CN116702069A - Medium destroying method based on state sensing - Google Patents
Medium destroying method based on state sensing Download PDFInfo
- Publication number
- CN116702069A CN116702069A CN202310989246.5A CN202310989246A CN116702069A CN 116702069 A CN116702069 A CN 116702069A CN 202310989246 A CN202310989246 A CN 202310989246A CN 116702069 A CN116702069 A CN 116702069A
- Authority
- CN
- China
- Prior art keywords
- destroying
- data
- medium
- destroyed
- destruction
- 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 49
- 238000005516 engineering process Methods 0.000 claims abstract description 16
- 230000006378 damage Effects 0.000 claims description 56
- 238000012549 training Methods 0.000 claims description 29
- 238000012545 processing Methods 0.000 claims description 27
- 238000001514 detection method Methods 0.000 claims description 24
- 238000004422 calculation algorithm Methods 0.000 claims description 19
- 238000003066 decision tree Methods 0.000 claims description 19
- 239000000126 substance Substances 0.000 claims description 18
- 238000013527 convolutional neural network Methods 0.000 claims description 17
- 238000004458 analytical method Methods 0.000 claims description 14
- 238000007781 pre-processing Methods 0.000 claims description 12
- 230000003287 optical effect Effects 0.000 claims description 10
- 238000013473 artificial intelligence Methods 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 8
- 238000003909 pattern recognition Methods 0.000 claims description 8
- 238000004140 cleaning Methods 0.000 claims description 6
- 239000000284 extract Substances 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 239000000203 mixture Substances 0.000 claims description 4
- 238000013501 data transformation Methods 0.000 claims description 3
- 230000002708 enhancing effect Effects 0.000 claims description 3
- 230000006870 function Effects 0.000 claims description 3
- 230000010354 integration Effects 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 claims description 3
- 239000002245 particle Substances 0.000 claims description 3
- 238000005192 partition Methods 0.000 claims description 3
- 238000011176 pooling Methods 0.000 claims description 3
- 238000000638 solvent extraction Methods 0.000 claims description 3
- 238000005520 cutting process Methods 0.000 claims description 2
- 238000000197 pyrolysis Methods 0.000 claims description 2
- 238000003860 storage Methods 0.000 claims description 2
- 230000003301 hydrolyzing effect Effects 0.000 claims 1
- 230000001590 oxidative effect Effects 0.000 claims 1
- 230000001603 reducing effect Effects 0.000 claims 1
- 230000000694 effects Effects 0.000 abstract description 5
- 230000008569 process Effects 0.000 description 7
- 239000000969 carrier Substances 0.000 description 3
- 239000012634 fragment Substances 0.000 description 3
- 230000003631 expected effect Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 239000000155 melt Substances 0.000 description 2
- 238000002844 melting Methods 0.000 description 2
- 230000008018 melting Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000007062 hydrolysis Effects 0.000 description 1
- 238000006460 hydrolysis reaction Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000002932 luster Substances 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000003647 oxidation Effects 0.000 description 1
- 238000007254 oxidation reaction Methods 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000006722 reduction reaction Methods 0.000 description 1
- 239000002904 solvent Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B09—DISPOSAL OF SOLID WASTE; RECLAMATION OF CONTAMINATED SOIL
- B09B—DISPOSAL OF SOLID WASTE NOT OTHERWISE PROVIDED FOR
- B09B3/00—Destroying solid waste or transforming solid waste into something useful or harmless
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B09—DISPOSAL OF SOLID WASTE; RECLAMATION OF CONTAMINATED SOIL
- B09B—DISPOSAL OF SOLID WASTE NOT OTHERWISE PROVIDED FOR
- B09B3/00—Destroying solid waste or transforming solid waste into something useful or harmless
- B09B3/40—Destroying solid waste or transforming solid waste into something useful or harmless involving thermal treatment, e.g. evaporation
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B09—DISPOSAL OF SOLID WASTE; RECLAMATION OF CONTAMINATED SOIL
- B09B—DISPOSAL OF SOLID WASTE NOT OTHERWISE PROVIDED FOR
- B09B3/00—Destroying solid waste or transforming solid waste into something useful or harmless
- B09B3/70—Chemical treatment, e.g. pH adjustment or oxidation
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F23—COMBUSTION APPARATUS; COMBUSTION PROCESSES
- F23G—CREMATION FURNACES; CONSUMING WASTE PRODUCTS BY COMBUSTION
- F23G7/00—Incinerators or other apparatus for consuming industrial waste, e.g. chemicals
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/18—Extraction of features or characteristics of the image
- G06V30/1801—Detecting partial patterns, e.g. edges or contours, or configurations, e.g. loops, corners, strokes or intersections
- G06V30/18019—Detecting partial patterns, e.g. edges or contours, or configurations, e.g. loops, corners, strokes or intersections by matching or filtering
- G06V30/18038—Biologically-inspired filters, e.g. difference of Gaussians [DoG], Gabor filters
- G06V30/18048—Biologically-inspired filters, e.g. difference of Gaussians [DoG], Gabor filters with interaction between the responses of different filters, e.g. cortical complex cells
- G06V30/18057—Integrating the filters into a hierarchical structure, e.g. convolutional neural networks [CNN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/19—Recognition using electronic means
- G06V30/191—Design or setup of recognition systems or techniques; Extraction of features in feature space; Clustering techniques; Blind source separation
- G06V30/19173—Classification techniques
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B09—DISPOSAL OF SOLID WASTE; RECLAMATION OF CONTAMINATED SOIL
- B09B—DISPOSAL OF SOLID WASTE NOT OTHERWISE PROVIDED FOR
- B09B2101/00—Type of solid waste
- B09B2101/15—Electronic waste
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Environmental & Geological Engineering (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Databases & Information Systems (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Biodiversity & Conservation Biology (AREA)
- Mechanical Engineering (AREA)
- Thermal Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Chemical Kinetics & Catalysis (AREA)
- General Chemical & Material Sciences (AREA)
- Toxicology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of destroying media, in particular to a method for destroying media based on state sensing, which comprises the following steps: collecting various physical state parameters of a medium to be destroyed, wherein the parameters comprise temperature, humidity and pressure; the method comprises the steps of reading and analyzing graphic data of a medium to be destroyed by utilizing a graphic recognition technology; determining a destroying mode and destroying degree of a medium to be destroyed based on the physical state parameters and the graphic data; according to the determined destroying mode and destroying degree, executing destroying operation; after the destroying operation is finished, detecting the destroyed residues to verify the completion condition of the destroying operation. According to the invention, through dynamically reading and analyzing the physical state parameters and the graphic data of the medium to be destroyed, the most suitable destroying mode and degree can be intelligently selected according to specific conditions, so that the destroying efficiency is enhanced, the reliability of the destroying effect is ensured, and the capability of data security guarantee is obviously improved.
Description
Technical Field
The invention relates to the technical field of destroying media, in particular to a method for destroying media based on state sensing.
Background
In the field of data security, the destruction of data carriers has an important meaning, in general, after the data carriers (including paper files, optical discs, magnetic tapes, hard discs, etc.) are used or damaged, in order to prevent the sensitive information contained therein from being illegally acquired and utilized, the conventional data carrier destruction method mainly depends on manual operations, such as manually shredding paper, magnetic tapes or optical discs, or using special destruction devices to physically impact the hard discs, however, there are many problems in these conventional methods, firstly, the manual operation efficiency is low, and destruction may not be thorough due to negligence, and secondly, a single destruction method may not be suitable for various data carriers of different types, and the destruction degree may not be flexibly adjusted.
In this context, a state-sensing-based data carrier destruction method has been developed, in which physical state parameters (such as temperature, humidity, pressure, etc.) and graphic data of a data carrier are read and analyzed, and then a destruction mode and degree are automatically determined according to an analysis result, and the method mainly uses machine learning technologies such as decision trees, convolutional neural networks, etc. to implement intelligent decision, however, the current state-sensing-based data carrier destruction method has many problems, for example, when the current method processes graphic data, feature extraction and classification of the graphic data are often ignored, so that the accuracy of the destruction decision is not high, and in addition, after the destruction operation is finished, the current method often neglects to detect the destroyed residues, so that the expected effect cannot be ensured each time of the destruction operation.
Therefore, a new state-sensing-based data carrier destroying method is urgently needed, which can effectively solve the problems, improve the efficiency and accuracy of data carrier destroying work, and simultaneously ensure the reliability and safety of destroying operation.
Disclosure of Invention
Based on the above purpose, the invention provides a method for destroying media based on state sensing.
A method of state-aware based media destruction, comprising the steps of:
step one: collecting various physical state parameters of a medium to be destroyed, wherein the parameters comprise temperature, humidity and pressure;
step two: the method comprises the steps of reading and analyzing graphic data of a medium to be destroyed by utilizing a graphic recognition technology;
step three: determining a destroying mode and destroying degree of a medium to be destroyed based on the physical state parameters and the graphic data;
step four: according to the determined destroying mode and destroying degree, executing destroying operation;
step five: after the destroying operation is finished, detecting the residue after destroying to verify the completion condition of the destroying operation;
wherein the destroying mode comprises physical destroying, chemical destroying or thermal destroying.
Further, the specific step of collecting each physical state parameter of the medium to be destroyed in the first step includes:
monitoring a medium to be destroyed in real time by using sensor equipment, wherein the sensor equipment comprises a temperature sensor, a humidity sensor and a pressure sensor;
the collected physical state parameters are transmitted to a data processing module, the data processing module converts the collected physical state parameters into readable and analyzed electric signals, wherein sensor equipment is distributed at each part of a medium to be destroyed so as to comprehensively acquire the state information of the medium, and the data processing module has a data cleaning function and accurately extracts all the physical state parameters and provides accurate data support for decision making.
Furthermore, the data processing module is internally provided with an artificial intelligent algorithm, the artificial intelligent algorithm improves the capability of identifying and analyzing physical state parameters and graphic data by learning and training historical data, and the data processing module also comprises a preprocessing sub-module for data preprocessing, wherein the processing mode comprises data cleaning, data integration and data transformation.
Further, the artificial intelligence algorithm adopts a decision tree algorithm, specifically: the decision tree is trained according to the following formula:
for training data set D, its Entropy (Entropy) is defined as:
where p_k is the probability that the kth sample appears in D;
we choose a as the optimal partitioning attribute, i.e. under the condition of attribute a, the information gain of D is maximum:
wherein E (D|A) represents the conditional entropy of D under the condition of the attribute A, and the calculation formula is as follows:
wherein,,
the |D≡v| represents the number of samples of the sample subset of the property A that takes the V-th value, V is the possible value number of A;
training dataset D: physical state parameters such as temperature, humidity and pressure of the medium, a reading result of graphic data, a corresponding destroying mode and degree;
p_k: probability of occurrence of the kth destruction mode in the training data set D;
e (D): entropy of training dataset D, representing the degree of uncertainty or confusion of D;
a: the attributes selected to partition the training data set D, including any physical state parameters of the medium or any characteristics of the graphical data;
g (D, a): information gain of the attribute A to the training data set D;
e (d|a): based on the value of attribute a, training the conditional entropy of dataset D, representing the uncertainty of D under this condition;
v: the number of possible values of attribute a.
Furthermore, the pattern recognition technology in the second step is based on a convolutional neural network (Convolutional Neural Networks, CNN), and advanced features of the pattern data are extracted through multi-layer convolutional and pooling operations, so as to be used for efficiently and accurately classifying or recognizing the pattern data, and specifically comprises the following steps: CNNs are used to identify specific symbols, text or images in the graphic data, which assist in determining the manner and extent to which the medium is destroyed.
Further, based on the pattern recognition technology, the recognition step of the medium to be destroyed comprises four steps of preprocessing, feature extraction, classification judgment and feedback,
in the preprocessing step, the quality of the graphic data is improved by adjusting the image size, enhancing the contrast, and removing noise;
the feature extraction step uses CNN to automatically identify and extract key features in the graphic data;
in the classifying judging step, classifying the graphic data based on the characteristics extracted in the step, and identifying whether specific symbols, characters or images containing sensitive information are contained;
in the feedback step, the classification judgment result is fed back to the data processing module, and the destruction mode and degree are determined by combining the physical state parameters.
Further, the physical destroying mode comprises crushing, cutting and tearing modes; the chemical destroying mode comprises oxidation, reduction and hydrolysis modes; the heat energy destroying mode comprises combustion, pyrolysis and high-temperature steam treatment.
Further, the destroying degree comprises complete destroying and partial destroying, and the partial destroying is performed according to specific information contained in the graphic data.
Further, the detection operation in the fifth step comprises physical detection, chemical analysis and optical detection, wherein,
physical detection includes measuring the weight, volume, particle size of the residue;
chemical analysis includes analysis of the composition, pH, and chemical properties of the residue;
optical detection involves observation of the color, gloss, transparency of the residue.
Further, the medium to be destroyed includes paper files, optical discs, hard disks or other storage devices containing sensitive information.
The invention has the beneficial effects that:
according to the invention, through dynamically reading and analyzing the physical state parameters and the graphic data of the medium to be destroyed, the most suitable destroying mode and degree can be intelligently selected according to specific conditions, so that not only is the destroying efficiency enhanced, but also the reliability of the destroying effect ensured, the capability of data security assurance is obviously improved, and a decision tree algorithm and a neural network technology are introduced, so that the decision of the destroying mode and degree is more scientific and accurate, especially when the graphic data is processed, the identification precision of the graphic data is improved through automatic feature extraction, and more accurate basis is provided for destroying decisions.
After the destroying operation is finished, the method detects the residue after destroying, can verify the completion condition of the destroying operation in time, ensures that the expected effect can be achieved during each destroying, further improves the reliability and the safety of the system, adjusts and optimizes the calculation model according to the actual destroying effect, ensures that the system has higher intelligent level, can adapt to more complex and variable destroying requirements, and provides a novel, effective and safe data carrier destroying method.
Drawings
In order to more clearly illustrate the invention or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only of the invention and that other drawings can be obtained from them without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a destroying method according to an embodiment of the present invention;
fig. 2 is a schematic diagram of a pattern recognition technique according to an embodiment of the invention.
Detailed Description
The present invention will be further described in detail with reference to specific embodiments in order to make the objects, technical solutions and advantages of the present invention more apparent.
It is to be noted that unless otherwise defined, technical or scientific terms used herein should be taken in a general sense as understood by one of ordinary skill in the art to which the present invention belongs. The terms "first," "second," and the like, as used herein, do not denote any order, quantity, or importance, but rather are used to distinguish one element from another. The word "comprising" or "comprises", and the like, means that elements or items preceding the word are included in the element or item listed after the word and equivalents thereof, but does not exclude other elements or items. The terms "connected" or "connected," and the like, are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "upper", "lower", "left", "right", etc. are used merely to indicate relative positional relationships, which may also be changed when the absolute position of the object to be described is changed.
Example 1
As shown in fig. 1-2, a method for destroying media based on state sensing includes the following steps:
step one: collecting various physical state parameters of a medium to be destroyed, wherein the parameters comprise temperature, humidity and pressure;
step two: the method comprises the steps of reading and analyzing graphic data of a medium to be destroyed by utilizing a graphic recognition technology;
step three: determining a destroying mode and destroying degree of a medium to be destroyed based on the physical state parameters and the graphic data;
step four: according to the determined destroying mode and destroying degree, executing destroying operation;
step five: after the destroying operation is finished, detecting the destroyed residues to verify the completion condition of the destroying operation.
The specific steps of collecting each physical state parameter of the medium to be destroyed in the first step include:
monitoring a medium to be destroyed in real time by using sensor equipment, wherein the sensor equipment comprises a temperature sensor, a humidity sensor and a pressure sensor;
the acquired physical state parameters are transmitted to a data processing module, the data processing module converts the acquired physical state parameters into readable and analyzed electric signals, wherein sensor equipment is distributed at each part of a medium to be destroyed so as to comprehensively acquire state information of the medium, the data processing module can be an independent hardware device or a software module integrated in other devices, in the transmission process, a wired or wireless mode or an encryption technology can be adopted to protect the safety of transmitted data, and the data processing module has a data cleaning function and can accurately extract all physical state parameters and provide accurate data support for decision making.
The data processing module is internally provided with an artificial intelligence algorithm, the artificial intelligence algorithm improves the capability of recognizing and analyzing physical state parameters and graphic data by learning and training historical data, the data processing module also comprises a preprocessing sub-module for preprocessing data, the processing mode comprises data cleaning, data integration and data transformation, the artificial intelligence algorithm can adjust model parameters according to real-time feedback so as to realize dynamic optimization, the computing equipment can select proper computing capability according to actual needs, including but not limited to GPU and TPU, so as to ensure the processing speed and accuracy, and when the artificial intelligence algorithm processes the data, the technology of multithreading, multitasking parallel processing and the like can be adopted so as to improve the data processing efficiency.
The artificial intelligence algorithm adopts a decision tree algorithm, and specifically comprises the following steps: the decision tree is a tree structure in which each internal node represents a decision on an attribute, each branch represents the output of a decision result, and each final leaf node represents a decision result. In the present invention, decision trees can be used to analyze physical state parameters and graphical data and determine the manner and extent of destruction based on this information.
Specifically, the decision tree is trained according to the following formula:
for training data set D, its Entropy (Entropy) is defined as:
where p_k is the probability that the kth sample appears in D;
we choose a as the optimal partitioning attribute, i.e. under the condition of attribute a, the information gain of D is maximum:
wherein E (D|A) represents the conditional entropy of D under the condition of the attribute A, and the calculation formula is as follows:
wherein,,
the |D≡v| represents the number of samples of the sample subset of the property A that takes the V-th value, V is the possible value number of A;
training dataset D: physical state parameters such as temperature, humidity and pressure of the medium, and a reading result of the graphic data, a corresponding destroying mode and degree (complete destroying or partial destroying);
p_k: the probability of the kth destruction means occurring in the training data set D, for example, if we have two destruction means, namely complete destruction and partial destruction, then p_1 and p_2 may represent the probabilities of complete destruction and partial destruction in all training samples, respectively;
e (D): entropy of the training data set D represents uncertainty or confusion degree of the D, in the medium destruction scheme, if all training samples select the same destruction mode, E (D) is 0 and represents no uncertainty, and if the selection probability of each destruction mode is equal, E (D) reaches the maximum value and represents the maximum uncertainty;
a: the attributes selected to partition the training data set D, including any physical state parameters of the medium or any characteristics of the graphical data;
g (D, a): the information gain of the attribute A to the training data set D represents how much the uncertainty of D is reduced after knowing the value of the attribute A, and the attribute with the maximum information gain is selected as the optimal dividing attribute;
e (d|a): based on the value of attribute a, training the conditional entropy of dataset D, representing the uncertainty of D under this condition;
v: the number of possible values of attribute a, for example, if a represents the temperature of the medium and we divide the temperature into three levels "low", "medium" and "high", then V is equal to 3;
this process is repeated until a stop condition is met, e.g., all attributes have been used, or all samples belong to the same category;
in the decision process of medium destruction, for example, we can select physical state parameters and graphic data of the medium to be destroyed as input attributes, destroy mode and degree as classification labels, and obtain a decision tree model through training. In the actual decision process, the actual physical state parameters and graphic data of the medium to be destroyed can be judged through a decision tree model to obtain a decision result of the destruction mode and degree.
The pattern recognition technology in the second step is based on a convolutional neural network (Convolutional Neural Networks, CNN), the CNN shows excellent performance in processing pattern data, and advanced features of the pattern data are extracted through multi-layer convolution and pooling operations and are used for efficiently and accurately classifying or recognizing the pattern data, and specifically comprises the following steps: the CNN is used for identifying specific symbols, characters or images in the graphic data to assist in determining the mode and degree of destroying media, and in addition, the CNN model can be pretrained in a migration learning mode, such as a model trained on a large number of image data sets (such as ImageNet) is used, so that the model training efficiency and the identification accuracy are greatly improved. In the using process, the CNN model can also perform online learning according to new graphic data, and dynamically optimize model parameters so as to cope with various complicated and changeable graphic data.
Based on the pattern recognition technology, the recognition step of the medium to be destroyed comprises four steps of preprocessing, feature extraction, classification judgment and feedback,
in the preprocessing step, the quality of the graphic data is improved by adjusting the image size, enhancing the contrast, and removing noise;
the feature extraction step uses CNN to automatically identify and extract key features in the graphic data;
in the classifying judging step, classifying the graphic data based on the characteristics extracted in the step, and identifying whether specific symbols, characters or images containing sensitive information are contained;
in the feedback step, the classification judgment result is fed back to the data processing module, and the destruction mode and degree are determined by combining the physical state parameters;
in all four steps, the pattern recognition technique can apply deep learning and other machine learning algorithms to improve recognition accuracy and processing efficiency.
The destroying degree comprises complete destroying and partial destroying according to specific information contained in the graphic data, for example, if the graphic data contains marks of sensitive information to the specific parts, only the parts can be destroyed, other parts can be reserved, or if the importance of the information represented by the graphic data to a medium to be destroyed is low, the partial destroying can be selected, in the decision of the destroying degree, the destroying degree can be dynamically determined by utilizing the decision tree algorithm and combining the physical state parameters of the medium to be destroyed with the graphic data, for example, the destroying degree can be set as a classification label of a decision tree, the physical state parameters and the graphic data are used as input, a decision tree model is obtained through training, and in the actual decision process, the decision result of the destroying degree can be obtained through the decision tree model according to the actual physical state parameters and the graphic data of the medium to be destroyed.
The detection operation in the fifth step comprises physical detection, chemical analysis and optical detection, wherein,
physical detection includes measuring the weight, volume, particle size of the residue;
chemical analysis includes analysis of the composition, pH, and chemical properties of the residue;
the optical detection comprises the steps of observing the color, the luster, the transparency and the like of the residues, if the detection result shows that the destroyed residues meet the preset standard, the destruction operation is considered to be completed, otherwise, the destruction mode and the destruction degree are adjusted according to the detection result, and the destruction operation is carried out again.
The present embodiment is based on physical means for data carrier destruction
In this embodiment, the medium to be destroyed is a paper file containing sensitive information, firstly, physical state parameters of the file, such as thickness, hardness and the like of the paper are read and analyzed, meanwhile, graphic data on the file are identified and analyzed through an image identification technology, for example, whether the file contains a specific sensitive information mark is judged, then, according to analysis results of the physical state parameters and the graphic data, a decision tree algorithm is utilized to decide to destroy the paper in a physical way, for example, a high-speed cutter is utilized to cut the paper into fine fragments, after the destruction is finished, residual fragments are detected, for example, the completeness of the destruction is verified by observing the size and the shape of the fragments, and if the detection result meets a preset standard, the destruction operation is considered to be completed; otherwise, the destroying mode or degree is adjusted according to the detection result, and the destroying operation is carried out again.
Example 2: data carrier destruction based on chemical means
In this embodiment, the medium to be destroyed is a plastic card containing sensitive information, firstly, physical state parameters of the card, such as type, hardness and the like of the plastic, are read and analyzed, and at the same time, graphic data on the card are identified and analyzed through an image identification technology, for example, whether the card contains a specific sensitive information mark is judged, and then, according to the analysis result of the physical state parameters and the graphic data, the decision tree algorithm is used for deciding to destroy the medium chemically, for example, using a solvent suitable for the plastic. After the destruction is completed, the residual solution is detected, such as by chemical analysis to verify the thoroughness of the destruction. If the detection result meets the preset standard, the destruction operation is considered to be completed; otherwise, the destroying mode or degree is adjusted according to the detection result, and the destroying operation is carried out again.
Example 3: data carrier destruction based on thermal energy mode
In this embodiment, the medium to be destroyed is a hard disk containing sensitive information, firstly, physical state parameters of the hard disk, such as materials, sizes and the like of the hard disk, are read and analyzed, and meanwhile, graphic data on the hard disk is identified and analyzed through an image identification technology, for example, whether the hard disk contains a specific sensitive information mark is judged, then, according to analysis results of the physical state parameters and the graphic data, a decision tree algorithm is utilized to decide to destroy in a thermal energy mode, and after deciding to destroy in the thermal energy mode, for example, a high-temperature furnace is utilized to melt. The hard disk is subjected to high-temperature treatment to melt the materials of the hard disk, so that all data in the hard disk are thoroughly destroyed. After the end of the destruction, the residual melt is detected, for example by observing the physical state and chemical properties of the melt to verify the thoroughness of the destruction. This can be accomplished by cooling the melt and then measuring the hardness, color, chemical composition, etc. If the detection result meets the preset standard, the destruction operation is considered to be completed; otherwise, the destroying mode or degree is adjusted according to the detection result, and the destroying operation is performed again, for example, if it is detected that some parts of the hard disk are not completely melted, the melting temperature may need to be increased or the melting time may need to be prolonged.
Through the embodiment, the medium destroying method based on state sensing can flexibly cope with different types of medium to be destroyed, and high-efficiency, accurate and safe destroying operation is realized. Whether in a physical mode, a chemical mode or a thermal energy mode, the method can be finely adjusted and controlled according to specific conditions so as to achieve the optimal destroying effect.
In order to evaluate the effect of the medium destruction method based on state sensing, a series of experiments are carried out, and the results are compared and analyzed, and the following experimental data table is provided:
as can be seen from an experimental data table, the state-sensing-based medium destroying method provided by the invention can successfully destroy paper files, plastic cards or hard disks, and the destroyed detection results meet preset standards to prove the completion condition of destroying operation. The method and the device can effectively identify the state of the medium to be destroyed, intelligently select a proper destroying mode according to the state parameters and the graphic data, and verify the thoroughly destroyed by detecting after destroying, thereby ensuring the safety of the data. Therefore, the invention provides an efficient, accurate and safe data carrier destruction method.
Those of ordinary skill in the art will appreciate that: the discussion of any of the embodiments above is merely exemplary and is not intended to suggest that the scope of the invention is limited to these examples; the technical features of the above embodiments or in the different embodiments may also be combined within the idea of the invention, the steps may be implemented in any order and there are many other variations of the different aspects of the invention as described above, which are not provided in detail for the sake of brevity.
The present invention is intended to embrace all such alternatives, modifications and variances which fall within the broad scope of the appended claims. Therefore, any omission, modification, equivalent replacement, improvement, etc. of the present invention should be included in the scope of the present invention.
Claims (10)
1. A method for destroying media based on state awareness, comprising the steps of:
step one: collecting various physical state parameters of a medium to be destroyed, wherein the parameters comprise temperature, humidity and pressure;
step two: the method comprises the steps of reading and analyzing graphic data of a medium to be destroyed by utilizing a graphic recognition technology;
step three: determining a destroying mode and destroying degree of a medium to be destroyed based on the physical state parameters and the graphic data;
step four: according to the determined destroying mode and destroying degree, executing destroying operation;
step five: after the destroying operation is finished, detecting the residue after destroying to verify the completion condition of the destroying operation;
wherein the destroying mode comprises physical destroying, chemical destroying or thermal destroying.
2. The method for destroying media based on state sensing according to claim 1, wherein the specific step of collecting each physical state parameter of the media to be destroyed in the step one comprises:
monitoring a medium to be destroyed in real time by using sensor equipment, wherein the sensor equipment comprises a temperature sensor, a humidity sensor and a pressure sensor;
the collected physical state parameters are transmitted to a data processing module, the data processing module converts the collected physical state parameters into readable and analyzed electric signals, wherein sensor equipment is distributed at each part of a medium to be destroyed so as to comprehensively acquire the state information of the medium, and the data processing module has a data cleaning function and accurately extracts all the physical state parameters and provides accurate data support for decision making.
3. A method for destroying media based on state sensing according to claim 2, wherein said data processing module is built-in with an artificial intelligence algorithm which improves its ability to recognize and analyze physical state parameters and graphic data by learning and training historical data, said data processing module further comprises a preprocessing sub-module for data preprocessing, and the processing modes include data cleaning, data integration, and data transformation.
4. A method of state-aware based media destruction as in claim 3, wherein the artificial intelligence algorithm employs a decision tree algorithm, the decision tree being trained according to the following formula:
for training data set D, its Entropy (Entropy) is defined as:
where p_k is the probability that the kth sample appears in D;
we choose a as the optimal partitioning attribute, i.e. under the condition of attribute a, the information gain of D is maximum:
wherein E (D|A) represents the conditional entropy of D under the condition of the attribute A, and the calculation formula is as follows:
wherein,,
the |D≡v| represents the number of samples of the sample subset of the property A that takes the V-th value, V is the possible value number of A;
training dataset D: physical state parameters including temperature, humidity and pressure of the medium, a reading result of graphic data, and a corresponding destroying mode and degree;
p_k: probability of occurrence of the kth destruction mode in the training data set D;
e (D): entropy of training dataset D, representing the degree of uncertainty or confusion of D;
a: the attributes selected to partition the training data set D, including any physical state parameters of the medium or any characteristics of the graphical data;
g (D, a): information gain of the attribute A to the training data set D;
e (d|a): based on the value of attribute a, training the conditional entropy of dataset D, representing the uncertainty of D under this condition;
v: the number of possible values of attribute a.
5. A method for destroying media based on state sensing according to claim 3, wherein the pattern recognition technology in the second step is based on convolutional neural network, and the advanced features of the pattern data are extracted through multi-layer convolution and pooling operations, so as to effectively and accurately classify or recognize the pattern data, specifically: CNNs are used to identify specific symbols, text or images in the graphic data, which assist in determining the manner and extent to which the medium is destroyed.
6. The method for destroying medium according to claim 5, wherein said pattern recognition technique is based on a recognition procedure of medium to be destroyed comprising four steps of preprocessing, feature extraction, classification judgment and feedback,
in the preprocessing step, the quality of the graphic data is improved by adjusting the image size, enhancing the contrast, and removing noise;
in the feature extraction step: automatically identifying and extracting key features in the graphic data by using CNN;
in the classifying judging step, classifying the graphic data based on the characteristics extracted in the step, and identifying whether specific symbols, characters or images containing sensitive information are contained;
in the feedback step, the classification judgment result is fed back to the data processing module, and the destruction mode and degree are determined by combining the physical state parameters.
7. A method for destroying media based on state sensing according to claim 1, wherein said physical destroying means comprises breaking, cutting and tearing means, said chemical destroying means comprises oxidizing, reducing and hydrolyzing means, and said thermal destroying means comprises burning, pyrolysis and high temperature steam treatment.
8. A method of state-aware based media destruction according to claim 1, wherein the degree of destruction comprises complete destruction, partial destruction, the partial destruction being based on specific information contained in the graphical data.
9. A method for state-aware based destruction of media according to claim 1, wherein the detection in step five comprises physical detection, chemical analysis, optical detection, wherein,
physical detection includes measuring the weight, volume, particle size of the residue;
chemical analysis includes analysis of the composition, pH, and chemical properties of the residue;
optical detection involves observation of the color, gloss, transparency of the residue.
10. A method of state-aware based media destruction according to claim 1, wherein the media to be destroyed comprises paper files, optical discs, hard discs or other storage devices containing sensitive information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310989246.5A CN116702069B (en) | 2023-08-08 | 2023-08-08 | Medium destroying method based on state sensing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310989246.5A CN116702069B (en) | 2023-08-08 | 2023-08-08 | Medium destroying method based on state sensing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116702069A true CN116702069A (en) | 2023-09-05 |
| CN116702069B CN116702069B (en) | 2023-11-24 |
Family
ID=87826162
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310989246.5A Active CN116702069B (en) | 2023-08-08 | 2023-08-08 | Medium destroying method based on state sensing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116702069B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117407927A (en) * | 2023-12-15 | 2024-01-16 | 山东万里红信息技术有限公司 | Hard disk data destruction method, computer equipment and storage medium |
| CN117457032A (en) * | 2023-12-25 | 2024-01-26 | 山东万里红信息技术有限公司 | Storage medium destroying method based on volume identification |
| CN117688596A (en) * | 2024-02-04 | 2024-03-12 | 北京中超伟业信息安全技术股份有限公司 | Data destruction recognition processing system and method based on artificial intelligence |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070075168A1 (en) * | 2005-10-03 | 2007-04-05 | Herman Rodriguez | Method and apparatus for document destruction |
| CN105117302A (en) * | 2015-07-24 | 2015-12-02 | 厦门宇高信息科技有限公司 | Verification method for data destruction of storage medium |
| CN111105332A (en) * | 2019-12-19 | 2020-05-05 | 河北工业大学 | Highway intelligent pre-maintenance method and system based on artificial neural network |
| CN113435424A (en) * | 2021-08-27 | 2021-09-24 | 北京中超伟业信息安全技术股份有限公司 | Method and system for identifying destroying granularity of confidential medium |
| CN113673004A (en) * | 2021-08-09 | 2021-11-19 | 国网重庆市电力公司电力科学研究院 | Data destruction method based on classification |
| CN114528950A (en) * | 2022-04-24 | 2022-05-24 | 北京中超伟业信息安全技术股份有限公司 | Destroying method and system for identifying type of confidential medium based on three-dimensional point cloud |
| CN115502166A (en) * | 2022-08-24 | 2022-12-23 | 艾斯特国际安全技术（深圳）有限公司 | Certificate automatic identification damage method, system, device and storage medium |
| CN116109636A (en) * | 2023-04-13 | 2023-05-12 | 北京中超伟业信息安全技术股份有限公司 | Magnetic medium destruction processing method and system based on visual monitoring |
| US20230237405A1 (en) * | 2020-06-16 | 2023-07-27 | Tomokazu KANDA | Information recording meduim destruction device management method |
-
2023
- 2023-08-08 CN CN202310989246.5A patent/CN116702069B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070075168A1 (en) * | 2005-10-03 | 2007-04-05 | Herman Rodriguez | Method and apparatus for document destruction |
| CN105117302A (en) * | 2015-07-24 | 2015-12-02 | 厦门宇高信息科技有限公司 | Verification method for data destruction of storage medium |
| CN111105332A (en) * | 2019-12-19 | 2020-05-05 | 河北工业大学 | Highway intelligent pre-maintenance method and system based on artificial neural network |
| US20230237405A1 (en) * | 2020-06-16 | 2023-07-27 | Tomokazu KANDA | Information recording meduim destruction device management method |
| CN113673004A (en) * | 2021-08-09 | 2021-11-19 | 国网重庆市电力公司电力科学研究院 | Data destruction method based on classification |
| CN113435424A (en) * | 2021-08-27 | 2021-09-24 | 北京中超伟业信息安全技术股份有限公司 | Method and system for identifying destroying granularity of confidential medium |
| CN114528950A (en) * | 2022-04-24 | 2022-05-24 | 北京中超伟业信息安全技术股份有限公司 | Destroying method and system for identifying type of confidential medium based on three-dimensional point cloud |
| CN115502166A (en) * | 2022-08-24 | 2022-12-23 | 艾斯特国际安全技术（深圳）有限公司 | Certificate automatic identification damage method, system, device and storage medium |
| CN116109636A (en) * | 2023-04-13 | 2023-05-12 | 北京中超伟业信息安全技术股份有限公司 | Magnetic medium destruction processing method and system based on visual monitoring |
Non-Patent Citations (2)
| Title |
|---|
| MEI CHEN 等: ""The application of intelligent control algorithm in sanitation monitoring system"", 2017 2ND INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION ENGINEERING (ICRAE) * |
| 闫国卿 等: ""信息存储介质的安全销毁方法及资源化技术"", 《材料导报》, vol. 27, no. 2 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117407927A (en) * | 2023-12-15 | 2024-01-16 | 山东万里红信息技术有限公司 | Hard disk data destruction method, computer equipment and storage medium |
| CN117407927B (en) * | 2023-12-15 | 2024-03-22 | 山东万里红信息技术有限公司 | Hard disk data destruction method, computer equipment and storage medium |
| CN117457032A (en) * | 2023-12-25 | 2024-01-26 | 山东万里红信息技术有限公司 | Storage medium destroying method based on volume identification |
| CN117457032B (en) * | 2023-12-25 | 2024-03-22 | 山东万里红信息技术有限公司 | Storage medium destroying method based on volume identification |
| CN117688596A (en) * | 2024-02-04 | 2024-03-12 | 北京中超伟业信息安全技术股份有限公司 | Data destruction recognition processing system and method based on artificial intelligence |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116702069B (en) | 2023-11-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116702069B (en) | Medium destroying method based on state sensing | |
| Bayar et al. | Towards open set camera model identification using a deep learning framework | |
| CN107067006A (en) | A kind of method for recognizing verification code and system for serving data acquisition | |
| CN110414367B (en) | Time sequence behavior detection method based on GAN and SSN | |
| Mikołajczyk et al. | Towards explainable classifiers using the counterfactual approach-global explanations for discovering bias in data | |
| Öztürk et al. | Comparison of HOG, MSER, SIFT, FAST, LBP and CANNY features for cell detection in histopathological images | |
| Suryawanshi et al. | Comparative study of Malaria parasite detection using euclidean distance classifier & SVM | |
| CN113112498A (en) | Grape leaf scab identification method based on fine-grained countermeasure generation network | |
| Ellingsgaard et al. | Detecting fingerprint alterations by orientation field and minutiae orientation analysis | |
| Chen et al. | Effective candidate component extraction for text localization in born-digital images by combining text contours and stroke interior regions | |
| Sainin et al. | Malaysian medicinal plant leaf shape identification and classification | |
| CN117857088A (en) | Network traffic abnormality detection method, system, equipment and medium | |
| Khamis et al. | Comparison of Palm Oil Fresh Fruit Bunches (FFB) Ripeness Classification Technique using Deep Learning Method | |
| CN114677750A (en) | Intelligent mall face recognition system and method based on big data | |
| Fan et al. | A dynamic size-based time series feature and application in identification of zinc flotation working conditions | |
| CN114139617A (en) | New class target identification method and device based on deep clustering | |
| Kumar et al. | Pomegranate Quality Analysis and Classification Using Feature Extraction and Machine Learning | |
| CN110619273A (en) | Efficient iris recognition method and device | |
| Thomas et al. | A plant identification and recommendation system | |
| Pocevičė et al. | Approach for Tattoo Detection and Identification Based on YOLOv5 and Similarity Distance | |
| Hernández Díaz et al. | Software to Assist Visually Impaired People During the Craps Game Using Machine Learning on Python Platform | |
| CN113780084B (en) | Face data amplification method based on generation type countermeasure network, electronic equipment and storage medium | |
| CN115687616A (en) | Multi-dimensional text information classification and labeling model and method | |
| Ahmed et al. | Detection of Paddy Blast: An Image Processing Approach with Threshold based OTSU | |
| Ning et al. | Scene text detection based on component-level fusion and region-level verification |
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 |