CN113934780A - Asset management system and method based on data middleboxes - Google Patents
Asset management system and method based on data middleboxes Download PDFInfo
- Publication number
- CN113934780A CN113934780A CN202111532843.2A CN202111532843A CN113934780A CN 113934780 A CN113934780 A CN 113934780A CN 202111532843 A CN202111532843 A CN 202111532843A CN 113934780 A CN113934780 A CN 113934780A
- Authority
- CN
- China
- Prior art keywords
- data
- decision
- unit
- management
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 15
- 238000007726 management method Methods 0.000 claims abstract description 109
- 230000009471 action Effects 0.000 claims abstract description 52
- 238000011156 evaluation Methods 0.000 claims abstract description 45
- 238000004088 simulation Methods 0.000 claims abstract description 34
- 238000012937 correction Methods 0.000 claims abstract description 19
- 235000012907 honey Nutrition 0.000 claims description 49
- 238000004458 analytical method Methods 0.000 claims description 27
- 230000003044 adaptive effect Effects 0.000 claims description 24
- 238000012423 maintenance Methods 0.000 claims description 24
- 230000000694 effects Effects 0.000 claims description 19
- 238000010801 machine learning Methods 0.000 claims description 15
- 241000257303 Hymenoptera Species 0.000 claims description 10
- 230000007246 mechanism Effects 0.000 claims description 8
- 238000013079 data visualisation Methods 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 238000013523 data management Methods 0.000 claims description 3
- 230000006978 adaptation Effects 0.000 claims description 2
- 238000012549 training Methods 0.000 claims description 2
- 241000256844 Apis mellifera Species 0.000 description 10
- 230000002996 emotional effect Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000007418 data mining Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000008451 emotion Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 241000256837 Apidae Species 0.000 description 1
- 206010010144 Completed suicide Diseases 0.000 description 1
- 238000000342 Monte Carlo simulation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000013439 planning Methods 0.000 description 1
- 239000002244 precipitate Substances 0.000 description 1
- 239000000047 product Substances 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 238000012552 review Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/283—Multi-dimensional databases or data warehouses, e.g. MOLAP or ROLAP
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/248—Presentation of query results
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/25—Integrating or interfacing systems involving database management systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an asset management system and method based on a data middlebox, and belongs to the technical field of data asset management. The system comprises a login access module, a multi-source data acquisition module, a data asset management module, a decision simulation evaluation module and a correction module; the output end of the login access module is connected with the input end of the multi-source data acquisition module; the output end of the multi-source data acquisition module is connected with the input end of the data asset management module; the output end of the data asset management module is connected with the input end of the decision simulation evaluation module; and the output end of the decision simulation evaluation module is connected with the input end of the correction module. Meanwhile, the asset management method based on the data center platform is provided, a data isolated island can be opened, data assets can be deposited, the value sharing among data is realized, an action decision is constructed based on the data center platform, and the complex data application scene is met.
Description
Technical Field
The invention relates to the technical field of data asset management, in particular to an asset management system and method based on a data middlebox.
Background
The data center platform is essentially a data management system and comprises a global data warehouse planning, a data specification definition, a data modeling research and development, a data connection extraction, a data operation and maintenance monitoring, a data asset management tool and the like. The data center platform is a data integration platform, is not only built for data analysis and mining, but also has the more important function of serving as a data source of each service and providing data and computing services for a service system. The essence of the data center station is "data warehouse + data service middleware".
However, in the current technical means, the data center often exists only as a database, and management and analysis of data assets of the data center become an important problem, and how to construct a corresponding decision system through the data center and utilize a machine to output decisions to avoid being influenced by artificial emotions becomes an urgent problem to be solved.
In the current life, the data center is also commonly applied to the field of colleges and universities, but is often used for managing and controlling the whereabouts of students or collecting the information of the students, and the problems of learning, psychology and the like of the students which exist all the time cannot be solved.
Disclosure of Invention
The present invention is directed to an asset management system and method based on a data middlebox, so as to solve the problems in the background art.
In order to solve the technical problems, the invention provides the following technical scheme:
a data center based asset management system, the system comprising: the system comprises a login access module, a multi-source data acquisition module, a data asset management module, a decision simulation evaluation module and a correction module;
the login access module is used for multi-party login access, realizing data access, conversion, writing and caching, and establishing a connection among multiple parties; the multi-source data acquisition module is used for acquiring multi-source data, establishing an information database and establishing a data center; the data asset management module manages data of the data center in a machine learning mode, analyzes user preference, constructs an output decision and provides data visualization service; the decision simulation evaluation module is used for establishing an evaluation threshold value for the output decision simulation result adaptive value and accepting or rejecting the output decision; the correction module is used for constructing an iteration threshold, correcting the output decision and finally outputting the decision meeting the condition;
the output end of the login access module is connected with the input end of the multi-source data acquisition module; the output end of the multi-source data acquisition module is connected with the input end of the data asset management module; the output end of the data asset management module is connected with the input end of the decision simulation evaluation module; and the output end of the decision simulation evaluation module is connected with the input end of the correction module.
According to the technical scheme, the login access module comprises a user side login unit, a manager side login unit and an operation and maintenance side login unit;
the user side login unit is used for user side login, does not set an access key, and only sets a login name; the management party login unit is used for logging in by a management party and setting an access key, and the management party login unit can issue a decision to reach a user party; the operation and maintenance party login unit is used for logging in the operation and maintenance party and setting an access key, and the operation and maintenance party has the right to manage the operation and maintenance of the data structure;
the output end of the user side login unit is connected with the input end of the multi-source data acquisition module; the management side login unit is connected with the input ends of the multi-source data acquisition module and the user side login unit; and the output end of the operation and maintenance side login unit is connected with the input ends of the user side login unit and the management side login unit.
According to the technical scheme, the multi-source data acquisition module comprises a historical data acquisition unit and a data sorting unit;
the historical data acquisition unit is used for acquiring and storing historical user data and constructing a database; the data sorting unit is used for sorting data, constructing a data middle platform and providing data visualization service;
the output end of the historical data acquisition unit is connected with the input end of the data sorting unit; and the output end of the data sorting unit is connected with the input end of the data asset management module.
According to the technical scheme, the data asset management module comprises a machine learning analysis unit and a decision analysis management unit;
the machine learning analysis unit is used for managing historical data according to a machine learning mode, outputting user preference based on user action and constructing a management action decision; the decision analysis management unit is used for analyzing action decisions of a management party and discarding decisions which do not meet a threshold;
the output end of the machine learning analysis unit is connected with the input end of the decision analysis management unit; and the output end of the decision analysis management unit is connected with the input end of the decision simulation evaluation module.
According to the technical scheme, the decision simulation evaluation module comprises a simulation unit and an evaluation unit;
the simulation unit is used for establishing a simulation model for the action decision of the management party, simulating the action decision of the management party and constructing a decision result adaptive value; the evaluation unit is used for establishing an evaluation threshold value, evaluating and selecting according to the decision result adaptive value and outputting a management party action decision meeting the condition;
the output end of the analog unit is connected with the input end of the evaluation unit; the output end of the evaluation unit is connected with the input end of the correction module.
According to the technical scheme, the correction module comprises a correction unit and an output unit;
the correcting unit is used for correcting the action decision of the management party; the output unit is used for outputting the final action decision of the management party for the selection of the management party;
the output end of the correction unit is connected with the input end of the output unit.
A method for asset management based on a data center, the method comprising the steps of:
s1, acquiring multi-source data, establishing an information database, constructing a data middle platform, realizing data access, conversion, writing and caching, and setting a data access authority entry;
s2, managing historical data by machine learning, constructing product suggestions based on actions of a user, outputting user preferences, providing data visualization services, and establishing action decisions of a manager;
s3, constructing a training data set, carrying out action decision based on a simulation analysis model practice management party, obtaining a prediction result, constructing a decision effect evaluation platform, and outputting an evaluation condition;
s4, constructing new data search, adding, deleting or changing tag data for correction, repeating the steps S2-S3 until the corrected evaluation condition meets the evaluation threshold value, and outputting a corrected action decision of a management party.
According to the technical scheme, the data access authority entry comprises a data user side entry, a data manager side entry and a data operation and maintenance side entry;
the data user side entrance is used for the user side to log in; the data management party inlet is used for the login and entry of a management party, a secret key is arranged, and the management party has the authority to send instruction information to a user party; the data operation and maintenance side inlet is used for the operation and maintenance side to log in, a secret key is arranged, and the operation and maintenance side has the authority to manage the data.
According to the technical scheme, in the steps S2-S3, based on the idea of artificial bee colony algorithm, a machine learning model is constructed:
the artificial bee colony algorithm is a specific application of a colony intelligent idea, and is mainly characterized in that special information of problems does not need to be known, only the advantages and the disadvantages of the problems need to be compared, and finally, a global optimum value is highlighted in a colony through local optimization behaviors of each artificial bee individual, so that the convergence rate is high;
in the invention, college students are taken as an example, how to make management decisions of new students according to behavior data of historical past students is one of the problems to be solved by the invention, so that under the condition of being based on a data center, numerous management decisions are output, and only the advantages and disadvantages of various decisions need to be contrastively analyzed to output an optimal scheme, so that the interference of artificial emotion is avoided, and stable and accurate results are given by focusing on all student data.
Considering the decision as a honey source; taking the decision achievement adaptive value as the nectar amount of the nectar source; the bee collecting device is used for giving a decision according to a student portrait mechanism and setting the observation bees to select according to the given decision; setting up a new decision for the scout bees under the condition that the provided decision cannot meet the preset condition;
outputting a management party action decision based on the data center;
establishing a simulation analysis model to simulate all management action decisions and obtain an evaluation value;
constructing an evaluation threshold value, and abandoning the action decision of the management party lower than the evaluation threshold value;
establishing a simulation analysis model to simulate all management action decisions so as to obtain the nectar amount, namely the adaptive value of the decision result:
and constructing a decision effect evaluation platform, establishing a decision achievement adaptive value threshold, and abandoning the honey sources lower than the decision achievement adaptive value threshold.
According to the above technical solution, in step S4, the correcting includes the steps of:
s10-1, constructing new data search;
s10-2, searching based on the new data, adding, deleting or changing the tag data, and finding a new honey source;
s10-3, constructing a new management action decision based on the new honey source, outputting the new management action decision to a decision effect evaluation platform, and calculating a decision result adaptive value;
s10-4, keeping the output of the management action decision meeting the threshold, abandoning the management action decision not meeting the threshold, and repeating the steps S10-1 to S10-4.
Compared with the prior art, the invention has the following beneficial effects:
the invention can promote the datamation construction by constructing the data middling stage, solve the problem of global data convergence, get through the conventional data isolated island, precipitate the data assets, realize the value sharing among the data, meet the complex data application scene based on the data middling stage, greatly improve the data quality, output the action decision of a manager by using a machine learning mode through the conventional data investment of colleges and universities, effectively help managers to customize the related management strategy for the new generations entering the colleges and universities, and simultaneously help the new generations to be integrated into the campus as soon as possible and create a better learning environment.
The invention is also provided with a certain management mechanism, so that the high-efficiency cooperation of the roles of a user side, a manager side, an operation and maintenance side and the like is realized, and the cooperation efficiency among the roles is improved.
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 principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a schematic flow diagram of a data-centric asset management system and method of the present invention;
FIG. 2 is a schematic diagram of the steps of a method for asset management based on a data center station according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1-2, in the present embodiment:
constructing a data center of a college:
constructing a user party as a student user, a management party as a campus manager and an operation and maintenance party as a background data operation and maintenance person;
the student users comprise new student users and old student users;
constructing a student portrait mechanism, wherein the student portrait mechanism comprises student footprint analysis, student community activities, student learning level, student emotional disputes and the like;
in the embodiment, four types of student portrait mechanisms are selected, namely, student footprint analysis, student community activity, student learning level and student emotional dispute;
the student footprint analysis comprises a student frequent location, student back-to-bed time and the like;
the student community activities comprise communities in which students participate, community activity conditions and the like;
the learning level of the student comprises achievement points, exemption probability, research achievements and the like;
the student emotional disputes comprise student shelf events, suicide events and the like;
obtaining an initial decision solution according to historical data of old student users:
and (3) analyzing by using an artificial bee colony algorithm:
taking the decision as a honey source; taking the decision achievement adaptive value as the nectar amount of the nectar source; the bee collecting device is used for giving a decision according to a student portrait mechanism and setting the observation bees to select according to the given decision; setting up a new decision for the scout bees under the condition that the provided decision cannot meet the preset condition;
further acquiring a final decision as a management action decision;
the honey bee is characterized in that the decision specific meaning given by the student portrait mechanism is as follows:
for example, according to the fact that the number of activities of a student participating in the community is M and the corresponding emotional dispute event is 0, the decision can be obtained as suggesting that the number of activities of the newly participated in the community is M, wherein M is a constant; according to the fact that the number of activities of the other student participating in the community is N, the corresponding achievement point is S, S is a low level, and N is a constant, the decision can be obtained that the number of activities of the newly-born participating community is recommended not to exceed N;
the initial decision solution is to assign a random value within a value range to all dimensions of each honey source, so as to randomly generate initial honey sources, wherein the number of the honey sources is G;
constructing a maximum value G of the number of honey sources; searching a dimension maximum value D; the maximum iteration number H;
recording the optimal value so far, and performing search in the neighborhood by the bee, wherein the formula for searching the new honey source in the honey source neighborhood is as follows:
wherein,
represents the first
A honey source
To (1) a
The value of the dimension is calculated,
，
the representative neighborhood of the honey source is,
；
to take a value in
A random number over the interval;
represents a new source of honey;
and the observation bees perform preliminary selection on the new honey source and the old honey source by a greedy selection strategy, the adaptation values of the new honey source and the old honey source are compared, and a superior is selected:
the preliminary selection of the greedy selection policy comprises:
for example, the old honey source decision is that according to the fact that the number of activities of a student participating in the community is M and the corresponding emotional dispute event is 0, the decision can be obtained as suggesting that the number of activities of the newly-born community is M, and M is a constant; the new honey source decision is that according to the fact that the number of activities of a student participating in the community is M-1 and the corresponding emotional dispute event is 1, the decision can be obtained as the fact that the number of activities of the student newly participating in the community is suggested to be M-1, and M is a constant; the priority selection strategy is to suggest that the number of newly-born community activities is M;
observing bee basis probability after primary selection
Final selection is performed, probability formula:
wherein,
the adaptive value of the ith solution corresponds to the rich degree of the honey source, and the richer the honey source is, the greater the probability of being selected is; the richness degree of the honey source refers to the richness degree of decision-making, and the more decision-making quantity, the richer richness degree of the honey source is represented;
outputting the final action decision of the management party;
establishing a simulation analysis model to simulate all management action decisions so as to obtain the nectar amount, namely the adaptive value of the decision result:
the simulation analysis model is a Monte Carlo simulation analysis model;
constructing an initial input: decision items, student reverberation, social satisfaction, wind learning construction and comprehensive teaching level;
utilizing SPSS software to carry out data mining, taking the adaptive value of the decision result as a dependent variable and taking initial input as an independent variable, and establishing a linear regression function, which is marked as F (v);
constructing simulation parameters: the confidence level is recorded as E, and the running times are recorded as R;
under the simulation parameters, obtaining a simulation result as a decision result adaptive value;
establishing a threshold value of a decision achievement adaptive value, discarding honey sources which do not meet the threshold value, and converting honey bees corresponding to the discarded honey sources into reconnaissance bees;
the reconnaissance bee starts new search to obtain a new honey source:
wherein;
、
respectively represent
An upper and lower bound of dimensions;
refers to a random number in the interval of 0 to 1;
the above process is recorded as one iteration;
repeating all the steps according to the new honey source searched by the scout bees, calculating a final decision result adaptive value, reserving satisfied management action decisions, continuously abandoning unsatisfied conditions, and entering next iteration;
establishing the maximum iteration frequency, recording as H, terminating the decision selection when the iteration frequency reaches H, outputting the finally reserved action decision of the management party for the management party to review, and determining the final action decision of the management party;
and guiding the newborn baby according to the final action decision of the management party so as to ensure that the system can accurately help the newborn baby to be quickly integrated into the campus and create a good teaching environment.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that changes may be made in the embodiments and/or equivalents thereof without departing from the spirit and scope of the invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. An asset management system based on a data center station, characterized in that: the system comprises: the system comprises a login access module, a multi-source data acquisition module, a data asset management module, a decision simulation evaluation module and a correction module;
the login access module is used for multi-party login access, realizing data access, conversion, writing and caching, and establishing a connection among multiple parties; the multi-source data acquisition module is used for acquiring multi-source data, establishing an information database and establishing a data center; the data asset management module manages data of the data center in a machine learning mode, analyzes user preference, constructs an output decision and provides data visualization service; the decision simulation evaluation module is used for establishing an evaluation threshold value for the output decision simulation result adaptive value and accepting or rejecting the output decision; the correction module is used for constructing an iteration threshold, correcting the output decision and finally outputting the decision meeting the condition;
the output end of the login access module is connected with the input end of the multi-source data acquisition module; the output end of the multi-source data acquisition module is connected with the input end of the data asset management module; the output end of the data asset management module is connected with the input end of the decision simulation evaluation module; and the output end of the decision simulation evaluation module is connected with the input end of the correction module.
2. The asset management system based on a data center station of claim 1, wherein: the login access module comprises a user side login unit, a manager side login unit and an operation and maintenance side login unit;
the user side login unit is used for user side login, does not set an access key, and only sets a login name; the management party login unit is used for logging in by a management party and setting an access key, and the management party login unit can issue a decision to reach a user party; the operation and maintenance party login unit is used for logging in the operation and maintenance party and setting an access key, and the operation and maintenance party has the right to manage the operation and maintenance of the data structure;
the output end of the user side login unit is connected with the input end of the multi-source data acquisition module; the management side login unit is connected with the input ends of the multi-source data acquisition module and the user side login unit; and the output end of the operation and maintenance side login unit is connected with the input ends of the user side login unit and the management side login unit.
3. The asset management system based on a data center station of claim 1, wherein: the multi-source data acquisition module comprises a historical data acquisition unit and a data sorting unit;
the historical data acquisition unit is used for acquiring and storing historical user data and constructing a database; the data sorting unit is used for sorting data, constructing a data middle platform and providing data visualization service;
the output end of the historical data acquisition unit is connected with the input end of the data sorting unit; and the output end of the data sorting unit is connected with the input end of the data asset management module.
4. The asset management system based on a data center station of claim 1, wherein: the data asset management module comprises a machine learning analysis unit and a decision analysis management unit;
the machine learning analysis unit is used for managing historical data according to a machine learning mode, outputting user preference based on user action and constructing a management action decision; the decision analysis management unit is used for analyzing action decisions of a management party and discarding decisions which do not meet a threshold;
the output end of the machine learning analysis unit is connected with the input end of the decision analysis management unit; and the output end of the decision analysis management unit is connected with the input end of the decision simulation evaluation module.
5. The asset management system based on a data center station of claim 1, wherein: the decision simulation evaluation module comprises a simulation unit and an evaluation unit;
the simulation unit is used for establishing a simulation model for the action decision of the management party, simulating the action decision of the management party and constructing a decision result adaptive value; the evaluation unit is used for establishing an evaluation threshold value, evaluating and selecting according to the decision result adaptive value and outputting a management party action decision meeting the condition;
the output end of the analog unit is connected with the input end of the evaluation unit; the output end of the evaluation unit is connected with the input end of the correction module.
6. The asset management system based on a data center station of claim 1, wherein: the correction module comprises a correction unit and an output unit;
the correcting unit is used for correcting the action decision of the management party; the output unit is used for outputting the final action decision of the management party for the selection of the management party;
the output end of the correction unit is connected with the input end of the output unit.
7. An asset management method based on a data center station is characterized in that: the method comprises the following steps:
s1, acquiring multi-source data, establishing an information database, constructing a data middle platform, realizing data access, conversion, writing and caching, and setting a data access authority entry;
s2, managing historical data by machine learning, constructing product suggestions based on actions of a user, outputting user preferences, providing data visualization services, and establishing action decisions of a manager;
s3, constructing a training data set, carrying out action decision based on a simulation analysis model practice management party, obtaining a prediction result, constructing a decision effect evaluation platform, and outputting an evaluation condition;
s4, constructing new data search, adding, deleting or changing tag data for correction, repeating the steps S2-S3 until the corrected evaluation condition meets the evaluation threshold value, and outputting a corrected action decision of a management party.
8. The asset management method based on a data center station according to claim 7, wherein: the data access authority entry comprises a data user side entry, a data manager side entry and a data operation and maintenance side entry;
the data user side entrance is used for the user side to log in; the data management party inlet is used for the login and entry of a management party, a secret key is arranged, and the management party has the authority to send instruction information to a user party; the data operation and maintenance side inlet is used for the operation and maintenance side to log in, a secret key is arranged, and the operation and maintenance side has the authority to manage the data.
9. The asset management method based on a data center station according to claim 8, wherein: in steps S2-S3, based on the idea of artificial bee colony algorithm, a machine learning model is constructed:
considering the decision as a honey source; taking the decision achievement adaptive value as the nectar amount of the nectar source; the bee collecting device is used for giving a decision according to a student portrait mechanism and setting the observation bees to select according to the given decision; setting up a new decision for the scout bees under the condition that the provided decision cannot meet the preset condition;
constructing an initial decision solution;
the initial decision solution is to assign a random value within a value range to all dimensions of each honey source, so as to randomly generate initial honey sources, wherein the number of the honey sources is G;
constructing a maximum value G of the number of honey sources; searching a dimension maximum value D; the maximum iteration number H;
recording the optimal value so far, and performing search in the neighborhood by the bee, wherein the formula for searching the new honey source in the honey source neighborhood is as follows:
wherein,
represents the first
A honey source
To (1) a
The value of the dimension is calculated,
，
the representative neighborhood of the honey source is,
；
to take a value in
A random number over the interval;
represents a new source of honey;
and the observation bees perform preliminary selection on the new honey source and the old honey source by a greedy selection strategy, the adaptation values of the new honey source and the old honey source are compared, and a superior is selected:
observing bee basis probability after primary selection
Final selection is performed, probability formula:
wherein,
the adaptive value of the ith solution corresponds to the rich degree of the honey source, and the richer the honey source is, the greater the probability of being selected is; the richness degree of the honey source refers to the richness degree of decision-making, and the more decision-making quantity, the richer richness degree of the honey source is represented;
outputting a management party action decision based on the data center;
establishing a simulation analysis model to simulate all management action decisions and obtain an evaluation value;
constructing an evaluation threshold value, and abandoning the action decision of the management party lower than the evaluation threshold value;
establishing a simulation analysis model to simulate all management action decisions so as to obtain the nectar amount, namely the adaptive value of the decision result:
and constructing a decision effect evaluation platform, establishing a decision achievement adaptive value threshold, and abandoning the honey sources lower than the decision achievement adaptive value threshold.
10. The asset management method based on a data center station according to claim 9, wherein: in step S4, the correction includes the steps of:
s10-1, constructing new data search;
s10-2, searching based on the new data, adding, deleting or changing the tag data, and finding a new honey source;
s10-3, constructing a new management action decision based on the new honey source, outputting the new management action decision to a decision effect evaluation platform, and calculating a decision result adaptive value;
s10-4, keeping the output of the management action decision meeting the threshold, abandoning the management action decision not meeting the threshold, and repeating the steps S10-1 to S10-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111532843.2A CN113934780B (en) | 2021-12-15 | 2021-12-15 | Asset management system and method based on data middleboxes |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111532843.2A CN113934780B (en) | 2021-12-15 | 2021-12-15 | Asset management system and method based on data middleboxes |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113934780A true CN113934780A (en) | 2022-01-14 |
| CN113934780B CN113934780B (en) | 2022-04-05 |
Family
ID=79289131
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111532843.2A Active CN113934780B (en) | 2021-12-15 | 2021-12-15 | Asset management system and method based on data middleboxes |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113934780B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117670066A (en) * | 2024-01-31 | 2024-03-08 | 深圳市拜特科技股份有限公司 | Judicial management method, system, equipment and storage medium based on intelligent decision |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109343995A (en) * | 2018-10-25 | 2019-02-15 | 金税信息技术服务股份有限公司 | Intelligent O&M analysis system based on multi-source heterogeneous data fusion, machine learning and customer service robot |
| CN112365143A (en) * | 2020-11-05 | 2021-02-12 | 信雅达科技股份有限公司 | Middle platform system applied to financial enterprises |
| CN113706101A (en) * | 2021-08-24 | 2021-11-26 | 国家电网有限公司 | Power grid project management intelligent system architecture and method |
-
2021
- 2021-12-15 CN CN202111532843.2A patent/CN113934780B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109343995A (en) * | 2018-10-25 | 2019-02-15 | 金税信息技术服务股份有限公司 | Intelligent O&M analysis system based on multi-source heterogeneous data fusion, machine learning and customer service robot |
| CN112365143A (en) * | 2020-11-05 | 2021-02-12 | 信雅达科技股份有限公司 | Middle platform system applied to financial enterprises |
| CN113706101A (en) * | 2021-08-24 | 2021-11-26 | 国家电网有限公司 | Power grid project management intelligent system architecture and method |
Non-Patent Citations (1)
| Title |
|---|
| 何尧 等: "人工蜂群算法研究综述", 《计算机应用研究》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117670066A (en) * | 2024-01-31 | 2024-03-08 | 深圳市拜特科技股份有限公司 | Judicial management method, system, equipment and storage medium based on intelligent decision |
| CN117670066B (en) * | 2024-01-31 | 2024-05-17 | 深圳市拜特科技股份有限公司 | Questor management method, system, equipment and storage medium based on intelligent decision |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113934780B (en) | 2022-04-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Goldman | A guide to social epistemology | |
| CN112700688B (en) | Intelligent classroom teaching auxiliary system | |
| Anand et al. | Framework for modelling multi-stakeholder city logistics domain using the agent based modelling approach | |
| Corea et al. | Hacking the venture industry: An Early-stage Startups Investment framework for data-driven investors | |
| CN108596420A (en) | A kind of talent assessment system and method for Behavior-based control | |
| CN114567815B (en) | Pre-training-based adaptive learning system construction method and device for lessons | |
| Mayangsari et al. | Understanding a viable value co-creation model for a sustainable entrepreneurial system: a case study of Batik Solo industrial cluster | |
| CN113934780B (en) | Asset management system and method based on data middleboxes | |
| CN111723973A (en) | Learning effect optimization method based on user behavior causal relationship in MOOC log data | |
| García-Cabrera et al. | A dynamic model of technology-based opportunity recognition | |
| Mer et al. | Building trust in SWAT model scenarios through a multi-institutional approach in Uruguay | |
| Le Pira | Transport planning with stakeholders: An agent-based modelling approach | |
| CN112860973B (en) | Tissue health assessment method based on social network analysis | |
| Bouzayane et al. | Prediction method based DRSA to improve the individual knowledge appropriation in a collaborative learning environment: case of MOOCs | |
| Halbe | Participatory modelling in sustainability transitions research | |
| McKee et al. | A multi-agent reinforcement learning model of reputation and cooperation in human groups | |
| Stenstrom | Decision-making experiences of public library CEOs: A study exploring the roles of interpersonal influence and evidence in everyday practice | |
| Anderson et al. | Indonesia Network Infrastructures and Workforce Adequacy to Implement Machine Learning for Large-Scale Manufacturing | |
| Jiang et al. | Learning analytics in a blended computer education course | |
| Miao | A hybrid model for student grade prediction using support vector machine and neural network | |
| Li et al. | Intelligent Stable Monitoring Algorithm of Students' Online Learning Behavior Based on User Portrait | |
| Varga | Social Innovation for the Welfare of the Community | |
| Peterlin | Perceived trends in viewing the future by Croatian and Slovenian business students: Implications for managerial education | |
| Yuan | [Retracted] A Novel Model of Network Ideological Education in Universities Based on Learning Analysis for the Era of 5G Mobile Computing | |
| Ozen et al. | Analyzing strategic thoughts of corporations based on cognitive map |
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 | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A data center based asset management system and method Granted publication date: 20220405 Pledgee: Bank of Nanjing Co.,Ltd. Jiangning sub branch Pledgor: Nanjing ditavi Data Technology Co.,Ltd. Registration number: Y2024980021879 |