CN111260220A - Group control equipment identification method and device, electronic equipment and storage medium - Google Patents
Group control equipment identification method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN111260220A CN111260220A CN202010047179.1A CN202010047179A CN111260220A CN 111260220 A CN111260220 A CN 111260220A CN 202010047179 A CN202010047179 A CN 202010047179A CN 111260220 A CN111260220 A CN 111260220A
- Authority
- CN
- China
- Prior art keywords
- group control
- app
- equipment
- preset
- vector
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/018—Certifying business or products
- G06Q30/0185—Product, service or business identity fraud
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application provides a group control equipment identification method, a group control equipment identification device, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring an APP list of equipment to be identified; determining the characteristic weight of the APP in the APP list according to the characteristic weight of a preset APP; calculating a feature vector of the equipment to be identified by using the feature weight of the APP in the APP list; acquiring a minimum value d1 in the vector similarity between the feature vector of the equipment to be identified and the feature vectors of cluster center equipment of a plurality of preset cluster control equipment clusters; acquiring a minimum value d2 in the vector similarity between the feature vector of the device to be identified and the feature vectors of cluster center devices of a plurality of preset non-cluster control device clusters; determining the probability that the device to be identified is a group control device using d1 and d 2. The method can improve the efficiency and accuracy of identifying the group control equipment.
Description
Technical Field
The invention relates to the technical field of big data service wind control, in particular to a group control equipment identification method and device, electronic equipment and a storage medium.
Background
In the technical field of big data service wind control, a large number of group control devices in gray and black products are accurately identified.
The prior art is mainly divided into two types:
the first method comprises the following steps: the identification method based on the technical attribute of the equipment and the identification method based on the service behavior of the equipment. For the identification method based on the technical attributes of the equipment, the working principle and the working mode are as follows: firstly, extracting technical attribute information of Equipment, such as International Mobile Equipment Identity (IMEI), Equipment fingerprint (Device fingerprint) and the like, then comparing the extracted technical attribute information with a compliance Equipment database, if the extracted technical attribute information is not in the database, considering the Equipment as illegal Equipment, and if the information of IP and the like of the Equipment has a gathering phenomenon, considering the Equipment as group control Equipment;
with the advent of various computer software, it is easier and cheaper to modify the technical attributes of a piece of equipment, so that the method is easily bypassed by grey and black products, thereby losing the recognition capability.
And the second method comprises the following steps: the identification method based on the equipment service behavior has the working principle and the working mode as follows: the method comprises the steps of firstly collecting various service behaviors of the equipment, such as the times of sending http requests by the equipment, the daily login times of the equipment and the like, then establishing a machine learning classification model, and outputting a frequency value of the equipment, which is a group control equipment, to each equipment.
The method has higher development cost, and needs to collect the actions of the equipment in each service scene; the time required for establishing a machine learning classification model with high accuracy is long, and a large amount of time is consumed for finding a few effective characteristics from a large amount of characteristics.
Disclosure of Invention
In view of this, the present application provides a group control device identification method, apparatus, electronic device and storage medium, which can improve efficiency and accuracy of identifying group control devices.
In order to solve the technical problem, the technical scheme of the application is realized as follows:
in one embodiment, a group control device identification method is provided, and the method includes:
acquiring an application program APP list of equipment to be identified;
determining the characteristic weight of the APP in the APP list according to the characteristic weight of a preset APP;
calculating a feature vector of the equipment to be identified by using the feature weight of the APP in the APP list;
acquiring a minimum value d1 in the vector similarity between the feature vector of the equipment to be identified and the feature vectors of cluster center equipment of a plurality of preset cluster control equipment clusters;
acquiring a minimum value d2 in the vector similarity between the feature vector of the device to be identified and the feature vectors of cluster center devices of a plurality of preset non-cluster control device clusters;
determining the probability that the device to be identified is a group control device using d1 and d 2.
The obtaining of the feature vector of the cluster center device of the preset cluster control device cluster and the feature vector of the cluster center device of the preset non-cluster control device cluster includes:
acquiring APP lists of a plurality of group control devices and APP lists of a plurality of non-group control devices;
determining the characteristic weight of the APP according to the APPs in the APP lists of the plurality of group control devices and the plurality of non-group control devices;
calculating a feature vector of the group control equipment by using the feature weight of the APP in the APP list of the group control equipment; clustering the cluster control equipment based on the characteristic vector to obtain a characteristic vector of cluster center equipment of a preset cluster control equipment cluster formed by clustering;
calculating a feature vector of the non-group control equipment by using the feature weight of the APP in the APP list of the non-group control equipment; and clustering the non-group control equipment based on the characteristic vector, and acquiring the characteristic vector of cluster center equipment of a preset non-group control equipment cluster formed by clustering.
Wherein, clustering is carried out by using a DBSCAN algorithm during clustering;
when clustering is conducted on the group control equipment, the distance threshold parameter is set to be the vector similarity of a middle value in the vector similarities between every two group control equipment, and the minimum cluster sample threshold is set to be a first preset ratio of the total number of the group control equipment;
when non-group control equipment is clustered, the distance threshold parameter is set to be the vector similarity of a middle value in the vector similarities between every two non-group control equipment, and the minimum cluster sample threshold is set to be a second preset ratio of the total number of the non-group control equipment; the first preset ratio and the second preset ratio are the same or different.
Wherein, the determining the feature weight of the APP according to the APPs in the APP lists of the plurality of group control devices and the plurality of non-group control devices includes:
determining a first distribution frequency of the group control equipment in the group control equipment and the non-group control equipment;
determining a second distribution frequency of the APP in the group control equipment and the non-group control equipment;
calculating an absolute value of a difference between the first distributed frequency and the second distributed frequency;
calculating a difference between 1 and an absolute value of the difference;
determining the difference between 1 and the absolute value of the difference as the characteristic weight of the APP.
Wherein, using the feature weights of the APPs in the APP list to calculate the feature vector comprises:
coding and converting the APP in the APP list into a character string; calculating a Hash value of a preset digit;
multiplying the characteristic weight of the APP by each digit in the Hash value to obtain a numerical value vector with the length being the preset digit;
adding corresponding bits of numerical vectors corresponding to the APPs in the APP list to obtain the numerical vectors with the lengths of preset bits corresponding to the APP list;
and setting each bit element in the numerical value vector with the length of a preset bit corresponding to the APP list according to a rule that the bit element is not less than 0 and is 1 and less than 0 and is 0 to obtain the feature vector of the preset bit.
Wherein the determining the probability that the device to be identified is a group control device using d1 and d2 comprises:
calculating the sum of d1 and d 2;
calculating the ratio of d2 to the sum;
and determining the ratio as the probability that the equipment to be identified is the group control equipment.
In another embodiment, there is provided a group control device identification apparatus, including: the device comprises a storage unit, a first acquisition unit, a first determination unit, a calculation unit, a second acquisition unit and a second determination unit;
the storage unit is used for storing the feature weight of a preset APP, the feature vectors of cluster center equipment of a plurality of preset cluster control equipment clusters and the feature vectors of cluster center equipment of a plurality of preset non-cluster control equipment clusters;
the first obtaining unit is used for obtaining an APP list of equipment to be identified;
the first determining unit is configured to determine, according to the feature weight of a preset APP stored in the storage unit, the feature weight of an APP in the APP list acquired by the first acquiring unit;
the calculating unit is used for calculating a feature vector of the equipment to be identified by using the feature weight of the APP in the APP list determined by the first determining unit;
the second obtaining unit is configured to obtain a minimum value d1 in vector similarities between the feature vector of the device to be identified, which is calculated by the calculating unit, and the feature vectors of the cluster center devices of the plurality of preset cluster control device clusters, which are stored in the storage unit; acquiring a minimum value d2 in the vector similarity between the feature vector of the device to be identified calculated by the calculating unit and the feature vectors of the cluster center devices of the plurality of preset non-cluster control device clusters stored by the storage unit;
the second determining unit is configured to determine the probability that the device to be identified is a group control device by using the d1 and the d2 acquired by the second acquiring unit.
Wherein the content of the first and second substances,
the first obtaining unit is further configured to obtain APP lists of a plurality of group control devices and APP lists of a plurality of non-group control devices;
the first determining unit is further configured to determine a feature weight of an APP according to APPs in APP lists of a plurality of group control devices and a plurality of non-group control devices;
the computing unit is further configured to compute a feature vector of the group control device by using the feature weight of the APP in the APP list of the group control device;
the storage unit is further configured to cluster the group control equipment based on the feature vector, obtain and store a feature vector of cluster center equipment of a preset group control equipment cluster formed by clustering; calculating a feature vector of the non-group control equipment by using the feature weight of the APP in the APP list of the non-group control equipment; and clustering the non-group control equipment based on the characteristic vector, and acquiring and storing the characteristic vector of cluster center equipment of a preset non-group control equipment cluster formed by clustering.
The storage unit is specifically used for clustering by using a DBSCAN algorithm during clustering;
when clustering is conducted on the group control equipment, the distance threshold parameter is set to be the vector similarity of a middle value in the vector similarities between every two group control equipment, and the minimum cluster sample threshold is set to be a first preset ratio of the total number of the group control equipment;
when non-group control equipment is clustered, the distance threshold parameter is set to be the vector similarity of a middle value in the vector similarities between every two non-group control equipment, and the minimum cluster sample threshold is set to be a second preset ratio of the total number of the non-group control equipment; the first preset ratio and the second preset ratio are the same or different.
The first determining unit is specifically configured to determine a first distribution frequency of the group control device in the group control device and the non-group control device; determining a second distribution frequency of the APP in the group control equipment and the non-group control equipment; calculating an absolute value of a difference between the first distributed frequency and the second distributed frequency; calculating a difference between 1 and an absolute value of the difference; determining the difference between 1 and the absolute value of the difference as the characteristic weight of the APP.
Wherein, the calculating unit, when being specifically configured to calculate the feature vector using the feature weights of the APPs in the APP list, includes:
coding and converting the APP in the APP list into a character string; calculating a Hash value of a preset digit;
multiplying the characteristic weight of the APP by each digit in the Hash value to obtain a numerical value vector with the length being the preset digit;
adding corresponding bits of numerical vectors corresponding to the APPs in the APP list to obtain the numerical vectors with the lengths of preset bits corresponding to the APP list;
and setting each bit element in the numerical value vector with the length of a preset bit corresponding to the APP list according to a rule that the bit element is not less than 0 and is 1 and less than 0 and is 0 to obtain the feature vector of the preset bit.
The second determining unit, when specifically determining the probability that the device to be identified is the group control device by using d1 and d2, includes:
calculating the sum of d1 and d 2;
calculating the ratio of d2 to the sum;
and determining the ratio as the probability that the equipment to be identified is the group control equipment.
In another embodiment, an electronic device is provided, comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the group control device identification method when executing the program.
In another embodiment, a computer readable storage medium is provided, on which a computer program is stored which, when being executed by a processor, carries out the steps of the group control device identification method.
According to the technical scheme, based on the characteristic vector clustering, the distance between the equipment to be identified and the characteristic vector of the cluster center equipment of the cluster formed by clustering is further determined to determine the probability that the equipment to be identified is the group control equipment. The scheme can improve the efficiency and accuracy of identifying the group control equipment. The feature weight calculation method based on APP frequency distribution in the above embodiment can reduce feature dimensionality, save storage space, and improve calculation speed. The feature quantity of each feature of one device is often more than one hundred thousand after the feature is subjected to code conversion, and the data quantity of the magnitude is huge in memory consumption and long in calculation time. By eliminating useless features and reserving a very small amount of useful features, the memory consumption and the calculation time can be effectively reduced, and the accuracy of identifying the group control equipment is not affected finally.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive labor.
Fig. 1 is a schematic flow chart illustrating a process of obtaining a feature vector of cluster center equipment of a preset group control equipment cluster and a preset non-group control equipment cluster in an embodiment of the present application;
FIG. 2 is a schematic flow chart illustrating a process of calculating feature vectors using feature weights of APPs in an APP list according to an embodiment of the present application;
FIG. 3 is a schematic flow chart illustrating identification of group control devices according to an embodiment of the present disclosure;
FIG. 4 is a schematic diagram of an apparatus for implementing the above technique in an embodiment of the present application;
fig. 5 is a schematic physical structure diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, 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 application.
The terms "first," "second," "third," "fourth," and the like in the description and in the claims, as well as in the drawings, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are, for example, capable of operation in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprising" and "having," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements explicitly listed, but may include other steps or elements not explicitly listed or inherent to such process, method, article, or apparatus.
The technical solution of the present invention will be described in detail with specific examples. Several of the following embodiments may be combined with each other and some details of the same or similar concepts or processes may not be repeated in some embodiments.
The embodiment of the application provides a group control equipment identification method, which can be executed by equipment with data processing capacity, such as a PC (personal computer), a server and the like.
Before group control equipment identification is carried out, feature vectors of cluster center equipment of a plurality of preset group control equipment clusters, feature vectors of cluster center equipment of a plurality of preset non-group control equipment clusters and feature weights of preset application programs (APP) need to be determined, and specific determination processes are respectively given as follows:
the feature vector in the embodiment of the present application refers to a numeric character string, such as a character string vector consisting of 0 and 1.
Referring to fig. 1, fig. 1 is a schematic flowchart of a process of acquiring a feature vector of a cluster center device of a preset group control device cluster and a preset non-group control device cluster in an embodiment of the present application, and the specific steps are as follows:
When obtaining the APP list, the APP list stored for each device may be directly obtained, or obtained from each group control device and non-group control device, and when obtaining the APP list from the group control device and the non-group control device, the APP list needs to be obtained in different manners for devices of different system types, which is specifically as follows:
for an Android device, an APP list of the device can be obtained through a packageManager of an Android SDK;
for apple devices, we can use LSApplationWorkspace to obtain APP lists before iOS11, and for versions above iOS11 we can check if App exists to obtain APP lists based on BundleId.
The foregoing provides a specific implementation manner for obtaining an APP list, and the implementation manner is only an example and is not limited to the implementation manner.
The APP in the APP list is an APP deployed on the device, such as an application program of WeChat, Paibao, chainmaker, Taobao, Jingdong, shell and the like.
And 102, determining the characteristic weight of the APP according to the APPs in the APP lists of the plurality of group control devices and the plurality of non-group control devices.
Determining the implementation of the weight of any APP specifically as follows:
the method comprises the steps of firstly, determining a first distribution frequency of the group control equipment in the group control equipment and the non-group control equipment.
The first distribution frequency is a ratio of the group control devices to all the devices (the group control devices and the non-group control devices), for example, N1 group control devices and N2 non-group control devices, the first distribution frequency P1 is N1/(N1+ N2);
and secondly, determining a second distribution frequency of the APP in the group control equipment and the non-group control equipment.
That is, for one APP, the ratio of the device that deploys the APP to all devices, for example, M1 devices that deploy the APP among N1 group control devices, and M2 devices that deploy the APP among N2 non-group control devices, then the second distribution frequency P2 ═ M1+ M2)/(N1+ N2.
And thirdly, calculating the absolute value of the difference value of the first distribution frequency and the second distribution frequency.
The third step may be: i P1-P2I.
And fourthly, calculating the difference between 1 and the absolute value of the difference.
The result of the fourth step may be 1- | P1-P2 |.
And fifthly, determining the difference between 1 and the absolute value of the difference as the feature weight of the APP.
The characteristic weight of APP is 1- | P1-P2 |.
This completes the determination of the feature weights of the APP.
By the method, the characteristic weight of each APP in the APP lists of all the devices (group control device and non-group control device) in the sample can be calculated, and recorded so as to determine the characteristic weight of the APP in the APP list of the device to be identified when the device to be identified is identified.
And calculating and recording the feature weight of each APP in the process of determining the feature vector of the cluster center equipment.
The feature weight calculation method based on APP frequency distribution can reduce feature dimensionality, save storage space and improve calculation speed. The number of the features of one device is more than one hundred thousand after passing through the OneHot, and the data volume of the order of magnitude is huge in memory consumption and long in calculation time. By eliminating useless features and reserving a very small amount of useful features, the memory consumption and the calculation time can be effectively reduced, and the accuracy of identifying the group control equipment is not affected finally.
103, calculating a feature vector of the group control equipment by using the feature weight of the APP in the APP list of the group control equipment; and clustering the cluster control equipment based on the characteristic vector to obtain the characteristic vector of cluster center equipment of a preset cluster control equipment cluster formed by clustering.
104, calculating a feature vector of the non-group control equipment by using the feature weight of the APP in the APP list of the non-group control equipment; and clustering the non-group control equipment based on the characteristic vector, and acquiring the characteristic vector of cluster center equipment of a preset non-group control equipment cluster formed by clustering.
Step 103 and step 104 are not in sequence when executed, and may be executed simultaneously.
In the embodiment of the application, the feature vector of the group control equipment is calculated by using the feature weight of the APP in the APP list of the group control equipment; the process of calculating the feature vector of the non-group control device by using the feature weight of the APP in the APP list of the non-group control device is similar to that of the feature vector of the non-group control device. Referring to fig. 2, fig. 2 is a schematic flowchart of computing a feature vector by using feature weights of APPs in an APP list in the embodiment of the present application.
The method comprises the following specific steps:
Each APP in the APP list can be encoded in an One-Hot manner, for example, the encoding of the One-Hot manner for the shell APP is shown in table 1, and table 1 is the content corresponding to the encoding of the shell APP in the One-Hot manner.
| Payment device | Taobao (treasure made of Chinese herbal medicine) | Jingdong | Shell | … | Chain family | |
| 0 | 0 | 0 | 0 | 1 | 0 |
TABLE 1
As shown in table 1, when an APP, which is a shell, is encoded, a code value corresponding to the APP is set to 1, and code values corresponding to other APPs are set to 0, where the APPs participating in encoding are all APPs related to the group control device and the non-group control device, and may also be all preset APPs.
The character string coded by the One-Hot mode is '00001 … 0', and the digit of the character string is the number of APPs;
the Hash value of the preset number of bits can be calculated by using an MD5 digest algorithm, but is not limited to the algorithm;
the preset digit can be set according to actual needs, for example, the value of the preset digit can be 64.
And step 202, multiplying the feature weight of the APP by each bit in the Hash value to obtain a numerical value vector with the length of the preset number of bits.
Through step 202, a numerical vector with the length of each APP being a preset digit can be calculated, and corresponding digits of the numerical vectors corresponding to multiple APPs in the APP list are added to obtain the numerical vector with the length of the preset digit corresponding to the APP list;
if there is only one APP in the current APP list, the numerical vector with the length of the preset digit obtained in step 202 is used as the numerical vector with the length of the preset digit corresponding to the APP list.
And 204, setting each bit element in the numerical value vector with the length of a preset bit corresponding to the APP list according to a rule that the bit element is not less than 0 and is set to 1 and less than 0 and is set to 0, and obtaining the feature vector of the preset bit.
The obtained feature vector here is a character string composed of 1 and 0 and having a length of a preset number of bits.
Thus, a feature vector of a device (cluster control device or non-cluster control device) is obtained. The method can be realized through the execution of the steps at each time in specific implementation, and the implementation mode can be packaged into a transcoding model file, and when the APP in an APP list is obtained, the transcoding model file is called to directly obtain the corresponding feature vector.
After the feature vectors of the devices are obtained, Clustering needs to be performed on the group control devices and the non-group control devices, and Clustering can be performed by using a Density-Based Clustering of application switching Noise (DBSCAN) algorithm during Clustering;
when clustering is carried out on the group control equipment by using a DBSCAN algorithm, the distance threshold parameter is set to be the vector similarity of a middle value in the vector similarities between every two group control equipment, and the minimum cluster sample threshold is set to be a first preset ratio of the total number of the group control equipment;
the implementation of determining the vector similarity of the intermediate values for the group control device is as follows:
acquiring the vector similarity between every two group control devices;
sequencing the obtained vector similarities from large to small or from small to large;
determining the vector similarity ordered at the middle position as the vector similarity of the middle numerical value;
if the vector similarity at the middle position is two, and if the two vector similarities at the middle position have the same value, determining the vector similarity as the vector similarity of the middle data; if the two vector similarities at the middle position are different, one vector similarity is selected according to a preset rule, for example, one vector similarity is randomly selected as the vector similarity of the middle value.
In the embodiment of the present application, the feature vector determined according to the feature weight may be, for example, a SimHash code, a TF feature vector, or the like.
The vector similarity may be a hamming distance obtained for the corresponding SimHash code, an edit distance obtained for the TF feature vector (TF-IDF).
When clustering is carried out on non-group control equipment by using a DBSCAN algorithm, the distance threshold parameter is set to be the vector similarity of a middle value in the vector similarities between every two non-group control equipment, and the minimum cluster sample threshold is set to be a second preset ratio of the total number of the non-group control equipment;
the implementation of determining the vector similarity of the intermediate values for the non-group control devices is as follows:
acquiring the vector similarity between every two pieces of non-group control equipment;
sequencing the obtained vector similarities from large to small or from small to large;
determining the vector similarity ordered at the middle position as the vector similarity of the middle numerical value;
if the vector similarity at the middle position is two, and if the two vector similarities at the middle position have the same value, determining the vector similarity as the vector similarity of the middle data; if the two vector similarities at the middle position are different, one vector similarity is selected according to a preset rule, for example, one vector similarity is randomly selected as the vector similarity of the middle value.
The first predetermined ratio and the second predetermined ratio may be the same or different, for example, both the first predetermined ratio and the second predetermined ratio may be set to 1%.
After the cluster control equipment is subjected to DBSCAN algorithm clustering based on the feature vector, a convergence class forms K1The cluster center equipment is determined at the same time, and since the eigenvector is calculated for each cluster control equipment before, K is obtained and recorded1The feature vector of the cluster center device of each cluster is recorded as: { g1,g2,……gk1}。
Clustering the non-group control equipment by using the DBSCAN algorithm based on the characteristic vector, and forming K by using the convergence class2The cluster center equipment is determined at the same time, and K is obtained and recorded as the characteristic vector is calculated for each non-cluster control equipment before2The feature vector of the cluster center device of each cluster is recorded as: { h1,h2,……hk2}。
The group control equipment identification method based on the characteristic vector clustering can reduce the number of the characteristic vectors to be matched, thereby improving the efficiency of identifying the group control equipment.
At this point, the preliminary preparation work for identifying the device to be identified is completed, and the process for identifying the group control device is given below.
Referring to fig. 3, fig. 3 is a schematic flowchart of identifying group control devices in the embodiment of the present application. The method comprises the following specific steps:
The APP list stored on the device to be identified can be directly obtained, and the software system type of the device to be identified can also be determined:
if the device to be identified is an Android device, an APP list of the device can be obtained through a packageManager of the Android SDK;
if the device to be identified is an apple device, before the iOS11, we can use lsappapplicationworkspace to obtain the APP list, and for versions above the iOS11, we can check whether APP exists according to the BundleId to obtain the APP list.
In the embodiment of the present application, the feature weight of the APP may be stored in advance, that is, the feature weight of the APP is preset, the obtaining mode may be implemented by the APPs in the APP lists of the plurality of group control devices and the non-group control device serving as the sample, and the specific implementation manner may be as described above, but is not limited to the above implementation manner.
The stored preset APP may have a feature weight of: shell: 80 percent; WeChat: 85%, Paibao: 80% and 86% of a chain family; panning: 50 percent; beijing Dong: 70%, etc.
The feature weight of the APP which is not stored can be treated as 0, and the sample group control device and the non-group control device can be obtained again to obtain the feature weight of the APP.
Calculating a feature vector using feature weights of the APPs in the APP list, including:
performing One-Hot coding on the APP in the APP list to convert the APP into a character string; calculating a Hash value of a preset digit;
multiplying the characteristic weight of the APP by each digit in the Hash value to obtain a numerical value vector with the length being the preset digit;
adding corresponding bits of numerical vectors corresponding to the APPs in the APP list to obtain the numerical vectors with the lengths of preset bits corresponding to the APP list;
and setting each bit element in the numerical value vector with the length of a preset bit corresponding to the APP list according to a rule that the bit element is not less than 0 and is 1 and less than 0 and is 0 to obtain the feature vector of the preset bit.
The method can be realized through the execution of the steps at each time in specific implementation, and the implementation mode can be packaged into a transcoding model file, and when the APP in an APP list is obtained, the transcoding model file is called to directly obtain the corresponding feature vector.
In specific implementation, the feature vectors with identification devices are respectively matched with K1Feature vector g of individual cluster center equipment1,g2,……gk1K is calculated1Vector similarity of K1One minimum value of the vector similarity is selected and recorded as d 1.
In a specific implementation, the calculation method in step 304 may also be packaged as a first distance model file, and when the feature vector of the device to be identified is obtained, the first distance model file is called to directly obtain the minimum value d 1.
In specific implementation, the feature vectors with identification devices are respectively matched with K2Features of individual cluster central facilitiesVector { h1,h2,……hk2K is calculated2Vector similarity of K2One minimum value of the vector similarity is selected and recorded as d 2.
In a specific implementation, the calculation method in step 305 may also be packaged as a second distance model file, and when the feature vector of the device to be recognized is obtained, the second distance model file is called to directly obtain the minimum value d 2.
The steps 304 and 305 may be executed in no order or in parallel.
And step 306, determining the probability that the device to be identified is a group control device by using d1 and d 2.
Determining the probability that the device to be identified is the group control device in the step includes:
calculating the sum of d1 and d 2; i.e., d1+ d2
Calculating the ratio of d2 to the sum; i.e., d2/(d1+ d2)
And determining the ratio as the probability that the equipment to be identified is the group control equipment.
During specific implementation, the implementation processes from step 303 to step 306 can be encapsulated into an identification group control device model file, the characteristic weight of the APP in the APP list of the device to be identified is obtained, the identification group control device model file is called, and the probability that the device to be identified is the group control device is directly obtained;
the implementation processes from step 302 to step 306 may also be encapsulated as an identification group control device model file, the APP of the device to be identified is obtained, the identification group control device model file is called, and the probability that the device to be identified is the group control device is directly obtained.
In summary, the probability that the device to be identified is the group control device is determined by determining the distance between the device to be identified and the feature vector of the cluster center device of the cluster formed by clustering based on the feature vector clustering. The scheme can improve the efficiency and accuracy of identifying the group control equipment.
Based on the same inventive concept, the embodiment of the application provides a group control equipment identification device. Referring to fig. 4, fig. 4 is a schematic structural diagram of an apparatus applied to the above technology in the embodiment of the present application. The device comprises: a storage unit 401, a first acquisition unit 402, a first determination unit 403, a calculation unit 404, a second acquisition unit 405, and a second determination unit 406;
the storage unit 401 is configured to store feature weights of preset APPs, feature vectors of cluster center devices of a plurality of preset cluster control device clusters, and feature vectors of cluster center devices of a plurality of preset non-cluster control device clusters;
a first obtaining unit 402, configured to obtain an APP list of a device to be identified;
a first determining unit 403, configured to determine, according to the feature weight of the preset APP stored in the storage unit 401, the feature weight of the APP in the APP list acquired by the first acquiring unit 402;
a calculating unit 404, configured to calculate a feature vector of the device to be identified using the feature weights of the APPs in the APP list determined by the first determining unit 403;
a second obtaining unit 405, configured to obtain a minimum value d1 in vector similarities between the feature vector of the device to be identified, which is calculated by the calculating unit 404, and the feature vectors of the cluster center devices of the multiple preset cluster control device clusters, which are stored in the storage unit 401; acquiring a minimum value d2 in the vector similarity between the feature vector of the device to be identified calculated by the calculating unit 404 and the feature vectors of the cluster center devices of the plurality of preset non-cluster-control device clusters stored in the storage unit 401;
a second determining unit 406, configured to determine the probability that the device to be identified is a group control device using d1 and d2 acquired by the second acquiring unit 405.
Preferably, the first and second electrodes are formed of a metal,
a first obtaining unit 402, further configured to obtain APP lists of a plurality of group control devices and APP lists of a plurality of non-group control devices;
a first determining unit 403, further configured to determine a feature weight of an APP according to APPs in APP lists of a plurality of group control devices and a plurality of non-group control devices;
a calculating unit 404, configured to calculate a feature vector of the group control device using a feature weight of an APP in an APP list of the group control device; calculating a feature vector of the non-group control equipment by using the feature weight of the APP in the APP list of the non-group control equipment;
the storage unit 401 is further configured to cluster the group control devices based on the feature vectors, and obtain and store feature vectors of cluster center devices of a preset group control device cluster formed by clustering; and clustering the non-group control equipment based on the characteristic vector, and acquiring and storing the characteristic vector of cluster center equipment of a preset non-group control equipment cluster formed by clustering.
Preferably, the first and second electrodes are formed of a metal,
the storage unit 401 is specifically configured to perform clustering by using a DBSCAN algorithm during clustering;
when clustering is conducted on the group control equipment, the distance threshold parameter is set to be the vector similarity of a middle value in the vector similarities between every two group control equipment, and the minimum cluster sample threshold is set to be a first preset ratio of the total number of the group control equipment;
when non-group control equipment is clustered, the distance threshold parameter is set to be the vector similarity of a middle value in the vector similarities between every two non-group control equipment, and the minimum cluster sample threshold is set to be a second preset ratio of the total number of the non-group control equipment; the first preset ratio and the second preset ratio are the same or different.
The first determining unit 403 is specifically configured to determine a first distribution frequency of the group control device in the group control device and the non-group control device; determining a second distribution frequency of the APP in the group control equipment and the non-group control equipment; calculating an absolute value of a difference between the first distributed frequency and the second distributed frequency; calculating a difference between 1 and an absolute value of the difference; determining the difference between 1 and the absolute value of the difference as the characteristic weight of the APP.
Preferably, the first and second electrodes are formed of a metal,
the calculating unit 404 is specifically configured to calculate the feature vector by using the feature weights of the APPs in the APP list, and includes:
coding and converting the APP in the APP list into a character string; calculating a Hash value of a preset digit;
multiplying the characteristic weight of the APP by each digit in the Hash value to obtain a numerical value vector with the length being the preset digit;
adding corresponding bits of numerical vectors corresponding to the APPs in the APP list to obtain the numerical vectors with the lengths of preset bits corresponding to the APP list;
and setting each bit element in the numerical value vector with the length of a preset bit corresponding to the APP list according to a rule that the bit element is not less than 0 and is 1 and less than 0 and is 0 to obtain the feature vector of the preset bit.
Preferably, the first and second electrodes are formed of a metal,
the second determining unit 406, when specifically determining the probability that the device to be identified is the group control device by using d1 and d2, includes:
calculating the sum of d1 and d 2;
calculating the ratio of d2 to the sum;
and determining the ratio as the probability that the equipment to be identified is the group control equipment.
The units of the above embodiments may be integrated into one body, or may be separately deployed; may be combined into one unit or further divided into a plurality of sub-units.
In another embodiment, an electronic device is further provided, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the group control device identification method when executing the program.
In another embodiment, a computer readable storage medium is also provided, having stored thereon computer instructions, which when executed by a processor, may implement the steps in the group control device identification method.
Fig. 5 is a schematic physical structure diagram of an electronic device according to an embodiment of the present invention. As shown in fig. 5, the electronic device may include: a Processor (Processor)510, a communication Interface (Communications Interface)520, a Memory (Memory)530 and a communication bus 540, wherein the Processor 510, the communication Interface 520 and the Memory 530 communicate with each other via the communication bus 540. Processor 510 may call logic instructions in memory 530 to perform the following method:
acquiring an APP list of equipment to be identified;
determining the characteristic weight of the APP in the APP list according to the characteristic weight of a preset APP;
calculating a feature vector of the equipment to be identified by using the feature weight of the APP in the APP list;
acquiring a minimum value d1 in the vector similarity between the feature vector of the equipment to be identified and the feature vectors of cluster center equipment of a plurality of preset cluster control equipment clusters;
acquiring a minimum value d2 in the vector similarity between the feature vector of the device to be identified and the feature vectors of cluster center devices of a plurality of preset non-cluster control device clusters;
determining the probability that the device to be identified is a group control device using d1 and d 2.
Furthermore, the logic instructions in the memory 530 may be implemented in the form of software functional units and stored in a computer readable storage medium when the software functional units are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (10)
1. A group control device identification method, the method comprising:
acquiring an application program APP list of equipment to be identified;
determining the characteristic weight of the APP in the APP list according to the characteristic weight of a preset APP;
calculating a feature vector of the equipment to be identified by using the feature weight of the APP in the APP list;
acquiring a minimum value d1 in the vector similarity between the feature vector of the equipment to be identified and the feature vectors of cluster center equipment of a plurality of preset cluster control equipment clusters;
acquiring a minimum value d2 in the vector similarity between the feature vector of the device to be identified and the feature vectors of cluster center devices of a plurality of preset non-cluster control device clusters;
determining the probability that the device to be identified is a group control device using d1 and d 2.
2. The method according to claim 1, wherein obtaining the eigenvector of the cluster center device of the preset cluster control device cluster and the eigenvector of the cluster center device of the preset non-cluster control device cluster comprises:
acquiring APP lists of a plurality of group control devices and APP lists of a plurality of non-group control devices;
determining the characteristic weight of the APP according to the APPs in the APP lists of the plurality of group control devices and the plurality of non-group control devices;
calculating a feature vector of the group control equipment by using the feature weight of the APP in the APP list of the group control equipment; clustering the cluster control equipment based on the characteristic vector to obtain a characteristic vector of cluster center equipment of a preset cluster control equipment cluster formed by clustering;
calculating a feature vector of the non-group control equipment by using the feature weight of the APP in the APP list of the non-group control equipment; and clustering the non-group control equipment based on the characteristic vector, and acquiring the characteristic vector of cluster center equipment of a preset non-group control equipment cluster formed by clustering.
3. The method of claim 2,
clustering by using a DBSCAN algorithm during clustering;
when clustering is conducted on the group control equipment, the distance threshold parameter is set to be the vector similarity of a middle value in the vector similarities between every two group control equipment, and the minimum cluster sample threshold is set to be a first preset ratio of the total number of the group control equipment;
when non-group control equipment is clustered, the distance threshold parameter is set to be the vector similarity of a middle value in the vector similarities between every two non-group control equipment, and the minimum cluster sample threshold is set to be a second preset ratio of the total number of the non-group control equipment; the first preset ratio and the second preset ratio are the same or different.
4. The method of claim 2, wherein the determining the feature weight of the APP according to the APPs in the APP lists of the plurality of group control devices and the plurality of non-group control devices comprises:
determining a first distribution frequency of the group control equipment in the group control equipment and the non-group control equipment;
determining a second distribution frequency of the APP in the group control equipment and the non-group control equipment;
calculating an absolute value of a difference between the first distributed frequency and the second distributed frequency;
calculating a difference between 1 and an absolute value of the difference;
determining the difference between 1 and the absolute value of the difference as the characteristic weight of the APP.
5. The method of claim 2, wherein computing the feature vector using the feature weights of the APPs in the APP list comprises:
coding and converting the APP in the APP list into a character string; calculating a Hash value of a preset digit;
multiplying the characteristic weight of the APP by each digit in the Hash value to obtain a numerical value vector with the length being the preset digit;
adding corresponding bits of numerical vectors corresponding to the APPs in the APP list to obtain the numerical vectors with the lengths of preset bits corresponding to the APP list;
and setting each bit element in the numerical value vector with the length of a preset bit corresponding to the APP list according to a rule that the bit element is not less than 0 and is 1 and less than 0 and is 0 to obtain the feature vector of the preset bit.
6. The method according to any one of claims 1-5, wherein the determining the probability that the device to be identified is a group control device using d1 and d2 comprises:
calculating the sum of d1 and d 2;
calculating the ratio of d2 to the sum;
and determining the ratio as the probability that the equipment to be identified is the group control equipment.
7. A group control device identification apparatus, the apparatus comprising: the device comprises a storage unit, a first acquisition unit, a first determination unit, a calculation unit, a second acquisition unit and a second determination unit;
the storage unit is used for storing the feature weight of a preset application program APP, the feature vectors of cluster center equipment of a plurality of preset cluster control equipment clusters and the feature vectors of cluster center equipment of a plurality of preset non-cluster control equipment clusters;
the first obtaining unit is used for obtaining an APP list of equipment to be identified;
the first determining unit is configured to determine, according to the feature weight of a preset APP stored in the storage unit, the feature weight of an APP in the APP list acquired by the first acquiring unit;
the calculating unit is used for calculating a feature vector of the equipment to be identified by using the feature weight of the APP in the APP list determined by the first determining unit;
the second obtaining unit is configured to obtain a minimum value d1 in vector similarities between the feature vector of the device to be identified, which is calculated by the calculating unit, and the feature vectors of the cluster center devices of the plurality of preset cluster control device clusters, which are stored in the storage unit; acquiring a minimum value d2 in the vector similarity between the feature vector of the device to be identified calculated by the calculating unit and the feature vectors of the cluster center devices of the plurality of preset non-cluster control device clusters stored by the storage unit;
the second determining unit is configured to determine the probability that the device to be identified is a group control device by using the d1 and the d2 acquired by the second acquiring unit.
8. The apparatus of claim 7,
the first obtaining unit is further configured to obtain APP lists of a plurality of group control devices and APP lists of a plurality of non-group control devices;
the first determining unit is further configured to determine a feature weight of an APP according to APPs in APP lists of a plurality of group control devices and a plurality of non-group control devices;
the computing unit is further configured to compute a feature vector of the group control device by using the feature weight of the APP in the APP list of the group control device;
the storage unit is further configured to cluster the group control equipment based on the feature vector, obtain and store a feature vector of cluster center equipment of a preset group control equipment cluster formed by clustering; calculating a feature vector of the non-group control equipment by using the feature weight of the APP in the APP list of the non-group control equipment; and clustering the non-group control equipment based on the characteristic vector, and acquiring and storing the characteristic vector of cluster center equipment of a preset non-group control equipment cluster formed by clustering.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method according to any of claims 1-6 when executing the program.
10. A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, is adapted to carry out the method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010047179.1A CN111260220B (en) | 2020-01-16 | 2020-01-16 | Group control equipment identification method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010047179.1A CN111260220B (en) | 2020-01-16 | 2020-01-16 | Group control equipment identification method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111260220A true CN111260220A (en) | 2020-06-09 |
| CN111260220B CN111260220B (en) | 2021-05-14 |
Family
ID=70950594
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010047179.1A Active CN111260220B (en) | 2020-01-16 | 2020-01-16 | Group control equipment identification method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111260220B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111915378A (en) * | 2020-08-17 | 2020-11-10 | 深圳墨世科技有限公司 | User attribute prediction method, device, computer equipment and storage medium |
| CN112926045A (en) * | 2021-02-24 | 2021-06-08 | 北京通付盾人工智能技术有限公司 | Group control equipment identification method based on logistic regression model |
| CN113449309A (en) * | 2021-06-28 | 2021-09-28 | 平安银行股份有限公司 | Terminal security state identification method, device, equipment and medium |
| CN117478685A (en) * | 2023-12-28 | 2024-01-30 | 中移(苏州)软件技术有限公司 | Group control device identification method, device, equipment and readable storage medium |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106295671A (en) * | 2015-06-11 | 2017-01-04 | 深圳市腾讯计算机系统有限公司 | A kind of list of application clustering method, device and the equipment of calculating |
| CN106934627A (en) * | 2015-12-28 | 2017-07-07 | 中国移动通信集团公司 | The detection method and device of a kind of electric business industry cheating |
| CN106940705A (en) * | 2016-12-20 | 2017-07-11 | 上海掌门科技有限公司 | A kind of method and apparatus for being used to build user's portrait |
| US20170372398A1 (en) * | 2016-06-24 | 2017-12-28 | Ebay Inc. | Vector representation of descriptions and queries |
| CN107622197A (en) * | 2016-07-15 | 2018-01-23 | 阿里巴巴集团控股有限公司 | Device identification method and device, weighing computation method and device for equipment identification |
| CN108763420A (en) * | 2018-05-24 | 2018-11-06 | 广州视源电子科技股份有限公司 | Sorting technique, device, terminal and the computer readable storage medium of data object |
| CN108959869A (en) * | 2018-07-03 | 2018-12-07 | 北京润信恒达科技有限公司 | A kind of recognition methods of natural person operation and device |
| CN109284380A (en) * | 2018-09-25 | 2019-01-29 | 平安科技（深圳）有限公司 | Illegal user's recognition methods and device, electronic equipment based on big data analysis |
| CN109657107A (en) * | 2018-11-02 | 2019-04-19 | 同盾控股有限公司 | A kind of Terminal-Matching and device based on third-party application |
| CN110210883A (en) * | 2018-05-09 | 2019-09-06 | 腾讯科技（深圳）有限公司 | The recognition methods of team control account, device, server and storage medium |
| CN110544109A (en) * | 2019-07-25 | 2019-12-06 | 深圳壹账通智能科技有限公司 | user portrait generation method and device, computer equipment and storage medium |
-
2020
- 2020-01-16 CN CN202010047179.1A patent/CN111260220B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106295671A (en) * | 2015-06-11 | 2017-01-04 | 深圳市腾讯计算机系统有限公司 | A kind of list of application clustering method, device and the equipment of calculating |
| CN106934627A (en) * | 2015-12-28 | 2017-07-07 | 中国移动通信集团公司 | The detection method and device of a kind of electric business industry cheating |
| US20170372398A1 (en) * | 2016-06-24 | 2017-12-28 | Ebay Inc. | Vector representation of descriptions and queries |
| CN107622197A (en) * | 2016-07-15 | 2018-01-23 | 阿里巴巴集团控股有限公司 | Device identification method and device, weighing computation method and device for equipment identification |
| CN106940705A (en) * | 2016-12-20 | 2017-07-11 | 上海掌门科技有限公司 | A kind of method and apparatus for being used to build user's portrait |
| CN110210883A (en) * | 2018-05-09 | 2019-09-06 | 腾讯科技（深圳）有限公司 | The recognition methods of team control account, device, server and storage medium |
| CN108763420A (en) * | 2018-05-24 | 2018-11-06 | 广州视源电子科技股份有限公司 | Sorting technique, device, terminal and the computer readable storage medium of data object |
| CN108959869A (en) * | 2018-07-03 | 2018-12-07 | 北京润信恒达科技有限公司 | A kind of recognition methods of natural person operation and device |
| CN109284380A (en) * | 2018-09-25 | 2019-01-29 | 平安科技（深圳）有限公司 | Illegal user's recognition methods and device, electronic equipment based on big data analysis |
| CN109657107A (en) * | 2018-11-02 | 2019-04-19 | 同盾控股有限公司 | A kind of Terminal-Matching and device based on third-party application |
| CN110544109A (en) * | 2019-07-25 | 2019-12-06 | 深圳壹账通智能科技有限公司 | user portrait generation method and device, computer equipment and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| HOWARD,JP 等: ""Cardiac Rhythm Device Identification Using Neural Networks"", 《JACC-CLINICAL ELECTROPHYSIOLOGY》 * |
| 辛永: ""基于条件随机场的设备主体名称识别"", 《第二届智能电网会议论文集》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111915378A (en) * | 2020-08-17 | 2020-11-10 | 深圳墨世科技有限公司 | User attribute prediction method, device, computer equipment and storage medium |
| CN112926045A (en) * | 2021-02-24 | 2021-06-08 | 北京通付盾人工智能技术有限公司 | Group control equipment identification method based on logistic regression model |
| CN112926045B (en) * | 2021-02-24 | 2023-12-26 | 北京通付盾人工智能技术有限公司 | Group control equipment identification method based on logistic regression model |
| CN113449309A (en) * | 2021-06-28 | 2021-09-28 | 平安银行股份有限公司 | Terminal security state identification method, device, equipment and medium |
| CN113449309B (en) * | 2021-06-28 | 2023-10-27 | 平安银行股份有限公司 | Terminal security state identification method, device, equipment and medium |
| CN117478685A (en) * | 2023-12-28 | 2024-01-30 | 中移(苏州)软件技术有限公司 | Group control device identification method, device, equipment and readable storage medium |
| CN117478685B (en) * | 2023-12-28 | 2024-04-09 | 中移(苏州)软件技术有限公司 | Group control device identification method, device, equipment and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111260220B (en) | 2021-05-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111260220B (en) | Group control equipment identification method and device, electronic equipment and storage medium | |
| CN107066616B (en) | Account processing method and device and electronic equipment | |
| US10796244B2 (en) | Method and apparatus for labeling training samples | |
| CN107423613B (en) | Method and device for determining device fingerprint according to similarity and server | |
| CN108399180B (en) | Knowledge graph construction method and device and server | |
| CN110705585A (en) | Network fraud identification method and device, computer device and storage medium | |
| CN111461164B (en) | Sample data set capacity expansion method and model training method | |
| CN106203103B (en) | File virus detection method and device | |
| CN109325118B (en) | Unbalanced sample data preprocessing method and device and computer equipment | |
| CN110288085B (en) | Data processing method, device and system and storage medium | |
| CN111090807A (en) | Knowledge graph-based user identification method and device | |
| CN115830649A (en) | Network asset fingerprint feature identification method and device and electronic equipment | |
| CN116049412B (en) | Text classification method, model training method, device and electronic equipment | |
| CN109783805B (en) | Network community user identification method and device and readable storage medium | |
| CN115965058B (en) | Neural network training method, entity information classification method, device and storage medium | |
| CN115174250B (en) | Network asset security assessment method and device, electronic equipment and storage medium | |
| CN114861746A (en) | Anti-fraud identification method and device based on big data and related equipment | |
| CN110162957B (en) | Authentication method and device for intelligent equipment, storage medium and electronic device | |
| CN115130536A (en) | Training method of feature extraction model, data processing method, device and equipment | |
| CN117390480A (en) | Information extraction method, device, equipment and storage medium | |
| CN112631945A (en) | Test case generation method and device and storage medium | |
| CN110071845B (en) | Method and device for classifying unknown applications | |
| CN111767419A (en) | Picture searching method, device, equipment and computer readable storage medium | |
| CN112149121A (en) | Malicious file identification method, device, equipment and storage medium | |
| CN116366603A (en) | Method and device for determining active IPv6 address |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200720 Address after: 100085 Floor 102-1, Building No. 35, West Second Banner Road, Haidian District, Beijing Applicant after: Seashell Housing (Beijing) Technology Co.,Ltd. Address before: 300 280 Tianjin Economic and Technological Development Zone Nangang Industrial Zone Office Building C Block 1, Room 112, Unit 05 Applicant before: BEIKE TECHNOLOGY Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20210309 Address after: 101309 room 24, 62 Farm Road, Erjie village, Yangzhen, Shunyi District, Beijing Applicant after: Beijing fangjianghu Technology Co.,Ltd. Address before: 100085 Floor 101 102-1, No. 35 Building, No. 2 Hospital, Xierqi West Road, Haidian District, Beijing Applicant before: Seashell Housing (Beijing) Technology Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |