
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310762038.1A Pending CN116502102A (en) | 2023-06-27 | 2023-06-27 | Self-research intelligent product operation system and method for cloud service |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116502102A (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106570080A (en) * | 2016-10-18 | 2017-04-19 | 河海大学常州校区 | Multilevel semantic matching method for cloud manufacturing resource services |
-
2023
- 2023-06-27 CN CN202310762038.1A patent/CN116502102A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106570080A (en) * | 2016-10-18 | 2017-04-19 | 河海大学常州校区 | Multilevel semantic matching method for cloud manufacturing resource services |
Non-Patent Citations (4)
| Title |
|---|
| 丁淑辉: "云制造下多粒度设计资源服务化方法与匹配策略研究", 《中国博士学位论文全文数据库》, pages 37 - 124 * |
| 李镇邦: "面向移动云计算的上下文自适应服务选择方法研究", 《中国优秀硕士学位论文全文数据库》, pages 21 - 38 * |
| 范国庆: "基于QoS的云制造服务推荐方法", 《中国优秀硕士学位论文全文数据库》, pages 22 - 23 * |
| 薛玉磊: "图像识别云服务自动测试系统设计与实现", 《中国优秀硕士学位论文全文数据库》, pages 20 - 22 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11321759B2 (en) | Method, computer program product and system for enabling personalized recommendations using intelligent dialog | |
| CN114721833B (en) | Intelligent cloud coordination method and device based on platform service type | |
| Ouadah et al. | SEFAP: an efficient approach for ranking skyline web services | |
| CN109299245B (en) | Method and device for recalling knowledge points | |
| CN111489095A (en) | Risk user management method and device, computer equipment and storage medium | |
| CN111061831A (en) | Method and device for switching machine customer service to manual customer service and electronic equipment | |
| US20200193330A1 (en) | Method and system for using existing models in connection with new model development | |
| CN105808590A (en) | Search engine realization method as well as search method and apparatus | |
| US20200402080A1 (en) | Method of selecting questions for respondents in a respondent-interrogator system | |
| CN113742492B (en) | Insurance scheme generation method and device, electronic equipment and storage medium | |
| CN111340148A (en) | Training method of business classification model, business classification method and terminal | |
| CN113312468B (en) | Conversation mode-based conversation recommendation method, device, equipment and medium | |
| KR101450453B1 (en) | Method and apparatus for recommending contents | |
| Shi et al. | Maximizing User Experience with LLMOps-Driven Personalized Recommendation Systems | |
| Özerol et al. | A parallel between regret theory and outranking methods for multicriteria decision making under imprecise information | |
| CN107851263B (en) | Method for processing recommendation request and recommendation engine | |
| CN111382232A (en) | Question and answer information processing method and device and computer equipment | |
| CN116502102A (en) | Self-research intelligent product operation system and method for cloud service | |
| CN114169418B (en) | Label recommendation model training method and device and label acquisition method and device | |
| CN115600818A (en) | Multi-dimensional scoring method and device, electronic equipment and storage medium | |
| CN109002498A (en) | Interactive method, device, equipment and storage medium | |
| TWI419071B (en) | Active knowledge management system, method and computer program product for problem solving | |
| CN114900556B (en) | Cloud interconnection method and system based on service preference learning in multi-cloud heterogeneous environment | |
| CN117668205B (en) | Smart logistics customer service processing method, system, equipment and storage medium | |
| CN117495512B (en) | Order data management method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20230728 |