CN115794798B - Market supervision informatization standard management and dynamic maintenance system and method - Google Patents
Market supervision informatization standard management and dynamic maintenance system and method Download PDFInfo
- Publication number
- CN115794798B CN115794798B CN202211591824.1A CN202211591824A CN115794798B CN 115794798 B CN115794798 B CN 115794798B CN 202211591824 A CN202211591824 A CN 202211591824A CN 115794798 B CN115794798 B CN 115794798B
- Authority
- CN
- China
- Prior art keywords
- standard
- data
- management
- informatization
- market supervision
- 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
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a market supervision informatization standard management and dynamic maintenance system and method, comprising an information input and acquisition unit, a standard classification unit, a standard detail creation unit, an editing management unit, a permission verification unit, an AI prediction unit and an association analysis unit, wherein a semantic information processing algorithm related to natural language processing is utilized to analyze standard files, the AI prediction unit trains a market supervision informatization standard management model through a training set and a testing set to obtain a market supervision informatization standard management and analysis model based on a BP neural network, and the similarity algorithm and the association analysis BP neural network are utilized to predict.
Description
Technical Field
The invention relates to the technical field of market supervision informatization and standardization, in particular to a market supervision informatization standard management and dynamic maintenance system and method.
Background
The current market supervision informatization construction faces a plurality of outstanding problems, such as: data format is not uniform, data quality is not high, information sharing is not smooth, system construction is not intensive, and the like. The informatization standardized construction is an important component part and basic work of informatization work, the establishment of a unified market supervision informatization standard system is a foundation for realizing the integration of market supervision informatization, and the information sharing and business collaboration support is provided for strengthening the unified specification of the market supervision informatization, improving the data quality and effectively developing information sharing and business collaboration. Since informatization construction is a very extensive system engineering involving a large number of standards and specifications, the standards and rules must be orderly arranged according to internal relations, and a complete informatization standard system is finally formed.
The existing market supervision informatization relates to a large number of standard files, a large number of established standards lack systematic management and maintenance, the standards are not classified clearly, the boundaries of all parts are not clear, and the establishment of blank fields of standard establishment and the enhancement of the requirements are not facilitated. In addition, the existing market supervision informatization standard analysis and processing process has a lot of defects, the standardized system is constructed mainly by manpower, the information acquisition is incomplete, the analysis is not fine, the standardized classification is lack of reasonable verification and the like, and the establishment and perfection of informatization standards cannot be systematically and integrally promoted.
Disclosure of Invention
The technical problem to be solved by the invention is that the traditional information standard system framework and the management of the detail list cannot be automated. The method can not automatically map a large number of established unordered standards into an ordered subsystem according to the common characters and regularity of the informatization standard system frameworks of various industries and departments, and demarcate various parts. No targeted analysis, maintenance, and prediction can be performed.
The invention provides the following technical scheme: a market regulatory informationized standard management and dynamic maintenance system, comprising:
the information input and acquisition unit is used for information input and acquisition of an informatization standard system framework and a detail table of each industry, and searching, inputting and updating of informatization related standards;
the standard classification unit is used for classifying the standard architecture into layers and categories;
the standard detail creation unit is used for creating market supervision informationized standard detail table data; the market supervision informationized standard detail table data comprise contents such as standard system numbers, standard names, versions, release dates, implementation dates, standard classification numbers, standard states and the like;
the editing management unit is used for editing and managing the informationized standard system framework and the standard detail table data;
the permission verification unit is used for matching with the operation permission of the verification management unit;
the AI prediction unit is used for analyzing the main content of the informationized related standard file based on AI, classifying and predicting the market supervision informationized standard detail table and dynamically adjusting the category according to the corresponding relation between the informationized standard system framework category and the standard file issued by each industry, and completing the management and dynamic maintenance of the market supervision informationized standard;
the association analysis unit is used for analyzing the informatization standards of each industry based on the market supervision informatization standard management and analysis model of the BP neural network and uniformly managing and predicting the market supervision informatization standards;
the output unit is used for outputting the update information of the framework category and the standard detail table of the market supervision informatization system;
the AI prediction unit analyzes and extracts standard document stems and keywords by collecting the corresponding relation between the informationized standard system frame categories and the standard detail list updating information issued by each industry, and performs classified prediction on the market supervision informationized standard detail list and dynamic adjustment on the standard system frame categories;
the AI prediction unit adopts a classification prediction model based on a BP neural network to carry out prediction analysis, wherein the BP neural network is provided with an input layer, an implicit layer and an output layer; the hidden layer adopts a tan sig function; the output layer adopts purelin function;
the input layer has detail table data characteristics and standard file data characteristics;
the output layer has standard system framework categories;
constructing a key feature model of a market supervision informatization standard, wherein the key feature model is shown in a formula (1), and generating a training set and a testing set according to the key feature model;
X(t)＝[X 1 (t),X 2 (t),X 3 (t),X 4 (t),X 5 (t),X 6 (t),X 7 (t),X 8 (t)] (1)
wherein: x (t) is a t-moment standard detail information set; x is X 1 (t) is the standard file data characteristic at the moment of t; x is X 2 (t) is a network security and management standard data feature at time t; x is X 3 (t) is the standard data characteristic of the data resource at the moment of t, X 4 (t) technical support standard data features at time t; x is X 5 (t) applying a standard data feature and X for time t 6 (t) is a time t infrastructure standard feature; x is X 7 (t) is a t-moment classification feature and X 8 (t) is a t-moment standard system frame feature; the classification prediction model based on the BP neural network is shown in a formula (2);
wherein: f (F) 7 () For the trained standard classification prediction model, F 8 () X is a trained standard system framework prediction model 7 (t+Δt) is the classification characteristic after Δt time, X 8 (t+Δt) is a standard architecture feature after Δt time;
the correlation analysis unit is used for carrying out correlation analysis on the BP neural network to predict based on the market supervision informatization standard management and analysis model of the BP neural network;
the AI prediction unit trains the market supervision informatization standard management data characteristics through a training set and a testing set to obtain a market supervision informatization standard management and analysis model based on the BP neural network, analyzes informatization standards of each industry by using a similarity algorithm and associated analysis, and performs unified management and prediction on the market supervision informatization standards.
Preferably, the AI prediction unit comprises a standard file data preprocessing module, a standard classification processing module and a market supervision informatization standard management module;
the data preprocessing module is used for carrying out semantic analysis, keyword extraction and data screening on the informationized standard data and removing redundant information;
the standard classification processing module is used for classifying related standards such as general universal standards, infrastructure standards, data standards, application support standards, business application standards, security standards, management standards and the like, and the standard classification processing module also comprises a design standard system framework, primary categories and secondary categories so as to construct a market supervision informationized standard detail table;
the market supervision informatization standard management module is used for managing a market supervision informatization standard system framework and a detail table, searching the latest release and update standard meeting the requirements according to the market supervision informatization related standard keywords extracted by the data preprocessing module, analyzing the classification of the standard by using the AI prediction unit, dynamically adjusting the standard system framework, updating the detail table and establishing a normalized maintenance mechanism.
Preferably, the AI prediction unit further comprises a contrast analysis module, wherein the contrast analysis module is used for predicting the BP neural network based on a similarity algorithm; specifically, analyzing the classified files based on semantic information processing algorithms related to natural language processing to obtain standard stems and keywords in the corresponding classified files, forming word segmentation, and predicting by using BP neural network of similarity algorithm;
the comparison analysis module calculates similarity S of the acquired training set and the test set file through a cosine similarity model j General purpose medicineCalculated by equation (3), as follows:
wherein A is i The method comprises the steps of (1) setting a set value of an ith word segmentation vector in a training set; b (B) i The method comprises the steps of (1) setting a set value of an ith word segmentation vector in a test set; cos (θ) is the cosine value of the corresponding word vector in the training set and test set files.
Preferably, the information input and collection unit performs information input and collection through AI automatic analysis and screening standard files.
Preferably, the association analysis unit specifically searches the frequent item set by adopting Apriori algorithm, and predicts through BP neural network.
Preferably, the standard classification processing module specifically supplements the data element, the information classification and the code secondary category, and increases the data quality secondary category; the method comprises the steps that a standard classification processing module is used for obtaining preset data standards, wherein the preset data standards comprise a general standard, an infrastructure standard, a data standard, an application support standard, a business application standard, a safety standard and a management standard; respectively constructing an ontology model according to the general standard, the infrastructure standard, the data standard, the application support standard, the business application standard, the security standard and the management standard; and constructing a corresponding knowledge graph according to the ontology model.
A market supervision informatization standard management and dynamic maintenance method comprises the following steps:
step one: acquiring information of an informatization standard system frame and a detail table of each industry, and training an AI prediction unit to obtain a market supervision informatization standard management and analysis model;
step two: carrying out semantic analysis, keyword extraction and data screening on the informationized standard file data, removing redundant information to form a key feature model, and characterizing the information data of the standard file object to obtain key features of the standard file object;
step three: according to the AI prediction unit and the key characteristics of the standard file object, analyzing and obtaining the classification characteristics of the standard file object;
step four: according to the classification characteristics of the standard file objects, training the market supervision informatization standard management model through a training set and a testing set to obtain a market supervision informatization standard management and analysis model based on the BP neural network, performing associated analysis on the BP neural network to analyze informatization standards of each industry, performing unified management and prediction on the market supervision informatization standards, and updating a market supervision informatization standard system framework and a detail table.
Preferably, the market supervision informatization standard management model is trained through a training set and a testing set to obtain a market supervision informatization standard management and analysis model based on the BP neural network, and the BP neural network is associated and analyzed to predict, specifically as follows:
(1) Mining frequent item sets of total data of different standard classification processing results by adopting an Apriori algorithm, and constructing the frequent item sets covering the sub-data of the different standard classification processing results;
(2) Pre-allocating memory for the unit arrays of the frequent item sets and the candidate item sets with the rule and the sizes of 1 and 2 respectively;
(3) Searching a frequent item set with the size of 1, namely a list of all items containing min Sup, searching a frequent item set with the size of more than or equal to 2, finding a rule with min Conf from the frequent item set, and pruning the candidate item set through the support degree based on the prior principle;
(4) Ordering the rules according to the confidence or support degree in descending order, and storing the rules in a text file to obtain the relevance of market supervision informationized standard information factors;
wherein the Support formula is Support (a, B) =p (a, B), and the Confidence formula is Confidence (a, B) =p (b|a); a binary value sort Flag is introduced indicating whether the rules should be ordered by support or confidence, when sort flag=1, the rules are ordered by support size, and when sort flag=2, the rules are ordered by confidence size.
Preferably, the method further comprises the step of obtaining the frequent item set of the total data of the standard classification processing result according to the preset minimum support threshold and the frequent item set of the standard classification processing result, wherein the frequent item set of the total data of the standard classification processing result is obtained as follows:
obtaining a minimum support count threshold according to the minimum support threshold and the number of transactions in the transaction data set; the transaction data set is a set of transactions contained in the total data;
calculating the support degree count of the frequent item set of each sub-data in the total data of the standard classification processing result by using a mapping reduction algorithm;
and taking the frequent item set of the sub-data with the support degree count in the standard classification processing result total data not smaller than the preset minimum support degree count threshold value as the frequent item set of the standard classification processing result total data.
Compared with the prior art, the invention has the following beneficial effects:
the invention creatively provides a market supervision informatization standard management and dynamic maintenance system, which utilizes big data technology to mine informatization standards of all the existing industries and departments at present and establish a standardized management and dynamic maintenance system.
The system can provide unified information collection and retrieval service for market supervision informatization standard management and maintenance work. Aiming at the particularity of the stable structure of the data element and the code set standard, the management of the data element and the code set of the issued market supervision informatization standard is realized, the data element and the code set are provided for a plurality of functions by establishing a database of the market supervision informatization standard management data element and the code set, the data standard requirement of continuous growth and change in the market supervision informatization standard management field is met, the support is provided for sharing and cooperating the market supervision informatization standard management information, the sharing interaction of the supervision data information of all levels of institutions and the coordination linkage of an application system are facilitated, the resultant force of the informatization construction of all levels of institutions is exerted, and the supervision efficiency and the service efficiency are greatly improved.
Drawings
FIG. 1 is a block diagram of a market regulatory informationized standard management and dynamic maintenance system;
FIG. 2 is a flow chart of a market supervision informatization standard management and dynamic maintenance method;
fig. 3 is a schematic diagram of a modular structure of an AI prediction unit in a market supervision informationized standard management and dynamic maintenance system.
Detailed Description
In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to specific embodiments thereof which are illustrated in the appended drawings.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways other than those described herein, and persons skilled in the art will readily appreciate that the present invention is not limited to the specific embodiments disclosed below.
Further, reference herein to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic can be included in at least one implementation of the invention. The appearances of the phrase "in one embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments.
Referring to fig. 1, 2 and 3, in one embodiment of the present invention, a system and a method for managing and dynamically maintaining market regulatory informationized standards are provided, the system includes:
the information input and acquisition unit is used for information input and acquisition of an informatization standard system framework and a detail table of each industry, and searching, inputting and updating of informatization related standards;
the standard classification unit is used for classifying the standard architecture into layers and categories;
the standard detail creation unit is used for creating market supervision informationized standard detail table data; the market supervision informationized standard detail table data comprise contents such as standard system numbers, standard names, versions, release dates, implementation dates, standard classification numbers, standard states and the like;
the editing management unit is used for editing and managing the informationized standard system framework and the standard detail table data;
the permission verification unit is used for matching with the operation permission of the verification management unit;
the AI prediction unit is used for analyzing the main content of the informationized related standard file based on AI, classifying and predicting the market supervision informationized standard detail table and dynamically adjusting the category according to the corresponding relation between the informationized standard system framework category and the standard file issued by each industry, and completing the management and dynamic maintenance of the market supervision informationized standard;
the association analysis unit is used for analyzing the informatization standards of each industry based on the market supervision informatization standard management and analysis model of the BP neural network and uniformly managing and predicting the market supervision informatization standards;
the output unit is used for outputting the update information of the framework category and the standard detail table of the market supervision informatization system;
the AI prediction unit adopts a classification prediction model based on a BP neural network to carry out prediction analysis, wherein the BP neural network is provided with an input layer, an implicit layer and an output layer; the hidden layer adopts a tan sig function; the output layer adopts purelin function;
the input layer has detail table data characteristics and standard file data characteristics;
the output layer has standard system framework categories;
constructing a key feature model of a market supervision informatization standard, wherein the key feature model is shown in a formula (1), and generating a training set and a testing set according to the key feature model;
X(t)＝[X 1 (t),X 2 (t),X 3 (t),X 4 (t),X 5 (t),X 6 (t),X 7 (t),X 8 (t)] (1)
wherein: x (t) is a t-moment standard detail information set; x is X 1 (t) is the standard file data characteristic at the moment of t; x is X 2 (t) is a network security and management standard data feature at time t; x is X 3 (t) is the standard data characteristic of the data resource at the moment of t, X 4 (t) technical support standard data features at time t; x is X 5 (t) applying a standard data feature and X for time t 6 (t) is a time t infrastructure standard feature; x is X 7 (t) is a t-moment classification feature and X 8 (t) is a t-moment standard system frame feature; the classification prediction model based on the BP neural network is shown in a formula (2);
wherein: f (F) 7 () For the trained standard classification prediction model, F 8 () X is a trained standard system framework prediction model 7 (t+Δt) is the classification characteristic after Δt time, X 8 (t+Δt) is a standard architecture feature after Δt time;
the correlation analysis unit is used for carrying out correlation analysis on the BP neural network to predict based on the market supervision informatization standard management and analysis model of the BP neural network;
the AI prediction unit trains the market supervision informatization standard management data characteristics through a training set and a testing set to obtain a market supervision informatization standard management and analysis model based on the BP neural network, analyzes informatization standards of each industry by using a similarity algorithm and associated analysis, and performs unified management and prediction on the market supervision informatization standards.
The AI prediction unit comprises a standard file data preprocessing module, a standard classification processing module and a market supervision informatization standard management module;
the data preprocessing module is used for carrying out semantic analysis, keyword extraction and data screening on the informationized standard data and removing redundant information;
the standard classification processing module is used for classifying related standards such as general universal standards, infrastructure standards, data standards, application support standards, business application standards, safety standards, management standards and the like, and the standard classification processing module also comprises a design standard system framework, primary categories and secondary categories so as to construct a market supervision informationized standard detail table;
the market supervision informatization standard management module is used for managing a market supervision informatization standard system frame and a detail table, searching the latest release and update standard meeting the requirements according to the market supervision informatization related standard keywords extracted by the data preprocessing module, analyzing the classification of the standard by using the AI prediction unit, dynamically adjusting the standard system frame, updating the detail table and establishing a normalized maintenance mechanism.
The AI prediction unit also comprises a contrast analysis module, wherein the contrast analysis module is used for predicting the BP neural network based on a similarity algorithm; specifically, analyzing the classified files based on semantic information processing algorithms related to natural language processing to obtain standard stems and keywords in the corresponding classified files, forming word segmentation, and predicting by using BP neural network of similarity algorithm;
the comparison analysis module calculates similarity S of the acquired training set and the test set file through a cosine similarity model j Calculated by equation (3), as follows:
wherein A is i The method comprises the steps of (1) setting a set value of an ith word segmentation vector in a training set; b (B) i The method comprises the steps of (1) setting a set value of an ith word segmentation vector in a test set; cos (θ) is the cosine value of the corresponding word vector in the training set and test set files.
The information input and acquisition unit performs information input and acquisition through AI automatic analysis and screening standard files.
The association analysis unit specifically searches frequent item sets by adopting an Apriori algorithm, and predicts through a BP neural network.
The standard classification processing module specifically supplements the data element, the information classification and the code secondary category, and increases the data quality secondary category; the method comprises the steps that a standard classification processing module is used for obtaining preset data standards, wherein the data standards comprise common standards, term standards, classification code standards, metadata standards and interface standards; constructing an ontology model according to a common standard, a term standard, a classification code standard, a metadata standard and an interface standard respectively; and constructing a corresponding knowledge graph according to the ontology model.
Referring to fig. 2, the present embodiment further provides a market supervision informatization standard management and dynamic maintenance method in combination with the above system, which includes the following steps:
step one: acquiring information of an informatization standard system frame and a detail table of each industry, and training an AI prediction unit to obtain a market supervision informatization standard management and analysis model;
step two: carrying out semantic analysis, keyword extraction and data screening on the informationized standard file data, removing redundant information to form a key feature model, and characterizing the information data of the standard file object to obtain key features of the standard file object;
step three: according to the AI prediction unit and the key characteristics of the standard file object, analyzing and obtaining the classification characteristics of the standard file object;
step four: according to the classification characteristics of the standard file objects, training the market supervision informatization standard management model through a training set and a testing set to obtain a market supervision informatization standard management and analysis model based on the BP neural network, performing associated analysis on the BP neural network to analyze informatization standards of each industry, performing unified management and prediction on the market supervision informatization standards, and updating a market supervision informatization standard system framework and a detail table.
Training the market supervision informatization standard management model through a training set and a testing set to obtain a market supervision informatization standard management and analysis model based on the BP neural network, and performing associated analysis on the BP neural network to predict, wherein the method comprises the following specific steps of:
(1) Mining frequent item sets of total data of different standard classification processing results by adopting an Apriori algorithm, and constructing the frequent item sets covering the sub-data of the different standard classification processing results;
(2) Pre-allocating memory for the unit arrays of the frequent item sets and the candidate item sets with the rule and the sizes of 1 and 2 respectively;
(3) Searching a frequent item set with the size of 1, namely a list of all items containing min Sup, searching a frequent item set with the size of more than or equal to 2, finding a rule with min Conf from the frequent item set, and pruning the candidate item set through the support degree based on the prior principle;
(4) Ordering the rules according to the confidence or support degree in descending order, and storing the rules in a text file to obtain the relevance of market supervision informationized standard information factors;
wherein the Support formula is Support (a, B) =p (a, B), and the Confidence formula is Confidence (a, B) =p (b|a); a binary value sort Flag is introduced indicating whether the rules should be ordered by support or confidence, when sort flag=1, the rules are ordered by support size, and when sort flag=2, the rules are ordered by confidence size.
The embodiment further includes obtaining a frequent item set of total data of the standard classification processing result according to a preset minimum support threshold and the frequent item set of the standard classification processing result, where the frequent item set of the total data of the standard classification processing result is as follows:
obtaining a minimum support count threshold according to the minimum support threshold and the number of transactions in the transaction data set; the transaction data set is a set formed by transactions contained in the total data of the standard classification processing result;
calculating the support degree count of the frequent item set of each sub-data in the total data of the standard classification processing result by using a mapping reduction algorithm;
and taking the frequent item set of the sub-data with the support degree count in the total data not smaller than the preset minimum support degree count threshold value as the frequent item set of the total data of the standard classification processing result.
In summary, the invention creatively provides a market supervision informatization standard management and dynamic maintenance system, the invention utilizes big data technology to mine a great deal of market supervision informatization data existing at present, and establishes a standardized management and dynamic maintenance system.
The system can provide unified information collection and retrieval service for market supervision informatization standard management and maintenance work. Aiming at the particularity of the stable structure of the data element and the code set standard, the management of the data element and the code set of the issued market supervision informatization standard is realized, the data element and the code set are provided for a plurality of functions by establishing a database of the market supervision informatization standard management data element and the code set, the data standard requirement of continuous growth and change in the market supervision informatization standard management field is met, the support is provided for sharing and cooperating the market supervision informatization standard management information, the sharing interaction of the supervision data information of all levels of institutions and the coordination linkage of an application system are facilitated, the resultant force of the informatization construction of all levels of institutions is exerted, and the supervision efficiency and the service efficiency are greatly improved.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on such understanding, the foregoing technical solutions may be embodied essentially or in part in the form of a software product, which may be stored in a computer-readable storage medium, such as a ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to perform the various embodiments or methods of some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (9)
1. A market regulatory informationized standard management and dynamic maintenance system, comprising:
the information input and acquisition unit is used for information input and acquisition of an informatization standard system framework and a detail table of each industry, and searching, inputting and updating of informatization related standards;
the standard classification unit is used for classifying the standard architecture into layers and categories;
the standard detail creation unit is used for creating market supervision informationized standard detail table data; the market supervision informationized standard detail table data comprise standard system numbers, standard names, versions, release dates, implementation dates, standard classification numbers and standard state contents;
the editing management unit is used for editing and managing the informationized standard system framework and the standard detail table data;
the permission verification unit is used for matching with the operation permission of the verification management unit;
the AI prediction unit is used for analyzing the main content of the informationized related standard file based on AI, classifying and predicting the market supervision informationized standard detail table and dynamically adjusting the category according to the corresponding relation between the informationized standard system framework category and the standard file issued by each industry, and completing the management and dynamic maintenance of the market supervision informationized standard;
the association analysis unit is used for analyzing the informatization standards of each industry based on the market supervision informatization standard management and analysis model of the BP neural network and uniformly managing and predicting the market supervision informatization standards;
the output unit is used for outputting the update information of the framework category and the standard detail table of the market supervision informatization system;
the AI prediction unit analyzes and extracts standard document stems and keywords by collecting the corresponding relation between the informationized standard system frame categories and the standard detail list updating information issued by each industry, and performs classified prediction on the market supervision informationized standard detail list and dynamic adjustment on the standard system frame categories;
the AI prediction unit adopts a classification prediction model based on a BP neural network to carry out prediction analysis, wherein the BP neural network is provided with an input layer, an implicit layer and an output layer; the hidden layer adopts a tan sig function; the output layer adopts purelin function;
the input layer has detail table data characteristics and standard file data characteristics;
the output layer has standard system framework categories;
constructing a key feature model of a market supervision informatization standard, wherein the key feature model is shown in a formula (1), and generating a training set and a testing set according to the key feature model;
X(t)＝[X 1 (t),X 2 (t),X 3 (t),X 4 (t),X 5 (t),X 6 (t),X 7 (t),X 8 (t)] (1)
wherein: x (t) is a t-moment standard detail information set; x is X 1 (t) is the standard file data characteristic at the moment of t; x is X 2 (t) is a network security and management standard data feature at time t; x is X 3 (t) is the standard data characteristic of the data resource at the moment of t, X 4 (t) technical support standard data features at time t; x is X 5 (t) applying a standard data feature and X for time t 6 (t) is a time t infrastructure standard feature; x is X 7 (t) is a t-moment classification feature and X 8 (t) is a t-moment standard system frame feature; the classification prediction model based on the BP neural network is shown in a formula (2);
wherein: f (F) 7 () For the trained standard classification prediction model, F 8 () X is a trained standard system framework prediction model 7 (t+Δt) is the classification characteristic after Δt time, X 8 (t+Δt) is a standard architecture feature after Δt time;
the AI prediction unit trains the market supervision informatization standard management data characteristics through a training set and a testing set to obtain a market supervision informatization standard management and analysis model based on the BP neural network, analyzes informatization standards of each industry by using a similarity algorithm and associated analysis, and performs unified management and prediction on the market supervision informatization standards.
2. The market supervision informatization standard management and dynamic maintenance system according to claim 1, wherein the AI prediction unit comprises a data preprocessing module, a standard classification processing module and a market supervision informatization standard management module;
the data preprocessing module is used for carrying out semantic analysis, keyword extraction and data screening on the informationized standard data and removing redundant information;
the standard classification processing module is used for classifying the general universal standard, the infrastructure standard, the data standard, the application support standard, the business application standard, the safety standard and the management standard related standard, and the standard classification processing module also comprises a design standard system framework, a primary category and a secondary category so as to construct a market supervision informationized standard detail table;
the market supervision informatization standard management module is used for managing a market supervision informatization standard system framework and a detail table, searching the latest release and update standard meeting the requirements according to the market supervision informatization related standard keywords extracted by the data preprocessing module, analyzing the classification of the standard by using the AI prediction unit, dynamically adjusting the standard system framework, updating the detail table and establishing a normalized maintenance mechanism.
3. The market supervision informationized standard management and dynamic maintenance system according to claim 1, wherein the AI prediction unit further comprises a contrast analysis module for predicting based on a BP neural network of a similarity algorithm; specifically, analyzing the classified files based on semantic information processing algorithms related to natural language processing to obtain standard stems and keywords in the corresponding classified files, forming word segmentation, and predicting by using BP neural network of similarity algorithm;
the comparison analysis module calculates similarity S of the acquired training set and the test set file through a cosine similarity model j Calculated by equation (3), as follows:
wherein A is i The method comprises the steps of (1) setting a set value of an ith word segmentation vector in a training set; b (B) i The method comprises the steps of (1) setting a set value of an ith word segmentation vector in a test set; cos (θ) is the cosine value of the corresponding word vector in the training set and test set files.
4. The market supervision informationized standard management and dynamic maintenance system according to claim 1, wherein the information input and collection unit performs information input and collection through AI automatic analysis and screening standard files.
5. The market supervision informationized standard management and dynamic maintenance system according to claim 1, wherein the association analysis unit is specifically configured to search frequent item sets by using Apriori algorithm, and predict by BP neural network.
6. The market regulatory informationized standard management and dynamic maintenance system according to claim 2, wherein said standard classification processing module specifically supplements data elements, information classifications and code secondary categories and adds data quality secondary categories; the method comprises the steps that a standard classification processing module is used for obtaining preset data standards, wherein the standards comprise general standards, infrastructure standards, data standards, application support standards, business application standards, safety standards and management standards;
the standard classification processing module respectively builds an ontology model according to the general standard, the infrastructure standard, the data standard, the application support standard, the business application standard, the security standard and the management standard;
and constructing a corresponding knowledge graph according to the ontology model.
7. A market supervision informatization standard management and dynamic maintenance method applied to the market supervision informatization standard management and dynamic maintenance system as claimed in claim 1, comprising the following steps:
step one: information data of market supervision objects are collected, information of each industry informatization standard system frame and detail table information are collected, and an AI prediction unit is trained to obtain a market supervision informatization standard management and analysis model;
step two: processing the informationized standard file data, carrying out semantic analysis, keyword extraction and data screening on the informationized standard file data, removing redundant information to form a key feature model, and characterizing the information data of the standard file object to obtain key features of the standard file object;
step three: according to the AI prediction unit and the key characteristics of the standard file object, analyzing and obtaining the classification characteristics of the standard file object;
step four: according to the classification characteristics of the standard file objects, training the market supervision informatization standard management model through a training set and a testing set to obtain a market supervision informatization standard management and analysis model based on the BP neural network, performing associated analysis on the BP neural network to analyze informatization standards of each industry, performing unified management and prediction on the market supervision informatization standards, and updating a market supervision informatization standard system framework and a detail table.
8. The method for managing and dynamically maintaining the market supervision informatization standard according to claim 7, wherein the market supervision informatization standard management model is trained by a training set and a test set to obtain a market supervision informatization standard management and analysis model based on the BP neural network, and the BP neural network is associated and analyzed to predict, specifically comprising the following steps:
(1) Mining frequent item sets of total data of different standard classification processing results by adopting an Apriori algorithm, and constructing the frequent item sets covering the sub-data of the different standard classification processing results;
(2) Pre-allocating memory for the unit arrays of the frequent item sets and the candidate item sets with the rule and the sizes of 1 and 2 respectively;
(3) Searching a frequent item set with the size of 1, namely a list of all items containing min Sup, searching a frequent item set with the size of more than or equal to 2, finding a rule with min Conf from the frequent item set, and pruning the candidate item set through the support degree based on the prior principle;
(4) Ordering the rules according to the confidence or support degree in descending order, and storing the rules in a text file to obtain the relevance of market supervision informationized standard information factors;
wherein the Support formula is Support (a, B) =p (a, B), and the Confidence formula is Confidence (a, B) =p (b|a); a binary value sort Flag is introduced indicating whether the rules should be ordered by support or confidence, when sort flag=1, the rules are ordered by support size, and when sort flag=2, the rules are ordered by confidence size.
9. The method for managing and dynamically maintaining the market supervision informatization standard according to claim 8, further comprising obtaining a frequent item set of total data of the standard classification processing result according to a preset minimum support threshold and the frequent item set of the standard classification processing result, wherein the frequent item set of the total data of the standard classification processing result is as follows:
obtaining a minimum support count threshold according to the minimum support threshold and the number of transactions in the transaction data set; the transaction data set is a set formed by transactions contained in the total data of the standard classification processing result;
calculating the support degree count of the frequent item set of each sub-data in the total data by using a mapping reduction algorithm;
and taking the frequent item set of the sub-data with the support degree count in the standard classification processing result total data not smaller than the preset minimum support degree count threshold value as the frequent item set of the standard classification processing result total data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211591824.1A CN115794798B (en) | 2022-12-12 | 2022-12-12 | Market supervision informatization standard management and dynamic maintenance system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211591824.1A CN115794798B (en) | 2022-12-12 | 2022-12-12 | Market supervision informatization standard management and dynamic maintenance system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115794798A CN115794798A (en) | 2023-03-14 |
| CN115794798B true CN115794798B (en) | 2023-09-15 |
Family
ID=85419342
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211591824.1A Active CN115794798B (en) | 2022-12-12 | 2022-12-12 | Market supervision informatization standard management and dynamic maintenance system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115794798B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117574318A (en) * | 2023-12-12 | 2024-02-20 | 江苏省工商行政管理局信息中心 | Market supervision information fusion platform based on multi-source data and method thereof |
| CN118013955A (en) * | 2024-04-08 | 2024-05-10 | 中国标准化研究院 | Standard information updating method based on association algorithm |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101365481B1 (en) * | 2013-04-25 | 2014-02-25 | 한양대학교 산학협력단 | System for generating and managing a portal for program management |
| CN109657947A (en) * | 2018-12-06 | 2019-04-19 | 西安交通大学 | A kind of method for detecting abnormality towards enterprises ' industry classification |
| CN111324602A (en) * | 2020-02-21 | 2020-06-23 | 上海软中信息技术有限公司 | Method for realizing financial big data oriented analysis visualization |
| CN111428307A (en) * | 2020-04-21 | 2020-07-17 | 广州高新工程顾问有限公司 | Indoor optimization design method and system based on BIM |
| CN112395854A (en) * | 2020-12-02 | 2021-02-23 | 中国标准化研究院 | Standard element consistency inspection method |
| CN114783540A (en) * | 2022-03-17 | 2022-07-22 | 中国科学院金属研究所 | Multi-element alloy performance prediction method based on particle swarm optimization BP neural network |
-
2022
- 2022-12-12 CN CN202211591824.1A patent/CN115794798B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101365481B1 (en) * | 2013-04-25 | 2014-02-25 | 한양대학교 산학협력단 | System for generating and managing a portal for program management |
| CN109657947A (en) * | 2018-12-06 | 2019-04-19 | 西安交通大学 | A kind of method for detecting abnormality towards enterprises ' industry classification |
| CN111324602A (en) * | 2020-02-21 | 2020-06-23 | 上海软中信息技术有限公司 | Method for realizing financial big data oriented analysis visualization |
| CN111428307A (en) * | 2020-04-21 | 2020-07-17 | 广州高新工程顾问有限公司 | Indoor optimization design method and system based on BIM |
| CN112395854A (en) * | 2020-12-02 | 2021-02-23 | 中国标准化研究院 | Standard element consistency inspection method |
| CN114783540A (en) * | 2022-03-17 | 2022-07-22 | 中国科学院金属研究所 | Multi-element alloy performance prediction method based on particle swarm optimization BP neural network |
Non-Patent Citations (1)
| Title |
|---|
| 基于客户细分和AdaBoost的电子商务客户流失预测研究;武小军;孟苏芳;;工业工程(第02期);第103-111页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115794798A (en) | 2023-03-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115794798B (en) | Market supervision informatization standard management and dynamic maintenance system and method | |
| US20210365486A1 (en) | Esg-based company evaluation device and an operation method thereof | |
| CN111767716B (en) | Method and device for determining enterprise multi-level industry information and computer equipment | |
| CN111967761B (en) | Knowledge graph-based monitoring and early warning method and device and electronic equipment | |
| CN112182246B (en) | Method, system, medium, and application for creating an enterprise representation through big data analysis | |
| CN109408574B (en) | Complaint responsibility confirmation system based on text mining technology | |
| CN113239130A (en) | Criminal judicial literature-based knowledge graph construction method and device, electronic equipment and storage medium | |
| CN111581193A (en) | Data processing method, device, computer system and storage medium | |
| CN113239208A (en) | Mark training model based on knowledge graph | |
| CN114491034B (en) | Text classification method and intelligent device | |
| CN115544272A (en) | Attention mechanism-based chemical accident cause knowledge graph construction method | |
| Taran et al. | Creating a brief review of judicial practice using clustering methods | |
| CN115879901B (en) | Intelligent personnel self-service platform | |
| US20050210382A1 (en) | System and method for performing functional analyses making use of a plurality of inputs | |
| CN109710730B (en) | Patrol information system and analysis method based on natural language analysis processing | |
| CN110888977B (en) | Text classification method, apparatus, computer device and storage medium | |
| Zhai et al. | TRIZ technical contradiction extraction method based on patent semantic space mapping | |
| CN112967759B (en) | DNA material evidence identification STR typing comparison method based on memory stack technology | |
| Lee et al. | Deep learning document analysis system based on keyword frequency and section centrality analysis | |
| CN115953041A (en) | Construction scheme and system of operator policy system | |
| CN115759253A (en) | Power grid operation and maintenance knowledge map construction method and system | |
| CN115618085A (en) | Interface data exposure detection method based on dynamic label | |
| CN115204393A (en) | Smart city knowledge ontology base construction method and device based on knowledge graph | |
| CN112988972A (en) | Administrative penalty file evaluation and checking method and system based on data model | |
| CN112818215A (en) | Product data processing method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |