CN109726763A - A kind of information assets recognition methods, device, equipment and medium - Google Patents
A kind of information assets recognition methods, device, equipment and medium Download PDFInfo
- Publication number
- CN109726763A CN109726763A CN201811643242.7A CN201811643242A CN109726763A CN 109726763 A CN109726763 A CN 109726763A CN 201811643242 A CN201811643242 A CN 201811643242A CN 109726763 A CN109726763 A CN 109726763A
- Authority
- CN
- China
- Prior art keywords
- asset
- information
- information asset
- training
- characteristic data
- 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 57
- 238000010801 machine learning Methods 0.000 claims abstract description 53
- 238000013145 classification model Methods 0.000 claims abstract description 51
- 238000012549 training Methods 0.000 claims description 158
- 239000000523 sample Substances 0.000 claims description 42
- 230000008569 process Effects 0.000 claims description 19
- 238000005457 optimization Methods 0.000 claims description 16
- 238000003860 storage Methods 0.000 claims description 15
- 238000004891 communication Methods 0.000 claims description 13
- 238000012545 processing Methods 0.000 claims description 12
- 230000004044 response Effects 0.000 claims description 7
- 238000013139 quantization Methods 0.000 claims description 6
- 238000007726 management method Methods 0.000 description 22
- 238000010586 diagram Methods 0.000 description 11
- 230000006870 function Effects 0.000 description 8
- 238000004590 computer program Methods 0.000 description 7
- 238000004422 calculation algorithm Methods 0.000 description 6
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 4
- 238000013500 data storage Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 3
- 238000007635 classification algorithm Methods 0.000 description 2
- 238000013480 data collection Methods 0.000 description 2
- 238000013079 data visualisation Methods 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
Landscapes
- Collating Specific Patterns (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of information assets recognition methods, device, equipment and media, are applied to machine learning techniques field, to solve the problems, such as that the asset management system in the prior art can not carry out automatic identification to information assets.Specifically: it is based on the corresponding assets feature data acquisition system of each information assets and class of assets, machine learning classification model is trained, obtain the information assets Fingerprint Model for determining class of assets, and then automatic identification can be carried out to information assets according to the information assets Fingerprint Model, and, according to assets feature data of each information assets under multiple setting dimensions, the information assets Fingerprint Model is trained, the information assets Fingerprint Model is enabled to combine the assets feature data of multiple dimensions, information assets is accurately identified, it has been avoided as much as having identical assets feature data due to multiple information assets, cause information assets Fingerprint Model to the problem of the recognition result inaccuracy of information assets.
Description
Technical Field
The invention relates to the technical field of machine learning, in particular to an information asset identification method, device, equipment and medium.
Background
With the continuous development of Information Technology (IT), most enterprises have been closely linked with IT Technology.
From the IT technology perspective, software and hardware resources in an enterprise, such as: network devices, security devices, computers, databases, middleware, etc. may be collectively referred to as information assets, and various enterprises may manage the information assets through an asset management system.
At present, an asset management system mainly provides asset management services for each enterprise, while identification of information assets is mainly based on manual identification, and the asset management system cannot realize accurate automatic identification of the information assets.
Disclosure of Invention
The embodiment of the invention provides an information asset identification method, device, equipment and medium, which are used for solving the problem that an asset management system in the prior art cannot accurately and automatically identify information assets.
The embodiment of the invention provides the following specific technical scheme:
in one aspect, an embodiment of the present invention provides an information asset identification method, including:
determining an information asset training set according to the set training category and the data acquisition network range corresponding to the set training category;
acquiring asset characteristic data of each information asset in multiple set dimensions, wherein the asset characteristic data are contained in an information asset training set, acquiring an asset characteristic data set corresponding to each information asset, and acquiring an asset class corresponding to each information asset;
and training the machine learning classification model based on the asset characteristic data set and the asset class corresponding to each information asset to obtain an information asset fingerprint model, wherein the information asset fingerprint model is used for determining the asset class corresponding to the information asset to be identified according to the asset characteristic data set of the information asset to be identified.
In a possible implementation manner, if the plurality of set dimensions are a plurality of set communication protocols, acquiring asset feature data of each information asset included in the information asset training set in the plurality of set dimensions to obtain an asset feature data set corresponding to each information asset, including:
selecting one probe set from the plurality of probe sets as a probe set corresponding to the information asset training set, wherein the probe set comprises a set number of request data packets corresponding to each of a plurality of set communication protocols;
and aiming at each information asset contained in the information asset training set, in a first set time range, sending a request data packet to a physical entity corresponding to the information asset based on the probe set according to set acquisition times, and obtaining an asset characteristic data set corresponding to the information asset based on each response data packet returned by the physical entity corresponding to the information asset.
In one possible implementation mode, the asset class corresponding to each information asset is described in a general classification mode.
In a possible implementation manner, obtaining asset categories corresponding to the respective information assets includes:
determining an information asset class set according to a set training class, respectively matching each information asset class contained in the information asset class set with each information asset, and determining the asset class corresponding to each information asset according to a matching result; or, the asset class corresponding to each information asset is extracted from the asset feature data set corresponding to each information asset.
In a possible implementation manner, training a machine learning classification model based on an asset feature data set and an asset class respectively corresponding to each information asset to obtain an information asset fingerprint model includes:
carrying out quantization processing on the asset characteristic data set and the asset class corresponding to each information asset to obtain a quantized asset characteristic data set and a quantized asset class corresponding to each information asset;
performing the following iterative training based on the quantized asset feature data set and the quantized asset class corresponding to each information asset:
performing parameter configuration on the machine learning classification model based on a target configuration parameter to obtain a target machine learning classification model, wherein the target configuration parameter is an initialization configuration parameter during first iterative training, the target configuration parameter is a configuration parameter obtained after adjusting the target configuration parameter used in the last iterative training process based on a configuration parameter adjusting step length determined in the last iterative training process during non-first iterative training;
selecting a set number of quantized asset characteristic data from the quantized asset characteristic data sets corresponding to the information assets respectively as target asset characteristic data corresponding to the information assets respectively;
inputting target asset characteristic data corresponding to each information asset into a target machine learning classification model to obtain a prediction asset class corresponding to each information asset;
determining the difference between the predicted asset class and the quantified asset class corresponding to each information asset;
judging whether the target machine learning classification model obtained by the iterative training meets the preset accuracy or not based on the difference degree corresponding to each information asset;
if so, determining the target machine learning classification model obtained by the iterative training as an information asset fingerprint model;
and if not, determining the adjustment step length of the configuration parameters based on the difference degree corresponding to each information asset.
In a possible implementation manner, the information asset identification method provided in the embodiment of the present invention further includes:
adjusting a data acquisition network range corresponding to the set training category, and determining an incremental information asset training set according to the adjusted data acquisition network range;
acquiring asset characteristic data of each incremental information asset in multiple set dimensions, wherein the asset characteristic data are contained in an incremental information asset training set, acquiring an asset characteristic data set corresponding to each incremental information asset, and acquiring an asset class corresponding to each incremental information asset;
and performing optimization training on the information asset fingerprint model based on the asset characteristic data set and the asset class corresponding to each incremental information asset.
In another aspect, an embodiment of the present invention provides an information asset identification apparatus, including:
the determining unit is used for determining an information asset training set according to the set training type and the data acquisition network range corresponding to the set training type;
the acquisition unit is used for acquiring asset characteristic data of each information asset in multiple set dimensions contained in the information asset training set to obtain an asset characteristic data set corresponding to each information asset;
the acquisition unit is used for acquiring the asset types corresponding to the information assets;
and the training unit is used for training the machine learning classification model based on the asset characteristic data set corresponding to each information asset acquired by the acquisition unit and the asset class corresponding to each information asset acquired by the acquisition unit to obtain an information asset fingerprint model, wherein the information asset fingerprint model is used for determining the asset class corresponding to the information asset to be identified according to the asset characteristic data set of the information asset to be identified.
In a possible implementation manner, if the multiple set dimensions are multiple set communication protocols, when acquiring asset feature data of each information asset included in the information asset training set in the multiple set dimensions to obtain an asset feature data set corresponding to each information asset, the acquisition unit is configured to:
selecting one probe set from the plurality of probe sets as a probe set corresponding to the information asset training set, wherein the probe set comprises a set number of request data packets corresponding to each of a plurality of set communication protocols;
and aiming at each information asset contained in the information asset training set, in a first set time range, sending a request data packet to a physical entity corresponding to the information asset based on the probe set according to set acquisition times, and obtaining an asset characteristic data set corresponding to the information asset based on each response data packet returned by the physical entity corresponding to the information asset.
In a possible implementation manner, the asset class corresponding to each information asset obtained by the obtaining unit is described in a general classification manner.
In a possible implementation manner, when the asset class corresponding to each information asset is obtained, the obtaining unit is configured to:
determining an information asset class set according to a set training class, respectively matching each information asset class contained in the information asset class set with each information asset, and determining the asset class corresponding to each information asset according to a matching result; or, the asset class corresponding to each information asset is extracted from the asset feature data set corresponding to each information asset.
In a possible implementation manner, when the machine learning classification model is trained based on the asset feature data set corresponding to each information asset acquired by the acquisition unit and the asset class corresponding to each information asset acquired by the acquisition unit to obtain the information asset fingerprint model, the training unit is configured to:
carrying out quantization processing on the asset characteristic data set and the asset class corresponding to each information asset to obtain a quantized asset characteristic data set and a quantized asset class corresponding to each information asset;
performing the following iterative training based on the quantized asset feature data set and the quantized asset class corresponding to each information asset:
performing parameter configuration on the machine learning classification model based on a target configuration parameter to obtain a target machine learning classification model, wherein the target configuration parameter is an initialization configuration parameter during first iterative training, the target configuration parameter is a configuration parameter obtained after adjusting the target configuration parameter used in the last iterative training process based on a configuration parameter adjusting step length determined in the last iterative training process during non-first iterative training;
selecting a set number of quantized asset characteristic data from the quantized asset characteristic data sets corresponding to the information assets respectively as target asset characteristic data corresponding to the information assets respectively;
inputting target asset characteristic data corresponding to each information asset into a target machine learning classification model to obtain a prediction asset class corresponding to each information asset;
determining the difference between the predicted asset class and the quantified asset class corresponding to each information asset;
judging whether the target machine learning classification model obtained by the iterative training meets the preset accuracy or not based on the difference degree corresponding to each information asset;
if so, determining the target machine learning classification model obtained by the iterative training as an information asset fingerprint model;
and if not, determining the adjustment step length of the configuration parameters based on the difference degree corresponding to each information asset.
In a possible implementation manner, the information asset identification apparatus provided in an embodiment of the present invention further includes:
the incremental training unit is used for adjusting the data acquisition network range corresponding to the set training category and determining an incremental information asset training set according to the adjusted data acquisition network range; acquiring asset characteristic data of each incremental information asset in multiple set dimensions, wherein the asset characteristic data are contained in an incremental information asset training set, acquiring an asset characteristic data set corresponding to each incremental information asset, and acquiring an asset class corresponding to each incremental information asset; and performing optimization training on the information asset fingerprint model based on the asset characteristic data set and the asset class corresponding to each incremental information asset.
In a third aspect, an embodiment of the present invention further provides an information asset identification device, including: the device comprises a memory, a processor and computer instructions stored on the memory, wherein the processor executes the computer instructions to realize the information asset identification method provided by the embodiment of the invention.
In a fourth aspect, the embodiment of the present invention further provides a computer-readable storage medium, where computer instructions are stored, and when the computer instructions are executed by a processor, the computer instructions implement the information asset identification method provided by the embodiment of the present invention.
The embodiment of the invention has the following beneficial effects:
in the embodiment of the invention, the machine learning classification model is trained based on the asset characteristic data set and the asset class corresponding to each information asset, so that an information asset fingerprint model for determining the asset class can be obtained, the information asset to be identified can be automatically identified according to the information asset fingerprint model, and the information asset fingerprint model is trained according to the asset characteristic data of each information asset in multiple set dimensions, so that the information asset fingerprint model can accurately identify the information asset by combining the asset characteristic data of multiple dimensions, and the problem that the identification result of the information asset fingerprint model to the information asset is inaccurate due to the fact that multiple information assets have the same asset characteristic data is avoided as much as possible.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention and not to limit the invention. In the drawings:
FIG. 1 is a schematic diagram of a system architecture of an information asset identification system in an embodiment of the invention;
FIG. 2 is a schematic flow chart of a method for identifying information assets in an embodiment of the invention;
FIG. 3 is a schematic flowchart of an iterative training method used in training a machine learning classification model according to an embodiment of the present invention;
FIG. 4 is a schematic flow chart of an iterative optimization training method used in optimizing an information asset fingerprint model according to an embodiment of the present invention;
FIG. 5 is a functional block diagram of an information asset identification apparatus according to an embodiment of the present invention;
fig. 6 is a schematic hardware configuration diagram of an information asset identification device in an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more clearly and clearly apparent, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the concrete practice process, the inventor of the present application finds that the current asset management system can only provide asset management service for each enterprise, and cannot accurately and automatically identify information assets, so that the inventor of the present application considers that a machine learning classification model can be trained based on an asset characteristic data set and an asset class corresponding to each information asset within a set time range, an information asset fingerprint model for determining the asset class is obtained, and then the information asset fingerprint model is configured into the asset management system, so that the asset management system can automatically identify the information assets according to the information asset fingerprint model, and the information asset fingerprint model is trained according to asset characteristic data of each information asset in a plurality of set dimensions, so that the information asset fingerprint model can be combined with asset characteristic data of a plurality of dimensions, the information assets are accurately identified, and the problem that the identification result of the information assets by the information asset fingerprint model is inaccurate due to the fact that a plurality of information assets have the same asset characteristic data is avoided as much as possible.
The present invention will be described in detail with reference to specific examples, but it is to be understood that the present invention is not limited to the examples.
An embodiment of the present invention provides an information asset identification training system, which is shown in fig. 1 and at least includes: a configuration management subsystem 101, a probe subsystem 102, a data acquisition subsystem 103, a category acquisition subsystem 104, a data storage subsystem 105, a model algorithm subsystem 106, and a data visualization subsystem 107, wherein:
a configuration management subsystem 101, configured to provide a configuration maintenance interface, and configure various parameters used in the training process for the information asset identification training system 100 according to the configuration instructions received from the configuration maintenance interface, for example: the method comprises the following steps of training range, the number of probes contained in a probe set, the number of data packets corresponding to each probe contained in the probe set, data acquisition times, a classification algorithm in a machine learning classification model, initialization configuration parameters corresponding to the classification algorithm, algorithm accuracy and the like.
The probe subsystem 102 is configured to send a request data packet to a physical entity corresponding to each information asset in a training range configured by the configuration management subsystem 101 based on the probe set configured by the configuration management subsystem 101 according to the data acquisition times configured by the configuration management subsystem 101.
The data acquisition subsystem 103 is configured to capture a response data packet returned by the physical entity corresponding to each information asset for the request data packet sent by the probe subsystem 102, that is, capture an asset feature data set corresponding to each information asset.
And the category acquiring subsystem 104 is used for acquiring the asset categories corresponding to the information assets. Specifically, the asset class corresponding to each information asset may be obtained according to the manual marking, or the asset class corresponding to each information asset may be obtained according to the automatic marking function.
And the data storage subsystem 105 is configured to store the asset feature data sets corresponding to the information assets acquired by the data acquisition subsystem 103 and the asset categories corresponding to the information assets acquired by the category acquisition subsystem 104.
And the model algorithm subsystem 106 is used for training the machine learning classification model based on the asset characteristic data set and the asset class respectively corresponding to each information asset stored by the data storage subsystem 105 to obtain an information asset fingerprint model.
And the data visualization subsystem 107 is used for displaying the information asset fingerprint model obtained by the model algorithm subsystem 106.
The information asset identification training system 100 shown in fig. 1 provided in the embodiment of the present invention is described below in detail with reference to the information asset identification method provided in the embodiment of the present invention, and referring to fig. 2, the flow of the information asset identification method provided in the embodiment of the present invention is as follows:
step 201: and determining an information asset training set according to the set training type and the data acquisition network range corresponding to the set training type.
In practical applications, step 201 may be performed in the configuration management subsystem 101, specifically, the configuration management subsystem 101 may determine a training category and a data collection network range corresponding to the training category according to a configuration instruction received from the configuration maintenance interface, for example: the training category may be operating system training, the data acquisition network range may be operating systems of all devices managed by the asset management system, and the configuration management subsystem 101 may determine the information asset training set according to the training category and the data acquisition network range corresponding to the training category.
Step 202: and acquiring asset characteristic data of each information asset in a plurality of set dimensions, wherein the asset characteristic data are contained in the information asset training set, acquiring an asset characteristic data set corresponding to each information asset, and acquiring an asset class corresponding to each information asset.
In practical applications, in order to enable the finally obtained information asset fingerprint model to accurately identify the information asset according to asset feature data of multiple dimensions, the configuration management subsystem 101 may set a probe including a set number of request packets for different communication protocols, and configure a plurality of probe sets according to the probes corresponding to the different communication protocols.
In particular implementations, asset characterization data for each information asset in multiple set dimensions may be collected through the cooperation between probe subsystem 102 and data collection subsystem 103. Specifically, the probe subsystem 102 may select one probe set from the plurality of probe sets configured by the configuration management subsystem 101 as a probe set corresponding to the information asset training set, and send a request data packet to a physical entity corresponding to the information asset based on the probe set according to the set data acquisition times for each information asset included in the information asset training set, and the data acquisition subsystem 103 may capture each response data packet returned by the physical entity corresponding to the information asset, thereby obtaining an asset feature data set corresponding to the information asset.
In a specific implementation, the asset class corresponding to each information asset may be obtained by the class obtaining subsystem 104. Specifically, the category obtaining subsystem 104 may determine an information asset category set according to the training range configured by the configuration management subsystem 101, and match each information asset category included in the information asset category set with each information asset, so as to determine the asset category corresponding to each information asset according to the matching result.
In another embodiment, the category obtaining subsystem 104 may also extract the asset category corresponding to each information asset from the asset feature data set corresponding to each information asset.
Further, after the category acquiring subsystem 104 acquires the asset categories corresponding to the information assets, it may further perform standardized description on the asset categories corresponding to the information assets in a general classification manner, for example, the asset categories corresponding to the information assets may be standardized and described by using asset types defined in Common Platform Enumeration (CPE), so that the finally acquired information asset fingerprint model can be adapted to all asset management systems.
Step 203: and training the machine learning classification model based on the asset characteristic data set and the asset class corresponding to each information asset to obtain an information asset fingerprint model, wherein the information asset fingerprint model is used for determining the asset class corresponding to the information asset to be identified according to the asset characteristic data set of the information asset to be identified.
In practical application, training of the information asset fingerprint model may be performed in the model algorithm subsystem 106, specifically, the model algorithm subsystem 106 may perform quantization processing on the asset feature data set and the asset class corresponding to each information asset, to obtain the quantized asset feature data set and the quantized asset class corresponding to each information asset, and then perform iterative training on the machine learning classification model by using the iterative training method shown in fig. 3, to obtain the information asset fingerprint model, which specifically includes:
step 301: and determining target configuration parameters, wherein the target configuration parameters are initialization configuration parameters during first iterative training, and the target configuration parameters are configuration parameters obtained after adjusting the target configuration parameters used in the last iterative training process based on the configuration parameter adjusting step length determined in the last iterative training process during non-first iterative training.
Step 302: and performing parameter configuration on the machine learning classification model based on the target configuration parameters to obtain the target machine learning classification model.
Step 303: and respectively selecting a set number of quantized asset characteristic data from the quantized asset characteristic data sets corresponding to the information assets as target asset characteristic data corresponding to the information assets.
Step 304: and inputting the target asset characteristic data corresponding to each information asset into a target machine learning classification model to obtain the predicted asset class corresponding to each information asset.
Step 305: and determining the difference degree between the predicted asset class and the quantified asset class corresponding to each information asset.
Step 306: judging whether the target machine learning classification model obtained by the iterative training meets the preset accuracy or not based on the difference degree corresponding to each information asset, if so, executing a step 307; if not, go to step 308.
Step 307: and determining the target machine learning classification model obtained by the iterative training as an information asset fingerprint model.
Step 308: and determining the adjustment step length of the configuration parameters based on the difference degree corresponding to each information asset, and returning to the step 301.
Further, after obtaining the information asset fingerprint model, the information asset fingerprint model may be optimally trained by using, but not limited to, the following methods: adjusting a data acquisition network range corresponding to a set training category, determining an incremental information asset training set according to the adjusted data acquisition network range, acquiring asset characteristic data of each incremental information asset in multiple set dimensions, which are contained in the incremental information asset training set, obtaining an asset characteristic data set corresponding to each incremental information asset, obtaining an asset category corresponding to each incremental information asset, and performing optimization training on an information asset fingerprint model based on the asset characteristic data set and the asset category corresponding to each incremental information asset. Specifically, the asset feature data set and the asset class corresponding to each incremental information asset may be quantized to obtain the quantized asset feature data set and the quantized asset class corresponding to each incremental information asset, and then the iterative optimization training may be performed on the information asset fingerprint model based on the quantized asset feature data set and the quantized asset class corresponding to each incremental information asset, specifically, as shown in fig. 4, the iterative optimization training method may have the following flow:
step 401: and determining target configuration parameters, wherein the target configuration parameters are configuration parameters of the information asset fingerprint model finally obtained after the training process of the steps 301 to 308 is finished during first iterative optimization training, and the target configuration parameters are configuration parameters obtained after the target configuration parameters used in the last iterative optimization training process are adjusted based on the configuration parameter adjustment step length determined in the last iterative optimization training process during non-first iterative optimization training.
Step 402: and performing parameter configuration on the information asset fingerprint model based on the target configuration parameters to obtain the target information asset fingerprint model.
Step 403: and respectively selecting a set number of quantized asset characteristic data from the quantized asset characteristic data sets corresponding to the incremental information assets as target asset characteristic data corresponding to the incremental information assets.
Step 404: and inputting the target asset characteristic data corresponding to each incremental information asset into a target machine learning classification model to obtain the predicted asset class corresponding to each incremental information asset.
Step 405: and determining the difference degree between the predicted asset class and the quantified asset class corresponding to each incremental information asset.
Step 406: judging whether the target machine learning classification model obtained by the iterative optimization training meets the preset accuracy or not based on the difference degree corresponding to each incremental information asset, if so, executing a step 307; if not, go to step 408.
Step 407: and outputting the target machine learning classification model obtained by the iterative optimization training, and exiting the optimization training process.
Step 408: and determining the adjustment step length of the configuration parameters based on the difference degree corresponding to each incremental information asset, and returning to the step 401.
Based on the above embodiment, an embodiment of the present invention provides an information asset identification apparatus, and referring to fig. 5, the information asset identification apparatus 500 at least includes:
a determining unit 501, configured to determine an information asset training set according to a set training category and a set data acquisition network range corresponding to the set training category;
the acquisition unit 502 is configured to acquire asset feature data of each information asset in multiple set dimensions, which are included in the information asset training set, to obtain an asset feature data set corresponding to each information asset;
an obtaining unit 503, configured to obtain asset types corresponding to the information assets;
a training unit 504, configured to train the machine learning classification model based on the asset feature data set corresponding to each information asset acquired by the acquisition unit 502 and the asset class corresponding to each information asset acquired by the acquisition unit 503, to obtain an information asset fingerprint model, where the information asset fingerprint model is used to determine the asset class corresponding to the information asset to be identified according to the asset feature data set of the information asset to be identified.
In a possible implementation manner, if the multiple set dimensions are multiple set communication protocols, when acquiring asset feature data of each information asset included in the information asset training set in the multiple set dimensions to obtain an asset feature data set corresponding to each information asset, the acquisition unit 502 is configured to:
selecting one probe set from the plurality of probe sets as a probe set corresponding to the information asset training set, wherein the probe set comprises a set number of request data packets corresponding to each of a plurality of set communication protocols;
and aiming at each information asset contained in the information asset training set, in a first set time range, sending a request data packet to a physical entity corresponding to the information asset based on the probe set according to set acquisition times, and obtaining an asset characteristic data set corresponding to the information asset based on each response data packet returned by the physical entity corresponding to the information asset.
In a possible implementation manner, the asset class corresponding to each information asset obtained by the obtaining unit 503 is described in a general classification manner.
In a possible implementation manner, when acquiring the asset classes corresponding to the respective information assets, the acquiring unit 503 is configured to:
determining an information asset class set according to a set training class, respectively matching each information asset class contained in the information asset class set with each information asset, and determining the asset class corresponding to each information asset according to a matching result; or, the asset class corresponding to each information asset is extracted from the asset feature data set corresponding to each information asset.
In a possible implementation manner, when the machine learning classification model is trained based on the asset feature data set corresponding to each information asset acquired by the acquisition unit and the asset class corresponding to each information asset acquired by the acquisition unit to obtain the information asset fingerprint model, the training unit 504 is configured to:
carrying out quantization processing on the asset characteristic data set and the asset class corresponding to each information asset to obtain a quantized asset characteristic data set and a quantized asset class corresponding to each information asset;
performing the following iterative training based on the quantized asset feature data set and the quantized asset class corresponding to each information asset:
performing parameter configuration on the machine learning classification model based on a target configuration parameter to obtain a target machine learning classification model, wherein the target configuration parameter is an initialization configuration parameter during first iterative training, the target configuration parameter is a configuration parameter obtained after adjusting the target configuration parameter used in the last iterative training process based on a configuration parameter adjusting step length determined in the last iterative training process during non-first iterative training;
selecting a set number of quantized asset characteristic data from the quantized asset characteristic data sets corresponding to the information assets respectively as target asset characteristic data corresponding to the information assets respectively;
inputting target asset characteristic data corresponding to each information asset into a target machine learning classification model to obtain a prediction asset class corresponding to each information asset;
determining the difference between the predicted asset class and the quantified asset class corresponding to each information asset;
judging whether the target machine learning classification model obtained by the iterative training meets the preset accuracy or not based on the difference degree corresponding to each information asset;
if so, determining the target machine learning classification model obtained by the iterative training as an information asset fingerprint model;
and if not, determining the adjustment step length of the configuration parameters based on the difference degree corresponding to each information asset.
In a possible implementation manner, the information asset identification apparatus 500 provided by the embodiment of the present invention further includes:
an incremental training unit 505, configured to adjust a data acquisition network range corresponding to a set training category, and determine an incremental information asset training set according to the adjusted data acquisition network range; acquiring asset characteristic data of each incremental information asset in multiple set dimensions, wherein the asset characteristic data are contained in an incremental information asset training set, acquiring an asset characteristic data set corresponding to each incremental information asset, and acquiring an asset class corresponding to each incremental information asset; and performing optimization training on the information asset fingerprint model based on the asset characteristic data set and the asset class corresponding to each incremental information asset.
It should be noted that, because the principle of solving the technical problem of the information asset identification 500 provided in the embodiment of the present invention is similar to the information asset identification method provided in the embodiment of the present invention, the implementation of the information asset identification apparatus 500 provided in the embodiment of the present invention may refer to the implementation of the information asset identification method provided in the embodiment of the present invention, and repeated details are not repeated.
After the information asset identification method and apparatus according to the exemplary embodiment of the present invention are described, a brief description will be given of an information asset identification device according to an embodiment of the present invention.
Referring to fig. 6, an information asset identification apparatus 600 according to an embodiment of the present invention includes at least: a processor 61 and a memory 62, wherein the memory 62 is used for storing computer instructions; and the processor 61 is used for executing computer instructions to realize the information asset identification method provided by the embodiment of the invention.
It should be noted that the information asset identification device 600 shown in fig. 6 is only an example, and should not bring any limitation to the functions and the scope of the application of the embodiment of the present invention.
The information asset identification device 600 provided by the embodiment of the present invention may further include a bus 63 connecting the various components including the processor 61 and the memory 62. Bus 63 represents one or more of any of several types of bus structures, including a memory bus, a peripheral bus, a local bus, and so forth.
The Memory 62 may include readable media in the form of volatile Memory, such as Random Access Memory (RAM) 621 and/or cache Memory 622, and may further include Read Only Memory (ROM) 623.
The memory 62 may also include a program tool 625 having a set (at least one) of program modules 624, the program modules 624 including, but not limited to: an operating subsystem, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may comprise an implementation of a network environment.
Information asset identification device 600 may also communicate with one or more external devices 64 (e.g., keyboard, remote control, etc.), with one or more devices (e.g., cell phone, computer, etc.) that enable a user to interact with information asset identification device 600, and/or with any device (e.g., router, modem, etc.) that enables information asset identification device 600 to communicate with one or more other information asset identification devices 600. This communication may be via an Input/Output (I/O) interface 65. Also, information asset identification device 600 may also communicate with one or more networks (e.g., a Local Area Network (LAN), Wide Area Network (WAN), and/or a public Network, such as the internet) via Network adapter 66. As shown in FIG. 6, network adapter 66 communicates with the other modules of information asset identification device 600 via bus 63. It should be understood that although not shown in FIG. 6, other hardware and/or software modules may be used in conjunction with information asset identification device 600, including but not limited to: microcode, device drivers, Redundant processors, external disk drive Arrays, disk array (RAID) subsystems, tape drives, and data backup storage subsystems, to name a few.
The following describes a computer-readable storage medium provided by an embodiment of the present invention. The embodiment of the invention provides a computer-readable storage medium, which stores computer instructions, and the computer instructions are executed by a processor to realize the information asset identification method provided by the embodiment of the invention. Specifically, the executable program may be built in the information asset identification device 600, so that the information asset identification device 600 may implement the information asset identification method provided by the embodiment of the present invention by executing the built-in executable program.
Furthermore, the information asset identification method provided by the embodiment of the present invention may also be implemented as a program product including program code for causing the information asset identification apparatus 600 to execute the information asset identification method provided by the embodiment of the present invention when the program product is run on the information asset identification apparatus 600.
The program product provided by the embodiment of the present invention may adopt any combination of one or more readable media, wherein the readable media may be readable signal media or readable storage media, and the readable storage media may be but not limited to systems, apparatuses or devices of electric, magnetic, optical, electromagnetic, infrared or semiconductor, or any combination thereof, and specifically, more specific examples (non-exhaustive list) of the readable storage media include: an electrical connection having one or more wires, a portable disk, a hard disk, a RAM, a ROM, an Erasable Programmable Read-Only Memory (EPROM), an optical fiber, a portable Compact disk Read-Only Memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
The program product provided by the embodiment of the invention can adopt a CD-ROM and comprises program codes, and can run on a computing device. However, the program product provided by the embodiments of the present invention is not limited thereto, and in the embodiments of the present invention, the readable storage medium may be any tangible medium that can contain or store the program, which can be used by or in connection with an instruction execution system, apparatus, or device.
A readable signal medium may include a propagated data signal with readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A readable signal medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, etc., or any suitable combination of the foregoing.
Program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user device, partly on the user device, as a stand-alone software package, partly on the user device, partly on a remote computing device, or entirely on the remote computing device or server. In situations involving remote computing devices, the remote computing devices may be connected to the user computing device over any kind of network, such as over a LAN or WAN; alternatively, an external computing device may be connected (e.g., through the Internet using an Internet service provider).
It should be noted that although several units or sub-units of the apparatus are mentioned in the above detailed description, such division is merely exemplary and not mandatory. Indeed, the features and functions of two or more of the units described above may be embodied in one unit, according to embodiments of the invention. Conversely, the features and functions of one unit described above may be further divided into embodiments by a plurality of units.
Moreover, while the operations of the method of the invention are depicted in the drawings in a particular order, this does not require or imply that the operations must be performed in this particular order, or that all of the illustrated operations must be performed, to achieve desirable results. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step execution, and/or one step broken down into multiple step executions.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various modifications and variations can be made in the embodiments of the present invention without departing from the spirit or scope of the embodiments of the invention. Thus, if such modifications and variations of the embodiments of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to encompass such modifications and variations.
Claims (14)
1. An information asset identification method, comprising:
determining an information asset training set according to a set training category and a data acquisition network range corresponding to the set training category;
acquiring asset characteristic data of each information asset in multiple set dimensions, wherein the asset characteristic data are contained in the information asset training set, acquiring an asset characteristic data set corresponding to each information asset, and acquiring an asset class corresponding to each information asset;
and training a machine learning classification model based on the asset characteristic data set and the asset class corresponding to each information asset to obtain an information asset fingerprint model, wherein the information asset fingerprint model is used for determining the asset class corresponding to the information asset to be identified according to the asset characteristic data set of the information asset to be identified.
2. The information asset identification method according to claim 1, wherein if the plurality of set dimensions are a plurality of set communication protocols, acquiring asset feature data of each information asset included in the information asset training set in the plurality of set dimensions to obtain an asset feature data set corresponding to each information asset, comprises:
selecting one probe set from a plurality of probe sets as a probe set corresponding to the information asset training set, wherein the probe set comprises a set number of request data packets corresponding to each of a plurality of set communication protocols;
and aiming at each information asset contained in the information asset training set, in a first set time range, according to set data acquisition times, sending a request data packet to a physical entity corresponding to the information asset based on the probe set, and obtaining an asset characteristic data set corresponding to the information asset based on each response data packet returned by the physical entity corresponding to the information asset.
3. The information asset identification method according to claim 1, wherein the asset class corresponding to each of the information assets is described in a general classification manner.
4. The information asset identification method according to claim 1, wherein obtaining the asset class corresponding to each of the information assets comprises:
determining an information asset class set according to the set training class, respectively matching each information asset class contained in the information asset class set with each information asset, and determining the asset class corresponding to each information asset according to the matching result; or,
and extracting the asset class corresponding to each information asset from the asset characteristic data set corresponding to each information asset.
5. The information asset identification method according to claim 1, wherein training a machine learning classification model based on the asset feature data set and the asset class corresponding to each of the information assets to obtain an information asset fingerprint model comprises:
carrying out quantization processing on the asset characteristic data set and the asset class corresponding to each information asset to obtain a quantized asset characteristic data set and a quantized asset class corresponding to each information asset;
performing the following iterative training based on the quantized asset feature data set and the quantized asset class corresponding to each information asset:
performing parameter configuration on the machine learning classification model based on a target configuration parameter to obtain a target machine learning classification model, wherein the target configuration parameter is an initialization configuration parameter during first iterative training, and the target configuration parameter is a configuration parameter obtained after the target configuration parameter used in the last iterative training process is adjusted based on a configuration parameter adjustment step length determined in the last iterative training process during non-first iterative training;
selecting a set number of quantized asset characteristic data from the quantized asset characteristic data sets corresponding to the information assets respectively as target asset characteristic data corresponding to the information assets respectively;
inputting the target asset characteristic data corresponding to each information asset into the target machine learning classification model to obtain a prediction asset class corresponding to each information asset;
determining the difference degree between the predicted asset class and the quantified asset class corresponding to each information asset;
judging whether the target machine learning classification model obtained by the iterative training meets the preset accuracy or not based on the difference degree corresponding to each information asset;
if so, determining the target machine learning classification model obtained by the iterative training as an information asset fingerprint model;
and if not, determining the adjustment step length of the configuration parameters based on the difference degree corresponding to each information asset.
6. The information asset identification method according to any one of claims 1 to 5, further comprising:
adjusting the data acquisition network range corresponding to the set training category, and determining an incremental information asset training set according to the adjusted data acquisition network range;
acquiring asset characteristic data of each incremental information asset in multiple set dimensions, wherein the asset characteristic data are contained in the incremental information asset training set, so as to obtain an asset characteristic data set corresponding to each incremental information asset, and acquire an asset class corresponding to each incremental information asset;
and performing optimization training on the information asset fingerprint model based on the asset characteristic data set and the asset class corresponding to each incremental information asset.
7. An information asset identification device, comprising:
the system comprises a determining unit, a processing unit and a processing unit, wherein the determining unit is used for determining an information asset training set according to a set training category and a set data acquisition network range corresponding to the set training category;
the acquisition unit is used for acquiring asset characteristic data of each information asset in a plurality of set dimensions contained in the information asset training set to obtain an asset characteristic data set corresponding to each information asset;
the acquisition unit is used for acquiring the asset types corresponding to the information assets;
and the training unit is used for training the machine learning classification model based on the asset characteristic data set corresponding to each information asset acquired by the acquisition unit and the asset class corresponding to each information asset acquired by the acquisition unit to obtain an information asset fingerprint model, wherein the information asset fingerprint model is used for determining the asset class corresponding to the information asset to be identified according to the asset characteristic data set of the information asset to be identified.
8. The information asset identification device according to claim 7, wherein the plurality of set dimensions are a plurality of set communication protocols, and when acquiring asset feature data of each information asset included in the information asset training set in the plurality of set dimensions to obtain an asset feature data set corresponding to each information asset, the acquisition unit is configured to:
selecting one probe set from a plurality of probe sets as a probe set corresponding to the information asset training set, wherein the probe set comprises a set number of request data packets corresponding to each of a plurality of set communication protocols;
and aiming at each information asset contained in the information asset training set, in a first set time range, according to set data acquisition times, sending a request data packet to a physical entity corresponding to the information asset based on the probe set, and obtaining an asset characteristic data set corresponding to the information asset based on each response data packet returned by the physical entity corresponding to the information asset.
9. The information asset identification device according to claim 7, wherein the asset class corresponding to each of the information assets obtained by the obtaining unit is described in a general classification manner.
10. The information asset identification device according to claim 7, wherein, when acquiring the asset class corresponding to each of the information assets, the acquiring unit is configured to:
determining an information asset class set according to the set training class, respectively matching each information asset class contained in the information asset class set with each information asset, and determining the asset class corresponding to each information asset according to the matching result; or,
and extracting the asset class corresponding to each information asset from the asset characteristic data set corresponding to each information asset.
11. The information asset identification device according to claim 7, wherein when the machine learning classification model is trained based on the asset feature data set corresponding to each of the information assets acquired by the acquisition unit and the asset class corresponding to each of the information assets acquired by the acquisition unit to obtain the information asset fingerprint model, the training unit is configured to:
carrying out quantization processing on the asset characteristic data set and the asset class corresponding to each information asset to obtain a quantized asset characteristic data set and a quantized asset class corresponding to each information asset;
performing the following iterative training based on the quantized asset feature data set and the quantized asset class corresponding to each information asset:
performing parameter configuration on the machine learning classification model based on a target configuration parameter to obtain a target machine learning classification model, wherein the target configuration parameter is an initialization configuration parameter during first iterative training, and the target configuration parameter is a configuration parameter obtained after the target configuration parameter used in the last iterative training process is adjusted based on a configuration parameter adjustment step length determined in the last iterative training process during non-first iterative training;
selecting a set number of quantized asset characteristic data from the quantized asset characteristic data sets corresponding to the information assets respectively as target asset characteristic data corresponding to the information assets respectively;
inputting the target asset characteristic data corresponding to each information asset into the target machine learning classification model to obtain a prediction asset class corresponding to each information asset;
determining the difference degree between the predicted asset class and the quantified asset class corresponding to each information asset;
judging whether the target machine learning classification model obtained by the iterative training meets the preset accuracy or not based on the difference degree corresponding to each information asset;
if so, determining the target machine learning classification model obtained by the iterative training as an information asset fingerprint model;
and if not, determining the adjustment step length of the configuration parameters based on the difference degree corresponding to each information asset.
12. The information asset identification device according to any one of claims 7-11, further comprising:
the incremental training unit is used for adjusting the data acquisition network range corresponding to the set training category and determining an incremental information asset training set according to the adjusted data acquisition network range; acquiring asset characteristic data of each incremental information asset in multiple set dimensions, wherein the asset characteristic data are contained in the incremental information asset training set, so as to obtain an asset characteristic data set corresponding to each incremental information asset, and acquire an asset class corresponding to each incremental information asset; and performing optimization training on the information asset fingerprint model based on the asset characteristic data set and the asset class corresponding to each incremental information asset.
13. An information asset identification device, comprising: a memory, a processor, and computer instructions stored on the memory, the processor executing the computer instructions to implement the information asset identification method of any of claims 1-6.
14. A computer-readable storage medium storing computer instructions which, when executed by a processor, implement the information asset identification method of any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811643242.7A CN109726763B (en) | 2018-12-29 | 2018-12-29 | Information asset identification method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811643242.7A CN109726763B (en) | 2018-12-29 | 2018-12-29 | Information asset identification method, device, equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109726763A true CN109726763A (en) | 2019-05-07 |
| CN109726763B CN109726763B (en) | 2021-05-28 |
Family
ID=66299393
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811643242.7A Active CN109726763B (en) | 2018-12-29 | 2018-12-29 | Information asset identification method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109726763B (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110991509A (en) * | 2019-11-25 | 2020-04-10 | 杭州安恒信息技术股份有限公司 | Asset identification and information classification method based on artificial intelligence technology |
| CN111260219A (en) * | 2020-01-16 | 2020-06-09 | 泰康保险集团股份有限公司 | Asset class identification method, device, equipment and computer readable storage medium |
| CN111369010A (en) * | 2020-03-31 | 2020-07-03 | 绿盟科技集团股份有限公司 | Information asset class identification method, device, medium and equipment |
| CN111985513A (en) * | 2019-05-22 | 2020-11-24 | 国家计算机网络与信息安全管理中心 | Rapid identification network asset attribution system and identification analysis method thereof |
| CN111984840A (en) * | 2020-09-07 | 2020-11-24 | 中国银行股份有限公司 | Online asset safety display locking method and device |
| CN112487270A (en) * | 2019-09-12 | 2021-03-12 | 北京白帽汇科技有限公司 | Method and device for asset classification and accuracy verification based on picture identification |
| CN112488143A (en) * | 2019-09-12 | 2021-03-12 | 北京白帽汇科技有限公司 | Network asset localization identification method, device, equipment and storage medium |
| CN112688973A (en) * | 2021-03-22 | 2021-04-20 | 远江盛邦（北京）网络安全科技股份有限公司 | Network space asset description method based on fingerprint technology |
| CN113239360A (en) * | 2021-04-30 | 2021-08-10 | 杭州安恒信息技术股份有限公司 | Network asset management method based on machine learning and related components |
| CN113743542A (en) * | 2021-11-05 | 2021-12-03 | 北京广通优云科技股份有限公司 | Network asset identification method and system based on encrypted flow |
| CN115766547A (en) * | 2022-10-26 | 2023-03-07 | 杭州迪普科技股份有限公司 | Asset identification terminal testing method and system |
| CN116996355A (en) * | 2023-09-22 | 2023-11-03 | 深圳海云安网络安全技术有限公司 | Industrial control network asset discovery method based on neural network |
| CN118468151A (en) * | 2024-06-28 | 2024-08-09 | 深圳市广通工程顾问有限公司 | Automatic management method and system for classification of network digital virtual assets |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140254865A1 (en) * | 2013-03-08 | 2014-09-11 | Trimble Navigation Limited | Image Identification Method and System |
| CN104200087A (en) * | 2014-06-05 | 2014-12-10 | 清华大学 | Parameter optimization and feature tuning method and system for machine learning |
| CN105184313A (en) * | 2015-08-24 | 2015-12-23 | 小米科技有限责任公司 | Classification model construction method and device |
| CN106101098A (en) * | 2016-06-13 | 2016-11-09 | 金邦达有限公司 | A kind of information assets recognition methods and device |
| CN106888194A (en) * | 2015-12-16 | 2017-06-23 | 国家电网公司 | Intelligent grid IT assets security monitoring systems based on distributed scheduling |
| CN107451660A (en) * | 2017-07-21 | 2017-12-08 | 江南大学 | Step-length optimization method in fuzzy neural network BP training process |
| CN109033471A (en) * | 2018-09-05 | 2018-12-18 | 中国信息安全测评中心 | A kind of information assets recognition methods and device |
| CN109104395A (en) * | 2017-06-21 | 2018-12-28 | 亿阳安全技术有限公司 | The method and apparatus of internet assets scanning discovery and service identification |
-
2018
- 2018-12-29 CN CN201811643242.7A patent/CN109726763B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140254865A1 (en) * | 2013-03-08 | 2014-09-11 | Trimble Navigation Limited | Image Identification Method and System |
| CN104200087A (en) * | 2014-06-05 | 2014-12-10 | 清华大学 | Parameter optimization and feature tuning method and system for machine learning |
| CN105184313A (en) * | 2015-08-24 | 2015-12-23 | 小米科技有限责任公司 | Classification model construction method and device |
| CN106888194A (en) * | 2015-12-16 | 2017-06-23 | 国家电网公司 | Intelligent grid IT assets security monitoring systems based on distributed scheduling |
| CN106101098A (en) * | 2016-06-13 | 2016-11-09 | 金邦达有限公司 | A kind of information assets recognition methods and device |
| CN109104395A (en) * | 2017-06-21 | 2018-12-28 | 亿阳安全技术有限公司 | The method and apparatus of internet assets scanning discovery and service identification |
| CN107451660A (en) * | 2017-07-21 | 2017-12-08 | 江南大学 | Step-length optimization method in fuzzy neural network BP training process |
| CN109033471A (en) * | 2018-09-05 | 2018-12-18 | 中国信息安全测评中心 | A kind of information assets recognition methods and device |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111985513A (en) * | 2019-05-22 | 2020-11-24 | 国家计算机网络与信息安全管理中心 | Rapid identification network asset attribution system and identification analysis method thereof |
| CN112487270A (en) * | 2019-09-12 | 2021-03-12 | 北京白帽汇科技有限公司 | Method and device for asset classification and accuracy verification based on picture identification |
| CN112488143A (en) * | 2019-09-12 | 2021-03-12 | 北京白帽汇科技有限公司 | Network asset localization identification method, device, equipment and storage medium |
| CN110991509B (en) * | 2019-11-25 | 2023-08-01 | 杭州安恒信息技术股份有限公司 | Asset identification and information classification method based on artificial intelligence technology |
| CN110991509A (en) * | 2019-11-25 | 2020-04-10 | 杭州安恒信息技术股份有限公司 | Asset identification and information classification method based on artificial intelligence technology |
| CN111260219A (en) * | 2020-01-16 | 2020-06-09 | 泰康保险集团股份有限公司 | Asset class identification method, device, equipment and computer readable storage medium |
| CN111369010A (en) * | 2020-03-31 | 2020-07-03 | 绿盟科技集团股份有限公司 | Information asset class identification method, device, medium and equipment |
| CN111369010B (en) * | 2020-03-31 | 2024-03-15 | 绿盟科技集团股份有限公司 | Information asset class identification method, device, medium and equipment |
| CN111984840A (en) * | 2020-09-07 | 2020-11-24 | 中国银行股份有限公司 | Online asset safety display locking method and device |
| CN111984840B (en) * | 2020-09-07 | 2023-09-22 | 中国银行股份有限公司 | Online asset security display locking method and device |
| CN112688973A (en) * | 2021-03-22 | 2021-04-20 | 远江盛邦（北京）网络安全科技股份有限公司 | Network space asset description method based on fingerprint technology |
| CN113239360A (en) * | 2021-04-30 | 2021-08-10 | 杭州安恒信息技术股份有限公司 | Network asset management method based on machine learning and related components |
| CN113743542A (en) * | 2021-11-05 | 2021-12-03 | 北京广通优云科技股份有限公司 | Network asset identification method and system based on encrypted flow |
| CN113743542B (en) * | 2021-11-05 | 2022-03-01 | 北京广通优云科技股份有限公司 | Network asset identification method and system based on encrypted flow |
| CN115766547A (en) * | 2022-10-26 | 2023-03-07 | 杭州迪普科技股份有限公司 | Asset identification terminal testing method and system |
| CN115766547B (en) * | 2022-10-26 | 2024-06-28 | 杭州迪普科技股份有限公司 | Asset identification terminal testing method and system |
| CN116996355A (en) * | 2023-09-22 | 2023-11-03 | 深圳海云安网络安全技术有限公司 | Industrial control network asset discovery method based on neural network |
| CN116996355B (en) * | 2023-09-22 | 2023-11-28 | 深圳海云安网络安全技术有限公司 | Industrial control network asset discovery method based on neural network |
| CN118468151A (en) * | 2024-06-28 | 2024-08-09 | 深圳市广通工程顾问有限公司 | Automatic management method and system for classification of network digital virtual assets |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109726763B (en) | 2021-05-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109726763B (en) | Information asset identification method, device, equipment and medium | |
| US10565442B2 (en) | Picture recognition method and apparatus, computer device and computer- readable medium | |
| CN109241418B (en) | Abnormal user identification method and device based on random forest, equipment and medium | |
| AU2020385264B2 (en) | Fusing multimodal data using recurrent neural networks | |
| KR102201919B1 (en) | Random forest model training method, electronic device and storage medium | |
| CN111143226B (en) | Automatic test method and device, computer readable storage medium and electronic equipment | |
| CN113326991B (en) | Automatic authorization method, device, computer equipment and storage medium | |
| CN109660533B (en) | Method and device for identifying abnormal flow in real time, computer equipment and storage medium | |
| CN109669853A (en) | Test report generation method and device, storage medium, electric terminal | |
| CN112181835B (en) | Automatic test method, device, computer equipment and storage medium | |
| CN111181757A (en) | Information security risk prediction method and device, computing equipment and storage medium | |
| CN111383100A (en) | Risk model-based full life cycle management and control method and device | |
| WO2020173270A1 (en) | Method and device used for parsing data and computer storage medium | |
| CN111199469A (en) | User payment model generation method and device and electronic equipment | |
| US20120226484A1 (en) | Calculation simulation system and method thereof | |
| CN116684330A (en) | Traffic prediction method, device, equipment and storage medium based on artificial intelligence | |
| CN115757075A (en) | Task abnormity detection method and device, computer equipment and storage medium | |
| CN104580109A (en) | Method and device for generating click verification code | |
| CN111582649B (en) | Risk assessment method and device based on user APP single-heat coding and electronic equipment | |
| CN110717315B (en) | System data batch modification method and device, storage medium and electronic equipment | |
| CN115147020A (en) | Decoration data processing method, device, equipment and storage medium | |
| CN110083807B (en) | Contract modification influence automatic prediction method, device, medium and electronic equipment | |
| CN114610590A (en) | Method, device and equipment for determining operation time length and storage medium | |
| CN112905896A (en) | Training method of recommended number model, and mixed content recommendation method and device | |
| WO2020232899A1 (en) | Troubleshooting method for data analysis system, and related device |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 100089 3rd floor, Yitai building, 4 Beiwa Road, Haidian District, Beijing Applicant after: NSFOCUS Technologies Group Co.,Ltd. Applicant after: NSFOCUS TECHNOLOGIES Inc. Address before: 100089 3rd floor, Yitai building, 4 Beiwa Road, Haidian District, Beijing Applicant before: NSFOCUS INFORMATION TECHNOLOGY Co.,Ltd. Applicant before: NSFOCUS TECHNOLOGIES Inc. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |