CN115617983A

CN115617983A - Text-based defect analysis method and device, electronic equipment and storage medium

Info

Publication number: CN115617983A
Application number: CN202211336975.2A
Authority: CN
Inventors: 陈洪美; 黄翔; 刘昊成; 罗垚; 徐雅琳; 穆琼
Original assignee: Agricultural Bank of China
Current assignee: Agricultural Bank of China
Priority date: 2022-10-28
Filing date: 2022-10-28
Publication date: 2023-01-17

Abstract

The invention discloses a text-based defect analysis method and device, electronic equipment and a storage medium. The text-based defect analysis method comprises the following steps: acquiring defect text information to be subjected to defect analysis; preprocessing the defect text information to obtain defect data; determining characteristic words based on the defect data and a set word bank, wherein the set word bank at least comprises words in a service scene corresponding to the defect text information; determining defect analysis result information based on the defect data and the feature words; and visually displaying the defect analysis result information. According to the technical scheme, the word bank is set in a combined manner in the defect analysis process, so that the defect analysis result is closer to the actual service requirement, the accuracy of defect analysis is improved, meanwhile, the defect analysis result information is visually displayed, the system is conveniently improved through the defect analysis result, and the convenience of defect analysis is improved.

Description

Text-based defect analysis method and device, electronic equipment and storage medium

Technical Field

The embodiment of the invention relates to the technical field of defect analysis, in particular to a text-based defect analysis method and device, electronic equipment and a storage medium.

Background

At present, the analysis aiming at the defects is isolated event analysis, and subjective experience analysis can be performed on the defect texts by people. In the face of a large amount of defect texts across systems or years in a banking system, it is difficult for human analysis to extract potentially accurate laws. Meanwhile, the content described by the text is unstructured data, and the research is difficult to be directly carried out by a statistical analysis or big data analysis method.

However, in the prior art, when unstructured data is converted into structured data for defect analysis, most of the defect texts are segmented based on the existing word stock, and when the defect texts of a bank system are faced, the existing word stock cannot segment the defect texts accurately, so that the accuracy of a defect analysis result is reduced; and when the structured data are obtained based on the defect text, developers can not directly analyze the defect reasons through the large amount of structured data. Therefore, how to improve the accuracy and convenience of defect analysis is a technical problem to be solved urgently at present.

Disclosure of Invention

The invention provides a text-based defect analysis method and device, electronic equipment and a storage medium, wherein a word bank is set to enable a defect analysis result to be closer to the actual business requirement, so that the accuracy of defect analysis is improved, meanwhile, the information of the defect analysis result is visually displayed, the system is conveniently improved through the defect analysis result, and the convenience of defect analysis is improved.

In a first aspect, an embodiment of the present invention provides a method for defect analysis based on a text, including:

acquiring defect text information to be subjected to defect analysis;

preprocessing the defect text information to obtain defect data;

determining characteristic words based on the defect data and a set word bank, wherein the set word bank at least comprises words in a service scene corresponding to the defect text information;

determining defect analysis result information based on the defect data and the feature words;

and visually displaying the defect analysis result information.

In a second aspect, an embodiment of the present invention provides a text-based defect analysis apparatus, including:

the acquisition module is used for acquiring defect text information to be subjected to defect analysis;

the preprocessing module is used for preprocessing the defect text information to obtain defect data;

the first determining module is used for determining characteristic words based on the defect data and a set word bank, wherein the set word bank at least comprises words in a service scene corresponding to the defect text information;

the second determining module is used for determining defect analysis result information based on the defect data and the feature words;

and the visual display module is used for visually displaying the defect analysis result information.

In a third aspect, an embodiment of the present invention provides an electronic device, including:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein, the first and the second end of the pipe are connected with each other,

the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to enable the at least one processor to perform the method according to the first aspect.

In a fourth aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the method according to the first aspect.

The embodiment of the invention provides a method and a device for defect analysis based on a text, an electronic device and a storage medium. The text-based defect analysis method comprises the following steps: acquiring defect text information to be subjected to defect analysis; preprocessing the defect text information to obtain defect data; determining characteristic words based on the defect data and a set word bank, wherein the set word bank at least comprises words under a service scene corresponding to the defect text information; determining defect analysis result information based on the defect data and the feature words; and visually displaying the defect analysis result information. According to the technical scheme, the word bank is set in a combined manner in the defect analysis process, so that the defect analysis result is closer to the actual service requirement, the accuracy of defect analysis is improved, meanwhile, the defect analysis result information is visually displayed, the system is conveniently improved through the defect analysis result, and the convenience of defect analysis is improved.

It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present invention, nor do they necessarily limit the scope of the invention. Other features of the present invention will become apparent from the following description.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the description below are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.

Fig. 1 is a flowchart of a method for text-based defect analysis according to an embodiment of the present invention;

FIG. 2 is a flowchart of a method for text-based defect analysis according to a second embodiment of the present invention;

FIG. 3 is a schematic structural diagram of a defect value mining tool based on a text analysis algorithm according to a third embodiment of the present invention;

FIG. 4 is a flowchart of determining defect analysis result information by a text analysis algorithm according to a third embodiment of the present invention;

fig. 5 is a schematic structural diagram of a text-based defect analysis apparatus according to a fourth embodiment of the present invention;

FIG. 6 illustrates a schematic structural diagram of an electronic device that may be used to implement embodiments of the present invention.

Detailed Description

In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in other sequences than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

It can be understood that, before the technical solutions disclosed in the embodiments of the present invention are used, the type, the use range, the use scenario, etc. of the personal information related to the present disclosure should be informed to the user and authorized by the user in a proper manner according to relevant laws and regulations.

For a bank system, two defects generally exist, one is a test defect discovered in a project research and development test process, and the test defect is solved before the bank system is put on production; the other is that after the project is put on line, a production event is triggered in the production environment, and then the exposed production defect, namely an escape defect, has negative influence on the operation of banking business and needs to be repaired through urgent change. The test defects can reflect the development quality of the system, the production defects can reflect the service condition of the system, and the comprehensive two aspects can reflect the quality of the full life cycle of the project. Therefore, performing defect analysis on the system may reveal the deficiencies and improved direction of the system.

When the system is subjected to defect analysis, a mode of converting unstructured data into structured data can be adopted, namely converting the defects described by unstructured texts into structured defect characteristics, and further analyzing the defects by applying a big data analysis mining technology and feeding back the value of the defects to the system construction. The unstructured data may be data that has an irregular or incomplete data structure, has no predefined data model, and is inconvenient to represent by using a database two-dimensional logic table, such as office documents, texts, pictures, hypertext Markup Language (HTML), various types of reports, images, audio/video information, and the like in all formats. Structured data, also referred to as row data, may refer to data logically represented and implemented by a two-dimensional table structure, and is stored and managed mainly by a relational database, strictly following data format and length specifications. The process of converting unstructured data into structured data is understood to be data parsing of unstructured data through classification or hierarchy so that the unstructured data can be represented in a structured manner.

Example one

Fig. 1 is a flowchart of a text-based defect analysis method according to an embodiment of the present invention, where the embodiment is applicable to a case where a defect text is analyzed, and the method can be executed by a text-based defect analysis apparatus, which can be implemented in software and/or hardware and integrated in an electronic device. Further, electronic devices include, but are not limited to: computers, notebook computers, smart phones, servers, and the like. As shown in fig. 1, the method includes:

and S110, acquiring defect text information to be subjected to defect analysis.

The defect text information may refer to information indicated by text describing the defect. The specific form of the defect text information is not limited, and may be various forms of text, such as a table or a document describing the defect. The defect text information can be used for defect analysis, and then a system for generating defects can be improved according to defect analysis result information obtained by defect analysis in the follow-up process.

In one embodiment, the defect text information includes one or more of defect identification, defect occurrence time, system to which the defect belongs, defect phenomenon description, defect cause analysis, and defect handling.

The defect identifier may be a code of a defect indicated in the defect text information, the defect identifier may be used to distinguish a plurality of defects indicated in the defect text information, and each defect identifier may correspond to only one defect indicated in the defect text information. For example, three defects are indicated in the defect text information, the defect identifier may be number 1, 2 or 3, and the defect corresponding to the number is identified by a different number.

And any defect mark corresponds to a unique defect, and the defect occurrence time, the system to which the defect belongs, the defect phenomenon description, the defect reason analysis and the defect disposal mode of the defect.

The defect occurrence time may refer to a time when a defect indicated in the defect text information occurs, such as a time when the defect is recorded or a time when the defect actually occurs, and is determined according to actual needs.

The defect belonging system may refer to a system that generates a defect indicated in the defect text information, for example, when facing banking, the defect belonging system may indicate which system the defect generating system is specific, for example, a payment system, a comprehensive pre-posed system, or a core service system, and may respectively implement different functions corresponding to a plurality of systems.

The defect phenomenon description may refer to a phenomenon of generating a defect indicated in the defect text information. The defect cause analysis may refer to a cause of generation of a defect indicated in the defect text information. The defect handling method may be a method of processing when a defect is generated, which is indicated in the defect text information. The defect phenomenon description, defect cause analysis or defect handling mode is not limited, and can be determined according to actual needs.

In one embodiment, the defect phenomenon description may be a system response timeout; the defect reason analysis can be that the hardware configuration in the system can not meet the normal operation of the system, so that the response speed of the system is too low; the defect handling mode can be to replace the hardware configuration in the system, so that the hardware configuration in the system can meet the normal operation of the system.

The method for obtaining the defect text information to be subjected to defect analysis is not limited, for example, the defect text information set according to actual needs is stored in a database in advance, and the electronic equipment accesses the database in the electronic equipment when needed, so that the defect text information can be obtained; for another example, the defect text information to be subjected to defect analysis may be acquired through a human-computer interaction interface, where the human-computer interaction interface may be an interface for a user to interact with the electronic device, and the human-computer interaction interface may display an interface for inputting the defect text information, and the user may input the defect text information through the interface, so that the electronic device may acquire the defect text information to be subjected to defect analysis through the human-computer interaction interface.

And S120, preprocessing the defect text information to obtain defect data.

The defect text information is preprocessed to obtain defect data, which can be understood as extracting essential information required in defect analysis as defect data according to the defect text information, so as to perform defect analysis through the defect data.

The defect data may refer to essential information required in defect analysis, for example, the defect data may be one of a defect phenomenon description, a defect cause analysis, and a defect handling manner included in the defect text information, or a combination of a plurality of the defect phenomenon description, the defect cause analysis, and the defect handling manner.

For example, when the defect text information is a table describing defects, one or more corresponding rows or columns in the defect phenomenon description, defect cause analysis and defect handling modes required can be searched in the table through a VLOOKUP function, and the searched result is used as defect data as required; for another example, when the defect text information is a document describing a defect, one or more of the defect phenomenon description, the defect cause analysis, and the defect handling manner may be used as a keyword, and the document may be searched according to the keyword, and the searched paragraph having the keyword may be used as defect data.

S130, determining characteristic words based on the defect data and a set word bank, wherein the set word bank at least comprises words in a service scene corresponding to the defect text information.

The word stock setting may be a word stock set according to actual needs, and the word stock is set for performing defect analysis. The set word bank is not limited, the set word bank can at least comprise words under a service scene corresponding to the defect text information, for example, when bank services are faced, the set word bank can contain words such as service rules, dates, mobile phone number sections, operation maintenance, service maintenance or blacklists, and the set word bank is considered during defect analysis, so that the defect analysis can be combined with an actual service scene, and the defect analysis result is more accurate.

The feature words may refer to words related to defect analysis extracted based on the defect data, such as words whose frequency of occurrence in the defect data exceeds a first set frequency, or words whose frequency of occurrence exceeds a first set frequency, and the like. The number of the feature words is not limited, and the number of the feature words can be determined according to actual needs. The first setting frequency or the first setting number is not limited, and the first setting frequency or the first setting number may be determined according to actual needs.

The method for determining the feature words based on the defect data and the set word stock is not limited, for example, the defect data and the set word stock can be introduced into a word segmentation tool, so that the word segmentation tool can perform word segmentation processing on the defect data by combining the set word stock with the word stock of the word segmentation tool to obtain data after word segmentation processing, and for the data after word segmentation processing, words with the occurrence frequency exceeding the first set frequency can be extracted as the feature words. The word segmentation tool is not limited, such as a jieba word segmentation tool. The word segmentation processing on the defect data can be understood as a process of recombining continuous word sequences in the defect data into word sequences according to a certain specification.

It should be noted that when determining the feature words based on the defect data and the set lexicon, the feature words finally used for defect analysis can be more closely attached to the defect features by combining with other lexicons, such as combining with the stop word lexicon to filter out the mood auxiliary words, prepositions, or conjunctions in the defect data. The stop word bank can be set according to actual needs.

And S140, determining defect analysis result information based on the defect data and the feature words.

The defect analysis result information may refer to information indicated by the result of the defect analysis. The defect analysis result information may be used to indicate whether any feature word is present in the defect data and the number of times the feature word is present.

The method for determining the defect analysis result information based on the defect data and the feature words is not limited, for example, the defect data is sequentially traversed according to different feature words to obtain a traversed result, and the traversed result can indicate whether any feature word appears in the defect data, the frequency of the feature word appearing, and the like.

The specific form of the defect analysis result information is not limited, for example, the defect analysis result information may include a defect feature matrix. The defect feature matrix may be a matrix indicating information of a defect analysis result, and the defect feature matrix is not limited, for example, in the defect feature matrix, each column may correspond to one feature word, each row corresponds to one defect, different identifiers are used to distinguish the feature words appearing in the defect data from the feature words not appearing in the defect data, the feature words appearing in the defect data are denoted as one identifier, and the feature words not appearing in the defect data are denoted as another identifier. And counting the marks in the defect characteristic matrix, namely determining whether any characteristic word appears in the defect data and the frequency of the characteristic word, namely determining the defect analysis result information.

And S150, visually displaying the defect analysis result information.

The visual display mode of the defect analysis result information is not limited, for example, the defect analysis result information is displayed on the human-computer interaction interface in different display modes by setting a script, so that a user can obtain the defect analysis result information through the human-computer interaction interface, and further, a system for generating defects is improved conveniently. The setting script is not limited, and the setting script may be a script developed according to actual needs.

The method for visually displaying the defect analysis result information is not limited, and for example, the feature words appearing in the defect data may be displayed in a word cloud manner according to the defect analysis result information. The word cloud display can display the feature words appearing in the defect analysis result information according to different appearance times. For example, the feature words with more occurrences are better visually, for example, the color is brighter or the font is larger; and the feature words appearing less frequently have a reduced visual effect, for example, a darker color or a smaller font. The method for realizing the word cloud display is not limited, for example, the word cloud display can be realized through a word cloud display tool, and the feature words with different occurrence times are visually distinguished through the word cloud display tool, so that the feature words appearing in the defect analysis result information are effectively presented, and a user can conveniently process the defects through the defect analysis result information.

According to the technical scheme of the embodiment of the invention, the set word bank is combined in the defect analysis process, so that the defect analysis result is closer to the actual business requirement, the accuracy of the defect analysis is improved, meanwhile, the defect analysis result information is visually displayed, the system is conveniently improved through the defect analysis result, and the convenience of the defect analysis is improved.

Example two

Fig. 2 is a flowchart of a text-based defect analysis method according to a second embodiment of the present invention, which is a further refinement on the basis of the first embodiment.

In the embodiment of the present invention, the preprocessing the defect text information to obtain defect data includes:

one of defect phenomenon description, defect reason analysis and defect treatment modes included in the defect text information is used as defect data; or the like, or, alternatively,

a plurality of defect phenomenon descriptions, defect cause analyses, and defect handling methods are combined as defect data.

In the embodiment of the present invention, determining the feature words based on the defect data and the set word bank includes:

performing word segmentation processing on the defect data based on the custom word bank to obtain first data after word segmentation processing;

performing stop word removal processing on the first data based on the stop word library to obtain second data after the stop word removal processing;

a set number of words are extracted from the second data as feature words.

In the embodiment of the present invention, determining defect analysis result information based on defect data and feature words includes:

comparing the defect data with the feature words to generate a defect feature matrix, wherein in the defect feature matrix, the position corresponding to the feature words appearing in the defect data is set as a first identifier, and the position corresponding to the feature words not appearing in the defect data is set as a second identifier;

the defect analysis result information comprises a defect feature matrix, the first identification and the second identification are different identifications, and the defect feature matrix represents feature words appearing in the defect data.

In the embodiment of the invention, the visualized display of the defect analysis result information comprises the following steps:

selecting one or more display modes in a human-computer interaction interface;

displaying the defect analysis result information on a human-computer interaction interface according to the selected display mode;

wherein, the display mode at least comprises: word cloud display, radar chart display, time line chart display and defect belonging system display.

In the embodiment of the present invention, acquiring defect text information to be subjected to defect analysis includes:

and acquiring the defect text information to be subjected to defect analysis through a human-computer interaction interface.

As shown in fig. 2, the method includes:

and S111, acquiring defect text information to be subjected to defect analysis through a human-computer interaction interface.

The human-computer interaction interface can be an interface for interaction between a user and the electronic equipment, the interface for inputting the defect text information can be displayed on the human-computer interaction interface, the user can input the defect text information through the interface, and the electronic equipment can further obtain the defect text information to be subjected to defect analysis through the human-computer interaction interface.

S121, taking one of defect phenomenon description, defect reason analysis and defect treatment modes included in the defect text information as defect data; or, a plurality of defect phenomenon descriptions, defect cause analyses, and defect handling methods are combined as defect data.

For example, when the defect text information is a table describing defects, each row in the table represents a defect, columns in the table respectively represent a defect identifier, a defect occurrence time, a system to which the defect belongs, a defect description, a defect cause analysis, and a defect handling manner, which are included in the defect text information, a column corresponding to one of the required defect description, defect cause analysis, and defect handling manner can be searched in the table through a VLOOKUP function, and data corresponding to the searched column is used as defect data.

The method of merging multiple defect phenomenon descriptions, defect cause analyses, and defect handling methods as defect data is not limited, for example, when the defect text information is a table describing defects, multiple corresponding data in the required defect phenomenon descriptions, defect cause analyses, and defect handling methods can be searched in the table through the VLOOKUP function, and the multiple corresponding data in the defect phenomenon descriptions, defect cause analyses, and defect handling methods can be spliced as required to serve as the defect data. When a plurality of corresponding data in the defect phenomenon description, the defect reason analysis and the defect treatment mode are spliced, the plurality of corresponding data in the defect phenomenon description, the defect reason analysis and the defect treatment mode corresponding to the same defect are spliced into a whole.

S131, performing word segmentation processing on the defect data based on the custom word bank to obtain first data after word segmentation processing.

S132, stop word processing is carried out on the first data based on the stop word lexicon, and second data after the stop word processing is obtained.

And S133, extracting a set number of words from the second data to serve as feature words.

The set word stock comprises a user-defined word stock and a stop word stock; the user-defined word stock comprises a first word stock and a second word stock; the first word bank comprises words which are obtained by performing word segmentation on set data and extracting words with the frequency exceeding the set frequency, the second word bank comprises words in a service scene corresponding to the defect text information, and the set data are determined based on historical defect text information. The stop word bank at least comprises one or more of a mood assistant word, a preposition and a conjunctive word.

The user-defined word stock can be a word stock set according to actual needs, and the user-defined word stock can comprise a first word stock and a second word stock.

The first word bank includes words which are segmented from the set data and words whose frequency of occurrence exceeds the set frequency are extracted. The set data may be determined based on historical defect text information, the historical defect text information may be defect text information before the defect text information to be subjected to defect analysis is acquired, and the historical defect text information may be set according to actual needs. The same method as that of step S121 may be adopted to extract one of the defect phenomenon description, defect cause analysis, and defect handling manner from the historical defect text information as the setting data; alternatively, a plurality of defect phenomenon descriptions, defect cause analyses, and defect handling methods are combined as the setting data. The word segmentation processing can be carried out on the set data by adopting a jieba word segmentation tool, and words with the occurrence frequency exceeding the set frequency are extracted and used as words in the first word stock. The set frequency is not limited.

The second lexicon includes words in the service scene corresponding to the defective text information, for example, when facing banking services, the second lexicon may include words such as service rules, dates, mobile phone number segments, operation maintenance, service maintenance or blacklists.

The stop word lexicon may refer to a lexicon composed of words that can save storage space and improve search efficiency in information retrieval. The words included in the stop word library may be stop words, and the stop words may refer to words or phrases that are automatically filtered before or after processing natural language data (or text) in order to save storage space and improve search efficiency in information retrieval, and these words or phrases are called stop words. The lexicon of stop words comprises at least one or more of words such as assist words, prepositions and conjunctive words, such as o, a/or and words. The stop word library can be downloaded through a webpage, and words with low relevance with a service scene can be added on the basis of webpage downloading.

And performing word segmentation processing on the defect data based on the custom word bank to obtain first data after word segmentation processing. The method for performing word segmentation processing is not limited, for example, the defect data and the custom lexicon can be imported into the word segmentation tool, so that the word segmentation tool can perform word segmentation processing on the defect data by combining the custom lexicon with the lexicon of the word segmentation tool, and the data after word segmentation processing is obtained and used as the first data.

And performing stop word processing on the first data based on the stop word library to obtain second data after the stop word processing. The method of processing the stop word is not limited, and for example, the first data may be traversed based on the stop word lexicon, and if a word included in the stop word lexicon appears in the first data, the word included in the stop word lexicon appearing in the first data is deleted as the second data.

And extracting a set number of words from the second data as feature words. When selecting the feature words, words with the occurrence times exceeding a second set time can be selected from the second data, and then words with a set number are extracted from the selected words to serve as the feature words. The second set number or the set number can be selected according to actual needs. For example, the set number may be 150.

S141, comparing the defect data with the feature words to generate a defect feature matrix, wherein in the defect feature matrix, the position corresponding to the feature words appearing in the defect data is set as a first identifier, and the position corresponding to the feature words not appearing in the defect data is set as a second identifier; the defect analysis result information comprises a defect feature matrix, the first identification and the second identification are different identifications, and the defect feature matrix represents feature words appearing in the defect data.

The first label and the second label are not limited as long as the first label and the second label are different.

The mode of comparing the defect data with the feature words is not limited, for example, the defect data is sequentially traversed according to different feature words to obtain a traversed result, and the traversed result can indicate whether any feature word appears in the defect data, the frequency of the feature word appearing and the like.

When the defect feature matrix is generated, each column may correspond to one feature word, each row corresponds to one defect, for each defect, a position corresponding to a feature word appearing in the defect data is set as a first identifier, and a position corresponding to a feature word not appearing in the defect data is set as a second identifier, that is, the number of feature words appearing in the defect data corresponding to the row may be determined by the number of the first identifiers counted in each row, or the number of times that the corresponding feature word appears in the defect text information may be determined by the number of the first identifiers counted in each column.

In one embodiment, the defect text information includes defect identifiers indicating that there are 5 defects, the number of feature words may be 150, and the defect feature matrix may be a matrix of 5 by 150, where each row in the defect feature matrix may correspond to one defect, and each column may correspond to one feature word. The first flag may be 1 and the second flag may be 0. When the defect feature matrix is generated, for one defect, the position corresponding to the feature word appearing in the defect data is set to 1, and the position corresponding to the feature word not appearing in the defect data is set to 0, so that the number of the feature words appearing in the defect data corresponding to the defect can be determined by counting the number of the first marks corresponding to the defect. Similarly, for a plurality of defects included in the defect text information, the feature word with the largest occurrence number can be counted through the number of the first marks appearing in a certain column of the defect feature matrix, so that the system is improved based on the defect analysis result information.

And S151, selecting one or more display modes in the human-computer interaction interface.

Wherein, the display mode at least comprises: word cloud display, radar map display, time line graph display and defect belonging system display.

The radar map display can refer to a display mode of displaying the radar map in a man-machine interaction interface. The radar map may be a graphical method of displaying multivariate data in the form of a two-dimensional graph of three, or more, quantitative variables represented on axes from the same point. In the radar map, each vertex may correspond to a defect, the length of the axis may represent the number of feature words appearing in the defect data corresponding to the defect, and a longer axis indicates a greater number of feature words appearing in the defect data corresponding to the defect.

The time line graph display can refer to a display mode of displaying a time line graph in a human-computer interaction interface, and the time line graph can indicate that the quantity of the characteristic words in defect data corresponding to the defects changes along with the occurrence time of the defects and the like.

The defect belonging system display may be displaying the defect belonging system in a human-computer interaction interface, for example, an interface for displaying the defect belonging system exists in the human-computer interaction interface, and the defect belonging system corresponding to the frequency of the occurrence of the feature words exceeding a third set frequency may be displayed on the interface, so that a user can optimize the defect belonging system. The third set number of times can be selected according to actual needs.

The human-computer interaction interface can be provided with an interface for selecting a display mode, the interface can be provided with a plurality of controls, each control corresponds to a unique display mode, and when a user clicks the control corresponding to the display mode on the interface, the display mode can be selected successfully.

And S152, displaying the defect analysis result information on a human-computer interaction interface according to the selected display mode.

When the selected display mode is determined in step S151, the defect analysis result information may be displayed on the human-computer interaction interface according to the selected display mode.

In an embodiment, if it is determined in step S151 that the selected presentation manner is word cloud presentation, the word cloud image may be displayed on the human-computer interaction interface through word cloud presentation. In the word cloud picture, the defect analysis result information indicates that the characteristic words with more occurrences have better visual effect, such as more vivid color or larger font; and the feature words appearing less frequently have a reduced visual effect, for example, a darker color or a smaller font. The word cloud picture can effectively present the characteristic words appearing in the defect analysis result information, and is convenient for a user to process the defects through the defect analysis result information.

According to the technical scheme of the embodiment of the invention, the first data is obtained by performing word segmentation processing on the defect data through the user-defined word bank, the second data is obtained by performing stop word processing on the first data through the stop word bank, and words with a set number are extracted from the second data to be used as feature words, so that the defect analysis is closer to the actual service requirement, and the accuracy of the defect analysis is improved; one or more display modes are selected from the human-computer interaction interface, and the defect analysis result information is displayed on the human-computer interaction interface according to the selected display modes, so that the system is improved conveniently through the defect analysis result, and the convenience of defect analysis is improved.

EXAMPLE III

The embodiments of the present invention are exemplary illustrations of the above-described embodiments. The embodiment of the invention provides a defect analysis method based on a text analysis algorithm. The description of the defects is usually unstructured data, the data volume is large, the detail description difference between events is large, time and labor are consumed for manual analysis, subjective analysis is influenced, and objective and unified characteristic rules are difficult to extract. Therefore, the embodiment of the invention provides a defect analysis method based on a text analysis algorithm, which aims to convert the defect described by an unstructured text into the structured defect characteristic through the text analysis algorithm, so as to facilitate defect analysis.

The defect analysis method based on the text analysis algorithm provided by the embodiment of the invention can be realized by a defect value mining tool based on the text analysis algorithm, and the tool can be integrated in electronic equipment. Fig. 3 is a schematic structural diagram of a defect value mining tool based on a text analysis algorithm according to a third embodiment of the present invention, as shown in fig. 3, the structure of the tool is composed of two parts, one is a foreground interface, which includes a defect import module for importing defects (i.e., acquiring defect text information to be subjected to defect analysis through a human-computer interaction interface), and an analysis result display module for graphically displaying analysis results (i.e., visually displaying defect analysis result information), where the foreground interface may be a human-computer interaction interface; the second is background algorithm, the core is text analysis algorithm and statistical analysis algorithm, structured transformation is carried out on the defect data through algorithm and rule extraction is carried out.

The embodiment of the invention provides a defect analysis method based on a text analysis algorithm, which comprises the following specific steps:

1. the defect text information can be imported into the electronic equipment through the defect import module, so that the electronic equipment can acquire the defect text information (namely acquiring the defect text information to be subjected to defect analysis through a human-computer interaction interface).

A standardized form template may be provided at the module, which may be used by a user to set defect text information, a defect text information setting table is shown in table 1, and a form template is provided in table 1.

Table 1 defect text information setting table

The defect ID is an Identity (ID) of the defect.

2. And determining defect analysis result information through a text analysis algorithm.

Fig. 4 is a flowchart of determining defect analysis result information by a text analysis algorithm according to a third embodiment of the present invention, where as shown in fig. 4, the flowchart includes;

preprocessing a source file (namely preprocessing defect text information to obtain defect data);

performing jieba word segmentation by combining the user-defined word bank (namely performing word segmentation processing on the defect data based on the user-defined word bank to obtain first data after word segmentation processing);

processing only from stop words by combining with a stop word lexicon (namely, performing stop word processing on the first data based on the stop word lexicon to obtain second data after the stop word processing);

extracting TOP 150 feature words by a word frequency inverse document frequency algorithm, namely extracting 150 feature words, wherein the extracted feature words can be words with the first 150 occurrence frequencies (namely extracting a set number of words from the second data as the feature words);

and performing structural processing on the defect text according to the feature words (namely determining defect analysis result information based on the defect data and the feature words).

The self-defined word stock can be formed by adding words with actual business meanings on the basis of the Chinese standard word stock as self-defined word groups according to the types and description modes of common defects of the bank system. If the word segmentation result of the text of the blacklist face recognition is 'blacklist/list/face/recognition' according to the jieba standard word stock, after the user-defined word group is added, the word segmentation result of the user-defined word stock is 'blacklist/face recognition', the processing result is more in line with the mode of banking system service definition and defect analysis, and the data mining is more facilitated. The self-defined word bank can contain words such as service rules, dates, mobile phone number segments, operation maintenance, service maintenance or blacklists.

The stop word lexicon can be formed by adding phrases irrelevant to defect analysis mining on the basis of common stop words according to the types and description modes of common defects of a bank system, reducing the interference of words without practical business meanings to defect characteristics in subsequent analysis, such as transaction, part, reduction and the like. Words such as or and words may be present in the stop word lexicon.

The extracted feature words can be words such as database, query, batch, log, node, server, file, call or face recognition.

3. And displaying the defect analysis result information (namely visually displaying the defect analysis result information) through a statistical analysis algorithm and an analysis result display module.

The statistical analysis algorithm can realize the calculation of the defect analysis result information, and different display modes of the defect analysis result information can be realized by inputting the defect analysis result information into the statistical analysis algorithm and combining the analysis result display module. Table 2 shows a display mode selection table displayed by the analysis result display module, the display modes in table 2 may be increased or deleted as needed, and the control corresponding to the display mode is clicked in table 2, that is, the defect analysis result information is displayed on the analysis result display module in the selected display mode.

Table 2 shows a mode selection table

In one embodiment, when the production defects of the bank system are analyzed, more than 800 production defects exist, the characters describing the defects are as high as 60 ten thousand characters, and uniform and objective rules are difficult to extract through manpower analysis. By the defect analysis method based on the text analysis algorithm, 150 defect characteristics (namely characteristic words) can be extracted, after each defect is converted into structural data formed by the characteristics, description characters are reduced to 1 ten thousand characters, and the text data volume is reduced by 60 times. The structured defect data is used as input, a data analysis mining algorithm can be realized, word cloud display can be realized, and defect characteristics can be visually processed.

According to the defect analysis method based on the text analysis algorithm, provided by the embodiment of the invention, the defect described by the unstructured text is converted into the structured defect characteristic through the text analysis algorithm, so that the defect analysis is facilitated; the feature words are determined through the self-defined word bank and the stop word bank, so that the defect analysis is closer to the actual service requirement, and the accuracy of the defect analysis is improved; the visual display of the defect analysis result information is realized, and the convenience of defect analysis is improved.

Example four

Fig. 5 is a schematic structural diagram of a text-based defect analysis apparatus according to a fourth embodiment of the present invention, which is applicable to a case of analyzing a defect text. As shown in fig. 5, the specific structure of the apparatus includes:

the acquiring module 21 is configured to acquire defect text information to be subjected to defect analysis;

the preprocessing module 22 is configured to preprocess the defect text information to obtain defect data;

the first determining module 23 is configured to determine the feature words based on the defect data and a set word bank, where the set word bank at least includes words in a service scene corresponding to the defect text information;

a second determining module 24, configured to determine defect analysis result information based on the defect data and the feature words;

and the visual display module 25 is used for visually displaying the defect analysis result information.

The defect analysis device based on the text provided by the embodiment firstly obtains the defect text information to be subjected to defect analysis through the obtaining module 21; then, preprocessing the defect text information through a preprocessing module 22 to obtain defect data; then, determining characteristic words through a first determining module 23 based on the defect data and a set word bank, wherein the set word bank at least comprises words in a service scene corresponding to the defect text information; determining defect analysis result information based on the defect data and the feature words through a second determining module 24; and finally, visually displaying the defect analysis result information through a visual display module 25.

Further, the defect text information includes one or more of defect identification, defect occurrence time, system to which the defect belongs, defect phenomenon description, defect cause analysis, and defect handling method.

Further, the preprocessing module 22 is specifically configured to:

Further, the first determining module 23 is specifically configured to:

performing stop word processing on the first data based on the stop word lexicon to obtain second data after the stop word processing;

extracting a set number of words from the second data as feature words;

the set word library comprises a user-defined word library and a stop word library;

the user-defined word stock comprises a first word stock and a second word stock; the first word bank comprises words which are obtained by performing word segmentation processing on set data and extracting words with the frequency exceeding the set frequency, the second word bank comprises words under a service scene corresponding to the defect text information, and the set data are determined based on historical defect text information;

the stop word bank at least comprises one or more of a mood assistant word, a preposition and a conjunctive word.

Further, the second determining module 24 is specifically configured to:

Further, the visualization display module 25 is specifically configured to:

selecting one or more display modes in a human-computer interaction interface;

Further, the obtaining module 21 is specifically configured to:

and acquiring defect text information to be subjected to defect analysis through a human-computer interaction interface.

The text-based defect analysis device provided by the embodiment of the invention can execute the text-based defect analysis method provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method.

EXAMPLE five

FIG. 6 illustrates a schematic structural diagram of an electronic device that may be used to implement embodiments of the present invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.

As shown in fig. 6, the electronic device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, and the like, wherein the memory stores a computer program executable by the at least one processor, and the processor 11 can perform various suitable actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from a storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data necessary for the operation of the electronic apparatus 10 may also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.

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, or the like; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.

The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, or the like. The processor 11 performs the various methods and processes described above, such as text-based defect analysis methods.

In some embodiments, the text-based defect analysis method may be implemented as a computer program tangibly embodied on a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the text-based defect analysis method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the text-based defect analysis method in any other suitable manner (e.g., by way of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

A computer program 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, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be performed. A computer program can execute entirely on a machine, partly on a machine, as a stand-alone software package partly on a machine and partly on a remote machine or entirely on a remote machine or server.

In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, 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 compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can 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 a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can 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, speech, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the Internet.

The computing system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical host and VPS service are overcome.

It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present invention may be executed in parallel, sequentially, or in different orders, and are not limited herein as long as the desired results of the technical solution of the present invention can be achieved.

The above-described embodiments should not be construed as limiting the scope of the invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, 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 text-based defect analysis method, comprising:

acquiring defect text information to be subjected to defect analysis;

preprocessing the defect text information to obtain defect data;

and visually displaying the defect analysis result information.

2. The method of claim 1, wherein the defect text information comprises one or more of defect identification, defect occurrence time, defect belonging system, defect phenomenon description, defect cause analysis, and defect handling.

3. The method according to claim 1 or 2, wherein the preprocessing the defect text information to obtain defect data comprises:

and combining a plurality of defect phenomenon description, defect cause analysis and defect treatment modes as defect data.

4. The method of claim 1, wherein determining feature words based on the defect data and a set word library comprises:

performing word segmentation processing on the defect data based on a custom word bank to obtain first data after word segmentation processing;

performing stop word removal processing on the first data based on a stop word library to obtain second data after the stop word removal processing;

extracting a set number of words from the second data as the feature words;

the set word bank comprises the user-defined word bank and the stop word bank;

the user-defined word stock comprises a first word stock and a second word stock; the first word bank comprises words which are obtained by performing word segmentation processing on set data and extracting words with frequency exceeding the set frequency, the second word bank comprises words in a service scene corresponding to the defect text information, and the set data are determined based on historical defect text information;

the stop word bank at least comprises one or more of mood auxiliary words, prepositions and conjunctions.

5. The method of claim 1, wherein determining defect analysis result information based on the defect data and the feature words comprises:

the defect analysis result information comprises the defect feature matrix, the first identification and the second identification are different identifications, and the defect feature matrix represents feature words appearing in the defect data.

6. The method of claim 1, wherein the visually presenting the defect analysis result information comprises:

selecting one or more display modes in the human-computer interaction interface;

7. The method according to claim 1, wherein the obtaining the defect text information to be subjected to defect analysis comprises:

8. A text-based defect analysis apparatus, comprising:

9. An electronic device, comprising:

at least one processor; and

the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-7.

10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1-7.