A method of test information formulation for an accident risk value test

Abstract

The present application relates to a kind of test information preparation methods of accident risk value test, which includes the following steps: S1, create the first test information database (Q1) for conducting instruction target test, the second test information database (Q2) for conducting equipment test and the third test information database (Q3) for conducting environment test;S2, the test item of the second test information database (Q2) is provided in data and signaling mode to the control unit of at least one training life-related equipment in the specified area to be evaluated accident risk value;S3, the test item of the third test information database (Q3) is provided in data and signaling mode to the control unit of at least one training life-related working equipment in the specified area to be evaluated accident risk value, also in parallel, at least one control unit of training life-related monitoring device is provided in data and signaling mode.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of group safety management system, and in particular to a test information preparation method for accident risk value test. BACKGROUND

[0002] In the information age, mobile Internet, cloud computing, Internet of Things and big data technology have been widely applied, and the explosive growth of data and the expansion of value will have a profound impact on the future development of groups. Group members will use various targeted business tools in their daily work, training, life and study, but the above data are independent of each other, and the data content and format differ greatly. Over time, although a lot of data has been accumulated, comprehensive information cannot be quickly and transparently obtained. Therefore, it is urgent to establish an accurate big data platform for various basic businesses of the group as soon as possible.

[0003] The patent document with publication number CN105357061A discloses an operation and maintenance monitoring analysis system based on big data stream processing technology. The system includes a monitoring end for obtaining monitoring data in the client and sending it to the storage end; a storage end for saving multiple early warning processing rules, multiple data mining rules and historical records; a cache end for synchronizing the early warning processing rules, data mining rules and historical records saved in the storage end to the cache end according to the preset time interval, and receiving the monitoring data stream sent by the monitoring end; a first processing group for early warning monitoring alarm analysis according to the early warning rules, historical records and monitoring data stream; a second processing group for data mining analysis according to the data mining rules, historical records and monitoring data stream, and outputting monitoring statistical analysis according to the analysis results.

[0004] The patent document with publication number CN111914004A discloses a learning warning method and system based on a data mining algorithm and a storage medium. The method includes the following steps: converting campus big data into the same data format by data cleaning; classifying the cleaned campus big data and adding corresponding classification labels; performing principal component analysis on data with different classification labels to obtain multiple characteristic factors related to the score; inputting the obtained characteristic factors into a pre-trained score prediction model to predict the scores of each student; and marking the student as a learning warning if the student's score is lower than the warning value. The present application fully mines campus big data through data cleaning and principal component analysis, breaks down data silos, and then comprehensively analyzes the learning situation of each student to facilitate teachers to give personalized teaching guidance.

[0005] The prior art can only analyze a single dimension of data source, and cannot analyze and manage multi-dimensions of data which are independent of each other and have great differences in data content and format, so a multi-dimensional data collection scenario that fits a group is needed to help decision makers make reasonable suggestions and decisions on the safety management of the group, the daily equipment and facility management of the group, and the comprehensive quality management of the instruction target, especially to help behavioral individuals or units to make targeted comprehensive evaluation and training planning.

[0006] In addition, on the one hand, there are differences in the understanding of those skilled in the art; on the other hand, the inventors have studied a large number of literatures and patents when making the present invention, but due to the limited space, all the details and contents are not listed in detail, which does not mean that the present invention does not have the characteristics of the prior art, on the contrary, the present invention has all the characteristics of the prior art, and the applicant reserves the right to add relevant prior art in the background art. SUMMARY

[0007] In view of the deficiencies of the prior art, the present application can obtain all-around data from a plurality of third-party data collection systems of a big data network platform, and establish different analysis models according to actual application requirements, fit business scenarios, and provide scientific basis and rationalization suggestions for decision-making and daily work of decision makers.

[0008] The technical scheme of the present application provides a test information preparation method for accident risk value test, which comprises the following steps: S1, creating a first test information database for instruction target test, a second test information database for equipment test, and a third test information database for environment test; S2, the test items of the second test information database are provided in data and signaling mode to the control unit of at least one training life-related device in the specified area to be evaluated for accident risk value; S3, when the test items of the third test information database are provided in data and signaling mode to the control unit of at least one training life-related work device in the specified area to be evaluated for accident risk value, they are also provided in data and signaling mode to the control unit of at least one training life-related monitoring device in parallel.

[0009] According to a preferred embodiment, step S1 at least comprises the following operations:

[0010] S1.1, when creating the first test information database for instruction target test, a first screening is performed on the instruction target in the specified area to be evaluated for accident risk value, and test information with test results conforming to normal distribution is selected to create the first test information database;

[0011] S1.2, the test information in the first test information database is secondly filtered according to the equipment usage in the training of the instruction target, and the test information with normal distribution is selected to create the second test information database;

[0012] S1.3, the test information in the second test information database is thirdly filtered according to whether the instruction target can complete the training by using the equipment under the specified environmental condition, and the test information with normal distribution is selected to create the third test information database.

[0013] According to a preferred embodiment, the first test information database is created by setting at least seven dimensions of thought, safety skill, theory, physical training, daily management, teaching self-study and special training after analyzing the accident risk value, and setting a group of test information for each of the seven dimensions to form the first test information database.

[0014] According to a preferred embodiment, the test information content of the seven dimensions includes specific items of test information and item archives for classifying and recording the behavior data of the instruction target in completing the test items, and the instruction target and the item archive data contained in the first test information database are based on the multiple behavior data of the instruction target in a certain period of time to filter the specified target in the specified area with accident risk to be evaluated, so as to filter the instruction target which can complete the test items in the specified area with accident risk to be evaluated.

[0015] According to a preferred embodiment, the stimulus information is sorted and stored in the archive unit according to the type and / or format of the stimulus information, and the first test information database, the second test information database and the third test information database are filtered multiple times according to different filtering conditions to filter the instruction target which can complete the test items by using the specific equipment under the specified environment.

[0016] According to a preferred embodiment, the behavior data of the instruction target is mined by the first data mining analysis module, and the decision maker screens the multi-dimensional behavior data associated with the instruction target by the second data mining analysis module, and establishes a multi-dimensional behavior data model of the instruction target by the preset weight configuration rule and the screened multi-dimensional behavior data within at least part of the time interval, so as to generate a comprehensive evaluation report of the instruction target by the multi-dimensional behavior data model taking the preset weight configuration rule as a framework basis. The advantage is that the security management system classifies and induces the behavior data of different dimensions twice, so that the decision maker can evaluate the comprehensive situation of the instruction target by the multi-kind of low correlation behavior data of the instruction target within the group, so that the comprehensive evaluation report of the instruction target generated by the security management system has the comprehensiveness of data, the evaluation result is fully supported by data, the accuracy of the evaluation is improved, the decision maker can make targeted guidance and planning for the instruction target (behavior individual or behavior unit) according to the comprehensive evaluation report, and the instruction target is promoted to quickly determine a reasonable development direction.

[0017] According to a preferred embodiment, the second data mining analysis module can compare the comprehensive evaluation report generated by the multi-dimensional behavior data model with the reference data model generated by the security management system in advance by using the test data, so as to evaluate the behavior safety of the instruction target; the second data mining analysis module generates at least one kind of prediction information of behavior data associated with the comparison result according to the comparison, or calls the prediction information of at least one kind of behavior data associated with the comparison result in the database, so as to display the obtained prediction information by the display terminal, so that the decision maker can manage the behavior safety of the instruction target according to the prediction information.

[0018] According to a preferred embodiment, the multi-dimensional behavior data mined by the first data mining analysis module from the security management system is classified and recorded by using a plurality of archive units, wherein any archive unit independently records the behavior data of a single dimension stored by the security management system, and the archive unit updates the recorded behavior data in real time; the archive unit also associates the recorded behavior data with the behavior individual or behavior unit generating the behavior data.

[0019] According to a preferred embodiment, the mining of the multi-dimensional behavior data by the first data mining analysis module is a secondary classification and collection of the behavior data classified and recorded by the security management system in a dimension division manner by using the archive unit, wherein the secondary classification and collection refers to reclassifying and summarizing the behavior data recorded by different archive units according to the differences of the behavior individual or behavior unit associated with the behavior data.

[0020] According to a preferred embodiment, the second data mining analysis module screens the behavior data associated with the instruction target from the behavior data mined by the first data mining analysis module and subjected to the secondary classification and collection processing using a plurality of single basic information of the instruction target as the search basis, and the second data mining analysis module performs secondary screening on the screened behavior data associated with the instruction target according to the time interval determined by the decision maker.

[0021] According to a preferred embodiment, the preset weight configuration rule refers to the relationship between the different dimension behavior data input by the decision maker in advance into the security management system through the display terminal and the comprehensive quality data of the instruction target, so that the second data mining analysis module establishes the multi-dimension behavior data model of the instruction target by filling the multi-dimension behavior data associated with the instruction target within at least part of the time interval screened by it into the relationship.

[0022] According to a preferred embodiment, the decision maker determines the weight occupied by the different dimension behavior data according to the correlation degree between the different dimension behavior data of the instruction target within at least part of the time interval that can be monitored by the security management system and the comprehensive quality data in the comprehensive evaluation report to be generated, so that the decision maker can formulate the weight configuration rule with different weight values corresponding to the different dimension behavior data.

[0023] According to a preferred embodiment, the prediction information of the behavior data generated or called by the second data mining analysis module is the historical data set information or the pre-recorded test data set information of the behavior individual or behavior unit recorded by the security management system. BRIEF DESCRIPTION OF DRAWINGS

[0024] Fig. 1 is a preferred workflow schematic diagram of the test information preparation method of the accident risk value test proposed by the present application;

[0025] Fig. 2 is a preferred database creation step schematic diagram of the test information preparation method of the accident risk value test proposed by the present application;

[0026] Fig. 3 is a normal distribution diagram satisfied when the test information of the preferred test information preparation method of the accident risk value test proposed by the present application is screened.

[0027] LIST OF REFERENCE NUMBERS

[0028] 1: archive unit; 2: first data mining analysis module; 3: second data mining analysis module; 4: display terminal; Q1: first test information database; Q2: second test information database; Q3: third test information database. DETAILED DESCRIPTION

[0029] The application will be described in detail below with reference to the accompanying drawings.

[0030] The test information preparation method of the accident risk value test provided by the application can be connected with other third-party data collection systems, so as to obtain safety record data of a group (for example, data such as attendance, going out, returning, drill, life system, boundary warning and patrol record of personnel of the group), and further establish an activity archive of the group and analyze safety management problems of the group. The application can also comprehensively analyze abnormal distribution locations, time periods, personnel and belonging institutions of safety data of various groups, and give early warning and reminders for abnormal conditions. In addition, the application can also provide emergency process management for decision makers of the group, and the decision makers can set emergency processes (the processes include conditions such as equipment (device) fixed point, personnel fixed point, administrator login in position, material in position) according to actual needs, and estimate the emergency exercise process and results in combination with vehicle and material equipment data of the group.

[0031] Embodiment 1

[0032] The embodiment provides a test information preparation method of an accident risk value test, which comprises an archive unit 1, a first data mining analysis module 2, a second data mining analysis module 3, a display terminal 4 and a plurality of data processing modules capable of supporting safety management of a group by a safety management system. The modules mentioned in the embodiment can be hardware, software or combined data processors capable of executing related steps thereof, and a certain method step corresponding to a certain module can also be split into a plurality of method steps and executed by a plurality of modules. In the case of no conflict or contradiction, the whole and / or part of the preferred embodiments of other embodiments can be supplemented as the embodiment.

[0033] According to Figs. 1-3 According to a specific embodiment shown, a test information preparation method of an accident risk value test comprises the following steps:

[0034] S1, creating a first test information database Q1 for performing instruction target test, a second test information database Q2 for performing equipment test and a third test information database Q3 for performing environment test;

[0035] S1.1, in creating the first test information database Q1 for the instruction target test, a first screening is performed on the instruction targets within the specified area to be evaluated for the accident risk value, and test information with test results conforming to a normal distribution is selected to create the first test information database Q1;

[0036] S1.2, a second screening is performed on the instruction targets within the specified area to be evaluated for the accident risk value according to the equipment usage of the instruction targets during training, and test information with test results conforming to a normal distribution is selected to create the second test information database Q2;

[0037] S1.3, a third screening is performed on the instruction targets within the specified area to be evaluated for the accident risk value according to whether the instruction targets can complete the training using the equipment under the specified environmental conditions, and test information with test results conforming to a normal distribution is selected to create the third test information database Q3.

[0038] S2, the test items of the second test information database Q2 are provided in a data and signaling manner to the control unit of at least one equipment related to the training life within the specified area to be evaluated for the accident risk value.

[0039] S3, when the test items of the third test information database Q3 are provided in a data and signaling manner to the control unit of at least one working equipment related to the training life within the specified area to be evaluated for the accident risk value, they are also provided in a data and signaling manner to the control unit of at least one monitoring device related to the training life in parallel.

[0040] Preferably, the archive unit 1 classifies and stores the behavior data of different dimensions of the group acquired by the security management system from other third-party data collection systems into different locations or storage sub-units according to the dimensions to which the behavior data belongs. The first data mining analysis module 2 can mine the behavior data of different dimensions belonging to different groups, individuals or equipment facilities from the different dimension behavior data classified and stored by the archive unit 1. The first data mining analysis module 2 can classify the behavior data it mines in a secondary classification manner and aggregate the behavior data after secondary classification into a behavior data set. The second data mining analysis module 3 can separately filter out all the behavior data related to the instruction target within a specific time interval from the behavior data set aggregated by the first data mining analysis module 2 based on the basic information of the instruction target selected by the decision maker. The second data mining analysis module 3 can establish a multi-dimensional behavior data model that can be used to evaluate the comprehensive situation of the instruction target within a specific time interval using the behavior data it filters out. Preferably, the multi-dimensional behavior data refers to behavior data of different dimensions. The decision maker can input the weight configuration rule that is the framework basis of the multi-dimensional behavior data model through the display terminal 4. The weight configuration rule can represent the degree of association between the behavior data of different dimensions and the comprehensive situation of the instruction target, so as to determine the weight of different behavior data in generating the comprehensive evaluation report of the instruction target according to the influence degree of different behavior data on the instruction target. The present application classifies and induces the behavior data of different dimensions, so that the decision maker can use the multi-association low behavior data of the instruction target within the group to evaluate the comprehensive situation of the instruction target, so that the comprehensive evaluation report of the instruction target generated by the security management system has the comprehensiveness of data, and the evaluation result can be fully supported by data, which improves the accuracy of the evaluation, and facilitates the decision maker to make targeted guidance and planning for the instruction target (behavior individual or behavior unit) according to the comprehensive evaluation report, and promotes the instruction target to quickly determine the reasonable development direction. Preferably, the instruction target can be a behavior individual or a behavior unit, wherein the behavior individual can be any personnel, teacher or student in the group.

[0041] Preferably, the first data mining analysis module 2 mines the multi-dimensional behavior data stored in the safety management system by means of automatic monitoring or data scanning. Preferably, the multi-dimensional behavior data mined by the first data mining analysis module 2 is classified and stored in the safety management system by the plurality of archive units 1. When the safety management system obtains behavior data from other third-party data collection systems, it is classified and stored according to the different dimensions of the behavior data, thereby forming multi-dimensional behavior data, i.e., the safety management system classifies and stores behavior data according to the different sources of the behavior data (representing the terminal collection equipment of the third-party data collection system). For example, one archive unit 1 stores the use records of all personnel using the same device or the same training field at different times. Preferably, the different dimensions of the behavior data mean that there is no data correlation between different behavior data except for the time sequence relationship due to the different terminal collection equipment or training equipment generating the behavior data. For example, there is no intuitive connection between the use data collected by the training field use record system and the sleep condition data collected by the sleep monitoring system installed in the dormitory. Preferably, any archive unit 1 only stores the behavior data collected by one terminal collection equipment received by the safety management system. The archive unit 1 updates the behavior data recorded by it in real time. Preferably, the terminal collection equipment that obtains behavior data collects data in real time and continuously, so the data transmitted to the safety management system is also continuously increasing, and therefore the archive unit 1 needs to continuously update or increase the behavior data stored by it. The behavior data stored by the archive unit 1 can be recorded when multiple individuals or units use the same training equipment, and therefore the archive unit 1 also associates the behavior data generated by the training equipment at different time points / time periods according to the different instruction targets (behavior individuals or behavior units) with the basic information of the instruction target, so that the first data mining analysis module 2 mines the behavior data generated by different terminal collection equipment associated with the instruction target according to the basic information of the instruction target. Preferably, the mining of multi-dimensional behavior data by the first data mining analysis module 2 is a secondary classification and collection of behavior data classified and recorded by the safety management system in a dimensionally divided manner by the archive unit 1. Preferably, the secondary classification and collection means reclassifying and summarizing the behavior data recorded by different archive units 1 according to the different behavior individuals or behavior units associated with the behavior data. The behavior data recorded by the archive unit 1 is classified and stored according to the different terminal collection equipment. In order to facilitate the second data mining analysis module 3 to mine the behavior data of a specified instruction target, the first data mining analysis module 2 performs secondary classification processing on the behavior data mined from the archive unit 1, so that behavior data of different dimensions is collected in different subgroups of behavior individuals or behavior units according to the different behavior individuals or behavior units associated with the behavior data.Preferably, the secondary classification aggregation refers to the classified data being split and aggregated into different data sets according to different classification methods. Preferably, the data sets aggregated secondarily can be arranged according to the order of collection time.

[0042] Preferably, the second data mining analysis module 3 filters the multi-dimensional behavior data associated with the instruction target in response to the instruction of the decision maker. The second data mining analysis module 3 can retrieve the multi-dimensional behavior data associated with the instruction target from the behavior data secondarily classified and aggregated by the first data mining analysis module 2 according to the basic information of the instruction target. Preferably, the second data mining analysis module 3 can also establish the multi-dimensional behavior data model of the instruction target according to the preset weight configuration rule and the filtered multi-dimensional behavior data within a time interval, so that the second data mining analysis module 3 generates the comprehensive evaluation report of the instruction target by using the multi-dimensional behavior data model. Preferably, the decision maker determines the weight of the different dimensional behavior data according to the correlation between the different dimensional behavior data of the instruction target recorded by the security management system within a time interval and the comprehensive quality data of the comprehensive evaluation report to be generated, so that the decision maker can formulate the weight configuration rule that the weight values corresponding to the different dimensional behavior data are different. The second data mining analysis module 3 further filters the retrieved behavior data by limiting the collection time of the behavior data, so as to obtain all the behavior data of the instruction target within a time interval. For example, the time and performance of all the devices or venues used by a behavior individual for training within a week. Preferably, the length of the time interval is selectively formulated according to the needs of the decision maker. Preferably, the behavior individual can be any member in the group, and the behavior unit can be the whole group or a small group.

[0043] Preferably, the second data mining analysis module 3 can compare the comprehensive evaluation report generated by it through the way of establishing a multi-dimensional behavior data model with the reference data model generated in advance by the safety management system using test data, so as to realize the evaluation of the behavior safety of the instruction target. Preferably, the test data of the safety management system can be a complete historical data of other behavior individuals or behavior units, or reference data loaded from other systems, or standard reference data obtained by big data analysis method. Preferably, the reference data model refers to the data model established by using test data and the same weight configuration rule, and the comprehensive evaluation data and the comprehensive evaluation report output by the data model are the comprehensive evaluation reference data and the comprehensive evaluation reference report. Preferably, the decision maker can evaluate the behavior safety of the instruction target by comparing the comprehensive evaluation report generated by the behavior data of the instruction target with the comprehensive evaluation reference report. Preferably, the evaluation of the behavior safety can refer to the judgment of whether the quality elements such as daily work, training, life, study and physical condition of the instruction target are reasonable. Preferably, the second data mining analysis module 3 retrieves at least one prediction information of the behavior data associated with the comparison result from the database according to the above comparison result, so as to display the obtained prediction information by the display terminal 4, so that the decision maker can manage the behavior safety of the instruction target according to the prediction information.

[0044] Preferably, the prediction information of the behavior data retrieved by the second data mining analysis module 3 is selected from the historical data set data or the pre-entered test data set data recorded by the safety management system. Preferably, the historical data set can be a complete historical data of other behavior individuals or behavior units. Preferably, the test data set is a summary of the aforementioned test data. Preferably, the second data mining analysis module 3 can compare the comprehensive evaluation report generated by it through the way of establishing a multi-dimensional behavior data model with the reference data model generated in advance by the safety management system using test data, so as to realize the evaluation of the behavior safety of the instruction target. Preferably, the prediction information refers to the analysis and prediction of the real-time condition and future behavior safety of the instruction target by using the historical behavior data corresponding to the behavior data of the instruction target in the historical data set, so as to facilitate the decision maker to make targeted guidance and planning for the instruction target (behavior individual or behavior unit) according to the comprehensive evaluation report, and promote the instruction target to quickly determine a reasonable development direction.

[0045] The second data mining analysis module 3 screens the behavior data associated with the instruction target from the behavior data classified and collected by the first data mining analysis module 2 by using a plurality of single basic information of the instruction target as the search basis, and the second data mining analysis module 3 performs secondary screening on the screened behavior data associated with the instruction target according to the time interval determined by the decision maker. Preferably, the single basic information can be the name, number and other basic information with single characteristics of the instruction target. Preferably, the preset weight configuration rule is that the decision maker inputs the relationship between the behavior data of different dimensions of the safety management system and the comprehensive quality data of the instruction target in advance by using the display terminal 4, so that the second data mining analysis module 3 establishes a multi-dimensional behavior data model of the instruction target by filling the multi-dimensional behavior data associated with the instruction target within a time interval into the relationship. The multi-dimensional behavior data model is constructed by combining the preset weight configuration rule with the multi-dimensional behavior data, and the comprehensive evaluation report is directly generated according to the preset weight configuration rule and the multi-dimensional behavior data.

[0046] Embodiment 2

[0047] This embodiment is a further improvement of embodiment 1, and the repeated contents will not be described again.

[0048] Preferably, the test information preparation method of the accident risk value test can also be composed of a data comprehensive display module, an ability support module and a business application module. The data comprehensive display module can classify and display the indicators and dimensions of the data of the business system of the group, help the instruction target observe and analyze the data from different angles, and focus on the trend of the data. The data comprehensive display module can also display the calculation and analysis results of different models, and can view through according to multiple dimension conditions. In addition, the data comprehensive display module can also monitor and analyze the data associated with it by establishing an early warning index or model, thereby establishing an early warning mechanism based on data mining. When the real-time data reaches the predetermined limit value or is abnormal, the safety management system will automatically issue an alarm, and the safety management system supports the limitation of alarm threshold, confidence threshold and other set values. Preferably, the safety management system supports a plurality of data screening methods, including field query, map circle selection, point selection, etc. Preferably, the ability support module can process data by reading all-around data and summarizing the processed data. The ability support module can also interact with data by selectively developing different types of data ports and feeding back the operation results in real time. Preferably, the decision maker can also customize the parameter weight of the application model established for each business involved in the safety management system, so that each model has a growth factor, and the model can be corrected according to the model output result.

[0049] Preferably, the business application module at least includes a flight personnel comprehensive capability data application, a personnel comprehensive quality data application, a support quality data application, an equipment failure hidden danger data application, a flight environment factor data application, a flight safety risk data application, a group safety management data application, and a comprehensive evaluation data application. Preferably, the flight personnel comprehensive capability data application is to analyze various data of the instructors and the students comprehensively, obtain individual advantages and disadvantages, comprehensive evaluation, and periodically give the analysis results of development direction and leak repair. The flight personnel comprehensive capability data application can also automatically generate the score of the individual, the unit, and the whole group.

[0050] Preferably, the personnel comprehensive quality data application includes a self-defined examination question and a self-defined score weight, an examination system for respectively examining the instructors and the students, and automatically generates the score of the individual and the unit. Based on the examination, the development direction and the deficiencies of the students are analyzed from the comprehensive data of the students, such as ideology, technology, safety skills, theory, physical training, daily management, teaching and self-study, and special training, and historical data. Preferably, the support quality data application analyzes a single item and multi-dimensional items of the equipment (attendance rate, perfect rate, maintenance quality, failure rate, etc.), reflects the comprehensive state of the equipment (perfect condition, historical data, etc.), and in combination with the work training scene, real-time prompts the instructors and the members whether the work training can be carried out. Preferably, the equipment failure hidden danger data application compares the flight parameters, the pilot feedback problems, and the support quality data, compares the same type of equipment data, and analyzes the common problems. Preferably, the flight environment factor data application models and analyzes the meteorological information, geographical information, terrain information, electromagnetic interference, flight activities, and site conditions before flight, and after the pilot selects the area, time, and height, the related prompts for the flight of the day are given. Preferably, the flight safety risk data application connects the flight safety evaluation plan implementation system and the copy flight safety dynamic monitoring data, comprehensively analyzes the flight cycle of the flight camp, generates a safety evaluation report, and analyzes each item in detail. Preferably, the group safety management data application analyzes the various data of the group safety management in real time, finds out the problems of the single aspect of the group safety and the trend of the concentrated stage development, gives early warning to the high-frequency and sudden problems, and comprehensively masters the change of the unstable factors of the group. Preferably, the comprehensive evaluation data application analyzes and evaluates the comprehensive combat capability of the whole brigade through the analysis of the above various data, and better provides auxiliary decision-making for the talent training, combat force adjustment, various unstable factor governance, and task execution of the whole brigade.

[0051] Preferably, the behavior data mining and retrieval operation of the first data mining analysis module 2 and the second data mining analysis module 3 is based on the text features of the retrieval request or retrieval target, uses a retrieval engine and a machine learning model to retrieve a retrieval result based on the text features, and combines a text feature retrieval method to associate knowledge based on a knowledge graph, perform knowledge reasoning based on a business target, and perform calculation based on graph calculation, machine learning and the like to obtain personnel multi-dimensional intelligent retrieval. Preferably, the retrieval dimensions include basic information, skill information, qualification ability, technical ability and professional inclination, etc. Preferably, the retrieval operation can also be based on personnel basic attributes, associated events (training, examination, simulation exercise, etc.), associated equipment (driven aircraft, trained equipment, etc.) to perform reasoning and display, further deep, multi-dimensional and intuitive to display personnel retrieval information.

[0052] Preferably, the safety management system establishes a personnel data tag system through the development of a personnel holographic multi-dimensional portrait tag system on the basis of a big data platform, integrates calculation of basic information, ideology, technology, safety skills, theory, physical training, daily management, teaching self-study and training of various personnel to construct a personnel information holographic knowledge graph, and on the basis thereof, combines artificial intelligence natural language technology to realize automatic evaluation and tagging of business quality, technical ability, safety skills, training achievements and teaching quality of personnel, form a 360-degree holographic portrait of personnel, support personnel selection and management analysis in training, examination training and simulation exercise and the like, improve training effect, and provide data support for long-term planning of training. A tag system construction, tag management, personnel portrait, tag application, effect evaluation tag construction closed loop covering the personnel holographic portrait evaluation is also established in the safety management system, and the landing of the precise scene based on the tag system empowers teaching training management. Preferably, the safety management system also carries out a life cycle management process of tag creation, review, release, evaluation, deactivation and optimization, realizes full life cycle management of personnel tags, guarantees efficient and stable and practical and effective personnel tags, and realizes periodic evaluation and tag version management of the tags through the life cycle management of the tags, guarantees adaptability of the tags to various scene analysis, and supports rapid landing of various tag operation organizational structures (strong matrix, balanced matrix and weak matrix).

[0053] Preferably, the present application can dynamically manage the label indicators. Specifically, the dynamic management of the label indicators includes traditional statistical analysis model management and big data analysis model management. The traditional statistical analysis model aggregates the labels of the statistical results by constructing the label indicators in multiple dimensions; the big data analysis model classifies and organizes the data features by extracting the data features describing the overall picture of the personnel, thereby forming the big data analysis labels. The present application realizes the dynamic management of the label indicators by defining the label rules (statistical analysis or calling the big data model). Preferably, the safety management system of the present application can also construct the group portrait of the personnel, show the group label situation of the examiners, instructors and the like, realize the rapid identification of the group characteristics of the personnel, assist the professional departments in formulating the differentiated management strategies for different groups of the personnel, and guide the preparation of appropriate teaching, training and logistics support schemes. The individual portrait of the personnel is constructed based on the information such as the qualifications and abilities, technical abilities, professional tendencies of the examiners or students, and the individual portrait of the personnel is constructed from the dimension of personnel management, and the personnel information is fully displayed from the specific grading evaluation indicators.

[0054] Preferably, the main basis data sources of the comprehensive evaluation report of the present application include the instructor data information and the student data information. The instructor data information includes the navigation knowledge score, the senior instructor evaluation, the performance of the affiliated students, the number of special situation disposal, and the number of flights and flight quality (assessment score and comprehensive flight parameters). The student data information includes the navigation knowledge score, the test score, the instructor evaluation, and the flight score. The present application can perform trend analysis on the students, instructors and the like, facilitate the decision makers to master the performance changes of the students, and thereby provide data support for the decision makers to select the best teaching methods, intensities, frequencies and combinations. The safety management system of the present application also opens a data interface which can provide auxiliary decision information to other programs.

[0055] Preferably, the comprehensive quality data refers to the summary of the information of the ideology, technology, safety skills, theory, physical training, daily management, teaching and self-study, and training of each personnel. The present application can perform single-direction analysis and multi-direction comprehensive analysis on each personnel, thereby reflecting the outstanding ability points and ability short boards of each flight personnel, and providing a basis for the cultivation planning of the comprehensive ability of each flight personnel; meanwhile, the present application also finds the advantages and short boards of the units by historical data analysis and multi-dimensional analysis at the unit level.

[0056] Preferably, the data recorded by the archive unit 1 can also be the thought information, technical information, safety skill information, theory information, physical training information, daily routine information, teaching and self-study information, training information, attendance information and group comprehensive management system data of each person. Preferably, the safety management system provides a function of setting the weight of each parameter, so that the safety management system can sort the different attributes of the person or the organization according to the weight configuration given by the decision maker, so that the terminal 4 can display the following contents:

[0057] Present the change trend of the person in the same professional direction, different periods and different abilities, and provide mutation prompt;

[0058] Present the performance of the person in the same period and different abilities, and provide advantages and disadvantages prompt;

[0059] Present the average performance of the organization in the same period and various aspects of work, and provide advantages and disadvantages prompt;

[0060] Present the change trend of the organization in the same work aspect and different periods, and provide mutation prompt.

[0061] Embodiment 3

[0062] This embodiment is a further improvement of embodiment 1, and the repeated contents will not be described again.

[0063] The safety management system sorts and classifies the personnel data, equipment data and environment data collected by different terminal collection devices. Preferably, the real-time state of the person is preliminarily judged by analyzing the personnel data, and whether the person can have the task execution ability or can be judged to have the enhanced training according to the judgment result and the real-time personnel state detection data. Preferably, when analyzing the personnel data, the actual use condition of the equipment is also judged by analyzing the equipment data, so as to ensure that the equipment can meet the needs of the personnel use while the personnel have the corresponding ability. In addition, when a suitable person (instruction target) is needed to execute a specific task or training, the environment of the area where the task or training is located also needs to be analyzed, so as to further screen the personnel in the group.

[0064] Preferably, the personnel data, the equipment data and the environment data can be used as three types of screening conditions for screening personnel from a group, so as to screen the best personnel who can complete a specific task or evaluate the success rate of different personnel in performing a specific task. Preferably, the personnel data can be basic information, thoughts, technical skills, safety skills, theories, physical training, daily management, teaching and self-study, training, and the like of various personnel. Preferably, the equipment data can be the type, model, purchase date, acquisition method, scrap time limit, validity period, use unit, user, custodian, storage location, and note information of the equipment. Preferably, the note information can be used to record the maintenance and abnormal work of the equipment and the like. Preferably, the environment data can be the weather forecast, geographic information, site conditions, obstacle distribution, electromagnetic interference, flight activities, and the like of the flight area. When the personnel in the group need to perform flight training, the weather forecast, geographic information, site conditions, obstacle distribution, electromagnetic interference, flight activities, and the like of the flight area are comprehensively collected, and the flight environment of the flight area is comprehensively analyzed, so as to find out the environmental factors that may affect the implementation of the flight and the safety of the flight, provide a basis for targeted prevention measures, implementation schemes and plan making, and be beneficial to improving the training quality and ensuring the safety of the flight. In the case of analyzing the environment data, the recent training state of the personnel and the use state of the equipment are analyzed by using the personnel data and the equipment data, so as to evaluate the risk of whether different personnel in the group can participate in the flight task, and thus select the appropriate personnel to perform the flight task.

[0065] Preferably, the embodiment further provides a safety score processing method, comprising: determining a historical ability index, a historical physiological index, a historical psychological index, a real-time psychological index and a real-time physiological index of a to-be-evaluated personnel according to to-be-evaluated personnel data, and further obtaining a personnel score therefrom. Determining a historical performance index and a current performance index of a to-be-evaluated equipment according to to-be-evaluated equipment data, and further obtaining an equipment score therefrom. Determining a task difficulty score associated with the to-be-evaluated personnel and the to-be-evaluated equipment according to to-be-performed task data, the historical ability index of the to-be-evaluated personnel and the to-be-evaluated equipment data. Determining an environment score associated with the to-be-performed task and the to-be-evaluated equipment according to environment data of the to-be-performed task, the to-be-evaluated equipment data and the to-be-performed task data. Based on a preset score rule, determining a safety score of the to-be-evaluated personnel in performing the to-be-performed task under the environment condition of the to-be-performed task according to the personnel score, the task difficulty score and the environment score. Wherein, only when the safety score is higher than a preset safety threshold, the to-be-evaluated personnel is allowed to perform the task to ensure that the to-be-performed task can be safely performed by the to-be-evaluated personnel in the environment of performing the task.

[0066] The personnel data includes basic information, ideology, technical skills, safety skills, theory, physical training, historical evaluation results, historical ideology assessment, historical psychological assessment, historical task completion, simulation theory test, simulation practical test, and current physical assessment. The personnel data is managed through dynamic tag closed loop management, and a precise data tag system is established through tag creation, review, release, evaluation, and disablement. The tag system is dynamically managed through indexes, including: constructing tag indexes through multiple dimensions, and summarizing into statistical result tags; a big data analysis model extracts various data characteristics describing the overall picture of the personnel, classifies and organizes the data characteristics in combination with the analysis target, and forms a big data analysis tag. The tag indexes are dynamically managed through defining tag rules (statistical analysis or calling a big data model), updating frequency, and updating task start scheduling. The group portrait of the personnel is constructed to quickly identify the group characteristics of the personnel, assist professional departments in formulating differentiated management strategies for different groups of personnel, and construct individual portraits of the personnel based on information such as the qualifications and abilities of the personnel, technical abilities, and professional tendencies.

[0067] The to-be-evaluated equipment data includes equipment usage plan quantity, attendance quantity, fault quantity, personnel usage plan quantity, attendance quantity, historical maintenance index, factory performance record, spare part replacement record, and spare part performance record. The equipment performance data is associated with at least temperature, humidity, wind speed, and air oxygen content.

[0068] Preferably, the environmental data includes regional weather forecast, geographic information, site conditions, obstacle distribution, electromagnetic interference, and flight activities. For various types of environmental data, GIS is used to present risk factors in the form of regional coloring, etc., to intuitively indicate the risk level of the region. Moreover, for a single task, the weight can be changed according to the score of the to-be-evaluated personnel, so that the same environmental factor presents different risk levels for personnel with different characteristics; and as time passes and environmental factors change, the risk level will change.

[0069] Preferably, after each task execution is completed, a task completion score is determined according to the task completion, and the preset scoring rules are adjusted based on the comparison and matching of the task completion score and the safety score. For example, when the difference between the task completion score and the safety score is greater than a preset accuracy threshold, a warning is issued and the relevant management personnel is informed to adjust and verify the preset rules. The personnel data and the equipment data are updated based on the task completion score. The task completion includes completion time, action accuracy, route accuracy, actual danger number during the task, and danger value of each danger.

[0070] Preferably, the safety management system uses collected real-time equipment data (aircraft usage data and maintenance data) and real-time environmental data to conduct targeted analysis and assessment of safety risk points, thereby identifying possible safety hazards, and focusing on special assessments of flight safety risks during important periods such as special periods and major tasks, thereby helping to reduce safety hazards.

[0071] Preferably, flight safety analysis refers to the use of comprehensive flight record data, equipment maintenance and use record data, flight personnel comprehensive numerical data and the flight environment data of the flight to screen for potential risks in the flight mission, thereby providing protection for the flight safety of the flight personnel. Preferably, the safety management system also has a rehearsal function for risk assessment of set flight activities. Based on personnel data, equipment data, and existing flight environment data, the specific safety management system provides personnel with the possible risk situations that may arise when executing designated flight projects under hypothetical conditions, thereby conducting risk simulation and prediction of flight activities that group personnel need to perform in major projects and important seasons.

[0072] Preferably, in use, the decision maker can select the aircraft model, the flight personnel, the flight date, the flight area, the flight route and the high-difficulty subject in the safety management system, and the safety management system will give the risk assessment value of the flight personnel in the specified time for the flight project, so as to provide a reference for the planning personnel. Preferably, the flight safety risk factor assessment made by the safety management system can be analyzed by different analysis methods according to different selected reference data, and the reference effect of the final output analysis result is not the same, so that the decision maker uses different analysis results to make different flight safety risk factor assessment. Preferably, the analysis method can be divided into horizontal comparison, trend analysis, blood mining and factor change simulation evaluation according to different reference data. Specifically, the horizontal comparison refers to using flight environment factor data, flight personnel comprehensive quality data, equipment guarantee condition data and flight parameter record data to trace back the causes of flight risks occurring in the flight process of the flight personnel, and analyze the reasons for the flight personnel to appear specific flight risks, so as to generate the possibility of the flight personnel to appear various flight risks when flying. Specifically, the trend analysis refers to using flight environment factor data, flight personnel comprehensive quality data, equipment guarantee condition data, flight parameter record data to draw a flight safety risk coefficient trend chart, so as to analyze and predict the change direction of the aircraft safety risk factor. Specifically, the blood mining refers to using flight environment factor data, flight personnel comprehensive quality data, equipment guarantee condition data, flight parameter record data, safety evaluation plan execution situation, item safety evaluation value and evaluation comprehensive result to analyze the flight safety risk factor distribution of the flight personnel, so as to assist in formulating the skill training scheme of the flight personnel. Specifically, the factor change simulation evaluation refers to using flight environment factor data, flight personnel comprehensive quality data, equipment guarantee condition data, flight parameter record data, safety evaluation plan execution situation, item safety evaluation value and evaluation comprehensive result to verify the established model, so as to estimate the growth of the flight personnel, and also can simulate and predict the risk of the specified flight activity, so as to give an early warning to the possible flight risk hidden danger, so as to provide the training direction beneficial to the ability improvement of the flight personnel.

[0073] It should be noted that the above specific embodiments are exemplary, and those skilled in the art can think of various solutions under the inspiration of the disclosure of the present application, and these solutions also belong to the disclosed range of the present application and fall within the protection scope of the present application. Those skilled in the art should understand that the specification and drawings of the present application are illustrative and not constitute a limitation on the claims. The protection scope of the present application is defined by the claims and their equivalents. Throughout the text, the features introduced by "preferably" are only optional ways, and should not be understood as necessarily provided, therefore the applicant reserves the right to abandon or delete the relevant preferred features at any time.

Claims

1. A method for compiling test information for an accident risk value test, characterized in that: The method comprises the following steps: S1. Create a first test information database (Q1) for performing instruction target testing, a second test information database (Q2) for performing device testing, and a third test information database (Q3) for performing environment testing; S2. The test items of the second test information database (Q2) are provided in the form of data and signaling to a control unit of at least one device related to training life in a designated area for which an accident risk value is to be assessed; S3, when the test items of the third test information database (Q3) are provided in the form of data and signaling to a control unit of at least one working equipment related to training life in the designated area for which the accident risk value is to be assessed, the test items of the third test information database (Q3) are also provided in the form of data and signaling to a control unit of at least one monitoring device related to training life in parallel; The behavior data of the instruction target is mined using the first data mining and analysis module (2). The decision maker uses the second data mining and analysis module (3) to screen the multi-dimensional behavior data associated with the instruction target, and establishes a multi-dimensional behavior data model of the instruction target through the preset weight configuration rule and the screened multi-dimensional behavior data within at least a part of the time interval, thereby generating a comprehensive evaluation report of the instruction target using the multi-dimensional behavior data model with the preset weight configuration rule as the framework basis; Step S1 includes at least the following operations: S1.

1. When creating the first test information database (Q1) for conducting command target testing, a first screening is performed on command targets within a designated area for which accident risk values ​​are to be assessed, and test information having test results that conform to a normal distribution is selected to create the first test information database (Q1); S1.

2. Performing a second screening of the test information in the first test information database (Q1) for the target within the designated area for the accident risk assessment based on the target's equipment usage during training, and selecting test information with test results that conform to a normal distribution to create a second test information database (Q2); S1.

3. Perform a third screening of the test information in the second test information database (Q2) based on whether the target can complete the training using the equipment under the specified environmental conditions, for the target within the specified area for which the accident risk value is to be assessed, and select test information whose test results conform to a normal distribution to create the third test information database (Q3); The first test information database (Q1) is created as follows: after analyzing the accident risk value, at least seven dimensions are set, namely, thinking, safety skills, theory, physical training, daily management, teaching and self-study, and special training. A set of test information is set for each of the seven dimensions to form the first test information database (Q1).

2. The method for compiling test information for an accident risk value test according to claim 1, wherein: The test information content of the seven dimensions includes specific items of test information and project files that classify and record the behavioral data of the instruction targets completing the test items. The instruction targets and their project file data contained in the first test information database (Q1) are based on the various behavioral data performed by the instruction targets within a certain period of time to screen the instruction targets within the specified area of ​​the accident risk value to be evaluated, thereby screening out instruction targets that can complete the test items within the specified area of ​​the accident risk value to be evaluated.

3. The method for compiling test information for an accident risk value test according to claim 2, wherein: The stimulation information is sorted and stored in the archive unit (1) according to the type of stimulation information and / or the format of stimulation information, The first test information database (Q1), the second test information database (Q2) and the third test information database (Q3) screen the stimulus information stored in the archive unit (1) multiple times according to different screening conditions, thereby screening out instruction targets that can complete test items using specific equipment in a specified environment.

4. The method for compiling test information for an accident risk value test according to claim 3, wherein: The second data mining and analysis module (3) is capable of comparing the comprehensive evaluation report generated by establishing a multi-dimensional behavior data model with a reference data model pre-generated by the safety management system using test data, thereby evaluating the behavior safety of the instruction target; The second data mining and analysis module (3) generates prediction information of at least one behavioral data associated with the comparison result based on the above comparison or retrieves prediction information of at least one behavioral data associated with the comparison result in the database, and then uses the display terminal (4) to display the obtained prediction information, so that the decision maker can perform behavioral safety management of the instruction target based on the prediction information.

5. The method for compiling test information for an accident risk value test according to claim 4, wherein: The multi-dimensional behavior data mined from the security management system by the first data mining and analysis module (2) is classified and recorded using a plurality of archive units (1), wherein: Any of the archive units (1) independently records the single-dimensional behavior data stored in the security management system, and the archive unit (1) updates the recorded behavior data in real time; The archive unit (1) also associates the recorded behavior data with the behavior individual or behavior unit that generated the behavior data.

6. The method for compiling test information for an accident risk value test according to claim 5, wherein: The multi-dimensional behavior data mining performed by the first data mining and analysis module (2) is to perform secondary classification and aggregation on the behavior data classified and recorded by the security management system using the archive unit (1) in a dimensional division manner, wherein: Secondary classification and aggregation refers to reclassifying and aggregating the behavioral data recorded in different file units (1) according to the different behavioral individuals or behavioral units associated with the behavioral data.

7. The method for compiling test information for an accident risk value test according to claim 6, wherein: The second data mining and analysis module (3) uses a plurality of single basic information of the instruction target as a retrieval basis to filter out the behavior data associated with the instruction target from the behavior data mined and secondary classified and aggregated by the first data mining and analysis module (2), and the second data mining and analysis module (3) performs a secondary screening on the filtered behavior data associated with the instruction target according to a time interval determined by the decision maker.

Images