Noise processing method and system applied to ultrasonic metering instrument

Abstract

The application provides a noise processing method and system applied to an ultrasonic metering instrument. Knowledge character extraction is performed on sample ultrasonic metering data to obtain a second description knowledge relationship network corresponding to the sample ultrasonic metering data. Knowledge character noise analysis and processing are performed on the first description knowledge relationship network and the second description knowledge relationship network to obtain knowledge character combined ultrasonic metering data. Based on the knowledge character combined ultrasonic metering data, a noise analysis result of the to-be-processed ultrasonic metering data is obtained. By performing knowledge character noise analysis and processing on the first description knowledge relationship network of the to-be-processed ultrasonic metering data and the second description knowledge relationship network of the sample ultrasonic metering data, interference factors existing between the first description knowledge relationship network and the second description knowledge relationship network are reduced, and then more accurate noise analysis results of the first description knowledge relationship network can be obtained by using the knowledge character combined ultrasonic metering data.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of noise processing, in particular to a noise processing method applied to an ultrasonic meter. BACKGROUND

[0002] The ultrasonic meter, electromagnetic flow meter and other meters are all non-obstructive flow meters because no obstructive elements are arranged in the flow passage of the meters, and are suitable for solving the problem of difficult flow measurement, especially having outstanding advantages in large-diameter flow measurement, and are one of the rapidly developing flow meters.

[0003] The ultrasonic meter is used to count ultrasonic data through an ultrasonic transducer, and noise interference may occur in the counting process, thereby causing errors in the counting of ultrasonic data. Therefore, a noise processing method is needed to improve the above technical problems. SUMMARY

[0004] To improve the technical problems in the related art, the present application provides a noise processing method applied to an ultrasonic meter.

[0005] In a first aspect, a noise processing method applied to an ultrasonic meter is provided, including: obtaining to-be-processed ultrasonic meter data and sample ultrasonic meter data; performing knowledge character extraction on the to-be-processed ultrasonic meter data to obtain a first description knowledge relationship network of the to-be-processed ultrasonic meter data, and performing knowledge character extraction on the sample ultrasonic meter data to obtain a second description knowledge relationship network corresponding to the sample ultrasonic meter data; performing knowledge character noise analysis processing on the first description knowledge relationship network and the second description knowledge relationship network to obtain knowledge character combined ultrasonic meter data; and obtaining a noise analysis result of the to-be-processed ultrasonic meter data based on the knowledge character combined ultrasonic meter data.

[0006] It can be understood that by performing knowledge character noise analysis processing on the first description knowledge relationship network of the to-be-processed ultrasonic meter data and the second description knowledge relationship network of the sample ultrasonic meter data, the interference factors between the first description knowledge relationship network and the second description knowledge relationship network are reduced, and then the knowledge character combined ultrasonic meter data can be used to obtain a more accurate noise analysis result of the first description knowledge relationship network.

[0007] In an independently implemented embodiment, the knowledge character extraction on the to-be-processed ultrasonic metrology data to obtain the first description knowledge relationship network of the to-be-processed ultrasonic metrology data comprises: performing multiple knowledge character extractions on the to-be-processed ultrasonic metrology data to obtain a first description knowledge relationship network corresponding to each knowledge character extraction; the knowledge character extraction on the sample ultrasonic metrology data to obtain the second description knowledge relationship network corresponding to the sample ultrasonic metrology data comprises: performing multiple knowledge character extractions on the sample ultrasonic metrology data to obtain a second description knowledge relationship network corresponding to each first description knowledge relationship network; and the knowledge character noise analysis processing on the first description knowledge relationship network and the second description knowledge relationship network to obtain the knowledge character combined ultrasonic metrology data comprises: for each first description knowledge relationship network, performing knowledge character noise analysis processing on the each first description knowledge relationship network and the second description knowledge relationship network corresponding to the each first description knowledge relationship network to obtain the knowledge character combined ultrasonic metrology data corresponding to the each first description knowledge relationship network.

[0008] It can be understood that, by performing multiple knowledge character extractions on the to-be-processed ultrasonic metrology data and the sample ultrasonic metrology data respectively, more knowledge characters in the to-be-processed ultrasonic metrology data and the sample ultrasonic metrology data are included in the obtained knowledge character combined ultrasonic metrology data, and the noise analysis result of the to-be-processed ultrasonic metrology data determined based on the knowledge character combined ultrasonic metrology data has higher accuracy.

[0009] In an independently implemented embodiment, the noise analysis result of the to-be-processed ultrasonic metrology data is obtained based on the knowledge character combined ultrasonic metrology data, comprising: obtaining the noise analysis result of each first description knowledge relationship network based on the knowledge character combined ultrasonic metrology data corresponding to the each first description knowledge relationship network; and obtaining the noise analysis result of the to-be-processed ultrasonic metrology data based on the noise analysis results of the first description knowledge relationship networks corresponding to multiple knowledge character extractions respectively.

[0010] It can be understood that, by obtaining the noise analysis result corresponding to each knowledge character extraction, the noise analysis result of the to-be-processed ultrasonic metrology data determined based on the noise analysis result corresponding to each knowledge character extraction has higher reliability.

[0011] In an independently implemented embodiment, the to-be-processed ultrasonic metrology data is subjected to multiple knowledge character extractions, and a transition description knowledge relation network corresponding to each knowledge character extraction is obtained; for a case where the each knowledge character extraction is a last knowledge character extraction, the transition description knowledge relation network corresponding to the last knowledge character extraction is determined as a first description knowledge relation network corresponding to the last knowledge character extraction; for a case where the each knowledge character extraction is a knowledge character extraction other than the last knowledge character extraction, a knowledge character combination is performed on the transition description knowledge relation network corresponding to the each knowledge character extraction and a first description knowledge relation network corresponding to a next knowledge character extraction of the each knowledge character extraction, to obtain a first description knowledge relation network corresponding to the each knowledge character extraction.

[0012] It can be understood that, by performing multiple knowledge character extractions on the to-be-processed ultrasonic metrology data, the first description knowledge relation networks obtained by different levels of knowledge character extractions contain different knowledge characters in the to-be-processed ultrasonic metrology data, and thus the noise analysis result of the to-be-processed ultrasonic metrology data determined based on the noise analysis results of the first description knowledge relation networks corresponding to the multiple knowledge character extractions respectively has higher reliability.

[0013] In an independently implemented embodiment, the knowledge character combination of the transition description knowledge relation network corresponding to the each knowledge character extraction and the first description knowledge relation network corresponding to the next knowledge character extraction of the each knowledge character extraction to obtain the first description knowledge relation network corresponding to the each knowledge character extraction comprises: deriving the first description knowledge relation network corresponding to the next knowledge character extraction of the each knowledge character extraction to obtain a derivation vector; and fusing the derivation vector and the transition description knowledge relation network corresponding to the each knowledge character extraction to obtain the first description knowledge relation network corresponding to the each knowledge character extraction.

[0014] It can be understood that, by derivation processing, the directions of the first description knowledge relation network and the corresponding transition description knowledge relation network are unified, and the fusion of the two is more convenient.

[0015] In an independently implemented embodiment, the knowledge character noise analysis processing on the each first description knowledge relationship net and the second description knowledge relationship net corresponding to the each first description knowledge relationship net comprises: based on the each first description knowledge relationship net and the second description knowledge relationship net corresponding to the each first description knowledge relationship net, performing knowledge character cleaning processing on the second description knowledge relationship net corresponding to the first description knowledge relationship net to obtain knowledge character cleaning ultrasonic metrology data of the second description knowledge relationship net corresponding to the first description knowledge relationship net; and based on the each first description knowledge relationship net and the second description knowledge relationship net corresponding to the each first description knowledge relationship net, obtaining significance ultrasonic metrology data corresponding to the each first description knowledge relationship net; wherein a target value of a random one flow data segment in the significance ultrasonic metrology data represents a noise value of a first data node in the first description knowledge relationship net that is positioned in association with the random one flow data segment; and based on the knowledge character cleaning ultrasonic metrology data and the significance ultrasonic metrology data, obtaining knowledge character combination ultrasonic metrology data corresponding to the each first description knowledge relationship net.

[0016] It can be understood that, by performing knowledge character cleaning on the second description knowledge relationship net of the sample ultrasonic metrology data, the difference between the to-be-processed ultrasonic metrology data and the sample ultrasonic metrology data caused by the collection noise, the association error and the production error existing in the to-be-processed ultrasonic metrology data can be reduced, and the flaw reliability of the to-be-processed ultrasonic metrology data can be improved.

[0017] In addition, by generating the significance ultrasonic metrology data corresponding to the first description knowledge relationship net of the to-be-processed ultrasonic metrology data, the target value of each flow data segment in the significance ultrasonic metrology data represents a noise value of a first data node that is positioned in the first description knowledge relationship net and has a flaw, and then the noise analysis result of the first description knowledge relationship net is determined according to the significance ultrasonic metrology data, which has higher reliability.

[0018] In an independently implemented embodiment, the knowledge character cleaning processing of the second description knowledge relationship network corresponding to the first description knowledge relationship network based on the first description knowledge relationship network and the second description knowledge relationship network corresponding to the first description knowledge relationship network comprises: for each first data node in the first description knowledge relationship network, determining a plurality of associated data nodes corresponding to the first data node from a plurality of second data nodes of the second description knowledge relationship network corresponding to the first description knowledge relationship network; wherein each associated data node corresponding to the first data node and the target second data node positioned in association with the first data node satisfy a set requirement; based on the common factor between the first data node and each associated data node, the target second data node positioned in association with the first data node is subjected to knowledge character cleaning processing.

[0019] It can be understood that by determining the associated data nodes for each first data node and determining the noise value of the corresponding third traffic data segment based on the common factor between the plurality of associated data nodes and the corresponding first data node, the noise value of the second traffic data segment corresponding to the third traffic data segment is obtained. The noise value of the second traffic data segment is affected by the plurality of traffic data segments in the sample ultrasonic measurement data, so as to reduce the interference of the noise on the noise analysis result of the second traffic data segment in the to-be-processed ultrasonic measurement data, and improve the flaw reliability of the to-be-processed ultrasonic measurement data.

[0020] In an independently implemented embodiment, the knowledge character cleaning processing of the second description knowledge relationship network corresponding to the first description knowledge relationship network based on the first data node and each associated data node comprises: based on the common factor between the first data node and each associated data node and the knowledge character parameters of each associated data node, the target second data node positioned in association with the first data node is subjected to knowledge character cleaning processing.

[0021] It can be understood that by the common factor of the associated data nodes and the first data node and the knowledge character parameters of each associated data node, the knowledge character parameters of the target second data node positioned in association with the first data node are determined again, so that the knowledge character parameters determined again can reduce the error existing between the first data node, so as to have higher reliability when identifying flaws based on knowledge character cleaning ultrasonic measurement data.

[0022] In an independently implemented embodiment, the knowledge character cleaning processing of a target second data node associated with the first data node is based on the commonality factor between the first data node and each associated data node and the knowledge character parameter of each associated data node, and includes: processing the knowledge character parameter of each associated data node corresponding to the first data node based on the commonality factor between the first data node and each associated data node to obtain a first processing result; splicing the commonality factor of each associated data node to obtain a second processing result; and comparing the first processing result and the second processing result to determine the knowledge character parameter of the target second data node after the knowledge character cleaning processing.

[0023] In an independently implemented embodiment, the significant ultrasonic metrology data corresponding to the first description knowledge relationship network is obtained based on the first description knowledge relationship network and the second description knowledge relationship network corresponding to the first description knowledge relationship network, and includes: determining, for each first data node in the first description knowledge relationship network, a plurality of associated data nodes corresponding to the first data node from a plurality of second data nodes of the second description knowledge relationship network corresponding to the first description knowledge relationship network, wherein the difference between each associated data node corresponding to the first data node and a target second data node associated with the first data node meets a set requirement; determining a noise value of the first data node based on the commonality factor between the first data node and each associated data node; and obtaining the significant ultrasonic metrology data based on the noise value of each first data node in the first description knowledge relationship network.

[0024] In an independently implemented embodiment, the noise value of the first data node is determined based on the commonality factor between the first data node and each associated data node, and includes: determining a maximum commonality factor of the commonality factor between each associated data node and the first data node; and determining the noise value of the first data node based on the maximum commonality factor.

[0025] In an independently implemented embodiment, the commonality factor between the first data node and a random one of the associated data nodes corresponding to the first data node is determined in the following manner: obtaining a first local description knowledge relationship network based on the positioning of the first data node in the first description knowledge relationship network and a previously set difference specification value; obtaining a second local description knowledge relationship network based on the positioning of a random one of the associated data nodes corresponding to the first data node in the second description knowledge relationship network and the difference specification value; and determining the commonality factor between the first data node and the random one of the associated data nodes corresponding to the first data node based on the first local description knowledge relationship network and the second local description knowledge relationship network.

[0026] In an independently implemented embodiment, the cleaning the ultrasonic metrology data based on the knowledge character, to obtain the significant ultrasonic metrology data, to obtain the knowledge character combination ultrasonic metrology data corresponding to the first description knowledge relationship network, comprises: integrating the knowledge character cleaning ultrasonic metrology data and the first description knowledge relationship network to obtain the integrated description knowledge relationship network corresponding to the first description knowledge relationship network; based on the significant ultrasonic metrology data and the integrated description knowledge relationship network, the knowledge character combination ultrasonic metrology data is obtained.

[0027] The application embodiment provided by the application provides a noise processing method applied to an ultrasonic metrology instrument. Knowledge characters are extracted from sample ultrasonic metrology data to obtain a second description knowledge relationship network corresponding to the sample ultrasonic metrology data. A first description knowledge relationship network and the second description knowledge relationship network are subjected to knowledge character noise analysis processing to obtain knowledge character combination ultrasonic metrology data. Based on the knowledge character combination ultrasonic metrology data, a noise analysis result of to-be-processed ultrasonic metrology data is obtained. By subjecting the first description knowledge relationship network of the to-be-processed ultrasonic metrology data and the second description knowledge relationship network of the sample ultrasonic metrology data to knowledge character noise analysis processing, interference factors existing between the first description knowledge relationship network and the second description knowledge relationship network are reduced. Then, the knowledge character combination ultrasonic metrology data can be used to obtain a more accurate noise analysis result of the first description knowledge relationship network. BRIEF DESCRIPTION OF DRAWINGS

[0028] In order to more clearly illustrate the technical solutions of the embodiments of the application, the following will briefly introduce the drawings needed to be used in the embodiments. It should be understood that the following drawings only show some of the embodiments of the application, and therefore should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can also be obtained without creative labor.

[0029] Figure 1 A flowchart of a noise processing method applied to an ultrasonic metrology instrument is provided by the application embodiment.

[0030] Figure 2 An architecture diagram of a noise processing system applied to an ultrasonic metrology instrument is provided by the application embodiment. DETAILED DESCRIPTION

[0031] For better understanding of the above technical solutions, the following will be described in detail by the drawings and specific embodiments. It should be understood that the embodiments and specific features in the embodiments are detailed descriptions of the technical solutions of the present application, and are not limitations of the technical solutions of the present application. In the case of no conflict, the technical features in the embodiments and the embodiments can be combined with each other.

[0032] Please refer to Figure 1 , a noise processing method applied to an ultrasonic meter is shown, which can include the technical solutions described in steps S101-S104.

[0033] S101: obtaining the to-be-processed ultrasonic metering data and the sample ultrasonic metering data;

[0034] For example, the sample ultrasonic metering data can be understood as the data that already exists.

[0035] S102: knowledge character extraction is performed on the to-be-processed ultrasonic metering data to obtain a first description knowledge relationship network of the to-be-processed ultrasonic metering data, and knowledge character extraction is performed on the sample ultrasonic metering data to obtain a second description knowledge relationship network corresponding to the sample ultrasonic metering data;

[0036] For example, the knowledge character can be understood as a feature. The first description knowledge relationship network can be understood as a data set composed of key elements in real-time ultrasonic data, and the second description knowledge relationship network can be understood as a data set composed of key elements in sample ultrasonic data.

[0037] S103: knowledge character noise analysis processing is performed on the first description knowledge relationship network and the second description knowledge relationship network to obtain knowledge character combined ultrasonic metering data;

[0038] For example, the description knowledge relationship network can be understood as a feature map.

[0039] S104: based on the knowledge character combined ultrasonic metering data, the noise analysis result of the to-be-processed ultrasonic metering data is obtained.

[0040] The above S101-S104 will be described in detail.

[0041] I: In S101 above, ultrasonic measurement data refers to data measured by ultrasonic measuring instruments. For example, ultrasonic measurement data may include the inner diameter of a pipeline, the flow rate of a liquid or gas, temperature, pressure, etc. In some embodiments, ultrasonic measurement data may be acquired via a sensor. Sample ultrasonic measurement data refers to template data established as a standard in industrial production, or ultrasonic measurement data recorded for qualified items used to identify defects in pending items. Here, qualified items are items without defects. Unprocessed ultrasonic measurement data refers to ultrasonic measurement data obtained for pending items.

[0042] The ultrasonic measurement data to be processed can be obtained, for example, by an ultrasonic measurement data acquisition module provided on the defect recognition device, or the ultrasonic measurement data to be processed can be received from other devices.

[0043] II: In the above S102, knowledge characters are extracted from the ultrasonic measurement data to be processed. For example, the following method can be adopted: multiple knowledge characters are extracted from the ultrasonic measurement data to be processed to obtain a first descriptive knowledge relationship network corresponding to each knowledge character extraction.

[0044] Exemplarily, each knowledge character extraction can obtain a transition description knowledge relationship network of the ultrasonic measurement data to be processed. For any two adjacent levels of knowledge character extraction, the transition description knowledge relationship network obtained by the previous knowledge character extraction serves as the input for the next knowledge character extraction. That is, the next knowledge character extraction is performed based on the transition description knowledge relationship network obtained by the previous knowledge character extraction to obtain the transition description knowledge relationship network of the next knowledge character extraction. For the last knowledge character extraction among multiple knowledge character extractions, the transition description knowledge relationship network corresponding to the last knowledge character extraction is determined as the first description knowledge relationship network corresponding to the last knowledge character extraction. For the other levels of knowledge character extraction among multiple knowledge character extractions except the last knowledge character extraction, the transition description knowledge relationship network corresponding to each knowledge character extraction is combined with the first description knowledge relationship network corresponding to the next knowledge character extraction of the knowledge character extraction to obtain the first description knowledge relationship network corresponding to each knowledge character extraction.

[0045] In the knowledge character combination of the transition descriptive knowledge relation net corresponding to each knowledge character extraction and the first descriptive knowledge relation net corresponding to the next knowledge character extraction of the knowledge character extraction, if the size of the first descriptive knowledge relation net corresponding to the next knowledge character extraction of the knowledge character extraction is smaller than the size of the transition descriptive knowledge relation net corresponding to the knowledge character extraction, the first descriptive knowledge relation net corresponding to the next knowledge character extraction of the knowledge character extraction is derived to obtain derived ultrasonic metrology data, the size of the derived ultrasonic metrology data is consistent with the size of the transition descriptive knowledge relation net corresponding to the knowledge character extraction, and then the derived ultrasonic metrology data and the transition descriptive knowledge relation net corresponding to the knowledge character extraction are fused to obtain the first descriptive knowledge relation net corresponding to the knowledge character extraction.

[0046] In the knowledge character combination of the transition descriptive knowledge relation net corresponding to each knowledge character extraction and the first descriptive knowledge relation net corresponding to the next knowledge character extraction of the knowledge character extraction, if the size of the first descriptive knowledge relation net corresponding to the next knowledge character extraction of the knowledge character extraction is equal to the size of the transition descriptive knowledge relation net corresponding to the knowledge character extraction, the first descriptive knowledge relation net corresponding to the next knowledge character extraction of the knowledge character extraction and the transition descriptive knowledge relation net corresponding to the knowledge character extraction can be directly fused to obtain the first descriptive knowledge relation net corresponding to the knowledge character extraction.

[0047] In a possible embodiment, a plurality of knowledge character extractions can be performed on the to-be-processed ultrasonic metrology data by using a preconfigured knowledge character extraction thread.

[0048] The embodiment of the present disclosure further provides a knowledge character extraction thread, comprising: a four-stage thread unit, which comprises, in sequence from front to back: a first-stage thread unit, a second-stage thread unit, a third-stage thread unit, and a fourth-stage thread unit.

[0049] The to-be-processed ultrasonic metrology data q is subjected to four-stage knowledge character extraction by using the four-stage thread unit, and each thread unit can output a transition descriptive knowledge relation net corresponding to the thread unit, wherein the first-stage thread unit performs first knowledge character extraction on the to-be-processed ultrasonic metrology data to obtain a transition descriptive knowledge relation net q1, the second-stage thread unit performs second knowledge character extraction on the transition descriptive knowledge relation net q1 to obtain a transition descriptive knowledge relation net q2, the third-stage thread unit performs third knowledge character extraction on the transition descriptive knowledge relation net q2 to obtain a transition descriptive knowledge relation net q3, and the fourth-stage thread unit performs fourth knowledge character extraction on the transition descriptive knowledge relation net q3 to obtain a transition descriptive knowledge relation net q4.

[0050] For the fourth level thread unit, the transition description knowledge relation net q4 is determined as the fourth level knowledge character extraction corresponding first description knowledge relation net q41;

[0051] For the third level thread unit, the fourth level knowledge character extraction corresponding first description knowledge relation net q41 is derived and fused with the third level knowledge character extraction corresponding transition description knowledge relation net q3 to obtain the third level knowledge character extraction corresponding first description knowledge relation net q31.

[0052] For the second level thread unit, the third level knowledge character extraction corresponding first description knowledge relation net q31 is derived and fused with the second level knowledge character extraction corresponding transition description knowledge relation net q2 to obtain the second level knowledge character extraction corresponding first description knowledge relation net q21.

[0053] For the first level thread unit, the second level knowledge character extraction corresponding first description knowledge relation net q21 is derived and fused with the first knowledge character extraction corresponding transition description knowledge relation net q1 to obtain the first knowledge character extraction corresponding first description knowledge relation net q11.

[0054] In the knowledge character extraction of the sample ultrasonic metrological data, multiple knowledge character extractions can also be performed on the sample ultrasonic metrological data to obtain second description knowledge relation nets corresponding to each first description knowledge relation net. The process of obtaining the second description knowledge relation net is similar to that of obtaining the first description knowledge relation net, and will not be described here.

[0055] Here, the sample ultrasonic metrological data can be subjected to multiple knowledge character extractions by using a pre-configured knowledge character extraction thread to obtain second description knowledge relation nets corresponding to the multiple knowledge character extractions respectively.

[0056] Here, the knowledge character extraction thread can be the same thread as the knowledge character extraction thread described above for obtaining the first description knowledge relation net, or can be two knowledge character extraction branches of similar threads. On the basis of the two knowledge character extraction threads being two knowledge character extraction branches of similar threads, the parameters of the two knowledge character extraction branches are the same.

[0057] Illustratively, the knowledge character extraction thread for obtaining the second description knowledge relation net and the knowledge character extraction thread for obtaining the first knowledge character highlight are two knowledge character extraction branches of similar threads.

[0058] The knowledge character extraction thread for obtaining the second description knowledge relation net is the same as the knowledge character extraction thread for obtaining the first description knowledge relation net, and also includes four-level thread units. The four-level thread units include, in sequence from front to back, a first-level thread unit, a second-level thread unit, a third-level thread unit, and a fourth-level thread unit.

[0059] The four-level knowledge character extraction is performed on the sample ultrasonic metrological data w by the four-level thread units. Each thread unit can output a transition description knowledge relation net corresponding to the thread unit. The first-level thread unit performs first knowledge character extraction on the sample ultrasonic metrological data to obtain a transition description knowledge relation net w1. The second-level thread unit performs second knowledge character extraction on the transition description knowledge relation net w1 to obtain a transition description knowledge relation net w2. The third-level thread unit performs third knowledge character extraction on the transition description knowledge relation net w2 to obtain a transition description knowledge relation net w3. The fourth-level thread unit performs fourth knowledge character extraction on the transition description knowledge relation net w3 to obtain a transition description knowledge relation net w4.

[0060] For the fourth-level thread unit, the transition description knowledge relation net w4 is determined as a second description knowledge relation net w42 corresponding to the fourth-level knowledge character extraction.

[0061] For the third-level thread unit, the second description knowledge relation net w42 corresponding to the fourth-level knowledge character extraction is derived and fused with the transition description knowledge relation net w3 corresponding to the third-level knowledge character extraction to obtain a second description knowledge relation net w32 corresponding to the third-level knowledge character extraction.

[0062] For the second-level thread unit, the second description knowledge relation net w32 corresponding to the third-level knowledge character extraction is derived and fused with the transition description knowledge relation net w2 corresponding to the second-level knowledge character extraction to obtain a second description knowledge relation net w22 corresponding to the second-level knowledge character extraction.

[0063] For the first-level thread unit, the second description knowledge relation net w22 corresponding to the second-level knowledge character extraction is derived and fused with the transition description knowledge relation net w1 corresponding to the first knowledge character extraction to obtain a second description knowledge relation net w21 corresponding to the first knowledge character extraction.

[0064] The process of multiple knowledge character extraction can be performed only once, and after obtaining the second description knowledge relationship network corresponding to each level of knowledge character extraction, the second description knowledge relationship network corresponding to each level of knowledge character extraction is saved in the pre-set storage location of the execution subject. When identifying defects of a certain part, if the second description knowledge relationship network of the sample ultrasonic metrology data corresponding to the part exists, it can be directly read from the pre-set storage location, and it is not necessary to perform multiple knowledge character extraction on the sample ultrasonic metrology data again.

[0065] In another embodiment, at least one knowledge character extraction can also be performed on the to-be-processed ultrasonic metrology data, and the output of the last knowledge character extraction is determined as the first description knowledge relationship network of the to-be-processed ultrasonic metrology data; at least one knowledge character extraction is performed on the sample ultrasonic metrology data, and the output of the last knowledge character extraction is determined as the second description knowledge relationship network of the sample ultrasonic metrology data.

[0066] III: In the above S103, when the first description knowledge relationship network and the second description knowledge relationship network are subjected to knowledge character noise analysis processing, for each type of first description knowledge relationship network, the knowledge character noise analysis processing can be performed on each type of first description knowledge relationship network and the second description knowledge relationship network corresponding to each type of first description knowledge relationship network, to obtain the knowledge character combined ultrasonic metrology data corresponding to each type of first description knowledge relationship network.

[0067] Exemplarily, the embodiment of the present disclosure also provides a method for performing knowledge character noise analysis processing on a first description knowledge relationship network and a second description knowledge relationship network corresponding to the first description knowledge relationship network.

[0068] S301: Based on the first description knowledge relationship network and the second description knowledge relationship network corresponding to the first description knowledge relationship network, the second description knowledge relationship network corresponding to the first description knowledge relationship network is subjected to knowledge character cleaning processing, to obtain the knowledge character cleaning ultrasonic metrology data of the second description knowledge relationship network corresponding to the first description knowledge relationship network.

[0069] In a specific implementation, the second description knowledge relationship network corresponding to the first description knowledge relationship network can be processed by the following method: for each first data node in the first description knowledge relationship network, a plurality of associated data nodes corresponding to the first data node are determined from a plurality of second data nodes of the second description knowledge relationship network corresponding to the first description knowledge relationship network; wherein each associated data node corresponding to the first data node has a difference with the target second data node positioned in association with the first data node that meets the set requirements; based on the common factor between the first data node and each associated data node, the target second data node positioned in association with the first data node is processed by knowledge character cleaning.

[0070] The plurality of associated data nodes corresponding to a random first data node, for example, are second data nodes in the second description knowledge relationship network that have a difference with the target second data node less than a certain difference specified value set in advance.

[0071] After determining the plurality of associated data nodes of the first data node, the common factor between each associated data node and the first data node can be determined by the following method: based on the positioning of the first data node in the first description knowledge relationship network and the difference specified value set in advance, a first local description knowledge relationship network is obtained; and based on the positioning of a random associated data node corresponding to the first data node in the second description knowledge relationship network and the difference specified value, a second local description knowledge relationship network is obtained; based on the first local description knowledge relationship network and the second local description knowledge relationship network, the common factor between the first data node and the random associated data node corresponding to the first data node is determined.

[0072] After obtaining the common factor between the first data node and each associated data node, the target second data node positioned in association with the first data node can be processed by the following method based on the common factor between the first data node and each associated data node and the knowledge character parameters of each associated data node.

[0073] For example, the knowledge character parameters corresponding to each of the plurality of associated data nodes can be processed based on the common factor between the associated data nodes and the first data node to obtain a first processing result; and the common factors corresponding to the plurality of associated data nodes are spliced to obtain a second processing result; the comparison of the first processing result and the second processing result determines the knowledge character parameters of the target second data node positioned in association with the first data node after the knowledge character cleaning processing.

[0074] After the knowledge character cleaning is performed on the target second data nodes associated with each first data node in the first description knowledge relationship network respectively, the knowledge character cleaning ultrasonic measurement data of the second description knowledge relationship network is obtained.

[0075] The process of knowledge character noise analysis and processing provided by the embodiments of the present disclosure further includes.

[0076] S302: Based on the first description knowledge relationship network and the second description knowledge relationship network corresponding to the first description knowledge relationship network, the significance ultrasonic measurement data corresponding to the first description knowledge relationship network is obtained; wherein the target value of a random one traffic data segment in the significance ultrasonic measurement data represents a noise value of the first data node in the first description knowledge relationship network that is associated with the random one traffic data segment.

[0077] Here, it should be noted that S301 and S302 above have no logical relationship.

[0078] In specific implementation, the significance ultrasonic measurement data corresponding to a random one Zhang first description knowledge relationship network can be obtained in the following manner: for each first data node in the first description knowledge relationship network, a plurality of associated data nodes corresponding to the first data node are determined from a plurality of second data nodes of the second description knowledge relationship network corresponding to the first description knowledge relationship network; wherein each associated data node corresponding to the first data node has a difference with the target second data node associated with the first data node that meets the set requirement; based on the common factor between the first data node and each associated data node, the noise value of the first data node is determined.

[0079] Here, the specific manner of the associated data node corresponding to the first data node and the manner of determining the common factor between the first data node and the associated data node are similar to those in S301 above, and will not be described here.

[0080] After the common factor between the first data node and each associated data node is determined, the maximum common factor of the common factors between the plurality of associated data nodes and the first data node can be determined, for example; based on the maximum common factor, the noise value of the first data node is determined.

[0081] For another example, the common factor mean can be determined according to the common factors between the plurality of associated traffic data segments and the first traffic data segment, and the noise value of the first traffic data segment is determined based on the common factor mean.

[0082] After the noise values corresponding to the first data nodes in the first description knowledge relationship network are determined, the significance ultrasonic metrology data is obtained based on the noise values corresponding to the first data nodes in the first description knowledge relationship network. At this time, for example, the ultrasonic metrology data formed by the noise values corresponding to all the first data nodes is determined as the significance ultrasonic metrology data.

[0083] S303: Based on the knowledge character cleaning ultrasonic metrology data, the significance ultrasonic metrology data is obtained, and the knowledge character combination ultrasonic metrology data corresponding to the first description knowledge relationship network is obtained.

[0084] Here, for example, the knowledge character cleaning ultrasonic metrology data and the first description knowledge relationship network can be integrated to obtain the integrated description knowledge relationship network corresponding to the first description knowledge relationship network. Then, based on the significance ultrasonic metrology data and the integrated description knowledge relationship network, the knowledge character combination ultrasonic metrology data is obtained.

[0085] In specific implementation, the knowledge character cleaning ultrasonic metrology data and the first description knowledge relationship network can be fused to obtain the integrated description knowledge relationship network.

[0086] When the knowledge character combination ultrasonic metrology data is obtained based on the significance ultrasonic metrology data and the integrated description knowledge relationship network, for example, the significance ultrasonic metrology data and the integrated description knowledge relationship network can be multiplied by a matrix to obtain the knowledge character combination ultrasonic metrology data.

[0087] In the embodiments of the present disclosure, the specific process of performing knowledge character noise analysis processing on the first description knowledge relationship network and the second description knowledge relationship network corresponding to the specified value can be implemented by using a pre-configured knowledge character noise analysis thread.

[0088] The abnormal attention module is configured to obtain the significance ultrasonic metrology data of the first description knowledge relationship network based on the method provided in S302. The knowledge character cleaning module is configured to obtain the knowledge character cleaning ultrasonic metrology data corresponding to the second description knowledge relationship network corresponding to the first description knowledge relationship network based on the method provided in S302.

[0089] Then, the knowledge character cleaning ultrasonic metrology data and the first description knowledge relationship network are fused to obtain the integrated description knowledge relationship network, and the knowledge character combination ultrasonic metrology data is obtained based on the significance ultrasonic metrology data and the integrated description knowledge relationship network.

[0090] In another embodiment, if the first and second description knowledge relationship networks each only have one, the first and second description knowledge relationship networks can also be processed in a similar manner as described above to obtain knowledge character combination ultrasonic measurement data. The specific knowledge character noise analysis processing method is not repeated here.

[0091] IV: In the above S104, when obtaining the noise analysis result of the to-be-processed ultrasonic measurement data based on the knowledge character combination ultrasonic measurement data, on the basis of obtaining the first and second description knowledge relationship networks corresponding to the plurality of feature processing respectively, the noise analysis result of each first description knowledge relationship network can be obtained based on the knowledge character combination ultrasonic measurement data corresponding to each first description knowledge relationship network; and the noise analysis result of the to-be-processed ultrasonic measurement data can be obtained based on the noise analysis results of the first description knowledge relationship networks corresponding to the plurality of knowledge character extractions respectively.

[0092] An exemplary pre-configured identification thread can be used to perform flaw identification processing on the knowledge character combination ultrasonic measurement data to obtain the noise analysis result corresponding to the to-be-processed ultrasonic measurement data. The identification thread provided by the disclosed embodiments uses, for example, a full convolution pixel-by-pixel target identification thread.

[0093] The positioning of the flaw region in the first description knowledge relationship network indicates the positioning of the flaw in the first description knowledge relationship network.

[0094] After obtaining the identification result of the first description knowledge relationship network corresponding to each of the plurality of knowledge character extractions, the identification results of the first description knowledge relationship networks corresponding to the plurality of knowledge character extractions can be integrated using, for example, a non-maximum suppression method to obtain the noise analysis result of the to-be-processed ultrasonic measurement data.

[0095] For another example, the intersection of the identification results of the first description knowledge relationship networks corresponding to the plurality of knowledge character extractions can also be taken to determine the noise analysis result of the to-be-processed ultrasonic measurement data.

[0096] The embodiment of the present disclosure obtains the first description knowledge relationship network ultrasonic measurement data corresponding to each knowledge character extraction by performing multiple knowledge character extractions on the to-be-processed ultrasonic measurement data, obtains the second description knowledge relationship network corresponding to each first description knowledge relationship network by performing multiple knowledge character extractions on the sample ultrasonic measurement data, and then performs knowledge character noise analysis processing on the first description knowledge relationship network and the second description knowledge relationship network corresponding to the first description knowledge relationship network for each first description knowledge relationship network to obtain the knowledge character combined ultrasonic measurement data corresponding to the first description knowledge relationship network, so as to reduce the interference factors existing between the first description knowledge relationship network and the second description knowledge relationship network by fusing the features in the to-be-processed ultrasonic measurement data and the sample ultrasonic measurement data, and then obtain the noise analysis result of the first description knowledge relationship network by using the knowledge character combined ultrasonic measurement data, and further obtain the noise analysis result of the to-be-processed ultrasonic measurement data with higher accuracy by comprehensively analyzing the noise analysis results of the first description knowledge relationship networks corresponding to multiple knowledge character extractions.

[0097] On the basis described above, a noise processing method and device applied to an ultrasonic measurement instrument are provided, and the device comprises:

[0098] A data obtaining module is configured to obtain to-be-processed ultrasonic measurement data and sample ultrasonic measurement data.

[0099] A character extraction module is configured to perform knowledge character extraction on the to-be-processed ultrasonic measurement data to obtain a first description knowledge relationship network of the to-be-processed ultrasonic measurement data, and perform knowledge character extraction on the sample ultrasonic measurement data to obtain a second description knowledge relationship network corresponding to the sample ultrasonic measurement data.

[0100] A data obtaining module is configured to obtain to-be-processed ultrasonic measurement data and sample ultrasonic measurement data.

[0101] A result analysis module is configured to obtain a noise analysis result of the to-be-processed ultrasonic measurement data based on the knowledge character combined ultrasonic measurement data.

[0102] On the basis described above, please refer to Figure 2 , a noise processing method system 300 applied to an ultrasonic measurement instrument is shown, which comprises a processor 310 and a memory 320 in communication with each other, the processor 310 is configured to read a computer program from the memory 320 and execute to realize the method described above.

[0103] Based on the above, a computer readable storage medium is also provided, and a computer program stored thereon, which, when executed, implements the method described above.

[0104] In summary, based on the above scheme, knowledge character extraction is performed on the sample ultrasonic metrology data to obtain a second description knowledge relationship network corresponding to the sample ultrasonic metrology data; knowledge character noise analysis processing is performed on the first description knowledge relationship network and the second description knowledge relationship network to obtain knowledge character combined ultrasonic metrology data; and based on the knowledge character combined ultrasonic metrology data, a noise analysis result of the to-be-processed ultrasonic metrology data is obtained. By performing knowledge character noise analysis processing on the first description knowledge relationship network of the to-be-processed ultrasonic metrology data and the second description knowledge relationship network of the sample ultrasonic metrology data, interference factors existing between the first description knowledge relationship network and the second description knowledge relationship network are reduced, and then a more accurate noise analysis result of the first description knowledge relationship network can be obtained by using the knowledge character combined ultrasonic metrology data.

[0105] It should be understood that the system and its modules shown above can be implemented in various ways. For example, in some embodiments, the system and its modules can be implemented by hardware, software, or a combination of software and hardware. The hardware part can be implemented by special logic; the software part can be stored in a memory and executed by a suitable instruction execution system, such as a microprocessor or a specially designed hardware. Those skilled in the art can understand that the above method and system can be implemented by computer executable instructions and / or included in processor control code, such as provided on a carrier medium, such as a magnetic disk, CD or DVD-ROM, a programmable memory, such as a read-only memory (firmware), or a data carrier, such as an optical or electronic signal carrier. The system and its modules of the present application can not only be implemented by hardware circuit, such as very large scale integrated circuit or gate array, semiconductor, such as logic chip, transistor, or programmable hardware device, such as field programmable gate array, programmable logic device, but also by software, such as executed by various types of processors, and also by a combination of the above hardware circuit and software (for example, firmware).

[0106] It should be noted that different embodiments can have different beneficial effects, and in different embodiments, the beneficial effects that can be produced can be any one or a combination of the above, or any other beneficial effects that can be obtained.

[0107] Having described the basic concepts, it is obvious to those skilled in the art that the foregoing detailed description of the application is intended for purposes of illustration only and is not intended to limit the scope of the present application. Although the present application has been described in detail with reference to certain illustrative embodiments, various modifications, improvements, and alterations can become apparent to those skilled in the art. Such modifications, improvements, and alterations are intended to fall within the spirit and scope of the present application, which is defined by the appended claims.

[0108] Also, the use of "an" or "one" to describe the present application shall not be construed to mean there is only one of the features or one of the embodiments described herein. Further, a plurality of items connected by "or" should be construed as individual items as well as in the conjunctive sense, i.e., an English publisher, or a French publisher, unless such context clearly indicates otherwise.

[0109] Moreover, those skilled in the art will appreciate that the various aspects of the present application can be described in terms of a few preferred embodiments or examples, but that the scope of the present application is not intended to be limited to only a few embodiments or examples. Rather, the scope of the present application is to be construed broadly as set forth in the appended claims, and herein before broadly interpreted in the context of the various aspects of the present application. Numerous alternative embodiments from those described herein will be apparent to those skilled in the art in view of the foregoing detailed description of the application.

[0110] Computer storage media can include volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, solid state drives (SSDs) that are based on RAM, flash memory or other solid state memory technology, CD-ROM, digital versatile discs (DVD), or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information in a non-transitory, computer readable format. Note that the computer storage media can be integrated within, or external to, a computing device such as a server, desktop computer, laptop computer, tablet computer, personal digital assistant (PDA), mobile telephone, smart phone, or any other device that can be used to execute program code.

[0111] Computer program code for carrying out operations of various aspects of the present application can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C++, C#, VB.NET, Python and others, conventional procedural programming languages, such as the "C" programming language, Visual Basic, Fortran 2003, Perl, COBOL 2002, PHP, ABAP, dynamic programming languages such as Python, Ruby and Groovy, or others. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any form of network, such as a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider) or cloud computing environment or as a service such as Software as a Service (SaaS).

[0112] Furthermore, the order of presentation of the processing elements and sequences described is not intended to be an indication of their relative importance or a suggestion that they are the only manners in which the processes and methods described can be carried out. Although the above disclosure discusses some presently preferred embodiments of the application, the present application should not be limited to these embodiments alone. Many variations in the embodiments described herein will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other embodiments without the use of the details below. For example, although the system components described above can be implemented by hardware devices, they can also be implemented by software solutions only, such as installing the described system on existing servers or mobile devices.

[0113] Similarly, it is to be noticed that the term "comprising", used in the description, should not be interpreted as being restricted to the means listed thereafter; it does not exclude other elements or steps. It is thus to be interpreted as specifying the presence of the stated features, integers, steps or components as referred to, but does not preclude the presence or addition of one or more other features, integers, steps or components, or groups thereof. Thus, the scope of the expression should be commensurate to the scope of the claims.

[0114] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise stated, "about", "approximately" or "substantially" indicate that the numbers allow adaptive changes. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which can be changed according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of the present application are approximate values, in specific embodiments, the settings of such numerical values ​​are as accurate as possible within the feasible range.

[0115] Each patent, patent application, patent application disclosure, and other materials, such as articles, books, specifications, publications, documents, etc., cited in this application is hereby incorporated by reference in its entirety. This includes application history documents that are inconsistent with or conflict with the content of this application, as well as documents (currently or subsequently attached to this application) that limit the broadest scope of the claims of this application. It should be noted that if the descriptions, definitions, and / or use of terms in the accompanying materials of this application are inconsistent or conflicting with the content of this application, the descriptions, definitions, and / or use of terms in this application shall prevail.

[0116] 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 variations may also fall within the scope of this application. Therefore, by way of example and not limitation, alternative configurations of the embodiments of this application may be considered consistent with the teachings of this application. Accordingly, the embodiments of this application are not limited to the embodiments explicitly introduced and described in this application.

[0117] The above are merely embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A noise processing method applied to ultrasonic measuring instruments, characterized in that: The method comprises: Obtaining ultrasonic measurement data to be processed and sample ultrasonic measurement data; Performing knowledge character extraction on the ultrasonic measurement data to be processed to obtain a first description knowledge relationship network of the ultrasonic measurement data to be processed, and performing knowledge character extraction on the sample ultrasonic measurement data to obtain a second description knowledge relationship network corresponding to the sample ultrasonic measurement data; Performing knowledge character noise analysis on the first description knowledge relationship network and the second description knowledge relationship network to obtain knowledge character combination ultrasonic measurement data; Combining ultrasonic measurement data based on the knowledge characters, obtaining a noise analysis result of the ultrasonic measurement data to be processed; The extracting knowledge characters from the ultrasonic measurement data to be processed to obtain a first description knowledge relationship network of the ultrasonic measurement data to be processed includes: extracting multiple knowledge characters from the ultrasonic measurement data to be processed to obtain a first description knowledge relationship network corresponding to each knowledge character extraction; The extracting knowledge characters from the sample ultrasonic measurement data to obtain a second description knowledge relationship network corresponding to the sample ultrasonic measurement data includes: extracting a plurality of knowledge characters from the sample ultrasonic measurement data to obtain a second description knowledge relationship network corresponding to each of the first description knowledge relationship networks; The step of performing knowledge character noise analysis on the first description knowledge relationship network and the second description knowledge relationship network to obtain knowledge character combination ultrasonic measurement data includes: for each first description knowledge relationship network, performing knowledge character noise analysis on each first description knowledge relationship network and the second description knowledge relationship network corresponding to each first description knowledge relationship network to obtain knowledge character combination ultrasonic measurement data corresponding to each first description knowledge relationship network; The performing knowledge character noise analysis on each of the first description knowledge relationship networks and the second description knowledge relationship networks corresponding to each of the first description knowledge relationship networks includes: Based on each of the first description knowledge relationship networks and the second description knowledge relationship networks corresponding to each of the first description knowledge relationship networks, performing knowledge character cleaning processing on the second description knowledge relationship network corresponding to the first description knowledge relationship network to obtain knowledge character cleansed ultrasonic measurement data of the second description knowledge relationship network corresponding to the first description knowledge relationship network; and based on each of the first description knowledge relationship networks and the second description knowledge relationship networks corresponding to each of the first description knowledge relationship networks, obtaining significant ultrasonic measurement data corresponding to each of the first description knowledge relationship networks; wherein the target value of a random flow data segment in the significant ultrasonic measurement data represents a noise value indicating a defect in locating a first data node associated with the random flow data segment in the first description knowledge relationship network; Based on the knowledge character cleaning ultrasonic measurement data and the significance ultrasonic measurement data, the knowledge character combination ultrasonic measurement data corresponding to each first description knowledge relationship network is obtained.

2. The noise processing method for ultrasonic measuring instruments according to claim 1, characterized in that: The step of combining ultrasonic measurement data based on the knowledge characters to obtain a noise analysis result of the ultrasonic measurement data to be processed includes: Based on the ultrasonic measurement data of the knowledge character combination corresponding to each first description knowledge relationship network, obtaining a noise analysis result of each first description knowledge relationship network; Based on the noise analysis results of the first description knowledge relationship network corresponding to the plurality of knowledge character extractions, a noise analysis result of the ultrasonic measurement data to be processed is obtained.

3. The noise processing method applied to ultrasonic measuring instruments according to claim 1 or 2, characterized in that: The step of extracting multiple knowledge characters from the ultrasonic measurement data to be processed to obtain a first description knowledge relationship network corresponding to each knowledge character extraction includes: Extracting multiple knowledge characters from the ultrasonic measurement data to be processed to obtain a transition description knowledge relationship network corresponding to each knowledge character extraction; In the case where the extraction of each knowledge character is the last knowledge character extraction, the transition description knowledge relationship network corresponding to the last knowledge character extraction is determined as the first description knowledge relationship network corresponding to the last knowledge character extraction; In the case where the various knowledge character extractions are other levels of knowledge character extractions except the last knowledge character extraction, the transition description knowledge relationship network corresponding to the various knowledge character extractions is combined with the first description knowledge relationship network corresponding to the next knowledge character extraction of the knowledge character extraction to obtain the first description knowledge relationship network corresponding to the various knowledge character extractions.

4. The noise processing method for ultrasonic measuring instruments according to claim 3, characterized in that: The step of combining the transition description knowledge relationship network corresponding to each knowledge character extraction with the first description knowledge relationship network corresponding to the next knowledge character extraction of the knowledge character extraction to obtain the first description knowledge relationship network corresponding to each knowledge character extraction includes: Derivatively extracting the first description knowledge relationship network corresponding to the next knowledge character extraction of the knowledge character extraction to obtain a derivative vector; After fusing the derivative vector with the transition description knowledge relationship network corresponding to the knowledge character extraction, a first description knowledge relationship network corresponding to the knowledge character extraction is obtained.

5. The noise processing method for ultrasonic measuring instruments according to claim 1, characterized in that: The step of performing knowledge character cleaning on the second description knowledge relationship network corresponding to each first description knowledge relationship network based on each first description knowledge relationship network and the second description knowledge relationship network corresponding to each first description knowledge relationship network includes: For each first data node in the first descriptive knowledge relationship network, determine a plurality of associated data nodes corresponding to the first data node from a plurality of second data nodes in a second descriptive knowledge relationship network corresponding to the first descriptive knowledge relationship network; wherein the difference between each associated data node corresponding to the first data node and a target second data node positioned and associated with the first data node meets set requirements; Based on the commonality factors between the first data node and each associated data node, a knowledge character cleaning process is performed on the target second data node located and associated with the first data node.

6. The noise processing method for ultrasonic measuring instruments according to claim 5, characterized in that: The step of performing knowledge character cleaning on a target second data node located and associated with the first data node based on a commonality factor between the first data node and each associated data node includes: Based on the common factors between the first data node and each associated data node and the knowledge character parameters of each associated data node, performing knowledge character cleaning processing on the target second data node located and associated with the first data node; The step of performing knowledge character cleaning on the target second data node located and associated with the first data node based on the commonality factor between the first data node and each associated data node and the knowledge character parameter of each associated data node includes: Based on the commonality factor between the first data node and each associated data node, processing the knowledge character parameters corresponding to the plurality of associated data nodes corresponding to the first data node to obtain a first processing result; splicing the common factors corresponding to the multiple associated data nodes to obtain a second processing result; The first processing result and the second processing result are compared to determine the knowledge character parameters after the knowledge character cleaning process is performed on the target second data node.

7. The noise processing method for ultrasonic measuring instruments according to claim 1, characterized in that: The obtaining of significant ultrasonic measurement data corresponding to the first description knowledge relationship network based on the first description knowledge relationship network and the second description knowledge relationship network corresponding to the first description knowledge relationship network includes: For each first data node in the first descriptive knowledge relationship network, determine a plurality of associated data nodes corresponding to the first data node from a plurality of second data nodes in a second descriptive knowledge relationship network corresponding to the first descriptive knowledge relationship network; wherein the difference between each associated data node corresponding to the first data node and a target second data node positioned and associated with the first data node meets set requirements; Determining a noise value of the first data node based on a commonality factor between the first data node and each associated data node; obtaining the significant ultrasonic measurement data based on the noise value corresponding to each first data node in the first descriptive knowledge relationship network; The step of determining the noise value of the first data node based on the commonality factors between the first data node and each of the associated data nodes includes: determining a maximum commonality factor of commonality factors between the first data node and each of the associated data nodes; and determining the noise value of the first data node based on the maximum commonality factor. The commonality factor between the first data node and a random associated data node corresponding to the first data node is determined in the following manner: Obtaining a first local description knowledge relationship network based on the location of the first data node in the first description knowledge relationship network and a pre-set difference specified value; and obtaining a second local description knowledge relationship network based on the location of a random associated data node corresponding to the first data node in the second description knowledge relationship network and the specified value of the difference; Determining a commonality factor between the first data node and the random associated data node corresponding to the first data node based on the first local description knowledge relationship network and the second local description knowledge relationship network; The step of obtaining the knowledge character combination ultrasonic measurement data corresponding to the first description knowledge relationship network based on the knowledge character cleaning ultrasonic measurement data and the significance ultrasonic measurement data includes: integrating the knowledge character cleaning ultrasonic measurement data and the first description knowledge relationship network to obtain an integrated description knowledge relationship network corresponding to the first description knowledge relationship network; and obtaining the knowledge character combination ultrasonic measurement data based on the significance ultrasonic measurement data and the integrated description knowledge relationship network.

8. A noise processing system for ultrasonic measuring instruments, characterized in that: The method comprises a processor and a memory communicating with each other, wherein the processor is configured to read a computer program from the memory and execute the program to implement the method according to any one of claims 1 to 7.

Images