CN114398521A - Device type determining method and data processing system for acquiring abnormal device - Google Patents
Device type determining method and data processing system for acquiring abnormal device Download PDFInfo
- Publication number
- CN114398521A CN114398521A CN202210167259.XA CN202210167259A CN114398521A CN 114398521 A CN114398521 A CN 114398521A CN 202210167259 A CN202210167259 A CN 202210167259A CN 114398521 A CN114398521 A CN 114398521A
- Authority
- CN
- China
- Prior art keywords
- equipment
- information
- tested
- target
- type
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/90335—Query processing
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Debugging And Monitoring (AREA)
Abstract
The invention provides a device type determining method and a data processing system for acquiring abnormal devices, wherein the method comprises the following steps: acquiring the association degree based on the first characteristic information of the equipment to be tested and the preset second characteristic information; sending equipment type detection information to the equipment to be detected based on the association degree and a preset association degree threshold value so that the equipment to be detected can generate real-time feedback information based on the equipment type detection information; if the real-time feedback information is matched with preset feedback information corresponding to the target equipment type, the equipment type of the equipment to be tested is determined to be the target equipment type, meanwhile, the equipment abnormality degree is obtained through user drawing information and APP information, the user and the equipment are tightly combined, the accurate equipment abnormality degree is obtained, the abnormality of the user is determined through the abnormality of the equipment, the accuracy of judging the real performance capability of the distinguishing information of the equipment user to be tested is further improved, and the safety of the equipment to be tested is effectively improved.
Description
[ technical field ] A method for producing a semiconductor device
The present invention relates to the field of information processing technologies, and in particular, to a device type determination method and a data processing system for acquiring an abnormal device.
[ background of the invention ]
With the development of science and technology, the amount of information contacted by people is increased explosively, and under specific conditions, people can hardly distinguish certain information to be real and reliable. In this regard, the related art proposes that it is possible to determine whether or not the user of the apparatus has the capability of distinguishing the authenticity of the information through the user image of the apparatus, and, taking the age of the user as an example, it is possible to assume that the user under the age of 50 has the capability of distinguishing the authenticity of the information.
However, the division method is too simple and rough, the reliability of the obtained result is very low, and misjudgment is easy to occur, so that negative effects are brought to the equipment user.
Therefore, how to accurately judge whether the device user has the capability of distinguishing the authenticity of the information becomes a technical problem to be solved urgently at present.
[ summary of the invention ]
The embodiment of the invention provides a device type determining method and a data processing system for acquiring abnormal devices, and aims to solve the technical problem that the reliability of a mode for judging whether a device user has the capability of distinguishing the authenticity of information is too low in the related technology.
In a first aspect, an embodiment of the present invention provides a device type determining method, including: determining the association degree of the device to be tested and the type of the target device based on first characteristic information and predetermined second characteristic information of the device to be tested, wherein the first characteristic information is used for representing the characteristic distribution condition of a user of the device to be tested on a plurality of characteristic dimensions, and the second characteristic information is used for representing the characteristic distribution condition of the user of the target device under the type of the target device on the plurality of characteristic dimensions; when the association degree is greater than or equal to a preset association degree threshold value, sending equipment type detection information associated with the target equipment type to the equipment to be detected, so that the equipment to be detected can generate real-time feedback information based on the equipment type detection information; acquiring the real-time feedback information; and if the real-time feedback information is matched with the preset feedback information corresponding to the target equipment type, determining that the equipment type of the equipment to be tested is the target equipment type.
In a second aspect, an embodiment of the present invention provides a data processing system for acquiring an abnormal device based on a device type determination method, where the system includes: an initial device ID list, a processor and a memory storing a computer program that, when executed by the processor, performs the steps of:
s100, acquiring a key device list A from the initial device list1，A2，……，AmIn which AiThe method refers to the ith key equipment ID, wherein i is 1 … … m, and m is the number of key equipment;
s200, according to AiCorresponding to the first characteristic information, obtaining AiCorresponding list of specified characteristics Bi＝{Bi1，Bi2，……，BinIn which BijMeans AiThe corresponding j-th specified characteristic value, j is 1 … … n, and n is the characteristic value number;
s300, according to BiObtaining AiCorresponding degree of equipment abnormality FiWherein F isiThe following conditions are met:
Fi＝W1×Ki1+W2×Ki2+W3×Ki3。
s400, according to FiObtaining FiPriority T of corresponding key devicexWherein, TxMeans of [ Hx-1，Hx) Corresponding device priority.
According to the technical scheme, the accuracy of judging the real performance capability of the resolution information of the equipment user to be tested is improved, and the safety of the equipment to be tested is effectively improved;
meanwhile, the equipment abnormality degree is acquired through the user drawing information and the APP information, the user and the equipment are closely combined to acquire the accurate equipment abnormality degree, and the abnormality of the user is determined through the abnormality of the equipment.
[ description of the drawings ]
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 shows a flow diagram of a device type determination method according to an embodiment of the invention.
FIG. 2 illustrates a flow diagram of an executive of a data processing system that acquires an exception device according to one embodiment of the invention.
[ detailed description ] embodiments
For better understanding of the technical solutions of the present invention, the following detailed descriptions of the embodiments of the present invention are provided with reference to the accompanying drawings.
It should be understood that the described embodiments are only some embodiments of the invention, and not all 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.
The terminology used in the embodiments of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the examples of the present invention and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
Example one
Fig. 1 shows a flow diagram of a device type determination method according to an embodiment of the invention.
As shown in fig. 1, a flow of a device type determination method according to an embodiment of the present invention includes:
The device to be tested refers to a device used by a user who needs to judge whether the device to be tested has the capability of distinguishing the true information, the first feature information is used for representing the feature distribution situation of the user of the device to be tested on a plurality of feature dimensions, and the second feature information is used for representing the feature distribution situation of the user of the target device under the type of the target device on the plurality of feature dimensions.
The difference between the feature distribution situation of the user of the device to be tested in the multiple feature dimensions and the feature distribution situation of the user of the target device in the target device type in the multiple feature dimensions, that is, the difference between the user of the device to be tested and the user of the target device in the target device type, is smaller, the higher the similarity of behavior patterns between the user of the device to be tested and the user of the target device in the target device type is, the higher the possibility that the device to be tested belongs to the target device type is. Therefore, based on the first characteristic information of the device under test and the predetermined second characteristic information, the association degree of the device under test and the target device type can be determined, and the association degree reflects the possibility that the device under test belongs to the target device type.
The plurality of feature dimensions include, but are not limited to, one or more of device user identity information, device user account login status information, device user publication information, and device user behavior distribution information.
The device user identity information includes but is not limited to the gender, age, occupation, academic calendar, personal hobbies, and other profile information disclosed by the device user. The device user account login state information includes hardware/operating system level information of hardware devices depended by the user during login and basic information of the account during login, wherein the hardware/operating system level information includes but is not limited to electronic device models, system version numbers and the like, and the basic information of the account includes but is not limited to user agents, IP addresses and the like. The device user published information is content published by the device user, and includes, but is not limited to, text, image, audio, video, and any other type of multimedia information, such as a head portrait, a nickname, or a short video published by a social account. The device user behavior distribution information includes multiple interactive behaviors of the device user and the device and/or the APP in the device, and the occurrence time and times of each interactive behavior, which reflect the behavior pattern, behavior rule and the like of the device user.
The characteristic information of the multi-characteristic dimension can reflect the actual situation of the equipment more comprehensively, and is beneficial to having higher reliability when determining whether the equipment user has the capability of distinguishing the information truth or not according to the characteristic information of the equipment in the following.
And 104, when the association degree is greater than or equal to a preset association degree threshold value, sending device type detection information associated with the target device type to the device to be tested, so that the device to be tested generates real-time feedback information based on the device type detection information.
The predetermined association threshold is the lowest association with the target device type required when the device to be detected has the possibility of belonging to the target device type, therefore, detecting whether the association is greater than or equal to the predetermined association threshold can be used as the first detection, when the association is greater than or equal to the predetermined association threshold, the device to be detected is determined to have the possibility of belonging to the target device type, and then the step of sending the device type detection information associated with the target device type to the device to be detected is performed again.
And responding to the association degree larger than or equal to a preset association degree threshold value, starting to detect again, and specifically sending device type detection information associated with the target device type to the device to be detected. When the method is used for judging whether the equipment user has the actual scene of distinguishing the authenticity of the information, the equipment type can comprise a safety class corresponding to the authenticity of the information which can be distinguished by the equipment user and a non-safety class corresponding to the authenticity of the information which cannot be distinguished by the equipment user. Of course, the scenarios that can be used in the present invention include, but are not limited to, the above examples, and may be any practical scenarios that can be used to divide the device types according to any condition, which meets the actual needs.
The device type detection information is used for detecting whether the device type of the device to be detected is the target device type, the device type detection information includes, but is not limited to, any voice information, text information, video information, audio information, image information and the like which are borne in network communication, and the device to be detected has an information acquisition function of acquiring real-time feedback information aiming at the device type detection information while providing the device type detection information for the device to be detected.
The real-time feedback information is information generated by interaction between a user of the equipment to be tested and the equipment to be tested based on the equipment type detection information. For example, when the device type detection information is voice information in a voice call, the corresponding real-time feedback information is information collected by the device to be tested and generated by a user of the device to be tested making a response based on the voice information, where the response includes, but is not limited to, the voice information and information generated by performing any manual operation on the device to be tested. For another example, when the device type detection information is text information in an email, the corresponding real-time feedback information is information collected by the device under test and generated by a user of the device under test making a response based on the text information, where the response includes, but is not limited to, editing information of the text information, reply information of the email, and the like. Of course, the real-time feedback information includes, but is not limited to, the above examples, and may be any other information collected or generated by the device under test.
And 106, acquiring the real-time feedback information.
And step 108, if the real-time feedback information is matched with the preset feedback information corresponding to the target equipment type, determining that the equipment type of the equipment to be tested is the target equipment type.
And then, acquiring real-time feedback information provided by the equipment to be tested. The preset feedback information corresponding to the type of the target equipment is feedback information generated by the target equipment under the type of the target equipment aiming at equipment type detection information associated with the type of the target equipment, and if the real-time feedback information generated by the equipment to be tested is matched with the preset feedback information, the equipment to be tested is similar to or the same as the target equipment, so that the equipment to be tested can be determined to belong to the type of the target equipment.
When the method is used for judging whether the equipment user has the actual scene of distinguishing the authenticity of the information, the type of the target equipment can be set as an unsafe class corresponding to the authenticity of the information which cannot be distinguished by the equipment user, the equipment type detection information associated with the type of the target equipment is set as first voice information sent through voice communication, and the first voice information can be pseudo information with the authenticity of 0. Correspondingly, the real-time feedback information of the device to be tested is second voice information replied by the user of the device to be tested aiming at the first voice information, and the second voice information reflects the real-time reflection of the user of the device to be tested on the first voice information and is used as a basis for judging whether the user of the device to be tested recognizes that the first voice information is the pseudo information.
According to the technical scheme, the relevance between the equipment to be tested and the type of the target equipment and the real-time feedback information of the equipment to be tested aiming at the equipment type detection information relevant to the type of the target equipment are subjected to double detection, so that whether the equipment to be tested belongs to the type of the target equipment or not is automatically and accurately identified, the accuracy of judging the real performance capability of the distinguishing information of the equipment to be tested user can be increased in the actual scene of judging whether the equipment to be tested user has the real performance capability of distinguishing information or not, the safety of the equipment to be tested is effectively improved, the parallel automatic detection of a large number of equipment to be tested is possible, the efficiency of judging the real performance capability of the distinguishing information of the equipment to be tested user is improved, and the time cost and the labor cost are saved.
Example two
On the basis of the first embodiment, a flow of the device type determination method according to another embodiment of the present invention includes:
step 202, determining the association degree between the device to be tested and the type of the target device based on the feature value of the user of the device to be tested in each of the multiple feature dimensions and the feature value or the feature value range of the user of the target device in the type of the target device in each of the multiple feature dimensions.
And 204, when the association degree is greater than or equal to a preset association degree threshold, sending device type detection information associated with the target device type to the device to be tested, so that the device to be tested generates real-time feedback information based on the device type detection information.
And step 206, acquiring the real-time feedback information.
And 208, if the real-time feedback information is matched with the preset feedback information corresponding to the target equipment type, determining that the equipment type of the equipment to be tested is the target equipment type.
At this time, the first feature information is a feature value of a user of the device to be tested in each of the plurality of feature dimensions, and the second feature information is a feature value or a feature value range of a user of the target device in the target device type in each of the plurality of feature dimensions.
The characteristic value of the user of the equipment to be tested in each dimension of the multiple characteristic dimensions reflects the characteristic level of the user of the equipment to be tested in each characteristic dimension, the characteristic value or the characteristic value range of the user of the target equipment in the type of the target equipment in each dimension of the multiple characteristic dimensions reflects the characteristic level of the user of the target equipment in the type of the target equipment in each characteristic dimension, and the characteristic value or the characteristic value range is embodied in a characteristic value/characteristic value range mode, so that the association degree of the equipment to be tested and the type of the target equipment can be conveniently calculated.
When calculating the association degree between the device to be tested and the target device type, first, a first parameter needs to be determined.
In one possible implementation, the determining the first parameter includes: and under each characteristic dimension in the plurality of characteristic dimensions, determining a first parameter corresponding to the characteristic dimension based on the characteristic value of the user of the target equipment under the type of the target equipment and the characteristic value of the user of the equipment to be tested.
The ratio of the characteristic value of the user of the target device under the target device type to the characteristic value of the user of the device to be tested can be determined as the first parameter corresponding to the characteristic dimension, and the closer the ratio is to 1, the closer the behavior patterns of the user of the device to be tested and the user of the target device under the target device type are.
In another possible implementation manner, the determining the first parameter includes: and under each characteristic dimension in the plurality of characteristic dimensions, determining a first parameter corresponding to the characteristic dimension based on an upper limit value, a lower limit value or a median of a characteristic value range of a user of the target equipment under the type of the target equipment and the characteristic value of the user of the equipment to be tested.
Since target devices of various types are provided, and the characteristic values of a large number of target devices in any characteristic dimension may not be completely the same, in order to accurately and reliably indicate the characteristic level of the user of the target device type, the characteristic value range corresponding to the target device type may be determined based on the respective characteristic values of the users of the large number of target devices provided in the target device type. In a feature dimension, the closer the ratio of the feature value of the user of the device under test to the upper limit value, the lower limit value or the median of the range of the feature value of the user of the target device under the target device type is to 1, the closer the behavior patterns of the user of the device under test and the user of the target device under the target device type are.
Of course, the manner of determining the first parameter is not limited to the manner of solving the ratio, and any calculation manner may be used to process the characteristic value data related to the user of the target device and the user of the device under test in the type of the target device, so as to determine the processing result as the first parameter.
Next, the association degree between the device to be tested and the type of the target device is determined based on the first parameter.
In a possible implementation manner, an average value of the first parameters corresponding to each of the plurality of feature dimensions may be determined as a degree of association between the device under test and the target device type.
The first parameter corresponding to one feature dimension reflects the degree of similarity of behavior patterns between the user of the device to be tested in the feature dimension and the user of the target device in the target device type, and then the minimum value of the first parameters corresponding to a plurality of feature dimensions reflects the degree of similarity of behavior patterns between the user of the device to be tested and the user of the target device in the target device type under the comprehensive action of the plurality of feature dimensions, and the higher the degree of similarity is, the higher the possibility that the device to be tested belongs to the target device type is. Therefore, the similarity reflects the relevance of the device to be tested and the type of the target device under the comprehensive action of a plurality of characteristic dimensions.
Due to unpredictability of behavior habits of users of the equipment to be detected, the users of the equipment to be detected may not have commonality with users of all equipment types in some characteristic dimensions, and thus, such characteristic dimensions have no reference significance for detecting whether the equipment to be detected belongs to the target equipment type, and even interfere with a result of detecting whether the equipment to be detected belongs to the target equipment type. In order to avoid the negative influence caused by the characteristic dimensions, a designated parameter threshold value can be set, and the designated parameter threshold value is used for reflecting the lowest ratio of the characteristic value corresponding to each characteristic dimension and the characteristic value of the equipment user under the equipment type when the user of the equipment to be tested shares at least with the equipment user under the equipment type.
That is, the first parameter of the device under test in one feature dimension can be used as a basis for detecting whether the device under test belongs to the target device type only when the first parameter is greater than or equal to the specified parameter threshold. Therefore, in another possible implementation manner, several target first parameters greater than or equal to a specified parameter threshold may be determined in the first parameters corresponding to each of the plurality of feature dimensions. And then determining the association degree of the equipment to be tested and the type of the target equipment based on the specified fault tolerance coefficient and the variance of the plurality of target first parameters.
For example, the difference between the variance of the target first parameters and the specified fault-tolerant coefficient may be set as the association degree between the device to be tested and the target device type, or the product of the variance of the target first parameters and the specified fault-tolerant coefficient may be set as the association degree between the device to be tested and the target device type.
The variance shows the data distribution of the first parameters of the targets, and reflects the similarity level between the user of the device under test and the user of the target device under the target device type in multiple feature dimensions. And the appointed fault-tolerant coefficient is used for reflecting the actual association degree of the equipment to be tested and the type of the target equipment and the deviation level of the variance, the variance is processed through the appointed fault-tolerant coefficient, and the difference between the processing result and the actual association degree is greatly reduced relative to the difference between the variance and the actual association degree, so that the more accurate and reliable association degree between the equipment to be tested and the type of the target equipment is obtained.
According to the technical scheme, the characteristic values under the characteristic dimensions are used as the image data of the user of the equipment to be tested, the association degree which really reflects the possibility that the equipment to be tested belongs to the type of the target equipment can be efficiently and accurately calculated, and the accuracy of judging the real performance capability of the resolution information of the user of the equipment to be tested can be increased in the actual scene of judging whether the user of the equipment to be tested has the real performance capability of the resolution information and the like.
EXAMPLE III
On the basis of the first embodiment, a flow of the device type determination method according to still another embodiment of the present invention includes:
step 302, determining a first matrix based on the feature vectors corresponding to the user of the device under test in the plurality of feature dimensions, and determining a second matrix based on the feature vectors corresponding to the user of the target device under the target device type in the plurality of feature dimensions.
Step 304, determining the association degree between the device to be tested and the target device type based on the first matrix and the second matrix.
At this time, the first feature information is the feature vectors of the user of the device to be tested in the plurality of feature dimensions, and the second feature information is the feature vectors of the user of the target device in the target device type in the plurality of feature dimensions.
In the technical scheme, the characteristic vector of the user of the device to be tested in each characteristic dimension reflects the characteristic level of the user of the device to be tested in each characteristic dimension, and the first matrix formed by the vectors reflects the characteristic level of the user of the device to be tested under the comprehensive action of a plurality of characteristic dimensions. Similarly, the second matrix reflects the feature level of the user of the target device under the type of the target device under the comprehensive action of a plurality of feature dimensions.
In one possible design, the correlation between the device under test and the target device type may be determined by multiplying the first matrix and the second matrix.
In another possible design, a difference matrix obtained by subtracting the covariance matrix of the first matrix from the covariance matrix of the second matrix may be determined, and the rank of the difference matrix is determined as the degree of association between the device to be tested and the type of the target device.
According to the technical scheme, the matrix formed by the feature vectors of the multiple feature dimensions is used as the image data of the user of the equipment to be tested, the association degree which really reflects the possibility that the equipment to be tested belongs to the type of the target equipment can be efficiently and accurately calculated, and the accuracy of judging the real performance of the resolution information of the user of the equipment to be tested can be increased in the actual scene of judging whether the user of the equipment to be tested has the real performance of the resolution information and the like.
Step 306, when the association degree is greater than or equal to a predetermined association degree threshold, sending device type detection information associated with the target device type to the device to be tested, so that the device to be tested generates real-time feedback information based on the device type detection information.
And 308, acquiring the real-time feedback information.
Step 310, if the real-time feedback information matches with the predetermined feedback information corresponding to the target device type, determining that the device type of the device to be tested is the target device type.
On the basis of the first embodiment and the third embodiment, the method further comprises the following steps: second feature information is preset, and specifically, the second feature information is determined based on the first device set, the second device set and the feature extraction model.
Wherein the first sample set includes a plurality of target devices of which the device types are the target device types, and belongs to a positive input sample composed of target devices under the target device types. The second device set comprises a plurality of sample devices of unknown device types randomly selected in a predetermined device set, which sample devices do not have commonality common to target devices of the target device type and belong to negative input samples.
Further, the feature extraction model for characterizing the difference between the first sample set and the second sample set takes the first sample set as a positive input sample, takes the second sample set as a negative input sample, and outputs second feature information, where the second feature information reflects the feature distribution of the user of the target device under the target device type in the multiple feature dimensions. Therefore, the feature extraction model outputs the second feature information which truly and comprehensively reflects the commonality of the positive input sample after learning the positive input sample and the negative input sample through the difference between the positive input sample and the negative input sample characterized by the feature extraction model.
On the basis of the first embodiment and the third embodiment, the device type detection information associated with the target device type includes a plurality of pieces of sub information, where each piece of sub information is provided with a feedback information association identifier. The sending the device type detection information associated with the target device type to the device to be tested and the acquiring the real-time feedback information include: sending first sub information in the plurality of sub information to the equipment to be tested; and acquiring real-time feedback information of the equipment to be tested aiming at the first sub-information, and if the plurality of sub-information has second sub-information of which the feedback information association identification is matched with the real-time feedback information aiming at the first sub-information, sending the second sub-information to the equipment to be tested.
That is, a plurality of pieces of sub information having the feedback information association flag may be set in the device type detection information associated with the target device type, and only one piece of sub information may be transmitted each time device type detection information is transmitted to a device under test. Specifically, when the sub information is sent for the first time, one sub information may be randomly selected to be sent, one sub information meeting the classification requirement of the actual device may be selected from a plurality of sub information in combination with the actual scene to be sent, the predetermined sub information for the first sending may be preset, and when the sub information is sent for the first time, the predetermined sub information is sent to the device to be tested.
Correspondingly, when the device to be tested receives one piece of sub information, real-time feedback information corresponding to the sub information is generated through user operation of the device to be tested and the like, and the real-time feedback information is broadcasted so that a system for detecting whether the device to be tested belongs to the type of the target device can receive the real-time feedback information. Next, the next sub-information to be sent to the device under test is determined based on the real-time feedback information. Specifically, the sub-information whose feedback information association identifier matches the real-time feedback information can be searched for in the plurality of sub-information, and the matched sub-information is sent to the device to be tested as the next sub-information to be sent to the device to be tested.
And circulating the steps of sending the sub-information and obtaining the corresponding real-time feedback information until the feedback information associated identifications of the plurality of sub-information are not matched with the real-time feedback information obtained at the current time.
Therefore, multiple real-time feedback information provided by the equipment to be detected can be combined, corresponding sub-information is selected for multiple times to serve as information for detecting the type of the equipment to be detected, and the multiple real-time feedback information provided by the equipment to be detected reflects the behavior mode, the operation habit and the like of a user of the equipment to be detected.
In another specific embodiment, a data processing system for acquiring an abnormal device based on the device type determining method of the first embodiment is provided, where the system implements the device type determining method of the first embodiment except for executing a program, and the system includes: an initial device list, a processor and a memory storing a computer program which, when executed by the processor, performs the steps of:
s100, acquiring a key device list A from the initial device list1，A2，……，AmIn which AiThe ith key device ID is referred to, i is 1 … … m, and m is the number of key devices.
Specifically, the key device ID refers to a unique identity that characterizes a key device, where the key device is a device to be tested in an initial device list, and may be understood as: the initial equipment list comprises equipment to be tested, abnormal equipment and non-abnormal equipment, wherein the abnormal equipment refers to the electronic equipment which is determined to be applied by the abnormal user, and the non-abnormal equipment refers to the electronic equipment which is determined to be applied by the non-abnormal user.
Embodiments of the present invention exist in a variety of forms, including but not limited to:
(1) mobile communication devices, which are characterized by mobile communication capabilities and are primarily targeted at providing voice and data communications. Such terminals include smart phones (e.g., iphones), multimedia phones, functional phones, and low-end phones, among others.
(2) The ultra-mobile personal computer equipment belongs to the category of personal computers, has calculation and processing functions and generally has the characteristic of mobile internet access. Such terminals include PDA, MID, and UMPC devices, such as ipads.
(3) Portable entertainment devices such devices may display and play multimedia content. Such devices include audio and video players (e.g., ipods), handheld game consoles, electronic books, as well as smart toys and portable car navigation devices.
(4) The server is similar to a general computer architecture, but has higher requirements on processing capability, stability, reliability, safety, expandability, manageability and the like because of the need of providing highly reliable services.
(5) And other electronic devices with data interaction functions.
S200, according to AiCorresponding to the first characteristic information, obtaining AiCorresponding list of specified characteristics Bi＝{Bi1，Bi2，……，BinIn which BijMeans AiThe corresponding j-th specified characteristic value, j is 1 … … n, and n is the characteristic value number; the specified feature value may be obtained by feature extraction by any method known in the art by those skilled in the art, and is not described herein again.
Specifically, the first feature information includes: the system comprises APP information and user portrait information, wherein the APP information refers to APP installation amount, APP liveness and the like, and the user portrait information comprises age, gender, occupation and the like of a user.
S300, according to BiObtaining AiCorresponding degree of equipment abnormality FiWherein F isiThe following conditions are met:
Fi＝W1×Ki1+W2×Ki2+W3×Ki3。
preferably, W1＝W2＝W3＝1。
Specifically, in the step S300, the following step of obtaining K is further includedi1：
S301, obtaining AiCorresponding target APP List Ci＝{Ci1，Ci2，……，CipiIn which C isiqRefers to the priority of the qth target APP, q is 1 … … pi, pi refers to the AiThe number of target APPs in the corresponding target device.
Specifically, the target APP refers to an APP installed in a key device.
Specifically, the priority of the target APP is used for characterizing the degree of abnormality of the APP, i.e. the greater the degree of abnormality of the APP, the greater the risk of the APP is.
S303, according to CiqObtaining AiCorresponding target APP quantity list Di＝{Di1，Di2，……，DisIn which D isirThe number of APPs corresponding to the r-th preset APP priority is defined, r is 1 … … s, and s is a preset APP priority number in a preset APP priority list.
Specifically, the step of S303 further includes the step of acquiring Dir: traverse CiAnd when Ciq is equal to the r-th APP priority in the preset APP priority list, the initial APP quantity D corresponding to the r-th preset APP priority0Is added with 1 so as to obtain DirWherein D is0＝0。
Preferably, s is 4, which can be understood as: the preset APP priority list comprises a first preset APP priority, a second preset APP priority, a third preset APP priority and a fourth preset APP priority, wherein the first preset APP priority is greater than the second preset APP priority is greater than the third preset APP priority is greater than the fourth preset APP priority.
S305, based on DirObtaining Ki1Wherein, K isi1The following conditions are met:
Further, in the step S300, the following step of obtaining K is further includedi2：
Ki2The following conditions are met:
Preferably, the designated APP refers to an APP for communication.
Further, in the step S300, the following step of obtaining K is further includedi3：
Ki3The following conditions are met:
Preferentially, the specified feature refers to a feature in which an IV value is greater than or equal to a preset IV threshold in all features corresponding to any initial device in the initial device list, and a person skilled in the art knows that the IV value of the feature is obtained through an abnormal device and a non-abnormal device in the initial device list, which is not described herein again; accurate characteristics can be screened out, the problem that the acquired equipment abnormality degree is interfered due to more characteristics is avoided, and the accurate equipment abnormality degree cannot be acquired is solved.
S400, according to FiObtaining FiPriority T of corresponding key devicexWherein, TxMeans of [ Hx-1，Hx) Corresponding device priority.
Specifically, the step S400 further includes the steps of:
s401, obtaining a preset abnormal threshold list H { [ H ]1，H2)，[H2，H3)，……，[Hz-1，Hz]In which, [ H ]x-1，Hx) The number x is 2 … … z, and z is the number of preset abnormal threshold intervals.
Preferably, z is 4, i.e. H1＝100、H2＝130，H3＝200，H4＝300，H＝{[100，130)，[130，200)，[200，300]}。
S403, when FiIs at [ H ]x-1，Hx) When determining FiPriority T of corresponding key devicexWherein, TxMeans of [ Hx-1，Hx) Corresponding device priority.
Specifically, the step of S401 further comprises the step of obtaining [ Hx-1，Hx)：
S4011, acquiring an intermediate device list and a device abnormality degree corresponding to any device in the intermediate device list.
Specifically, the device abnormality degree in S4011 can be obtained by referring to S100 to S300, which is not described herein again.
S4013, traversing the intermediate device list and obtaining a first device ratio T1，T1The following conditions are met:
T1＝L1/L2，L1number of devices equal to abnormal device in the intermediate device list, L2Refers to the number of devices in the intermediate device list that are not equal to the anomalous device.
S4015, traversing the intermediate device list and obtaining a second device ratio T2，T2The following conditions are met:
T2＝L3x/L1，L3xfor the device abnormality degree in the intermediate device list to be in [ H ]x-1，Hx) Number of abnormal devices within.
S4017, traversing the intermediate device list and obtaining a third device ratio T3，T3The following conditions are met:
T3＝L3x/L4x，L4xfor the device abnormality degree in the intermediate device list to be in [ H ]x-1，Hx) The number of all devices in the system.
S4019, when T1Satisfies a predetermined first proportional threshold and T2Satisfies a predetermined second ratio threshold and T3When a preset third proportion threshold value is met, saving Hx-1，Hx) The change is not changed; otherwise, use
Substitution of [ Hx-1，Hx) Those skilled in the art will appreciate that the new preset anomaly threshold interval may be obtained by any method
For example, the preset abnormality threshold interval is subdivided.
Specifically, the steps S4011 to S4019 can determine an accurate abnormal threshold interval according to the ratio of the three dimensions, which is beneficial to accurately determining whether the key device is an abnormal device according to the degree of abnormality of the device, and avoiding omission of the abnormal device.
The embodiment provides a data processing system for acquiring abnormal equipment, which acquires the equipment abnormality degree through user drawing information and APP information, closely combines a user and the equipment to acquire accurate equipment abnormality degree, and determines the abnormality of the user through the abnormality of the equipment.
The technical scheme of the invention is described in detail in combination with the attached drawings, and by the technical scheme of the invention, the accuracy of judging the real performance capability of the resolution information of the equipment user to be tested is increased, and the safety of the equipment to be tested is effectively improved.
It should be understood that the term "and/or" as used herein is merely one type of association that describes an associated object, meaning that three relationships may exist, e.g., a and/or B may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship.
It should be understood that although the terms first, second, etc. may be used to describe the characteristic information in the embodiments of the present invention, the characteristic information should not be limited to these terms. These terms are only used to distinguish the characteristic information from each other. For example, the first characteristic information may also be referred to as second characteristic information, and similarly, the second characteristic information may also be referred to as first characteristic information, without departing from the scope of the embodiments of the present invention.
The word "if" as used herein may be interpreted as "at … …" or "when … …" or "in response to a determination" or "in response to a detection", depending on the context. Similarly, the phrases "if determined" or "if detected (a stated condition or event)" may be interpreted as "when determined" or "in response to a determination" or "when detected (a stated condition or event)" or "in response to a detection (a stated condition or event)", depending on the context.
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 method for device type determination, comprising:
determining the association degree of the device to be tested and the type of the target device based on the first characteristic information of the device to be tested and the predetermined second characteristic information,
the first feature information is used for representing feature distribution conditions of a user of the device to be tested on a plurality of feature dimensions, and the second feature information is used for representing feature distribution conditions of the user of the target device under the target device type on the plurality of feature dimensions;
when the association degree is greater than or equal to a preset association degree threshold value, sending equipment type detection information associated with the target equipment type to the equipment to be detected, so that the equipment to be detected can generate real-time feedback information based on the equipment type detection information;
acquiring the real-time feedback information;
and if the real-time feedback information is matched with the preset feedback information corresponding to the target equipment type, determining that the equipment type of the equipment to be tested is the target equipment type.
2. The device type determination method according to claim 1, wherein determining the association degree between the device to be tested and the target device type based on the first feature information of the device to be tested and the predetermined second feature information comprises:
and determining the association degree of the device to be tested and the type of the target device based on the characteristic value of the user of the device to be tested in each dimension of the plurality of characteristic dimensions and the characteristic value or the characteristic value range of the user of the target device in the type of the target device in each dimension of the plurality of characteristic dimensions.
3. The device type determination method according to claim 2, wherein determining the association degree between the device to be tested and the target device type based on the first feature information of the device to be tested and the predetermined second feature information comprises:
at each of the plurality of feature dimensions,
determining a first parameter corresponding to the feature dimension based on the feature value of the user of the target device under the type of the target device and the feature value of the user of the device to be tested, or
Determining a first parameter corresponding to the characteristic dimension based on an upper limit value, a lower limit value or a median value of a characteristic value range of a user of the target equipment under the type of the target equipment and a characteristic value of the user of the equipment to be tested;
determining the mean value of the first parameters corresponding to the feature dimensions as the association degree of the equipment to be tested and the type of the target equipment;
or
Determining a plurality of target first parameters which are greater than or equal to a specified parameter threshold value in the first parameters respectively corresponding to the plurality of characteristic dimensions;
and determining the association degree of the equipment to be tested and the type of the target equipment based on the specified fault-tolerant coefficient and the variance of the first parameters of the targets.
4. The device type determination method according to claim 1, wherein determining the association degree between the device to be tested and the target device type based on the first feature information of the device to be tested and the predetermined second feature information comprises:
determining a first matrix based on the feature vectors corresponding to the plurality of feature dimensions respectively by the user of the device to be tested;
determining a second matrix based on the feature vectors corresponding to the plurality of feature dimensions of the user of the target device under the type of the target device;
and determining the association degree of the equipment to be tested and the type of the target equipment based on the first matrix and the second matrix.
5. The device type determination method according to any one of claims 1 to 4, further comprising:
determining the second feature information based on the first set of devices, the second set of devices, and a feature extraction model, wherein,
the first sample set comprises a plurality of target devices with device types of the target devices, the second device set comprises a plurality of sample devices with unknown device types and randomly selected from a preset device set, and the feature extraction model takes the first sample set as a positive input sample, takes the second sample set as a negative input sample, and takes the second feature information as an output, so as to characterize the difference between the first sample set and the second sample set.
6. The device type determination method according to any one of claims 1 to 4, wherein the device type detection information associated with the target device type includes a plurality of pieces of sub information, wherein each piece of sub information is provided with a feedback information association identifier;
the sending the device type detection information associated with the target device type to the device to be tested and the acquiring the real-time feedback information include:
sending first sub information in the plurality of sub information to the equipment to be tested;
obtaining real-time feedback information of the equipment to be tested aiming at the first sub-information, and if the plurality of sub-information has second sub-information of which the feedback information association identification is matched with the real-time feedback information aiming at the first sub-information, sending the second sub-information to the equipment to be tested;
and looping the last step until the feedback information correlation identifications of the plurality of pieces of sub information are not matched with the current obtained real-time feedback information.
7. A data processing system for acquiring an abnormal device based on the device type determination method according to any one of claims 1 to 6, the system comprising: an initial device ID list, a processor and a memory storing a computer program that, when executed by the processor, performs the steps of:
s100, acquiring a key device list A from the initial device list1，A2，……，AmIn which AiThe method refers to the ith key equipment ID, wherein i is 1 … … m, and m is the number of key equipment;
s200, according to AiCorresponding to the first characteristic information, obtaining AiCorresponding list of specified characteristics Bi＝{Bi1，Bi2，……，BinIn which BijMeans AiThe corresponding j-th specified characteristic value, j is 1 … … n, and n is the characteristic value number;
s300, according to BiObtaining AiCorresponding degree of equipment abnormality FiWherein F isiThe following conditions are met:
Fi＝W1×Ki1+W2×Ki2+W3×Ki3。
s400, according to FiObtaining FiPriority T of corresponding key devicexWherein, TxMeans of [ Hx-1，Hx) Corresponding device priority.
8. The data processing system for acquiring exception equipment according to claim 7, further comprising the step of acquiring K in step S300i1：
S301, obtaining AiCorresponding target APP List Ci＝{Ci1，Ci2，……，CipiIn which C isiqRefers to the priority of the qth target APP, q is 1 … … pi, pi refers to the AiThe number of target APPs in the corresponding target equipment;
s303, according to CiqObtaining AiCorresponding target APP quantity list Di＝{Di1，Di2，……，DisIn which D isirThe number of the APPs corresponding to the r-th preset APP priority is defined, wherein r is 1 … … s, and s is the preset APP priority number in the preset APP priority list;
s305, based on DirObtaining Ki1Wherein, K isi1The following conditions are met:
9. The data processing system for acquiring an abnormal device of claim 8, further comprising the step of acquiring K in step S300i2：
Ki2The following conditions are met:
10. The data processing system for acquiring an abnormal device of claim 9, further comprising the step of acquiring K in step S300i3：
Ki3The following conditions are met:
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2021102013260 | 2021-02-23 | ||
| CN202110201326 | 2021-02-23 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114398521A true CN114398521A (en) | 2022-04-26 |
Family
ID=81234868
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210167259.XA Pending CN114398521A (en) | 2021-02-23 | 2022-02-23 | Device type determining method and data processing system for acquiring abnormal device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114398521A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116257791A (en) * | 2023-05-10 | 2023-06-13 | 北京云真信科技有限公司 | Device set determination method, electronic device, and computer-readable storage medium |
| CN116956076A (en) * | 2023-09-20 | 2023-10-27 | 奇点数联(北京)科技有限公司 | Prompting system for abnormal state of user quantity |
-
2022
- 2022-02-23 CN CN202210167259.XA patent/CN114398521A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116257791A (en) * | 2023-05-10 | 2023-06-13 | 北京云真信科技有限公司 | Device set determination method, electronic device, and computer-readable storage medium |
| CN116257791B (en) * | 2023-05-10 | 2023-08-11 | 北京云真信科技有限公司 | Device set determination method, electronic device, and computer-readable storage medium |
| CN116956076A (en) * | 2023-09-20 | 2023-10-27 | 奇点数联(北京)科技有限公司 | Prompting system for abnormal state of user quantity |
| CN116956076B (en) * | 2023-09-20 | 2024-01-05 | 奇点数联(北京)科技有限公司 | Prompting system for abnormal state of user quantity |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109241415B (en) | Project recommendation method and device, computer equipment and storage medium | |
| CN107872436B (en) | Account identification method, device and system | |
| CN105022761B (en) | Group searching method and device | |
| CN114398521A (en) | Device type determining method and data processing system for acquiring abnormal device | |
| KR102218506B1 (en) | Account complaint handling method and server | |
| CN110807207A (en) | Data processing method and device, electronic equipment and storage medium | |
| JP6595718B2 (en) | Credit score model training method, credit score calculation method, apparatus and server | |
| CN114139209B (en) | Information anti-theft method and system applied to big data of business user | |
| CN111090807A (en) | Knowledge graph-based user identification method and device | |
| Zhang et al. | A trust model stemmed from the diffusion theory for opinion evaluation | |
| CN113641993A (en) | Data security processing method based on cloud computing and data security server | |
| CN112839014A (en) | Method, system, device and medium for establishing model for identifying abnormal visitor | |
| CN111931048A (en) | Artificial intelligence-based black product account detection method and related device | |
| CN110348215B (en) | Abnormal object identification method, abnormal object identification device, electronic equipment and medium | |
| CN114662602A (en) | Outlier detection method and device, electronic equipment and storage medium | |
| CN111652284A (en) | Scanner identification method and device, electronic equipment and storage medium | |
| CN111160919A (en) | Block chain address risk assessment method and device | |
| US11334934B2 (en) | Item presentation method, item presentation program, and item presentation apparatus | |
| CN109657148A (en) | For abnormal operation recognition methods, device, server and the medium for reporting POI | |
| CN109753561B (en) | Automatic reply generation method and device | |
| CN111241821B (en) | Method and device for determining behavior characteristics of user | |
| JP7070665B2 (en) | Information processing equipment, control methods, and programs | |
| CN110781410A (en) | Community detection method and device | |
| CN113254919B (en) | Abnormal device identification method, electronic device, and computer-readable storage medium | |
| CN114416462A (en) | Machine behavior identification method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |