CN111178778A - Security activity scheme generation method and system based on machine learning and security activity management system - Google Patents
Security activity scheme generation method and system based on machine learning and security activity management system Download PDFInfo
- Publication number
- CN111178778A CN111178778A CN202010001258.9A CN202010001258A CN111178778A CN 111178778 A CN111178778 A CN 111178778A CN 202010001258 A CN202010001258 A CN 202010001258A CN 111178778 A CN111178778 A CN 111178778A
- Authority
- CN
- China
- Prior art keywords
- security
- security activity
- activity
- scheme
- machine learning
- 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
- 230000000694 effects Effects 0.000 title claims abstract description 198
- 238000010801 machine learning Methods 0.000 title claims abstract description 61
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000012549 training Methods 0.000 claims abstract description 37
- 238000004458 analytical method Methods 0.000 claims description 15
- 230000008520 organization Effects 0.000 claims description 14
- 238000012800 visualization Methods 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 6
- 238000009826 distribution Methods 0.000 claims description 6
- 230000007246 mechanism Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 abstract description 18
- 238000012544 monitoring process Methods 0.000 abstract description 5
- 230000000007 visual effect Effects 0.000 abstract description 4
- 238000012545 processing Methods 0.000 description 8
- 238000004364 calculation method Methods 0.000 description 5
- 238000004590 computer program Methods 0.000 description 5
- 238000012937 correction Methods 0.000 description 4
- 238000001914 filtration Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 238000002485 combustion reaction Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 230000003111 delayed effect Effects 0.000 description 2
- 238000012217 deletion Methods 0.000 description 2
- 230000037430 deletion Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000008030 elimination Effects 0.000 description 2
- 238000003379 elimination reaction Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000007500 overflow downdraw method Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000004080 punching Methods 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- Quality & Reliability (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- General Business, Economics & Management (AREA)
- Operations Research (AREA)
- Software Systems (AREA)
- Educational Administration (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Alarm Systems (AREA)
Abstract
The invention discloses a security activity scheme generation method based on machine learning, which comprises the following steps: acquiring a plurality of security activity schemes to establish a machine learning training sample; performing machine learning according to the machine learning training samples to generate one or more security activity models; generating one or more predicted security activity solutions based on the one or more security models and candidate security activity solutions; determining a target security activity scheme from the one or more predicted security activity schemes. The invention realizes the dynamic management of the participators in the fire safety protection activity by formulating a scheme according to experience by the commonly used workers in the fire safety protection in the past and adopting a machine learning and self-adaptive recommendation optimal scheme in the process of manually distributing tasks, thereby realizing the omnibearing visual monitoring of the running state of the safety protection target and the flattening of command scheduling.
Description
Technical Field
The invention belongs to the technical field of security, and particularly relates to a security activity scheme generation method and system based on machine learning and a security activity management system.
Background
The security activity scheme is used as a guideline of security work, all workers manufacture the security activity scheme according to previous experiences in the original manufacturing process, data collection is not timely, and efficiency is not high. Meanwhile, in the security process, the problems of unclear working level, deffection of responsibility of the fire safety theme of social units and the like exist, the security tasks are difficult to distribute, and the tasks, particularly the temporarily added tasks, are difficult to be received in time by duty personnel, venue workers and the like and cannot be transmitted in place in time. As the security target building has complex structure and large area, part of the staff on duty is not familiar to the place, the full coverage is difficult to carry out the inspection, and the work is easy to leak. When emergent the disposition, command unit is difficult to master in real time person on duty and equip quantity, position, can't carry out the flattening commander.
Disclosure of Invention
In view of the above-mentioned shortcomings of the prior art, the present invention aims to provide a security activity scheme generation method, system and security activity management system based on machine learning, which are used to solve the shortcomings of the prior art.
In order to achieve the above objects and other related objects, the present invention provides a security activity scheme generation method based on machine learning, including:
acquiring a plurality of security activity schemes to establish a machine learning training sample;
performing machine learning according to the machine learning training samples to generate one or more security activity models;
generating one or more predicted security activity solutions based on the one or more security models and candidate security activity solutions;
determining a target security activity scheme from the one or more predicted security activity schemes.
Optionally, generating one or more predicted security activity schemes based on the one or more security models and the candidate security activity schemes specifically includes:
inputting the characteristics of the candidate security activity scheme into one or more security models, and outputting one or more predicted security activity parties, wherein the characteristics of the candidate security activity scheme at least comprise: activity type, scheme level, security location, participating security organization unit.
Optionally, if there are multiple predicted security activity schemes, selecting the predicted security activity scheme with the maximum matching degree with the candidate security activity scheme as a target security activity scheme.
Optionally, the features of the security activity scheme include: the system comprises an activity type, a scheme grade, a security position, a security organization unit, a security organization architecture, a security worker task division, an emergency worker type, an emergency worker wearing device and a parking position, an emergency vehicle type and a parking position, an attack route and a linkage unit.
Optionally, the security activity scheme generating method further includes:
model parameters of one or more security activity models are adjusted.
To achieve the above and other related objects, the present invention provides a security activity scheme generating system based on machine learning, comprising:
the system comprises a sample construction module, a machine learning training module and a security activity analysis module, wherein the sample construction module is used for acquiring a plurality of security activity schemes so as to establish a machine learning training sample;
the model training module is used for performing machine learning according to the machine learning training samples to generate one or more security activity models;
a scenario generation module to generate one or more predicted security activity scenarios based on the one or more security models and candidate security activity scenarios;
a scheme determination module to determine a target security activity scheme based on the one or more predicted security activity schemes.
Optionally, if there are multiple predicted security activity schemes, selecting the predicted security activity scheme with the maximum matching degree with the candidate security activity scheme as a target security activity scheme.
Optionally, the security data includes: activity type, scheme level, security location, participating security organization unit.
To achieve the above and other related objects, the present invention provides a security activity management system based on machine learning, the management system comprising:
the scheme making end is used for generating one or more candidate security activity schemes by adopting the security activity scheme generating method and sending the one or more candidate security activity schemes to the task generating end;
the task generating end is used for determining a target security activity scheme based on one or more candidate security activity schemes, generating one or more security tasks based on the target security activity scheme, and distributing the one or more security tasks to the mobile application end;
the mobile application end is used for receiving the one or more security tasks and feeding back the completion condition of the one or more security tasks to the task generating end;
and the visualization end is used for displaying the target security activity scheme.
Optionally, the task live end performs task allocation by using a subscription mechanism of a message queue.
As described above, the security activity scheme generation method, system and security activity management system based on machine learning according to the present invention have the following advantages:
the invention realizes the dynamic management of the participators in the fire safety protection activity by formulating a scheme according to experience by the commonly used workers in the fire safety protection in the past and adopting a machine learning and self-adaptive recommendation optimal scheme in the process of manually distributing tasks, thereby realizing the omnibearing visual monitoring of the running state of the safety protection target and the flattening of command scheduling.
Drawings
FIG. 1 is a flowchart of a security activity scheme generation method based on machine learning according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a security activity scheme generation system based on machine learning according to an embodiment of the present invention;
fig. 3 is a schematic diagram of a security activity management system based on machine learning according to an embodiment of the present invention.
Detailed Description
The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict.
It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present invention, and the components related to the present invention are only shown in the drawings rather than drawn according to the number, shape and size of the components in actual implementation, and the type, quantity and proportion of the components in actual implementation may be changed freely, and the layout of the components may be more complicated.
As shown in fig. 1, a security activity scheme generation method based on machine learning includes:
s11, acquiring a plurality of security activity schemes to establish a machine learning training sample;
s12, performing machine learning according to the machine learning training sample to generate one or more security activity models;
s13 generating one or more predicted security activity solutions based on the one or more security models and the candidate security activity solutions;
s14 determines a target security activity scheme from the one or more predicted security activity schemes.
The invention realizes the machine learning and self-adaptive recommendation of the optimal scheme in the process of manually distributing tasks by making the scheme according to experience by the common working personnel in the fire protection security in the past, and improves the efficiency and the accuracy.
In step S11, security activity schemes are obtained, wherein the security activity schemes are security activity schemes that have been executed in the past and are used as training samples for machine learning.
In step S12, machine learning is performed according to the machine learning training samples, and one or more security activity models are generated.
In the process of machine learning, some effective features need to be extracted from the security activity scheme first, and the effective features are used as training samples. In the process of establishing the security activity model, training sample data needs to be preprocessed. Wherein the preprocessing comprises filtering of data features, screening out significant features and discarding non-significant features. And selecting a training model from comprehensive consideration of sample number, feature dimension and data feature. The filtering of the data may include: through data cleaning work, duplicate removal processing is carried out on duplicate values, correction or elimination is carried out on error values of abnormal values, filling correction or deletion is carried out on missing values, and sampling processing is carried out on data. And analyzing and exploring the preprocessed data by using data analysis methods such as trend analysis, mean variance analysis, sequencing TOP analysis, aspect ratio comparison analysis of a same-ratio ring ratio, frequency analysis, correlation relation analysis and the like.
In the training process of the model, the optimizer can be used for adjusting the parameters of the model, and meanwhile, a multi-model fusion method is adopted to improve the effect. After the model training is finished, a priori constraint condition can be added to process the model, and obvious errors are removed.
In step S13, generating one or more predicted security activity schemes based on the one or more security models and the candidate security activity schemes;
when a training model is adopted to obtain a target security activity scheme, generating one or more predicted security activity schemes based on the one or more security models and the candidate security activity schemes, specifically comprising:
inputting the characteristics of the candidate security activity scheme into one or more security models, and outputting one or more predicted security activity parties, wherein the characteristics of the candidate security activity scheme at least comprise: activity type, scheme level, security location, participating security organization unit. Wherein, the security activity scheme includes: the system comprises an activity type, a scheme grade, a security position, a security organization unit, a security organization architecture, a security worker task division, an emergency worker type, an emergency worker wearing device and a parking position, an emergency vehicle type and a parking position, an attack route, a linkage unit and the like.
In step S14, a target security activity scheme is determined from the one or more predicted security activity schemes.
In this embodiment, a plurality of predicted security activity schemes may be generated, and thus one scheme needs to be determined from the plurality of predicted security activity schemes as a target security activity scheme. The specific determination method may include: and calculating the matching degree of the plurality of predicted security activity schemes and the candidate security activity schemes, and taking the predicted security activity scheme with the highest matching degree as a target security activity scheme. The calculation method of the matching degree can adopt text correlation (content matching) for calculation.
In one embodiment, whether a target security activity scheme is an optimal scheme needs to be judged, if not, adjustment needs to be performed, and the adjustment method comprises manual adjustment and automatic adjustment, wherein the automatic adjustment is to adjust model parameters of one or more security activity models; manual adjustment is to edit the scheme.
After the target security activity scheme is obtained, data related to the target security activity scheme can be added to an existing training sample to be used as a new training sample to train the security activity model.
As shown in fig. 2, a security activity scheme generation system based on machine learning, the security activity scheme generation system includes:
the sample construction module 21 is used for acquiring a plurality of security activity schemes to establish a machine learning training sample;
the model training module 22 is used for performing machine learning according to the machine learning training samples to generate one or more security activity models;
a scenario generation module 23, configured to generate one or more predicted security activity scenarios based on the one or more security models and the candidate security activity scenarios;
and a scheme determining module 24, configured to determine a target security activity scheme according to the one or more predicted security activity schemes.
The invention realizes the machine learning and self-adaptive recommendation of the optimal scheme in the process of manually distributing tasks by making the scheme according to experience by the common working personnel in the fire protection security in the past, and improves the efficiency and the accuracy.
The sample construction module 21 is configured to obtain a plurality of security activity schemes, where the security activity schemes are security activity schemes that have been executed in the past, and the security activity schemes are used to form training samples for machine learning.
And the model training module 22 is used for performing machine learning according to the machine learning training samples to generate one or more security activity models.
In the process of machine learning, some effective features need to be extracted from the security activity scheme first, and the effective features are used as training samples. In the process of establishing the security activity model, training sample data needs to be preprocessed. Wherein the preprocessing comprises filtering of data features, screening out significant features and discarding non-significant features. And selecting a training model from comprehensive consideration of sample number, feature dimension and data feature. The filtering of the data may include: through data cleaning work, duplicate removal processing is carried out on duplicate values, correction or elimination is carried out on error values of abnormal values, filling correction or deletion is carried out on missing values, and sampling processing is carried out on data. And analyzing and exploring the preprocessed data by using data analysis methods such as trend analysis, mean variance analysis, sequencing TOP analysis, aspect ratio comparison analysis of a same-ratio ring ratio, frequency analysis, correlation relation analysis and the like.
In the training process of the model, the optimizer can be used for adjusting the parameters of the model, and meanwhile, a multi-model fusion method is adopted to improve the effect. After the model training is finished, a priori constraint condition can be added to process the model, and obvious errors are removed.
A scenario generation module 23 that generates one or more predicted security activity scenarios based on the one or more security models and the candidate security activity scenarios;
inputting the characteristics of the candidate security activity scheme into one or more security models, and outputting one or more predicted security activity parties, wherein the characteristics of the candidate security activity scheme at least comprise: activity type, scheme level, security location, participating security organization unit. Wherein, the security activity scheme includes: the system comprises an activity type, a scheme grade, a security position, a security organization unit, a security organization architecture, a security worker task division, an emergency worker type, an emergency worker wearing device and a parking position, an emergency vehicle type and a parking position, an attack route, a linkage unit and the like.
And the scheme determining module 24 is used for determining a target security activity scheme according to the one or more predicted security activity schemes.
In this embodiment, a plurality of predicted security activity schemes may be generated, and thus one scheme needs to be determined from the plurality of predicted security activity schemes as a target security activity scheme. The specific determination method may include: and calculating the matching degree of the plurality of predicted security activity schemes and the candidate security activity schemes, and taking the predicted security activity scheme with the highest matching degree as a target security activity scheme. The calculation method of the matching degree can adopt text correlation (content matching) for calculation.
In one embodiment, whether a target security activity scheme is an optimal scheme needs to be judged, if not, adjustment needs to be performed, and the adjustment method comprises manual adjustment and automatic adjustment, wherein the automatic adjustment is to adjust model parameters of one or more security activity models; manual adjustment is to edit the scheme.
As shown in fig. 3, a security activity management system based on machine learning, the management system comprising: a scheme making end 31, a task generating end 32, a mobile application end 33 and a visualization end 34;
the scheme making end 31 is configured to generate one or more candidate security activity schemes by using the security activity scheme generation method shown in fig. 1, and send the one or more candidate security activity schemes to the task generation end;
and the scheme making end continuously reads real-time data such as security organizations, personnel, vehicles, equipment, behaviors and the like, performs statistical analysis on the data from different dimensions, and feeds back an analysis result to the visualization end.
The task generating end 32 is configured to determine a target security activity scheme based on one or more candidate security activity schemes, generate one or more security tasks based on the target security activity scheme, and allocate the one or more security tasks to the mobile application end;
in the process of task allocation, a self-adaptive flow is adopted to push task allocation conditions and information prompting messages to the mobile application terminal, and in the process of automatically allocating task division conditions and information prompting messages in the self-adaptive flow, a subscription mechanism of a message queue is adopted. The method carries out comprehensive management and monitoring on the trajectory data and the index data of security personnel, provides accurate basic information for scheduling decisions, adopts optimization strategies such as optimization theory and reinforcement learning to carry out calculation, and makes a global optimal allocation decision.
Aiming at the characteristic of strong uncertainty of security task allocation, the embodiment provides two strategies: firstly, a scheduling strategy is delayed, namely, under the condition that the grades of some hidden trouble tasks are lower, allocation decisions are delayed; and secondly, the system automatically dispatches a strategy, namely, the security task can still evaluate the real-time position and the current task condition of each security worker in real time even if the security task is distributed to the security workers, and the security task is helped to analyze and judge whether overtime risks exist. If so, it is evaluated whether there are better security personnel to handle. And meanwhile, automatically copying and sending to a relevant leader to prompt the progress of the supervision task.
The mobile application end 33 is configured to receive the one or more security tasks, and feed back the completion conditions of the one or more security tasks to the task generating end;
the mobile application terminal can receive the security task and feed the completion condition of the security task back to the task generation terminal, and can also realize the functions of quick updating, approval and checking of a scheme, prompt in time of the task, quick operation of supervision and inspection work, automatic card punching of daily attendance, convenient and quick recording of security logs, an address book and the like, and provide convenient and quick mobile operation application for security personnel.
The mobile application end can report hidden danger events, the task generation end is automatically distributed to corresponding responsible persons and supervisors, meanwhile, the visual end automatically prompts, the responsible persons feed back results through the mobile application end after the processing of the responsible persons is completed, the supervisors check whether the results are qualified or not, if the results are qualified, the task generation end automatically files, and otherwise, the tasks are dispatched again for processing. The mobile application terminal can report an emergency event, the task generation terminal automatically starts an emergency response scheme, all security personnel are reminded through the mobile application terminal, details of the event, surrounding conditions and the dynamics of emergency disposal personnel are directly positioned and displayed through the visualization terminal, the situation trend condition is displayed, an audio and video conversation function is provided to support and command scheduling, and the task generation terminal automatically files after the event is processed. The hidden trouble event may be considered as a possible event when a certain value exceeds a set threshold, and the emergency event may be considered as an event that has already occurred. For example, if a temperature threshold T is set for an electrical distribution box, then when the detected temperature of the electrical distribution box exceeds T, but no combustion is occurring in the electrical distribution box, it may be considered a hazard, but if a combustion is occurring in the electrical distribution box, it is considered an emergency.
And the visualization end 34 is used for displaying the target security activity scheme. Including the display of real-time information such as personnel, vehicles, equipment, sites, facilities, organizational structures, and the like.
The visualization end integrates various types of data such as 2/3 dimensional geographic information, Internet of things monitoring data, statistical data and camera collected pictures, and comprehensively controls the comprehensive situation of the city.
The invention realizes the dynamic management of the participants in the fire safety protection activity, the omnibearing visual monitoring of the running state of the safety protection target and the flattening of the command scheduling by formulating a scheme according to experience by the common staff in the fire safety protection in the past and recommending an optimal scheme by machine learning and computer self-adaption in the process of manually allocating tasks. The invention analyzes the data of the real-time data and the historical data of the security target, focuses on the trend rule and supports the decision.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working processes of the units and modules in the system may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus/terminal device and method may be implemented in other ways. For example, the above-described embodiments of the apparatus/terminal device are merely illustrative, and for example, the division of the modules or units is only one logical division, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated modules/units, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, all or part of the flow of the method according to the embodiments of the present invention may also be implemented by a computer program, which may be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method embodiments may be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer readable medium may comprise any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a Random Access Memory (RAM), an electrical carrier signal, a telecommunications signal, a software distribution medium, etc.
The foregoing embodiments are merely illustrative of the principles and utilities of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or change the above-mentioned embodiments without departing from the spirit and scope of the present invention. Accordingly, it is intended that all equivalent modifications or changes which can be made by those skilled in the art without departing from the spirit and technical spirit of the present invention be covered by the claims of the present invention.
Claims (10)
1. A security activity scheme generation method based on machine learning is characterized by comprising the following steps:
acquiring a plurality of security activity schemes to establish a machine learning training sample;
performing machine learning according to the machine learning training samples to generate one or more security activity models;
generating one or more predicted security activity solutions based on the one or more security models and candidate security activity solutions;
determining a target security activity scheme from the one or more predicted security activity schemes.
2. The machine learning-based security activity scheme generation method of claim 1, wherein generating one or more predicted security activity schemes based on the one or more security models and candidate security activity schemes comprises:
inputting the characteristics of the candidate security activity scheme into one or more security models, and outputting one or more predicted security activity parties, wherein the characteristics of the candidate security activity scheme at least comprise: activity type, scheme level, security location, participating security organization unit.
3. The machine learning-based security activity scheme generation method according to claim 1, wherein if there are a plurality of predicted security activity schemes, selecting a predicted security activity scheme with a maximum matching degree with the candidate security activity scheme as a target security activity scheme.
4. The machine learning-based security activity scheme generation method of claim 1, wherein the features of the security activity scheme comprise: the system comprises an activity type, a scheme grade, a security position, a security organization unit, a security organization architecture, a security worker task division, an emergency worker type, an emergency worker wearing device and a parking position, an emergency vehicle type and a parking position, an attack route and a linkage unit.
5. The machine learning-based security activity scheme generation method of claim 1, further comprising:
model parameters of one or more security activity models are adjusted.
6. A machine learning-based security activity scheme generation system, comprising:
the system comprises a sample construction module, a machine learning training module and a security activity analysis module, wherein the sample construction module is used for acquiring a plurality of security activity schemes so as to establish a machine learning training sample;
the model training module is used for performing machine learning according to the machine learning training samples to generate one or more security activity models;
a scenario generation module to generate one or more predicted security activity scenarios based on the one or more security models and candidate security activity scenarios;
a scheme determination module to determine a target security activity scheme based on the one or more predicted security activity schemes.
7. The machine learning-based security activity scheme generation system of claim 6, wherein if there are multiple predicted security activity schemes, selecting the predicted security activity scheme with the highest degree of matching with the candidate security activity scheme as the target security activity scheme.
8. The machine-learning based security activity scheme generation system of claim 6, wherein the security data comprises: activity type, scheme level, security location, participating security organization unit.
9. A machine learning based security activity management system, the management system comprising:
the scheme making end is used for generating one or more candidate security activity schemes by adopting the security activity scheme generating method according to any one of claims 1 to 4 and sending the one or more candidate security activity schemes to the task generating end;
the task generating end is used for determining a target security activity scheme based on one or more candidate security activity schemes, generating one or more security tasks based on the target security activity scheme, and distributing the one or more security tasks to the mobile application end;
the mobile application end is used for receiving the one or more security tasks and feeding back the completion condition of the one or more security tasks to the task generating end;
and the visualization end is used for displaying the target security activity scheme.
10. The machine-learning based security activity management system of claim 9, wherein the task live end employs a subscription mechanism of message queues for task distribution.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010001258.9A CN111178778A (en) | 2020-01-02 | 2020-01-02 | Security activity scheme generation method and system based on machine learning and security activity management system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010001258.9A CN111178778A (en) | 2020-01-02 | 2020-01-02 | Security activity scheme generation method and system based on machine learning and security activity management system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111178778A true CN111178778A (en) | 2020-05-19 |
Family
ID=70654426
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010001258.9A Pending CN111178778A (en) | 2020-01-02 | 2020-01-02 | Security activity scheme generation method and system based on machine learning and security activity management system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111178778A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112258068A (en) * | 2020-10-30 | 2021-01-22 | 武汉理工光科股份有限公司 | Security activity scheme generation and dynamic update method and device |
| CN112258367A (en) * | 2020-11-13 | 2021-01-22 | 珠海大横琴科技发展有限公司 | Monitoring processing method and device |
| CN112288155A (en) * | 2020-10-23 | 2021-01-29 | 云南昆船设计研究院有限公司 | Security plan generation scheduling method and system based on machine learning and collaborative filtering |
| CN113204916A (en) * | 2021-04-15 | 2021-08-03 | 特斯联科技集团有限公司 | Intelligent decision method and system based on reinforcement learning |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104680843A (en) * | 2013-11-29 | 2015-06-03 | 大连君方科技有限公司 | Tugboat cooperation scheme generation method based on artificial neural network |
| CN107133210A (en) * | 2017-04-20 | 2017-09-05 | 中国科学院上海高等研究院 | Scheme document creation method and system |
| CN107194542A (en) * | 2017-04-24 | 2017-09-22 | 深圳市龙岗远望软件技术有限公司 | On-site emergency disposal method, system and moving emergency server |
| CN110084374A (en) * | 2019-04-24 | 2019-08-02 | 第四范式（北京）技术有限公司 | Construct method, apparatus and prediction technique, device based on the PU model learnt |
| CN110188910A (en) * | 2018-07-10 | 2019-08-30 | 第四范式（北京）技术有限公司 | The method and system of on-line prediction service are provided using machine learning model |
-
2020
- 2020-01-02 CN CN202010001258.9A patent/CN111178778A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104680843A (en) * | 2013-11-29 | 2015-06-03 | 大连君方科技有限公司 | Tugboat cooperation scheme generation method based on artificial neural network |
| CN107133210A (en) * | 2017-04-20 | 2017-09-05 | 中国科学院上海高等研究院 | Scheme document creation method and system |
| CN107194542A (en) * | 2017-04-24 | 2017-09-22 | 深圳市龙岗远望软件技术有限公司 | On-site emergency disposal method, system and moving emergency server |
| CN110188910A (en) * | 2018-07-10 | 2019-08-30 | 第四范式（北京）技术有限公司 | The method and system of on-line prediction service are provided using machine learning model |
| CN110084374A (en) * | 2019-04-24 | 2019-08-02 | 第四范式（北京）技术有限公司 | Construct method, apparatus and prediction technique, device based on the PU model learnt |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112288155A (en) * | 2020-10-23 | 2021-01-29 | 云南昆船设计研究院有限公司 | Security plan generation scheduling method and system based on machine learning and collaborative filtering |
| CN112288155B (en) * | 2020-10-23 | 2022-12-09 | 云南昆船设计研究院有限公司 | Security plan generation scheduling method and system based on machine learning and collaborative filtering |
| CN112258068A (en) * | 2020-10-30 | 2021-01-22 | 武汉理工光科股份有限公司 | Security activity scheme generation and dynamic update method and device |
| CN112258367A (en) * | 2020-11-13 | 2021-01-22 | 珠海大横琴科技发展有限公司 | Monitoring processing method and device |
| CN113204916A (en) * | 2021-04-15 | 2021-08-03 | 特斯联科技集团有限公司 | Intelligent decision method and system based on reinforcement learning |
| CN113204916B (en) * | 2021-04-15 | 2021-11-19 | 特斯联科技集团有限公司 | Intelligent decision method and system based on reinforcement learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111178778A (en) | Security activity scheme generation method and system based on machine learning and security activity management system | |
| CN110782370A (en) | Comprehensive operation and maintenance management platform for power dispatching data network | |
| Martin et al. | The interactional affordances of technology: An ethnography of human-computer interaction in an ambulance control centre | |
| CN110599007A (en) | Project progress management system | |
| CN110570113A (en) | Work order processing method and system | |
| CN111445204A (en) | Work order processing method and device, storage medium and terminal | |
| CN110956402A (en) | Work order processing method | |
| CN110048897A (en) | A kind of intelligent network cutover centralized dispatching management system and method | |
| CN113239750A (en) | System, method, equipment and application for detecting personnel behaviors in electric power business hall | |
| CN109117526A (en) | One kind being suitable for mechanical system maintenance of equipment and guides data record and analysis system | |
| CN115795118A (en) | Information cooperative processing method and device for multi-source heterogeneous data | |
| CN116720720A (en) | Geotechnical engineering equipment interconnection scheduling management method and system | |
| CN114091944A (en) | Cloud-end-coordinated distribution network engineering field operation analysis decision system | |
| CN118014321A (en) | Event-driven public safety emergency treatment method and system | |
| CN110322218A (en) | Intelligent society insurance business operation and monitoring method and system | |
| CN116596281B (en) | Lightweight three-dimensional property management system | |
| CN113129469A (en) | Inspection monitoring method and system and computer readable storage medium | |
| CN110225294B (en) | Automatic video conference scheduling system | |
| CN116955304A (en) | Track traffic resource sharing and calling system based on cloud platform | |
| CN114118878B (en) | Online centralized quality analysis decision system based on hub detection and review framework | |
| CN115630818A (en) | Emergency management method and device, electronic equipment and storage medium | |
| CN116796947A (en) | Intelligent scheduling method for team management technicians | |
| CN115239179A (en) | Chemical production operation flow system | |
| JP2019209796A (en) | Operation schedule evaluation system and method for the same | |
| CN114037339A (en) | Event processing scheme scheduling system and method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 401329 No. 5-6, building 2, No. 66, Nongke Avenue, Baishiyi Town, Jiulongpo District, Chongqing Applicant after: MCC CCID information technology (Chongqing) Co.,Ltd. Address before: Building 1, No. 11, Huijin Road, North New District, Yubei District, Chongqing Applicant before: CISDI CHONGQING INFORMATION TECHNOLOGY Co.,Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200519 |