CN117829291B - Whole-process consultation knowledge integrated management system and method - Google Patents
Whole-process consultation knowledge integrated management system and method Download PDFInfo
- Publication number
- CN117829291B CN117829291B CN202410147592.3A CN202410147592A CN117829291B CN 117829291 B CN117829291 B CN 117829291B CN 202410147592 A CN202410147592 A CN 202410147592A CN 117829291 B CN117829291 B CN 117829291B
- Authority
- CN
- China
- Prior art keywords
- consultation
- module
- knowledge
- sub
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 74
- 230000008569 process Effects 0.000 claims abstract description 52
- 238000007726 management method Methods 0.000 claims abstract description 47
- 238000005065 mining Methods 0.000 claims abstract description 39
- 230000010354 integration Effects 0.000 claims abstract description 25
- 238000005516 engineering process Methods 0.000 claims abstract description 18
- 238000012216 screening Methods 0.000 claims abstract description 17
- 238000012545 processing Methods 0.000 claims abstract description 14
- 238000007405 data analysis Methods 0.000 claims abstract description 12
- 230000000007 visual effect Effects 0.000 claims abstract description 11
- 230000006870 function Effects 0.000 claims abstract description 10
- 238000004140 cleaning Methods 0.000 claims abstract description 8
- 238000007781 pre-processing Methods 0.000 claims abstract description 8
- 230000005540 biological transmission Effects 0.000 claims abstract description 4
- 230000006399 behavior Effects 0.000 claims description 45
- 238000012544 monitoring process Methods 0.000 claims description 37
- 230000002159 abnormal effect Effects 0.000 claims description 26
- 238000011156 evaluation Methods 0.000 claims description 19
- 238000012986 modification Methods 0.000 claims description 17
- 230000004048 modification Effects 0.000 claims description 17
- 238000005259 measurement Methods 0.000 claims description 16
- 230000003993 interaction Effects 0.000 claims description 15
- 238000002372 labelling Methods 0.000 claims description 15
- 238000004891 communication Methods 0.000 claims description 14
- 238000009223 counseling Methods 0.000 claims description 14
- 238000012360 testing method Methods 0.000 claims description 14
- 238000004458 analytical method Methods 0.000 claims description 13
- 238000000605 extraction Methods 0.000 claims description 12
- 238000012550 audit Methods 0.000 claims description 9
- 238000009960 carding Methods 0.000 claims description 9
- 230000005856 abnormality Effects 0.000 claims description 8
- 238000001514 detection method Methods 0.000 claims description 7
- 238000009411 base construction Methods 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 5
- 230000006698 induction Effects 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 230000007246 mechanism Effects 0.000 claims description 4
- 238000012795 verification Methods 0.000 claims description 4
- 230000000903 blocking effect Effects 0.000 claims description 3
- 230000008859 change Effects 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 3
- 239000003607 modifier Substances 0.000 claims description 3
- 238000012800 visualization Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 claims description 2
- 238000004806 packaging method and process Methods 0.000 claims description 2
- 238000011161 development Methods 0.000 description 4
- 230000008520 organization Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000013480 data collection Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000013439 planning Methods 0.000 description 1
Abstract
The invention discloses a whole process consultation knowledge integrated management system and a method, which relate to the technical field of knowledge information management, wherein the system comprises: the system comprises a data acquisition module, a data analysis module, a user access module, a knowledge integration module, a knowledge tracing module and a visual management module; the data acquisition module is used for acquiring multi-source data in a target data source by utilizing a data acquisition engine based on a keyword technology, and cleaning, screening and uniformly preprocessing the multi-source data; the data analysis module is used for constructing an open knowledge processing network, mining the multi-source data in a distributed mining mode, and realizing data security transmission and storage by combining encryption technology. The invention integrates knowledge information from multi-source data, provides comprehensive and high-quality information resources, combines Bayesian network and user behavior, provides integrated and dynamically updated consultation service, improves decision support capability, and has humanized consultation and knowledge recommendation functions.
Description
Technical Field
The invention relates to the technical field of knowledge information management, in particular to a whole-process consultation knowledge integrated management system and method.
Background
As engineering projects become more complex and bulky, traditional manual consultation methods have been difficult to meet the needs of rapidity and efficiency. The whole process consultation is a consultation method widely used for engineering project development, and aims to help engineering to realize success in the whole life cycle. This consultation method emphasizes not only solving specific problems or challenges, but also comprehensively considering engineering goals, flows and development needs.
The whole process consultation considers the whole life cycle of the project, from planning and creation at the initial stage to growth, development, problem solving and termination, and aims to provide long-term and comprehensive support for the project. And thus is a long-term partnership, not just a disposable item. Whole process consultation involves continuous feedback and assessment to ensure that the formulated strategy and solution is valid and is adjusted as needed.
Integrated management of whole process consultation knowledge refers to methods and practices for effectively collecting, integrating, storing and managing related knowledge and information during the whole process consultation process, which helps to ensure consistency and sustainability of consultation activities and provides deep knowledge about development and performance of projects. In whole process consultation, critical data and information often relates to the status of the project, goals, internal and external environments, employee feedback, etc. The data collected from the different sources is integrated into a system to create a comprehensive information base. Effective knowledge management is a key element of whole process consultation, including ensuring accessibility, sharing, updating and protection of knowledge so that consultants and engineering members can access and use relevant information at any time.
The existing whole process consultation knowledge integrated management system still has the following defects and the points to be improved: data quality and consistency problems, inaccurate, outdated or incomplete information may exist in the knowledge base; knowledge discovery and updating still rely on a large amount of manual or semi-automatic work, requiring more automated and intelligent techniques; the quality of natural language processing needs to be improved, especially in dealing with complex problems and multi-language scenarios; user interfaces and interactive experiences may be further improved, including more intuitive speech recognition and personalized suggestions; performance and scalability need to be improved to cope with large-scale data and high concurrent access; the improvement of data multi-modal support and integration helps to provide a richer consultation experience and better application integration; user feedback and improvement mechanisms should be more flexible to push systems to increase continuously. Improving these aspects will help to increase the effectiveness, availability, and user satisfaction of the overall process consultation knowledge integrated management system.
Disclosure of Invention
Based on this, it is necessary to provide a system and a method for integrated management of whole process consultation knowledge aiming at the technical problems.
In a first aspect, the present invention provides a whole process consulting knowledge integrated management system, the system comprising: the system comprises a data acquisition module, a data analysis module, a user access module, a knowledge integration module, a knowledge tracing module and a visual management module;
the data acquisition module is used for acquiring multi-source data in a target data source by utilizing a data acquisition engine based on a keyword technology, and cleaning, screening and uniformly preprocessing the multi-source data;
the data analysis module is used for constructing an open knowledge processing network, excavating multi-source data in a distributed excavating mode, and realizing data safety transmission and storage by combining encryption technology;
the user access module is used for building a user access scoring system, monitoring user behaviors in real time, classifying user grades based on user history behaviors and giving user rights of different grades;
The knowledge integration module is used for integrating the scattered knowledge content into an integration platform and building an integrated and dynamically updated consultation access cluster based on the Bayesian network and the user behavior;
the knowledge tracing module is used for carrying a data information tracing mechanism and automatically positioning and tracing abnormal knowledge content and illegal consultation behaviors in the whole process of consultation;
And the visual management module is used for comprehensively managing and dynamically displaying knowledge content, participating users and system working conditions by utilizing a real-time monitoring result and a visual technology.
Further, the data analysis module comprises an open network sub-module, a distributed mining sub-module, a global carding sub-module and an encryption communication sub-module;
the system comprises a network sub-module, a knowledge database and a knowledge database, wherein the network sub-module is used for defining knowledge association rules, extracting concept elements of mass existing knowledge data by using a semi-supervised learning method, and integrating and constructing the concept elements to form an open knowledge database;
the distributed mining sub-module is used for providing distributed mining sub-nodes, and the mining sub-nodes mine the acquired multi-source data by utilizing a clue association and relationship reasoning mode on the basis of a knowledge base to acquire knowledge content and respective corresponding concept elements;
The global carding sub-module is used for providing a global carding center which is in communication connection with the excavating sub-node, acquiring and carding knowledge excavating results, and storing knowledge content and concept elements thereof into a knowledge base to realize dynamic updating of the knowledge base;
the encryption communication sub-module is used for establishing an encryption communication channel between the mining sub-node and the global carding center, setting encryption authentication for the mining sub-node, and only the mining sub-node after the encryption authentication has the authority to access the knowledge base.
Further, the open network submodule comprises an association rule definition unit, a semi-supervised learning labeling unit, a concept element extraction unit and a knowledge base construction unit;
The association rule definition unit is used for defining knowledge association rules based on domain knowledge, text analysis and keyword matching, and establishing extraction and labeling bases and rules of existing knowledge data;
The semi-supervised learning labeling unit is used for labeling mass existing knowledge data on the basis of knowledge association rules by utilizing a semi-supervised learning mode;
A concept element extraction unit for extracting a concept element from existing knowledge data, the concept element including a data type, a data entity, a data attribute, and a data relationship;
and the knowledge base construction unit is used for integrating the marked and extracted existing knowledge data into an open network database to create a knowledge base meeting the whole process consultation.
Further, the user access module comprises an access record sub-module, a consultation browsing sub-module, an uploading sharing sub-module, a behavior monitoring sub-module, a grade evaluation sub-module and a permission management sub-module;
The access recording sub-module is used for providing verification and authentication of user identity information and recording and managing login access of the whole process consultation integrated platform of the user;
the consultation browsing sub-module is used for providing a user consultation retrieval function, retrieving knowledge content corresponding to the retrieval from the knowledge base according to the consultation information input by the user for the user to browse;
the uploading sharing sub-module is used for providing a user uploading sharing function, and the user automatically uploads, modifies or answers the knowledge content about the consultation information and verifies and validates the answer content;
The behavior monitoring sub-module is used for monitoring and recording behavior interaction information of the users in the consultation process, wherein the behavior interaction information comprises consultation information, click information, browsing information, downloading information and uploading information, and generating a consultation log library of each user according to the behavior interaction information;
the grade evaluation sub-module is used for carrying out user grade evaluation on the users according to the behavior interaction information and dividing the users into authenticated users, active users and common users;
And the permission management sub-module is used for managing the user permission of the user in the consultation process and giving the user permission of different levels to the users of different user levels.
Further, the knowledge integration module comprises an integration classification sub-module, a consultation model sub-module, a cluster reasoning sub-module, a dynamic updating sub-module and a feedback evaluation sub-module;
the integrated classification sub-module is used for integrating the interface of the knowledge base into an integrated platform, and the integrated platform carries out induction classification according to the concept elements of the knowledge content;
The consultation model sub-module is used for constructing a consultation access model according to a consultation log library of the authenticated user or the active user, and analyzing and calculating consultation parameters of the authenticated user or the active user in an active time period by utilizing the consultation access model;
The cluster reasoning sub-module is used for reasoning the consultation access cluster of the user in the active time period by using the Bayesian network to obtain a consultation knowledge cluster which is exclusive to the user and is dynamically updated;
the dynamic updating sub-module is used for updating the active time period of the integrated platform of the user participation, and updating the simplified log library and the consultation access cluster along with the update synchronization of the active time period;
And the feedback evaluation sub-module is used for collecting objective evaluation of the consultation access cluster by the user.
Further, the consultation model submodule comprises a log screening unit, a frequency counting unit and a probability analysis unit;
the log screening unit is used for setting an active time period, filtering and screening the consultation log library in the active time period, and obtaining a simplified log library after the processing is finished;
the frequency counting unit is used for counting the frequency of each consultation item consulted by the authenticated user or the active user in the simplified log library and taking the frequency as the consultation frequency of the consultation item;
The probability analysis unit is used for calculating the ratio of the total frequency of all consultation items in the reduced log library, and the calculation expression is as the prior probability:
Where P (x i) represents the prior probability of the counseling term x i;
x i represents the ith consulting term in the condensed log library;
p xi represents the counseling frequency of counseling item x i;
m represents the number of consultation items in the reduced log library;
p xm represents the consultation frequency of the mth consultation item in the reduced log library.
Further, the cluster reasoning sub-module comprises a frequency sorting unit, a node measuring unit, a node testing unit, a path optimizing unit and a cluster generating unit;
The frequency ordering unit is used for taking the consultation items as nodes of the Bayesian network, and arranging all the consultation items in the simplified log library in descending order from high to low according to the consultation frequency to obtain a frequency-reducing queue consisting of the nodes;
The node measurement unit is used for calculating the relevance measurement of two nodes by utilizing mutual information between two adjacent nodes, counting node pairs with the relevance measurement larger than a measurement threshold value, connecting arcs of the initial connection graph according to the ordering of the down-conversion queue to form an initial arc set, and counting all node pairs which meet the relevance measurement and have open paths between the nodes again to form a node pair set;
The node testing unit is used for searching a minimum blocking set of each node pair in the node pair set, carrying out an independence test on the node pair by utilizing node pair mutual information, and if the mutual information is larger than an independent threshold value, merging the node pair with the initial arc set to obtain a new initial arc set;
The path optimizing unit is used for judging the arcs in the new initial arc set, deleting the arcs if an open path exists between the node pairs forming the arcs, searching the minimum obstruction set of the node pairs, and performing an independence test again until the mutual information of the node pairs is smaller than an independent threshold value, and reserving the minimum obstruction set of the node pairs to obtain a counsel item cluster of the Bayesian network;
The cluster generating unit is used for traversing the simplified log library, estimating the network parameters of each consultation item by using a probability estimation formula, and merging the network parameters of each consultation item into the consultation item cluster to obtain a complete consultation knowledge cluster.
Further, the knowledge tracing module comprises an abnormality detection sub-module, a tracing marking sub-module, a tracing inquiring sub-module and a monitoring and early warning sub-module;
the abnormality detection sub-module is used for monitoring a knowledge base and a consultation process, and monitoring existing abnormality information in real time, wherein the abnormality information comprises abnormal knowledge content and illegal consultation behaviors;
the tracing mark sub-module is used for embedding tracing marks into knowledge contents in the knowledge base;
the tracing inquiry sub-module is used for inquiring and tracing the abnormal information according to the tracing mark to acquire the data source, the change history and the access history of the abnormal information;
The monitoring and early warning sub-module is used for monitoring whether abnormal information exists in the knowledge base and the consultation process in real time, and triggering an alarm or a notification after judging that the abnormal information exists.
Further, the traceability marking submodule comprises a metadata generation unit, an identifier unit, an audit log unit and a permission control unit;
the system comprises a metadata generation unit, a storage unit and a storage unit, wherein the metadata generation unit is used for generating metadata of knowledge content, and the metadata comprises acquisition time, modification time, a digger, a modifier and data version information;
An identifier unit, configured to package each knowledge content and its concept element, metadata together, and generate an identifier unique to the knowledge content;
The audit log unit is used for recording consultation access and modification events of the knowledge content, wherein the modification events comprise user identifications, time stamps and modification types, and storing to form an audit log;
the right control unit is used for managing the access, modification or examination operation right of the user.
In a second aspect, the present invention also provides a whole process consultation knowledge integrated management method, which includes the following steps:
s1, acquiring multi-source data in a target data source by utilizing a data acquisition engine based on a keyword technology, and cleaning, screening and uniformly preprocessing the multi-source data;
S2, constructing an open knowledge processing network, mining multi-source data in a distributed mining mode, and summarizing and combining the multi-source data to a global carding center through distributed mining child nodes to form a knowledge base;
s3, building a user access scoring system, monitoring user behaviors in real time, classifying user grades based on user history behaviors, giving user rights of different grades, and recording and generating a user consultation log library;
S4, integrating the knowledge base and the scattered knowledge content into an integrated platform, and building an integrated and dynamically updated consultation access cluster based on the Bayesian network and the consultation log base;
s5, automatically positioning and tracking abnormal knowledge content and illegal consultation behaviors in the whole process of consultation by using an abnormal monitoring mode, acquiring abnormal information and carrying out early warning correction;
and S6, comprehensively managing and dynamically displaying knowledge content, participating users and system working conditions by utilizing a real-time monitoring result and a visualization technology.
The beneficial effects of the invention are as follows:
1. Through distributed data acquisition and mining analysis, knowledge information from multi-source data can be integrated, comprehensive and high-quality information resources are provided, integrated and dynamically updated consultation services are provided by combining Bayesian networks and user behaviors, decision support capacity is improved, humanized consultation and knowledge recommendation functions are achieved, consultation interaction efficiency and accuracy are effectively improved, a decision maker is helped to better know knowledge content and system state, and further knowledge management and consultation service efficiency and quality are improved, so that the intelligent and safety are achieved.
2. The knowledge base is constructed by utilizing knowledge association rules and a semi-supervised learning method, concept elements are extracted from mass existing knowledge data, knowledge content is mined, the knowledge base is enriched, meanwhile, the knowledge base is dynamically updated, the storage of mining results is ensured, the safety of the knowledge base is protected by utilizing encryption communication and access control, knowledge mining and safety are integrated, an effective solution is provided for perfecting, dynamic and safe management of the knowledge base, and therefore the value and credibility of the knowledge base are improved.
3. The accessibility and the organization structure of the knowledge base are improved through concept element induction classification, a personalized consultation access model is built according to the user consultation log, accurate consultation advice is provided, namely, a user-specific and dynamically updated consultation knowledge cluster is generated based on Bayesian network reasoning, decision support capability is improved, meanwhile, the knowledge cluster and the log base are synchronously updated with the active time period of the user, information timeliness is ensured, and the efficiency and the user experience of the knowledge integrated management system are enhanced.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention and do not constitute a limitation on the invention. In the drawings:
FIG. 1 is a system block diagram of a whole process consulting knowledge integration management system in accordance with an embodiment of the invention;
Fig. 2 is a flowchart of a whole process consulting knowledge integration management method in accordance with an embodiment of the invention.
Reference numerals: 1. a data acquisition module; 2. a data analysis module; 201. opening a network sub-module; 202. a distributed digging sub-module; 203. a global carding sub-module; 204. an encrypted communication sub-module; 3. a user access module; 301. accessing a recording sub-module; 302. a consulting and browsing sub-module; 303. uploading the sharing sub-module; 304. a behavior monitoring sub-module; 305. a grade evaluation sub-module; 306. a rights management sub-module; 4. a knowledge integration module; 401. integrating a classification sub-module; 402. a consulting model sub-module; 403. a cluster reasoning sub-module; 404. dynamically updating the sub-module; 405. a feedback evaluation sub-module; 5. a knowledge tracing module; 501. an anomaly detection sub-module; 502. a tracing marking sub-module; 503. a trace back query sub-module; 504. a monitoring and early warning sub-module; 6. and a visual management module.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Referring to fig. 1, there is provided a whole process consultation knowledge integrated management system, the system including: the system comprises a data acquisition module 1, a data analysis module 2, a user access module 3, a knowledge integration module 4, a knowledge tracing module 5 and a visual management module 6.
The data acquisition module 1 is used for acquiring multi-source data in a target data source by utilizing a data acquisition engine based on a keyword technology, and cleaning, screening and uniformly preprocessing the multi-source data.
In the description of the present invention, a keyword technology-based data collection engine automatically retrieves data from a target website or data source by configuring keywords, URLs or other retrieval conditions, covering a plurality of websites, databases or online resources, to obtain various types of information.
The data collection engine has the ability to capture data from multiple target websites of different origin. After data acquisition, the module cleans the acquired data, including removing noise, repairing format errors, correcting inconsistencies, to ensure accuracy and quality of the data. The filtering function may exclude unnecessary or duplicate data to reduce data redundancy, reduce storage and processing costs, and ensure that information in the knowledge base is targeted.
The data acquisition module 1 also performs format unified preprocessing on the multi-source data, ensures that the data is stored in a consistent format and structure, is beneficial to improving the manageability and usability of the data, and reduces the complexity of subsequent processing.
The data analysis module 2 is used for constructing an open knowledge processing network, mining the multi-source data in a distributed mining mode, and realizing data security transmission and storage by combining encryption technology.
In the description of the present invention, the data analysis module 2 includes an open network sub-module 201, a distribution mining sub-module 202, a global carding sub-module 203, and an encryption communication sub-module 204.
The open network submodule 201 is configured to define a knowledge association rule, extract concept elements of massive existing knowledge data by using a semi-supervised learning method, and integrate and construct an open knowledge base.
In the description of the present invention, the open network submodule 201 includes an association rule definition unit, a semi-supervised learning labeling unit, a concept element extraction unit, and a knowledge base construction unit.
The association rule definition unit is used for defining knowledge association rules based on domain knowledge, text analysis and keyword matching, and establishing extraction and labeling bases and rules of existing knowledge data.
Knowledge association rules associated with a domain are defined using domain knowledge, such as industry terms, concepts, and rules. Entities, relationships, and specific concepts in text are identified and understood through text analysis techniques. For example, keywords, noun phrases, verb phrases, etc. in the text are identified for further processing. In knowledge data, a list of keywords defined in advance can be used by looking up a particular keyword or phrase in text to identify relevant knowledge.
In the association rule definition unit, rules are defined based on the domain knowledge and the results of text analysis, including logic rules, pattern matching rules, association rules, etc., for guiding how information is extracted and annotated from existing knowledge data.
And the semi-supervised learning labeling unit is used for labeling mass existing knowledge data on the basis of the knowledge association rule by utilizing a semi-supervised learning mode.
In the description of the present invention, the semi-supervised learning labeling unit uses known label data, i.e., data labeled according to knowledge association rules, to train a supervised learning model to help identify specific patterns and relationships in the data. The semi-supervised learning labeling unit then applies this trained model to unlabeled data, automatically assigning labels to unlabeled data based on known rules and patterns. The semi-supervised learning method can remarkably improve the labeling precision, and ensures that the labeled data is consistent with the definition of the knowledge association rule by utilizing the existing label data and combining the information of unlabeled data.
And the concept element extraction unit is used for extracting concept elements from the existing knowledge data, wherein the concept elements comprise data types, data entities, data attributes and data relationships.
Wherein, data type: the data type refers to a category or type to which the knowledge data belongs, such as text, numbers, dates, images, audio, and the like. The extraction of the elements helps to classify and organize the different types of knowledge data.
Data entity: a data entity is a specific object, individual, or entity in knowledge data, such as a person, place, organization, product, etc. The concept element extraction unit is responsible for identifying and extracting these entities from the data to build an entity database.
Data attributes: data attributes are specific information or attributes related to an entity, such as price of a product, age of a person, coordinates of a place, etc. The extraction of the elements helps to build an attribute database, making the attribute information easy to retrieve and manage.
Data relationship: data relationships are associations or connections between different entities, such as relationships between people, relationships between products and companies, and so forth.
And the knowledge base construction unit is used for integrating the marked and extracted existing knowledge data into an open network database to create a knowledge base meeting the whole process consultation.
The distributed mining sub-module 202 is configured to provide distributed mining sub-nodes, and mine the acquired multi-source data by using a clue association and relationship reasoning mode on the basis of the knowledge base, so as to mine the knowledge content and the concept elements corresponding to the knowledge content.
The global carding sub-module 203 is configured to provide a global carding center that is communicatively connected with the excavating sub-node, obtain and comb knowledge excavating results, and store knowledge content and concept elements thereof into the knowledge base, so as to realize dynamic update of the knowledge base.
The encryption communication sub-module 204 is configured to establish an encryption communication channel between the mining sub-node and the global carding center, and set encryption authentication for the mining sub-node, where only the mining sub-node after completing the encryption authentication has the authority to access the knowledge base.
And the user access module 3 is used for building a user access scoring system, monitoring user behaviors in real time, classifying user grades based on user history behaviors and giving user rights of different grades.
In the description of the present invention, the user access module 3 includes an access record sub-module 301, a consultation browsing sub-module 302, an upload sharing sub-module 303, a behavior monitoring sub-module 304, a rating evaluation sub-module 305, and a rights management sub-module 306.
The access recording sub-module 301 is configured to provide verification and authentication of user identity information, and record and manage login access of the whole process consultation integration platform for user participation.
The consulting browse sub-module 302 is configured to provide a user consulting search function, and search the knowledge content corresponding to the call from the knowledge base for the user to browse according to the consulting information input by the user.
The upload sharing sub-module 303 is configured to provide a user upload sharing function, and the user automatically uploads, modifies or answers the knowledge content about the consultation information, and verifies and validates the answer content.
The behavior monitoring sub-module 303 is configured to monitor and record behavior interaction information of the user during the consultation process, where the behavior interaction information includes consultation information, click information, browsing information, downloading information and uploading information, and generate a respective consultation log library of each user according to the behavior interaction information.
The level evaluation sub-module 304 is configured to perform user level evaluation on the users according to the behavior interaction information, and divide the users into authenticated users, active users and normal users.
Authenticating a user: authenticated users are typically advanced users in the system that have passed identity verification or completed a certain authentication procedure. This level is typically of higher authority and privileges to access sensitive information or to perform critical operations. In the invention, the authenticated user needs to meet the highest-level consultation browsing, knowledge modification and answering tasks to acquire the identity, and simultaneously enjoys the authority of viewing knowledge traceability.
Active users: active users are active participants in the system who frequently interact, raise questions, answer questions, or share knowledge in the system. This level is typically privileged to encourage their participation. In the invention, the active user can acquire the identity by accumulating and completing the medium-level consultation browsing and answering task, and can participate in the right of knowledge modification under the identity.
The average user: ordinary users are general users in the system who use the system but may not have frequent interactions or contributions. This level typically has basic rights to consult for access to public knowledge.
The rights management sub-module 305 is used for managing the user rights of the user in the consultation process, and giving different levels of user rights to users with different user levels.
The knowledge integration module 4 is used for integrating the scattered knowledge content into an integration platform and building an integrated and dynamically updated consultation access cluster based on the Bayesian network and the user behavior.
In the description of the present invention, the knowledge integration module 4 includes an integration classification sub-module 401, a consultation model sub-module 402, a cluster reasoning sub-module 403, a dynamic update sub-module 404, and a feedback evaluation sub-module 405.
The integration classification sub-module 401 is configured to integrate the interface of the knowledge base into an integration platform, and the integration platform performs induction classification according to the concept elements of the knowledge content.
The consulting model sub-module 402 is configured to construct a consulting access model according to a consulting log library of the authenticated user or the active user (the normal user does not participate in constructing the consulting access model due to authority limit), and then analyze and calculate the consulting parameters of the authenticated user or the active user in the active time period by using the consulting access model.
In the description of the present invention, the consulting model submodule 402 includes a log screening unit, a frequency statistics unit, and a probability analysis unit.
The log screening unit is used for setting an active time period, filtering and screening the consultation log library in the active time period, and obtaining the simplified log library after the processing is finished.
Specifically, for each log record in the consultation log base, its time stamp (or date and time information) is checked. Only log records generated during the active period are selected. The record may include information such as a user's consultation request, clicks, browses, downloads, etc.
Records that are not generated during the active period are removed from the advisory log library and saved by simply filtering out the records or creating a new data structure. If duplicate records are contained in the consulting log library, a unique record is selected to be kept to reduce the size of the log library.
After screening, the log records of the consultation log library are subjected to data cleaning and standardization, including incomplete or erroneous record removal, date and time format unification, abnormal value processing and the like.
Finally, the screened, cleaned and standardized records are combined into a new reduced log library, and the reduced log library only contains records generated in an active time period, so that the records are easier to manage and analyze.
The frequency counting unit is used for counting the frequency of each consultation item consulted by the authenticated user or the active user in the simplified log library and taking the frequency as the consultation frequency of the consultation item.
The probability analysis unit is used for calculating the ratio of the total frequency of all consultation items in the reduced log library, and the calculation expression is as the prior probability:
wherein P (x i) represents the prior probability of the counseling item x i, x i represents the ith counseling item in the reduced log library, P xi represents the counseling frequency of the counseling item x i, M represents the number of the counseling items in the reduced log library, and P xm represents the counseling frequency of the mth counseling item in the reduced log library.
The cluster reasoning sub-module 403 is configured to use a bayesian network to infer a consultation access cluster of the user in an active period, so as to obtain a consultation knowledge cluster which is exclusive to the user and dynamically updated.
In the description of the present invention, the cluster inference sub-module 403 includes a frequency sorting unit, a node measurement unit, a node test unit, a path optimizing unit, and a cluster generating unit.
The frequency ordering unit is used for taking the consultation items as nodes of the Bayesian network, and arranging all the consultation items in the simplified log base in descending order according to the consultation frequency, so as to obtain a frequency-reducing queue consisting of the nodes.
And the node measurement unit is used for calculating the relevance measurement of two nodes by utilizing mutual information between two adjacent nodes, counting node pairs with the relevance measurement larger than a measurement threshold value, connecting arcs of the initial connection graph according to the ordering of the down-conversion queue to form an initial arc set, and counting all the node pairs which meet the relevance measurement and have open paths between the nodes again to form a node pair set.
The mutual information (Mutual Information) is an important concept in the information theory and is used for measuring the correlation and the dependency relationship between two random variables. The computation of mutual information typically involves a joint probability distribution of two random variables and a respective marginal probability distribution.
In the invention, the mutual information expression for the relevance metric calculation is:
Where I (x i,xj) represents a relevance metric between node x i and node x j, P (x i) represents the prior probability of node x i, P (x j) represents the prior probability of node x j, and P (x i,xj) represents the prior probability of node pair (x i,xj).
The node testing unit is used for searching the minimum blocking set of each node pair in the node pair set, carrying out an independence test on the node pair by utilizing the node pair mutual information, and if the mutual information is larger than the independence threshold value, merging the node pair with the initial arc set to obtain a new initial arc set.
The mutual information expression between the nodes for the independence test is as follows:
Where I (x i,xj |r) represents the node pair independence test result, R represents the minimum block set, and R represents an instance of the minimum block set.
And the path optimizing unit is used for judging the arcs in the new initial arc set, deleting the arcs if an open path exists between the node pairs forming the arcs, searching the minimum obstruction set of the node pairs, and performing an independence test again until the mutual information of the node pairs is smaller than an independent threshold value, and reserving the minimum obstruction set of the node pairs to obtain the counseling item cluster of the Bayesian network.
The cluster generating unit is used for traversing the simplified log library, estimating the network parameters of each consultation item by using a probability estimation formula, and combining the network parameters of each consultation item into the consultation item cluster to obtain a complete consultation knowledge cluster, wherein the probability estimation formula is as follows:
Where λ i represents a network parameter of the ith consultation item, W (x i,Pa(xi)j) represents the number of logs when the node value is x i in the reduced log library, where the node value combination is Pa (x i)j), and W (Pa (x i)j) represents the number of logs when the node value combination is Pa (x i)j) in the reduced log library, and the node value combination is x i.
The dynamic update sub-module 404 is configured to update an active period of the integrated platform in which the user participates, and update the reduced log library and the consulting access cluster in synchronization with the update of the active period.
And the feedback evaluation submodule 405 is used for collecting objective evaluation of the consultation access cluster by the user.
The knowledge tracing module 5 is used for carrying a data information tracing mechanism and automatically positioning and tracing abnormal knowledge content and illegal consultation behaviors in the whole process of consultation.
In the description of the present invention, the knowledge traceability module 5 includes an anomaly detection sub-module 501, a traceability marking sub-module 502, a traceability query sub-module 503 and a monitoring and early warning sub-module 504.
The anomaly detection sub-module 501 is configured to monitor a knowledge base and a consultation process, and monitor existing anomaly information in real time, where the anomaly information includes anomaly knowledge content and illegal consultation behavior.
The traceability marking sub-module 502 is configured to embed traceability marks into knowledge content in the knowledge base;
In the description of the present invention, the trace source flag sub-module 502 includes a metadata generation unit, an identifier unit, an audit log unit, and a rights control unit.
The metadata generation unit is used for generating metadata of the knowledge content, wherein the metadata comprises acquisition time, modification time, a miner, a modifier and data version information.
And the identifier unit is used for packaging each knowledge content, the concept elements and metadata of the knowledge content together and generating an identifier unique to the knowledge content.
And the audit log unit is used for recording consultation access and modification events of the knowledge content, wherein the modification events comprise user identification, time stamp and modification type, and storing to form an audit log.
The right control unit is used for managing the access, modification or examination operation right of the user.
And the trace back query sub-module 503 is configured to query and trace back the abnormal information according to the trace back mark, and obtain a data source, a change history and an access history of the abnormal information.
The monitoring and early warning sub-module 504 is configured to monitor, in real time, whether abnormal information exists in the knowledge base and the consultation process, and trigger an alarm or notification after determining that an abnormality exists.
And the visual management module 6 is used for comprehensively managing and dynamically displaying knowledge content, participating users and system working conditions by utilizing the real-time monitoring result and the visual technology.
Referring to fig. 2, there is also provided a whole process consultation knowledge integrated management method, which includes the steps of:
S1, acquiring multi-source data in a target data source by utilizing a data acquisition engine based on a keyword technology, and cleaning, screening and uniformly preprocessing the multi-source data.
S2, constructing an open knowledge processing network, mining the multi-source data in a distributed mining mode, and summarizing and combining the multi-source data to a global carding center through distributed mining child nodes to form a knowledge base.
And S3, building a user access scoring system, monitoring user behaviors in real time, classifying user grades based on user history behaviors, giving user rights of different grades, and recording and generating a user consultation log library.
And S4, integrating the knowledge base and the scattered knowledge content into an integrated platform, and building an integrated and dynamically updated consultation access cluster based on the Bayesian network and the consultation log base.
S5, automatically positioning and tracing abnormal knowledge content and illegal consultation behaviors in the whole process of consultation by using an abnormal monitoring mode, acquiring abnormal information and carrying out early warning correction.
And S6, comprehensively managing and dynamically displaying knowledge content, participating users and system working conditions by utilizing a real-time monitoring result and a visualization technology.
In summary, by means of the above technical scheme, knowledge information from multi-source data can be integrated through distributed data acquisition and mining analysis, comprehensive and high-quality information resources are provided, integrated and dynamically updated consultation services are provided by combining Bayesian networks and user behaviors, decision support capability and humanized consultation and knowledge recommendation functions are improved, consultation interaction efficiency and accuracy are effectively improved, a decision maker is facilitated to better know knowledge content and system state, and further knowledge management and consultation service efficiency and quality are improved, so that the intelligent and safety are achieved. The knowledge base is constructed by utilizing knowledge association rules and a semi-supervised learning method, concept elements are extracted from mass existing knowledge data, knowledge content is mined, the knowledge base is enriched, meanwhile, the knowledge base is dynamically updated, the storage of mining results is ensured, the safety of the knowledge base is protected by utilizing encryption communication and access control, knowledge mining and safety are integrated, an effective solution is provided for perfecting, dynamic and safe management of the knowledge base, and therefore the value and credibility of the knowledge base are improved. The accessibility and the organization structure of the knowledge base are improved through concept element induction classification, a personalized consultation access model is built according to the user consultation log, accurate consultation advice is provided, namely, a user-specific and dynamically updated consultation knowledge cluster is generated based on Bayesian network reasoning, decision support capability is improved, meanwhile, the knowledge cluster and the log base are synchronously updated with the active time period of the user, information timeliness is ensured, and the efficiency and the user experience of the knowledge integrated management system are enhanced.
It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited in order and may be performed in other orders, unless explicitly stated herein. Moreover, at least some of the steps in the flowcharts of the figures may include a plurality of sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, the order of their execution not necessarily being sequential, but may be performed in turn or alternately with other steps or at least a portion of the other steps or stages.
Claims (10)
1. An integrated process consultation knowledge management system, comprising: the system comprises a data acquisition module, a data analysis module, a user access module, a knowledge integration module, a knowledge tracing module and a visual management module;
The data acquisition module is used for acquiring multi-source data in a target data source by utilizing a data acquisition engine based on a keyword technology, and cleaning, screening and uniformly preprocessing the multi-source data;
The data analysis module is used for constructing an open knowledge processing network, excavating multi-source data in a distributed excavating mode, and realizing data safety transmission and storage by combining encryption technology;
The user access module is used for building a user access scoring system, monitoring user behaviors in real time, classifying user grades based on user history behaviors and giving user rights of different grades;
The knowledge integration module is used for integrating the scattered knowledge content into an integration platform, and building an integrated and dynamically updated consultation access cluster based on a Bayesian network and user behaviors;
The knowledge tracing module is used for carrying a data information tracing mechanism and automatically positioning and tracing abnormal knowledge content and illegal consultation behaviors in the whole process of consultation;
The visual management module is used for comprehensively managing and dynamically displaying knowledge content, participating users and system working conditions by utilizing a real-time monitoring result and a visual technology.
2. The integrated whole process consultation knowledge management system according to claim 1, wherein the data analysis module comprises an open network sub-module, a distributed mining sub-module, a global carding sub-module and an encrypted communication sub-module;
The open network sub-module is used for defining knowledge association rules, extracting concept elements of mass existing knowledge data by using a semi-supervised learning method, and integrating and constructing an open knowledge base;
The distributed mining sub-module is used for providing distributed mining sub-nodes, and the mining sub-nodes mine the acquired multi-source data by utilizing a clue association and relationship reasoning mode on the basis of the knowledge base to acquire knowledge content and concept elements corresponding to the knowledge content;
The global carding sub-module is used for providing a global carding center which is in communication connection with the excavating sub-node, acquiring and carding knowledge excavating results, and storing the knowledge content and concept elements thereof into the knowledge base to realize dynamic updating of the knowledge base;
The encryption communication sub-module is used for establishing an encryption communication channel between the mining sub-node and the global carding center, setting encryption authentication for the mining sub-node, and only the mining sub-node after the encryption authentication has the authority to access the knowledge base.
3. The integrated management system of whole process consultation knowledge according to claim 2, wherein the open network sub-module comprises an association rule definition unit, a semi-supervised learning labeling unit, a concept element extraction unit and a knowledge base construction unit;
the association rule definition unit is used for defining knowledge association rules based on domain knowledge, text analysis and keyword matching, and establishing extraction and labeling bases and rules of existing knowledge data;
The semi-supervised learning labeling unit is used for labeling mass existing knowledge data on the basis of the knowledge association rule by utilizing a semi-supervised learning mode;
the concept element extraction unit is used for extracting concept elements from the existing knowledge data, wherein the concept elements comprise data types, data entities, data attributes and data relationships;
the knowledge base construction unit is used for integrating the existing knowledge data which are marked and extracted into a database of an open network to create a knowledge base which meets the whole process consultation.
4. The integrated management system of whole process consultation knowledge according to claim 3, wherein the user access module comprises an access record sub-module, a consultation browsing sub-module, an uploading sharing sub-module, a behavior monitoring sub-module, a level evaluation sub-module and a permission management sub-module;
The access recording sub-module is used for providing verification and authentication of user identity information and recording and managing login access of the whole process consultation integrated platform of the user;
The consultation browsing sub-module is used for providing a user consultation retrieval function, retrieving knowledge content corresponding to the retrieval from the knowledge base according to consultation information input by the user for the user to browse;
The uploading sharing sub-module is used for providing a user uploading sharing function, and the user automatically uploads, modifies or answers the knowledge content about the consultation information and verifies and validates the answer content;
The behavior monitoring sub-module is used for monitoring and recording behavior interaction information of users in the consultation process, wherein the behavior interaction information comprises consultation information, click information, browsing information, downloading information and uploading information, and generating respective consultation log base of each user according to the behavior interaction information;
the grade evaluation sub-module is used for evaluating the grade of the user according to the behavior interaction information and dividing the user into an authenticated user, an active user and a common user;
the permission management sub-module is used for managing the user permission of the user in the consultation process and giving the user permission of different levels to the users of different user levels.
5. The system of claim 4, wherein the knowledge integration module comprises an integration classification sub-module, a consultation model sub-module, a cluster reasoning sub-module, a dynamic updating sub-module and a feedback evaluation sub-module;
The integrated classification sub-module is used for integrating the interface of the knowledge base into the integrated platform, and the integrated platform carries out induction classification according to the concept elements of the knowledge content;
The consultation model sub-module is used for constructing a consultation access model according to the consultation log library of the authentication user or the active user, and analyzing and calculating consultation parameters of the authentication user or the active user in an active time period by utilizing the consultation access model;
the cluster reasoning sub-module is used for reasoning the consultation access clusters of the user in the active time period by using a Bayesian network to obtain a consultation knowledge cluster which is exclusive to the user and is dynamically updated;
the dynamic updating sub-module is used for updating the active time period of the integrated platform of the participation of the user, and updating the simplified log library and the consultation access cluster along with the updating synchronization of the active time period;
And the feedback evaluation sub-module is used for collecting objective evaluation of the consultation access cluster by the user.
6. The integrated management system of whole process consultation knowledge according to claim 5, wherein the consultation model submodule includes a log screening unit, a frequency counting unit and a probability analysis unit;
The log screening unit is used for setting an active time period, filtering and screening the consultation log library in the active time period, and obtaining a simplified log library after the processing is finished;
The frequency counting unit is used for counting the frequency of each consultation item consulted by the authentication user or the active user in the simplified log library and taking the frequency as the consultation frequency of the consultation item;
The probability analysis unit is used for calculating the ratio of the total frequency of all consultation items in the reduced log library, and the calculation expression is as the prior probability:
Where P (x i) represents the prior probability of the counseling term x i;
x i represents the ith consulting term in the condensed log library;
p xi represents the counseling frequency of counseling item x i;
m represents the number of consultation items in the reduced log library;
p xm represents the consultation frequency of the mth consultation item in the reduced log library.
7. The integrated management system of whole process consultation knowledge according to claim 6, wherein the cluster reasoning submodule includes a frequency ordering unit, a node measuring unit, a node testing unit, a path optimizing unit and a cluster generating unit;
The frequency ordering unit is used for taking the consultation items as nodes of a Bayesian network, and arranging all the consultation items in the simplified log library in descending order according to the consultation frequency to obtain a frequency-reducing queue consisting of the nodes;
The node measurement unit is used for calculating the relevance measurement of two nodes by utilizing mutual information between two adjacent nodes, counting node pairs with the relevance measurement larger than a measurement threshold value, connecting arcs of an initial connection diagram according to the sequence of the down-conversion queue to form an initial arc set, and counting all node pairs which meet the relevance measurement and have open paths between the nodes again to form a node pair set;
The node testing unit is used for searching a minimum blocking set of each node pair in the node pair set, performing an independence test on the node pair by utilizing node pair mutual information, and if the mutual information is larger than an independent threshold value, merging the node pair with an initial arc set to obtain a new initial arc set;
the path optimizing unit is used for judging the arcs in the new initial arc set, deleting the arcs if an open path exists between the node pairs forming the arcs, searching the minimum obstruction set of the node pairs, and performing an independence test again until the mutual information of the node pairs is smaller than an independent threshold value, and reserving the minimum obstruction set of the node pairs to obtain a consultation item cluster of the Bayesian network;
the cluster generating unit is used for traversing the simplified log library, estimating the network parameters of each consultation item by using a probability estimation formula, and combining the network parameters of each consultation item into the consultation item cluster to obtain a complete consultation knowledge cluster.
8. The integrated management system of whole process consultation knowledge according to claim 7, wherein the knowledge traceability module comprises an anomaly detection sub-module, a traceability marking sub-module, a traceability inquiry sub-module and a monitoring and early warning sub-module;
The abnormality detection sub-module is used for monitoring the knowledge base and the consultation process and monitoring existing abnormality information in real time, wherein the abnormality information comprises abnormal knowledge content and illegal consultation behaviors;
The tracing mark sub-module is used for embedding a tracing mark into the knowledge content in the knowledge base;
the tracing and inquiring sub-module is used for inquiring and tracing the abnormal information according to the tracing mark to acquire the data source, the change history and the access history of the abnormal information;
The monitoring and early warning sub-module is used for monitoring whether abnormal information exists in the knowledge base and the consultation process in real time, and triggering an alarm or a notification after judging that the abnormal information exists.
9. The whole process consultation knowledge integrated management system according to claim 8, wherein the traceability marking submodule comprises a metadata generation unit, an identifier unit, an audit log unit and a permission control unit;
The metadata generation unit is used for generating metadata of the knowledge content, wherein the metadata comprises acquisition time, modification time, a digger, a modifier and data version information;
The identifier unit is used for packaging each knowledge content, the concept elements and metadata of the knowledge content together and generating an identifier unique to the knowledge content; the audit log unit is used for recording consultation access and modification events of the knowledge content, wherein the modification events comprise user identifications, time stamps and modification types, and storing to form an audit log;
the right control unit is used for managing the access, modification or examination operation right of the user.
10. An integrated whole process consulting knowledge management method for implementing an application of the integrated whole process consulting knowledge management system as claimed in any one of claims 1-9, characterized in that the method comprises the steps of:
s1, acquiring multi-source data in a target data source by utilizing a data acquisition engine based on a keyword technology, and cleaning, screening and uniformly preprocessing the multi-source data;
S2, constructing an open knowledge processing network, mining multi-source data in a distributed mining mode, and summarizing and combining the multi-source data to a global carding center through distributed mining child nodes to form a knowledge base;
s3, building a user access scoring system, monitoring user behaviors in real time, classifying user grades based on user history behaviors, giving user rights of different grades, and recording and generating a user consultation log library;
S4, integrating the knowledge base and the scattered knowledge content into an integrated platform, and building an integrated and dynamically updated consultation access cluster based on a Bayesian network and the consultation log base;
s5, automatically positioning and tracking abnormal knowledge content and illegal consultation behaviors in the whole process of consultation by using an abnormal monitoring mode, acquiring abnormal information and carrying out early warning correction;
and S6, comprehensively managing and dynamically displaying knowledge content, participating users and system working conditions by utilizing a real-time monitoring result and a visualization technology.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410147592.3A CN117829291B (en) | 2024-02-02 | Whole-process consultation knowledge integrated management system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410147592.3A CN117829291B (en) | 2024-02-02 | Whole-process consultation knowledge integrated management system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117829291A CN117829291A (en) | 2024-04-05 |
| CN117829291B true CN117829291B (en) | 2024-07-16 |
Family
ID=
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108829704A (en) * | 2018-04-28 | 2018-11-16 | 安徽瑞来宝信息科技有限公司 | Big data distributed mining analysis service technology |
| CN114266486A (en) * | 2021-12-24 | 2022-04-01 | 桂林电子科技大学 | AHP-FCE method-based risk evaluation method for whole-process cost consultation service |
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108829704A (en) * | 2018-04-28 | 2018-11-16 | 安徽瑞来宝信息科技有限公司 | Big data distributed mining analysis service technology |
| CN114266486A (en) * | 2021-12-24 | 2022-04-01 | 桂林电子科技大学 | AHP-FCE method-based risk evaluation method for whole-process cost consultation service |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Schröer et al. | A systematic literature review on applying CRISP-DM process model | |
| Costantini et al. | Digital forensics and investigations meet artificial intelligence | |
| Bavota et al. | Methodbook: Recommending move method refactorings via relational topic models | |
| Burattin et al. | Online discovery of declarative process models from event streams | |
| CN110008288A (en) | The construction method in the knowledge mapping library for Analysis of Network Malfunction and its application | |
| Baier et al. | Matching events and activities by integrating behavioral aspects and label analysis | |
| Hossain et al. | Belief‐rule‐based expert systems for evaluation of e‐government: a case study | |
| CN111680153A (en) | Big data authentication method and system based on knowledge graph | |
| US20220114603A1 (en) | Systems and methods for tracking data shared with third parties using artificial intelligence-machine learning | |
| Arshad et al. | Formal knowledge model for online social network forensics | |
| Bykau et al. | Fine-grained controversy detection in Wikipedia | |
| CN115309913A (en) | Deep learning-based financial data risk identification method and system | |
| Martínez-Fernández et al. | Towards automated data integration in software analytics | |
| CN113779261B (en) | Quality evaluation method and device of knowledge graph, computer equipment and storage medium | |
| Sarirah Husin et al. | Process mining approach to analyze user navigation behavior of a news website | |
| Okoye et al. | Semantic fuzzy mining: Enhancement of process models and event logs analysis from syntactic to conceptual level | |
| Pauwels et al. | Detecting and explaining drifts in yearly grant applications | |
| CN117829291B (en) | Whole-process consultation knowledge integrated management system and method | |
| Rodrigues et al. | Privacy threat modeling language | |
| Roubtsova et al. | KPIs and their properties defined with the EXTREME method | |
| CN117829291A (en) | Whole-process consultation knowledge integrated management system and method | |
| CN115274121A (en) | Health medical data management method, system, electronic device and storage medium | |
| Alhabashneh et al. | Adaptive information retrieval system based on fuzzy profiling | |
| Kettler et al. | Towards a knowledge base of business process redesign: forming the structure | |
| Žontar et al. | Adoption of object-oriented software metrics for ontology evaluation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |