CN109543424A - Data-privacy guard method, device, system and storage medium - Google Patents
Data-privacy guard method, device, system and storage medium Download PDFInfo
- Publication number
- CN109543424A CN109543424A CN201811308408.XA CN201811308408A CN109543424A CN 109543424 A CN109543424 A CN 109543424A CN 201811308408 A CN201811308408 A CN 201811308408A CN 109543424 A CN109543424 A CN 109543424A
- Authority
- CN
- China
- Prior art keywords
- data
- initial data
- text
- privacy
- initial
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/606—Protecting data by securing the transmission between two devices or processes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/62—Protecting access to data via a platform, e.g. using keys or access control rules
- G06F21/6218—Protecting access to data via a platform, e.g. using keys or access control rules to a system of files or objects, e.g. local or distributed file system or database
- G06F21/6245—Protecting personal data, e.g. for financial or medical purposes
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Bioethics (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Computer Security & Cryptography (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Hardware Design (AREA)
- Medical Informatics (AREA)
- Databases & Information Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention provides a kind of data-privacy guard method, device, system and storage medium, this method, comprising: passes through and obtains the initial data that internet of things equipment is sent；Privacy detection is carried out to the initial data, if including private data in the initial data, the initial data is labeled as confidential data；Secret protection processing is carried out to the confidential data, the target data that obtains that treated；The target data is sent to corresponding intended recipient end.To realize in the initial data sent close to data source header side to internet of things equipment; privacy detection and secret protection processing are carried out using the method for machine learning; by the purpose at privacy treated data are sent to corresponding intended recipient end; to solve the safety problem during data distance data transmission; secret protection treatment effeciency is improved, manpower and material resources are saved.
Description
Technical field
The present invention relates to internet of things field more particularly to a kind of data-privacy guard method, device, system and storages
Medium.
Background technique
With the development of technology of Internet of things, various internet of things equipment can all generate huge data volume daily.In Internet of Things
It often include the private data of some users in the data that equipment generates, if do not protected these private datas,
It will cause the leakage of private data in Internet communication.
In the prior art, the data that internet of things equipment generates can be uniformly sent to background data center/Cloud Server, so
Data privacy detection is carried out by background server afterwards.And when carrying out private data differentiation, artificial screening is generally used, or
The mode of Keywords matching.
But the mode of artificial screening can expend a large amount of manpower and material resources, and be difficult to cover all data.And keyword
Matched mode is highly dependent on the keywords database included, can if the keyword in the keywords database included is not comprehensive
Cause the missing inspection of private data.In addition, data pass since internet of things equipment and background data center/Cloud Server are apart from far
It is defeated to need by multihop network, therefore be easy to reveal private data in transmission process.
Summary of the invention
The present invention provides a kind of data-privacy guard method, device, system and storage medium, with reality now close to data source
The initial data that head side sends internet of things equipment carries out privacy detection using the method for machine learning and secret protection is handled,
By privacy, treated that data are sent to the purpose at corresponding intended recipient end, to solve data distance data transmission process
In safety problem, improve secret protection treatment effeciency, save manpower and material resources.
In a first aspect, the embodiment of the present invention provides a kind of data-privacy guard method, comprising:
Obtain the initial data that internet of things equipment is sent；
Privacy detection is carried out to the initial data, if including private data in the initial data, by the original
Beginning data markers are confidential data；
Secret protection processing is carried out to the confidential data, the target data that obtains that treated；
The target data is sent to corresponding intended recipient end.
Optionally, privacy detection is carried out to the initial data, comprising:
Determine the data type of the initial data；Wherein, the data type includes: text data, numerical data；
According to the data type of the initial data, various forms of feature extractions are carried out, obtain the initial data pair
The vector matrix answered；
The vector matrix is inputted in preset machine learning model, institute is exported by the preset machine learning model
State the testing result of initial data.
Optionally, according to the data type of the initial data, various forms of feature extractions are carried out, are obtained described original
The corresponding vector matrix of data, comprising:
If the data type of the initial data is text data, word segmentation processing is carried out to the initial data, is obtained
Corresponding text feature collection；Wherein, the text feature after word segmentation processing includes: word, binary phrase；
It obtains the text feature and concentrates characteristic value corresponding to each text feature；
According to the characteristic value, the corresponding vector matrix of the initial data is constructed.
Optionally, it obtains the text feature and concentrates characteristic value corresponding to each text feature, comprising:
The text frequency values and inverse text frequency values of the text feature are obtained respectively；
The product for calculating the text frequency values and inverse text frequency values, obtains the characteristic value of the text feature.
Optionally, the text frequency values and inverse text frequency values of the text feature are obtained respectively, comprising:
The frequency of appearance is concentrated to be defined as the calculation formula of text frequency values S1, S1 in text feature the text feature
It is as follows:
Wherein, n is that text feature concentrates the number occurred in text feature, and N is all text features in text feature collection
The number summation of middle appearance；
The calculation formula of the inverse text frequency values S2 is as follows:
Wherein: D is general act number in knowledge base, and C is the number of the file comprising corresponding text feature.
Optionally, according to the data type of the initial data, various forms of feature extractions are carried out, are obtained described original
The corresponding vector matrix of data, comprising:
If the data type of the initial data is numerical data, by the number in the numerical data according to preset
Format forms corresponding vector matrix.
Optionally, the preset machine learning model uses trained supporting vector machine model.
Optionally, after carrying out privacy detection to the initial data, further includes:
If not including private data in the initial data, the initial data is directly sent to corresponding target
Receiving end.
Optionally, secret protection processing is carried out to the confidential data, the target data that obtains that treated, comprising:
Privacyization processing is carried out to the private data in the confidential data, going privacy processing mode includes: that K- hides
Nameization, I- diversity, difference privacy.
Second aspect, the embodiment of the present invention provide a kind of data-privacy protective device, comprising:
Module is obtained, for obtaining the initial data of internet of things equipment transmission；
Privacy detection module, for carrying out privacy detection to the initial data, if including hidden in the initial data
The initial data is then labeled as confidential data by private data；
Processing module, for carrying out secret protection processing to the confidential data, the target data that obtains that treated；
Forwarding module, for the target data to be sent to corresponding intended recipient end.
Optionally, privacy detection module is specifically used for:
Determine the data type of the initial data；Wherein, the data type includes: text data, numerical data；
According to the data type of the initial data, various forms of feature extractions are carried out, obtain the initial data pair
The vector matrix answered；
The vector matrix is inputted in preset machine learning model, institute is exported by the preset machine learning model
State the testing result of initial data.
Optionally, according to the data type of the initial data, various forms of feature extractions are carried out, are obtained described original
The corresponding vector matrix of data, comprising:
If the data type of the initial data is text data, word segmentation processing is carried out to the initial data, is obtained
Corresponding text feature collection；Wherein, the text feature after word segmentation processing includes: word, binary phrase；
It obtains the text feature and concentrates characteristic value corresponding to each text feature；
According to the characteristic value, the corresponding vector matrix of the initial data is constructed.
Optionally, it obtains the text feature and concentrates characteristic value corresponding to each text feature, comprising:
The text frequency values and inverse text frequency values of the text feature are obtained respectively；
The product for calculating the text frequency values and inverse text frequency values, obtains the characteristic value of the text feature.
Optionally, the text frequency values and inverse text frequency values of the text feature are obtained respectively, comprising:
The frequency of appearance is concentrated to be defined as the calculation formula of text frequency values S1, S1 in text feature the text feature
It is as follows:
Wherein, n is that text feature concentrates the number occurred in text feature, and N is all text features in text feature collection
The number summation of middle appearance；
The calculation formula of the inverse text frequency values S2 is as follows:
Wherein: D is general act number in knowledge base, and C is the number of the file comprising corresponding text feature.
Optionally, according to the data type of the initial data, various forms of feature extractions are carried out, are obtained described original
The corresponding vector matrix of data, comprising:
If the data type of the initial data is numerical data, by the number in the numerical data according to preset
Format forms corresponding vector matrix.
Optionally, the preset machine learning model uses trained supporting vector machine model.
Optionally, further includes:
Diverter module is used for after carrying out privacy detection to the initial data, if not including in the initial data
There is private data, then the initial data is directly sent to corresponding intended recipient end.
Optionally, processing module is specifically used for:
Privacyization processing is carried out to the private data in the confidential data, going privacy processing mode includes: that K- hides
Nameization, I- diversity, difference privacy.
The third aspect, the embodiment of the present invention provide a kind of data-privacy protection system, comprising: memory and processor are deposited
The executable instruction of the processor is stored in reservoir；Wherein, the processor is configured to via the execution executable finger
It enables to execute data-privacy guard method described in any one of first aspect.
Fourth aspect, the embodiment of the present invention provide a kind of computer readable storage medium, are stored thereon with computer program,
Data-privacy guard method described in any one of first aspect is realized when the program is executed by processor.
The present invention provides a kind of data-privacy guard method, device, system and storage medium, passes through and obtains internet of things equipment
The initial data of transmission；Privacy detection is carried out to the initial data, it, will if including private data in the initial data
The initial data is labeled as confidential data；Secret protection processing is carried out to the confidential data, the number of targets that obtains that treated
According to；The target data is sent to corresponding intended recipient end.Internet of Things is set close to data source header side to realize
The initial data that preparation is sent carries out privacy detection using the method for machine learning and secret protection is handled, and by privacy, treated
Data are sent to the purpose at corresponding intended recipient end, so that the safety problem during data distance data transmission is solved,
Secret protection treatment effeciency is improved, manpower and material resources are saved.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is this hair
Bright some embodiments for those of ordinary skill in the art without any creative labor, can be with
It obtains other drawings based on these drawings.
Fig. 1 is the schematic illustration of an application scenarios of the invention；
Fig. 2 is the flow chart for the data-privacy guard method that the embodiment of the present invention one provides；
Fig. 3 is the flow chart of data-privacy guard method provided by Embodiment 2 of the present invention；
Fig. 4 is the structural schematic diagram for the data-privacy protective device that the embodiment of the present invention three provides；
Fig. 5 is the structural schematic diagram for the data-privacy protective device that the embodiment of the present invention four provides；
Fig. 6 is the structural schematic diagram that the data-privacy that the embodiment of the present invention five provides protects system.
Through the above attached drawings, it has been shown that the specific embodiment of the disclosure will be hereinafter described in more detail.These attached drawings
It is not intended to limit the scope of this disclosure concept by any means with verbal description, but is by referring to specific embodiments
Those skilled in the art illustrate the concept of the disclosure.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
Description and claims of this specification and term " first ", " second ", " third " " in above-mentioned attached drawing
The (if present)s such as four " are to be used to distinguish similar objects, without being used to describe a particular order or precedence order.It should manage
The data that solution uses in this way are interchangeable under appropriate circumstances, so that the embodiment of the present invention described herein for example can be to remove
Sequence other than those of illustrating or describe herein is implemented.In addition, term " includes " and " having " and theirs is any
Deformation, it is intended that cover it is non-exclusive include, for example, containing the process, method of a series of steps or units, system, production
Product or equipment those of are not necessarily limited to be clearly listed step or unit, but may include be not clearly listed or for this
A little process, methods, the other step or units of product or equipment inherently.
Technical solution of the present invention is described in detail with specifically embodiment below.These specific implementations below
Example can be combined with each other, and the same or similar concept or process may be repeated no more in some embodiments.
Fig. 1 is the schematic illustration of an application scenarios of the invention, as shown in Figure 1, data-privacy provided by the invention is protected
Device is deployed in the internet of things equipment close to data source header side, and internet of things equipment includes various sensors and can acquire and give birth to
At the computer equipment of data, such as brightness, humidity, temperature sensor, the Intelligent bracelet that can acquire human body situation is set
It is standby, the office computer etc. of each employee in the automobile data recorder and mobile phone of acquisition position information and movement track and enterprise.It is right
In the data of any required outgoing of internet of things equipment, it is necessary first to first pass through the processing of data-privacy protective device.These numbers
According to including: internet of things sensors, the mail that the data of the equipment such as Intelligent bracelet, enterprise's office computer are externally sent, document and
Need to send the data of background data center backup and analysis.Data-privacy protective device is set by obtaining module acquisition Internet of Things
The initial data that preparation is sent, privacy detection module carry out privacy detection to initial data.Data are divided by diverter module
Stream process: if in initial data including private data, secret protection processing is carried out to initial data by processing module, most
Corresponding intended recipient end is externally sent to according to its destination address by forwarding module afterwards；If not including in initial data
Initial data is then directly passed through forwarding module according to its destination address, is externally sent to corresponding intended recipient by private data
End.Wherein, intended recipient end includes background data center, Cloud Server etc..
To realize in the initial data sent close to data source header side to internet of things equipment, using the side of machine learning
Method carries out privacy detection and secret protection processing, by the purpose at privacy treated data are sent to corresponding intended recipient end,
To solve the safety problem during data distance data transmission, secret protection treatment effeciency is improved, manpower is saved
Material resources.
It may be implemented using the above method in the initial data sent close to data source header side to internet of things equipment, using machine
The method of device study carries out privacy detection and secret protection processing, and by privacy, treated that data are sent to corresponding intended recipient
The purpose at end improves secret protection treatment effeciency to solve the safety problem during data distance data transmission, section
Manpower and material resources are saved.
How to be solved with technical solution of the specifically embodiment to technical solution of the present invention and the application below above-mentioned
Technical problem is described in detail.These specific embodiments can be combined with each other below, for the same or similar concept
Or process may repeat no more in certain embodiments.Below in conjunction with attached drawing, the embodiment of the present invention is described.
Fig. 2 is the flow chart for the data-privacy guard method that the embodiment of the present invention one provides, as shown in Fig. 2, the present embodiment
In method may include:
S101, the initial data that internet of things equipment is sent is obtained.
In the present embodiment, internet of things equipment includes various sensors and can acquire and generate the computers of data and set
It is standby, such as brightness, humidity, temperature sensor, can acquire the Intelligent bracelet equipment of human body situation, acquisition position information with
And movement track automobile data recorder and mobile phone and each employee in enterprise office computer etc..The internet of things equipment of acquisition is sent out
The initial data sent refers to the data of any required outgoing of internet of things equipment, comprising: internet of things sensors, Intelligent bracelet etc. are set
The standby location information externally sent, the individual privacy informations such as electrocardiogram (ECG) data, age information, exercise data etc., enterprise's office computer
The mail externally sent, document, secret mail, physical examination report, credit report etc. and need to send background data center backup
With the data of analysis.
S102, privacy detection is carried out to initial data, if in initial data including private data, by initial data mark
It is denoted as confidential data.
In the present embodiment, the data type of initial data is determined；Wherein, data type includes: text data, digital number
According to；According to the data type of initial data, various forms of feature extractions are carried out, obtain the corresponding vector matrix of initial data；
Vector matrix is inputted in preset machine learning model, by the detection knot of preset machine learning model output initial data
Fruit.
In a kind of possible design, if the data type of initial data is text data, initial data is divided
Word processing, obtains corresponding text feature collection；It obtains text feature and concentrates characteristic value corresponding to each text feature；According to spy
Value indicative, the corresponding vector matrix of building initial data.Optionally, it obtains text feature and concentrates spy corresponding to each text feature
Value indicative, comprising: obtain the text frequency values and inverse text frequency values of text feature respectively；Calculate text frequency values and inverse text frequency
The product of rate value obtains the characteristic value of text feature.Wherein, the frequency occurred is concentrated to be defined as in text feature text feature
The calculation formula of text frequency values S1, S1 are as follows:
Wherein, n is that text feature concentrates the number occurred in text feature, and N is all text features in text feature collection
The number summation of middle appearance；
The calculation formula of inverse text frequency values S2 is as follows:
Wherein: D is general act number in knowledge base, and C is the number of the file comprising corresponding text feature.
Specifically, it is determined as the initial data of text data come area's grading mode by data suffix or specific format,
Initial data is segmented first, forms word set.Such as " Zhang San stays in the institute of West Road ,Anningzhuang, Haidian District ,Beijing City 9, year
This initial data of age 33 " carries out word segmentation processing and obtains word segmentation result are as follows: Zhang San, live, Beijing, Haidian District, the peaceful village,
West Road, 9, number institute, age, 33, year.Then, text feature is extracted, feature set is formed, by the way of word+binary phrase.
Above-mentioned example feature set are as follows: Zhang San, live, Beijing, Haidian District, the peaceful village, West Road, 9, number institute, the age, 33, year, Zhang San
Firmly, it stays in, at Beijing, Haidian District, Beijing City, the peacefulness village, Haidian District, peaceful village West Road, the institute of West Road 9,9, number institute's age, year
Age 33,33 years old.Subsequently, the characteristic value for calculating each text forms a list.Then, the text of above-mentioned each feature is calculated
Frequency values S1 and inverse text frequency values S2, obtains text feature and concentrates characteristic value corresponding to each text feature, calculate text
The product of frequency values S1 and inverse text frequency values S2, obtain the characteristic value T of text feature.For example, above-mentioned example characteristic value difference
For T1, T2, T3, T4, T5, T6 ....Finally, construction feature value vector matrix { T1, T2, T3, T4, T5, T6 ... }, knows in this way
Know all sample texts in library and be respectively formed this vector matrix, and is also the label of non-private data with being private data.
These vector matrixs are inputted into preset machine learning model, obtain the testing result of initial data.Optionally, preset machine
Learning model uses trained supporting vector machine model.
It, will be in numerical data if the data type of initial data is numerical data in alternatively possible design
Number forms corresponding vector matrix according to preset format.
Specifically, be numerical data for the data type of initial data, then according to unified format, organize data into
It measures { A1, A2, A3 .. }, such as one group of data of GPS positioning, is exactly such a 12 dimensional vector, multi-group data forms moment of a vector
Battle array, inputs preset machine learning model, obtains the testing result of initial data.
S103, secret protection processing is carried out to confidential data, the target data that obtains that treated.
In the present embodiment, privacyization processing is carried out to the private data in confidential data, removes privacy processing mode packet
It includes: K- anonymization, I- diversity, difference privacy.These go privacy processing mode all and are existing mature to go to privacy processing side
Method, details are not described herein again.The data obtained after secret protection processing are the target data removed after privacy, can externally be sent.
S104, target data is sent to corresponding intended recipient end.
In the present embodiment, according to its destination address, target data is externally sent to corresponding intended recipient end；Wherein,
Intended recipient end includes background data center, Cloud Server etc..
It should be noted that the type of the unlimited receiving end that sets the goal of the present embodiment, those skilled in the art can basis
Actual conditions increase or reduce the type at intended recipient end.
The present embodiment, the initial data sent by obtaining internet of things equipment；Privacy detection is carried out to initial data, if former
Include private data in beginning data, then initial data is labeled as confidential data；Secret protection processing is carried out to confidential data,
The target data that obtains that treated；Target data is sent to corresponding intended recipient end.To realize close to data source
The initial data that head side sends internet of things equipment carries out privacy detection using the method for machine learning and secret protection is handled,
By privacy, treated that data are sent to the purpose at corresponding intended recipient end, to solve data distance data transmission process
In safety problem, improve secret protection treatment effeciency, save manpower and material resources.
Fig. 3 is the flow chart of data-privacy guard method provided by Embodiment 2 of the present invention, as shown in figure 3, the present embodiment
In method may include:
S201, the initial data that internet of things equipment is sent is obtained.
S202, privacy detection is carried out to initial data, if in initial data including private data, by initial data mark
It is denoted as confidential data.
S203, secret protection processing is carried out to confidential data, the target data that obtains that treated.
S204, target data is sent to corresponding intended recipient end.
In the present embodiment, step S201~step S204 specific implementation process and technical principle are shown in Figure 2
Associated description in method in step S101~step S104, details are not described herein again.
If not including private data in S205, initial data, initial data is directly sent to corresponding target and is connect
Receiving end.
In the present embodiment, for not including private data in initial data, then by diverter module directly by original number
According to corresponding intended recipient end is sent to, do not need to carry out secret protection processing.
The present embodiment, the initial data sent by obtaining internet of things equipment；Privacy detection is carried out to initial data, if former
Include private data in beginning data, then initial data is labeled as confidential data；Secret protection processing is carried out to confidential data,
The target data that obtains that treated；Target data is sent to corresponding intended recipient end.To realize close to data source
The initial data that head side sends internet of things equipment carries out privacy detection using the method for machine learning and secret protection is handled,
By privacy, treated that data are sent to the purpose at corresponding intended recipient end, to solve data distance data transmission process
In safety problem, improve secret protection treatment effeciency, save manpower and material resources.
In addition, the present embodiment for not including private data in initial data, then passing through diverter module directly will be original
Data are sent to corresponding intended recipient end, do not need to carry out secret protection processing, improve treatment effeciency.
Fig. 4 is the structural schematic diagram for the data-privacy protective device that the embodiment of the present invention three provides, as shown in figure 4, this reality
The data-privacy protective device for applying example may include:
Module 31 is obtained, for obtaining the initial data of internet of things equipment transmission；
Privacy detection module 32, for carrying out privacy detection to initial data, if in initial data including private data,
Initial data is then labeled as confidential data；
Processing module 33, for carrying out secret protection processing to confidential data, the target data that obtains that treated；
Forwarding module 34, for target data to be sent to corresponding intended recipient end.
In a kind of possible design, privacy detection module 32 is specifically used for:
Determine the data type of initial data；Wherein, data type includes: text data, numerical data；
According to the data type of initial data, various forms of feature extractions are carried out, obtain the corresponding vector of initial data
Matrix；
Vector matrix is inputted in preset machine learning model, by preset machine learning model output initial data
Testing result.
In a kind of possible design, according to the data type of initial data, various forms of feature extractions is carried out, are obtained
The corresponding vector matrix of initial data, comprising:
If the data type of initial data is text data, word segmentation processing is carried out to initial data, obtains corresponding text
Eigen collection；
It obtains text feature and concentrates characteristic value corresponding to each text feature；
According to characteristic value, the corresponding vector matrix of initial data is constructed.
In a kind of possible design, obtains text feature and concentrates characteristic value corresponding to each text feature, comprising:
The text frequency values and inverse text frequency values of text feature are obtained respectively；
The product for calculating text frequency values and inverse text frequency values, obtains the characteristic value of text feature.
In a kind of possible design, the text frequency values and inverse text frequency values of text feature are obtained respectively, comprising:
The frequency occurred is concentrated to be defined as the calculation formula of text frequency values S1, S1 such as in text feature text feature
Under:
Wherein, n is that text feature concentrates the number occurred in text feature, and N is all text features in text feature collection
The number summation of middle appearance；
The calculation formula of inverse text frequency values S2 is as follows:
Wherein: D is general act number in knowledge base, and C is the number of the file comprising corresponding text feature.
In a kind of possible design, according to the data type of initial data, various forms of feature extractions is carried out, are obtained
The corresponding vector matrix of initial data, comprising:
If the data type of initial data is numerical data, by the number in numerical data according to preset format, group
At corresponding vector matrix.
In a kind of possible design, preset machine learning model uses trained supporting vector machine model.
In a kind of possible design, processing module 33 is specifically used for:
Privacyization processing is carried out to the private data in confidential data, going privacy processing mode includes: K- anonymization,
I- diversity, difference privacy.
The present embodiment, the initial data sent by obtaining internet of things equipment；Privacy detection is carried out to initial data, if former
Include private data in beginning data, then initial data is labeled as confidential data；Secret protection processing is carried out to confidential data,
The target data that obtains that treated；Target data is sent to corresponding intended recipient end.To realize close to data source
The initial data that head side sends internet of things equipment carries out privacy detection using the method for machine learning and secret protection is handled,
By privacy, treated that data are sent to the purpose at corresponding intended recipient end, to solve data distance data transmission process
In safety problem, improve secret protection treatment effeciency, save manpower and material resources.
The data-privacy protective device of the present embodiment can execute the technical solution in method shown in Fig. 2, specific implementation
Associated description in process and technical principle method shown in Figure 2, details are not described herein again.
Fig. 5 is the structural schematic diagram for the data-privacy protective device that the embodiment of the present invention four provides, as shown in figure 5, this reality
On the basis of the data-privacy protective device device shown in Fig. 4 for applying example, can also include:
Diverter module 35 is used for after carrying out privacy detection to initial data, if in initial data not including privacy
Initial data is then directly sent to corresponding intended recipient end by data.
The present embodiment, the initial data sent by obtaining internet of things equipment；Privacy detection is carried out to initial data, if former
Include private data in beginning data, then initial data is labeled as confidential data；Secret protection processing is carried out to confidential data,
The target data that obtains that treated；Target data is sent to corresponding intended recipient end.To realize close to data source
The initial data that head side sends internet of things equipment carries out privacy detection using the method for machine learning and secret protection is handled,
By privacy, treated that data are sent to the purpose at corresponding intended recipient end, to solve data distance data transmission process
In safety problem, improve secret protection treatment effeciency, save manpower and material resources.
In addition, the present embodiment for not including private data in initial data, then passing through diverter module directly will be original
Data are sent to corresponding intended recipient end, do not need to carry out secret protection processing, improve treatment effeciency.
The data-privacy protective device of the present embodiment, can execute the technical solution in method shown in Fig. 2, Fig. 3, specific
The associated description of realization process and technical principle referring to fig. 2, in method shown in Fig. 3, details are not described herein again.
Fig. 6 is the structural schematic diagram that the data-privacy that the embodiment of the present invention five provides protects system, as shown in fig. 6, this reality
The data-privacy protection system 40 for applying example may include: processor 41 and memory 42.
Memory 42 (such as realizes application program, the function of above-mentioned data-privacy guard method for storing computer program
Module etc.), computer instruction etc.；
Above-mentioned computer program, computer instruction etc. can be with partitioned storages in one or more memories 42.And
Above-mentioned computer program, computer instruction, data etc. can be called with device 41 processed.
Processor 41, for executing the computer program of the storage of memory 42, to realize method that above-described embodiment is related to
In each step.
It specifically may refer to the associated description in previous methods embodiment.
Processor 41 and memory 42 can be absolute construction, be also possible to the integrated morphology integrated.Work as processing
When device 41 and memory 42 are absolute construction, memory 42, processor 41 can be of coupled connections by bus 43.
The server of the present embodiment can execute the technical solution in method shown in Fig. 2, Fig. 3, specific implementation process and
Associated description of the technical principle referring to fig. 2, in method shown in Fig. 3, details are not described herein again.
In addition, the embodiment of the present application also provides a kind of computer readable storage medium, deposited in computer readable storage medium
Computer executed instructions are contained, when at least one processor of user equipment executes the computer executed instructions, user equipment
Execute above-mentioned various possible methods.
Wherein, computer-readable medium includes computer storage media and communication media, and wherein communication media includes being convenient for
From a place to any medium of another place transmission computer program.Storage medium can be general or specialized computer
Any usable medium that can be accessed.A kind of illustrative storage medium is coupled to processor, to enable a processor to from this
Read information, and information can be written to the storage medium.Certainly, storage medium is also possible to the composition portion of processor
Point.Pocessor and storage media can be located in ASIC.In addition, the ASIC can be located in user equipment.Certainly, processor and
Storage medium can also be used as discrete assembly and be present in communication equipment.
The application also provides a kind of program product, and program product includes computer program, and computer program is stored in readable
In storage medium, at least one processor of server can read computer program from readable storage medium storing program for executing, at least one
Reason device executes the data-privacy guard method that computer program makes the server implementation embodiments of the present invention any.
Those of ordinary skill in the art will appreciate that: realize that all or part of the steps of above-mentioned each method embodiment can lead to
The relevant hardware of program instruction is crossed to complete.Program above-mentioned can be stored in a computer readable storage medium.The journey
When being executed, execution includes the steps that above-mentioned each method embodiment to sequence；And storage medium above-mentioned include: ROM, RAM, magnetic disk or
The various media that can store program code such as person's CD.
Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention., rather than its limitations；To the greatest extent
Pipe present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: its according to
So be possible to modify the technical solutions described in the foregoing embodiments, or to some or all of the technical features into
Row equivalent replacement；And these are modified or replaceed, various embodiments of the present invention technology that it does not separate the essence of the corresponding technical solution
The range of scheme.
Claims (10)
1. a kind of data-privacy guard method characterized by comprising
Obtain the initial data that internet of things equipment is sent；
Privacy detection is carried out to the initial data, if including private data in the initial data, by the original number
According to labeled as confidential data；
Secret protection processing is carried out to the confidential data, the target data that obtains that treated；
The target data is sent to corresponding intended recipient end.
2. the method according to claim 1, wherein carrying out privacy detection to the initial data, comprising:
Determine the data type of the initial data；Wherein, the data type includes: text data, numerical data；
According to the data type of the initial data, various forms of feature extractions are carried out, it is corresponding to obtain the initial data
Vector matrix；
The vector matrix is inputted in preset machine learning model, the original is exported by the preset machine learning model
The testing result of beginning data.
3. according to the method described in claim 2, it is characterized in that, being carried out different according to the data type of the initial data
The feature extraction of form obtains the corresponding vector matrix of the initial data, comprising:
If the data type of the initial data is text data, word segmentation processing is carried out to the initial data, is corresponded to
Text feature collection；
It obtains the text feature and concentrates characteristic value corresponding to each text feature；
According to the characteristic value, the corresponding vector matrix of the initial data is constructed.
4. according to the method described in claim 3, concentrating each text feature institute right it is characterized in that, obtaining the text feature
The characteristic value answered, comprising:
The text frequency values and inverse text frequency values of the text feature are obtained respectively；
The product for calculating the text frequency values and inverse text frequency values, obtains the characteristic value of the text feature.
5. according to the method described in claim 4, it is characterized in that, obtaining the text frequency values of the text feature and inverse respectively
Text frequency values, comprising:
The frequency occurred is concentrated to be defined as the calculation formula of text frequency values S1, S1 such as in text feature the text feature
Under:
Wherein, n is that text feature concentrates the number occurred in text feature, and N is that all text features are concentrated out in text feature
Existing number summation；
The calculation formula of the inverse text frequency values S2 is as follows:
Wherein: D is general act number in knowledge base, and C is the number of the file comprising corresponding text feature.
6. according to the method described in claim 2, it is characterized in that, being carried out different according to the data type of the initial data
The feature extraction of form obtains the corresponding vector matrix of the initial data, comprising:
If the data type of the initial data is numerical data, by the number in the numerical data according to preset lattice
Formula forms corresponding vector matrix.
7. a kind of data-privacy protective device characterized by comprising
Module is obtained, for obtaining the initial data of internet of things equipment transmission；
Privacy detection module, for carrying out privacy detection to the initial data, if in the initial data including privacy number
According to then by the initial data labeled as confidential data；
Processing module, for carrying out secret protection processing to the confidential data, the target data that obtains that treated；
Forwarding module, for the target data to be sent to corresponding intended recipient end.
8. device according to claim 7, which is characterized in that privacy detection module is specifically used for:
Determine the data type of the initial data；Wherein, the data type includes: text data, numerical data；
According to the data type of the initial data, various forms of feature extractions are carried out, it is corresponding to obtain the initial data
Vector matrix；
The vector matrix is inputted in preset machine learning model, the original is exported by the preset machine learning model
The testing result of beginning data.
9. a kind of data-privacy protects system characterized by comprising memory and processor are stored in memory described
The executable instruction of processor；Wherein, the processor is configured to carry out perform claim requirement via the execution executable instruction
Data-privacy guard method described in any one of 1-6.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is by processor
Data-privacy guard method of any of claims 1-6 is realized when execution.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811308408.XA CN109543424A (en) | 2018-11-05 | 2018-11-05 | Data-privacy guard method, device, system and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811308408.XA CN109543424A (en) | 2018-11-05 | 2018-11-05 | Data-privacy guard method, device, system and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109543424A true CN109543424A (en) | 2019-03-29 |
Family
ID=65846549
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811308408.XA Pending CN109543424A (en) | 2018-11-05 | 2018-11-05 | Data-privacy guard method, device, system and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109543424A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111092723A (en) * | 2019-12-23 | 2020-05-01 | 长春理工大学 | Data privacy protection quantum computing method |
| CN112818390A (en) * | 2021-01-26 | 2021-05-18 | 支付宝(杭州)信息技术有限公司 | Data information publishing method, device and equipment based on privacy protection |
| CN114595465A (en) * | 2020-12-04 | 2022-06-07 | 成都鼎桥通信技术有限公司 | Data encryption processing method and device and electronic equipment |
| CN116366375A (en) * | 2023-06-02 | 2023-06-30 | 北京华科海讯科技股份有限公司 | Safety operation method and system based on artificial intelligence |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104376011A (en) * | 2013-08-14 | 2015-02-25 | 华为终端有限公司 | Privacy protection implementing method and device |
| CN106446697A (en) * | 2016-07-26 | 2017-02-22 | 邬超 | Method and device for saving private data |
| CN107292193A (en) * | 2017-05-25 | 2017-10-24 | 北京北信源软件股份有限公司 | A kind of method and system for realizing leakage prevention |
| CN107577958A (en) * | 2017-09-08 | 2018-01-12 | 中国联合网络通信集团有限公司 | Go privacy to melt put method and device, remove private data retrogressive method and device |
-
2018
- 2018-11-05 CN CN201811308408.XA patent/CN109543424A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104376011A (en) * | 2013-08-14 | 2015-02-25 | 华为终端有限公司 | Privacy protection implementing method and device |
| CN106446697A (en) * | 2016-07-26 | 2017-02-22 | 邬超 | Method and device for saving private data |
| CN107292193A (en) * | 2017-05-25 | 2017-10-24 | 北京北信源软件股份有限公司 | A kind of method and system for realizing leakage prevention |
| CN107577958A (en) * | 2017-09-08 | 2018-01-12 | 中国联合网络通信集团有限公司 | Go privacy to melt put method and device, remove private data retrogressive method and device |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111092723A (en) * | 2019-12-23 | 2020-05-01 | 长春理工大学 | Data privacy protection quantum computing method |
| CN114595465A (en) * | 2020-12-04 | 2022-06-07 | 成都鼎桥通信技术有限公司 | Data encryption processing method and device and electronic equipment |
| CN112818390A (en) * | 2021-01-26 | 2021-05-18 | 支付宝(杭州)信息技术有限公司 | Data information publishing method, device and equipment based on privacy protection |
| CN116366375A (en) * | 2023-06-02 | 2023-06-30 | 北京华科海讯科技股份有限公司 | Safety operation method and system based on artificial intelligence |
| CN116366375B (en) * | 2023-06-02 | 2023-08-15 | 北京华科海讯科技股份有限公司 | Safety operation method and system based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109543424A (en) | Data-privacy guard method, device, system and storage medium | |
| Rauber et al. | Foolbox native: Fast adversarial attacks to benchmark the robustness of machine learning models in pytorch, tensorflow, and jax | |
| Demertzis et al. | Extreme deep learning in biosecurity: the case of machine hearing for marine species identification | |
| CN107122375A (en) | The recognition methods of image subject based on characteristics of image | |
| CN114610773A (en) | Data application scene recognition method based on big data and cloud computing server | |
| CN109344262A (en) | Architectonic method for building up, device and storage medium | |
| CN113434685B (en) | Information classification processing method and system | |
| CN109886021A (en) | A kind of malicious code detecting method based on API overall situation term vector and layered circulation neural network | |
| CN108831442A (en) | Point of interest recognition methods, device, terminal device and storage medium | |
| CN109033148A (en) | One kind is towards polytypic unbalanced data preprocess method, device and equipment | |
| CN109191167A (en) | A kind of method for digging and device of target user | |
| Demertzis et al. | A machine hearing framework for real-time streaming analytics using Lambda architecture | |
| CN106169961A (en) | The network parameter processing method and processing device of neutral net based on artificial intelligence | |
| CN110110218A (en) | A kind of Identity Association method and terminal | |
| CN111626311B (en) | Heterogeneous graph data processing method and device | |
| CN109960730A (en) | A kind of short text classification method, device and equipment based on feature extension | |
| CN110189767A (en) | A kind of recording mobile device detection method based on dual-channel audio | |
| CN110597990B (en) | Financial analysis method and system based on intelligent classification | |
| CN116257609A (en) | Cross-modal retrieval method and system based on multi-scale text alignment | |
| Liu et al. | Real-time graph partition and embedding of large network | |
| CN109542766A (en) | Extensive program similitude based on code mapping and morphological analysis quickly detects and evidence generation method | |
| CN105574038B (en) | Content of text discrimination test method and device based on anti-identification rendering | |
| CN110309312B (en) | Associated event acquisition method and device | |
| CN107145847B (en) | Remote sensing images recognition methods based on center dictionary | |
| CN110334235A (en) | A kind of fine granularity search method of center sequence loss and the positioning of Weakly supervised object |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190329 |
|
| RJ01 | Rejection of invention patent application after publication |