CN118152899B - Environment perception monitoring method and system - Google Patents
Environment perception monitoring method and system Download PDFInfo
- Publication number
- CN118152899B CN118152899B CN202410583818.4A CN202410583818A CN118152899B CN 118152899 B CN118152899 B CN 118152899B CN 202410583818 A CN202410583818 A CN 202410583818A CN 118152899 B CN118152899 B CN 118152899B
- Authority
- CN
- China
- Prior art keywords
- monitoring
- sequence
- environmental data
- data
- environmental
- 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.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 260
- 238000000034 method Methods 0.000 title claims abstract description 47
- 230000008447 perception Effects 0.000 title claims abstract description 13
- 230000007613 environmental effect Effects 0.000 claims abstract description 162
- 238000012806 monitoring device Methods 0.000 claims description 19
- 230000035945 sensitivity Effects 0.000 claims description 15
- 238000007405 data analysis Methods 0.000 claims description 5
- 239000000428 dust Substances 0.000 claims description 5
- 238000003860 storage Methods 0.000 claims description 5
- 238000012163 sequencing technique Methods 0.000 claims description 2
- 238000006243 chemical reaction Methods 0.000 abstract description 9
- 230000004927 fusion Effects 0.000 abstract description 5
- 238000004590 computer program Methods 0.000 description 10
- 238000012545 processing Methods 0.000 description 8
- 238000004364 calculation method Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 230000011218 segmentation Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 238000013515 script Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000005059 dormancy Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000003344 environmental pollutant Substances 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 238000011065 in-situ storage Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 231100000719 pollutant Toxicity 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
Abstract
The invention relates to an environment perception monitoring method, a platform and a system, wherein the method comprises the following steps: obtaining discretized environmental data segments based on historical environmental data; finding a key environment data sequence corresponding to each monitoring result; constructing a monitoring equipment sequence aiming at each monitoring result based on the key environment data sequence and the corresponding monitoring result; and when the monitoring result changes, selecting the monitoring equipment for conversion based on the sequence of the monitoring equipment in the monitoring equipment sequence for subsequent real-time monitoring. The invention reduces the difficulty of sensing fusion, simultaneously reduces the hardware cost generated in the environment sensing process, and greatly improves the environment sensing monitoring efficiency.
Description
Technical Field
The invention belongs to the technical field of data monitoring, and particularly relates to an environment perception monitoring method and system.
Background
Environmental awareness and environmental data monitoring are scientific research fields for real-time awareness, analysis, prediction, control and regulation of ecological environment, climate change, pollutant emission, climate condition and the like; the environmental monitoring refers to monitoring of natural, ecological or other detected objects in a certain time and space range, and aims to sense, explore and judge the change rule of environmental conditions, accurately predict the state of the environment, diagnose, manage and control various problems possibly happened to the environment, and early warn, feed back, control and regulate the objects existing in the environment.
The demand of environmental perception monitoring is larger and larger, but two hot spot problems exist in the process of environmental perception monitoring by adopting the existing sensor; one is that the sensors have limited ability to collect data and the sensor layout overhead is large. The extensive arrangement of the sensors or the maintenance of the sensors in a long-term operating state can lead to significant hardware overhead and loss and significant stress on the power support. Another is that, first, different sensing methods, i.e. different sensor data types, are different, the information involved is also diverse, and how to perform multi-modal sensing data fusion is a challenge. Secondly, the multi-mode data has uneven layers, the data types are complex, and comprehensive utilization cannot be performed. Sensory data fusion involves combining data from multiple sensors to produce a more accurate, comprehensive environmental perception or measurement. By integrating data from different types of sensors, such as radar, lidar, cameras, infrared sensors, etc., sensor fusion can provide more detailed information while reducing the limitations of a single sensor. The information processing process is carried out by using computer technology to automatically analyze and integrate information and data from multiple sensors or multiple sources under a certain criterion to complete the needed decision and estimation.
The big data technology is a novel technology for collecting, storing and analyzing and processing a large amount of data, along with the continuous increase of the types and the quantity of industries existing in the market in recent years, the traditional data processing mode can not be used for scientifically and effectively solving the two problems, the big data technology is used for ecological environment monitoring, the technology such as data mining, machine learning and the like is used for deeply analyzing and processing massive data, accurate information support is provided for the ecological environment monitoring, the implementation efficiency and the management effect are improved, and support is possibly provided for environment data monitoring, control and decision.
Disclosure of Invention
In order to solve the above-mentioned problems in the prior art, the present invention proposes an environmental awareness monitoring method and system, the method comprising:
Step S1: acquiring multi-mode historical environmental data and corresponding monitoring results thereof, segmenting the data, and discretizing the data based on time intervals to obtain discretized environmental data segments; wherein: the multi-mode historical environmental data comprises a plurality of records, wherein each record comprises environmental data and one or more monitoring results corresponding to the environmental data; each record relates to one or more environmental data types;
step S2: analyzing the environmental data segments based on the time sequence of the distance monitoring results, and finding out a key environmental data sequence corresponding to each monitoring result, wherein the key environmental data sequence comprises one or more key environmental data arranged according to the time sequence; wherein: the time is the time of the distance monitoring result;
step S21: classifying the environmental data segments according to the different monitoring results; sequentially acquiring an unprocessed monitoring result classification ；
Step S22: sequentially acquiring an unprocessed environmental data segment in the unprocessed monitoring result classification；; Wherein: Is the t-th environmental data in the environmental data segment; Is the first Monitoring a result; Is the number of the time interval(s), ；Is the maximum time interval number of the environmental data in the environmental data segment; is the first in the environment data An environmental data type;
step S23: respectively for the environment data types Collecting data; building an environment data value with time interval t as an abscissa for each environment data type kCoordinate system with ordinate；
Step S24: for each context data in the unprocessed data segment; the environmental data value is setPut into a coordinate systemNeutralizing the positions corresponding to the time interval t and the environment data value;
Step S25: judging whether all unprocessed environment data segments are processed, if so, entering the next step, otherwise, returning to the step S22;
step S26: in turn for the coordinate system Clustering the environmental data values in each time interval t to obtain one or more key environmental data values; obtaining a clustering center value after completing clustering of all time intervals, and taking the clustering center value as key environment data; all the cluster center values are arranged according to the sequence of time intervals to obtain the monitoring resultAnd environmental data typeCritical environmental data sequence；
Step S27: judging whether all monitoring results are classifiedAfter the treatment is finished, if yes, ending; otherwise, returning to the step S21;
Step S3: based on key environment data sequence And constructing a monitoring equipment sequence aiming at each monitoring result according to the corresponding monitoring result; the monitoring equipment sequence is the use priority sequence of the monitoring equipment under the corresponding monitoring result; the method comprises the following steps: normalizing the key environment data sequence, and comparing the distances between monitoring results of the key environment data sequences from the dimension of the environment data type k one by one, so as to find out the sensitivity difference of different environment data types k in different monitoring results, wherein the sensitivity is stronger when the distance is larger, and the sensitivity is weaker when the distance is smaller; according to the sensitivity, arranging the monitoring devices corresponding to the environment data type k in sequence to form a monitoring device sequence aiming at each monitoring result;
Step S4: when the monitoring result changes, selecting monitoring equipment to be converted based on the sequence of the monitoring equipment in the monitoring equipment sequence for subsequent real-time monitoring; and setting the monitoring equipment which is not used for subsequent real-time monitoring in a low-power consumption state.
Further, the environmental data includes weather environmental information.
Further, the environmental data includes one or more of temperature, wind speed, humidity, light intensity, dust, and/or rain.
Further, environmental data is acquired by various types of monitoring devices.
Further, each critical environmental data in the sequence of critical environmental data is a tuple or a tuple.
Further, when the dimension-by-dimension comparison is performed on the distances between the monitoring results of the key environment data sequences, the adopted distances are Euclidean distances between the sequences.
An environmental awareness monitoring system, comprising: a server and an early warning terminal; the server is used for realizing the environment perception monitoring method; the early warning terminal is used for sending an environment perception monitoring request to the server.
An environmental awareness monitoring platform comprising a processor coupled to a memory, the memory storing program instructions that when executed by the processor implement the environmental awareness monitoring method.
A computer readable storage medium comprising a program which, when run on a computer, causes the computer to perform the method of context-aware monitoring.
An environmental data analysis server configured to perform the environmental awareness monitoring method.
The beneficial effects of the invention include:
(1) Supporting big data environmental data sensing and monitoring by using a large amount of multi-mode environmental data, reducing the complexity of the multi-mode big data through data segmentation and discretization, converting the multi-mode sensing data into a digitized key environmental data sequence, finding out the key environmental data sequence under different monitoring results through intelligent data analysis, setting and calculating the deviation sequence to find out the diversified sensibility of the sensing data at the positions where different monitoring result stages appear, and thus supporting the mode of switching the environmental data types at different monitoring result stages to solve the problem of difficult sensing fusion;
furthermore, the environment data is subjected to multi-dimensional splitting from three dimensions such as monitoring results, time intervals, environment data types and the like, so that complex multi-mode data which cannot be converted into regular multi-mode data are converted, and the multi-mode environment big data are effectively utilized;
(2) By adopting a quantitative calculation mode based on big data, under the condition of needing less calculation amount, the dynamic discovery of the monitoring result can be supported based on real-time environment data, and the sensors used in the environment sensing process can be synchronously switched, so that part of the sensors are in a working state, and the other sensors are in a non-working state, thereby greatly reducing hardware expenditure in the environment sensing process, reducing power support and greatly improving the monitoring efficiency;
further, the handover overhead and other handover necessary considerations that may occur during the handover procedure are reduced by the double weighting.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate and together with the description serve to explain the application, if necessary:
Fig. 1 is a schematic diagram of an environmental awareness monitoring method according to the present invention.
Detailed Description
The present invention will now be described in detail with reference to the drawings and the specific embodiments thereof, wherein the exemplary embodiments and the description are for the purpose of illustrating the invention only and are not to be construed as limiting the invention.
The invention provides an environment perception monitoring method and system, as shown in figure 1, wherein the method comprises the following steps:
Step S1: acquiring multi-mode historical environmental data and corresponding monitoring results thereof, segmenting the data and discretizing the data to obtain discretized environmental data segments; wherein: the multi-mode historical environmental data comprises a plurality of records, wherein each record comprises environmental data and one or more monitoring results corresponding to the environmental data; each record relates to one or more environmental data types;
the data segmentation is specifically as follows: carrying out data segmentation on the historical environmental data and the corresponding monitoring results thereof to obtain one or more environmental data and environmental data segments formed by the corresponding monitoring results thereof; each environmental data segment corresponds to one monitoring result;
the discretization is specifically as follows: dividing the historical environment data into one or more data intervals according to a preset time interval; calculating a representative value of each environmental data type in the data interval as a discrete value representing the data interval, and arranging the discrete values according to a time sequence to obtain discretized environmental data segments; for example: (rd 1 to sr1, rd2 to sr 2), wherein: rd 1-and rd 2-are continuous or irregularly distributed multi-mode environmental data; the segmentation is carried out to obtain (rd 1) - (sr 1), (rd 2) - (sr 2), and the discretization is carried out to obtain two data segments (rd 1, rd2, sr 1), (rd 3, rd4, rd5, sr 2); wherein: rd 1-rd 5 are discretized environmental data, each environmental data comprising data values of one or more environmental data; sr1 to sr2 are monitoring results; the monitoring result is a tuple; and the type of the environmental data contained in each environmental data is the same or different;
Preferably: the representative value is an environment data value with the average value or the largest occurrence number;
preferably: the preset time interval is different for different monitoring results, and the higher the level of the monitoring result is, the shorter the corresponding preset time interval is; the preset time interval length corresponds to the monitoring result l;
Preferably: the monitoring result is an actual monitoring result corresponding to the acquired historical environment data or a monitoring result obtained by high-accuracy analysis of the historical environment data; for example: inputting the environmental data into the artificial intelligent model to obtain a monitoring result, wherein the accuracy of the artificial intelligent model is ensured; that is, the monitoring results obtained here are trusted; the monitoring result indicates early warning information provided according to the current environment sensing condition; may be described in terms of a class or type; when the grade is higher, the warning condition is more serious; the following is employed to quantify the monitoring results ；
Preferably: the high accuracy is 95-100%;
Preferably: the environmental data includes weather environmental information, such as: temperature, wind speed, humidity, light intensity, dust, rainfall, image analysis results obtained for various targets, and the like;
Preferably: acquiring environmental data through various types of monitoring equipment; for example: the external temperature acquired by the temperature sensor, the external humidity acquired by the rainfall sensor, the external illumination intensity acquired by the light sensor and the dust concentration acquired by the dust sensor;
step S2: analyzing the environmental data segments based on the time sequence of the distance monitoring results, and finding out a key environmental data sequence corresponding to each monitoring result, wherein the key environmental data sequence comprises one or more key environmental data arranged according to the time sequence; wherein: the time is the time of the distance monitoring result; obviously, each environmental data in the environmental data segment occurs before the monitoring result is obtained;
Preferably: each tuple corresponds to a data value of one or more environmental data;
the step S2 specifically includes the following steps:
step S21: classifying the environmental data segments according to the corresponding monitoring results; sequentially acquiring an unprocessed monitoring result classification ；
Step S22: sequentially acquiring an unprocessed environmental data segment in the unprocessed monitoring result classification；; Wherein: Is the t-th environmental data in the environmental data segment; Is the first Monitoring a result; Also the number of the time interval, ；Is the maximum time interval number of the environmental data in the environmental data segment, and the time of the maximum time interval is closest to or equal to theThe derived time of (2);
step S23: respectively for the environment data types Collecting data; building an environment data value with time interval t as an abscissa for each environment data type kCoordinate system with ordinate；
Step S24: for each context data in the unprocessed data segment; the environmental data value is setPut into a coordinate systemNeutralizing the positions corresponding to the time interval t and the environment data value; wherein: is the first in the environment data An environmental data type;
Step S25: judging whether all unprocessed environment data segments are processed, if so, entering the next step, otherwise, returning to the step S22;
step S26: in turn for the coordinate system Clustering the environmental data values in each time interval t to obtain one or more key environmental data values; obtaining a clustering center value after completing clustering of all time intervals, and taking the clustering center value as key environment data; all the cluster center values are arranged according to the sequence of time intervals to obtain the monitoring resultAnd environmental data typeCritical environmental data sequence；
Preferably: when the key environment data values are 1, selecting the largest clustering center value as the key environment data of the time interval t;
Preferably: the clustering distance is considered in the clustering process, so that a plurality of clustering centers can exist for each time interval t, and a plurality of key environment data sequences can be obtained after the clustering centers are arranged; sequentially arranging according to a preset arrangement rule conforming to a data change rule in the arrangement process; further, some clusters with fewer elements and scattered points may be discarded, and for some time intervals, their cluster centers may be multiplexed to form a continuous sequence; then, at this time, multiple times of comparison and judgment are needed in sequence when the comparison and judgment are carried out subsequently;
step S27: judging whether all monitoring results are classified After the treatment is finished, if yes, ending; at this time, the key environment data sequences aiming at different environment data types aiming at each monitoring result are obtained; Otherwise, returning to the step S21; it will be appreciated that the T values are the same or different for different critical environmental data sequences;
Step S3: based on key environment data sequence And constructing a monitoring equipment sequence aiming at each monitoring result according to the corresponding monitoring result; the monitoring equipment sequence is the use priority sequence of the monitoring equipment under the corresponding monitoring result; the method comprises the following steps: normalizing the key environment data sequence, and comparing the distances between monitoring results of the key environment data sequences from the dimension of the environment data type k one by one, so as to find the sensitivity difference of different environment data types k in different monitoring results, and arranging the monitoring devices corresponding to the environment data types k in sequence according to the sensitivity so as to form a monitoring device sequence for each monitoring result;
the step S3 specifically includes the following steps:
Step S31: the key environmental data sequence of each environmental data type is sequentially calculated Processing; acquiring an unprocessed context data type；
Step S32: normalizing the key environment data sequence [ ]; The method specifically comprises the following steps:
Step S321: acquiring minimum element values in a critical environment data sequence For each element, the distance between the element and the minimum value is calculated; Wherein: the minimum element value is obtained for one monitoring result l or across monitoring results; the method comprises the following steps: the distance between the minimum value and the minimum value is obtained by adopting the following formula (1)；
(1)；
Step S322: obtaining the distance duty ratio as normalized element value to obtain normalized key environment data sequence; The method comprises the following steps: performing distance normalization by adopting the following formula (2);
(2)；
backfilling the elements in situ after normalization, so that the names of the elements are not changed;
step S33: calculating the deviation condition among monitoring results of the key environment data sequences to construct a deviation sequence # ; Each element in the deviation sequence indicates the degree of deviation between the key environment data sequence of the corresponding monitoring result and the key environment data sequences of other monitoring results; the method comprises the following steps: calculating the value of each element in the offset sequence using the following formula (3); T1 is the length of the aligned critical environmental data sequence; is the maximum number of the monitoring result;
(3);
Preferably: when the lengths of the critical environmental data sequences are inconsistent, aligning to the maximum time interval T and intercepting from the minimum time interval, namely the head of the sequence; t1 is the length of the aligned critical environmental data sequence;
here, we consider that the monitoring result i is continuously changed, and the deviation situation can be obtained two by two for the discontinuous change situation, and the similar treatment is carried out;
Step S34: judging whether all the environment data types are processed, if so, entering the next step; otherwise, returning to the step S31;
Step S35: for each monitoring result, calculating the deviation sequence of each environmental data type Entropy value of (2); Arranging entropy values corresponding to all environment data types k in order from large to small to obtain an entropy value sequence; Wherein: The serial numbers of the environment data types after the sequencing; the sensitivity of the monitoring equipment corresponding to each monitoring result is different, and the higher the entropy value is, the stronger the sensitivity of the monitoring equipment is for the monitoring result;
Preferably: the entropy value Equal to the mean of elements in the sequence of deviations of the type of environmental data；
Alternatively, the following is used: ; i.e. the degree of deviation of the deviation value;
Step S36: constructing a monitoring equipment sequence corresponding to the monitoring result based on the entropy value sequence; the monitoring equipment sequence is the use priority sequence of the monitoring equipment under the corresponding monitoring result; the method comprises the following steps: taking the arrangement sequence of the environment data type numbers corresponding to the elements in the entropy value sequence as the arrangement sequence of the corresponding monitoring equipment, wherein the monitoring equipment arranged in front has higher priority;
the step S36 specifically includes the following steps:
step S361: for each monitoring result, sequentially acquiring one entropy value in the entropy value sequence ；
Step S362: acquiring its environment data typeThe corresponding monitoring equipment can monitor and acquire the environmental data of the environmental data type kq; the number of the monitoring devices corresponding to each environment data type kq is one or more;
step S363: arranging the monitoring devices according to the acquisition order to obtain a monitoring device sequence ; That is, for the monitoring result i, the first element in the sequenceOptimal for it, the sensitivity is the strongest;
Preferably: monitoring the elements in the device sequence as one or more;
Preferably: a monitoring device may monitor one or more environmental data types, so that monitoring devices in a sequence of monitoring devices may be combined, where the principle of combining is that if there is a coincidence between a monitoring device involved in a later element and a previous element, the type of the coincident monitoring device is preferentially selected; of course, monitoring equipment which is not the overlapping part can be directly deleted, so that the complexity of the sequence of the monitoring equipment is reduced;
Step S4: when the monitoring result changes, converting monitoring equipment for real-time monitoring based on the monitoring equipment sequence; setting monitoring equipment which is not used for real-time monitoring in a low-power consumption state;
Preferably: the change of the monitoring result is based on an adjustment of external feedback or on an adjustment for a request;
Alternatively, the step S4 specifically includes: determining whether to perform monitoring result adjustment and monitoring equipment conversion, and converting monitoring equipment for performing real-time monitoring based on the monitoring equipment sequence when determining; setting monitoring equipment which is not used for real-time monitoring in a low-power consumption state;
The determining whether to adjust the monitoring result and switch the monitoring equipment specifically comprises the following steps: determining whether to perform monitoring equipment conversion or not based on real-time environment data obtained by real-time monitoring, a current monitoring result and a key environment data sequence; the method specifically comprises the following steps:
step S4A1: with in-use monitoring equipment Real-time monitoring and acquiring real-time environment data of the nearest continuous first time interval length;
preferably: the first time interval length is equal to ; Wherein: the preset time interval length corresponds to the monitoring result l;
Step S4A2: acquiring current monitoring result and in-use monitoring device Obtaining and currently monitoring resultsMonitoring deviceCorresponding key environment data sequence [ ]；
Step S4A3: when effective deviation is generated between the real-time environment data and the key environment data sequence, determining that monitoring result adjustment and monitoring equipment conversion are required; wherein: the adjustment of the monitoring result is bidirectional and can be forward adjustment, and the current monitoring result is set as the next monitoring result; or the current monitoring result is set as the previous monitoring result by backward adjustment;
The monitoring result is adjusted, specifically: selecting a monitoring result closest to the current monitoring result and not generating effective deviation as an adjustment object; the fact that no effective deviation is generated means that no effective deviation is generated between the corresponding key environment data sequence and the real-time environment data; the calculation method is the same as that of the step S4A3;
Preferably: the nearest is the previous monitoring result or the latter monitoring result;
the step of setting the current monitoring result as the next monitoring result specifically comprises the following steps: setting up ; When the next or previous monitoring result does not exist, not adjusting the monitoring result;
The setting the current monitoring result as the previous monitoring result specifically comprises the following steps: setting up ；
Preferably: setting the initial value of the monitoring result to the minimum monitoring result, i.e. setting; The monitoring result is an enumerated value, and the minimum monitoring result is used for indicating the lowest monitoring level or the lightest monitoring type; conversely, the maximum monitoring result is used for indicating the highest monitoring level or the heaviest monitoring type;
Preferably: when judging that effective deviation is generated between the real-time environment data and the key environment data sequence, if a section of continuous environment data exists in the real-time environment data, and the Euclidean distance average value between the section of environment data and the key environment data sequence or part of key environment data sequence is smaller than a judgment threshold value, determining that the effective deviation is not generated, otherwise, determining that the effective deviation is generated;
Preferably: the decision threshold is a preset value;
Preferably: the time interval length related to the continuous environmental data is larger than the effective judgment time interval length; for example: the length of the effective decision time interval is equal to ；
Preferably: when the Euclidean distance judgment is carried out, the calculation of the Euclidean distance is unordered, that is, the comparison between the continuous environmental data and the key environmental data sequence or part of the key environmental data sequence is not used for distinguishing the sequence of the environmental data; the continuous environmental data can be compared with any environmental data in the key environmental data sequence or part of key environmental data sequence, euclidean distance is calculated, and the final Euclidean distance average value calculation is participated; but instead, alternatively: when the Euclidean distance judgment is carried out, the calculation of the Euclidean distance is disordered, that is to say, the comparison between the continuous environmental data and the key environmental data sequence or part of the key environmental data sequence is to distinguish the sequence of the environmental data; the comparison between the environmental data is to distinguish time sequence; whether loose or strict comparison is used depends, of course, on the degree of redundancy and sensitivity of the monitoring; if the redundancy is high, some monitoring omission can be caused, otherwise, if the sensitivity is high, wrong monitoring result feedback can be caused;
Preferably: the part of the key environment data sequence is a continuous subsequence in the key environment data sequence; for example: 50-80% of the total weight of the product;
Preferably: when the Euclidean distance judgment is performed, part of real-time environmental data can be discarded, that is, when the continuous environmental data is compared with the key environmental data sequence or part of key environmental data sequence, part of environmental data with larger Euclidean distance can not participate in calculation of Euclidean distance average value; of course this part is proportionally limited, for example: discarding 20% of the discrete environmental data;
The monitoring equipment for real-time monitoring based on the monitoring equipment sequence conversion comprises the following specific steps: acquiring a current monitoring result, acquiring a corresponding monitoring equipment sequence based on the current monitoring result, taking monitoring equipment corresponding to the forefront in the monitoring equipment sequence as monitoring equipment to be converted, and taking the converted monitoring equipment as monitoring equipment for real-time monitoring; when the monitoring equipment corresponding to the forefront comprises the monitoring equipment currently in use, not performing monitoring equipment conversion;
Alternatively, the following is used: the monitoring equipment for real-time monitoring based on the monitoring equipment sequence conversion comprises the following specific steps: for monitoring equipment sequence Weighting by double weighting to obtain weighted monitoring equipment sequence; Wherein: is the use weight of the monitoring equipment, Is the monitoring device switching weight;
Preferably: the said AndIs a preset value; when the using cost and/or the switching time of the monitoring equipment are smaller, the using weight is larger, otherwise, the using weight is smaller; when the monitoring equipment is overlapped with the monitoring equipment which is currently used, the conversion weight is larger, and conversely, the conversion weight is smaller;
The monitoring equipment which is not used for real-time monitoring is in a low power consumption state, and specifically comprises the following components: setting the monitoring equipment which is not used for real-time monitoring in low power consumption states such as closing, dormancy, low frequency or standby;
based on the same inventive concept, the present invention also provides an environmental awareness monitoring system, the system comprising: a server and an early warning terminal; the server is used for realizing the environment perception monitoring method; the early warning terminal is used for sending an environment perception monitoring request to the server;
Preferably: the server is an environmental data analysis server; the number of the servers is one or more;
preferably: the server is a big data server;
preferably: the early warning terminal is a computing terminal positioned on the environment sensing site;
A computer program (also known as a program, software application, script, or code) can be written in any form of programming language, including compiled or interpreted languages, declarative or procedural languages, and it can be deployed in any form, including as a stand-alone program or as a module, component, subroutine, object or other unit suitable for use in a computing environment. The computer program may, but need not, correspond to a file in a file system. A program can be stored in a portion of a file that holds other programs or data (e.g., one or more scripts stored in a markup language document), in a single file dedicated to the program, or in multiple coordinated files (e.g., files that store one or more modules, subroutines, or portions of code). A computer program can be deployed to be executed on one computer or on multiple computers at one site or distributed across multiple sites and interconnected by a communication network.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Finally, it should be noted that: the above embodiments are only for illustrating the technical aspects of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the above embodiments, it should be understood by those of ordinary skill in the art that: modifications and equivalents may be made to the specific embodiments of the invention without departing from the spirit and scope of the invention, which is intended to be covered by the claims.
Claims (10)
1. A method of environmental awareness monitoring, the method comprising:
Step S1: acquiring multi-mode historical environmental data and corresponding monitoring results thereof, segmenting the data, and discretizing the data based on time intervals to obtain discretized environmental data segments; wherein: the multi-mode historical environmental data comprises a plurality of records, wherein each record comprises environmental data and one or more monitoring results corresponding to the environmental data; each record relates to one or more environmental data types;
step S2: analyzing the environmental data segments based on the time sequence of the distance monitoring results, and finding out a key environmental data sequence corresponding to each monitoring result, wherein the key environmental data sequence comprises one or more key environmental data arranged according to the time sequence; wherein: the time is the time of the distance monitoring result;
step S21: classifying the environmental data segments according to the different monitoring results; sequentially acquiring an unprocessed monitoring result classification ；
Step S22: sequentially acquiring an unprocessed environmental data segment in the unprocessed monitoring result classification；; Wherein: Is the t-th environmental data in the environmental data segment; Is the first Monitoring a result; Is the number of the time interval(s), ；Is the maximum time interval number of the environmental data in the environmental data segment; is the first in the environment data An environmental data type;
step S23: respectively for the environment data types Collecting data; building an environment data value with time interval t as an abscissa for each environment data type kCoordinate system with ordinate；
Step S24: for each context data in the unprocessed data segment; the environmental data value is setPut into a coordinate systemNeutralizing the positions corresponding to the time interval t and the environment data value;
Step S25: judging whether all unprocessed environment data segments are processed, if so, entering the next step, otherwise, returning to the step S22;
step S26: in turn for the coordinate system Clustering the environmental data values in each time interval t to obtain one or more key environmental data values; obtaining a clustering center value after completing clustering of all time intervals, and taking the clustering center value as key environment data; all the cluster center values are arranged according to the sequence of time intervals to obtain the monitoring resultAnd environmental data typeCritical environmental data sequence；
Step S27: judging whether all monitoring results are classifiedAfter the treatment is finished, if yes, ending; otherwise, returning to the step S21;
Step S3: based on key environment data sequence And constructing a monitoring equipment sequence aiming at each monitoring result according to the corresponding monitoring result; the monitoring equipment sequence is the use priority sequence of the monitoring equipment under the corresponding monitoring result; the method comprises the following steps: normalizing the key environment data sequence, and then performing distance comparison among monitoring results on the key environment data sequence dimension by dimension from the dimension of the environment data type k, so as to find out the sensitivity difference of different environment data types k in different monitoring results; for each monitoring result, calculating the deviation sequence of each environmental data typeEntropy value of (2); Arranging entropy values corresponding to all environment data types k in order from large to small to obtain an entropy value sequence; Wherein: The serial numbers of the environment data types after the sequencing; the sensitivity of the monitoring equipment corresponding to each monitoring result is different, and the higher the entropy value is, the stronger the sensitivity of the monitoring equipment is for the monitoring result; the entropy value Equal to the mean of elements in the sequence of deviations of the type of environmental data; According to the sensitivity, arranging the monitoring devices corresponding to the environment data type k in sequence to form a monitoring device sequence aiming at each monitoring result;
Step S4: when the monitoring result changes, selecting monitoring equipment to be converted based on the sequence of the monitoring equipment in the monitoring equipment sequence for subsequent real-time monitoring; and setting the monitoring equipment which is not used for subsequent real-time monitoring in a low-power consumption state.
2. The environmental awareness monitoring method of claim 1 wherein the environmental data comprises weather environmental information.
3. The environmental awareness monitoring method of claim 2 wherein the environmental data comprises one or more of temperature, wind speed, humidity, light intensity, dust and/or rain.
4. A method of environmental awareness monitoring according to claim 3 wherein the environmental data is obtained by various types of monitoring devices.
5. The method of claim 4, wherein each critical environmental data in the sequence of critical environmental data is a univariate or a multi-tuple.
6. The method according to claim 5, wherein the distance used in the dimension-by-dimension comparison of distances between monitoring results of critical environmental data sequences is the euclidean distance between the sequences.
7. An environmental awareness monitoring system, comprising: a server and an early warning terminal; the server is configured to implement the context awareness monitoring method of any of the preceding claims 1-6; the early warning terminal is used for sending an environment perception monitoring request to the server.
8. A context aware monitoring platform comprising a processor coupled to a memory, the memory storing program instructions that when executed by the processor implement the context aware monitoring method of any of claims 1-6.
9. A computer readable storage medium comprising a program which, when run on a computer, causes the computer to perform the context awareness monitoring method of any of claims 1-6.
10. An environmental data analysis server, characterized in that the environmental data analysis server is configured to perform the environmental awareness monitoring method of any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410583818.4A CN118152899B (en) | 2024-05-11 | Environment perception monitoring method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410583818.4A CN118152899B (en) | 2024-05-11 | Environment perception monitoring method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118152899A CN118152899A (en) | 2024-06-07 |
| CN118152899B true CN118152899B (en) | 2024-07-12 |
Family
ID=
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116029605A (en) * | 2023-01-31 | 2023-04-28 | 江苏宁宸贝立科技有限公司 | Water environment monitoring method and system |
| CN116403059A (en) * | 2023-01-17 | 2023-07-07 | 珠海高凌信息科技股份有限公司 | Multi-mode depth model-based environment identification method, device and storage medium |
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116403059A (en) * | 2023-01-17 | 2023-07-07 | 珠海高凌信息科技股份有限公司 | Multi-mode depth model-based environment identification method, device and storage medium |
| CN116029605A (en) * | 2023-01-31 | 2023-04-28 | 江苏宁宸贝立科技有限公司 | Water environment monitoring method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102159692B1 (en) | solar photovoltatic power generation forecasting apparatus and method based on big data analysis | |
| CN106059492A (en) | Photovoltaic assembly shadow fault type determination method based on power prediction | |
| CN112348339A (en) | Power distribution network planning method based on big data analysis | |
| CN108540310B (en) | Behavior prediction method based on wireless network cooperative sensing | |
| Cao et al. | CNN-based intelligent safety surveillance in green IoT applications | |
| WO2019214016A1 (en) | Lora technology-based multi-functional led smart street lamp system | |
| CN104697107A (en) | Intelligent learning energy-saving regulation and control system and method | |
| CN103633938A (en) | Photovoltaic array fault positioning method | |
| CN103543697B (en) | Traffic tunnel device clusters formula intelligent control method | |
| CN116822115A (en) | Environment management method and system for intelligent park based on digital twin technology | |
| CN116311593A (en) | Energy consumption calculation method and system | |
| CN116317943A (en) | Photovoltaic array hot spot detection method | |
| CN117460129B (en) | Energy-saving street lamp control method and system based on Internet of things driving | |
| CN118152899B (en) | Environment perception monitoring method and system | |
| CN108470699B (en) | intelligent control system of semiconductor manufacturing equipment and process | |
| CN118152899A (en) | Environment perception monitoring method and system | |
| CN117011790A (en) | Intelligent park management method and device based on multi-mode vision tracking | |
| CN111563886A (en) | Tunnel steel rail surface disease detection method and device based on unsupervised feature learning | |
| CN115545962A (en) | Crop growth period control method and system based on multi-sensor system | |
| CN114820825B (en) | Green detection method and system for underground pipe gallery assembled structure | |
| CN115327942A (en) | Intelligent environment monitoring system | |
| CN111625525B (en) | Environment data repairing/filling method and system | |
| CN112532953B (en) | Data processing method and system for intelligent city road lighting control | |
| CN111931798B (en) | Method for classifying and detecting cold head state and predicting service life | |
| Gao et al. | The design of the prognostics and health management system for special vehicle |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |