CN109800249B - Knowledge service method and system based on industrial service cloud platform user behavior awareness - Google Patents
Knowledge service method and system based on industrial service cloud platform user behavior awareness Download PDFInfo
- Publication number
- CN109800249B CN109800249B CN201811582979.2A CN201811582979A CN109800249B CN 109800249 B CN109800249 B CN 109800249B CN 201811582979 A CN201811582979 A CN 201811582979A CN 109800249 B CN109800249 B CN 109800249B
- Authority
- CN
- China
- Prior art keywords
- knowledge
- user
- service
- resources
- personalized
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000004519 manufacturing process Methods 0.000 claims abstract description 39
- 230000000694 effects Effects 0.000 claims abstract description 14
- 230000006399 behavior Effects 0.000 claims description 75
- 238000004364 calculation method Methods 0.000 claims description 14
- 230000008859 change Effects 0.000 claims description 10
- 230000008447 perception Effects 0.000 claims description 7
- 230000003068 static effect Effects 0.000 claims description 7
- 230000006870 function Effects 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 4
- 238000005562 fading Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 238000007619 statistical method Methods 0.000 claims description 3
- 201000004569 Blindness Diseases 0.000 abstract description 2
- 238000011156 evaluation Methods 0.000 description 9
- 238000004458 analytical method Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 7
- 238000011160 research Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 230000003993 interaction Effects 0.000 description 3
- 238000013461 design Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009960 carding Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000006798 recombination Effects 0.000 description 1
- 238000005215 recombination Methods 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
Classifications
-
- 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
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to a knowledge service method and system based on industrial service cloud platform user behavior awareness. The method comprises the following steps: 1) The knowledge resources in the industrial service cloud platform are uniformly described through the ontology, so that the structural and semantic isomerism of different knowledge resources is eliminated; 2) Acquiring personalized knowledge requirements of a user according to business activities of the user in an industrial service cloud platform, and establishing a user personalized model according to the personalized knowledge requirements of the user; 3) Based on the established user personalized model, knowledge resources meeting the user personalized knowledge requirements are obtained by retrieving the knowledge resources of the industrial service cloud platform. The invention can provide personalized intelligent knowledge service perceived by user behavior for various large, medium and small industrial manufacturing enterprises of the industrial Internet, can greatly reduce blindness of searching knowledge resources for users, and provides required knowledge resources for users rapidly.
Description
Technical Field
The invention belongs to the technical field of information technology and knowledge service, and particularly relates to a knowledge service method and system based on perception of user behaviors of an industrial service cloud platform.
Background
Along with the rapid development of information technologies such as cloud computing, cloud manufacturing, internet of things, big data and the like and the rising of the Internet and traditional industrial manufacturing industry, information, data and knowledge resources generated by industrial enterprises in full life cycle business activities are rapidly increased, and the intelligent manufacturing resources are various and huge in quantity. How to provide valuable knowledge resource service for users accurately and rapidly is a big problem to be solved for improving the intellectual making service capability of industrial enterprises.
Research shows that the behavior of a user in a mobile network can be influenced by a plurality of subtle factors, and the behavior, the emotion, the knowledge service requirement and the like of the user can be analyzed, modeled and predicted through the behavior track of the user in a big data mobile environment and the dynamic change of the social relationship of the user in the network. The information service mechanism is helped to sense the knowledge service market, sense the user requirement and capability, sense the future development situation and the like after relevant data such as the character, the preference, the willingness and the like of the user are directly and truly displayed through analyzing the footprint, the click history, the browsing history and the information feedback of the user in the big data mobile environment, so that the information service mechanism makes more scientific decisions on value evaluation, service capability, service level and the like, and recommends more proper information.
Although the popularization and application of the knowledge cloud service technology have advanced to a certain extent, many group enterprises have managed and uniformly displayed knowledge resources in groups in a centralized manner, and knowledge centralized sharing is primarily realized, research on personalized service modes by most of knowledge service products on the market is still less, platform users are difficult to acquire required resources in massive knowledge data, service providers lack knowledge of service requesters, knowledge service is difficult to provide in a targeted manner, and service operators are difficult to know invisible requirements of the users. Most of the knowledge service products have the problems of knowledge management, no use, low utilization rate, poor personalized knowledge service capability and the like, and have lower popularization strength, low initiative of user enthusiasm and different service demands of different types of users in the application and implementation process. The existing technology provides two knowledge service modes, namely a static knowledge service mode and a dynamic knowledge service mode, aiming at the requirements and the characteristics of the knowledge service of the cloud manufacturing platform, but does not consider a personalized knowledge service mode based on user behaviors. Therefore, personalized services can be provided for different users in the industrial Internet platform, and the key of knowledge service capability is formed.
At present, the research on the knowledge service is mainly regarded as an important content under a cloud manufacturing platform, the active creation value of the knowledge service is not exerted, and the deep research on cloud manufacturing and intelligent manufacturing cannot be supported forcefully. If the user demands can be comprehensively considered, a more perfect method or technology is applied to provide the knowledge service, the content of the cloud manufacturing service research can be perfected, the connotation of the cloud manufacturing service research can be expanded, the intelligent level of the manufacturing process can be further improved, and intelligent decisions can be provided for the production process.
Disclosure of Invention
The good personalized knowledge service can enable the user to have dependence on the platform, the viscosity of the user is improved, and meanwhile the service platform can also know the interests and the demands of the user. Compared with other internet platforms, the industrial internet cloud manufacturing service platform has strong professionals and territories and can cover the full life cycle of industrial products. The users are more in variety and different in demand, and are less influenced by time and place factors. Aiming at the problems, the invention performs enterprise knowledge service analysis in an industrial Internet environment on the basis of the prior art, establishes a user personalized interest model, realizes personalized knowledge service by knowledge expression based on an ontology and user behavior evaluation, and provides active, intelligent and personalized knowledge resources for users.
The knowledge service method based on user behavior perception under the industrial service cloud platform is based on the knowledge service platform with strong resource integration capability, massive information analysis capability and data mining capability, is driven by taking the trend and the intention of user demands as targets and is oriented to the knowledge content and problem solving process, provides a value added service for problem solving decision, and provides application level knowledge cloud service based on user behavior perception, high scale and modularization.
The key point of the invention is that the knowledge demand of the user can be acquired by utilizing the user behavior analysis model, so that knowledge service in a cloud environment can be accurately provided for the industrial manufacturing industry user, the efficiency of searching and knowledge acquisition is improved, and meanwhile, personalized service throughout the whole life cycle of product manufacturing is provided.
The technical scheme adopted by the invention is as follows:
a knowledge service method based on industrial service cloud platform user behavior awareness comprises the following steps:
1) The knowledge resources in the industrial service cloud platform are uniformly described through the ontology, so that the structural and semantic isomerism of different knowledge resources is eliminated;
2) Acquiring personalized knowledge requirements of a user according to business activities of the user in an industrial service cloud platform, and establishing a user personalized model according to the personalized knowledge requirements of the user;
3) Based on the established user personalized model, knowledge resources meeting the user personalized knowledge requirements are obtained by retrieving the knowledge resources of the industrial service cloud platform.
Further, the knowledge resources comprise static knowledge resources and dynamic knowledge resources, wherein the static knowledge resources mainly refer to document knowledge resources, and the dynamic knowledge resources mainly refer to knowledge resources which can be dynamically invoked and are formed by encapsulating tools and methods.
Further, step 2) obtains relevant information capable of reflecting the personalized knowledge requirement of the user according to the business activity of the user in the industrial service cloud platform, including: user basic information, user behavior information and user service information; the user basic information comprises user professions, units, departments and education backgrounds, and the user basic information is filled in when the user registers a cloud manufacturing platform; the user behavior information comprises direct behaviors and indirect behaviors, wherein the direct behaviors comprise service scoring, service collection, service subscription and service recommendation; the user service information is service content provided by a user to the platform and service content required to be acquired from the platform, and comprises service names, belonging fields, keywords, function descriptions, time effectiveness, service transaction history records and service transaction user associated users.
Further, step 2) describes the requirement level of the user on the knowledge resource by adopting the knowledge requirement level; the knowledge demand level comprises a knowledge attention level and a knowledge value level; the knowledge attention is described from the perspective of the operation behavior of the user on the knowledge, and reflects the attention of the user on the knowledge resource; the knowledge value reflects the knowledge quality by subjectively evaluating the value of the knowledge resource by the user.
Further, knowledge browsing, knowledge downloading, knowledge clicking, knowledge recommending, knowledge collecting and knowledge subscribing behaviors in the knowledge attention degree are quantified through statistical calculation, the knowledge comment and knowledge question-answering behaviors comprise positive and negative user requirements, positive comments and answers reflect positive and attention of a user to the knowledge resource, and negative comments and answer reactions reflect negative of the user to the knowledge resource; the knowledge value is scored from four aspects of knowledge resource availability, relevance, innovation and readability.
Further, step 3) sets a corresponding threshold value for the knowledge demand level as a condition for filtering the knowledge resources, thereby providing the high-quality knowledge resources required by the user to the user.
Further, the method further comprises a step of updating the user personalized model, wherein the updating is performed by combining the content of the user behavior and the knowledge resource and considering the time factor, and comprises the following steps:
a) Aiming at knowledge services actively provided by an industrial service cloud platform for users, after the users view and use knowledge resources, the knowledge behaviors of the users are counted, the satisfaction degree of the users on the knowledge resources provided by the platform is obtained through calculation, the change of personal knowledge demands is judged, knowledge concepts which do not meet a set knowledge demand degree threshold are deleted, otherwise, knowledge concept sets, attribute sets and relationship sets are combined, and a user personalized model is updated to form a new concept set;
b) Aiming at the knowledge behavior of a user in an industrial service cloud platform, acquiring new knowledge demands of the user through statistical analysis, acquiring a characteristic word set through word segmentation processing aiming at new knowledge resources possibly needed by the user, merging with an original word set, and updating a user model;
c) Aiming at the problems that the user demands can decay and change along with the time, the requirements of fading and forgetting are deleted through the calculation of the concept demand degree.
Further, the user of the industrial service cloud platform realizes interaction with the platform through various terminal devices, including registering personal information, acquiring manufacturing service, and providing manufacturing service and knowledge resources for the platform; the industrial service cloud platform provides intelligent and active knowledge service for users through behaviors and knowledge requirements of the users.
A knowledge service system based on industrial service cloud platform user behavior awareness, comprising:
the knowledge resource unified description module is responsible for carrying out unified description on knowledge resources in the industrial service cloud platform through the ontology, and eliminating the isomerism of different knowledge resources in structure and semantics;
the user personalized model building module is in charge of acquiring personalized knowledge requirements of the user according to business activities of the user in the industrial service cloud platform and building a user personalized model according to the personalized knowledge requirements of the user;
the knowledge resource acquisition module is responsible for acquiring knowledge resources meeting the personalized knowledge requirements of the user by searching the knowledge resources of the industrial service cloud platform based on the established personalized user model.
The beneficial effects of the invention are as follows:
the invention constructs a personalized knowledge service framework aiming at the industrial cloud manufacturing environment, comprehensively evaluates the explicit behavior and implicit behavior of the user through analyzing the behavior of the user of the platform, calculates the personalized knowledge demand of each user, establishes a personalized knowledge service flow based on a user behavior analysis model, and modularizes the knowledge service so that the user can acquire the personalized knowledge resource from the network platform efficiently and conveniently.
The invention can provide personalized intelligent knowledge service perceived by user behavior for various large, medium and small industrial manufacturing enterprises of the industrial Internet, can greatly reduce blindness of searching knowledge resources for users, rapidly provide required knowledge resources for users, improve efficiency, realize service and collaboration by a patent technology method, thereby embodying personalized intelligent characteristics of knowledge service.
Drawings
FIG. 1 is a schematic diagram of a knowledge service platform architecture.
Fig. 2 is a schematic diagram of user model information.
Fig. 3 is a schematic diagram of a user behavior evaluation index.
FIG. 4 is a flow chart for personalized knowledge extraction based on user behavior.
Fig. 5 is a diagram of a personalized user model.
FIG. 6 is a flow chart for user behavior personalization model update.
Description of the embodiments
The present invention will be further described in detail with reference to the following examples and drawings, so that the above objects, features and advantages of the present invention can be more clearly understood.
Knowledge service based on user behavior perception under an industrial service cloud platform focuses on solving the problem of knowledge resource demand of a user by providing service, and very important to analyze the demand of the user, determining the demand of the user according to the problem and the problem environment, forming a knowledge product just meeting the demand through extraction and recombination of information, and providing service based on logic acquisition. Knowledge services are services that traverse the process of solving problems for users, and that traverse the process of capturing, analyzing, reorganizing, and applying knowledge for users, and dynamically and continuously organize services according to the needs of users. The information behavior of the user is in dynamic change, and as the external factors such as environment and the like are changed and the problem of the user demand is solved continuously, the factors influencing the information demand are changed. The change of the user's demand makes the scheme of knowing the service adjust accordingly, solve better according to the characteristic and change of the user's information activity.
1. Knowledge service platform functional structure
The cloud manufacturing platform service relates to the full life cycle business activity of the product, and knowledge resources in the platform comprise a plurality of types of standard specifications, patent information, document knowledge, expert experience, model knowledge, experience data and the like related to the manufacturing field. By unified modeling of knowledge resources, knowledge services are provided for platform users, and personalized knowledge service functional structures in a cloud manufacturing environment are shown in fig. 1.
(1) Knowledge resource of industrial service cloud platform
Knowledge service types in an industrial service cloud platform are mainly divided into two types of knowledge resources, namely static knowledge resources and dynamic knowledge resources. The static knowledge resource mainly refers to document knowledge resource, and the dynamic knowledge resource mainly refers to knowledge resource which is formed by encapsulating tools and methods and can be dynamically called. The knowledge resources are uniformly described through the ontology, so that the heterogeneous problem of different knowledge resources in structure and semantics can be solved. The term "ontology" refers to a formalized representation of a set of concepts and their relationships to each other within a particular domain. The term "unified description" refers to the unified semantic description of knowledge resources without semantics.
(2) Personalized knowledge demand acquisition
In the industrial service cloud platform, a user can conduct business activities of all stages of the whole life cycle of a product, and business activities borne by the user are different, so that the user has different knowledge requirements and corresponds to different user models. The knowledge requirement of the user is influenced by information such as industry, field, unit, specialty and the like, the business requirement of the user and the like. Thus, a user personalization model is built by capturing the user's business activities (including system usage logs) and personal roles in the platform to capture the user's personalized knowledge needs.
(3) Personalized knowledge filtering
Based on the user personalized model and knowledge requirements, knowledge resources meeting the requirements are obtained through knowledge retrieval. Because the industrial service cloud platform has huge knowledge resources and uneven knowledge resource quality, the knowledge resources with high quality, which are needed by users, are filtered and ordered by introducing knowledge evaluation, and are provided for the users.
(4) Platform interaction
The industrial service cloud platform user realizes interaction with the platform through various terminal devices, the user registers personal information through the platform and acquires manufacturing service, manufacturing service and knowledge resources can be provided for the platform, and the platform provides intelligent and active knowledge service for the user through personal system behaviors and knowledge requirements.
2. User behavior analysis
1. User behavior classification
In the cloud manufacturing platform, users have a variety of behavior information such as types of service search, service call, service evaluation, and service transaction. In order to comprehensively acquire the knowledge demands of users, a system user model is built through three layers of user basic information, user behavior information and user service information. By comprehensive analysis, the relevant information capable of reflecting the knowledge needs of the user is summarized as shown in fig. 2.
(1) User basic information
Personal information including user professions, units, departments, educational backgrounds, etc., is filled in when the user registers with the cloud manufacturing platform.
(2) User behavior information
The system behavior capable of directly or indirectly reflecting the knowledge demands of the user comprises service scoring, service collection, service recommendation, service retrieval, service comment, service downloading, service browsing, service uploading, service clicking and the like, wherein the service scoring, the service collection, the service subscription and the service recommendation belong to the behavior which directly reflects the knowledge demands of the user in the operation behavior of the user and are called direct behavior. Other operational behaviors pertain to indirect behaviors, such as mining user-related service combinations and associated user information in a cloud manufacturing environment by data analysis of service usage data (service browsing, service clicking, etc.) accumulated in the platform.
(3) User service information
The platform user provides service contents to the platform and service contents required to be acquired from the platform, and mainly refers to dynamic knowledge service, wherein basic attributes of the provided or acquired service include service names, belonging fields, keywords, function descriptions, time validity, service transaction histories, service transaction user associated users and the like, the service transaction histories and the service transaction associated users are important contents of a user information model, and are direct data sources for establishing relations among cloud manufacturing platform users.
2. User behavior assessment
The user basic information and the user service information in the user model information are stored in a database table, corresponding knowledge demand conceptual terms, such as key words of service, function description, professions of users, departments and the like, can be obtained by directly reading the related database table, and the user knowledge demands can be obtained by ontology searching and semantic expansion. In order to provide knowledge resources with urgent needs and high quality for users, the invention provides a concept of knowledge demand level for describing the demand level of the users on the knowledge resources.
The knowledge demand level includes a knowledge attention level and a knowledge value level. Knowledge attention is described from the perspective of the operation behavior of the user on the knowledge, and the attention of the user on knowledge resources is reflected by statistically analyzing implicit behaviors such as scoring, commenting, collecting, subscribing, asking-answering and the like of the user on the knowledge. The knowledge value reflects the quality of knowledge by subjectively evaluating the value of the knowledge resource by a user, and scores the knowledge resource from four aspects of effectiveness, relativity, innovation and readability. Fig. 3 is a schematic diagram of a user behavior evaluation index.
(1) Knowledge attention
Knowledge browsing, knowledge downloading, knowledge clicking, knowledge recommending, knowledge collecting and knowledge subscribing behaviors in knowledge attention degree can be quantified through statistical calculation, the knowledge comment and knowledge question-answering behaviors comprise positive and negative user requirements, positive comments and answers reflect positive and attention of a user to the knowledge resource, and conversely, negative judgment of the user to the knowledge resource is reflected.
(2) Knowledge value degree
The calculation of the knowledge value is obtained through interactive evaluation by a user when browsing knowledge resources, and the knowledge value is evaluated from four indexes of knowledge validity, knowledge relativity, knowledge innovation and knowledge readability. Through the knowledge value evaluation, the feedback of the user to the knowledge resource can be embodied, and then the personalized model of the user is updated and optimized.
Knowledge availability is used to reflect the role and value of the knowledge resource itself; the knowledge correlation is used for reflecting the association degree of the knowledge resource and the user; the knowledge innovation is used for reflecting the innovation degree of knowledge resources and encouraging platform users to carry out knowledge innovation; knowledge readability is used to reflect the clear, reasonable degree of knowledge resources, facilitating the user to provide a high level of knowledge resources. Each index was evaluated in 1-5 points, and the higher the score, the better the index was, and the evaluation rule of each index was as shown in Table 1.
(3) Knowledge demand level
And setting a corresponding threshold value through the calculation of the knowledge demand degree to serve as a condition for filtering the knowledge resources. Firstly, judging whether the knowledge attention degree and the knowledge value degree are larger than a threshold value, and if so, calculating the knowledge demand degree. If the knowledge demand is greater than the threshold, the knowledge resource is marked and stored as the resource possibly needed by the user, and a judgment basis is provided for personalized service, and the calculation flow is shown in fig. 4.
3. Personalized knowledge service demand modeling based on user behavior
1. User personalized model representation
The industrial manufacturing service platform has strong professionals and territories, and covers manufacturing services of the whole life cycle of products, the types of users of the platform are more, the demands are different, and relatively speaking, the demands of the user knowledge have uncertainty and territory professionals. On one hand, the field expertise of the user knowledge requirement under cloud manufacturing is less influenced by factors such as time, place and the like, and is closely related to the service combination of the user service history record and the field life. On the other hand, the service provider lacks knowledge of the service demander, and the platform operator has difficulty in knowing the invisible requirement of the user, which makes the knowledge requirement of the user uncertain. Through user modeling, the knowledge modeling method can be consistent with the knowledge modeling method in the platform, and a foundation is laid for matching, sharing and reusing the knowledge demands of the users and the knowledge services. In addition, the semantic relation of the ontology can be fully exerted by using user personalized knowledge modeling, knowledge service resources required by the user can be rapidly found through semantic expansion when knowledge service is carried out, uncertainty of knowledge requirements of the user in an industrial cloud manufacturing environment is overcome, and further knowledge service efficiency and quality are improved.
The personalized knowledge demand model of the user is obtained through a personalized knowledge modeling method based on the user behavior, as shown in fig. 5. The relationship between classes and subclasses and between classes and instances in the ontology of the user model are given in the figure. As can be seen from the figure, the knowledge demand of the user is biased to concepts such as spacecraft, structural design and parameterized design, and personalized knowledge resources can be provided for the user through the concepts and the relations among the concepts.
2. Personalized model update for user behavior analysis
After the user personalized model reaches maturity and stability through accumulation of user data for a period of time, the user personalized model can accurately express the preference of the user. At this time, the personalized knowledge resources provided by the cloud manufacturing platform can well meet the knowledge demands of users, the time for the users to acquire knowledge services is greatly reduced, the efficiency of the users to quickly locate key knowledge resources is improved, and more importantly, the personalized knowledge resources provided by the platform can better help the users to master related resources meeting the preferences of the users, and the deeper demands of the users are met. Meanwhile, enterprises may encounter the following two difficulties when applying the personalized knowledge service function in the cloud manufacturing platform:
(1) Because of the inertia of platform users, the lack of power and enthusiasm provide services and knowledge to the platform to score, comment and other valuable user behavior operations, so that the user interest model constructed based on the personalized knowledge service technology of user behavior perception cannot deeply characterize the user demands.
(2) The bottleneck of personalized knowledge service under the industrial manufacturing cloud platform is that the quantity of knowledge service which is arranged and released inside an enterprise is limited, so that platform users are further led to 'inertia' of personalized knowledge service functions of an enterprise application platform, and the enrichment of a knowledge base is greatly influenced by objective factors such as enterprise scale, leading importance degree, employee knowledge contribution willingness and the like.
The invention combines the content of user behavior and knowledge resources, and simultaneously considers time factors, and establishes a comprehensive user model updating method, wherein the model updating flow is shown in figure 6, and comprises the following steps:
(1) And counting knowledge behaviors of the user after the knowledge resources are checked and used by the user aiming at knowledge services actively provided by the platform to the user, acquiring satisfaction degree of the user to the knowledge resources provided by the platform through calculation, judging the change of personal knowledge demands, deleting knowledge concepts which do not meet a set knowledge demand degree threshold, otherwise merging a knowledge concept set, an attribute set and a relationship set, and updating a user personalized model to form a new concept set. Wherein the set of attributes defines a set of attributes, and an instance of the set of attributes contains specific values of a portion of the attributes. The relationship set refers to a knowledge relationship cluster.
(2) Aiming at the knowledge behavior of the user in the platform, acquiring new knowledge demands of the user through statistical analysis. Aiming at new knowledge resources possibly needed by a user, a characteristic word set is obtained through word segmentation processing, and is combined with an original model word set to update a user model.
(3) Aiming at the problems that the user demand can decay, change and the like along with the time, the requirements of fading and forgetting are deleted through the calculation of the concept demand degree. When a user does not relate to a certain knowledge concept for a long time, the demand degree of the knowledge concept is calculated, and if the demand degree is smaller than a threshold value, the knowledge demand is deleted. The calculation formula of the demand level of the knowledge concept is as follows:
wherein x represents a demand degree parameter when forgetting to stabilize, yc represents a demand degree of a user for a knowledge concept c, and δis a Yc value when 0.ltoreq.x.ltoreq.α,representing weights +.>Representing the weight of knowledge concept c in the user's demand,/->Representing turning points where knowledge is forgotten.
In the process of implementing the personalized knowledge service of user behavior perception, industrial enterprises need to consider for a long time and advance steadily. On the one hand, the management of the carding and organization of the internal knowledge resources needs to be enhanced, the knowledge assets of enterprises are precipitated, and the knowledge base is enriched. On the other hand, it is necessary to build enterprise culture of knowledge sharing, and encourage employees to contribute knowledge resources and improve participation of employees through effective incentive measures.
Another embodiment of the present invention provides a knowledge service system based on industrial service cloud platform user behavior awareness, which includes:
the knowledge resource unified description module is responsible for carrying out unified description on knowledge resources in the industrial service cloud platform through the ontology, and eliminating the isomerism of different knowledge resources in structure and semantics;
the user personalized model building module is in charge of acquiring personalized knowledge requirements of the user according to business activities of the user in the industrial service cloud platform and building a user personalized model according to the personalized knowledge requirements of the user;
the knowledge resource acquisition module is responsible for acquiring knowledge resources meeting the personalized knowledge requirements of the user by searching the knowledge resources of the industrial service cloud platform based on the established personalized user model.
The specific implementation of each module is referred to in the description of the method of the invention.
The above embodiments are only for illustrating the technical solution of the present invention and not for limiting the same, and those skilled in the art may modify or substitute the technical solution of the present invention without departing from the spirit and scope of the present invention, and the protection scope of the present invention shall be defined by the claims.
Claims (5)
1. The knowledge service method based on the perception of the user behavior of the industrial service cloud platform is characterized by comprising the following steps of:
1) The knowledge resources in the industrial service cloud platform are uniformly described through the ontology, so that the structural and semantic isomerism of different knowledge resources is eliminated;
2) Acquiring personalized knowledge requirements of a user according to business activities of the user in an industrial service cloud platform, and establishing a user personalized model according to the personalized knowledge requirements of the user;
3) Based on the established user personalized model, knowledge resources meeting the user personalized knowledge requirements are obtained by searching the knowledge resources of the industrial service cloud platform;
step 2) describing the requirement level of the user on the knowledge resource by adopting the knowledge requirement level; the knowledge demand level comprises a knowledge attention level and a knowledge value level; the knowledge attention is described from the perspective of the operation behavior of the user on the knowledge, and reflects the attention of the user on the knowledge resource; the knowledge value reflects the knowledge quality by subjectively evaluating the value of the knowledge resource by a user;
the knowledge browsing, knowledge downloading, knowledge clicking, knowledge recommending, knowledge collecting and knowledge subscribing behaviors in the knowledge attention degree are quantified through statistical calculation, the knowledge comment and knowledge question-answering behaviors comprise positive and negative user requirements, positive comments and answers reflect positive and attention of a user to the knowledge resource, and negative comments and answers reflect negative of the user to the knowledge resource; the knowledge value degree is scored from four aspects of validity, relativity, innovativeness and readability of knowledge resources;
step 3) setting a corresponding threshold value for the knowledge demand degree as a condition for filtering the knowledge resources, so that the high-quality knowledge resources required by the user are provided for the user;
the method also comprises the step of updating the user personalized model, wherein the updating is performed by combining the content of user behaviors and knowledge resources and considering time factors, and comprises the following steps:
a) Aiming at knowledge services actively provided by an industrial service cloud platform for users, after the users view and use knowledge resources, the knowledge behaviors of the users are counted, the satisfaction degree of the users on the knowledge resources provided by the platform is obtained through calculation, the change of personal knowledge demands is judged, knowledge concepts which do not meet a set knowledge demand degree threshold are deleted, otherwise, knowledge concept sets, attribute sets and relationship sets are combined, and a user personalized model is updated to form a new concept set;
b) Aiming at the knowledge behavior of a user in an industrial service cloud platform, acquiring new knowledge demands of the user through statistical analysis, acquiring a characteristic word set through word segmentation processing aiming at new knowledge resources possibly needed by the user, merging with an original word set, and updating a user model;
c) Aiming at the problems that the user demand can decay and change along with the time, the requirements of fading and forgetting are deleted through the calculation of the concept demand degree;
in step c), when the user does not relate to a certain knowledge concept for a long time, calculating the demand degree of the knowledge concept, and deleting the knowledge demand if the demand degree is smaller than a threshold value; the calculation formula of the demand level of the knowledge concept is as follows:
，
wherein ,xa desirability parameter indicating when forgetting to stabilize,Y c representing user versus knowledge conceptcIs used for the degree of demand of (1),when (1)Y c Value of->Representing weights +.>Representing knowledge conceptscWeight in user demand, +.>Representing turning points where knowledge is forgotten.
2. The method of claim 1, wherein the knowledge resources comprise static knowledge resources and dynamic knowledge resources, the static knowledge resources mainly refer to document-type knowledge resources, and the dynamic knowledge resources mainly refer to dynamically callable knowledge resources formed by encapsulating tools and methods.
3. The method of claim 1, wherein step 2) of obtaining relevant information capable of reflecting personalized knowledge needs of the user according to business activities of the user in the industrial service cloud platform comprises: user basic information, user behavior information and user service information; the user basic information comprises user professions, units, departments and education backgrounds, and the user basic information is filled in when the user registers a cloud manufacturing platform; the user behavior information comprises direct behaviors and indirect behaviors, wherein the direct behaviors comprise service scoring, service collection, service subscription and service recommendation; the user service information is service content provided by a user to the platform and service content required to be acquired from the platform, and comprises service names, belonging fields, keywords, function descriptions, time effectiveness, service transaction history records and service transaction user associated users.
4. The method of claim 1, wherein a user of the industrial service cloud platform interacts with the platform through various terminal devices, including registering personal information, obtaining manufacturing services, and providing manufacturing services and knowledge resources to the platform; the industrial service cloud platform provides intelligent and active knowledge service for users through behaviors and knowledge requirements of the users.
5. The method according to claim 1, characterized in that it comprises:
the knowledge resource unified description module is responsible for carrying out unified description on knowledge resources in the industrial service cloud platform through the ontology, and eliminating the isomerism of different knowledge resources in structure and semantics;
the user personalized model building module is in charge of acquiring personalized knowledge requirements of the user according to business activities of the user in the industrial service cloud platform and building a user personalized model according to the personalized knowledge requirements of the user;
the knowledge resource acquisition module is responsible for acquiring knowledge resources meeting the personalized knowledge requirements of the user by searching the knowledge resources of the industrial service cloud platform based on the established personalized user model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811582979.2A CN109800249B (en) | 2018-12-24 | 2018-12-24 | Knowledge service method and system based on industrial service cloud platform user behavior awareness |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811582979.2A CN109800249B (en) | 2018-12-24 | 2018-12-24 | Knowledge service method and system based on industrial service cloud platform user behavior awareness |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109800249A CN109800249A (en) | 2019-05-24 |
| CN109800249B true CN109800249B (en) | 2023-08-04 |
Family
ID=66557432
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811582979.2A Active CN109800249B (en) | 2018-12-24 | 2018-12-24 | Knowledge service method and system based on industrial service cloud platform user behavior awareness |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109800249B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110807051B (en) * | 2019-10-31 | 2021-03-26 | 太原科技大学 | Context-aware real-time service recommendation method based on cloud platform |
| CN111967753B (en) * | 2020-08-10 | 2023-06-02 | 成都信息工程大学 | Cloud manufacturing environment information sensing system and method for manufacturing task execution |
| CN113569007A (en) * | 2021-06-18 | 2021-10-29 | 武汉理工数字传播工程有限公司 | Method, device and storage medium for processing knowledge service resources |
| CN113568998A (en) * | 2021-06-18 | 2021-10-29 | 武汉理工数字传播工程有限公司 | Knowledge service resource processing method, device, equipment and storage medium |
| CN117725192B (en) * | 2024-02-18 | 2024-05-14 | 张家港快工品科技有限公司 | Langchain-based proprietary industrial information interaction calling method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2011000046A1 (en) * | 2009-07-01 | 2011-01-06 | Ozmota Inc. | Systems and methods for determining information and knowledge relevancy, relevant knowledge discovery and interactions, and knowledge creation |
| CN103995858A (en) * | 2014-05-15 | 2014-08-20 | 北京航空航天大学 | Individualized knowledge active pushing method based on task decomposition |
| CN104239660A (en) * | 2013-06-08 | 2014-12-24 | 北京航空航天大学 | Knowledge fusion method based on dynamic body in cloud manufacturing mode |
| CN105373546A (en) * | 2014-08-25 | 2016-03-02 | 北大方正集团有限公司 | Information processing method and system for knowledge services |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103733194A (en) * | 2011-01-27 | 2014-04-16 | 康姆普特奈科斯特有限公司 | Dynamically organizing cloud computing resources to facilitate discovery |
-
2018
- 2018-12-24 CN CN201811582979.2A patent/CN109800249B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2011000046A1 (en) * | 2009-07-01 | 2011-01-06 | Ozmota Inc. | Systems and methods for determining information and knowledge relevancy, relevant knowledge discovery and interactions, and knowledge creation |
| CN104239660A (en) * | 2013-06-08 | 2014-12-24 | 北京航空航天大学 | Knowledge fusion method based on dynamic body in cloud manufacturing mode |
| CN103995858A (en) * | 2014-05-15 | 2014-08-20 | 北京航空航天大学 | Individualized knowledge active pushing method based on task decomposition |
| CN105373546A (en) * | 2014-08-25 | 2016-03-02 | 北大方正集团有限公司 | Information processing method and system for knowledge services |
Non-Patent Citations (1)
| Title |
|---|
| 李新.基于本体的制造资源建模与智能搜索研究开发.中国优秀硕士学位论文数据库.2017,全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109800249A (en) | 2019-05-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109800249B (en) | Knowledge service method and system based on industrial service cloud platform user behavior awareness | |
| CN109767255B (en) | Method for realizing intelligent operation and accurate marketing through big data modeling | |
| Feng et al. | An expert recommendation algorithm based on Pearson correlation coefficient and FP-growth | |
| Wu et al. | Research on internet information mining based on agent algorithm | |
| Chianese et al. | Cultural heritage and social pulse: a semantic approach for CH sensitivity discovery in social media data | |
| CN111538844B (en) | Target field knowledge base generation and problem solution method and device | |
| CN109902216A (en) | A kind of data collection and analysis method based on social networks | |
| CN108052605A (en) | A kind of intelligent Answer System based on client feature library | |
| CN104298785B (en) | Searching method for public searching resources | |
| US9069880B2 (en) | Prediction and isolation of patterns across datasets | |
| Moalla et al. | Data warehouse design approaches from social media: review and comparison | |
| Al-Qurishi et al. | User profiling for big social media data using standing ovation model | |
| Spirin et al. | People search within an online social network: Large scale analysis of facebook graph search query logs | |
| CN111931022A (en) | AI hot spot content intelligent editing system | |
| CN117149988B (en) | Data management processing method and system based on education digitization | |
| CN114637903A (en) | Public opinion data acquisition system for directional target data expansion | |
| CN117236624A (en) | Issue repairer recommendation method and apparatus based on dynamic graph | |
| US20140244741A1 (en) | Computer-Implemented System And Method For Context-Based APP Searching And APP Use Insights | |
| Rojas-Galeano et al. | A bibliometric perspective on AI research for job-résumé matching | |
| CN116595191A (en) | Construction method and device of interactive low-code knowledge graph | |
| Wang et al. | Research on intelligent information system of library under big data and digitization technology | |
| Becheru et al. | Towards social data analytics for smart tourism: A network science perspective | |
| Gu et al. | Design and implementation of knowledge sharing system based on WeChat small program | |
| CN109388649B (en) | Land intelligent recommendation method and system | |
| Proskurnia et al. | Analyzing large-scale public campaigns on twitter |
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 |