Method and apparatus for monitoring a list of metrics for a business scenario

Abstract

The present disclosure provides a checking method and device for monitoring the index list of a business scenario, equipment and storage medium, which can be applied to the field of information security technology and the field of financial technology. The method comprises: performing word segmentation processing on each row of data in the business scenario list table to obtain a word set; generating a similarity matrix corresponding to the word set according to the similarity between each two words in the word set; for each row in the word set, calculating the probability value corresponding to each word in each row according to the similarity matrix; obtaining a keyword set according to the probability value corresponding to each word in each row; and matching the keyword set with the index list for monitoring the business scenario according to a preset matching rule to obtain a matching result, thereby achieving the checking of the index list for monitoring the business scenario.

Description

Technical Field

[0001] This disclosure relates to the fields of information security technology and financial technology, and in particular to a method, apparatus, equipment, medium and program product for checking indicator lists for monitoring business scenarios. Background Technology

[0002] With the development of electronic payment and other businesses, business scenarios are becoming increasingly flexible and complex in terms of time, location, operation type, and transaction category, leading to closer integration between business scenario monitoring and business scenarios. However, for large-scale business scenarios with highly complex application functions, a single application may have hundreds or even thousands of subdivided business functions. At the same time, due to differences in naming preferences and description methods for business scenario-related fields among different project teams and applications, it is impossible to quickly obtain relevant information and perform batch checks on monitoring configurations through direct filtering.

[0003] Therefore, how to quickly check the list of metrics used for monitoring business scenarios is a technical problem that needs to be solved in related technologies. Summary of the Invention

[0004] In view of the above problems, this disclosure provides a method, apparatus, device, medium and program product for checking indicator lists for monitoring business scenarios.

[0005] According to the first aspect of this disclosure, a method for checking a list of metrics for monitoring business scenarios is provided, including:

[0006] Each row of data in the business scenario list table is segmented into words to obtain a word set;

[0007] Based on the similarity between every two words in the above word set, generate a similarity matrix corresponding to the above word set;

[0008] For each row in the above word set, the probability value corresponding to each word in each row is calculated based on the above similarity matrix;

[0009] Based on the probability value corresponding to each word in each of the above rows, the keyword set is obtained;

[0010] According to the preset matching rules, the above keyword set is matched with the indicator list used to monitor the business scenarios to obtain the matching results, so as to realize the inspection of the indicator list used to monitor the above business scenarios.

[0011] According to embodiments of this disclosure, the method for checking the indicator list for monitoring business scenarios further includes:

[0012] Obtain business scenario information and metric information for monitoring the above business scenarios;

[0013] Select the first target field from the above business scenario information to obtain the above business scenario list table;

[0014] Select the second target field from the indicator information used to monitor the above business scenarios to obtain a list of indicators used to monitor the above business scenarios.

[0015] According to embodiments of this disclosure, the above-described word segmentation process is performed on each row of data in the business scenario list table to obtain a word set, including:

[0016] Extract the target keywords from the above business scenario list table, and obtain the keyword dictionary table after deduplication;

[0017] Based on the keyword dictionary table above, determine the fixed phrases in the business scenario list table above;

[0018] Based on the above fixed phrases, each row of data in the above business scenario list table is segmented into words to obtain the above segmentation results corresponding to each row of data.

[0019] The word set is obtained by removing duplicates from the word segmentation results corresponding to each row of data.

[0020] According to embodiments of this disclosure, generating a similarity matrix corresponding to the word set based on the similarity between every two words in the word set includes:

[0021] Feature extraction is performed on each word in the above word set to obtain the word vector corresponding to each word;

[0022] Based on the word vectors corresponding to each of the above words, the similarity between every two words in the above word set is calculated;

[0023] Based on the similarity between every two words in the above word set, the above similarity matrix is ​​obtained.

[0024] According to embodiments of this disclosure, for each row of the aforementioned word set, the probability value corresponding to each word in each row is calculated based on the aforementioned similarity matrix, including:

[0025] For each word in each row of the above word set, obtain the target similarity with each word from the above similarity matrix;

[0026] Based on the target similarity to each of the above words, the probability value corresponding to each of the above words is calculated.

[0027] According to embodiments of this disclosure, the aforementioned keyword set includes a first keyword set, a second keyword set, and a third keyword set. The keyword set is obtained based on the probability value corresponding to each word in each row, and includes:

[0028] For each row in the above word set, sort the probability values ​​of each word in each row in descending order to obtain a list of keyword arrangements;

[0029] Based on the above keyword list, select the word with the highest probability value in each row to obtain the first keyword set.

[0030] Based on the above keyword list, select the word with the second highest probability value in each row to obtain the second keyword set.

[0031] Based on the keyword list above, select the third word in each row with the highest probability value in descending order to obtain the third keyword set.

[0032] According to embodiments of this disclosure, the keyword set is matched with a list of indicators used to monitor business scenarios according to preset matching rules to obtain matching results, thereby enabling the inspection of the aforementioned business scenarios, including:

[0033] Based on the aforementioned first keyword set, the first-level template list is obtained;

[0034] The words in the first keyword set and the second keyword set are combined to obtain the first list in the second-level template list;

[0035] The words in the first keyword set and the third keyword set are combined to obtain the second list in the second-level template list;

[0036] The words in the first keyword set, the second keyword set, and the third keyword set are combined to obtain the third-level template list;

[0037] Based on the first-level template list, the second-level template list, and the third-level template list, a list of indicator templates for monitoring the above business scenarios is obtained.

[0038] The above-mentioned indicator template list used to monitor the above-mentioned business scenarios is matched with the above-mentioned indicator list to obtain the above-mentioned matching results.

[0039] According to embodiments of this disclosure, the method for checking the indicator list for monitoring business scenarios further includes:

[0040] If the above matching results indicate that there is data in the above indicator template list that does not match the above indicator list, the above indicator list used to monitor the above business scenario will be checked and supplemented according to the above matching results.

[0041] The second aspect of this disclosure provides an apparatus for checking a list of indicators for monitoring business scenarios, comprising: a word segmentation module, a generation module, a calculation module, an acquisition module, and a matching module. The word segmentation module performs word segmentation on each row of data in the business scenario list table to obtain a word set. The generation module generates a similarity matrix corresponding to the word set based on the similarity between any two words in the word set. The calculation module calculates the probability value corresponding to each word in each row of the word set based on the similarity matrix. The acquisition module obtains a keyword set based on the probability value corresponding to each word in each row. The matching module matches the keyword set with the list of indicators for monitoring business scenarios according to preset matching rules to obtain a matching result, thereby enabling the checking of the list of indicators for monitoring the aforementioned business scenarios.

[0042] A third aspect of this disclosure provides an electronic device comprising: one or more processors; and a memory for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors perform the methods described above.

[0043] A fourth aspect of this disclosure also provides a computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, cause the processor to perform the methods described above.

[0044] The fifth aspect of this disclosure also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0045] According to the inspection method, device, equipment, medium, and program products for monitoring business scenarios provided in this disclosure, each row of data in the business scenario list table is segmented to obtain a word set. Based on the similarity between every two words in the word set, a similarity matrix corresponding to the word set is generated. Thus, for each row in the word set, the probability value corresponding to each word in each row can be calculated based on the similarity matrix. Based on the probability value corresponding to each word in each row, a keyword set is obtained. Finally, the keyword set can be matched with the indicator list for monitoring business scenarios according to preset matching rules to obtain matching results, thereby realizing the inspection of the indicator list for monitoring business scenarios. Generating a keyword set based on the business scenario list table can solve the problem of difficulty in batch matching due to different input habits, and can improve the comprehensiveness and effectiveness of business scenario monitoring. Attached Figure Description

[0046] The foregoing contents, as well as other objects, features, and advantages of this disclosure, will become clearer from the following description of embodiments with reference to the accompanying drawings, in which:

[0047] Figure 1 The illustration schematically depicts an application scenario diagram of a method for checking a list of indicators for monitoring business scenarios according to an embodiment of the present disclosure;

[0048] Figure 2 A flowchart illustrating a method for checking a list of metrics for monitoring business scenarios according to an embodiment of this disclosure is shown schematically.

[0049] Figure 3 A flowchart illustrating the process of obtaining a vocabulary set according to an embodiment of the present disclosure is shown schematically;

[0050] Figure 4 A flowchart illustrating the process of obtaining a similarity matrix according to an embodiment of the present disclosure is shown schematically;

[0051] Figure 5 A flowchart illustrating the process of obtaining the probability value for each word according to an embodiment of the present disclosure is shown schematically.

[0052] Figure 6 A flowchart illustrating the process of obtaining matching results according to an embodiment of the present disclosure is shown schematically;

[0053] Figure 7 The illustration shows a schematic diagram of an inspection system for a list of indicators for monitoring business scenarios according to an embodiment of the present disclosure;

[0054] Figure 8 This schematically illustrates a structural block diagram of an inspection apparatus for monitoring a list of metrics in a business scenario according to an embodiment of the present disclosure; and

[0055] Figure 9 A block diagram of an electronic device suitable for implementing a method for checking a list of indicators for monitoring business scenarios, according to an embodiment of the present disclosure, is illustrated. Detailed Implementation

[0056] The embodiments of the present disclosure will now be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the disclosure. In the following detailed description, numerous specific details are set forth to provide a thorough understanding of the embodiments of the present disclosure for ease of explanation. However, it will be apparent that one or more embodiments may be practiced without these specific details. Furthermore, descriptions of well-known structures and techniques are omitted in the following description to avoid unnecessarily obscuring the concepts of the present disclosure.

[0057] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit this disclosure. The terms “comprising,” “including,” etc., as used herein indicate the presence of the stated features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0058] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein are to be interpreted in a manner consistent with the context of this specification, and not in an idealized or overly rigid way.

[0059] When using expressions such as "at least one of A, B, and C", they should generally be interpreted in accordance with the meaning that is commonly understood by a person skilled in the art (e.g., "a system having at least one of A, B, and C" should include, but is not limited to, a system having A alone, a system having B alone, a system having C alone, a system having A and B, a system having A and C, a system having B and C, and / or a system having A, B, and C, etc.).

[0060] In the technical solutions disclosed herein, the collection, storage, use, processing, transmission, provision, disclosure, and application of data (including but not limited to user personal information) comply with the provisions of relevant laws and regulations, necessary confidentiality measures have been taken, and they do not violate public order and good morals.

[0061] During the implementation of this disclosure, it was discovered that the business scenarios and application functions of large commercial banks are extremely complex. A single application may have hundreds or even thousands of subdivided business functions. Currently, monitoring configurations for these business scenarios are primarily checked manually, or reactively after problems occur. Furthermore, due to differences in naming preferences and description methods among project teams and applications regarding business scenario-related fields, it is impossible to quickly obtain relevant information and perform batch checks on monitoring configurations through direct filtering. This leads to issues such as incomplete monitoring coverage and unreasonable thresholds, hindering the ability to quickly respond to customer-impacting events. Therefore, how to achieve rapid checking of the indicator list used for monitoring business scenarios is a technical problem that needs to be solved in related technologies.

[0062] To this end, embodiments of this disclosure provide a method for checking a list of indicators for monitoring business scenarios, including: performing word segmentation on each row of data in the business scenario list table to obtain a word set; generating a similarity matrix corresponding to the word set based on the similarity between every two words in the word set; calculating the probability value corresponding to each word in each row of the word set based on the similarity matrix; obtaining a keyword set based on the probability value corresponding to each word in each row; and matching the keyword set with the list of indicators for monitoring business scenarios according to a preset matching rule to obtain a matching result, thereby realizing the checking of the list of indicators for monitoring business scenarios.

[0063] Figure 1 The illustration schematically depicts an application scenario diagram of a method for checking a list of indicators for monitoring business scenarios according to an embodiment of the present disclosure.

[0064] like Figure 1 As shown, application scenario 100 according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 serves as a medium for providing a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include various connection types, such as wired or wireless communication links, or fiber optic cables, etc.

[0065] Users can interact with server 105 via network 104 using at least one of the first terminal device 101, second terminal device 102, and third terminal device 103 to receive or send messages, etc. Various communication client applications can be installed on the first terminal device 101, second terminal device 102, and third terminal device 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social media platform software, etc. (for example only).

[0066] The first terminal device 101, the second terminal device 102, and the third terminal device 103 can be various electronic devices with displays and support web browsing, including but not limited to smartphones, tablets, laptops, and desktop computers.

[0067] Server 105 can be a server that provides various services, such as a backend management server that supports websites browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103 (this is just an example). The backend management server can analyze and process data such as received user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal devices.

[0068] For example, server 105 can perform word segmentation on each row of data in the business scenario list table to obtain a word set; based on the similarity between every two words in the word set, a similarity matrix corresponding to the word set can be generated; and for each row in the word set, based on the similarity matrix, the probability value corresponding to each word in each row can be calculated, so as to obtain a keyword word set based on the probability value corresponding to each word in each row. Finally, according to the preset matching rules, the keyword word set is matched with the indicator list used to monitor the business scenario to obtain the matching result, so as to realize the inspection of the indicator list used to monitor the business scenario.

[0069] It should be noted that the method for checking the indicator list for monitoring business scenarios provided in this embodiment can generally be executed by server 105. Correspondingly, the device for checking the indicator list for monitoring business scenarios provided in this embodiment can generally be located in server 105. The method for checking the indicator list for monitoring business scenarios provided in this embodiment can also be executed by a server or server cluster that is different from server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or server 105. Correspondingly, the device for checking the indicator list for monitoring business scenarios provided in this embodiment can also be located in a server or server cluster that is different from server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or server 105.

[0070] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0071] The following will be based on Figure 1 The described scene, through Figures 2-7 The present disclosure provides a detailed description of the method for checking the indicator list for monitoring business scenarios according to embodiments of the present disclosure.

[0072] Figure 2 A flowchart illustrating a method for checking a list of metrics for monitoring business scenarios according to an embodiment of this disclosure is shown.

[0073] like Figure 2 As shown, the method 200 includes operations S210 to S250.

[0074] In operation S210, each row of data in the business scenario list table is segmented into words to obtain a word set.

[0075] According to embodiments of this disclosure, the Jieba word segmentation method can be used to segment each row of data in the business scenario list table to obtain a word set corresponding to the business scenario list table.

[0076] In operation S220, a similarity matrix corresponding to the word set is generated based on the similarity between every two words in the word set.

[0077] According to embodiments of this disclosure, word vectors can be trained for each word in the word set using the Ship-gram model in Word2Vec (Word to Vector, a model for generating word vectors), resulting in word vectors corresponding to each word. The similarity between each word vector, i.e., the similarity between every two words, can then generate a similarity matrix corresponding to the word set.

[0078] In operation S230, for each row in the word set, the probability value corresponding to each word in each row is calculated based on the similarity matrix.

[0079] According to embodiments of this disclosure, the probability value corresponding to each word in each line can be calculated using the TextRank (a text ranking algorithm) model based on the similarity matrix.

[0080] In operation S240, the keyword set is obtained based on the probability value corresponding to each word in each row.

[0081] According to embodiments of this disclosure, a keyword set can be obtained based on the probability value of each word in each row. The word with the highest probability value in each row is extracted and deduplicated to obtain a first keyword set; the word with the second highest probability value in each row is extracted and deduplicated to obtain a second keyword set; and the word with the third highest probability value in each row is extracted and deduplicated to obtain a third keyword set.

[0082] When operating the S250, the keyword set is matched with the indicator list used for monitoring business scenarios according to the preset matching rules to obtain the matching results, so as to realize the inspection of the indicator list used for monitoring business scenarios.

[0083] According to embodiments of this disclosure, the keyword set may include a first keyword set, a second keyword set, and a third keyword set. A preset matching rule can represent combining words from the first, second, and third keyword sets according to a preset rule, and then matching them respectively with a list of indicators used for monitoring business scenarios.

[0084] According to embodiments of this disclosure, each row of data in the business scenario list table is segmented to obtain a word set. Based on the similarity between every two words in the word set, a similarity matrix corresponding to the word set is generated. Thus, for each row in the word set, the probability value corresponding to each word in each row can be calculated based on the similarity matrix. Based on the probability value corresponding to each word in each row, a keyword set is obtained. Finally, the keyword set can be matched with the indicator list used to monitor business scenarios according to preset matching rules to obtain matching results, thereby enabling the inspection of the indicator list used to monitor business scenarios. Generating a keyword set based on the business scenario list table can solve the problem of difficulty in batch matching due to different input habits, and can improve the comprehensiveness and effectiveness of business scenario monitoring.

[0085] According to embodiments of this disclosure, the above-mentioned method for checking the indicator list for monitoring business scenarios further includes: obtaining business scenario information and indicator information for monitoring business scenarios; selecting a first target field from the business scenario information to obtain a business scenario list table; and selecting a second target field from the indicator information for monitoring business scenarios to obtain an indicator list for monitoring business scenarios.

[0086] According to embodiments of this disclosure, business scenario information registered in the asset management system and business scenario monitoring indicator information in the monitoring system can be collected and uploaded. The indicator information used to monitor business scenarios can represent the business scenario monitoring indicator information in the monitoring system.

[0087] According to embodiments of this disclosure, the first target field may include a business scenario ID, a business scenario name, a business scenario description, a business domain, and an entry application. The second target field may include a metric name, a metric description, and a threshold.

[0088] According to embodiments of this disclosure, a first target field can be selected from business scenario information to obtain a business scenario list table. Each row in the business scenario list table may include a business scenario ID and the business scenario name, business scenario description, business domain, and entry application corresponding to the business scenario ID. A second target field can be selected from indicator information used to monitor business scenarios to obtain an indicator list used to monitor business scenarios.

[0089] According to the embodiments of this disclosure, the first target field and the second target field in the business scenario information and the indicator information used to monitor the business scenario are retained respectively, thereby realizing the preprocessing of the business scenario information and the indicator information used to monitor the business scenario, wherein the first target field and the second target field can be used for subsequent analysis and processing.

[0090] Figure 3 A flowchart illustrating the process of obtaining a vocabulary set according to an embodiment of this disclosure is shown schematically.

[0091] like Figure 3 As shown, the method 300 includes operations S310 to S340.

[0092] In operation S310, target keywords are extracted from the business scenario list table, and after deduplication, a keyword dictionary table is obtained.

[0093] According to embodiments of this disclosure, in order to improve the accuracy of keyword extraction for business scenarios, the target keywords in the business scenario list table need to be extracted first, and then the obtained target keywords are deduplicated to obtain a keyword dictionary table.

[0094] According to embodiments of this disclosure, target keywords can characterize business domain fields in a business scenario list table, where the business domain fields are standardized. Based on the business domain fields in the business scenario list table, duplicate keywords are deduplicated to obtain standard descriptive keywords for the business domain, which can be used for subsequent analysis.

[0095] According to embodiments of this disclosure, the obtained standard descriptive keywords can be input into a dictionary table to obtain a keyword dictionary table.

[0096] When operating S320, determine the fixed phrases in the business scenario list table based on the keyword dictionary table.

[0097] According to embodiments of this disclosure, each keyword in the keyword dictionary can be regarded as a fixed phrase, thereby determining the fixed phrases in the business scenario list.

[0098] When operating S330, based on fixed phrases, each row of data in the business scenario list table is segmented into words to obtain the segmentation result corresponding to each row of data.

[0099] According to the embodiments of this disclosure, the keyword dictionary table is loaded as a custom dictionary for Jieba word segmentation. The business scenario list table is used as a dataset, and each row of data in the business scenario list table is segmented to obtain the segmentation result.

[0100] According to embodiments of this disclosure, the business scenario name and business scenario description fields can be extracted from each row of data in the business scenario list table, and word segmentation can be performed on the business scenario name and business scenario description. During the word segmentation process for the business scenario name and business scenario description fields, fixed phrases within these fields are not segmented; the rest are segmented normally. That is, phrases appearing in the business scenario name and business scenario description fields that are present in the keyword dictionary table are not segmented. For example, segmenting "use keyword dictionary as a custom dictionary load" normally yields "use / keyword / dictionary / as / custom / dictionary / load"; if the keyword dictionary table includes both a keyword dictionary and a custom dictionary (i.e., the fixed phrase includes both), then "use / keyword dictionary / as / custom dictionary / load" can be obtained.

[0101] According to embodiments of this disclosure, the business scenario name and business scenario description fields in each row of data in the business scenario list table can be segmented. The segmentation results for each row can include the business scenario ID, business domain, entry application, and the segmentation results of the business scenario name and business scenario description fields.

[0102] In operation S340, the word set is obtained by deduplicating the word segmentation results corresponding to each row of data.

[0103] According to embodiments of this disclosure, duplicate words can be removed from the word segmentation results corresponding to each line of data to obtain a word set.

[0104] According to embodiments of this disclosure, based on a keyword dictionary table, each row of data in the business scenario list table is segmented to obtain segmentation results. After deduplication of the segmentation results corresponding to each row of data, a word set can be obtained, which can then be used for subsequent analysis and processing.

[0105] Figure 4 A flowchart illustrating the process of obtaining a similarity matrix according to an embodiment of the present disclosure is shown.

[0106] like Figure 4 As shown, the method 400 includes operations S410 to S430.

[0107] In operation S410, features are extracted from each word in the word set to obtain the word vector corresponding to each word.

[0108] According to embodiments of this disclosure, a word set can be obtained by performing global deduplication on the word segmentation results corresponding to each row of data in the business scenario list table.

[0109] According to embodiments of this disclosure, word vectors can be trained for each word in the word set using the Ship-gram model in Word2Vec, resulting in word vectors corresponding to each word, and the similarity between word vectors can be calculated.

[0110] According to embodiments of this disclosure, the logarithm of the objective function of the Ship-gram model in Word2Vec can be expressed as the following formula (1).

[0111] L=∑ ω∈T log p(Context(ω)|ω) (1)

[0112] Where T can represent a word set, ω can represent a word in word set T, Context(ω) can represent the context set of word ω, and p(Context(ω)|ω) can represent the probability value of word ω from the root node to the leaf node.

[0113] According to embodiments of this disclosure, features can be extracted from each word in the word set to obtain a word vector corresponding to each word.

[0114] In operation S420, the similarity between every two words in the word set is calculated based on the word vector corresponding to each word.

[0115] According to embodiments of this disclosure, the similarity between every two words in every two word sets, i.e., the similarity between every two word vectors, can be calculated based on the obtained word vectors corresponding to each word.

[0116] According to embodiments of this disclosure, the similarity calculation formula can be expressed as the following formula (2).

[0117]

[0118] Among them, e i It can represent the i-th word in the word set, e j It can represent the i-th word in the word set.

[0119] cosθ (i,j () can represent word vectors and The angle between them and Word vectors can be represented separately. and The corresponding module.

[0120] In operation S430, a similarity matrix is ​​obtained based on the similarity between every two words in the word set.

[0121] According to the embodiments of this disclosure, the similarity between every two words in the word set can be obtained according to the above formula (2), and a similarity matrix can be obtained based on the similarity between every two words in the word set.

[0122] According to embodiments of this disclosure, the similarity matrix can be expressed as the following formula (3).

[0123]

[0124] Where t can represent the number of words in the vocabulary set, ω 11 It can represent the similarity between the first words in a word set, ω 1t ω can represent the similarity between the first word and the t-th word in the vocabulary set. t1 ω can represent the similarity between the t-th word and the first word in the word set. tt It can represent the similarity between the t-th word and the t-th word in the word set.

[0125] According to embodiments of this disclosure, for example, if the word set may include 10 words, the generated similarity matrix can be represented as a 10×10 matrix.

[0126] According to embodiments of this disclosure, word vectors can be trained for each word in the word set using the Ship-gram model in Word2Vec, and the similarity between word vectors can be calculated to determine the degree of association between words.

[0127] Figure 5 A flowchart illustrating the process of obtaining the probability value for each word according to an embodiment of the present disclosure is shown.

[0128] like Figure 5 As shown, the method 500 includes operations S510 and S520.

[0129] In operation S510, for each word in each row of the word set, the target similarity with each word is obtained from the similarity matrix.

[0130] According to embodiments of this disclosure, the TextRank (a text ranking algorithm) model can be used to construct the weight relationship between adjacent words using a sliding window, and combined with the obtained similarity matrix, a probability transition can be constructed, which is the probability value of a word being a keyword in the corresponding row.

[0131] According to embodiments of this disclosure, for each word in each row of the word set, the target similarity corresponding to each word can be obtained from the similarity matrix.

[0132] In operation S520, the probability value corresponding to each word is calculated based on the target similarity to each word.

[0133] According to embodiments of this disclosure, for example, the business scenario name and business scenario description corresponding to each business scenario ID constitute a long sentence. After word segmentation, the average number of words is about 30, and the sliding window is set to 6.

[0134] According to an embodiment of this disclosure, the iterative calculation formula for TextRank can be expressed as the following formula (4).

[0135]

[0136] Where d can represent the damping factor (usually taken as 0.85), TR(W) i ) can represent word node W i The TextRank value, i.e., word W, is obtained through calculation. i ω represents the probability value of a keyword. The summation formula can represent the contribution of each adjacent word node to the current word node. ij It can represent the word W obtained from the similarity matrix (probability transition matrix). i and word W j Similarity between them, In(W i ) can represent word node W i in-degree (pointing to word node W) i The set of (W), Out(W) j ) can be represented as word node W j Out-degree (word node W) j A set of pointers to nodes), TR(W) j ) can represent the word W obtained from the previous iteration. j It is the probability value of the keyword, ω jk The term W can be used to characterize j and word W k Similarity between them.

[0137] According to embodiments of this disclosure, target similarity may include word W. i and word W j Similarity between and word W j and word W k Similarity between them. Target similarity can characterize the similarity with word W. i This represents the similarity between out-degree and in-degree terms. TR(W) j In the absence of information, initial values ​​can be set manually.

[0138] According to the embodiments of this disclosure, the probability value of each word in the word set being a keyword in the corresponding row can be calculated using the above formula (4).

[0139] According to embodiments of this disclosure, the keyword set may include a first keyword set, a second keyword set, and a third keyword set. The keyword set is obtained based on the probability value corresponding to each word in each row, including: for each row in the keyword set, arranging the probability values ​​corresponding to each word in each row in descending order to obtain a keyword list; selecting the word with the highest probability value in each row from the keyword list to obtain the first keyword set; selecting the word with the second highest probability value in each row from the keyword list to obtain the second keyword set; and selecting the word with the third highest probability value in each row from the keyword list to obtain the third keyword set.

[0140] According to an embodiment of this disclosure, for each row in the word set, the probability values ​​corresponding to each word obtained according to the above formula (4) are arranged in descending order to obtain a keyword arrangement list.

[0141] According to embodiments of this disclosure, keyword hierarchical analysis can be performed based on a keyword ranking list. The first keyword can be defined as the word with the highest probability value in each row; therefore, the word with the highest probability value in each row is selected to obtain the first keyword set. The second keyword can be defined as the word with the second highest probability value in each row in descending order; therefore, the word with the second highest probability value in each row in descending order is selected to obtain the second keyword set. The third keyword can be defined as the word with the third highest probability value in each row in descending order; therefore, the word with the third highest probability value in each row in descending order is selected to obtain the third keyword set.

[0142] According to embodiments of this disclosure, a first keyword set, a second keyword set, and a third keyword set can be obtained based on the probability value corresponding to each word in the keyword ranking list, so as to be used for obtaining a list of indicator templates for subsequent monitoring business scenarios.

[0143] Figure 6 A flowchart illustrating the process of obtaining matching results according to an embodiment of the present disclosure is shown.

[0144] like Figure 6 As shown, the method 600 includes operations S610 to S660.

[0145] When operating S610, the first-level template list is obtained based on the first keyword set.

[0146] According to an embodiment of this disclosure, the first-level business monitoring indicators may contain only the first keyword, and a first-level template list can be obtained based on each first keyword in the first keyword set.

[0147] In operation S620, the words in the first keyword set and the second keyword set are combined to obtain the first list in the second-level template list.

[0148] According to the embodiments of this disclosure, the second-layer business monitoring indicators can simultaneously include a first keyword and a second keyword. Therefore, the first keyword in the first keyword set and the second keyword in the second keyword set can be combined to obtain the first list in the second-layer template list.

[0149] In operation S630, the words in the first keyword set and the third keyword set are combined to obtain the second list in the second-level template list.

[0150] According to the embodiments of this disclosure, the second-level business monitoring indicators may also include both a first keyword and a third keyword. In this case, the first keyword in the first keyword set and the third keyword in the third keyword set can be combined to obtain the second list in the second-level template list.

[0151] In operation S640, the words in the first keyword set, the second keyword set, and the third keyword set are combined to obtain the third-level template list.

[0152] According to the embodiments of this disclosure, the third-layer business monitoring indicators can simultaneously include a first keyword, a second keyword, and a third keyword (regardless of order). Then, the first keyword in the first keyword set, the second keyword in the second keyword set, and the third keyword in the third keyword set can be combined to obtain the third-layer template list.

[0153] When operating S650, a list of indicator templates for monitoring business scenarios is obtained based on the first-level template list, the second-level template list, and the third-level template list.

[0154] According to embodiments of this disclosure, the indicator template list for monitoring business scenarios may include a first-level template list, a second-level template list, and a third-level template list.

[0155] When operating S660, the list of indicator templates used to monitor business scenarios is matched with the indicator list to obtain the matching results.

[0156] According to embodiments of this disclosure, a list of indicator templates for monitoring business scenarios can be matched with an indicator list to obtain a matching result. The indicator templates for monitoring business scenarios are matched with the indicator name and indicator description fields in the indicator list for monitoring business scenarios to the first, second, and third-level business monitoring indicators, respectively.

[0157] According to embodiments of this disclosure, the matching relationship table can be as shown in Table 1.

[0158] Table 1

[0159]

[0160] According to embodiments of this disclosure, as shown in Table 1, for the first-level business monitoring indicators, the indicator list used for monitoring business scenarios can be matched with the first-level target list in the indicator template list used for monitoring business scenarios, i.e., only the first keyword is matched; for the second-level business monitoring indicators, the indicator list used for monitoring business scenarios can be matched with the second-level target list in the indicator template list used for monitoring business scenarios, i.e., both the first keyword and the third keyword or the first keyword and the second keyword are matched simultaneously; for the third-level business monitoring indicators, the indicator list used for monitoring business scenarios can be matched with the third-level target list in the indicator template list used for monitoring business scenarios, i.e., the first keyword, the second keyword, and the third keyword are matched simultaneously.

[0161] According to embodiments of this disclosure, a list of indicator templates for monitoring business scenarios can be obtained based on a first set of keywords, a second set of keywords, and a third set of keywords. This list can then be matched with the list of indicators for monitoring business scenarios to obtain a matching result, thereby enabling the inspection of the list of indicators for monitoring the business scenarios.

[0162] According to embodiments of this disclosure, the above-mentioned business scenario inspection method further includes: when there is data in the matching result characterization indicator template list that does not match the indicator list, the indicator list used for monitoring business scenarios is checked and supplemented according to the matching result.

[0163] According to embodiments of this disclosure, for data in the indicator list used for monitoring business scenarios that cannot be matched in the indicator template list used for monitoring business scenarios, matching results can be output for operation and maintenance personnel to verify and supplement.

[0164] Figure 7 The illustration shows a schematic diagram of an inspection system for a list of indicators for monitoring business scenarios according to an embodiment of the present disclosure.

[0165] like Figure 7 As shown, the inspection system 700 for monitoring the indicator list of business scenarios may include a data acquisition module 710, a data analysis module 720, and an inspection module 730.

[0166] According to embodiments of this disclosure, the main function of the data acquisition module 710 is to collect and analyze various types of data required by the asset management system and monitoring system, while performing data preprocessing. Specifically, the data acquisition unit in the data acquisition module 710 can be used to acquire business scenario information and indicator information for monitoring business scenarios; the data preprocessing unit in the data acquisition module 710 can be used to select a first target field from the business scenario information to obtain a business scenario list; and to select a second target field from the indicator information for monitoring business scenarios to obtain an indicator list for monitoring business scenarios; the business domain keyword cleaning unit in the data acquisition module 710 can be used to extract target keywords from the business scenario list and remove duplicates to obtain standard descriptive keywords for the business domain.

[0167] According to embodiments of this disclosure, the main function of the data analysis module 720 is to perform word segmentation on the input data, conduct word vector training and keyword analysis, and perform keyword hierarchical analysis. Specifically, the data preprocessing unit in the data analysis module 720 can be used to perform the above-mentioned operation S210 for word segmentation of the input data; the word vector analysis unit in the data analysis module 720 can be used to perform the above-mentioned operation S220 for word vector training; the keyword calculation unit in the data analysis module 720 can be used to perform the above-mentioned operation S230 for keyword analysis; and the keyword hierarchical unit in the data analysis module 720 can be used to perform the above-mentioned operation S240 for keyword hierarchical analysis.

[0168] According to embodiments of this disclosure, the inspection module 730 can be used to perform the above-described operation S250. The indicator template list generation unit for monitoring business scenarios in the inspection module 730 can be used to perform the above-described operations S610 to S650; the inspection analysis unit in the inspection module 730 can be used to perform the above-described operation S660.

[0169] According to embodiments of this disclosure, the present invention is applicable to all systems and can be dynamically adjusted according to inspection needs, without special requirements on system type or version. It can automate keyword analysis and generate a list of indicators for monitoring business scenarios, solving the problem of difficulty in batch matching business scenarios due to different input habits of developers in various business systems, thus improving the comprehensiveness and effectiveness of business scenario monitoring.

[0170] Based on the above-mentioned business scenario inspection method, this disclosure also provides an inspection device for a list of indicators for monitoring business scenarios. The following will combine... Figure 8 The device is described in detail.

[0171] Figure 8The diagram illustrates a structural block diagram of an inspection apparatus for monitoring a list of indicators in a business scenario, according to an embodiment of the present disclosure.

[0172] like Figure 8 As shown, the inspection device 800 for monitoring the indicator list of business scenarios in this embodiment includes a word segmentation module 810, a generation module 820, a calculation module 830, an acquisition module 840, and a matching module 850.

[0173] The word segmentation module 810 is used to segment each row of data in the business scenario list table to obtain a word set. In one embodiment, the word segmentation module 810 can be used to perform the operation S210 described above, which will not be repeated here.

[0174] The generation module 820 is used to generate a similarity matrix corresponding to the word set based on the similarity between every two words in the word set. In one embodiment, the generation module 820 can be used to perform the operation S220 described above, which will not be repeated here.

[0175] The calculation module 830 is used to calculate the probability value corresponding to each word in each row of the word set based on the similarity matrix. In one embodiment, the calculation module 830 can be used to perform the operation S230 described above, which will not be repeated here.

[0176] The obtaining module 840 is used to obtain a keyword set based on the probability value corresponding to each word in each line. In one embodiment, the obtaining module 840 can be used to perform the operation S240 described above, which will not be repeated here.

[0177] The matching module 850 is used to match the keyword set with the indicator list used for monitoring business scenarios according to preset matching rules, and obtain the matching result to realize the inspection of the indicator list used for monitoring business scenarios. In one embodiment, the matching module 850 can be used to perform the operation S250 described above, which will not be repeated here.

[0178] According to embodiments of this disclosure, the above-mentioned inspection device 800 for monitoring the indicator list of business scenarios further includes an acquisition module, a first selection module, and a second selection module.

[0179] The acquisition module is used to acquire business scenario information and metric information for monitoring business scenarios.

[0180] The first selection module is used to select the first target field from the business scenario information to obtain the business scenario list table.

[0181] The second selection module is used to select a second target field from the indicator information used for monitoring business scenarios, and obtain a list of indicators used for monitoring business scenarios.

[0182] According to embodiments of this disclosure, the word segmentation module 810 includes an extraction unit, a determination unit, a first acquisition unit, and a second acquisition unit.

[0183] The extraction unit is used to extract target keywords from the business scenario list table and obtain a keyword dictionary table after deduplication.

[0184] The "determine unit" is used to determine fixed phrases in the business scenario list table based on the keyword dictionary table.

[0185] The first obtaining unit is used to perform word segmentation on each row of data in the business scenario list table based on fixed word groups, and obtain the word segmentation result corresponding to each row of data.

[0186] The second obtaining unit is used to obtain a word set by deduplicating the word segmentation results corresponding to each row of data.

[0187] According to embodiments of this disclosure, the generation module 820 includes a third obtaining unit, a first calculation unit, and a fourth obtaining unit.

[0188] The third acquisition unit is used to extract features from each word in the word set to obtain the word vector corresponding to each word.

[0189] The first calculation unit is used to calculate the similarity between every two words in the word set based on the word vector corresponding to each word.

[0190] The fourth unit is used to obtain a similarity matrix based on the similarity between every two words in the word set.

[0191] According to an embodiment of this disclosure, the calculation module 830 includes an acquisition unit and a second calculation unit.

[0192] The acquisition unit is used to obtain the target similarity with each word in each row of the word set from the similarity matrix.

[0193] The second calculation unit is used to calculate the probability value corresponding to each word based on the target similarity to each word.

[0194] According to embodiments of this disclosure, the obtaining module 840 includes a fifth obtaining unit, a first selecting unit, a second selecting unit, and a third selecting unit.

[0195] The fifth unit is used to sort the probability values ​​of each word in each row of the word set in descending order to obtain a list of keyword rankings.

[0196] The first selection unit is used to select the word with the highest probability value in each row of the keyword list to obtain the first keyword set.

[0197] The second selection unit is used to select the word with the second highest probability value in each row of the keyword list, in descending order, to obtain the second keyword set.

[0198] The third selection unit is used to select the third word in each row with the third probability value in descending order based on the keyword list, thus obtaining the third keyword set.

[0199] According to embodiments of this disclosure, the matching module 850 includes a sixth obtaining unit, a first combining unit, a second combining unit, a third combining unit, a seventh obtaining unit, and a matching unit.

[0200] The sixth obtaining unit is used to obtain the first-level template list based on the first keyword set.

[0201] The first combination unit is used to combine words from the first keyword set and the second keyword set to obtain the first list in the second-level template list.

[0202] The second combination unit is used to combine words from the first keyword set and the third keyword set to obtain the second list in the second-level template list.

[0203] The third combination unit is used to combine words from the first keyword set, the second keyword set, and the third keyword set to obtain a third-level template list.

[0204] The seventh obtaining unit is used to obtain a list of indicator templates for monitoring business scenarios based on the first-level template list, the second-level template list, and the third-level template list.

[0205] The matching unit is used to match the list of indicator templates used for monitoring business scenarios with the indicator list to obtain the matching results.

[0206] According to embodiments of this disclosure, the above-mentioned inspection device 800 for monitoring the indicator list of business scenarios further includes a verification and supplementation unit.

[0207] The verification and supplementation unit is used to verify and supplement the indicator list used for monitoring business scenarios based on the matching results when there is data in the indicator template list that does not match the indicator list.

[0208] According to embodiments of this disclosure, any multiple modules among the word segmentation module 810, generation module 820, calculation module 830, acquisition module 840, and matching module 850 can be combined into one module, or any one of these modules can be split into multiple modules. Alternatively, at least some of the functions of one or more of these modules can be combined with at least some of the functions of other modules and implemented in one module. According to embodiments of this disclosure, at least one of the word segmentation module 810, generation module 820, calculation module 830, acquisition module 840, and matching module 850 can be at least partially implemented as hardware circuitry, such as a field-programmable gate array (FPGA), a programmable logic array (PLA), a system-on-a-chip, a system-on-a-substrate, a system-on-package, an application-specific integrated circuit (ASIC), or implemented in hardware or firmware by any other reasonable means of integrating or packaging the circuitry, or implemented in software, hardware, or firmware, or in any suitable combination of any of these three implementation methods. Alternatively, at least one of the word segmentation module 810, generation module 820, calculation module 830, acquisition module 840 and matching module 850 may be at least partially implemented as a computer program module, which can perform corresponding functions when the computer program module is run.

[0209] Figure 9 A block diagram of an electronic device suitable for implementing a method for checking a list of indicators for monitoring business scenarios, according to an embodiment of the present disclosure, is illustrated.

[0210] like Figure 9 As shown, an electronic device 900 according to an embodiment of the present disclosure includes a processor 901, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 902 or a program loaded from a storage portion 908 into a random access memory (RAM) 903. The processor 901 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or an associated chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 901 may also include onboard memory for caching purposes. The processor 901 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0211] RAM 903 stores various programs and data required for the operation of electronic device 900. Processor 901, ROM 902, and RAM 903 are interconnected via bus 904. Processor 901 performs various operations of the method flow according to embodiments of the present disclosure by executing programs in ROM 902 and / or RAM 903. It should be noted that the programs may also be stored in one or more memories other than ROM 902 and RAM 903. Processor 901 may also perform various operations of the method flow according to embodiments of the present disclosure by executing programs stored in said one or more memories.

[0212] According to embodiments of this disclosure, the electronic device 900 may further include an input / output (I / O) interface 905, which is also connected to a bus 904. The electronic device 900 may also include one or more of the following components connected to the input / output (I / O) interface 905: an input section 906 including a keyboard, mouse, etc.; an output section 907 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 908 including a hard disk, etc.; and a communication section 909 including a network interface card such as a LAN card, modem, etc. The communication section 909 performs communication processing via a network such as the Internet. A drive 910 is also connected to the input / output (I / O) interface 905 as needed. A removable medium 911, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 910 as needed so that computer programs read from it can be installed into the storage section 908 as needed.

[0213] This disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or it may exist independently and not assembled into the device / apparatus / system. The computer-readable storage medium carries one or more programs that, when executed, implement the method according to the embodiments of this disclosure.

[0214] According to embodiments of this disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, such as including, but not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this disclosure, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, according to embodiments of this disclosure, the computer-readable storage medium may include ROM 902 and / or RAM 903 and / or one or more memories other than ROM 902 and RAM 903 described above.

[0215] Embodiments of this disclosure also include a computer program product comprising a computer program containing program code for performing the methods shown in the flowchart. When the computer program product is run on a computer system, the program code is used to cause the computer system to implement the item recommendation method provided in the embodiments of this disclosure.

[0216] When the computer program is executed by the processor 901, it performs the functions defined in the system / apparatus of this disclosure embodiments. According to embodiments of this disclosure, the systems, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0217] In one embodiment, the computer program may rely on a tangible storage medium such as an optical storage device or a magnetic storage device. In another embodiment, the computer program may also be transmitted and distributed in the form of signals over a network medium, and downloaded and installed via the communication section 909, and / or installed from a removable medium 911. The program code contained in the computer program can be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination thereof.

[0218] In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 909, and / or installed from the removable medium 911. When the computer program is executed by the processor 901, it performs the functions defined in the system of this disclosure embodiment. According to embodiments of this disclosure, the systems, devices, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0219] According to embodiments of this disclosure, program code for executing the computer programs provided in embodiments of this disclosure can be written in any combination of one or more programming languages. Specifically, these computational programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, languages ​​such as Java, C++, Python, "C", or similar programming languages. The program code can execute entirely on the user's computing device, partially on the user's device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0220] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0221] Those skilled in the art will understand that the features described in the various embodiments and / or claims of this disclosure can be combined or combined in various ways, even if such combinations or combinations are not explicitly described in this disclosure. In particular, the features described in the various embodiments and / or claims of this disclosure can be combined or combined in various ways without departing from the spirit and teachings of this disclosure. All such combinations and / or combinations fall within the scope of this disclosure.

[0222] The embodiments of this disclosure have been described above. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of this disclosure. Although various embodiments have been described above, this does not mean that the measures in the various embodiments cannot be used advantageously in combination. The scope of this disclosure is defined by the appended claims and their equivalents. Various substitutions and modifications can be made by those skilled in the art without departing from the scope of this disclosure, and all such substitutions and modifications should fall within the scope of this disclosure.

Claims

1. A method for checking a list of metrics for monitoring business scenarios, comprising: Each row of data in the business scenario list table is segmented into words to obtain a word set; Based on the similarity between every two words in the word set, generate a similarity matrix corresponding to the word set; For each row in the word set, the probability value corresponding to each word in each row is calculated based on the similarity matrix. Based on the probability value corresponding to each word in each row, a keyword set is obtained, wherein the keyword set includes a first keyword set, a second keyword set, and a third keyword set; According to preset matching rules, the keyword set is matched with a list of indicators used to monitor business scenarios to obtain a matching result, thereby enabling the inspection of the list of indicators used to monitor the business scenarios. This includes: obtaining a first-level template list based on the first keyword set; combining words from the first and second keyword sets to obtain a first list in the second-level template list; combining words from the first and third keyword sets to obtain a second list in the second-level template list; combining words from the first, second, and third keyword sets to obtain a third-level template list; obtaining an indicator template list for monitoring the business scenarios based on the first, second, and third template lists; and matching the indicator template list for monitoring the business scenarios with the indicator list to obtain the matching result.

2. The method according to claim 1, further comprising: Obtain business scenario information and metric information for monitoring the business scenario; Select the first target field from the business scenario information to obtain the business scenario list table; Select a second target field from the indicator information used to monitor the business scenario to obtain a list of indicators used to monitor the business scenario.

3. The method according to claim 2, wherein, The process of segmenting each row of data in the business scenario list table to obtain a word set includes: Extract the target keywords from the business scenario list table, and obtain the keyword dictionary table after deduplication; Based on the keyword dictionary, determine the fixed phrases in the business scenario list table; Based on the fixed phrases, each row of data in the business scenario list table is segmented into words to obtain the segmentation result corresponding to each row of data. The word set is obtained by removing duplicates from the word segmentation results corresponding to each row of data.

4. The method according to claim 1, wherein, The step of generating a similarity matrix corresponding to the word set based on the similarity between every two words in the word set includes: Feature extraction is performed on each word in the word set to obtain a word vector corresponding to each word; Based on the word vector corresponding to each word, the similarity between every two words in the word set is calculated; The similarity matrix is ​​obtained based on the similarity between every two words in the word set.

5. The method according to claim 1, wherein, For each row of the word set, the probability value corresponding to each word in each row is calculated based on the similarity matrix, including: For each word in each row of the word set, obtain the target similarity with each word from the similarity matrix; Based on the target similarity to each word, the probability value corresponding to each word is calculated.

6. The method according to claim 1, wherein, The keyword set is obtained based on the probability value corresponding to each word in each row, including: For each row in the word set, the probability values ​​corresponding to each word in each row are sorted in descending order to obtain a keyword list; Based on the keyword list, the word with the highest probability value in each row is selected to obtain the first keyword set. Based on the keyword list, select the word with the second probability value in descending order in each row to obtain the second keyword set; Based on the keyword list, the third word in each row with the third probability value in descending order is selected to obtain the third keyword set.

7. The method according to claim 1, further comprising: If the matching result indicates that there is data in the indicator template list that does not match the indicator list, the indicator list used to monitor the business scenario is checked and supplemented according to the matching result.

8. An inspection device for a list of metrics used to monitor business scenarios, comprising: The word segmentation module is used to segment each row of data in the business scenario list table to obtain a word set; The generation module is used to generate a similarity matrix corresponding to the word set based on the similarity between every two words in the word set; The calculation module is used to calculate the probability value of each word in each row of the word set based on the similarity matrix. The acquisition module is used to obtain a keyword set based on the probability value corresponding to each word in each row, wherein the keyword set includes a first keyword set, a second keyword set, and a third keyword set; The matching module is used to match the keyword set with the indicator list used to monitor the business scenario according to the preset matching rules, so as to obtain the matching result and realize the inspection of the indicator list used to monitor the business scenario. The matching module includes a sixth obtaining unit, a first combining unit, a second combining unit, a third combining unit, a seventh obtaining unit, and a matching unit. The sixth obtaining unit is used to obtain a first-level template list based on the first keyword set; The first combination unit is used to combine the words in the first keyword set and the second keyword set to obtain the first list in the second-level template list; The second combination unit is used to combine the words in the first keyword set and the third keyword set to obtain the second list in the second-level template list; The third combination unit is used to combine the words in the first keyword set, the second keyword set, and the third keyword set to obtain a third-level template list; The seventh obtaining unit is used to obtain an indicator template list for monitoring the business scenario based on the first layer template list, the second layer template list and the third layer template list; The matching unit is used to match the list of indicator templates used to monitor the business scenario with the indicator list to obtain the matching result.

9. An electronic device, comprising: One or more processors; Storage device for storing one or more programs. Wherein, when the one or more programs are executed by the one or more processors, the one or more processors perform the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, cause the processor to perform the method according to any one of claims 1 to 7.

11. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1 to 7.

Images