A production equipment maintenance method and system

Abstract

The present application provides a production equipment maintenance method and system. The present application selects production equipment detection data nodes from the production equipment detection data after clustering processing and transmits the artificial intelligence thread, thereby avoiding as much as possible the transmission of the selected global production equipment detection data nodes to the artificial intelligence thread after each clustering process, thereby improving the problem of excessive workload of the artificial intelligence thread, and thus effectively improving the efficiency of production equipment detection. Therefore, the production volume of the production equipment can be increased.

Description

Technical Field

[0001] The present application relates to the field of data detection technology, and in particular, to a production equipment maintenance method and system. Background Art

[0002] Equipment maintenance refers to technical activities carried out to maintain, restore and improve the technical status of equipment. It includes maintenance to keep the equipment in good technical status, repairs to restore its function after equipment deterioration or failure, and technical activities to improve the technical status of equipment.

[0003] At present, with mechanized equipment replacing manual labor, the production efficiency can be effectively improved. However, in the actual operation process, since the production equipment can work continuously, it may cause excessive workload and cause damage to the production equipment. In this way, it is difficult to ensure the production efficiency of the production equipment. Therefore, it is necessary to inspect and maintain the production equipment in real time to ensure the efficiency of the production equipment detection and the production volume of the production equipment. Summary of the invention

[0004] In view of this, the present application provides a production equipment maintenance method and system.

[0005] In a first aspect, a production equipment maintenance method is provided, which is applied to an equipment maintenance system, and the method at least comprises:

[0006] Performing clustering processing on the production equipment detection data to be processed to obtain the production equipment detection data after clustering processing;

[0007] Screening out at least one production equipment detection data node from the production equipment detection data after the clustering process; determining the production equipment detection data nodes to be clustered from the at least one production equipment detection data node, wherein the number and recognition degree of the production equipment detection data nodes to be clustered determined sequentially based on the first round and the non-first round of clustering process are inconsistent;

[0008] On the basis of the non-first round of clustering processing, the production equipment detection data nodes to be clustered are determined from the at least one production equipment detection data node according to the real-time description content of the key description of the production equipment detection data to be processed; and the evaluation and quantitative results of the key description in the production equipment detection data nodes to be clustered are obtained through the artificial intelligence thread;

[0009] The detection result of the production equipment detection data to be processed is determined according to the evaluation and quantification result of the key description in the production equipment detection data node to be clustered.

[0010] In an independently implemented embodiment, clustering the production equipment detection data to be processed includes:

[0011] The production equipment detection data to be processed is clustered according to the compression setting values ​​that have not been used in the compression ratio set.

[0012] In an independently implemented embodiment, determining the detection result of the production equipment detection data to be processed according to the evaluation quantification result of the key description in the production equipment detection data node to be clustered includes:

[0013] Based on the fact that there is no unused compression setting value in the compression proportion set or it is determined that there is no production equipment detection data node to be clustered in the at least one production equipment detection data node, the detection result of the production equipment detection data to be processed is determined based on the evaluation and quantification results of the key descriptions in the production equipment detection data nodes to be clustered.

[0014] In an independently implemented embodiment, the compression ratio set includes: no less than two inconsistent compression setting values, and a smaller compression setting value is used first relative to a larger compression setting value.

[0015] In an independently implemented embodiment, determining the production equipment detection data nodes to be clustered from the at least one production equipment detection data nodes includes: based on the first round of clustering processing, all global production equipment detection data nodes are used as production equipment detection data nodes to be clustered.

[0016] In an independently implemented embodiment, the determination of the production equipment detection data nodes to be clustered from the at least one production equipment detection data nodes includes: on the basis of a non-first round of clustering processing, the number of production equipment detection data nodes to be clustered is less than or equal to the number of production equipment detection data nodes screened out in real time, and / or the data recognition degree of the production equipment detection data to be processed after real-time clustering processing exceeds the data recognition degree after the last clustering processing.

[0017] In an independently implemented embodiment, the determining the production equipment detection data nodes to be clustered from the at least one production equipment detection data node according to the real-time description content of the key description of the production equipment detection data to be processed includes:

[0018] Determining the real-time description content of each key description according to the real-time evaluation quantification result of each key description among the several key descriptions included in the production equipment detection data to be processed;

[0019] Counting the real-time description content of the key description in the production equipment detection data set to be processed bound to the production equipment detection data node to achieve the number of key descriptions of the pre-set description content;

[0020] The production equipment detection data nodes whose number of key descriptions realizing the preset description content does not satisfy the preset condition are determined as production equipment detection data nodes to be clustered.

[0021] In an independently implemented embodiment, determining the production equipment detection data node whose number of key descriptions for implementing the preset description content does not meet the preset condition as the production equipment detection data node to be clustered includes:

[0022] Based on the production equipment detection data node, on the basis that the proportion of the number of key descriptions of the pre-set description content and the number of global key descriptions in the production equipment detection data set to be processed bound to the production equipment detection data node is lower than the pre-set proportion, the production equipment detection data node is determined as the production equipment detection data node to be clustered.

[0023] In an independently implemented embodiment, the step of obtaining the real-time evaluation quantitative results of each key description of the production equipment detection data to be processed includes:

[0024] On the basis of the first round of clustering processing, the evaluation and quantification results of each key description in the global production equipment detection data nodes to be clustered output by the artificial intelligence thread are associated with the production equipment detection data to be processed, so as to obtain the evaluation and quantification results of each key description of the production equipment detection data to be processed; wherein, the evaluation and quantification results of each key description of the production equipment detection data to be processed are used as the real-time evaluation and quantification results of each key description of the production equipment detection data to be processed.

[0025] In an independently implemented embodiment, the step of obtaining the real-time evaluation and quantitative results of each key description of the production equipment detection data to be processed includes: on the basis of a non-first round of clustering processing, associating the evaluation and quantitative results of each key description in the global production equipment detection data nodes to be clustered output by the artificial intelligence thread to the production equipment detection data to be processed, and obtaining the evaluation and quantitative results of several key descriptions of the production equipment detection data to be processed; optimizing the real-time evaluation and quantitative results of the corresponding key descriptions of the production equipment detection data to be processed based on the evaluation and quantitative results of several key descriptions of the production equipment detection data to be processed obtained in this round.

[0026] In an independently implemented embodiment, optimizing the real-time evaluation quantification results of the corresponding key descriptions of the production equipment detection data to be processed based on the evaluation quantification results of several key descriptions of the production equipment detection data to be processed obtained in this round includes:

[0027] Counting the evaluation quantification results of several key descriptions of the production equipment detection data to be processed obtained in this round and the judgment values ​​of the real-time evaluation quantification results of the corresponding key descriptions in the production equipment detection data to be processed;

[0028] The statistically determined judgment values ​​are used to optimize the real-time evaluation and quantification results of the corresponding key descriptions in the production equipment detection data to be processed.

[0029] In an independently implemented embodiment, determining the detection result of the production equipment detection data to be processed according to the evaluation quantification result of the key description in the production equipment detection data node to be clustered includes:

[0030] On the premise of one of the key descriptions in the production equipment detection data to be processed, the best percentage result among the percentage results belonging to various categories in the real-time evaluation quantification result of the key description is determined, and the best percentage result and the category bound to the best percentage result are used as the detection result of the key description.

[0031] In an independently implemented embodiment, the recognition degree of the production equipment detection data example configured for the artificial intelligence thread includes: clustering the production equipment detection data in turn according to each compression setting value in the compression ratio set, and obtaining the recognition degree of each production equipment detection data.

[0032] In a second aspect, a production equipment maintenance system is provided, comprising a processor and a memory communicating with each other, wherein the processor is used to retrieve a computer program from the memory and implement the above method by running the computer program.

[0033] The present application provides a production equipment maintenance method and system. The present application selects production equipment detection data nodes from the production equipment detection data after clustering processing and transmits the artificial intelligence thread, thereby avoiding as much as possible the transmission of the selected global production equipment detection data nodes to the artificial intelligence thread after each clustering process, thereby improving the problem of excessive workload of the artificial intelligence thread, and thus effectively improving the efficiency of production equipment detection. Therefore, the production volume of the production equipment can be increased. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0035] Figure 1 A flowchart of a production equipment maintenance method provided in an embodiment of the present application.

[0036] Figure 2 A block diagram of a production equipment maintenance device provided in an embodiment of the present application.

[0037] Figure 3 An architectural diagram of a production equipment maintenance system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0038] In order to better understand the above technical scheme, the technical scheme of the present application is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present application and the specific features in the embodiments are detailed descriptions of the technical scheme of the present application, rather than limitations on the technical scheme of the present application. In the absence of conflict, the embodiments of the present application and the technical features in the embodiments can be combined with each other.

[0039] See also Figure 1 , shows a production equipment maintenance method, which may include the technical solutions described in the following steps 100-140.

[0040] step100, clustering the production equipment detection data to be processed to obtain the production equipment detection data after clustering processing.

[0041] In an alternative embodiment, the present disclosure may use a variety of methods to perform clustering processing on the production equipment detection data to be processed. For example, the present disclosure may pre-configure a compression ratio set, which includes no less than two inconsistent compression setting values. The present disclosure may select an unused compression setting value from the compression ratio set, and perform clustering processing on the production equipment detection data to be processed based on the selected compression setting value. In addition, when selecting an unused compression setting value, the present disclosure generally first selects the smallest unused compression setting value. Furthermore, the present disclosure may also perform clustering processing on the production equipment detection data to be processed using convolution processing or compression processing.

[0042] step110. Filter out at least one production equipment detection data node from the production equipment detection data after clustering processing.

[0043] In an alternative embodiment, the present disclosure generally divides the production equipment detection data obtained after clustering processing into a number of production equipment detection data nodes according to the preset conditions of the artificial intelligence thread for transmission data, and the presets of the screened global production equipment detection data nodes are generally completely consistent. Each screened production equipment detection data node corresponds to a set of production equipment detection data to be processed in turn, and inconsistent production equipment detection data nodes correspond to inconsistent sets. The preset general compression setting value of the set bound to the production equipment detection data node is related to the preset conditions of the artificial intelligence thread for transmission data.

[0044] step120, determine the production equipment detection data nodes to be clustered from at least one production equipment detection data node.

[0045] In an alternative embodiment, based on the first round of clustering processing, the present disclosure may use all global production equipment detection data nodes as production equipment detection data nodes to be clustered, and based on the non-first round of clustering processing, the number of production equipment detection data nodes to be clustered determined by the present disclosure will generally be lower than the number of global production equipment detection data nodes screened out in real time.

[0046] In an alternative embodiment, on the basis of performing clustering processing in a non-first round, the present disclosure can select each screened production equipment detection data node according to the real-time description content of the key description of the production equipment detection data to be processed, and the selected production equipment detection data node is the production equipment detection data node to be clustered. For example, the present disclosure first determines the real-time description content of each key description based on the real-time evaluation quantification result of each key description in the production equipment detection data to be processed. For example, for a key description in the production equipment detection data to be processed, the first percentage result (best percentage result) and the second percentage result (second largest percentage result) of the key description are counted, and the counted percentage result is used as the real-time description content of the key description. According to this processing, the real-time description content of the global key description in the production equipment detection data to be processed can be obtained. Then, the real-time description contents of the key descriptions in the production equipment detection data set to be processed to which the production equipment detection data node is bound are counted to achieve the number of key descriptions of the pre-set description contents, and the production equipment detection data nodes whose number of key descriptions that achieve the pre-set description contents does not meet the pre-set conditions are determined as production equipment detection data nodes to be clustered. For example, on the basis of the production equipment detection data nodes, on the basis that the proportion of the number of key descriptions that achieve the pre-set description contents to the number of global key descriptions in the production equipment detection data set to be processed to which the production equipment detection data node is bound is lower than the pre-set proportion, the production equipment detection data node can be determined as the production equipment detection data node to be clustered.

[0047] In an alternative embodiment, the present disclosure can obtain the real-time evaluation and quantification results of each key description of the production equipment detection data to be processed in the following two ways:

[0048] (1) Based on the first round of clustering processing, the evaluation and quantification results of each key description in the global production equipment detection data node to be clustered output by the artificial intelligence thread are associated with the production equipment detection data to be processed, and the evaluation and quantification results of each key description of the production equipment detection data to be processed are obtained. The present disclosure can use the evaluation and quantification results of each key description of the production equipment detection data to be processed obtained in real time as the real-time evaluation and quantification results of each key description of the production equipment detection data to be processed.

[0049] (2) On the basis of the clustering process that is not performed in the first round, the evaluation and quantification results of each key description in the global production equipment detection data node to be clustered output by the artificial intelligence thread are associated with the production equipment detection data to be processed, and the evaluation and quantification results of several key descriptions of the production equipment detection data to be processed are obtained, and the real-time evaluation and quantification results of the corresponding key descriptions of the production equipment detection data to be processed are optimized based on the evaluation and quantification results of several key descriptions of the production equipment detection data to be processed obtained in this round. For example, the evaluation and quantification results of several key descriptions of the production equipment detection data to be processed obtained in this round and the judgment values ​​of the real-time evaluation and quantification results of the corresponding key descriptions in the production equipment detection data to be processed are counted, and the real-time evaluation and quantification results of the corresponding key descriptions in the production equipment detection data to be processed are optimized using the statistical judgment values. After the optimization process, the present disclosure obtains the real-time evaluation and quantification results of each key description of the production equipment detection data to be processed.

[0050] step130. Obtain the evaluation and quantitative results of the key descriptions in the production equipment detection data nodes to be clustered through the artificial intelligence thread.

[0051] In an alternative embodiment, the artificial intelligence thread in the present disclosure may be an artificial intelligence thread. The present disclosure clusters the production equipment detection data to be processed, and transmits the data set to be clustered in the clustered production equipment detection data to the artificial intelligence thread, which is conducive to improving the computing power of the artificial intelligence thread, thereby helping to improve the problem that the artificial intelligence thread has errors in the key description of the production equipment detection data.

[0052] In an alternative embodiment, the artificial intelligence thread in the present disclosure is obtained by configuring the production equipment detection data examples with multiple inconsistent recognition degrees. For example, the recognition degrees of each global production equipment detection data example belong to the recognition degrees bound in sequence to the compression setting values ​​in the compression ratio set. For example, the reduction ratio set includes: a first compression setting value, a second compression setting value, and a third compression setting value, the first compression setting value corresponds to the first recognition degree, the second compression setting value corresponds to the second recognition degree, and the third compression setting value corresponds to the third recognition degree. The present disclosure can use the production equipment detection data example with the first recognition degree, the production equipment detection data example with the second recognition degree, and the production equipment detection data example with the third recognition degree to configure the artificial intelligence thread to be configured, and the successfully configured artificial intelligence thread can be used for the production equipment detection data matching of the present disclosure.

[0053] step140, determining the detection results of the production equipment detection data to be processed based on the evaluation and quantification results of the key descriptions in the production equipment detection data nodes to be clustered.

[0054] In an alternative embodiment, the present disclosure will perform the step of determining the detection result of the production equipment detection data to be processed based on the evaluation and quantification results of the key descriptions in the production equipment detection data nodes to be clustered, based on the fact that there is no unused compression setting value in the compression ratio set or that the production equipment detection data nodes to be clustered cannot be determined from at least one production equipment detection data node. For example, based on one of the key descriptions in the production equipment detection data to be processed, the best percentage result among the percentage results belonging to various categories in the real-time evaluation and quantification results of the key description is determined, and the best percentage result and the category bound to the best percentage result are used as the detection result of the key description.

[0055] The production equipment maintenance method disclosed in the present invention may specifically include the following steps: step 200, step 210, step 220 and step 230.

[0056] step200, clustering the production equipment detection data to be processed according to the minimum compression setting value that has not been used in the compression ratio set.

[0057] In an alternative embodiment, the compression ratio set is composed of a plurality of compression setting values, and the value of each compression setting value is greater than 1 and not greater than 2.

[0058] In an alternative embodiment, the present disclosure should be sorted according to the compression setting value, and a compression setting value is selected from the compression ratio set each time, and the production equipment detection data to be processed is clustered according to the selected compression setting value. The selected compression setting value becomes the used compression setting value.

[0059] step210, dividing the clustered production equipment detection data into no less than one production equipment detection data node.

[0060] In an alternative embodiment, the present disclosure generally divides the production equipment detection data obtained after clustering processing into a number of production equipment detection data nodes according to the preset conditions of the artificial intelligence thread for transmission data, and the presets of the screened global production equipment detection data nodes are generally completely consistent. Each screened production equipment detection data node corresponds to a set of production equipment detection data to be processed in turn, and inconsistent production equipment detection data nodes correspond to inconsistent sets. The preset general compression setting value of the set bound to the production equipment detection data node is related to the preset conditions of the artificial intelligence thread for transmission data.

[0061] Step 220, select a production equipment detection data node from each production equipment detection data node according to the real-time description content of the key description of the production equipment detection data to be processed, and obtain the evaluation quantitative results of each key description in each selected production equipment detection data node through the artificial intelligence thread. Among them, the selected production equipment detection data node is the production equipment detection data node to be clustered.

[0062] In an alternative embodiment, based on the first round of clustering processing, the present disclosure generally uses all the screened global production equipment detection data nodes as selected production equipment detection data nodes. The present disclosure can be considered that based on the first round of clustering processing, the real-time description content of the key description of the production equipment detection data to be processed is optimized. Therefore, the screened global production equipment detection data nodes are all selected and transmitted to the artificial intelligence thread in sequence, so that the evaluation and quantification results of the global key descriptions of the global production equipment detection data nodes screened in this round can be obtained through the artificial intelligence thread. The evaluation and quantification results of the global key descriptions of the global production equipment detection data nodes obtained in this round can be used to optimize the real-time description content of the key descriptions of the production equipment detection data to be processed. For example, it is set that the artificial intelligence thread of the present disclosure can be divided and processed for M categories. After each production equipment detection data node passes through the artificial intelligence thread in sequence, the present disclosure can obtain the evaluation and quantification results of the global key descriptions in the global production equipment detection data nodes for M categories in sequence.

[0063] In an alternative embodiment, based on the clustering process that is not performed in the first round, the present disclosure generally selects production equipment detection data nodes from the global production equipment detection data nodes screened out in this round based on the real-time description content of the key description of the production equipment detection data to be processed. It is understandable that the production equipment detection data nodes selected in this round may be the global production equipment detection data nodes screened out in this round, or may be part of the global production equipment detection data nodes screened out in this round; of course, it is also possible that a random production equipment detection data node cannot be selected from the global production equipment detection data nodes screened out in this round.

[0064] The present disclosure clusters the production equipment detection data to be processed, and transmits the data set in the clustered production equipment detection data to an artificial intelligence thread (such as an artificial intelligence thread), which is beneficial to improving the computing power of the artificial intelligence thread (such as an artificial intelligence thread), thereby helping to improve the problem of errors in the key description of the production equipment detection data by the artificial intelligence thread.

[0065] The method disclosed herein for selecting production equipment detection data nodes (ie, production equipment detection data nodes to be clustered) based on the real-time description content of the key description of the production equipment detection data to be processed may specifically include the following steps.

[0066] Step 300: Determine the real-time description content of each key description based on the real-time evaluation quantification results of each key description of the production equipment detection data to be processed.

[0067] In an alternative embodiment, the real-time evaluation and quantification results of each key description of the production equipment detection data to be processed in the present disclosure are composed based on the evaluation and quantification results of each key description in the production equipment detection data node output by the artificial intelligence thread for each production equipment detection data node that has been transmitted multiple times. In each clustering process performed by the present disclosure, the real-time evaluation and quantification results of each key description of the production equipment detection data to be processed need to be optimized (such as optimizing the real-time evaluation and quantification results of each key description of the production equipment detection data to be processed).

[0068] In an alternative embodiment, for a random key description (M, N) in the production equipment detection data to be processed, the method for determining the real-time description content of the key description (M, N) according to the real-time evaluation quantification result of the key description (M, N) of the production equipment detection data to be processed can be: setting the artificial intelligence thread to be able to screen out M categories from the production equipment detection data, the real-time evaluation quantification result of the key description (M, N) will include M percentage results, the present disclosure can identify the best percentage result and the second largest percentage result (i.e., the second largest percentage result) from these M percentage results, and statistically calculate the proportion of the identified first percentage result and the second percentage result, and the present disclosure can use the proportion result as the real-time description content of the key description (M, N). The present disclosure can also use other methods to determine the real-time description content of each key description of the production equipment detection data to be processed according to the real-time evaluation quantification results of each key description of the production equipment detection data to be processed, and the present disclosure does not limit the specific method of determining the real-time description content of each key description of the production equipment detection data to be processed.

[0069] Step 310: Count the real-time description contents of the key descriptions in the original production equipment detection data set bound to the production equipment detection data node to realize the number of key descriptions of the pre-set description contents.

[0070] In an alternative embodiment, the preset description content in the present disclosure may be preset based on real-time configuration, for example, the preset description content may be configured as 8.

[0071] Step 320: The production equipment detection data nodes whose number of key descriptions realizing the preset description content does not satisfy the preset conditions are selected as the production equipment detection data nodes.

[0072] In an alternative embodiment, for any production equipment detection data node, if the ratio of the number of key descriptions that realize the pre-set description content to the number of global key descriptions in the original production equipment detection data set bound to the production equipment detection data node does not achieve the pre-set ratio result, the production equipment detection data node can be used as a selected production equipment detection data node and transmitted to the artificial intelligence thread, so as to obtain the evaluation quantitative results of each key description in the production equipment detection data node through the artificial intelligence thread; if the above ratio result achieves the pre-set ratio result, there is no need to transmit the production equipment detection data node to the artificial intelligence thread. The pre-set ratio result in the present disclosure can be based on real-time configuration.

[0073] In addition, the present disclosure may also use other methods to determine the production equipment detection data nodes that do not meet the pre-set conditions. For example, based on the result of determining that there is a difference between the number of key descriptions that implement the pre-set description content in the original production equipment detection data set bound to the production equipment detection data node and the number of key descriptions that do not implement the pre-set description content in the set, the production equipment detection data node can be selected as the production equipment detection data node and transmitted to the artificial intelligence thread. Otherwise, there is no need to transmit the production equipment detection data node to the artificial intelligence thread. For another example, based on determining that the proportion of the number of key descriptions that implement the pre-set description content in the original production equipment detection data set bound to the production equipment detection data node and the number of key descriptions that do not implement the pre-set description content in the set does not achieve the pre-set proportion result, the production equipment detection data node can be selected as the production equipment detection data node and transmitted to the artificial intelligence thread. Otherwise, there is no need to transmit the production equipment detection data node to the artificial intelligence thread.

[0074] The steps disclosed herein for optimizing the real-time evaluation quantification results of each key description of the production equipment detection data to be processed may specifically include the following:

[0075] Step 400, the production equipment maintenance method disclosed in the present invention starts. Optionally, the present invention can update the real-time evaluation quantization results of each key description of the production equipment detection data to be processed at the beginning of the production equipment maintenance method, such as configuring the real-time evaluation quantization results of each key description of the production equipment detection data to be processed to 0. Of course, it is also completely feasible not to perform the update step for the real-time evaluation quantization results of each key description of the production equipment detection data to be processed.

[0076] Based on the first round of clustering processing performed in the present disclosure, the execution of step 410 is triggered.

[0077] Based on the second or third time or other non-first round of clustering processing in the present disclosure, the execution of step 440 is triggered.

[0078] Step 410, all global production equipment detection data nodes selected by the production equipment detection data after the clustering process are transmitted to the artificial intelligence thread, so that the artificial intelligence thread will sequentially output the evaluation quantification results of each key description in each production equipment detection data node for the selected global production equipment detection data. Go to step 420.

[0079] Step 420, the evaluation and quantification results of each key description in each production equipment detection data node output by the artificial intelligence thread are sequentially associated with the production equipment detection data to be processed, so as to obtain the evaluation and quantification results of each key description of the production equipment detection data to be processed. Go to step 430.

[0080] In an alternative embodiment, based on the first round of clustering processing performed in the present disclosure, the evaluation and quantification results of a random key description (M, N) in the production equipment detection data to be processed are obtained based on the evaluation and quantification results of each key description in each production equipment detection data node output by the artificial intelligence thread. Wherein, the first round of clustering processing is performed, W represents the number of categories divided by the artificial intelligence thread, represents the evaluation and quantification results that a random key description (M, N) in the production equipment detection data to be processed belongs to the first category based on the recognition processing performed in the first round, represents the evaluation and quantification results that a random key description (M, N) in the production equipment detection data to be processed belongs to the second category based on the recognition processing performed in the first round, represents the evaluation and quantification results that a random key description (M, N) in the production equipment detection data to be processed belongs to the Wth category based on the recognition processing performed in the first round.

[0081] step430, taking the evaluation and quantification results of each key description of the production equipment detection data to be processed obtained in this round as the real-time evaluation and quantification results of each key description of the production equipment detection data to be processed, for example, the real-time evaluation and quantification result of a random key description (M, N) of the production equipment detection data to be processed.

[0082] Step 440, select a production equipment detection data node from the global production equipment detection data nodes selected by the production equipment detection data after the current round of clustering processing, and transmit the selected production equipment detection data node to the artificial intelligence thread. Go to step 450.

[0083] Step 450, sequentially associate the evaluation and quantification results of each key description in each production equipment detection data node output by the artificial intelligence thread with the production equipment detection data to be processed, thereby obtaining the evaluation and quantification results of at least part of the key description of the production equipment detection data to be processed. Go to step 460.

[0084] In an alternative embodiment, based on the o-th (o exceeds 2) clustering process performed in the present disclosure, based on the evaluation and quantification results of each key description in each production equipment detection data node output by the artificial intelligence thread, the evaluation and quantification results of a random key description (M, N) in the production equipment detection data to be processed are obtained. Wherein, o represents the o-th execution of clustering process, W represents the number of categories divided by the artificial intelligence thread, represents the evaluation and quantification results of a random key description (M, N) in the production equipment detection data to be processed belonging to the first category based on the o-th execution of recognition process, represents the evaluation and quantification results of a random key description (M, N) in the production equipment detection data to be processed belonging to the second category based on the o-th execution of recognition process, represents the evaluation and quantification results of a random key description (M, N) in the production equipment detection data to be processed belonging to the Wth category based on the o-th execution of recognition process. It can be understood that if the key description (M, N) in the production equipment detection data to be processed belongs to the key description of the set of production equipment detection data nodes selected by this round of clustering processing and associated with the production equipment detection data to be processed, then it is the evaluation quantification result of the corresponding key description output by the artificial intelligence thread, and if the key description (M, N) does not belong to the key description of the set of production equipment detection data nodes selected by this round of clustering processing and associated with the production equipment detection data to be processed, then the present disclosure can be configured as 0.

[0085] Step 460, using the evaluation and quantification results of at least part of the key descriptions of the production equipment detection data to be processed obtained in this round to optimize the real-time evaluation and quantification results of each key description of the production equipment detection data to be processed.

[0086] In an alternative embodiment, based on the second or third non-first round of clustering processing, the present disclosure obtains real-time evaluation and quantification results of each key description of the production equipment detection data to be processed by iterating the evaluation and quantification results of each key description in each production equipment detection data node obtained in sequence.

[0087] It is set that on the basis of the first round of clustering processing, the evaluation and quantification result of a random key description (M, N) in the production equipment detection data to be processed obtained by the present invention is so that the present invention will record it as the real-time evaluation and quantification result of a random key description (M, N) in the production equipment detection data to be processed.

[0088] Based on the second execution of clustering processing, the evaluation and quantification result of a random key description (M, N) in the production equipment detection data to be processed obtained by the artificial intelligence thread in the present disclosure can be expressed as follows: if the key description (M, N) in the production equipment detection data to be processed belongs to the key description of the set of production equipment detection data nodes selected by the second clustering processing process and associated with the production equipment detection data to be processed, then it is the evaluation and quantification result of the corresponding key description output by the artificial intelligence thread; if the key description (M, N) in the production equipment detection data to be processed does not belong to the key description of the set of production equipment detection data nodes selected by the second clustering processing process and associated with the production equipment detection data to be processed, then it is 0; the present disclosure can target the judgment value of the statistical sum that is not 0, and use the statistical judgment value to optimize the real-time evaluation and quantification result of the corresponding key description (M, N) in the production equipment detection data to be processed.

[0089] Based on the third execution of clustering processing, the evaluation and quantification result of a random key description (M, N) in the production equipment detection data to be processed obtained by the artificial intelligence thread in the present disclosure can be expressed as follows: if the key description (M, N) in the production equipment detection data to be processed belongs to the key description of the set of production equipment detection data nodes selected by the third clustering processing process and associated with the production equipment detection data to be processed, then it is the evaluation and quantification result of the corresponding key description output by the artificial intelligence thread; if the key description (M, N) in the production equipment detection data to be processed does not belong to the key description of the set of production equipment detection data nodes selected by the third clustering processing process and associated with the production equipment detection data to be processed, then it is 0; the present disclosure can target the judgment value of the statistical sum that is not 0, and use the statistical judgment value to optimize the real-time evaluation and quantification result of the corresponding key description (M, N) in the production equipment detection data to be processed.

[0090] Further, based on the above-mentioned process of optimizing the real-time evaluation and quantification results of each key description of the production equipment detection data to be processed based on the second and third executions of clustering processing, it can be known that the process of optimizing the real-time evaluation and quantification results of each key description of the production equipment detection data to be processed based on the fourth or fifth non-first round (oth time) of clustering processing is actually splicing the evaluation and quantification results of each time, for example, splicing to form the real-time evaluation and quantification results of each key description of the production equipment detection data to be processed after optimization. However, when the present disclosure selects the production equipment detection data node that needs to transmit the artificial intelligence thread, the real-time evaluation and quantification results of each key description of the production equipment detection data to be processed based on are the results of splicing the evaluation and quantification results of each previous time, for example, the results of splicing.

[0091] step230. On the basis that there is no unused minimum compression setting value in the compression ratio set or no production equipment detection data node can be selected from each production equipment detection data node, determine the detection result of the production equipment detection data to be processed based on the evaluation and quantification results of each key description in the production equipment detection data to be processed which are composed of the evaluation and quantification results of each key description in each production equipment detection data node; otherwise, return to the above step200.

[0092] In an alternative embodiment, on the basis that there is no unused minimum compression setting value in the compression ratio set, the present disclosure can determine the detection result of the production equipment detection data to be processed according to the real-time evaluation quantization result of the global key description in the production equipment detection data to be processed, that is, the present disclosure takes the best percentage result as the detection result of the key description (M, N) in the production equipment detection data to be processed after splicing the detection results.

[0093] In a replaceable embodiment, on the basis that a production equipment detection data node cannot be selected from each production equipment detection data node, the present disclosure can determine the detection result of the production equipment detection data to be processed based on the real-time evaluation quantization result of the global key description in the production equipment detection data to be processed, that is, the present disclosure targets the detection results and after splicing, uses the best percentage result as the detection result of the key description (M, N) in the production equipment detection data to be processed.

[0094] In an alternative embodiment, when configuring an artificial intelligence thread, the present disclosure generally uses production equipment detection data examples with multiple identifications, and the number of inconsistent identifications is generally related to the number of compression setting values ​​in the compression ratio set. For example, on the basis that the compression ratio set includes three compression setting values, the example data set should at least include production equipment detection data examples with identifications bound to these three compression setting values, and each production equipment detection data example has significant information. On a general basis, in the example data set, the number of production equipment detection data examples with inconsistent identifications is substantially the same. The present disclosure configures the artificial intelligence thread using production equipment detection data examples with inconsistent identifications in the example data set, which is beneficial to improving the accuracy and reliability of the evaluation quantification results output by the artificial intelligence thread for each transmitted production equipment detection data node, thereby helping to improve the credibility of the artificial intelligence thread's matching of production equipment detection data.

[0095] Based on the above, please refer to Figure 2 , a production equipment maintenance device 200 is provided, which is applied to a production equipment maintenance system, and the device comprises:

[0096] A data clustering module 210 is used to perform clustering processing on the production equipment detection data to be processed to obtain the production equipment detection data after clustering processing;

[0097] The data detection module 220 is used to select at least one production equipment detection data node from the production equipment detection data after the clustering process; determine the production equipment detection data node to be clustered from the at least one production equipment detection data node, wherein the number and recognition degree of the production equipment detection data nodes to be clustered determined in sequence based on the first round and the non-first round of clustering process are inconsistent;

[0098] The result detection module 230 is used to determine the production equipment detection data node to be clustered from the at least one production equipment detection data node according to the real-time description content of the key description of the production equipment detection data to be processed based on the non-first round of clustering processing; obtain the evaluation and quantitative results of the key description in the production equipment detection data node to be clustered through the artificial intelligence thread;

[0099] The result quantification module 240 is used to determine the detection result of the production equipment detection data to be processed according to the evaluation quantification result of the key description in the production equipment detection data node to be clustered.

[0100] Based on the above, please refer to Figure 3 , shows a production equipment maintenance system 300, including a processor 310 and a memory 320 that communicate with each other, and the processor 310 is used to read and execute a computer program from the memory 320 to implement the above method.

[0101] Based on the above, a computer-readable storage medium is also provided, on which a computer program stored implements the above method when running.

[0102] In summary, based on the above scheme, the present disclosure selects production equipment detection data nodes from the production equipment detection data after clustering processing and transmits the artificial intelligence thread, thereby avoiding as much as possible the transmission of the selected global production equipment detection data nodes to the artificial intelligence thread after each clustering process, thereby improving the problem of excessive workload of the artificial intelligence thread, and thus effectively improving the efficiency of production equipment detection. Therefore, the production output of the production equipment can be increased.

[0103] 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. Among them, the hardware part can be implemented using dedicated logic; the software part can be stored in a memory and executed by an appropriate instruction execution system, such as a microprocessor or a dedicated design hardware. Those skilled in the art will understand that the above methods and systems can be implemented using computer executable instructions and / or included in a processor control code, such as a carrier medium such as a 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. Such code is provided on the carrier medium such as a 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 circuits such as ultra-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 can also be implemented by software such as executed by various types of processors, and can also be implemented by a combination of the above hardware circuits and software (e.g., firmware).

[0104] It should be noted that different embodiments may produce different beneficial effects. In different embodiments, the beneficial effects that may be produced may be any one or a combination of the above, or any other beneficial effects that may be obtained.

[0105] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of the present application. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements and amendments to the present application. Such modifications, improvements and amendments are suggested in the present application, so such modifications, improvements and amendments still belong to the spirit and scope of the exemplary embodiments of the present application.

[0106] At the same time, the present application uses specific words to describe the embodiments of the present application. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of the present application. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, some features, structures or characteristics in one or more embodiments of the present application can be appropriately combined.

[0107] In addition, it will be appreciated by those skilled in the art that various aspects of the present application may be illustrated and described by a number of patentable categories or situations, including any new and useful process, machine, product or combination of substances, or any new and useful improvements thereto. Accordingly, various aspects of the present application may be performed entirely by hardware, entirely by software (including firmware, resident software, microcode, etc.), or by a combination of hardware and software. The above hardware or software may all be referred to as "data blocks", "modules", "engines", "units", "components" or "systems". In addition, various aspects of the present application may be represented as a computer product located in one or more computer-readable media, which includes computer-readable program code.

[0108] A computer storage medium may include a propagated data signal containing computer program code, for example, in baseband or as part of a carrier wave. The propagated signal may be in a variety of forms, including electromagnetic, optical, etc., or a suitable combination. A computer storage medium may be any computer-readable medium other than a computer-readable storage medium, which can be connected to an instruction execution system, device or apparatus to communicate, propagate or transmit the program for use. The program code on the computer storage medium may be transmitted via any suitable medium, including radio, cable, fiber optic cable, RF, or similar media, or any combination of the above media.

[0109] The computer program codes required for the operation of each part of the present 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 language, Visual Basic, Fortran 2003, Perl, COBOL 2002, PHP, ABAP, dynamic programming languages ​​such as Python, Ruby and Groovy, or other programming languages, etc. The program code can be run entirely on the user's computer, or run on the user's computer as an independent software package, or run partially on the user's computer and partially on a remote computer, or run 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 form, such as a local area network (LAN) or a 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).

[0110] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this application, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this application. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this application. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0111] Similarly, it should be noted that in order to simplify the description of the disclosure of this application and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this application, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the object of this application are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0112] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used for the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "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 characteristics of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining the digits. Although the numerical domains and parameters used to confirm the breadth of the range in some embodiments of the present application are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0113] Each patent, patent application, patent application disclosure, and other materials, such as articles, books, instructions, publications, documents, etc., cited in this application are hereby incorporated by reference in their entirety. Except for application history documents that are inconsistent with or conflicting with the content of this application, documents that limit the broadest scope of the claims of this application (currently or later attached to this application) are also excluded. It should be noted that if the descriptions, definitions, and / or use of terms in the attached materials of this application are inconsistent or conflicting with the content described in this application, the descriptions, definitions, and / or use of terms in this application shall prevail.

[0114] Finally, it should be understood that the embodiments described in this application are only used to illustrate the principles of the embodiments of the present application. Other variations may also fall within the scope of the present application. Therefore, as an example and not a limitation, the alternative configurations of the embodiments of the present application may be considered to be consistent with the teachings of the present application. Accordingly, the embodiments of the present application are not limited to the embodiments explicitly introduced and described in the present application.

[0115] The above are only 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 modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A production equipment maintenance method, characterized in that: Applied to an equipment maintenance system, the method at least comprises: Performing clustering processing on the production equipment detection data to be processed to obtain the production equipment detection data after clustering processing; Screening out at least one production equipment detection data node from the production equipment detection data after the clustering process; determining the production equipment detection data nodes to be clustered from the at least one production equipment detection data node, wherein the number and recognition degree of the production equipment detection data nodes to be clustered determined sequentially based on the first round and the non-first round of clustering process are inconsistent; On the basis of the non-first round of clustering processing, the production equipment detection data nodes to be clustered are determined from the at least one production equipment detection data node according to the real-time description content of the key description of the production equipment detection data to be processed; and the evaluation and quantitative results of the key description in the production equipment detection data nodes to be clustered are obtained through the artificial intelligence thread; Determining the detection result of the production equipment detection data to be processed according to the evaluation quantification result of the key description in the production equipment detection data node to be clustered; The clustering process of the production equipment detection data to be processed includes: Clustering the production equipment detection data to be processed according to the compression setting values ​​that have not been used in the compression ratio set; The compression ratio set includes: no less than two inconsistent compression setting values, and the smaller compression setting value is used first relative to the larger compression setting value; The step of determining the production equipment detection data nodes to be clustered from the at least one production equipment detection data node according to the real-time description content of the key description of the production equipment detection data to be processed includes: Determining the real-time description content of each key description according to the real-time evaluation quantification result of each key description among the several key descriptions included in the production equipment detection data to be processed; Counting the real-time description content of the key description in the production equipment detection data set to be processed bound to the production equipment detection data node to achieve the number of key descriptions of the pre-set description content; The production equipment detection data nodes whose number of key descriptions realizing the preset description content does not satisfy the preset condition are determined as production equipment detection data nodes to be clustered.

2. The method according to claim 1, characterized in that The step of determining the detection result of the production equipment detection data to be processed according to the evaluation quantification result of the key description in the production equipment detection data node to be clustered comprises: Based on the fact that there is no unused compression setting value in the compression proportion set or it is determined that there is no production equipment detection data node to be clustered in the at least one production equipment detection data node, the detection result of the production equipment detection data to be processed is determined based on the evaluation and quantification results of the key descriptions in the production equipment detection data nodes to be clustered.

3. The method according to any one of claims 1 to 2, characterized in that The determining of the production equipment detection data nodes to be clustered from the at least one production equipment detection data node comprises: based on the first round of clustering processing, taking all global production equipment detection data nodes as the production equipment detection data nodes to be clustered; Among them, the determination of the production equipment detection data nodes to be clustered from the at least one production equipment detection data nodes includes: on the basis of a non-first round of clustering processing, the number of production equipment detection data nodes to be clustered is less than or equal to the number of production equipment detection data nodes screened out in real time, and / or the data recognition degree of the production equipment detection data to be processed after real-time clustering processing exceeds the data recognition degree after the last clustering processing.

4. The method according to any one of claims 1 to 2, characterized in that The step of determining the production equipment detection data node whose number of key descriptions realizing the preset description content does not meet the preset condition as the production equipment detection data node to be clustered comprises: Based on the production equipment detection data node, on the basis of realizing that the ratio of the number of key descriptions of the pre-set description content to the number of global key descriptions in the production equipment detection data set to be processed bound to the production equipment detection data node is lower than the pre-set ratio, the production equipment detection data node is determined as the production equipment detection data node to be clustered; The step of obtaining the real-time evaluation quantitative results of each key description of the production equipment detection data to be processed includes: On the basis of the first round of clustering processing, the evaluation and quantification results of each key description in the global production equipment detection data nodes to be clustered output by the artificial intelligence thread are associated with the production equipment detection data to be processed, so as to obtain the evaluation and quantification results of each key description of the production equipment detection data to be processed; wherein, the evaluation and quantification results of each key description of the production equipment detection data to be processed are used as the real-time evaluation and quantification results of each key description of the production equipment detection data to be processed.

5. The method according to claim 4, characterized in that The step of obtaining the real-time evaluation and quantification results of each key description of the production equipment detection data to be processed includes: on the basis of performing clustering processing in a non-first round, associating the evaluation and quantification results of each key description in the global production equipment detection data nodes to be clustered output by the artificial intelligence thread to the production equipment detection data to be processed, and obtaining the evaluation and quantification results of several key descriptions of the production equipment detection data to be processed; optimizing the real-time evaluation and quantification results of the corresponding key descriptions of the production equipment detection data to be processed based on the evaluation and quantification results of several key descriptions of the production equipment detection data to be processed obtained in this round.

6. The method according to claim 5, characterized in that The optimization of the real-time evaluation quantification results of the corresponding key descriptions of the production equipment detection data to be processed based on the evaluation quantification results of several key descriptions of the production equipment detection data to be processed obtained in this round includes: Counting the evaluation quantification results of several key descriptions of the production equipment detection data to be processed obtained in this round and the judgment values ​​of the real-time evaluation quantification results of the corresponding key descriptions in the production equipment detection data to be processed; Utilize the statistically determined judgment values ​​to optimize the real-time evaluation and quantification results of the corresponding key descriptions in the production equipment detection data to be processed; Wherein, determining the detection result of the production equipment detection data to be processed according to the evaluation quantification result of the key description in the production equipment detection data node to be clustered includes: On the premise of one of the key descriptions in the production equipment detection data to be processed, the best percentage result among the percentage results belonging to various categories in the real-time evaluation quantification result of the key description is determined, and the best percentage result and the category bound to the best percentage result are used as the detection result of the key description.

7. The method according to any one of claims 1 to 2, characterized in that The recognition degree of the production equipment detection data example configured for the artificial intelligence thread includes: clustering the production equipment detection data in turn according to each compression setting value in the compression ratio set, and obtaining the recognition degree of each production equipment detection data.

8. A production equipment maintenance system, characterized in that: It comprises a processor and a memory communicating with each other, the processor is used to call a computer program from the memory, and implement the method according to any one of claims 1 to 7 by running the computer program.

Images