CN112711755A - Information screening work method for scientific and technological specializer through cloud platform - Google Patents

Information screening work method for scientific and technological specializer through cloud platform Download PDF

Info

Publication number
CN112711755A
CN112711755A CN202011569698.0A CN202011569698A CN112711755A CN 112711755 A CN112711755 A CN 112711755A CN 202011569698 A CN202011569698 A CN 202011569698A CN 112711755 A CN112711755 A CN 112711755A
Authority
CN
China
Prior art keywords
behavior
safety behavior
safety
agriculture
staff
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
Application number
CN202011569698.0A
Other languages
Chinese (zh)
Inventor
杨琴
师铭
姚平波
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Chongqing Yangcheng Big Data Technology Co ltd
Original Assignee
Chongqing Yangcheng Big Data Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Chongqing Yangcheng Big Data Technology Co ltd filed Critical Chongqing Yangcheng Big Data Technology Co ltd
Priority to CN202011569698.0A priority Critical patent/CN112711755A/en
Publication of CN112711755A publication Critical patent/CN112711755A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F21/50—Monitoring users, programs or devices to maintain the integrity of platforms, e.g. of processors, firmware or operating systems
    • G06F21/55—Detecting local intrusion or implementing counter-measures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F21/50—Monitoring users, programs or devices to maintain the integrity of platforms, e.g. of processors, firmware or operating systems
    • G06F21/55—Detecting local intrusion or implementing counter-measures
    • G06F21/56—Computer malware detection or handling, e.g. anti-virus arrangements

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Security & Cryptography (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • Computer Hardware Design (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Computation (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Biology (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Virology (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention provides a method for carrying out information screening work on a science and technology specializer through a cloud platform, which comprises the following steps: in the process of screening the safety behavior marks of the three-agriculture workers, a safety behavior expectation function is established, probability measurement is carried out on the safety behavior marks of the three-agriculture workers through a weight function, accordingly, expected targets of the safety behavior marks of the three-agriculture workers are evaluated, a decision-making model is formed, the expected targets are uploaded to a cloud server to carry out data synchronization, and the expected targets are distributed to an upper computer server cluster.

Description

Information screening work method for scientific and technological specializer through cloud platform
Technical Field
The invention relates to the field of IoT (Internet of things) data security, in particular to a method for carrying out information screening work on a scientific and technological special distributor through a cloud platform.
Background
The degree of current social informatization gradually improves, it needs the IoT thing networking to carry out technical support to accomplish everything interconnection in the intelligence house field, every gateway node all needs the uploading and downloading of data, its cloud server of these data is in the transmission course distributes data and carries out the security behavior analysis, the security behavior interaction is with data as the carrier, in carrying out safe operation process to three agricultural workers of IoT thing networking, it is crucial to whole network security to the information security problem of IoT thing networking, this needs technical personnel in the field to solve corresponding technical problem urgently.
Disclosure of Invention
The invention aims to at least solve the technical problems in the prior art, and particularly creatively provides a method for screening information by a scientific and technological specializer through a cloud platform.
In order to achieve the above object, the present invention provides a method for a science and technology specializer to perform information screening work through a cloud platform, comprising:
in the process of screening the safety behavior marks of the three-agriculture workers, a safety behavior expectation function is established, probability measurement is carried out on the safety behavior marks of the three-agriculture workers through a weight function, accordingly, expected targets of the safety behavior marks of the three-agriculture workers are evaluated, a decision-making model is formed, the expected targets are uploaded to a cloud server to carry out data synchronization, and the expected targets are distributed to an upper computer server cluster.
Preferably, the method further comprises the following steps:
when the safety behavior marks of the working personnel of three farmers are screened, different expected expectations can be generated due to the difference of external environments for executing the safety behaviors, the difference of the safety behaviors is assumed to be ignored now, a safety behavior expectation function is established,
Figure BDA0002862415480000021
Δdimarking the safety behavior of the three agricultural workers with diIs used for cumulatively counting the security behavior markers, label (Δ d)i) Obtaining parameter values for the three agro-worker safety behavior of the set tag label, multiplying by a joint probability distribution P (d)i|xi)，xiFor the example of a safety behavior marker, μ is the convergence threshold, Pi(di) Marking d for safety actioniThe marking d of the safety behavior of the three-agriculture staff is completed through the safety behavior adjusting coefficient alphaiResult limit value of
Figure BDA0002862415480000022
The definition of (1).
Preferably, the method further comprises the following steps:
the three-agriculture staff safety behavior mark forms a weight function of a behavior decision, and for the probability measurement of calling an expected safety behavior mark result in the cloud server, the influence of the expected safety behavior mark result on the change of the sending behavior of the three-agriculture staff safety behavior mark is required; designing a marking weight function of the safety behavior of the three-agriculture staff according to the marking example of the safety behavior as follows:
Figure BDA0002862415480000023
wherein, the first and second connecting parts are connected with each other; h is used as a metric value of the difficulty degree of obtaining the safety behavior to mark the safety behavior of the three-agriculture staff through a beta fitting function, the result occurrence probability W of the safety behavior mark is constrained by the safety behavior expectation function of the three-agriculture staff, h is more than 0 and less than 1, and a result function y is judged through the behaviorkImplementing a Security behavior Mark instance xiAnd (4) under the condition of judging the behavior stability, obtaining the stable data of the safety behavior mark of the three-agriculture staff by the designed safety behavior mark weight function X (h).
Preferably, the method further comprises the following steps:
the three-agriculture worker safety behavior marking decision model expression mode is as follows:
Figure BDA0002862415480000024
wherein s isiRepresenting the actual outcome of the security action indicia; l(s)i) I represents the number of safety behavior marks which occur as a judgment function of the actual safety behavior marking result; v (x)i) Representing the probability of occurrence of a security action marker; x (h) is a weight function, and the weight function and the probability of occurrence of the safety behavior mark are subjected to weight judgment; evaluating the distance of the safety behavior marking result from the reference point through a value function lambda so as to obtain the safety behavior marking resultAnd the cloud server sends the decision value of the safety behavior mark of the three-agriculture staff, and decides and judges the decision value of the safety behavior mark of the three-agriculture staff.
In summary, due to the adoption of the technical scheme, the invention has the beneficial effects that:
the safety behavior analysis method comprises the steps that data analysis can be conducted on safety behaviors of three agricultural workers in the IoT internet of things through data calling processes of the cloud server and the local server, data distribution is conducted on safety behavior analysis results through user calling instructions, the safety behaviors can be identified, high-accuracy safety behavior data are formed after clustering, and the high-accuracy safety behavior data are transmitted to the cloud server.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The above and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a general schematic of the present invention;
FIG. 2 is a schematic diagram of an embodiment of the present invention;
FIG. 3 is a schematic diagram of an embodiment of a fetch instruction;
fig. 4 is a flow chart of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention.
As shown in fig. 1 to 4, the invention discloses a method for a science and technology specializer to perform information screening work through a cloud platform, which comprises the following steps:
as shown in fig. 1, a user sends a work instruction to a cloud server through a wireless network, and obtains the work data of the IoT internet of things three-farmer staff in a local server to acquire, classify and optimally extract IoT internet of things data, and performs data convergence aiming at the use behavior of the abnormal IoT internet of things, and stores the converged data in a virtual server for the user to call in real time,
because each local server performs data interaction with the cloud server independently in the process of distributing or collecting data by the traditional cloud server, a black wall (black wall) effect exists in the interaction process, namely, data of the interaction of two parallel local servers can be tampered after network data attacks, the authenticity of the tampered data cannot be identified by the cloud server, and the original data of the corresponding local server group cannot be checked.
In order to prevent the problem caused by data tampering, as shown in fig. 2 and 3, a local server group is set at each AP site, where the local server group includes an upper computer server cluster and a local server cluster, where one AP, that is, the upper computer server cluster of AP1, can obtain original data of another AP, that is, the local server cluster of AP2 and the original data of the local server cluster of AP3, and then perform data interaction with the cloud server through the upper computer server cluster of AP1, and at the same time, the upper computer server cluster of AP2 also performs data interaction with the cloud server, so that data verification can be performed, behavior of three agricultural workers is analyzed, and security is determined.
S1, selecting safety behavior data of three-agricultural workers as target data from a cloud server in an IoT Internet of things to perform safety behavior perception, obtaining safety behavior state data of the target data, and selecting the safety behavior state data of the target data according to protection requirements;
s1-1, analyzing and evaluating the safety behavior state data to generate an analysis and evaluation result; matching a safety protection strategy according to the analysis and evaluation result, executing at least one safety control method according to the safety protection strategy to perform safety control on the safety behavior state data, and determining a corresponding safety control result; screening the safety behavior state data layer by layer again according to the safety control result to obtain the safety state of the safety behavior state data, starting to acquire the safety behavior data of the safety behavior state data, and generating a corresponding safety behavior data feature set, wherein the feature set comprises attribute features; performing granulation screening on the attribute features of the feature set to generate a corresponding particle set comprising specific safety behavior data particles corresponding to the safety behavior state data; the security behavior data granule includes: when an IoT Internet of things cloud server encounters malicious attack, a host computer server cluster performing data interaction with the cloud server is down or attacked maliciously, and a local server cluster is down or attacked maliciously;
s1-2, combining with the security behavior data feature set { B } of the security behavior state data of the three-agriculture staff acquired by the cloud server1,B2,…,BAC, and a set of particles of the cloud server C1,C2,…,CAConstructing a behavior state matrix { D) of the cloud server1,D2,…,DA}；
Initializing relevant parameters of safety behavior state data of the three-agricultural workers; behavior state matrix D of cloud server corresponding to security behavior state attribute b of three-agriculture staffbBehavior state matrix D about its corresponding cloud serverbAnd behavior acquisition time feature matrix EbConstructing a safety behavior training function Fb；
The iteration upper limit reached by iteration control variable G by judging and extracting the safety behavior state data of the three-agricultural workers is G;
training function F of safety behaviorbObtaining a temporal feature matrix E for a behaviorbBehavior state matrix D of cloud serverbConverging; simultaneous time feature matrix E for behaviorbBehavior state matrix D of cloud serverbTraining function F for safety behaviorbPerforming iterative optimization; judging the safety behavior state attributes of the three-agriculture staff of all processed cloud servers;
s1-3, tracking and monitoring the safety behavior state data according to specific safety behavior data particles, and determining the safety behavior state of the safety behavior state data; carrying out data identification on the target data to obtain marking information of the target data; the marking information comprises a data label, a data log and a self-defined mode;
s1-4, safety behavior training function F for safety behavior stateaThe calculation is carried out in such a way that,
Figure BDA0002862415480000051
wherein
Figure BDA0002862415480000052
Calculating a particle matrix C of the cloud server corresponding to the security behavior state attribute b of the three-peasant staff through the Euclidean distancebProduct of convergence threshold μ, and behavior state matrix D of cloud serverbAnd behavior acquisition time feature matrix EbOptimizing the difference between the transposed products to reduce the difference;
to FaAn optimization iteration is carried out, and the optimization iteration,
Figure BDA0002862415480000061
Figure BDA0002862415480000062
Figure BDA0002862415480000063
wherein Db(c,g)Representation matrix DbRow c, column g, the control variable element; eb(t,g)Representing behavior acquisition time feature matrix EaThe time element of the t-th row, the control variable element of the g-th column;
Figure BDA0002862415480000064
behavior state matrix D representing cloud serverbTransposing;
Figure BDA0002862415480000065
representing behavior acquisition time feature matrix EbTransposing;
Figure BDA0002862415480000066
particle matrix C representing cloud serverbTransposing; cb(m,g)Particle matrix C representing cloud serverbRow m, column g, the control variable element; thereby judging the safety behavior state attribute of the three-agriculture staff in all the cloud servers;
s2, setting a format of the security behavior state marks of the cloud server three agricultural workers, generating the security behavior state marks of the cloud server three agricultural workers, and respectively storing the security behavior state marks of the cloud server three agricultural workers in an upper computer server cluster of a local server and a local server cluster;
s2-1, loading upper computer server cluster data marked by the safety behavior state of the three-agricultural workers to a memory when the upper computer server cluster is started, updating the safety behavior state marking data of the three-agricultural workers in real time in the running process of the upper computer server cluster, and updating the stored safety behavior state marking data of the three-agricultural workers in the upper computer server cluster in a database of a cloud server;
setting a Label Label of a data collection format for marking the safety behavior state of the three-farmer staff, and marking the identity information of the three-farmer staff, the classification information of the safety behavior of the three-farmer staff, the safety behavior target of the three-farmer staff and the safety behavior strategy of the three-farmer staff by using the Label, wherein the identity information of the three-farmer staff is a mark identifier: marking data for identifying the safety behaviors of the three-farmer staff;
the three-agriculture staff security behavior strategy is used for identifying security strategies related to the three-agriculture staff security behavior mark; the sensitivity of the safety behavior classification information of the three-agriculture staff is adjusted, and the value of the marked safety behavior grade is set as an integer; the sensitivity behavior degree refined to the safety behaviors of the three-farmer staff is specified, and a safety strategy corresponding to the safety behaviors of the three-farmer staff is specified; a plurality of safety behavior tags of the same three-agriculture worker safety attribute related information are called to form a target tag group TagSet;
s2-2, backing up the data related to the three-farmer worker safety behavior marking by the three-farmer worker safety behavior marking data in the upper computer server cluster, and the working environment data of the upper computer server cluster and the working environment data of the cloud server through a cache unit of the upper computer server cluster; the local server cluster is used for backing up safety behavior marking data of each corresponding upper computer server cluster about the safety behavior of the three-farmer staff and backing up the safety behavior marking data of the cloud server about the three-farmer staff; the local server cluster creates a security label of the three-agricultural workers, guarantees the uniqueness of the identity information of the three-agricultural workers and completes the initialization operation of the security behavior label of the three-agricultural workers;
s2-3, creating a label storage table of the three-agriculture staff safety behavior label data in each server of the upper computer server cluster, wherein the label storage table stores label data when the three-agriculture staff carries out safety behavior input, when the label safety behavior data in the label storage table is less than a certain amount, applying a certain reserved space as a three-agriculture staff safety behavior label as a storage area for the labeled local server cluster to ensure that the label data in the label storage table meets the label creation requirement of the upper computer server cluster, wherein the label storage table of each upper computer server cluster is stored in the upper computer server cluster, dynamically loaded into the cache of the upper computer server cluster during running, updating the three-agriculture staff safety behavior database of the upper computer server cluster in real time, after receiving a request for creating a new three-agriculture staff safety behavior label, taking the safety behavior marking data of the three agricultural workers in the reserved space of the local server cluster from the marking storage table, then creating safety behavior marks of the three agricultural workers and returning the safety behavior marks to the local server cluster as storage results, and simultaneously synchronizing newly-recorded creating information of the safety behavior marking data of the three agricultural workers to the upper computer server cluster and the local server cluster;
s2-4, carrying out the creating operation of the safety behavior mark of the three-agriculture staff, wherein the creating operation comprises the following steps: the safety behavior marking record of the three-farmer staff is carried out, the marking identifier is used for searching the safety behavior marking record of the three-farmer staff to find whether the repeated safety behavior mark exists or not, if the repeated safety behavior marks exist, deleting the historical safety behavior mark records, not recording new safety behavior marks of the three-agriculture staff, keeping the historical safety behavior mark records, if the repeated safety behavior mark does not exist, the new safety behavior mark of the three-agriculture staff is recorded, modifying the safety behavior data of the three-agriculture staff, if the safety behavior data of the three-agriculture staff generates updated safety behavior data, judging whether the updated safety behavior modification mark has a complete modification label, if so, modifying the safety behavior mark associated data, modifying the working environment data of the upper computer server cluster, and simultaneously updating the working environment data of the cloud server; when the safety behavior data of the three-farmer staff are deleted, firstly, the safety behavior marks of the three-farmer staff are deleted, and meanwhile, the cluster working environment data of the upper computer server and the cloud server working environment data are deleted.
S2-5, the safety behavior mark of the working personnel of three farmers is responsible for ensuring the uniqueness of the mark identifier, after the initialization operation of the mark is completed, the mark storage table in the upper computer server cluster stores a certain number of pre-applied marks, and when the safety behavior mark data in the mark storage table is less than a certain number, the pre-applied marks are cached in the upper computer server cluster component so as to ensure that the safety behavior mark data in the mark storage table meets the mark creation requirement of the upper computer server cluster; after the mark storage table of each upper computer server cluster is stored, the mark storage table is loaded into a cache in dynamic operation, the cloud server is continuously updated, the safety behavior marks reserved from the local server cluster are taken out from the mark storage table, then the safety behavior marks are created and returned as results,
s2-6, in the process of security behavior marking by the upper computer server cluster, when receiving a request of security behavior marking retrieval and verifying a legality instruction of the security behavior marking retrieval request, if the security behavior marking retrieval information is loaded in a cache, directly retrieving the security behavior marking from the cache and recording the security behavior marking as a legal retrieval request, otherwise, retrieving a corresponding security behavior marking in the upper computer server cluster, executing a cloud server proxy response instruction, calling the retrieved security behavior marking in the local server cluster, and executing a cloud server proxy response instruction; in order to improve the efficiency of the upper computer server cluster for executing the three-agriculture worker safety behavior marking retrieval, the retrieval positions have the priority sequence of a first-level cache, a second-level upper computer server cluster and a third-level local server cluster.
S2-7, when the upper computer server cluster receives the three-agriculture staff safety behavior mark modification request and verifies the validity of the modification request, the upper computer server cluster and the local server cluster are modified and synchronized, the three-agriculture staff safety behavior mark, the marked safety behavior related data and the buffer data are executed, the cloud server proxy response instruction is executed, the upper computer server cluster and the local server cluster are modified and synchronized, after the safety behavior mark proxy of the upper computer server cluster receives the deletion request and verifies the validity of the deletion request, the upper computer server cluster and the local server cluster are deleted and synchronized, the cloud server proxy response instruction is executed, the upper computer server cluster and the local server cluster are deleted and synchronized for the safety behavior mark and the marked safety behavior related data and the buffer data, and if the safety behavior marking data of the three-agriculture staff of the cloud server needs to be deleted, executing the broadcasting response of the upper computer server cluster, and synchronizing the deletion instructions of all the upper computer server clusters controlled by the cloud server, thereby ensuring the consistency of the safety behavior marking data of the three-agriculture staff.
S3, in the process of screening the safety behavior marks of the three-agriculture workers, establishing a safety behavior expectation function, and performing probability measurement on the safety behavior marks of the three-agriculture workers by setting a weight function, so as to evaluate the expected targets of the safety behavior marks of the three-agriculture workers, form a decision model, upload the decision model to a cloud server for data synchronization, and distribute the decision model to an upper computer server cluster;
s3-1, when the safety behavior mark of the working personnel of three farmers is screened, different expected expectations can be generated due to the difference of the external environment for executing the safety behavior, the difference of the safety behavior is assumed to be ignored now, the safety behavior expectation function is established,
Figure BDA0002862415480000091
Δdimarking the safety behavior of the three agricultural workers with diIs used for cumulatively counting the security behavior markers, label (Δ d)i) Obtaining parameter values for the three agro-worker safety behavior of the set tag label, multiplying by a joint probability distribution P (d)i|xi)，xiFor the example of a safety behavior marker, μ is the convergence threshold, Pi(di) Marking d for safety actioniThe marking d of the safety behavior of the three-agriculture staff is completed through the safety behavior adjusting coefficient alphaiResult limit value of
Figure BDA0002862415480000101
The definition of (1);
s3-2, the three-agriculture staff security behavior mark forms a weight function of behavior decision, and for the probability measurement of calling the expected security behavior mark result in the cloud server, the influence of the expected security behavior mark result on the change of the sending behavior of the three-agriculture staff security behavior mark is needed; designing a marking weight function of the safety behavior of the three-agriculture staff according to the marking example of the safety behavior as follows:
Figure BDA0002862415480000102
wherein, the first and second connecting parts are connected with each other; h is used as a metric value of the difficulty degree of obtaining the safety behavior to mark the safety behavior of the three-agriculture staff through a beta fitting function, the result occurrence probability W of the safety behavior mark is constrained by the safety behavior expectation function of the three-agriculture staff, h is more than 0 and less than 1, and a result function y is judged through the behaviorkImplementing a Security behavior Mark instance xiPerforming behavior stability judgment, and acquiring stability data of the safety behavior marks of the three-agriculture staff by using a designed safety behavior mark weight function X (h);
s3-3, the three-agriculture worker safety behavior marking decision model expression mode is as follows:
Figure BDA0002862415480000103
wherein s isiRepresenting the actual outcome of the security action indicia; l(s)i) I represents the number of safety behavior marks which occur as a judgment function of the actual safety behavior marking result; v (x)i) Representing the probability of occurrence of a security action marker; x (h) is a weight function, and the weight function and the probability of occurrence of the safety behavior mark are subjected to weight judgment; evaluating the distance of the safety behavior marking result from the reference point through the value function lambda, sending the decision value of the safety behavior marking of the three-agriculture staff to the cloud server, and judging the decision of the safety behavior marking value of the three-agriculture staff.
While embodiments of the invention have been shown and described, it will be understood by those of ordinary skill in the art that: various changes, modifications, substitutions and alterations can be made to the embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.

Claims (4)

1. A method for carrying out information screening work by a scientific and technological specializer through a cloud platform is characterized by comprising the following steps:
in the process of screening the safety behavior marks of the three-agriculture workers, a safety behavior expectation function is established, probability measurement is carried out on the safety behavior marks of the three-agriculture workers through a weight function, accordingly, expected targets of the safety behavior marks of the three-agriculture workers are evaluated, a decision-making model is formed, the expected targets are uploaded to a cloud server to carry out data synchronization, and the expected targets are distributed to an upper computer server cluster.
2. The method for information screening work of the scientific and technological specializer according to claim 1 through the cloud platform, further comprising:
when the safety behavior marks of the working personnel of three farmers are screened, different expected expectations can be generated due to the difference of external environments for executing the safety behaviors, the difference of the safety behaviors is assumed to be ignored now, a safety behavior expectation function is established,
Figure FDA0002862415470000011
Δdimarking the safety behavior of the three agricultural workers with diIs used for cumulatively counting the security behavior markers, label (Δ d)i) Obtaining parameter values for the three agro-worker safety behavior of the set tag label, multiplying by a joint probability distribution P (d)i|xi)，xiFor the example of a safety behavior marker, μ is the convergence threshold, Pi(di) Marking d for safety actioniThe marking d of the safety behavior of the three-agriculture staff is completed through the safety behavior adjusting coefficient alphaiResult limit value of
Figure FDA0002862415470000012
The definition of (1).
3. The method for information screening work of the scientific and technological specializer according to claim 1 through the cloud platform, further comprising:
the three-agriculture staff safety behavior mark forms a weight function of a behavior decision, and for the probability measurement of calling an expected safety behavior mark result in the cloud server, the influence of the expected safety behavior mark result on the change of the sending behavior of the three-agriculture staff safety behavior mark is required; designing a marking weight function of the safety behavior of the three-agriculture staff according to the marking example of the safety behavior as follows:
Figure FDA0002862415470000021
wherein, the first and second connecting parts are connected with each other; h is used as a metric value of the difficulty degree of obtaining the safety behavior to mark the safety behavior of the three-agriculture staff through a beta fitting function, the result occurrence probability W of the safety behavior mark is constrained by the safety behavior expectation function of the three-agriculture staff, h is more than 0 and less than 1, and a result function y is judged through the behaviorkImplementing a Security behavior Mark instance xiAnd (4) under the condition of judging the behavior stability, obtaining the stable data of the safety behavior mark of the three-agriculture staff by the designed safety behavior mark weight function X (h).
4. The method for information screening work of the scientific and technological specializer according to claim 1 through the cloud platform, further comprising:
the three-agriculture worker safety behavior marking decision model expression mode is as follows:
Figure FDA0002862415470000022
wherein s isiRepresenting the actual outcome of the security action indicia; l(s)i) I represents the number of safety behavior marks which occur as a judgment function of the actual safety behavior marking result; v (x)i) Representing the probability of occurrence of a security action marker; x (h) is a weight function, and the weight function and the probability of occurrence of the safety behavior mark are subjected to weight judgment; evaluating the distance of the safety behavior marking result from the reference point through the value function lambda, sending the decision value of the safety behavior marking of the three-agriculture staff to the cloud server, and judging the decision of the safety behavior marking value of the three-agriculture staff.
CN202011569698.0A 2020-12-26 2020-12-26 Information screening work method for scientific and technological specializer through cloud platform Pending CN112711755A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011569698.0A CN112711755A (en) 2020-12-26 2020-12-26 Information screening work method for scientific and technological specializer through cloud platform

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011569698.0A CN112711755A (en) 2020-12-26 2020-12-26 Information screening work method for scientific and technological specializer through cloud platform

Publications (1)

Publication Number Publication Date
CN112711755A true CN112711755A (en) 2021-04-27

Family

ID=75546931

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011569698.0A Pending CN112711755A (en) 2020-12-26 2020-12-26 Information screening work method for scientific and technological specializer through cloud platform

Country Status (1)

Country Link
CN (1) CN112711755A (en)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106548296A (en) * 2016-11-22 2017-03-29 西南科技大学 Promote the mixed power generation power deals match method of cleaning high-quality electric energy consumption
CN108616491A (en) * 2016-12-13 2018-10-02 北京酷智科技有限公司 A kind of recognition methods of malicious user and system
CN108985195A (en) * 2018-06-29 2018-12-11 平安科技（深圳）有限公司 Activity recognition method, apparatus, computer equipment and storage medium
CN109711424A (en) * 2018-11-12 2019-05-03 平安科技（深圳）有限公司 A kind of rule of conduct acquisition methods, device and equipment based on decision tree
CN110516950A (en) * 2019-08-21 2019-11-29 西北工业大学 A kind of risk analysis method of entity-oriented parsing task
CN111314120A (en) * 2020-01-23 2020-06-19 福州大学 Cloud software service resource self-adaptive management framework based on iterative QoS model
CN111935161A (en) * 2020-08-14 2020-11-13 国网重庆市电力公司电力科学研究院 Network attack and defense analysis method and system based on game theory

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106548296A (en) * 2016-11-22 2017-03-29 西南科技大学 Promote the mixed power generation power deals match method of cleaning high-quality electric energy consumption
CN108616491A (en) * 2016-12-13 2018-10-02 北京酷智科技有限公司 A kind of recognition methods of malicious user and system
CN108985195A (en) * 2018-06-29 2018-12-11 平安科技（深圳）有限公司 Activity recognition method, apparatus, computer equipment and storage medium
CN109711424A (en) * 2018-11-12 2019-05-03 平安科技（深圳）有限公司 A kind of rule of conduct acquisition methods, device and equipment based on decision tree
CN110516950A (en) * 2019-08-21 2019-11-29 西北工业大学 A kind of risk analysis method of entity-oriented parsing task
CN111314120A (en) * 2020-01-23 2020-06-19 福州大学 Cloud software service resource self-adaptive management framework based on iterative QoS model
CN111935161A (en) * 2020-08-14 2020-11-13 国网重庆市电力公司电力科学研究院 Network attack and defense analysis method and system based on game theory

Similar Documents

Publication Publication Date Title
US20050097111A1 (en) System and method for data integration using multi-dimensional, associative unique identifiers
CN109934615B (en) Product marketing method based on deep sparse network
CN109255342B (en) Image region-of-interest extraction method and system based on two-step clustering of eye movement trajectory data
CN102045358A (en) Intrusion detection method based on integral correlation analysis and hierarchical clustering
US20170214716A1 (en) Violation information management module forming violation information intelligence analysis system
CN113971527A (en) Data risk assessment method and device based on machine learning
CN114187036B (en) Internet advertisement intelligent recommendation management system based on behavior characteristic recognition
CN116582349A (en) Attack path prediction model generation method and device based on network attack graph
CN117495205B (en) Industrial Internet experiment system and method
CN109067778B (en) Industrial control scanner fingerprint identification method based on honeynet data
US20170214715A1 (en) Violation information intelligence analysis system
CN117933999A (en) Network asset risk identification method, system, equipment and storage medium
CN110166422A (en) Domain name Activity recognition method, apparatus, readable storage medium storing program for executing and computer equipment
CN112711755A (en) Information screening work method for scientific and technological specializer through cloud platform
CN112738076A (en) Method for carrying out three-agriculture worker safety behavior analysis through IoT (Internet of things)
CN112733139A (en) Working method for safely cleaning agricultural data through big data network
CN112560111A (en) Time sequence data acquisition tamper-proofing method and device suitable for Internet of things
CN112580028A (en) Agricultural information data security optimization method through distributed computation
CN113065604B (en) Air target grouping method based on DTW-DBSCAN algorithm
CN115208938A (en) User behavior control method and device and computer readable storage medium
CN113434868A (en) Information generation method based on threat perception big data and artificial intelligence perception system
JP6906469B2 (en) Information processing equipment, information processing methods, and programs
CN116187895B (en) Intelligent warehouse cargo flow planning method, system and electronic equipment
CN115796793B (en) File digital conversion and management method, system and storage medium
CN113807600B (en) Link prediction method in dynamic social network

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20210427