A data cleaning method and system of an ultrasonic metering instrument

Abstract

The application provides an ultrasonic meter data cleaning method and system, based on the data node description attribute of a target data segment and the data node description attribute of an abnormal range in the target data segment, the data node description attribute without an abnormal range in the target data segment is the information described by the data positioning of the data node, so that the data positioning without an abnormal range can be determined very accurately, and the ultrasonic interaction data obtained by cleaning the data node description attribute without an abnormal range is more accurate and reliable; in addition, since the data node description attribute without an abnormal range in the target data segment is determined first, and then the data node description attribute without an abnormal range is cleaned, more accurate and reliable ultrasonic data can be obtained, and the accuracy and reliability of subsequent ultrasonic meter measurement are improved.

Description

Technical Field

[0001] This application relates to the field of data cleaning technology, and more specifically, to a data cleaning method and system for ultrasonic metering instruments. Background Technology

[0002] Ultrasonic meters measure flow rate by detecting the effect of fluid flow on an ultrasonic beam (or ultrasonic pulse). They typically employ advanced multi-pulse technology, digital signal processing technology, and error correction technology, making them more adaptable to industrial environments and thus widely applicable in fields such as petroleum, chemical, metallurgy, power, water supply and drainage, and gas.

[0003] When ultrasonic metering instruments are used to measure fluid flow, the acquisition of ultrasonic data may be affected by interference from multiple instruments, resulting in inaccurate or unreliable ultrasonic data. Therefore, a technology is urgently needed to clean the ultrasonic data before measurement to reduce interference and ensure the accuracy and precision of ultrasonic flow measurement. Summary of the Invention

[0004] To address the technical problems existing in related technologies, this application provides a data cleaning method and system for ultrasonic metering instruments.

[0005] In a first aspect, a data cleaning method for ultrasonic metering instruments is provided. The method includes: determining data node description attributes of a target data segment and abnormal ultrasonic interaction data including the target data segment based on ultrasonic interaction data to be analyzed; determining target ultrasonic interaction data input to an ultrasonic interaction data parsing thread based on the abnormal ultrasonic interaction data; processing the target ultrasonic interaction data in conjunction with the ultrasonic interaction data parsing thread to obtain output ultrasonic interaction data; determining data node description attributes of the target data segment showing abnormal ranges based on the output ultrasonic interaction data; determining data node description attributes of the target data segment without abnormal ranges based on the data node description attributes of the target data segment and the data node description attributes showing abnormal ranges in the target data segment; and cleaning the data node description attributes without abnormal ranges based on the data node description attributes of the target data segment without abnormal ranges.

[0006] In one independently implemented embodiment, the method further includes: determining the element values ​​corresponding to each data node on the data node description attribute of the target data segment based on the output ultrasonic interactive data; determining the data node description attribute without abnormal range in the target data segment based on the data node description attribute of the target data segment and the data node description attribute with abnormal range in the target data segment includes: determining the undetermined element value that meets the second target value requirement among the element values ​​corresponding to each data node on the data node description attribute of the target data segment; determining the data node description attribute corresponding to the undetermined element value as the data node description attribute with intermediate range; and determining the data node description attribute without abnormal range in the target data segment based on the data node description attribute with abnormal range in the target data segment and the data node description attribute with intermediate range.

[0007] In one standalone embodiment, determining the data node description attributes of the target data segment based on the ultrasonic interaction data to be analyzed includes: performing important content detection on the ultrasonic interaction data to be analyzed to obtain important data of the target data segment; and determining the data node description attributes of the target data segment based on the important data of the target data segment.

[0008] In one standalone embodiment, determining abnormal ultrasonic interaction data including the target data segment based on the ultrasonic interaction data to be analyzed includes: determining converted ultrasonic interaction data based on the ultrasonic interaction data to be analyzed and a sample conversion database; performing anomaly identification processing on the converted ultrasonic interaction data to obtain the abnormal ultrasonic interaction data; determining the data node description attributes of the abnormal range in the target data segment based on the output ultrasonic interaction data includes: determining the data node description attributes of the abnormal range in the target data segment based on the output ultrasonic interaction data and the sample conversion database.

[0009] In one independent embodiment, the output ultrasonic interaction data includes: a target queue with the same number of data nodes as the target ultrasonic interaction data or the abnormal ultrasonic interaction data; the element values ​​of each element in the target queue characterize the probability that the data node corresponding to each element belongs to the target data segment or a non-target data segment; determining the descriptive attributes of the data nodes with abnormal ranges in the target data segment based on the output ultrasonic interaction data includes: determining the element values ​​of each element in the target queue as the element values ​​corresponding to each data node in the abnormal ultrasonic interaction data; and determining the descriptive attributes of the data nodes with abnormal ranges in the target data segment based on the element values ​​corresponding to each data node in the abnormal ultrasonic interaction data and a sample conversion database.

[0010] In one independently implemented embodiment, determining the descriptive attributes of data nodes exhibiting anomalies in the target data segment based on the element values ​​corresponding to each data node in the abnormal ultrasonic interaction data and the sample conversion database includes: determining the element values ​​corresponding to each data node in the local ultrasonic interaction data (including the target data segment) corresponding to the abnormal ultrasonic interaction data in the ultrasonic interaction data to be analyzed, based on the element values ​​corresponding to each data node in the abnormal ultrasonic interaction data and the sample conversion database; and determining the descriptive attributes of data nodes exhibiting anomalies in the target data segment based on the element values ​​corresponding to each data node in the local ultrasonic interaction data.

[0011] In one independently implemented embodiment, determining the data node description attribute of the abnormal range in the target data segment based on the feature values ​​corresponding to each data node in the local ultrasonic interactive data includes: determining a target feature value that meets a first target value requirement from the feature values ​​corresponding to each data node in the local ultrasonic interactive data based on the data node description attribute of the target data segment; determining the data node description attribute of a first designated data node in the local ultrasonic interactive data corresponding to a second designated data node in the ultrasonic interactive data to be analyzed; and determining the data node description attribute of the abnormal range in the target data segment based on the data node description attribute of the target feature value in the local ultrasonic interactive data and the data node description attribute of the second designated data node.

[0012] In one independently implemented embodiment, determining the data node description attribute of the abnormal range in the target data segment based on the element values ​​corresponding to each data node in the local ultrasonic interactive data includes: determining the element values ​​corresponding to each data node in a specified range of the ultrasonic interactive data to be analyzed, excluding the local ultrasonic interactive data; determining, based on the data node description attribute of the target data segment, a specified element value that satisfies a first target value requirement from the element values ​​corresponding to each data node in the specified range and the element values ​​of each data node in the local ultrasonic interactive data; and determining the data node description attribute of the abnormal range in the target data segment based on the data node description attribute of the specified element value corresponding to the ultrasonic interactive data to be analyzed.

[0013] In one standalone embodiment, the method further includes: optimizing the intermediate range based on the data node description attributes of the intermediate range.

[0014] In one standalone embodiment, the method further includes: obtaining a configuration example set; the configuration example set includes several configuration example ultrasonic interaction data; at least one data segment in each of the configuration example ultrasonic interaction data is abnormal; obtaining a target example set; the target example set includes several target example ultrasonic interaction data; each of the target example ultrasonic interaction data includes data in the data segment that is not abnormal; and configuring the ultrasonic interaction data parsing thread based on the configuration example set and the target example set.

[0015] Secondly, a data cleaning system for ultrasonic metering instruments is provided, comprising a processor and a memory that communicate with each other, wherein the processor is used to read a computer program from the memory and execute it to implement the above-described method.

[0016] The ultrasonic metering instrument data cleaning method and system provided in this application determines the data node description attributes of the target data segment and the data node description attributes of the data segment with abnormal ranges. Based on these attributes, the data node description attributes of the target data segment without abnormal ranges are determined to be the information describing the data location of the data node. This allows for very precise determination of the data location without abnormal ranges, making the ultrasonic interactive data obtained by cleaning the data node description attributes without abnormal ranges more accurate and reliable. Furthermore, by first determining the data node description attributes without abnormal ranges in the target data segment and then cleaning them, more accurate and reliable ultrasonic data can be obtained, improving the accuracy and reliability of subsequent ultrasonic metering. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart illustrating a data cleaning method for an ultrasonic metering instrument provided in an embodiment of this application. Detailed Implementation

[0019] To better understand the above technical solutions, the technical solutions of this application will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments of this application and the specific features in the embodiments are detailed descriptions of the technical solutions of this application, rather than limitations on the technical solutions of this application. In the absence of conflict, the embodiments of this application and the technical features in the embodiments can be combined with each other.

[0020] Please see Figure 1 This paper illustrates a data cleaning method for ultrasonic metering instruments, which may include the technical solutions described in steps S101-S103.

[0021] S101. Based on the ultrasonic interactive data to be analyzed, determine the data node description attributes of the target data segment and the data node description attributes of the abnormal range in the target data segment.

[0022] For example, ultrasonic interactive data can be understood as ultrasonic data received through an ultrasonic transducer.

[0023] Furthermore, the ultrasonic interaction data to be analyzed can be ultrasonic interaction data awaiting cleaning treatment. The ultrasonic interaction data to be analyzed can include partial ultrasonic interaction data, which can be understood as acquiring a portion of the ultrasonic interaction data to be analyzed. This portion of data can include information such as ultrasonic amplitude information and ultrasonic frequency information.

[0024] Furthermore, the ultrasonic interaction data to be analyzed may include target data segments and abnormal data segments (abnormal data segments may be due to data loss or data interference, etc.).

[0025] Furthermore, the data node description attributes of the target data segment may include data node description attributes of visible target data segments and data node description attributes of invisible target data segments (i.e., data node description attributes of the abnormal range in the target data segment).

[0026] Furthermore, the data node description attribute of the target data segment can refer to the data node description attribute of the secondary data nodes in the target data segment, or it can refer to the data node description attribute of each data node in the target data segment. The data node description attribute of the abnormal range in the target data segment can include the data node description attribute of the secondary data nodes in the target data segment where the abnormal range occurs, or it can include the data node description attribute of each data node in the target data segment where the abnormal range occurs.

[0027] In one possible implementation, determining the data node description attributes of the target data segment based on the ultrasonic interactive data to be analyzed may include: performing important content detection on the ultrasonic interactive data to be analyzed to obtain important data of the target data segment; and determining the data node description attributes of the target data segment based on the important data of the target data segment.

[0028] For example, the key content can be understood as the feature data in the ultrasonic interaction data to be analyzed. Here, feature data can be understood as the data described by the ultrasonic waves.

[0029] In one possible implementation, determining the descriptive attributes of data nodes in the target data segment that exhibit abnormal ranges based on the ultrasonic interaction data to be analyzed may include: determining the descriptive attributes of data nodes in the target data segment that exhibit abnormal ranges based on the ultrasonic interaction data parsing thread and the ultrasonic interaction data to be analyzed.

[0030] For example, the ultrasonic interactive data parsing thread can be understood as an artificial intelligence analysis network.

[0031] S102. Based on the data node description attributes of the target data segment and the data node description attributes of the target data segment that have an abnormal range, determine the data node description attributes of the target data segment that do not have an abnormal range.

[0032] For example, a data node description attribute can be understood as the content described by one of the nodes in the ultrasonic data.

[0033] In one possible implementation, data node description attributes in the target data segment, excluding those with abnormal ranges in the target data segment, can be determined as data node description attributes without abnormal ranges in the target data segment.

[0034] In an alternative embodiment, an intermediate range can be determined, and the comparison between the probability that each data node in the intermediate range belongs to the target data segment and the probability that it belongs to a non-target data segment is less than a target value; the data node description attributes in the target data segment, excluding the data node description attributes that have abnormal ranges in the target data segment and the data node description attributes of the intermediate range, are determined as data node description attributes that do not have abnormal ranges in the target data segment.

[0035] The data node description attributes that do not fall within the abnormal range in the target data segment can include the data node description attributes of secondary data nodes that do not fall within the abnormal range in the target data segment, or they can include the data node description attributes of each data node that falls within the abnormal range in the target data segment.

[0036] S103. Based on the data node description attributes that do not have an abnormal range in the target data segment, perform cleaning processing on the data node description attributes that do not have an abnormal range.

[0037] For example, by describing the data nodes in the target data segment that do not have anomalies, the precise location of the data in the target data segment that do not have anomalies can be obtained, thereby enabling precise cleaning of the data without anomalies.

[0038] For example, the target data segment region and the range of abnormal occurrence of the target data segment can be applied to the ultrasonic interaction data to be analyzed, abnormal ultrasonic interaction data, converted ultrasonic interaction data, local ultrasonic interaction data, or target ultrasonic interaction data mentioned in any embodiment of this disclosure.

[0039] In this embodiment, since the data node description attributes of the target data segment and the data node description attributes of the data segment with abnormal ranges are determined, the data node description attributes of the target data segment without abnormal ranges, determined based on these attributes, are the information described by the data location of the data node. This allows for very precise determination of the data location without abnormal ranges, making the ultrasonic interactive data obtained by cleaning the data node description attributes without abnormal ranges more accurate and reliable. Furthermore, by first determining the data node description attributes without abnormal ranges in the target data segment and then cleaning them, more accurate and reliable ultrasonic data can be obtained, improving the accuracy and reliability of subsequent ultrasonic metering instruments.

[0040] This disclosure provides another data cleaning method for ultrasonic metering instruments, which may specifically include the following:

[0041] S301. Perform important content detection on the ultrasonic interactive data to be analyzed to obtain important data of the target data segment.

[0042] For example, performing important content detection on the ultrasonic interactive data to be analyzed can refer to locating the data of each data segment (including the target data segment) based on the ultrasonic interactive data to be analyzed.

[0043] S302. Based on the important data of the target data segment, determine the data node description attributes of the target data segment.

[0044] S303. Based on the ultrasonic interactive data parsing thread and the ultrasonic interactive data to be analyzed, determine the descriptive attributes of the data nodes in the target data segment where anomalies occur.

[0045] In one possible implementation, the output ultrasonic interaction data can be determined based on the ultrasonic interaction data parsing thread and the ultrasonic interaction data to be analyzed, and the data node description attributes of the abnormal range in the target data segment can be determined based on the output ultrasonic interaction data.

[0046] In one possible implementation, the ultrasonic interactive data to be analyzed can be input into the ultrasonic interactive data parsing thread, so that the ultrasonic interactive data parsing thread processes the ultrasonic interactive data to be analyzed and obtains the output ultrasonic interactive data corresponding to the ultrasonic interactive data to be analyzed. Based on the output ultrasonic interactive data corresponding to the ultrasonic interactive data to be analyzed, the data node description attributes of the abnormal range in the target data segment can be determined.

[0047] In an alternative embodiment, the ultrasonic interaction data to be analyzed can be processed to obtain target ultrasonic interaction data. The target ultrasonic interaction data is then input into an ultrasonic interaction data parsing thread, which processes the target ultrasonic interaction data and outputs output ultrasonic interaction data corresponding to the target ultrasonic interaction data. Based on the output ultrasonic interaction data corresponding to the target ultrasonic interaction data, the descriptive attributes of data nodes exhibiting abnormal ranges within the target data segment are determined.

[0048] The following describes several methods for determining target ultrasonic interaction data: For example, the target ultrasonic interaction data can be obtained by performing anomaly identification processing on the ultrasonic interaction data to be analyzed; another example is that the ultrasonic interaction data to be analyzed can be transformed to obtain transformed ultrasonic interaction data, and the target ultrasonic interaction data can be obtained by performing anomaly identification processing on the transformed ultrasonic interaction data.

[0049] S304. Based on the data node description attributes of the target data segment and the data node description attributes of the target data segment that have an abnormal range, determine the data node description attributes of the target data segment that do not have an abnormal range.

[0050] S305. Based on the data node description attributes that do not have an abnormal range in the target data segment, perform cleaning processing on the data node description attributes that do not have an abnormal range.

[0051] In this embodiment of the disclosure, since the data node description attributes of the target data segment are determined based on the important data of the target data segment, the data node description attributes of the target data segment are: the data node description attributes of the visible part and the data node description attributes of the invisible part of the target data segment. Therefore, based on the data node description attributes of the target data segment and the data node description attributes of the target data segment with abnormal ranges, the data node description attributes of the target data segment without abnormal ranges can be obtained. This provides a way to obtain the data node description attributes of the target data segment without abnormal ranges, and the way to determine the data node description attributes of the target data segment without abnormal ranges is simple.

[0052] In this embodiment of the disclosure, since the data node description attributes of the abnormal range in the target data segment are determined based on the ultrasonic interactive data parsing thread, the accuracy of the data node description attributes of the abnormal range in the target data segment can be improved.

[0053] This disclosure provides another data cleaning method for ultrasonic metering instruments, which may specifically include the following:

[0054] S401. Based on the ultrasonic interaction data to be analyzed, determine the data node description attributes of the target data segment.

[0055] S402. Based on the ultrasonic interaction data to be analyzed, identify the abnormal ultrasonic interaction data including the target data segment.

[0056] In one possible implementation, the converted ultrasonic interaction data can be obtained based on the ultrasonic interaction data to be analyzed and the sample conversion database. Then, the converted ultrasonic interaction data is subjected to anomaly identification processing to obtain abnormal ultrasonic interaction data.

[0057] In one possible implementation, the sample conversion database can be a sample conversion database for transforming the ultrasonic interaction data to be analyzed into the converted ultrasonic interaction data. The amount of data in the converted ultrasonic interaction data, including the local region of the target data segment (including the local region of the target data segment, which is the abnormal ultrasonic interaction data), can be consistent with the amount of data in the ultrasonic interaction data input to the model.

[0058] The sample conversion database corresponding to the ultrasonic interactive data to be analyzed can be determined based on the area occupied by the target data segment in the ultrasonic interactive data to be analyzed and / or the amount of input ultrasonic interactive data that the ultrasonic interactive data parsing thread can input.

[0059] Key point identification can be performed on the converted ultrasonic interactive data to obtain important data of the target data segment. Then, anomaly detection processing can be performed on the converted ultrasonic interactive data based on the important data of the target data segment. In an alternative embodiment, anomaly detection processing can be performed on the converted ultrasonic interactive data based on the important data of the target data segment in the ultrasonic interactive data to be analyzed, or based on the important data of the target data segment in the ultrasonic interactive data to be analyzed and a sample conversion database. In still other embodiments, anomaly detection processing can be performed on the converted ultrasonic interactive data based on the base point and other data positioning information of the target data segment in the ultrasonic interactive data to be analyzed or the converted ultrasonic interactive data, to obtain abnormal ultrasonic interactive data. The abnormal ultrasonic interactive data should include the entire target data segment.

[0060] In an alternative embodiment, anomaly identification processing can be performed on the ultrasonic interaction data to be analyzed to obtain abnormal ultrasonic interaction data. For example, key point identification can be performed on the ultrasonic interaction data to be analyzed to obtain important data of the target data segment in the ultrasonic interaction data to be analyzed. Based on the important data of the target data segment in the ultrasonic interaction data to be analyzed, anomaly identification processing can be performed on the ultrasonic interaction data to be analyzed to obtain abnormal ultrasonic interaction data.

[0061] By performing anomaly identification processing on the ultrasonic interactive data to be analyzed or the converted ultrasonic interactive data, most of the abnormal data in the ultrasonic interactive data to be analyzed or the converted ultrasonic interactive data can be removed.

[0062] S403. Based on abnormal ultrasonic interaction data, determine the target ultrasonic interaction data to be input to the ultrasonic interaction data parsing thread.

[0063] In one possible implementation, the abnormal ultrasonic interaction data can be processed to obtain the target ultrasonic interaction data.

[0064] In an alternative embodiment, anomalous ultrasonic interaction data can be used as target ultrasonic interaction data.

[0065] S404. Use the ultrasonic interactive data parsing thread to process the target ultrasonic interactive data to obtain the output ultrasonic interactive data.

[0066] In one possible implementation, the output ultrasonic interactive data may include: a target queue with the same number of data nodes as the target ultrasonic interactive data; element values ​​for each element in the target queue, representing the probability that the data node corresponding to each element belongs to a target data segment or a non-target data segment. If the element values ​​for each element in the target queue represent the probability that the data node corresponding to each element belongs to a target data segment, then it is determined that the data node corresponding to the target ultrasonic interactive data with an element value greater than a first target value belongs to a visible target data segment, and it is determined that the data node corresponding to the target ultrasonic interactive data with an element value less than or equal to the first target value belongs to another region outside the visible target data segment. If the element values ​​for each element in the target queue represent the probability that the data node corresponding to each element belongs to a non-target data segment, then it is determined that the data node corresponding to the target ultrasonic interactive data with an element value less than a second target value belongs to a visible target data segment, and it is determined that the data node corresponding to the target ultrasonic interactive data with an element value greater than or equal to the second target value belongs to another region outside the visible target data segment.

[0067] Each data node in the target ultrasonic interactive data or abnormal ultrasonic interactive data can have a one-to-one correspondence with each element in the target queue.

[0068] S405. Based on the output ultrasonic interactive data, determine the descriptive attributes of the data nodes in the target data segment where anomalies occur.

[0069] Since the target ultrasonic interactive data input to the ultrasonic interactive data parsing thread is obtained based on the ultrasonic interactive data to be analyzed and the sample conversion database, the visible target data segment region and other regions outside the visible target data segment region in the target ultrasonic interactive data can be determined based on the output ultrasonic interactive data of the ultrasonic interactive data parsing thread. Furthermore, based on the output ultrasonic interactive data, the sample conversion database, and the data node description attributes of the target data segment, the data node description attributes of the abnormal range in the target data segment of the ultrasonic interactive data to be analyzed can be determined.

[0070] S406. Based on the data node description attributes of the target data segment and the data node description attributes of the target data segment that have an abnormal range, determine the data node description attributes of the target data segment that do not have an abnormal range.

[0071] S407. Based on the data node description attributes that do not have an abnormal range in the target data segment, perform cleaning processing on the data node description attributes that do not have an abnormal range.

[0072] In this embodiment of the disclosure, based on the ultrasonic interaction data to be analyzed, abnormal ultrasonic interaction data including the target data segment is determined; based on the abnormal ultrasonic interaction data, the target ultrasonic interaction data is determined, so that the target ultrasonic interaction data input to the ultrasonic interaction data parsing thread only involves the features of the target data segment and the area near the target data segment, so that the ultrasonic interaction data parsing thread does not need to process ultrasonic interaction data features other than those of the abnormal ultrasonic interaction data, thereby improving the accuracy of the output ultrasonic interaction data of the ultrasonic interaction data parsing thread.

[0073] This disclosure provides another data cleaning method for ultrasonic metering instruments, which may specifically include the following:

[0074] S501. Based on the ultrasonic interaction data to be analyzed, determine the data node description attributes of the target data segment.

[0075] S502. Based on the ultrasonic interaction data to be analyzed and the sample conversion database, determine the converted ultrasonic interaction data.

[0076] S503. Perform anomaly identification processing on the converted ultrasonic interactive data to obtain abnormal ultrasonic interactive data.

[0077] The amount of abnormal ultrasonic interactive data can be the same as the amount of input data corresponding to the ultrasonic interactive data parsing thread.

[0078] In this way, since the target ultrasonic interactive data input to the ultrasonic interactive data parsing thread is obtained through the sample conversion database and the ultrasonic interactive data to be analyzed, the obtained target ultrasonic interactive data can maintain the flatness and parallelism of the ultrasonic interactive data to be analyzed, and the target ultrasonic interactive data can meet the input of the ultrasonic interactive data parsing thread. Then, by processing the target ultrasonic interactive data through the ultrasonic interactive data parsing thread, the output ultrasonic interactive data that represents the abnormal range in the target data segment can be accurately obtained. Then, by using the output ultrasonic interactive data and the sample conversion database, the data node description attributes of the abnormal range in the ultrasonic interactive data to be analyzed can be accurately obtained.

[0079] In this embodiment, the ultrasonic interactive data to be analyzed is first converted to obtain converted ultrasonic interactive data, and then anomaly identification processing is performed on the converted ultrasonic interactive data to obtain abnormal ultrasonic interactive data. This ensures that even when the conversion includes rotation, the abnormal ultrasonic interactive data can still retain the features of the ultrasonic interactive data to be analyzed, thereby improving the accuracy of the obtained output ultrasonic interactive data.

[0080] S504. Based on the abnormal ultrasonic interaction data, determine the target ultrasonic interaction data to be input to the ultrasonic interaction data parsing thread.

[0081] S505. The target ultrasonic interactive data is processed using the ultrasonic interactive data parsing thread to obtain the output ultrasonic interactive data.

[0082] S506. Based on the output ultrasonic interactive data and sample conversion database, determine the descriptive attributes of the data nodes in the target data segment where anomalies occur.

[0083] The output ultrasonic interaction data may include: a target queue with the same number of data nodes as the target ultrasonic interaction data, the element values ​​of each element in the target queue, and the probability that the data node corresponding to each element belongs to the target data segment or a non-target data segment.

[0084] In the target queue, the element value of each element represents the probability that the data node corresponding to that element belongs to the target data segment. Therefore, the larger the element value, the higher the probability that the data node in the target ultrasonic interactive data corresponding to that element belongs to the target data segment, and vice versa. Similarly, in the target queue, the element value of each element represents the probability that the data node corresponding to that element belongs to a non-target data segment. Therefore, the smaller the element value, the lower the probability that the data node in the target ultrasonic interactive data corresponding to that element belongs to a non-target data segment, and vice versa.

[0085] S507. Based on the data node description attributes of the target data segment and the data node description attributes of the target data segment that have an abnormal range, determine the data node description attributes of the target data segment that do not have an abnormal range.

[0086] S508. Based on the data node description attributes that do not have an abnormal range in the target data segment, perform cleaning processing on the data node description attributes that do not have an abnormal range.

[0087] In this embodiment, since the converted ultrasonic interaction data is first obtained through the sample conversion database and the ultrasonic interaction data to be analyzed, and then the abnormal ultrasonic interaction data is determined based on the converted ultrasonic interaction data, the abnormal ultrasonic interaction data can maintain the flatness and parallelism of the ultrasonic interaction data to be analyzed, and the amount of abnormal ultrasonic interaction data can meet the input of the ultrasonic interaction data parsing thread. Then, the target ultrasonic interaction data determined based on the abnormal ultrasonic interaction data is processed by the ultrasonic interaction data parsing thread, and the output ultrasonic interaction data representing the abnormal range in the target data segment can be accurately obtained. Then, by using the output ultrasonic interaction data and the sample conversion database, the data node description attributes of the abnormal range in the target data segment of the ultrasonic interaction data to be analyzed can be accurately obtained.

[0088] Another embodiment of this disclosure provides a data cleaning method for ultrasonic metering instruments. This method may specifically include the following:

[0089] S601. Based on the ultrasonic interactive data to be analyzed, determine the data node description attributes of the target data segment.

[0090] S602. Based on the ultrasonic interaction data to be analyzed and the sample conversion database, determine the converted ultrasonic interaction data.

[0091] S603. Perform anomaly identification processing on the converted ultrasonic interactive data to obtain abnormal ultrasonic interactive data.

[0092] S604. Based on abnormal ultrasonic interaction data, determine the target ultrasonic interaction data to be input to the ultrasonic interaction data parsing thread.

[0093] S605. The target ultrasonic interactive data is processed using the ultrasonic interactive data parsing thread to obtain the output ultrasonic interactive data.

[0094] The output ultrasonic interaction data may include: a target queue with the same number of data nodes as the target ultrasonic interaction data, the element values ​​of each element in the target queue, and the probability that the data node corresponding to each element belongs to the target data segment or a non-target data segment.

[0095] S606. Determine the element values ​​of each element in the target queue as the element values ​​corresponding to each data node in the abnormal ultrasonic interactive data.

[0096] S607. Based on the feature values ​​and sample transformation database corresponding to each data node in the abnormal ultrasonic interactive data, determine the descriptive attributes of the data nodes in the target data segment where the abnormal range occurs.

[0097] During implementation, S607 can be achieved in the following ways: based on the feature values ​​corresponding to each data node in the abnormal ultrasonic interactive data and the sample transformation database, determine the feature values ​​corresponding to each data node in the local ultrasonic interactive data, including the target data segment, that corresponds to the abnormal ultrasonic interactive data; based on the feature values ​​corresponding to each data node in the local ultrasonic interactive data, determine the descriptive attributes of the data nodes in the target data segment where the abnormal range occurs.

[0098] In this way, based on the feature values ​​corresponding to each data node in the abnormal ultrasonic interactive data and the sample transformation database, it is possible to calculate the feature values ​​corresponding to each data node in the local ultrasonic interactive data corresponding to the abnormal ultrasonic interactive data in the ultrasonic interactive data to be analyzed. Then, based on the feature values ​​corresponding to each data node in the local ultrasonic interactive data, the descriptive attributes of the data nodes in the target data segment where the abnormal range occurs can be determined, thus providing an easy-to-implement method for determining the descriptive attributes of the data nodes in the target data segment where the abnormal range occurs.

[0099] In some embodiments, the target feature value that meets the first target value requirement can be determined from the feature values ​​corresponding to each data node in the local ultrasonic interactive data, based on the data node description attribute of the target data segment; the data node description attribute of the first specified data node in the local ultrasonic interactive data and the corresponding second specified data node in the ultrasonic interactive data to be analyzed can be determined; and the data node description attribute of the abnormal range in the target data segment can be determined based on the data node description attribute of the target feature value in the local ultrasonic interactive data and the data node description attribute of the second specified data node.

[0100] In one possible implementation, determining the target element value that meets the first target value requirement from the element values ​​corresponding to each data node in the local ultrasonic interactive data may include: determining the target element value that is greater than the first target value or less than the second target value from the element values ​​corresponding to each data node in the local ultrasonic interactive data.

[0101] Specifically, considering the element values ​​of each element in the target queue, which represent the probability that the data node corresponding to each element belongs to the target data segment, target element values ​​less than the second target value are determined. Conversely, considering the element values ​​of each element in the target queue, which represent the probability that the data node corresponding to each element belongs to a non-target data segment, target element values ​​greater than the first target value are determined. This allows us to obtain the descriptive attributes of each data node within the anomaly range of the target data segment of the abnormal ultrasonic interactive data. Furthermore, based on the descriptive attributes of each data node within the anomaly range of the target data segment of the abnormal ultrasonic interactive data and the sample transformation database, we can obtain the descriptive attributes of each data node within the anomaly range of the target data segment in the local ultrasonic interactive data.

[0102] In other embodiments, the feature values ​​corresponding to each data node in a specified range, excluding local ultrasonic interactive data, in the ultrasonic interactive data to be analyzed can be determined; in the data node description attributes of the target data segment, the specified feature values ​​that meet the first target value requirements are determined from the feature values ​​corresponding to each data node in the specified range and the feature values ​​of each data node in the local ultrasonic interactive data; based on the data node description attributes of the specified feature values ​​in the ultrasonic interactive data to be analyzed, the data node description attributes of the abnormal range in the target data segment are determined.

[0103] In one possible implementation, determining a specified element value that satisfies the first target value requirement from the element values ​​corresponding to each data node in the specified range and the element values ​​of each data node in the local ultrasonic interactive data may include: determining a specified element value that is greater than the first target value or less than the second target value from the element values ​​corresponding to each data node in the specified range and the element values ​​of each data node in the local ultrasonic interactive data.

[0104] In this way, by determining the element values ​​corresponding to each data node within a specified range excluding local ultrasonic interactive data in the ultrasonic interactive data to be analyzed, the element values ​​corresponding to each data node in the ultrasonic interactive data to be analyzed can be obtained. Then, based on the magnitude of the element values ​​corresponding to each data node in the ultrasonic interactive data to be analyzed, the descriptive attributes of the data nodes in the target data segment where anomalies occur can be determined. This method of determining the descriptive attributes of data nodes in the target data segment where anomalies occur is simple and easy to implement.

[0105] S608. Based on the data node description attributes of the target data segment and the data node description attributes of the target data segment that have an abnormal range, determine the data node description attributes of the target data segment that do not have an abnormal range.

[0106] S609. Based on the data node description attributes that do not have an abnormal range in the target data segment, perform cleaning processing on the data node description attributes that do not have an abnormal range.

[0107] In this embodiment, the element values ​​of the target queue output by the ultrasonic interactive data parsing thread are determined as the element values ​​corresponding to each data node in the abnormal ultrasonic interactive data, thereby providing a method for determining the element values ​​corresponding to each data node in the abnormal ultrasonic interactive data. Based on the element values ​​corresponding to each data node in the abnormal ultrasonic interactive data and the sample conversion database, it is possible to determine whether each data node of the local ultrasonic interactive data corresponding to the abnormal ultrasonic interactive data in the ultrasonic interactive data to be analyzed belongs to the target data segment. Thus, the data node description attributes with abnormal ranges in the target data segment are determined by the data node positions, and the data node description attributes without abnormal ranges are accurately cleaned, making the processing of the target data segment more accurate.

[0108] Another embodiment of this disclosure provides a data cleaning method for ultrasonic metering instruments, which may specifically include the following:

[0109] S701. Perform important content detection on the ultrasonic interactive data to be analyzed to obtain important data of the target data segment.

[0110] S702. Based on the important data of the target data segment, determine the data node description attributes of the target data segment.

[0111] S703. Based on the ultrasonic interaction data to be analyzed, identify the abnormal ultrasonic interaction data including the target data segment.

[0112] S704. Based on abnormal ultrasonic interaction data, determine the target ultrasonic interaction data to be input to the ultrasonic interaction data parsing thread.

[0113] S705. The target ultrasonic interactive data is processed using the ultrasonic interactive data parsing thread to obtain the output ultrasonic interactive data.

[0114] S706. Based on the output ultrasonic interactive data, determine the descriptive attributes of the data nodes in the target data segment where anomalies occur.

[0115] In one possible implementation, the feature values ​​corresponding to each data node in the data node description attribute of the target data segment can be determined based on the output ultrasonic interactive data. Then, based on the feature values ​​corresponding to each data node in the data node description attribute of the target data segment, the data node description attribute in the target data segment where the abnormal range occurs can be determined.

[0116] The feature values ​​of each element in the target queue can be identified as the feature values ​​of each data node in the abnormal ultrasonic interactive data. Then, based on the feature values ​​of each data node in the abnormal ultrasonic interactive data and the sample transformation database, the feature values ​​of each data node in the local ultrasonic interactive data (including the target data segment) that corresponds to the abnormal ultrasonic interactive data can be determined. Since the local ultrasonic interactive data is the part of the ultrasonic interactive data to be analyzed that includes the target data segment, the feature values ​​of each data node in the data node description attribute of the target data segment can be determined based on the feature values ​​of each data node in the local ultrasonic interactive data.

[0117] In another embodiment, if the ultrasonic interaction data to be analyzed is subjected to anomaly identification processing to obtain abnormal ultrasonic interaction data, then based on the element values ​​corresponding to each data node in the abnormal ultrasonic interaction data, the element values ​​corresponding to each data node in the local ultrasonic interaction data can be determined, thereby obtaining the element values ​​corresponding to each data node in the data node description attribute of the target data segment.

[0118] S707. Among the feature values ​​corresponding to each data node in the data node description attribute of the target data segment, determine the undetermined feature values ​​that meet the requirements of the second target value.

[0119] In one possible implementation, S707 can be achieved by: determining, among the feature values ​​corresponding to each data node in the data node description attribute of the target data segment, a pending feature value that is less than or equal to a first target value and greater than a third target value, or greater than or equal to a second target value and less than or equal to a fourth target value.

[0120] Prior to S707, it was possible to perform the step of determining the feature values ​​corresponding to each data node in the data node description attribute of the target data segment based on the output ultrasonic interactive data.

[0121] During implementation, when the element value of each element in the target queue represents the probability that the data node corresponding to each element belongs to the target data segment, the undetermined element value is determined to be greater than or equal to the second target value and less than or equal to the fourth target value. When the element value of each element in the target queue represents the probability that the data node corresponding to each element belongs to the non-target data segment, the undetermined element value is determined to be less than or equal to the first target value and greater than the third target value.

[0122] S708. Determine the data node description attribute corresponding to the value of the undetermined feature as the data node description attribute of the intermediate range.

[0123] S709. Based on the data node description attributes of the abnormal range and the data node description attributes of the intermediate range in the target data segment, determine the data node description attributes of the target data segment that do not have an abnormal range.

[0124] In this implementation, the target data segment can include three regions: an abnormal range, an intermediate range, and a range without abnormalities. Data node description attributes other than those showing abnormal ranges and intermediate ranges can be defined as data node description attributes without abnormalities in the target data segment.

[0125] S710. Based on the data node description attributes of the intermediate range, optimize the intermediate range.

[0126] In one possible implementation, step S710 may be omitted.

[0127] In this embodiment, the descriptive attributes of data nodes in the intermediate range can be determined first. The feature values ​​corresponding to each data node in the intermediate range indicate that each data node may belong to the target data segment or a non-target data segment. Based on the descriptive attributes of data nodes with abnormal ranges in the target data segment and the descriptive attributes of data nodes in the intermediate range, the descriptive attributes of data nodes without abnormal ranges in the target data segment can be determined. This can reduce the possibility of determining some data nodes in the intermediate range as data nodes without abnormal ranges, and thus accurately determine the descriptive attributes of data nodes without abnormal ranges in the target data segment.

[0128] This disclosure provides a method for determining an ultrasonic interactive data parsing thread, which may specifically include the following:

[0129] S801. Obtain the configuration example set; the configuration example set includes several configuration example ultrasonic interaction data; at least one data segment in each configuration example ultrasonic interaction data is abnormal.

[0130] In one possible implementation, at least one data segment may include only the target data segment. In an alternative implementation, at least one data segment may include not only the target data segment but also other data segments besides the target data segment.

[0131] S802. Obtain the target example set; the target example set includes several target example ultrasonic interaction data; each target example ultrasonic interaction data includes data in the data segment that does not contain any anomalies.

[0132] When at least one data segment consists only of the target data segment, data in that data segment that is free of anomalies can be considered data in the target data segment that is free of anomalies. When at least one data segment includes not only the target data segment but also other data segments, data in that data segment that is free of anomalies includes not only data in the target data segment but also data in other data segments that is free of anomalies.

[0133] S803. Based on the configuration example set and the target example set, configure the ultrasonic interactive data parsing thread.

[0134] When at least one data segment contains only the target data segment, the obtained ultrasonic interactive data parsing thread can determine whether each data node in the input ultrasonic interactive data belongs to the visible target data segment or other areas outside the visible target data segment.

[0135] When at least one data segment comprises several data segments, the resulting ultrasonic interactive data parsing thread can determine whether each data node in the input ultrasonic interactive data belongs to any of the visible data segments or other regions outside of them. For example, if the ultrasonic interactive data to be analyzed comprises several data segments, anomaly identification processing can be performed on the ultrasonic interactive data to be analyzed, resulting in several anomalous ultrasonic interactive data. Based on these anomalous ultrasonic interactive data, several target ultrasonic interactive data are obtained, and these target ultrasonic interactive data are input into the ultrasonic interactive data parsing thread. This allows the thread to determine whether each data node in the target ultrasonic interactive data belongs to any of the visible data segments or other regions outside of them, thus confirming that each data node in the input ultrasonic interactive data belongs to any of the visible data segments or other regions outside of them.

[0136] In this embodiment of the disclosure, several sample ultrasonic interaction data are used as configuration inputs and several target sample ultrasonic interaction data are used as configuration targets to configure an ultrasonic interaction data parsing thread. The ultrasonic interaction data parsing thread can process the subsequently input target ultrasonic interaction data to obtain the data node description attributes that have no abnormal range in the target data segment. Therefore, by automatically obtaining the data node description attributes that have no abnormal range in the target data segment, the accuracy of the determined data node description attributes that have no abnormal range in the target data segment can be improved.

[0137] Based on the above, a data cleaning device for ultrasonic metering instruments is provided, the device comprising:

[0138] The data determination module is used to determine the data node description attributes of the target data segment and the abnormal ultrasonic interaction data including the target data segment based on the ultrasonic interaction data to be analyzed.

[0139] The data input module is used to determine the target ultrasonic interaction data to be input to the ultrasonic interaction data parsing thread based on the abnormal ultrasonic interaction data.

[0140] The data processing module is used to process the target ultrasonic interactive data in conjunction with the ultrasonic interactive data parsing thread to obtain output ultrasonic interactive data.

[0141] The attribute determination module is used to determine the descriptive attributes of data nodes in the target data segment where anomalies occur, based on the output ultrasonic interactive data.

[0142] The attribute description module is used to determine the data node description attributes in the target data segment that do not have abnormal ranges based on the data node description attributes of the target data segment and the data node description attributes in the target data segment that show abnormal ranges.

[0143] The data cleaning module is used to clean the data node description attributes that do not have an abnormal range in the target data segment.

[0144] Based on the above, a data cleaning system for an ultrasonic meter is shown, comprising a processor and a memory that communicate with each other. The processor is used to read a computer program from the memory and execute it to implement the method described above.

[0145] Based on the above, a computer-readable storage medium is also provided, on which a computer program stored implements the above method during runtime.

[0146] In summary, based on the above scheme, since the data node description attributes of the target data segment and the data node description attributes of the data nodes with abnormal ranges within the target data segment are determined, the data node description attributes of the target data segment without abnormal ranges, determined based on these attributes, provide information describing the data location of the data nodes. This allows for very precise determination of the data location without abnormal ranges, making the ultrasonic interactive data obtained by cleaning the data node description attributes without abnormal ranges more accurate and reliable. Furthermore, by first determining the data node description attributes without abnormal ranges in the target data segment and then cleaning them, more accurate and reliable ultrasonic data can be obtained, improving the accuracy and reliability of subsequent ultrasonic metering instruments.

[0147] It should be understood that the systems and modules described above can be implemented in various ways. For example, in some embodiments, the systems and modules can be implemented by hardware, software, or a combination of both. The hardware portion can be implemented using dedicated logic; the software portion can be stored in memory and executed by an appropriate instruction execution system, such as a microprocessor or dedicated-design hardware. Those skilled in the art will understand that the methods and systems described above can be implemented using computer-executable instructions and / or included in processor control code, for example, such code provided on a carrier medium such as a disk, CD, or DVD-ROM, a programmable memory such as read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The systems and modules of this application can be implemented not only by hardware circuits such as very large-scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field-programmable gate arrays, programmable logic devices, etc., but also by software executed by various types of processors, or by a combination of the aforementioned hardware circuits and software (e.g., firmware).

[0148] It should be noted that different embodiments may produce different beneficial effects. In different embodiments, the beneficial effects may be any one or a combination of the above, or any other possible beneficial effects.

[0149] The basic concepts have been described above. Obviously, for those skilled in the art, the detailed disclosure above is merely illustrative and does not constitute a limitation of this application. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements, and corrections to this application. Such modifications, improvements, and corrections are suggested in this application, and therefore remain within the spirit and scope of the exemplary embodiments of this application.

[0150] Furthermore, this application uses specific terms to describe embodiments of the application. For example, "an embodiment," "one embodiment," and / or "some embodiments" refer to a particular feature, structure, or characteristic associated with at least one embodiment of the application. Therefore, it should be emphasized and noted that "an embodiment," "one embodiment," or "an alternative embodiment" mentioned twice or more in different locations in this specification do not necessarily refer to the same embodiment. In addition, certain features, structures, or characteristics in one or more embodiments of the application can be appropriately combined.

[0151] Furthermore, those skilled in the art will understand that aspects of this application can be described and illustrated through several patentable types or situations, including any new and useful combination of processes, machines, products, or substances, or any new and useful improvements thereof. Accordingly, aspects of this application can be implemented entirely by hardware, entirely by software (including firmware, resident software, microcode, etc.), or by a combination of hardware and software. All of the above hardware or software may be referred to as a “data block,” “module,” “engine,” “unit,” “component,” or “system.” Furthermore, aspects of this application may manifest as a computer product located on one or more computer-readable media, the product including computer-readable program code.

[0152] Computer storage media may contain a propagated data signal containing computer program code, for example, on baseband or as part of a carrier wave. This propagated signal may take various forms, including electromagnetic, optical, and suitable combinations thereof. Computer storage media can be any computer-readable medium other than a computer-readable storage medium, which can be connected to an instruction execution system, apparatus, or device to enable communication, propagation, or transmission of a program for use. The program code located on the computer storage medium can be propagated through any suitable medium, including radio, cable, fiber optic cable, RF, or similar media, or any combination of the above media.

[0153] The computer program code required for the operation of each part of this application can be written in any one or more programming languages, including object-oriented programming languages ​​such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C++, C#, VB.NET, Python, etc.; conventional procedural programming languages ​​such as C, Visual Basic, Fortran2003, Perl, COBOL2002, PHP, ABAP; dynamic programming languages ​​such as Python, Ruby, and Groovy; or other programming languages. This program code can run entirely on the user's computer, or as a standalone software package on the user's computer, or partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the latter case, the remote computer can be connected to the user's computer through any network, such as a local area network (LAN) or wide area network (WAN), or connected to an external computer (e.g., via the Internet), or in a cloud computing environment, or used as a service such as Software as a Service (SaaS).

[0154] Furthermore, unless expressly stated in the claims, the order of processing elements and sequences, the use of numbers and letters, or other names described in this application are not intended to limit the order of the processes and methods of this application. Although the foregoing disclosure has discussed some currently considered useful embodiments of the invention through various examples, it should be understood that such details are for illustrative purposes only, and the appended claims are not limited to the disclosed embodiments; rather, the claims are intended to cover all modifications and equivalent combinations that conform to the substance and scope of the embodiments of this application. For example, while the system components described above can be implemented using hardware devices, they can also be implemented solely through software solutions, such as installing the described system on existing servers or mobile devices.

[0155] Similarly, it should be noted that, in order to simplify the description of the present application and thus aid in the understanding of one or more embodiments of the invention, the foregoing description of the embodiments of the present application sometimes combines multiple features into a single embodiment, drawing, or description thereof. However, this disclosure method does not imply that the subject matter of the application requires more features than those mentioned in the claims. In fact, the embodiments contain fewer features than all the features of the single embodiments disclosed above.

[0156] In some embodiments, numbers describing the quantity of components and attributes are used. It should be understood that such numbers used in the description of embodiments are modified in some examples with the terms "approximately," "approximately," or "generally." Unless otherwise stated, "approximately," "approximately," or "generally" indicates that the numbers are open to adaptive variation. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may be changed depending on the characteristics required by individual embodiments. In some embodiments, numerical parameters are taken into account a specified number of significant digits and employ a general method of digit reservation. Although the numerical ranges and parameters used to confirm their breadth of application in some embodiments of this application are approximate values, in specific embodiments, such values ​​are set as precisely as feasible.

[0157] For each patent, patent application, patent application publication, and other material such as articles, books, specifications, publications, and documents referenced in this application, the entire contents of that patent are incorporated herein by reference. This excludes historical application documents that are inconsistent with or conflict with the content of this application, as well as documents that limit the broadest scope of the claims in this application (currently or subsequently appended to this application). It should be noted that if there are any inconsistencies or conflicts between the descriptions, definitions, and / or terminology used in the supplementary materials of this application and the content of this application, the descriptions, definitions, and / or terminology used in this application shall prevail.

[0158] Finally, it should be understood that the embodiments described in this application are merely illustrative of the principles of the embodiments of this application. Other modifications may also fall within the scope of this application. Therefore, alternative configurations of the embodiments of this application are considered as examples and not limitations, and are regarded as consistent with the teachings of this application. Accordingly, the embodiments of this application are not limited to the embodiments explicitly described and illustrated in this application.

[0159] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A data cleaning method for ultrasonic metering instruments, characterized in that, The method includes: Based on the ultrasonic interaction data to be analyzed, determine the data node description attributes of the target data segment and the abnormal ultrasonic interaction data including the target data segment: The ultrasonic interactive data to be analyzed is subjected to important content detection to obtain the important data of the target data segment; Based on the important data of the target data segment, determine the data node description attributes of the target data segment; Based on the ultrasound interaction data to be analyzed and the sample conversion database, the converted ultrasound interaction data is determined; Anomaly identification processing is performed on the converted ultrasonic interaction data to obtain the abnormal ultrasonic interaction data. Based on the abnormal ultrasonic interaction data, determine the target ultrasonic interaction data to be input to the ultrasonic interaction data parsing thread; The target ultrasonic interactive data is processed by the ultrasonic interactive data parsing thread to obtain output ultrasonic interactive data. Based on the output ultrasonic interaction data, determine the descriptive attributes of the data nodes in the target data segment where anomalies occur: Based on the output ultrasonic interactive data and the sample conversion database, determine the descriptive attributes of the data nodes in the target data segment that exhibit abnormal ranges; Based on the data node description attributes of the target data segment and the data node description attributes of the target data segment showing abnormal ranges, it is determined that the data node description attributes of the target data segment do not have abnormal ranges. Based on the output ultrasonic interactive data, determine the element values ​​corresponding to each data node in the data node description attribute of the target data segment; Among the feature values ​​corresponding to each data node in the data node description attribute of the target data segment, determine the undetermined feature values ​​that meet the second target value requirements; determine the data node description attribute corresponding to the undetermined feature values ​​as the data node description attribute within the middle range; and determine the data node description attribute without an abnormal range in the target data segment based on the data node description attributes with abnormal ranges in the target data segment and the data node description attributes within the middle range. Based on the data node description attributes that do not have an abnormal range in the target data segment, the data node description attributes that do not have an abnormal range are cleaned.

2. The method according to claim 1, characterized in that, The output ultrasonic interaction data includes: a target queue with the same number of data nodes as the target ultrasonic interaction data or the abnormal ultrasonic interaction data, and the element value of each element in the target queue, which represents the probability that the data node corresponding to each element belongs to the target data segment or a non-target data segment. The step of determining the data node description attributes of the abnormal range in the target data segment based on the output ultrasonic interactive data includes: determining the element value of each element in the target queue as the element value corresponding to each data node in the abnormal ultrasonic interactive data; and determining the data node description attributes of the abnormal range in the target data segment based on the element value corresponding to each data node in the abnormal ultrasonic interactive data and the sample conversion database.

3. The method according to claim 2, characterized in that, The step of determining the descriptive attributes of data nodes in the target data segment that exhibit anomalies, based on the feature values ​​corresponding to each data node in the abnormal ultrasonic interactive data and the sample conversion database, includes: Based on the element values ​​corresponding to each data node in the abnormal ultrasonic interaction data and the sample conversion database, determine the element values ​​corresponding to each data node in the local ultrasonic interaction data, including the target data segment, that corresponds to the abnormal ultrasonic interaction data in the ultrasonic interaction data to be analyzed. Based on the element values ​​corresponding to each data node in the local ultrasonic interactive data, the descriptive attributes of the data nodes in the target data segment where anomalies occur are determined.

4. The method according to claim 3, characterized in that, The step of determining the descriptive attributes of data nodes exhibiting abnormal ranges in the target data segment based on the feature values ​​corresponding to each data node in the local ultrasonic interactive data includes: In the data node description attribute of the target data segment, the target element value that meets the first target value requirement is determined from the element values ​​corresponding to each data node in the local ultrasonic interactive data. Determine the first specified data node in the local ultrasonic interactive data, and the corresponding data node description attribute in the second specified data node in the ultrasonic interactive data to be analyzed; Based on the data node description attributes corresponding to the target element value on the local ultrasonic interactive data and the data node description attributes of the second specified data node, the data node description attributes of the abnormal range in the target data segment are determined.

5. The method according to claim 3, characterized in that, The step of determining the descriptive attributes of data nodes exhibiting abnormal ranges in the target data segment based on the feature values ​​corresponding to each data node in the local ultrasonic interactive data includes: Determine the element values ​​corresponding to each data node within a specified range in the ultrasonic interaction data to be analyzed, excluding the local ultrasonic interaction data. In the data node description attribute of the target data segment, a specified element value that meets the first target value requirement is determined from the element values ​​corresponding to each data node in the specified range and the element values ​​of each data node in the local ultrasonic interactive data. Based on the data node description attributes corresponding to the specified element values ​​on the ultrasonic interactive data to be analyzed, the data node description attributes of the abnormal range in the target data segment are determined.

6. The method according to claim 1, characterized in that, The method further includes: optimizing the intermediate range based on the data node description attributes of the intermediate range; The method further includes: Obtain a configuration example set; the configuration example set includes several configuration example ultrasonic interaction data. In each of the aforementioned configuration examples, at least one data segment in the ultrasonic interaction data exhibits an anomaly. Obtain a target example set; the target example set includes several target example ultrasonic interaction data; Each of the aforementioned target example ultrasonic interaction data includes data in the data segment that does not contain any anomalies; Based on the configuration example set and the target example set, the ultrasonic interactive data parsing thread is configured.

7. A data cleaning system for an ultrasonic metering instrument, characterized in that, The method includes a processor and a memory that communicate with each other, the processor being configured to read a computer program from the memory and execute it to implement the method of any one of claims 1-6.

Images