A multi-institutional collaborative monitoring filtering method and system

Abstract

The present invention provides a multi-institution collaborative monitoring and filtering method and system, the method comprising: obtaining a number of result data records corresponding to the weather from a meteorological forecasting agency to construct a first equivalent partition; obtaining a number of process data records corresponding to the weather from a data acquisition base station to construct a second equivalent partition; merging the second equivalent partitions of different data acquisition base stations into a data acquisition base station partition set, and obtaining a first correct decision value in combination with the first equivalent partition; judging the data acquisition base station as an important base station or an initial redundant base station based on the first correct decision value, and merging the important base stations into an important base station set; obtaining a third correct decision value of the important base station set to determine whether the decision-making ability of the important base station set meets the requirements, and then completing the screening and elimination of the final redundant base stations. Based on the above method, the number of data acquisition base stations is streamlined and the accuracy and efficiency of the prediction are improved while ensuring the stability of the decision-making ability.

Description

Technical Field

[0001] The present invention relates to the field of data prediction technology, and in particular to a multi-agency collaborative monitoring filtering method and system. Background Art

[0002] In today's information age, the construction and operation of meteorological forecasting systems face increasingly complex and dynamic challenges. Collaborative monitoring of multiple data collection base stations, a key forecasting model, has gradually become a focus of attention because it effectively integrates the resources and advantages of different data collection base stations to improve forecasting performance.

[0003] However, the traditional multi-agency collaborative monitoring method has exposed many shortcomings in actual operation. Specifically, under the traditional model, with the complexity of weather forecast scenarios, the number of data collection base stations has gradually increased, and the total amount of data obtained has continued to grow. The massive amount of data will lead to reduced data processing efficiency, and the data quality between different data collection base stations is inconsistent. The data provided by data collection base stations with low data quality will not only fail to improve the quality of weather forecasts, but will also further affect the efficiency of data processing, thereby reducing the accuracy and effectiveness of weather forecasts. Summary of the Invention

[0004] In view of the shortcomings of the existing technology, the purpose of the present invention is to provide a multi-institutional collaborative monitoring and filtering method and system, aiming to solve the technical problem in the existing technology that the accuracy and efficiency of weather forecasts are reduced as the number of data collection base stations with different data quality gradually increases.

[0005] To achieve the above objectives, in a first aspect, embodiments of the present application provide a multi-institution collaborative monitoring and filtering method for eliminating final redundant base stations from a plurality of data collection base stations. The multi-institution collaborative monitoring and filtering method comprises the following steps:

[0006] Obtaining a plurality of result data records corresponding to weather from a meteorological forecasting agency, extracting a plurality of decision attribute values ​​from the plurality of result data records based on a decision attribute, assigning a first unique identifier to each of the decision attribute values ​​to construct a first equivalence partition, wherein the first equivalence partition includes a plurality of first equivalence classes;

[0007] Acquire a plurality of process data records corresponding to weather from the data collection base station, the process data records corresponding to the number of the result data records, extract collection attribute value groups from the process data records based on a plurality of collection attributes, assign a second unique identifier to each of the collection attribute value groups to construct a second equivalence partition, the second equivalence partition including a plurality of second equivalence classes;

[0008] Merging the second equivalence partitions of different data collection base stations into a data collection base station partition set including a plurality of third equivalence classes, and determining a first correct decision value of the data collection base station partition set in combination with the first equivalence partition;

[0009] Based on the first correct decision value, the data collection base station is judged to be an important base station or an initial redundant base station, and the important base stations are merged into an important base station set;

[0010] Obtain a third correct decision value of the set of important base stations to determine whether the decision-making capability of the set of important base stations meets the requirements based on the first correct decision value and the third correct decision value; if the decision-making capability of the set of important base stations meets the requirements, all the initial redundant base stations are selected as the final redundant base stations, and the final redundant base stations are eliminated.

[0011] Compared with the prior art, the beneficial effects of the present invention are: by constructing the first equivalence partition with the first unique identifier and constructing the second equivalence partition with the second unique identifier, the result data record and the process data record themselves are not directly transmitted and processed, thereby ensuring the privacy and security of the data; by analyzing the impact of different data acquisition base stations on the decision-making ability of the overall meteorological forecasting system through the first correct decision value, the importance of different data acquisition base stations is determined, and then, under the premise of ensuring the stability of the decision-making ability of the meteorological forecasting system, the number of data acquisition base stations is simplified to the greatest extent, that is, while reducing the overall data volume, data acquisition base stations with lower data quality are filtered out, which solves the problems of data redundancy, computational complexity and inconsistent data quality to a certain extent, and improves the accuracy and efficiency of the prediction.

[0012] Furthermore, the step of constructing a first equivalence partition, wherein the first equivalence partition includes a plurality of first equivalence classes, includes:

[0013] comparing whether different decision attribute values ​​are the same;

[0014] If the same decision attribute value exists, the first unique identifiers corresponding to the same decision attribute value are merged into a plurality of first sets, and the first unique identifiers corresponding to different decision attribute values ​​are divided into a plurality of second sets;

[0015] The first set and the second set are both defined as first equivalence classes, and a number of the first equivalence classes are combined into a first equivalence partition.

[0016] Furthermore, the step of extracting a plurality of acquisition attribute value groups from the process data record based on the plurality of acquisition attributes is specifically as follows:

[0017] Acquire several acquisition attributes corresponding to the data acquisition base station, match the acquisition attributes with the process data record to extract acquisition attribute values ​​corresponding to the acquisition attributes from the process data record, and combine several acquisition attribute values ​​into an acquisition attribute value group.

[0018] Furthermore, the step of constructing a second equivalence partition, wherein the second equivalence partition includes a plurality of second equivalence classes, includes:

[0019] comparing whether different groups of collected attribute values ​​are the same;

[0020] If the same collection attribute value group exists, merging the second unique identifiers corresponding to the same collection attribute value group into a plurality of third sets, and dividing the second unique identifiers corresponding to different collection attribute value groups into a plurality of fourth sets;

[0021] The third set and the fourth set are both defined as second equivalence classes, and a number of the second equivalence classes are combined into a second equivalence partition.

[0022] Furthermore, the step of merging the second equivalent partitions of different data collection base stations into a data collection base station partition set includes:

[0023] Selecting one of the second equivalent partitions as a benchmark equivalent partition, and selecting the remaining second equivalent partitions as equivalent partitions to be checked;

[0024] Perform intersection judgment on each of the second equivalence classes in the benchmark equivalence partition and each of the second equivalence classes in the equivalence partition to be checked;

[0025] If there is an intersection part, the intersection part is extracted to form a fifth set, the fifth set is defined as a third equivalence class, and several third equivalence classes are combined into a data acquisition base station partition set.

[0026] Furthermore, the step of determining a first correct decision value of the data collection base station partition set in combination with the first equivalent partition includes:

[0027] Determining whether each of the third equivalence classes in the data acquisition base station partition set is completely included in a first equivalence class in the first equivalence partition;

[0028] A first correct decision value of the data collection base station partition set is determined based on the number of the third equivalence classes that are completely included in a certain first equivalence class in the first equivalence partition.

[0029] Furthermore, the step of determining whether the data collection base station is an important base station or an initial redundant base station based on the first correct decision value includes:

[0030] Eliminating a data collection base station from the plurality of data collection base stations to obtain a remaining base station partition set of the remaining data collection base stations, and obtaining a second correct decision value of the remaining base station partition set;

[0031] Obtaining a degree of change in decision-making ability based on the first correct decision value and the second correct decision value;

[0032] The degree of change in the decision-making ability is compared with a first threshold. If the degree of change in the decision-making ability is greater than the first threshold, the data collection base station that is eliminated is an important base station. If the degree of change in the decision-making ability is less than the first threshold, the data collection base station that is eliminated is an initial redundant base station.

[0033] Furthermore, the calculation formula for the degree of change in decision-making ability is:

[0034] ,

[0035] in, Indicates that the data collection base station is removed The degree of change in decision-making ability after Indicates that the data collection base station is removed The second correct decision value after represents the first correct decision value.

[0036] Furthermore, in the step of obtaining the third correct decision value of the important base station set to determine whether the decision-making capability of the important base station set meets the requirements based on the first correct decision value and the third correct decision value, if the decision-making capability of the important base station set meets the requirements, all the initial redundant base stations are selected as the final redundant base stations, and the final redundant base stations are eliminated, the step further includes:

[0037] If the decision-making capability of the important base station set does not meet the requirements, selecting a base station to be added from the plurality of initial redundant base stations, and adding the base station to be added to the important base station set;

[0038] Obtaining a fourth correct decision value of the important base station set after the base station to be added is added, so as to determine whether the decision-making capability of the important base station set after the base station to be added meets the requirements according to the first correct decision value and the fourth correct decision value;

[0039] If the decision-making capability of the important base station set after adding the base station to be added meets the requirement, the remaining initial redundant base stations are selected as the final redundant base stations, and the final redundant base stations are eliminated.

[0040] In a second aspect, an embodiment of the present application provides a multi-institution collaborative monitoring and filtering system, which is applied to the multi-institution collaborative monitoring and filtering method described in the first aspect above, and the system includes:

[0041] a first acquisition module, configured to acquire a plurality of result data records corresponding to weather from a meteorological forecasting agency, extract a plurality of decision attribute values ​​from the plurality of result data records based on a decision attribute, assign a first unique identifier to each of the decision attribute values, and thereby construct a first equivalence partition, wherein the first equivalence partition includes a plurality of first equivalence classes;

[0042] a second acquisition module, configured to acquire a plurality of process data records corresponding to weather conditions from the data acquisition base station, the process data records corresponding to the number of result data records, extract acquisition attribute value groups from the process data records based on a plurality of acquisition attributes, assign a second unique identifier to each of the acquisition attribute value groups, and construct a second equivalence partition, the second equivalence partition including a plurality of second equivalence classes;

[0043] a combining module, configured to combine the second equivalence partitions of different data acquisition base stations into a data acquisition base station partition set comprising a plurality of third equivalence classes, and determine a first correct decision value of the data acquisition base station partition set in combination with the first equivalence partition;

[0044] a classification module, configured to determine, based on the first correct decision value, whether the data collection base station is an important base station or an initial redundant base station, and merge the important base stations into an important base station set;

[0045] an execution module, configured to obtain a third correct decision value of the set of important base stations, to determine whether the decision-making capability of the set of important base stations meets the requirements based on the first correct decision value and the third correct decision value; if the decision-making capability of the set of important base stations meets the requirements, all the initial redundant base stations are selected as the final redundant base stations, and the final redundant base stations are eliminated.

[0046] In a third aspect, an embodiment of the present application provides a computer comprising a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the multi-institutional collaborative monitoring and filtering method as described in the first aspect above is implemented.

[0047] In a fourth aspect, an embodiment of the present application provides a storage medium on which a computer program is stored. When the computer program is executed by a processor, it implements the multi-institutional collaborative monitoring and filtering method as described in the first aspect above. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 Flowchart of the multi-organization collaborative monitoring and filtering method in the first embodiment of the present invention;

[0049] Figure 2 This is a structural block diagram of a multi-organization collaborative monitoring and filtering system according to a second embodiment of the present invention;

[0050] The following specific embodiments will further illustrate the present invention in conjunction with the above-mentioned drawings. DETAILED DESCRIPTION

[0051] To facilitate understanding of the present invention, the present invention will be described more fully below with reference to the accompanying drawings. The drawings illustrate several embodiments of the present invention. However, the present invention may be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and comprehensive understanding of the present invention.

[0052] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be an intermediate element. When an element is referred to as being "connected to" another element, it may be directly connected to the other element or there may be an intermediate element. The terms "vertical," "horizontal," "left," "right," and similar expressions used herein are for illustrative purposes only.

[0053] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one skilled in the art to which this invention pertains. The terms used in this specification of the present invention are for the purpose of describing specific embodiments only and are not intended to limit the present invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0054] See also Figure 1 The first embodiment of the present invention provides a multi-institution collaborative monitoring and filtering method for eliminating final redundant base stations from a plurality of data collection base stations. The multi-institution collaborative monitoring and filtering method includes the following steps:

[0055] S10: obtaining a plurality of result data records corresponding to weather from a meteorological forecasting agency, extracting a plurality of decision attribute values ​​from the plurality of result data records based on a decision attribute, assigning a first unique identifier to each of the decision attribute values ​​to construct a first equivalence partition, wherein the first equivalence partition includes a plurality of first equivalence classes;

[0056] Assume that the result data records are weather records for three days. The decision attribute is weather, that is, by using weather as a keyword to extract specific weather conditions from the weather records, it can be understood that the decision attribute values ​​are sunny, cloudy, rainy and / or snowy.

[0057] Specifically, step S10 includes:

[0058] S110: Comparing different decision attribute values ​​to see if they are the same;

[0059] S120: If the same decision attribute value exists, merging the first unique identifiers corresponding to the same decision attribute value into a plurality of first sets, and dividing the first unique identifiers corresponding to different decision attribute values ​​into a plurality of second sets;

[0060] Taking three days of weather records as an example, if the decision attribute values ​​are sunny, cloudy, and sunny, then after assigning the first unique identifier, the values ​​are 1, sunny; 2, cloudy; and 3, sunny. In this case, the same decision attribute value exists. Therefore, the first set is (1, 3), the second set is (2), and the first equivalence partition is {(1, 3), (2)}.

[0061] It can be understood that if the same decision attribute value does not exist, the first unique identifiers corresponding to different decision attribute values ​​are respectively divided into a plurality of sixth sets;

[0062] Taking the weather records of three days as an example, if the decision attribute values ​​are sunny, cloudy, and rainy, then after assigning the first unique identifier, they are 1, sunny; 2, cloudy; 3, rainy. At this time, there is no identical decision attribute value, so the three sixth sets are (1), (2), (3), and the first equivalence partition is {(1), (2), (3)}.

[0063] It should be noted that the first set, the second set, and the sixth set have the same meaning, and only the number of records included, that is, the number of first unique identifiers may be different.

[0064] S130: defining the first set and the second set as a first equivalence class, and combining a plurality of the first equivalence classes into a first equivalence partition;

[0065] The first equivalence partition is the set of the first equivalence classes.

[0066] S20: Acquire a plurality of process data records corresponding to weather conditions from the data acquisition base station, wherein the number of the process data records corresponds to the number of the result data records, extract acquisition attribute value groups from the process data records based on a plurality of acquisition attributes, assign a second unique identifier to each of the acquisition attribute value groups, and construct a second equivalence partition, wherein the second equivalence partition includes a plurality of second equivalence classes;

[0067] Different data collection base stations may collect the same or different data. For example, if there are three data collection base stations, the first data collection base station may collect air pressure, wind speed, and temperature; the second data collection base station may collect humidity and wind speed; and the third data collection base station may collect wind speed and temperature. It is understood that the process data record is the data collection record of the data collection base station. If several result data records are three-day weather records, then the process data record is the data collection record of three days. Each of the different data collection base stations has process data records corresponding to the number of result data records.

[0068] The step S20 includes:

[0069] S210: Acquire a plurality of acquisition attributes corresponding to the data acquisition base station, match the acquisition attributes with the process data record to extract acquisition attribute values ​​corresponding to the acquisition attributes from the process data record, and combine the plurality of acquisition attribute values ​​into an acquisition attribute value group;

[0070] The collection attributes are the collection targets of the data collection base station, namely, wind speed, temperature, humidity, air pressure, etc. When wind speed is the collection attribute, the collection attribute values ​​are high, medium, and low. Taking the example of mechanism 1 in the above example, the collection attribute values ​​extracted from the first process data record are: high, large, and high, representing high air pressure, high wind, and high temperature, respectively. These three collection attribute values ​​form the collection attribute value group. The number of collection attribute value groups corresponds to the number of process data records.

[0071] S220: Compare different collection attribute value groups to see if they are the same;

[0072] S230: If the same collection attribute value group exists, merging the second unique identifiers corresponding to the same collection attribute value group into a plurality of third sets, and dividing the second unique identifiers corresponding to different collection attribute value groups into a plurality of fourth sets;

[0073] S240: defining the third set and the fourth set as second equivalence classes, and combining a plurality of the second equivalence classes into a second equivalence partition;

[0074] The second equivalence partition is obtained in a manner substantially identical to the first equivalence partition. Still taking the three data collection base stations as an example, after obtaining the collection attribute value groups of the data collection base stations and assigning the second unique identifiers, the results are shown in Tables 1, 2, and 3:

[0075] Table 1

[0076] ,

[0077] Table 2

[0078] ,

[0079] Table 3

[0080] ,

[0081] For data collection base station 1, the second equivalent partition is: {(1), (2), (3)}; for data collection base station 2, the second equivalent partition is: {(1, 3), (2)}; for data collection base station 3, the second equivalent partition is: {(1, 3), (2)}. It can be understood that the number of the second equivalent partitions corresponds to the number of the data collection base stations.

[0082] S30: merging the second equivalence partitions of different data collection base stations into a data collection base station partition set including a plurality of third equivalence classes, and determining a first correct decision value of the data collection base station partition set in combination with the first equivalence partition;

[0083] Specifically, step S30 includes:

[0084] S310: selecting one of the second equivalence partitions as a benchmark equivalence partition, and selecting the remaining second equivalence partitions as equivalence partitions to be checked;

[0085] Extending the above example, the second equivalent partition of data acquisition base station 1 is: {(1), (2), (3)}, the second equivalent partition of data acquisition base station 2 is: {(1, 3), (2)}, and the second equivalent partition of data acquisition base station 3 is: {(1, 3), (2)}. Data acquisition base station 1 is selected as the benchmark equivalent partition, and data acquisition base station 2 and data acquisition base station 3 are selected as the equivalent partitions to be checked.

[0086] S320: Performing intersection judgment on each of the second equivalence classes in the benchmark equivalence partition and each of the second equivalence classes in the equivalence partition to be checked;

[0087] S330: If an intersection exists, extract the intersection to form a fifth set, define the fifth set as a third equivalence class, and combine several third equivalence classes into a data collection base station partition set;

[0088] The second equivalence classes of data acquisition base station 1 are 3, namely (1), (2), and (3). The second equivalence classes of data acquisition base station 2 are 2, namely (1, 3), and (2). After performing intersection judgment on (1) in data acquisition base station 1 and (1, 3), (2) in data acquisition base station 1, (1) and (1, 3) have an intersection, so the intersection part is (1). The rest of the intersection judgments are similar, and the data acquisition base station partition set can be obtained as {(1), (2), (3)}.

[0089] S340: Determine whether each of the third equivalence classes in the data collection base station partition set is completely included in a first equivalence class in the first equivalence partition;

[0090] S350: Determine a first correct decision value of the data collection base station partition set based on the number of the third equivalence classes that are completely included in a first equivalence class in the first equivalence partition;

[0091] Assume that the first equivalence partition is {(1, 3), (2)}, the data acquisition base station partition set is {(1), (2), (3)}, the first equivalence classes are 2, (1, 3), (2), and the third equivalence classes are 3, (1), (2), (3). Then, (1) and (3) of the data acquisition base station partition set are completely included in (1, 3) of the first equivalence partition, and (2) of the data acquisition base station partition set is completely included in (2) of the first equivalence partition. Then, the first correct decision value is 3.

[0092] If the first equivalent partition is {(1, 3), (2)}, and the data acquisition base station partition set is {(1, 2), (3)}, then only (3) of the data acquisition base station partition set is completely included in (1, 3) of the first equivalent partition, and the first correct decision value is 1.

[0093] S40: Determine, based on the first correct decision value, that the data collection base station is an important base station or an initial redundant base station, and merge the important base stations into an important base station set;

[0094] The step S40 includes:

[0095] S410: Eliminate a data collection base station from the plurality of data collection base stations to obtain a remaining base station partition set of the remaining data collection base stations, and obtain a second correct decision value of the remaining base station partition set;

[0096] That is, if there are three data collection base stations, after eliminating one of the data collection base stations, the remaining base station partition set is obtained based on the remaining two data collection base stations. The remaining base station partition set is obtained in the same way as the data collection base station partition set, and the second correct decision value is obtained in the same way as the first correct decision value, which will not be repeated here.

[0097] S420: Obtaining a degree of change in decision-making ability based on the first correct decision value and the second correct decision value;

[0098] The calculation formula for the degree of change in decision-making ability is:

[0099] ,

[0100] in, Indicates that the data collection base station is removed The degree of change in decision-making ability after Indicates that the data collection base station is removed The second correct decision value after represents the first correct decision value.

[0101] S430: Compare the degree of change in the decision-making ability with a first threshold. If the degree of change in the decision-making ability is greater than the first threshold, the data collection base station that is eliminated is an important base station. If the degree of change in the decision-making ability is less than the first threshold, the data collection base station that is eliminated is an initial redundant base station.

[0102] It can be understood that by eliminating the data collection base stations one by one, the impact of eliminating all the data collection base stations on the decision-making ability can be obtained separately, thereby determining the importance of the data collection base stations.

[0103] S50: Obtaining a third correct decision value of the important base station set, and determining whether the decision-making capability of the important base station set meets the requirements based on the first correct decision value and the third correct decision value; if the decision-making capability of the important base station set meets the requirements, selecting all the initial redundant base stations as the final redundant base stations, and eliminating the final redundant base stations;

[0104] The third correct decision value is obtained in the same manner as the first correct decision value, and will not be described in detail here. The judgment formula for whether the decision-making ability of the important base station set meets the requirements is:

[0105] ,

[0106] in, represents the third correct decision value, represents the first correct decision value, represents a first threshold. That is, when the difference between the ratio of the third correct decision value to the first correct decision value and 1 is less than the first threshold, it is determined that the decision-making capability of the important base station set meets the requirements. Conversely, when the difference between the ratio of the third correct decision value to the first correct decision value and 1 is greater than the first threshold, the decision-making capability of the important base station set does not meet the requirements.

[0107] If the decision-making capability of the important base station set does not meet the requirements, selecting a base station to be added from the plurality of initial redundant base stations, and adding the base station to be added to the important base station set;

[0108] In this embodiment, several of the initial redundant base stations are ranked according to the degree of influence of the change in decision-making capability. The degree of influence of the change in decision-making capability can be obtained based on step S40, and the initial redundant base station with the highest degree of influence of the change in decision-making capability is selected as the base station to be added, thereby forming a new set of important base stations.

[0109] Obtaining a fourth correct decision value of the important base station set after the base station to be added is added, so as to determine whether the decision-making capability of the important base station set after the base station to be added meets the requirements according to the first correct decision value and the fourth correct decision value;

[0110] The steps for obtaining the fourth correct decision value are consistent with those for obtaining the first correct decision value, and the judgment on whether the decision-making ability meets the requirements is consistent with the aforementioned judgment, which will not be repeated here.

[0111] If the decision-making ability of the important base station set after adding the base station to be added meets the requirement, the remaining initial redundant base stations are selected as the final redundant base stations, and the final redundant base stations are eliminated;

[0112] It should be noted that if the decision-making capability still does not meet the requirements, the next base station to be added will continue to be selected until the decision-making capability meets the requirements. It should be noted that the first equivalent division can be completed within the meteorological forecasting agency, and the second equivalent division can be completed within the data collection base station, and then the first equivalent division and the second equivalent division are encrypted and uploaded to the central cloud server for subsequent processing to further improve the security of the data. After the final redundant base station is proposed, the meteorological forecasting agency can make weather forecasts based on the data collected by the remaining data collection base stations.

[0113] By constructing the first equivalence partition with the first unique identifier and constructing the second equivalence partition with the second unique identifier, the result data record and the process data record themselves are not directly transmitted and processed, thereby ensuring the privacy and security of the data; by analyzing the impact of different data acquisition base stations on the decision-making ability of the meteorological forecasting system through the first correct decision value, the importance of different data acquisition base stations is determined, and then, under the premise of ensuring the stability of the decision-making ability of the meteorological forecasting system, the number of data acquisition base stations is simplified to the greatest extent, that is, while reducing the overall data volume, data acquisition base stations with lower data quality are filtered out, which solves the problems of data redundancy, computational complexity and inconsistent data quality to a certain extent, and improves the accuracy and efficiency of the prediction.

[0114] See also Figure 2 , the second embodiment of the present invention provides a multi-institution collaborative monitoring and filtering system, which is applied to the multi-institution collaborative monitoring and filtering method described in the above embodiment, and will not be repeated here. As used below, the terms "module", "unit", "sub-unit", etc. can be a combination of software and / or hardware that implements a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and conceivable.

[0115] The system comprises:

[0116] A first acquisition module 10 is configured to obtain a plurality of result data records corresponding to weather from a meteorological forecasting agency, extract a plurality of decision attribute values ​​from the plurality of result data records based on a decision attribute, assign a first unique identifier to each of the decision attribute values, and construct a first equivalence partition, wherein the first equivalence partition includes a plurality of first equivalence classes;

[0117] The first acquisition module 10 includes:

[0118] The first unit is used to compare whether different decision attribute values ​​are the same;

[0119] a second unit, configured to, if the same decision attribute value exists, merge the first unique identifiers corresponding to the same decision attribute value into a plurality of first sets, and divide the first unique identifiers corresponding to different decision attribute values ​​into a plurality of second sets;

[0120] A third unit is configured to define the first set and the second set as first equivalence classes, and combine a plurality of the first equivalence classes into a first equivalence partition;

[0121] a second acquisition module 20 configured to acquire a plurality of process data records corresponding to weather conditions from the data acquisition base station, the process data records corresponding to the number of result data records, extract acquisition attribute value groups from the process data records based on a plurality of acquisition attributes, assign a second unique identifier to each of the acquisition attribute value groups, and construct a second equivalence partition, the second equivalence partition including a plurality of second equivalence classes;

[0122] The second acquisition module 20 includes:

[0123] a fourth unit configured to obtain a plurality of collection attributes corresponding to the data collection base station, match the collection attributes with the process data record to extract collection attribute values ​​corresponding to the collection attributes from the process data record, and combine the plurality of collection attribute values ​​into a collection attribute value group;

[0124] A fifth unit is used to compare whether different collection attribute value groups are the same;

[0125] a sixth unit, configured to, if the same collection attribute value group exists, merge the second unique identifiers corresponding to the same collection attribute value group into a plurality of third sets, and divide the second unique identifiers corresponding to different collection attribute value groups into a plurality of fourth sets;

[0126] A seventh unit is configured to define the third set and the fourth set as second equivalence classes, and combine a plurality of the second equivalence classes into a second equivalence partition;

[0127] a combining module 30, configured to combine the second equivalence partitions of different data collection base stations into a data collection base station partition set comprising a plurality of third equivalence classes, and determine a first correct decision value of the data collection base station partition set in combination with the first equivalence partition;

[0128] The combined module 30 includes:

[0129] An eighth unit is configured to select one of the second equivalence partitions as a benchmark equivalence partition, and select the remaining second equivalence partitions as equivalence partitions to be checked;

[0130] A ninth unit is configured to perform intersection determination on each of the second equivalence classes in the benchmark equivalence partition and each of the second equivalence classes in the equivalence partition to be checked;

[0131] a tenth unit, configured to extract the intersection part if there is one, and form a fifth set, define the fifth set as a third equivalence class, and combine a plurality of the third equivalence classes into a data collection base station partition set;

[0132] an eleventh unit, configured to determine whether each of the third equivalence classes in the data collection base station partition set is completely included in a first equivalence class in the first equivalence partition;

[0133] A twelfth unit is configured to determine a first correct decision value of the data collection base station partition set based on the number of the third equivalence classes that are completely included in a certain first equivalence class in the first equivalence partition;

[0134] A classification module 40 is configured to determine, based on the first correct decision value, whether the data collection base station is an important base station or an initial redundant base station, and merge the important base stations into an important base station set;

[0135] The classification module 40 includes:

[0136] A thirteenth unit is configured to eliminate a data collection base station from the plurality of data collection base stations to obtain a remaining base station partition set of the remaining data collection base stations, and obtain a second correct decision value of the remaining base station partition set;

[0137] A fourteenth unit is configured to obtain a degree of change in decision-making ability based on the first correct decision value and the second correct decision value;

[0138] A fifteenth unit is configured to compare the degree of change in the decision-making capability with a first threshold value; if the degree of change in the decision-making capability is greater than the first threshold value, the data collection base station that is eliminated is an important base station; if the degree of change in the decision-making capability is less than the first threshold value, the data collection base station that is eliminated is an initial redundant base station;

[0139] an execution module 50 configured to obtain a third correct decision value of the set of important base stations, and determine whether the decision-making capability of the set of important base stations meets the requirements based on the first correct decision value and the third correct decision value; if the decision-making capability of the set of important base stations meets the requirements, select all the initial redundant base stations as the final redundant base stations, and eliminate the final redundant base stations;

[0140] The execution module 50 is further configured to, if the decision-making capability of the important base station set does not meet the requirements, select a base station to be added from a number of the initial redundant base stations and add the base station to the important base station set; obtain a fourth correct decision value of the important base station set after the base station to be added is added, so as to determine whether the decision-making capability of the important base station set after the base station to be added is added meets the requirements based on the first correct decision value and the fourth correct decision value; if the decision-making capability of the important base station set after the base station to be added is added meets the requirements, select the remaining initial redundant base stations as the final redundant base stations, and eliminate the final redundant base stations.

[0141] The present invention also provides a computer comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the multi-agency collaborative monitoring and filtering method as described in the above technical solution is implemented.

[0142] The present invention also provides a storage medium on which a computer program is stored. When the computer program is executed by a processor, it implements the multi-institutional collaborative monitoring and filtering method described in the above technical solution.

[0143] Throughout this specification, reference to terms such as "one embodiment," "some embodiments," "examples," "specific examples," or "some examples" means that the specific features, structures, materials, or characteristics described in conjunction with that embodiment or example are included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0144] The above-described embodiments merely illustrate several implementations of the present invention, and while their descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art would be able to make numerous variations and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be determined by the appended claims.

Claims

1. A multi-organization collaborative monitoring filtering method for eliminating final redundant base stations from a number of data collection base stations, characterized in that: The multi-agency collaborative monitoring and filtering method comprises the following steps: Obtaining a number of result data records corresponding to weather from a meteorological forecasting agency, extracting a number of decision attribute values ​​from the number of result data records based on decision attributes, and assigning a first unique identifier to each of the decision attribute values ​​to construct a first equivalence partition, wherein the first equivalence partition includes a number of first equivalence classes; Acquire a number of process data records corresponding to weather from the data collection base station, the number of the process data records corresponding to the number of the result data records, extract a collection attribute value group from the process data record based on a number of collection attributes, assign a second unique identifier to each of the collection attribute value groups to construct a second equivalence partition, the second equivalence partition including a number of second equivalence classes; Combining the second equivalent partitions of different data collection base stations into a data collection base station partition set including a plurality of third equivalent classes, and determining a first correct decision value of the data collection base station partition set in combination with the first equivalent partition; Based on the first correct decision value, the data collection base station is judged to be an important base station or an initial redundant base station, and the important base stations are merged into an important base station set; Obtain the third correct decision value of the important base station set to determine whether the decision-making ability of the important base station set meets the requirements based on the first correct decision value and the third correct decision value; if the decision-making ability of the important base station set meets the requirements, select all the initial redundant base stations as the final redundant base stations, and eliminate the final redundant base stations.

2. The multi-institutional collaborative monitoring and filtering method according to claim 1 is characterized in that: The step of constructing a first equivalence partition, wherein the first equivalence partition includes a plurality of first equivalence classes, comprises: comparing whether different decision attribute values ​​are the same; If the same decision attribute value exists, the first unique identifiers corresponding to the same decision attribute value are respectively combined into a plurality of first sets, and the first unique identifiers corresponding to different decision attribute values ​​are respectively divided into a plurality of second sets; The first set and the second set are both defined as first equivalence classes, and a number of the first equivalence classes are combined into a first equivalence partition.

3. The multi-institutional collaborative monitoring and filtering method according to claim 1 is characterized in that: The step of extracting a plurality of acquisition attribute value groups from the process data record based on a plurality of acquisition attributes is specifically as follows: Acquire a plurality of acquisition attributes corresponding to the data acquisition base station, match the acquisition attributes with the process data record to extract acquisition attribute values ​​corresponding to the acquisition attributes from the process data record, and combine a plurality of the acquisition attribute values ​​into an acquisition attribute value group.

4. The multi-institutional collaborative monitoring and filtering method according to claim 1 is characterized in that: The step of constructing a second equivalence partition, wherein the second equivalence partition includes a plurality of second equivalence classes, comprises: comparing whether different groups of collected attribute values ​​are the same; If the same collection attribute value group exists, the second unique identifiers corresponding to the same collection attribute value group are respectively combined into a plurality of third sets, and the second unique identifiers corresponding to different collection attribute value groups are respectively divided into a plurality of fourth sets; The third set and the fourth set are both defined as second equivalence classes, and a number of the second equivalence classes are combined into a second equivalence partition.

5. The multi-institution collaborative monitoring and filtering method according to claim 1 is characterized in that: The step of merging the second equivalent partitions of different data collection base stations into a data collection base station partition set comprises: Selecting one of the second equivalent partitions as a benchmark equivalent partition, and selecting the remaining second equivalent partitions as equivalent partitions to be checked; Perform intersection judgment on each of the second equivalence classes in the benchmark equivalence partition and each of the second equivalence classes in the to-be-checked equivalence partition; If there is an intersection part, the intersection part is extracted to form a fifth set, the fifth set is defined as a third equivalence class, and a number of the third equivalence classes are combined into a data collection base station partition set.

6. The multi-institutional collaborative monitoring and filtering method according to claim 1 is characterized in that: The step of determining the first correct decision value of the data acquisition base station partition set in combination with the first equivalent partition comprises: Determine whether each of the third equivalence classes in the data acquisition base station partition set is completely included in a first equivalence class in the first equivalence partition; A first correct decision value of the data collection base station partition set is determined based on the number of the third equivalence classes that are completely included in a certain first equivalence class in the first equivalence partition.

7. The multi-organization collaborative monitoring and filtering method according to claim 1 is characterized in that: The step of judging whether the data acquisition base station is an important base station or an initial redundant base station based on the first correct decision value comprises: Eliminate a data collection base station from the plurality of data collection base stations to obtain a remaining base station partition set of the remaining data collection base stations, and obtain a second correct decision value of the remaining base station partition set; Obtaining a degree of change in decision-making ability based on the first correct decision value and the second correct decision value; The degree of change in the decision-making ability is compared with a first threshold. If the degree of change in the decision-making ability is greater than the first threshold, the eliminated data collection base station is an important base station. If the degree of change in the decision-making ability is less than the first threshold, the eliminated data collection base station is an initial redundant base station.

8. The multi-organization collaborative monitoring and filtering method according to claim 7 is characterized in that: The calculation formula for the degree of change in decision-making ability is: ， in, Indicates that the data collection base station is removed The degree of change in decision-making ability after Indicates that the data collection base station is removed The second correct decision value after represents the first correct decision value.

9. The multi-organization collaborative monitoring and filtering method according to claim 1, characterized in that: In the step of obtaining the third correct decision value of the important base station set, determining whether the decision-making ability of the important base station set meets the requirements according to the first correct decision value and the third correct decision value, if the decision-making ability of the important base station set meets the requirements, selecting all the initial redundant base stations as the final redundant base stations, and eliminating the final redundant base stations, further includes: If the decision-making ability of the important base station set does not meet the requirement, selecting a base station to be added from a plurality of the initial redundant base stations, and adding the base station to be added to the important base station set; Obtaining a fourth correct decision value of the important base station set after the base station to be added is added, so as to determine whether the decision-making capability of the important base station set after the base station to be added meets the requirements according to the first correct decision value and the fourth correct decision value; If the decision-making capability of the important base station set after adding the base station to be added meets the requirement, the remaining initial redundant base stations are selected as the final redundant base stations, and the final redundant base stations are eliminated.

10. A multi-institution collaborative monitoring and filtering system, applied to the multi-institution collaborative monitoring and filtering method as claimed in any one of claims 1 to 9, characterized in that: The system comprises: A first acquisition module is used to obtain a plurality of result data records corresponding to weather from a meteorological forecasting agency, extract a plurality of decision attribute values ​​from the plurality of result data records based on decision attributes, and assign a first unique identifier to each of the decision attribute values ​​to construct a first equivalence partition, wherein the first equivalence partition includes a plurality of first equivalence classes; A second acquisition module is used to acquire a number of process data records corresponding to the weather from the data acquisition base station, the number of the process data records corresponding to the number of the result data records, extract a collection attribute value group from the process data record based on a number of collection attributes, and assign a second unique identifier to each of the collection attribute value groups to construct a second equivalence partition, wherein the second equivalence partition includes a number of second equivalence classes; A combining module, used for combining the second equivalent partitions of different data collection base stations into a data collection base station partition set including a plurality of third equivalent classes, and determining a first correct decision value of the data collection base station partition set in combination with the first equivalent partition; a classification module, configured to determine, based on the first correct decision value, that the data collection base station is an important base station or an initial redundant base station, and merge the important base stations into an important base station set; An execution module is used to obtain a third correct decision value of the important base station set, so as to determine whether the decision-making ability of the important base station set meets the requirements according to the first correct decision value and the third correct decision value; if the decision-making ability of the important base station set meets the requirements, all the initial redundant base stations are selected as final redundant base stations, and the final redundant base stations are eliminated.

Images