Alarm information classification method and device of transformer substation, electronic equipment and storage medium

Abstract

The invention discloses an alarm information classification method and device of a transformer substation, electronic equipment and a storage medium. The method comprises the steps that a target data set is acquired, and the target data set comprises multiple pieces of alarm information of a transformer substation; converting each piece of alarm information in the target data set into a target character string, and determining a character string distance between every two pieces of alarm information in the target data set according to the target character string; performing hierarchical clustering on the alarm information in the target data set according to the character string distance to obtain a hierarchical clustering tree diagram; and determining a classification result of the alarm information according to the hierarchical clustering tree diagram and a preset classification number. According to the technical scheme provided by the embodiment of the invention, the problems of difficulty in alarm information classification and low processing efficiency in related technologies are solved, the alarm information can be effectively classified, and the classification efficiency of the alarm information is improved.

Description

Technical Field

[0001] The embodiments of the present invention relate to the technical field of automatic operation and maintenance of substations, and in particular to a method, device, electronic equipment and storage medium for classifying alarm information of a substation. Background Art

[0002] During the operation of the power system, the substation will generate a large amount of alarm information, which is crucial for detecting equipment status and ensuring the safety of the power grid. Classifying a large amount of alarm information can effectively simplify the fault handling and equipment maintenance work of the substation.

[0003] However, in the related art, professionals manually identify the types of alarm information. Since there are many devices in the substation, the alarm information of each device has different contents and forms, and the alarm information is of various types and sources, which makes the classification of alarm information time-consuming and labor-intensive, and the processing efficiency is low.

[0004] Therefore, an efficient alarm information processing solution is needed to improve the intelligent management level of substations. Summary of the invention

[0005] The present invention provides a method, device, electronic equipment and storage medium for classifying alarm information of a substation, so as to efficiently classify the alarm information of the substation and improve the detection efficiency.

[0006] According to one aspect of the present invention, a method for classifying alarm information of a substation is provided, comprising:

[0007] Acquire a target data set, wherein the target data set includes multiple alarm information of the substation;

[0008] Convert each of the alarm information in the target data set into a target character string, and determine the character string distance between every two alarm information in the target data set according to the target character string;

[0009] Performing hierarchical clustering on the alarm information in the target data set according to the string distance to obtain a hierarchical clustering dendrogram;

[0010] The classification result of the alarm information is determined according to the hierarchical clustering dendrogram and a preset number of classifications.

[0011] According to another aspect of the present invention, there is provided an alarm information classification device for a substation, comprising:

[0012] An acquisition module, used for acquiring a target data set, wherein the target data set includes a plurality of alarm information of a substation;

[0013] A character string distance determination module, used to convert each of the alarm information in the target data set into a target character string, and determine the character string distance between every two alarm information in the target data set according to the target character string;

[0014] A hierarchical clustering module, used for performing hierarchical clustering on the alarm information in the target data set according to the string distance to obtain a hierarchical clustering dendrogram;

[0015] The classification module is used to determine the classification result of the alarm information according to the hierarchical clustering dendrogram and a preset number of classifications.

[0016] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0017] at least one processor; and

[0018] a memory communicatively connected to the at least one processor; wherein,

[0019] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the alarm information classification method for a substation described in any embodiment of the present invention.

[0020] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the alarm information classification method for a substation described in any embodiment of the present invention when executed.

[0021] The technical solution of the embodiment of the present invention firstly obtains a target data set. Since the target data set includes multiple alarm information of the substation, the alarm information to be classified can be quickly collected in batches to provide a data basis for the subsequent classification processing of the alarm information; then, by converting each of the alarm information in the target data set into a target character string respectively, different types of alarm information can be uniformly converted into a character string format, which is convenient for subsequent processing and analysis, and can significantly improve processing efficiency and accuracy. The character string distance between each two alarm information in the target data set is determined according to the target character string, and the similarity between the alarm information can be quantified, which helps to identify highly similar events from a large amount of alarm information, thereby classifying and processing potential repeated alarms and realizing accurate analysis of the alarm information; then, by The alarm information in the target data set is hierarchically clustered according to the string distance to obtain a hierarchical clustering tree diagram, which can classify similar alarm information and effectively reveal the correlation between alarm information, which helps to simplify the management of a large amount of alarm information. The visualized hierarchical clustering tree diagram facilitates the understanding and analysis of alarm information. Finally, by determining the classification result of the alarm information according to the hierarchical clustering tree diagram and a preset number of classifications, the alarm information can be divided into a preset number of categories, supporting flexible classification of alarm information, solving the problem of difficult classification and low processing efficiency of alarm information in related technologies, and effectively classifying alarm information, improving the classification accuracy and efficiency of alarm information, helping to simplify the management and maintenance of substations and improve the efficiency of fault detection and preventive maintenance.

[0022] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 is a flow chart of a method for classifying alarm information of a substation provided according to the first embodiment of the present invention;

[0025] Figure 2 is a flow chart of a method for classifying alarm information of a substation provided according to Embodiment 2 of the present invention;

[0026] Figure 3It is a schematic diagram of a hierarchical clustering tree diagram of a method for classifying alarm information of a substation applicable to an embodiment of the present invention;

[0027] Figure 4 is a flow chart of a method for classifying alarm information of a substation provided according to Embodiment 3 of the present invention;

[0028] Figure 5 This is a schematic diagram of the structure of an alarm information classification device for a substation provided according to a fourth embodiment of the present invention;

[0029] Figure 6 It is a structural schematic diagram of an electronic device for implementing the alarm information classification method of a substation according to an embodiment of the present invention. DETAILED DESCRIPTION

[0030] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0031] It should be noted that the term "target" and the like in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0032] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0033] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0034] It is understandable that before using the technical solutions disclosed in the embodiments of the present disclosure, the types, scope of use, usage scenarios, etc. of the personal information involved in the present disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0035] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly prompt the user that the operation requested to be performed will require obtaining and using the user's personal information. Thus, the user can autonomously choose whether to provide personal information to software or hardware such as an electronic device, application, server, or storage medium that performs the operation of the technical solution of the present disclosure according to the prompt message.

[0036] As an optional but non-limiting implementation, in response to receiving an active request from the user, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0037] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet the relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0038] It is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and relevant provisions.

[0039] Embodiment 1

[0040] Figure 1 A flowchart of a method for classifying alarm information of a substation is provided for the first embodiment of the present invention. This embodiment is applicable to the case of classifying alarm information of a substation. The method can be executed by an alarm information classification device of a substation. The alarm information classification processing device of the substation can be implemented in the form of hardware and / or software. Optionally, it can be implemented by an electronic device, which can be a mobile terminal, a PC or a server. Figure 1 As shown, the method may specifically include:

[0041] S110. Obtain a target data set, wherein the target data set includes multiple alarm information of a substation.

[0042] The target data set can be understood as a data set that collects multiple alarm information of the substation, which may include alarm information collected from multiple preset detection points and / or alarm information obtained from the system log of the operation and maintenance system of the substation. The alarm information can be understood as abnormal prompt information generated when the equipment status or operation status of at least one device in the substation is abnormal. The alarm information may include but is not limited to at least one of the information such as the time, location, type and possible consequences of the fault.

[0043] It can be understood that the method of obtaining the alarm information may include but is not limited to the following methods: determining at least one preset data collection point in one or more target substation equipment in the substation, for example, the target substation equipment may include at least one of the detection equipment, sensor or relay protection equipment; further, data collection equipment can be used to collect alarm information from the data collection point, wherein the data collection equipment may include distributed control equipment or other automation control equipment, etc.

[0044] Since the original alarm information may encounter various problems during the collection process, including but not limited to data entry errors, incomplete information or data "noise" caused by signal interference. In order to ensure the accuracy and reliability of alarm information analysis, after obtaining multiple alarm information of the substation, the alarm information can be cleaned. The data cleaning process may include but is not limited to at least one of removing outliers, filling missing values ​​and noise reduction, and formatting according to a unified format to ensure the quality and consistency of the alarm information.

[0045] S120, convert each of the alarm information in the target data set into a target character string, and determine the character string distance between every two of the alarm information in the target data set according to the target character string.

[0046] The target character string can be understood as a character string in a unified format formed by standardizing the alarm information, so as to facilitate unified analysis and processing. The character string distance can be understood as a measure of the difference between two target character strings, which is used to quantify the difference between the two character strings in character composition or arrangement.

[0047] On the basis of the above scheme, the alarm information may include Chinese characters, uppercase English letters or lowercase English letters, etc. In order to uniformly analyze and process the alarm information, optionally, converting each of the alarm information in the target data set into a target character string respectively includes: for each of the alarm information in the target data set, converting the alarm information into a target character string by at least one of the following operations: when the alarm information includes Chinese characters, translating the Chinese characters into Chinese pinyin, and translating the Chinese pinyin into uppercase English letters; when the alarm information includes lowercase English letters, translating the English letters into uppercase English letters.

[0048] It is understandable that converting the alarm information into uppercase English letters can reduce the processing difficulty caused by the complex relationship between characters. At the same time, the unified capitalization ensures that the case of English letters will not affect the comparison between character strings, and also ensures the consistency and readability of the converted alarm information.

[0049] Based on the above solution, after converting each of the alarm information in the target data set into a target character string, the following may be further included: character string verification. The character string verification includes checking the integrity, consistency and accuracy of the character string to ensure that no error is introduced during the conversion process.

[0050] The above scheme, by effectively converting the alarm information of the substation into a target string in a unified format, provides a basis for subsequent alarm information analysis and hierarchical clustering.

[0051] S130 , hierarchically clustering the alarm information in the target data set according to the character string distance to obtain a hierarchical clustering dendrogram.

[0052] S140: Determine a classification result of the alarm information according to the hierarchical clustering dendrogram and a preset number of classifications.

[0053] Specifically, the hierarchical clustering can be an unsupervised learning method for clustering similar objects together to form clusters. The hierarchical clustering can cluster the alarm information in the target data set into a hierarchical structure by analyzing the similarity or distance between the alarm information. In the present embodiment, the hierarchical clustering merges the alarm information in the target data set into a cluster and represents it graphically as a hierarchical clustering dendrogram. The hierarchical clustering dendrogram can intuitively display how the alarm information is gradually merged into clusters, and the string distance between the alarm information in each merging step. Each leaf node of the hierarchical clustering dendrogram represents a separate alarm information, while the internal nodes represent the merged clusters. The string distance between the nodes reflects the similarity measure during the merge. Exemplarily, the hierarchical clustering dendrogram uses the information identifier of the alarm information as the horizontal axis and the string distance as the vertical axis. The specific method of hierarchically clustering the alarm information in the target data set according to the string distance is not limited here.

[0054] Through the above scheme, the alarm information can be classified according to the string distance to form a hierarchical structure. The hierarchical clustering dendrogram can be used to show the hierarchical structure of all alarm information aggregated from a single alarm information to the overall target data set. The hierarchical clustering dendrogram can not only intuitively represent the similarity between alarm information, but also can be used to determine the classification result. Exemplarily, when a specific classification threshold is selected to cut the dendrogram, the classification result of the preset number of classifications can be obtained. Exemplarily, the classification result of the alarm information is determined according to the hierarchical clustering dendrogram and the preset number of classifications, including: determining the string distance as the classification threshold according to the preset number of classifications, and drawing a straight line parallel to the horizontal axis of the hierarchical clustering dendrogram at the classification threshold; determining the classification result of the alarm information according to the intersection of the straight line and the hierarchical clustering dendrogram.

[0055] The preset number of categories may be a preset number of clusters. The preset number of categories may be selected according to the needs of the actual application scenario to achieve the best classification effect. The classification threshold may be a value of a string distance determined in a hierarchical clustering dendrogram according to the preset number of categories, so that the classification results of the preset number of categories can be obtained by cutting the hierarchical clustering dendrogram under this string distance value.

[0056] It can be understood that a straight line parallel to the horizontal axis is drawn in the hierarchical clustering dendrogram, and the ordinate of the straight line is the classification threshold. The intersection of the straight line and the hierarchical clustering dendrogram represents the classification node of the cluster.

[0057] like Figure 3As shown, if the preset number of classifications is 4, the classification threshold that can produce 4 classification results is determined in the hierarchical clustering tree diagram. The string distance selected here is 0.5, and a straight line is drawn at the string distance. It can be obtained that the straight line has four intersections with the clusters in the hierarchical clustering tree diagram. The intersections are the classification nodes of the clusters. The classification nodes divide the hierarchical clustering tree diagram into 4 parts, and each classification node represents a classification category.

[0058] The above scheme, by automatically dividing the alarm information into a preset number of categories according to the character string distance, the alarm information in the classification results has a high similarity, which helps to simplify management and maintenance work and provide support for fault detection and preventive maintenance.

[0059] The technical solution of the embodiment of the present invention firstly obtains a target data set. Since the target data set includes multiple alarm information of the substation, the alarm information to be classified can be quickly collected in batches to provide a data basis for the subsequent classification processing of the alarm information; then, by converting each of the alarm information in the target data set into a target character string respectively, different types of alarm information can be uniformly converted into a character string format, which is convenient for subsequent processing and analysis, and can significantly improve processing efficiency and accuracy. The character string distance between each two alarm information in the target data set is determined according to the target character string, and the similarity between the alarm information can be quantified, which helps to identify highly similar events from a large amount of alarm information, thereby classifying and processing potential repeated alarms and realizing accurate analysis of the alarm information; then, by The alarm information in the target data set is hierarchically clustered according to the string distance to obtain a hierarchical clustering tree diagram, which can classify similar alarm information and effectively reveal the correlation between alarm information, which helps to simplify the management of a large amount of alarm information. The visualized hierarchical clustering tree diagram facilitates the understanding and analysis of alarm information. Finally, by determining the classification result of the alarm information according to the hierarchical clustering tree diagram and a preset number of classifications, the alarm information can be divided into a preset number of categories, supporting flexible classification of alarm information, solving the problem of difficult classification and low processing efficiency of alarm information in related technologies, and effectively classifying alarm information, improving the classification accuracy and efficiency of alarm information, helping to simplify the management and maintenance of substations and improve the efficiency of fault detection and preventive maintenance.

[0060] Embodiment 2

[0061] Figure 2A flowchart of a method for classifying alarm information of a substation is provided in the second embodiment of the present invention. The technical solution of this embodiment is based on the above embodiment, and further refines how to determine the character string distance between every two alarm messages in the target data set. Optionally, the character string distance between every two alarm messages in the target data set is determined according to the target character string, including: for every two alarm messages in the target data set, determining the target character distance between the last characters in the target character string corresponding to the two alarm messages; determining the character string distance between the two alarm messages according to the target character distance and the length of the two target character strings. For specific implementation methods, please refer to the description of this embodiment. Among them, technical features that are the same or similar to those in the above embodiments are not repeated here. Figure 2 As shown, the method may specifically include:

[0062] S210. Obtain a target data set, wherein the target data set includes multiple alarm information of a substation.

[0063] S220, converting each of the alarm messages in the target data set into a target character string, and determining, for every two alarm messages in the target data set, a target character distance between the last characters in the target character strings corresponding to the two alarm messages.

[0064] Wherein, the target character distance can be understood as the distance measurement between the last characters in the target character strings corresponding to the two alarm messages. Exemplarily, optionally, the determination of the target character distance between the last characters in the target character strings corresponding to the two alarm messages includes: determining the single character distance between each two character strings from front to back in accordance with the character arrangement order in the target character strings, so as to obtain the target character distance between the last characters in the target character strings corresponding to the two alarm messages.

[0065] The single character distance is related to the character arrangement position of the target character string and the character at the corresponding character arrangement position. Specifically, the single character distance between two characters with the same character arrangement position in the target character string can be determined based on character consistency; the single character distance between two characters with different character arrangement positions in the target character string can be associated with the single character distance associated with the adjacent characters of the characters.

[0066] The character consistency can be understood as whether the characters at the corresponding positions in the two target strings are the same, which is used to measure the similarity of the two target strings at a certain position. For example, if the characters at the same position in the two target strings are the same, the two characters are consistent; if the characters at the same position in the two target strings are different, the two characters are not consistent.

[0067] The single character distance of each arrangement position between the target strings can be determined by recursively determining the single character distance of adjacent positions until the last character is calculated. When determining the string distance, character consistency is the basis for determining the single character distance. Optionally, the single character distance between each two strings is determined from front to back according to the character arrangement order in the target string using the following formula:

[0068]

[0069]

[0070] Among them, C i+1,j+1 is the single character distance between the i+1th character in the target string S and the j+1th character in the target string T; C i,j is the single character distance between the i-th character in the target string S and the j-th character in the target string T; C i+1,j is the single character distance between the i+1th character in the target string S and the jth character in the target string T, C i,j+1 is the single-character distance between the i-th character in the target string S and the j+1-th character in the target string T.

[0071] In this embodiment, character consistency is used to determine whether the characters in the same arrangement position in the two target strings are the same, so as to determine the single character distance. The single character distance can be determined from front to back according to the character arrangement order in the target string. The single character distance between the first characters of the two target strings can be a preset value, for example, can be 0.

[0072] For example, when the characters in the same arrangement position of the two strings are the same, the single character distance of the arrangement position is 0 (indicating consistency); when the characters in the same arrangement position of the two target strings are different, the single character distance of the arrangement position is 1 (indicating inconsistency). When the character arrangement position between the i-th character in the target string S and the j-th character in the target string T is the same, C i,j Add the result of the determined character consistency to determine the next single character distance C i+1,j+1; In the case where the character arrangement positions of the i-th character in the target string S and the j-th character in the target string T are different, the C i,j and its previous character pair C i+1,j and C i,j+1 The size of the single character distance, select the smallest single character distance, and add 1 to get the next single character distance C i+1,j+1 .

[0073] S230: Determine the character string distance between the two pieces of the alarm information according to the target character distance and the lengths of the two target character strings.

[0074] Based on the above scheme, optionally, determining the string distance between the two alarm messages according to the target character distance and the lengths of the two target character strings includes: summing the lengths of the two target character strings to obtain a total character length; and determining the ratio of the target character distance to the total character length as the string distance between the two alarm messages.

[0075] The total character length can be understood as the sum of the lengths of the two target character strings. The length of the target character string can be understood as the total number of characters included in the target character string. The character string distance can be determined based on the ratio of the target character distance to the total character length.

[0076] For example, taking the above target string S and target string T as an example, assuming that the number of characters in the target string S is m, the number of characters in the target string T is n, C i+1,j+1 is the single character distance between the i+1th character in the target string S and the j+1th character in the target string T, then the string distance between the i+1th character in the target string S and the j+1th character in the target string T can be determined as follows:

[0077] L(T,S)=C i+1,j+1 / (m+n);

[0078] Wherein, L(T, S) is the string distance between the target string S and the target string T.

[0079] S240 , hierarchically clustering the alarm information in the target data set according to the character string distance to obtain a hierarchical clustering dendrogram.

[0080] S250: Determine a classification result of the alarm information according to the hierarchical clustering dendrogram and a preset number of classifications.

[0081] The technical solution of the embodiment of the present invention effectively identifies and classifies different alarm information by determining the string distance between alarm information, and ensures the accuracy of the determined character distance through the consistency and position difference of the characters. By calculating the ratio of the single character distance and the total length as the string distance, the complexity is simplified, the processing speed and accuracy are improved, which is conducive to rapid positioning of automated detection, reduces false alarm rate, and improves overall efficiency and response speed.

[0082] Embodiment 3

[0083] Figure 4 The flowchart of a method for classifying alarm information of a substation provided in the third embodiment of the present invention is an optional embodiment of the above embodiment. Figure 4 As shown, the method may specifically include:

[0084] First, multiple alarm information including the substation is obtained, and the target data set is constructed using the obtained multiple alarm information;

[0085] Then, each alarm message is converted into a target character string. The conversion process includes: when the alarm message includes Chinese characters, the Chinese characters are translated into Chinese pinyin, and the Chinese pinyin is translated into uppercase English letters; when the alarm message includes lowercase English letters, the lowercase English letters are translated into uppercase English letters.

[0086] Next, calculate the distance of the target string. This can be done in the following ways:

[0087] For the target string T and the target string S corresponding to the x-th alarm information and the y-th alarm information in the target data set, the number of characters of the target string T and the target string S are calculated and assigned to the variables m and n respectively;

[0088] Construct a matrix C with m+1 rows and n+1 columns to store the single-character distance between two target strings; wherein the data elements of the first row in the matrix C are 0 to n, and the data elements of the first column are 0 to m; that is, the initial value of the first element of the matrix C is 0.

[0089] The other data elements in matrix C are obtained by formula (1):

[0090]

[0091]

[0092] Among them, C i+1,j+1 is the element in the i+1th row and j+1th column of the matrix C; C i,j is the element in the i-th row and j-th column of the matrix C; i+1,jis the element in the i+1th row and jth column of the matrix C, C i,j+1 is the element in the i-th row and j+1-th column of the matrix C; min{C i,j ,C i+1,j ,C i,j+1} represents the operation of finding the element with the smallest value among three elements.

[0093] The number of characters m in the target string T and the number of characters n in the target string S are summed to obtain the total number of characters m+n;

[0094] The ratio of the single character distance to the total number of characters is determined as the string distance between the two pieces of the alarm information, which can be obtained by the following formula:

[0095] L(T,S)=C i+1,j+1 / (m+n).

[0096] Similarly, the values ​​of all elements in the string distance matrix can be obtained.

[0097] Then, hierarchical clustering is performed on the alarm information in the target data set according to the string distance. The two alarm information with the smallest string distance are merged into one cluster, and the string distance matrix is ​​updated according to the merged alarm information until all the alarm information is merged into one cluster.

[0098] Next, a hierarchical clustering dendrogram is determined based on the results of the hierarchical clustering.

[0099] Finally, the character string distance as the classification threshold is determined according to the preset classification number. A straight line parallel to the horizontal axis is drawn in the hierarchical clustering dendrogram, and the ordinate of the straight line is equal to the classification threshold; the intersection of the straight line and the hierarchical clustering dendrogram represents the classification node of the cluster. Each classification node represents a classification category, thereby obtaining the classification result of the alarm information.

[0100] The technical solution of the embodiment of the present invention can effectively identify and classify the alarm information of the substation by converting the alarm information into a target character string of uppercase English letters, calculating the character string distance between the alarm information, and then hierarchically clustering the alarm information according to the character string distance, thereby improving the efficiency and accuracy of alarm information processing, determining the classification threshold according to a preset number of classifications, realizing flexible classification of the alarm information, improving the classification accuracy and classification efficiency of the alarm information, helping to simplify the management and maintenance of the substation, and improving the efficiency of fault detection and preventive maintenance.

[0101] Embodiment 4

[0102] Figure 5 This is a schematic diagram of the structure of a substation alarm information classification device provided by the fourth embodiment of the present invention. Figure 5 As shown, the device includes: an acquisition module 510, a character string distance determination module 520, a hierarchical clustering module 530, and a classification module 540.

[0103] Among them, the acquisition module 510 is used to obtain the target data set, wherein the target data set includes multiple alarm information of the substation; the string distance determination module 520 is used to convert each of the alarm information in the target data set into a target string, and determine the string distance between every two alarm information in the target data set according to the target string; the hierarchical clustering module 530 is used to hierarchically cluster the alarm information in the target data set according to the string distance to obtain a hierarchical clustering tree diagram; the classification module 540 is used to determine the classification result of the alarm information according to the hierarchical clustering tree diagram and a preset number of classifications.

[0104] The technical solution of the embodiment of the present invention first obtains the target data set through the acquisition module 510. Since the target data set includes multiple alarm information of the substation, the alarm information to be classified can be quickly collected in batches to provide a data basis for the subsequent classification processing of the alarm information; then, each of the alarm information in the target data set is converted into a target string through the string distance determination module 520, and different types of alarm information can be uniformly converted into a string format, which is convenient for subsequent processing and analysis, and can significantly improve processing efficiency and accuracy. The string distance between each two alarm information in the target data set is determined according to the target string, and the similarity between the alarm information can be quantified, which helps to identify highly similar events from a large amount of alarm information, thereby classifying and processing potential repeated alarms and realizing accurate analysis of the alarm information; then, The alarm information in the target data set is hierarchically clustered according to the string distance through the hierarchical clustering module 530 to obtain a hierarchical clustering tree diagram. Similar alarm information can be classified, and the correlation between the alarm information can be effectively revealed, which helps to simplify the management of a large amount of alarm information. The visualized hierarchical clustering tree diagram facilitates the understanding and analysis of the alarm information. Finally, the classification result of the alarm information is determined according to the hierarchical clustering tree diagram and the preset number of classifications through the classification module 540. The alarm information can be divided into a preset number of categories, which supports flexible classification of the alarm information and solves the problem of difficult classification and low processing efficiency of alarm information in related technologies. The alarm information can be effectively classified, and the classification accuracy and efficiency of the alarm information can be improved, which helps to simplify the management and maintenance of substations and improve the efficiency of fault detection and preventive maintenance.

[0105] Based on the above device, optionally, a conversion submodule is used to convert each of the alarm messages in the target data set into a target character string by using at least one of the following operations: when the alarm message includes Chinese characters, the Chinese characters are translated into Chinese pinyin, and the Chinese pinyin is translated into uppercase English letters; when the alarm message includes lowercase English letters, the English letters are translated into uppercase English letters.

[0106] On the basis of the above device, optionally, the character string distance determination module 420 includes: a target character distance determination submodule and a character string distance determination submodule.

[0107] Among them, the target character distance determination submodule is used to determine the target character distance between the last characters in the target character strings corresponding to each two alarm messages in the target data set; the character string distance determination submodule is used to determine the character string distance between the two alarm messages based on the target character distance and the lengths of the two target character strings.

[0108] Based on the above device, optionally, the target character distance determination submodule includes: a target character distance determination unit.

[0109] Among them, the target character distance determination unit is used to determine the single character distance between every two character strings from front to back in accordance with the character arrangement order in the target character string, so as to obtain the target character distance between the last characters in the target character strings corresponding to the two alarm messages; wherein the single character distance between two characters with the same character arrangement position in the target character string is determined based on character consistency; the single character distance between two characters with different character arrangement positions in the target character string is associated with the single character distance associated with the adjacent characters of the characters.

[0110] On the basis of the above device, optionally, a single character distance determination subunit is used to determine the single character distance between every two character strings from front to back according to the character arrangement order in the target character string by using the following formula:

[0111]

[0112]

[0113] Among them, C i+1,j+1 is the single character distance between the i+1th character in the target string S and the j+1th character in the target string T; C i,j is the single character distance between the i-th character in the target string S and the j-th character in the target string T; Ci+1,j is the single character distance between the i+1th character in the target string S and the jth character in the target string T, C i,j+1 is the single-character distance between the i-th character in the target string S and the j+1-th character in the target string T.

[0114] Based on the above device, optionally, a character string distance determination unit is used to sum the lengths of the two target character strings to obtain a total character length; and determine the ratio of the target character distance to the total character length as the character string distance between the two alarm messages.

[0115] Based on the above-mentioned device, optionally, the hierarchical clustering dendrogram uses the information identifier of the alarm information as the horizontal axis and the character string distance as the vertical axis; the classification module 540 is specifically used to determine the character string distance as the classification threshold according to the preset number of classifications, and draw a straight line parallel to the horizontal axis of the hierarchical clustering dendrogram at the classification threshold; the classification result of the alarm information is determined according to the intersection of the straight line and the hierarchical clustering dendrogram.

[0116] The alarm information classification device for a substation provided in an embodiment of the present invention can execute the alarm information classification method for a substation provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0117] Embodiment 5

[0118] Figure 6 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0119] like Figure 6As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0120] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0121] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the alarm information classification method of the substation.

[0122] In some embodiments, the alarm information classification method for a substation may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the alarm information classification method for a substation described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the alarm information classification method for a substation in any other appropriate manner (e.g., by means of firmware).

[0123] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0124] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0125] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0126] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0127] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0128] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0129] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0130] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for classifying alarm information of a substation, It is characterized in that include: Acquire a target data set, wherein the target data set includes multiple alarm information of the substation; Convert each of the alarm information in the target data set into a target character string, and determine the character string distance between every two alarm information in the target data set according to the target character string; Performing hierarchical clustering on the alarm information in the target data set according to the string distance to obtain a hierarchical clustering dendrogram; The classification result of the alarm information is determined according to the hierarchical clustering dendrogram and a preset number of classifications.

2. The method according to claim 1, It is characterized in that The step of converting each piece of the alarm information in the target data set into a target character string comprises: For each piece of the alarm information in the target data set, at least one of the following operations is used to convert the alarm information into a target character string: In the case where the alarm information includes Chinese characters, the Chinese characters are translated into Chinese pinyin, and the Chinese pinyin is translated into capital English letters; In the case where the alarm information includes lowercase English letters, the English letters are translated into uppercase English letters.

3. The method according to claim 1, It is characterized in that The step of determining the character string distance between every two pieces of the alarm information in the target data set according to the target character string comprises: For each two pieces of the alarm information in the target data set, determining a target character distance between the last characters in the target character strings corresponding to the two pieces of the alarm information; The character string distance between the two pieces of the alarm information is determined according to the target character distance and the lengths of the two target character strings.

4. The method according to claim 3, It is characterized in that The step of determining the target character distance between the last characters in the target character strings corresponding to the two pieces of the alarm information comprises: The single-character distance between each two character strings is determined from front to back in accordance with the character arrangement order in the target character string to obtain the target character distance between the last characters in the target character strings corresponding to the two alarm messages; wherein the single-character distance between two characters with the same character arrangement position in the target character string is determined based on character consistency; and the single-character distance between two characters with different character arrangement positions in the target character string is associated with the single-character distance associated with the adjacent characters of the characters.

5. The method according to claim 4, It is characterized in that According to the character arrangement order in the target character string, the single character distance between every two character strings is determined from front to back using the following formula: Among them, C i+1,j+1 is the single character distance between the i+1th character in the target string S and the j+1th character in the target string T; C i,j is the single character distance between the i-th character in the target string S and the j-th character in the target string T; C i+1,j is the single character distance between the i+1th character in the target string S and the jth character in the target string T, C i,j+1 is the single-character distance between the i-th character in the target string S and the j+1-th character in the target string T.

6. The method according to claim 3, It is characterized in that The step of determining the character string distance between two pieces of the alarm information according to the target character distance and the lengths of the two target character strings comprises: Sum the lengths of the two target character strings to obtain a total character length; The ratio of the target character distance to the total character length is determined as the character string distance between the two pieces of the alarm information.

7. The method according to claim 1, It is characterized in that The hierarchical clustering dendrogram uses the information identifier of the alarm information as the abscissa and the character string distance as the ordinate; Determining the classification result of the alarm information according to the hierarchical clustering dendrogram and a preset number of classifications includes: Determine the character string distance as a classification threshold according to the preset classification quantity, and draw a straight line parallel to the horizontal axis of the hierarchical clustering dendrogram at the classification threshold; The classification result of the alarm information is determined according to the intersection of the straight line and the hierarchical clustering dendrogram.

8. A substation alarm information classification device, It is characterized in that include: An acquisition module, used for acquiring a target data set, wherein the target data set includes a plurality of alarm information of a substation; A character string distance determination module, used to convert each of the alarm information in the target data set into a target character string, and determine the character string distance between every two alarm information in the target data set according to the target character string; A hierarchical clustering module, used for performing hierarchical clustering on the alarm information in the target data set according to the string distance to obtain a hierarchical clustering dendrogram; The classification module is used to determine the classification result of the alarm information according to the hierarchical clustering dendrogram and a preset number of classifications.

9. An electronic device, It is characterized in that include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor executes the alarm information classification method for a substation according to any one of claims 1 to 7.

10. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the alarm information classification method for a substation as described in any one of claims 1 to 7 when executed.

Images