CN115952459A - Error reporting identification method, device, equipment and storage medium - Google Patents
Error reporting identification method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN115952459A CN115952459A CN202310031950.XA CN202310031950A CN115952459A CN 115952459 A CN115952459 A CN 115952459A CN 202310031950 A CN202310031950 A CN 202310031950A CN 115952459 A CN115952459 A CN 115952459A
- Authority
- CN
- China
- Prior art keywords
- error
- error reporting
- service
- node
- reporting
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Debugging And Monitoring (AREA)
Abstract
The invention relates to the technical field of computers, in particular to an error reporting identification method, an error reporting identification device, error reporting identification equipment and a storage medium, wherein the error reporting identification method comprises the following steps: acquiring service error reporting information in a service development process, and analyzing the service error reporting information to obtain service error reporting characteristics; inputting the service error reporting characteristics into an error reporting identification model constructed based on a decision tree algorithm, and outputting error categories through the error reporting identification model; and taking the error category output by the error reporting identification model as a target error category corresponding to the service error reporting information. The invention realizes the improvement of the efficiency of searching the service error.
Description
Technical Field
The present invention relates to the field of computer technologies, and in particular, to an error recognition method, an error recognition device, an error recognition apparatus, and a computer-readable storage medium.
Background
In the process of developing the service, when an error occurs in the service development, the development system reports the error, and the error reporting of the development system usually contains useless information to cause the ambiguity of error information, so that a service person is usually required to locate the error in a log record according to the error reporting information, or the service person is required to locate the error according to the experience of the service person. The processing mode causes the time consumption of the positioning error process to be too long, and the efficiency of positioning error of business personnel is not high.
Disclosure of Invention
The invention mainly aims to provide an error-reporting identification method, device and equipment and a computer readable storage medium, aiming at improving the efficiency of searching for business errors.
In order to achieve the above object, the present invention provides an error reporting identification method, which comprises the following steps:
acquiring service error reporting information in a service development process, and analyzing the service error reporting information to obtain service error reporting characteristics;
inputting the service error reporting characteristics into an error reporting identification model constructed based on a decision tree algorithm, and outputting error categories through the error reporting identification model;
and taking the error category output by the error reporting identification model as a target error category corresponding to the service error reporting information.
Optionally, before the step of obtaining the service error reporting information in the service development process, the method further includes:
acquiring a plurality of historical error reporting information of known error categories;
analyzing each historical error reporting information to obtain the respective historical error reporting characteristics of each historical error reporting information, and establishing a node data set based on each historical error reporting characteristic;
and constructing a decision tree based on the node data set and a decision tree algorithm, and taking the decision tree as an error reporting identification model.
Optionally, the step of constructing a decision tree based on the node data set and the decision tree algorithm includes:
determining the node data set as a data set of root nodes, and calculating root node damping coefficients corresponding to each keyword of each historical error reporting characteristic in the node data set;
taking the historical error reporting characteristic corresponding to the minimum root node kiney coefficient in each root node kiney coefficient as an optimal characteristic, and taking the keyword corresponding to the minimum root node kiney coefficient as an optimal segmentation point;
dividing the root node into two sub-nodes based on the optimal feature and the optimal segmentation point, and dividing the node data set into respective data sets of the two sub-nodes based on the optimal feature and the optimal segmentation point;
detecting whether nodes to be segmented exist in the two child nodes;
if the node to be segmented exists, segmenting the node to be segmented into two sub-nodes based on the data set of the node to be segmented, and executing the step of detecting whether the node to be segmented exists in the two sub-nodes;
and if the node to be segmented does not exist, determining to finish constructing the decision tree.
Optionally, the step of detecting whether there are nodes to be segmented in the two child nodes includes:
for any child node to be detected in the two child nodes, calculating child node kini coefficients corresponding to each keyword of each historical error reporting characteristic in the data set of the child node to be detected;
detecting whether the kini coefficient of each child node is smaller than a preset coefficient threshold value;
if the kini coefficient of each child node is smaller than the coefficient threshold value, determining that the child node to be detected is not the node to be segmented;
and if the kini coefficient of each child node is greater than or equal to the coefficient threshold value, determining the child node to be detected as the node to be segmented.
Optionally, after the step of using the error category output by the error reporting identification model as the target error category corresponding to the service error reporting information, the method further includes:
and determining the description and the solution corresponding to the target error category as a target description and a target scheme, and outputting and displaying the target description and the target scheme.
Optionally, the step of analyzing the service error reporting information to obtain a service error reporting characteristic includes:
and extracting keywords from the service error reporting information, and taking the extracted keywords as service error reporting characteristics.
Optionally, after the step of outputting the error category through the error recognition model, the method further comprises:
if the error category corresponding to the service error reporting information is an unknown category, receiving an uploading category and an uploading solution uploaded by service personnel;
and updating model parameters of the error reporting identification model based on the service error reporting information, the uploading category and the uploading solution to obtain an updated model, and taking the updated model as the error reporting identification model.
In addition, to achieve the above object, the present invention provides an error recognition apparatus, including:
the analysis module is used for acquiring service error reporting information in a service development process and analyzing the service error reporting information to obtain service error reporting characteristics;
the input module is used for inputting the service error reporting characteristics into an error reporting identification model constructed based on a decision tree algorithm and outputting error categories through the error reporting identification model;
and the determining module is used for taking the error category output by the error reporting identification model as a target error category corresponding to the service error reporting information.
In addition, in order to achieve the above object, the present invention further provides an error recognition apparatus, which includes a memory, a processor, and an error recognition program stored in the memory and operable on the processor, wherein the error recognition program, when executed by the processor, implements the steps of the error recognition method.
In addition, to achieve the above object, the present invention further provides a computer readable storage medium, on which an error recognition program is stored, and the error recognition program realizes the steps of the above error recognition method when executed by a processor.
In the invention, the service error reporting information in the service development process is acquired, the service error reporting information is analyzed to obtain the service error reporting characteristics, the service error reporting characteristics are input into an error reporting identification model constructed based on a decision tree algorithm, the error category is output through the error reporting identification model, and the error category output by the error reporting identification model is used as the target error category corresponding to the service error reporting information.
Compared with the method that the service personnel can locate the problem according to the service error reporting information by means of log records and historical experience, the method and the device have the advantages that the error reporting identification model constructed based on the decision tree algorithm outputs the target error category corresponding to the service error information according to the service error reporting information, so that the service personnel can directly process the service error according to the target error category, the time for the service personnel to search the service error is shortened, the error is quickly located, and the efficiency of searching the service error is improved.
Drawings
Fig. 1 is a schematic structural diagram of an error reporting identification device according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating a first embodiment of an error reporting identification method according to the present invention;
FIG. 3 is a flowchart illustrating an error reporting identification method according to an embodiment of the present invention;
fig. 4 is a functional block diagram of an error recognition apparatus according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a computer-readable storage medium according to an embodiment of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
As shown in fig. 1, fig. 1 is a schematic device structure diagram of a hardware operating environment according to an embodiment of the present invention.
It should be noted that, an embodiment of the present invention provides an error-reporting identifying device, where the error-reporting identifying device may be a device such as a smart phone or a personal computer, and is not limited herein.
As shown in fig. 1, the error recognition apparatus may include: a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, a communication bus 1002. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., a WI-FI interface). The memory 1005 may be a high-speed RAM memory or a non-volatile memory (e.g., a magnetic disk memory). The memory 1005 may alternatively be a storage device separate from the processor 1001.
Those skilled in the art will appreciate that the configuration of the apparatus shown in fig. 1 does not constitute a limitation of the error recognition apparatus and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components.
As shown in fig. 1, a memory 1005, which is a kind of computer storage medium, may include therein an operating system, a network communication module, a user interface module, and an error recognition program. The operating system is a program that manages and controls the hardware and software resources of the device, supporting the execution of error reporting identification programs as well as other software or programs. In the device shown in fig. 1, the user interface 1003 is mainly used for data communication with a client; the network interface 1004 is mainly used for establishing communication connection with an external network; and the processor 1001 may be configured to call the error recognition program stored in the memory 1005 and perform the following operations:
acquiring service error reporting information in a service development process, and analyzing the service error reporting information to obtain service error reporting characteristics;
inputting the service error reporting characteristics into an error reporting identification model constructed based on a decision tree algorithm, and outputting error categories through the error reporting identification model;
and taking the error category output by the error reporting identification model as a target error category corresponding to the service error reporting information.
Further, before the operation of acquiring the service error reporting information in the service development process, the processor 1001 may be further configured to call an error reporting identification program stored in the memory 1005, and perform the following operations:
acquiring a plurality of historical error reporting information of known error categories;
analyzing each historical error reporting information to obtain the respective historical error reporting characteristics of each historical error reporting information, and establishing a node data set based on each historical error reporting characteristic;
and constructing a decision tree based on the node data set and a decision tree algorithm, and taking the decision tree as an error reporting identification model.
Further, the operation of constructing a decision tree based on the node data set and the decision tree algorithm includes:
determining the node data set as a data set of root nodes, and calculating root node damping coefficients corresponding to each keyword of each historical error reporting characteristic in the node data set;
taking the historical error reporting characteristic corresponding to the minimum root node kiney coefficient in each root node kiney coefficient as an optimal characteristic, and taking the keyword corresponding to the minimum root node kiney coefficient as an optimal segmentation point;
dividing the root node into two sub-nodes based on the optimal feature and the optimal segmentation point, and dividing the node data set into respective data sets of the two sub-nodes based on the optimal feature and the optimal segmentation point;
detecting whether nodes to be segmented exist in the two child nodes;
if the node to be segmented exists, segmenting the node to be segmented into two sub-nodes based on the data set of the node to be segmented, and executing the step of detecting whether the node to be segmented exists in the two sub-nodes;
and if the node to be segmented does not exist, determining to finish constructing the decision tree.
Further, the operation of detecting whether there are nodes to be partitioned in the two child nodes includes:
for any child node to be detected in the two child nodes, calculating child node kini coefficients corresponding to each keyword of each historical error reporting characteristic in the data set of the child node to be detected;
detecting whether the kini coefficient of each child node is smaller than a preset coefficient threshold value;
if the kini coefficient of each child node is smaller than the coefficient threshold value, determining that the child node to be detected is not the node to be segmented;
and if the kini coefficient of each child node is greater than or equal to the coefficient threshold value, determining the child node to be detected as the node to be segmented.
Further, after the operation of taking the error category output by the error reporting identification model as the target error category corresponding to the service error reporting information, the processor 1001 may be further configured to call an error reporting identification program stored in the memory 1005, and perform the following operations:
and determining the description and the solution corresponding to the target error category as a target description and a target scheme, and outputting and displaying the target description and the target scheme.
Further, the operation of analyzing the service error reporting information to obtain the service error reporting characteristics includes:
and extracting keywords from the service error reporting information, and taking the extracted keywords as service error reporting characteristics.
Further, after the operation of outputting the error category through the error recognition model, the processor 1001 may be further configured to call an error recognition program stored in the memory 1005, and perform the following operations:
if the error category corresponding to the service error reporting information is an unknown category, receiving an uploading category and an uploading solution uploaded by service personnel;
and updating model parameters of the error reporting identification model based on the service error reporting information, the uploading category and the uploading solution to obtain an updated model, and taking the updated model as the error reporting identification model.
Based on the above structure, various embodiments of the error reporting identification method of the present invention are provided.
An embodiment of the invention provides an error reporting identification method, and referring to fig. 2, fig. 2 is a flowchart illustrating a first embodiment of the error reporting identification method according to the invention.
While a logical order is shown in the flow chart, in some cases, the steps shown or described may be performed in an order different than presented herein. In this embodiment, the execution subject of the error reporting identification method may be an error reporting identification device, and the error reporting identification device may be a smart phone, a personal computer, or the like. In this embodiment, the error reporting identification method includes:
step S10: acquiring service error reporting information in a service development process, and analyzing the service error reporting information to obtain service error reporting characteristics;
in the process of developing the service, when the existing error is developed, the service development platform reports the error. In this embodiment, error information in the service development process is obtained (hereinafter referred to as service error information for distinction), in a specific embodiment, the service error information may be a code, for example, a status code such as 404, and the service error information may also be information in a text form, for example, a stack, which is not limited herein.
In this embodiment, after the service error reporting information in the service development process is acquired, the service error reporting information is analyzed to obtain the feature of the service error reporting information, and the feature is referred to as a service error reporting feature to show the distinction. Specifically, in an embodiment, the analyzing the service error information to obtain the service error characteristics may be obtained by extracting keywords, such as text analysis, and keyword extraction based on deep learning; in another embodiment, the analyzing the service error reporting information to obtain the service error reporting characteristics may also be a preset word bank, and a word in the service error reporting information that is the same as a preset word in the preset word bank is used as the service error reporting characteristics, which may be specifically set according to actual requirements, and is not limited herein.
Step S20: inputting the service error reporting characteristics into an error reporting identification model constructed based on a decision tree algorithm, and outputting error categories through the error reporting identification model;
in this embodiment, the error reporting in the service development process is divided into a plurality of categories (hereinafter referred to as error reporting categories for convenience of description), different error reporting may correspond to different error categories, and specifically, the error category may be in a number form, for example, category one; the method may also be in a general form, for example, a web browsing error, and may be specifically set according to an actual requirement, which is not limited herein. And pre-constructing a classification tree based on a decision tree algorithm, and determining the constructed classification tree as an error reporting identification model for identifying and developing categories corresponding to errors.
Specifically, in this embodiment, after the service error reporting information is analyzed to obtain the service error reporting characteristics, the service error reporting characteristics are input to the error reporting identification model constructed based on the decision tree algorithm, and the error category is output through the error reporting identification model.
Step S30: and taking the error category output by the error reporting identification model as a target error category corresponding to the service error reporting information.
In this embodiment, the service error reporting feature is input to construct an error reporting recognition model based on a decision tree algorithm, and after the error category is output by the error reporting recognition model, the error category output by the error reporting recognition model is used as the error category corresponding to the service error reporting information (hereinafter referred to as a target error category to show differentiation).
Further, in some possible embodiments, in the step S30: after the error category output by the error reporting identification model is used as the target error category corresponding to the service error reporting information, the error reporting identification method further includes:
step S40: and determining the description and the solution corresponding to the target error category as a target description and a target scheme, and outputting and displaying the target description and the target scheme.
In this embodiment, descriptions and solutions corresponding to known error categories are preset, and in a specific implementation, the error categories, the descriptions, and the solutions may be in a one-to-one correspondence relationship. In a specific embodiment, the description may be a description of a service error reporting chinese form, for example, if the error category corresponding to the error reporting information 404 is category one, then the description corresponding to category one is that when the user browses a web page, the server cannot provide correct information or the server cannot send information to the visitor for unknown reasons.
In this embodiment, the description and the solution corresponding to the target error category are determined as the description (hereinafter referred to as target description for distinguishing) and the solution (hereinafter referred to as target solution for distinguishing) corresponding to the service error reporting information, and the target description and the target solution are output and displayed for the service personnel to process the error reporting in the service development process by referring to the target description and the target solution.
It should be noted that by providing the target description and the target solution corresponding to the service error reporting information, the present embodiment may push a popular and understandable description and solution according to the service error reporting information, so that there is a reference when solving the service error, and compared with a service worker processing the service error according to his own experience, the present embodiment reduces the workload of the service worker, and improves the work efficiency of the service worker.
In addition, the embodiment enables the business error report to be processed without depending on the technology of business personnel, and improves the operability of processing the business error report.
Further, in some possible embodiments, the step S10: analyzing the service error reporting information to obtain service error reporting characteristics, including:
step S101: and extracting keywords from the service error reporting information, and taking the extracted keywords as service error reporting characteristics.
In this embodiment, the service error reporting feature is obtained by extracting a keyword from the service error reporting information. Specifically, in this embodiment, after the service error reporting information is obtained, keyword extraction is performed on the service error reporting information, in a specific implementation, the keyword extraction may be performed through text analysis, or may be performed through keyword extraction based on deep learning, and the keyword extraction may be specifically set according to an actual requirement, which is not limited herein.
In this embodiment, the keyword is extracted from the service error reporting information, and the extracted keyword is used as a service error reporting feature. It should be noted that, in an embodiment, the service error reporting feature may include a plurality of keywords.
Compared with the method that words in the service error reporting information, which are the same as the preset word bank, are used as the service error reporting characteristics, the method can adapt to various forms of service error reporting information, and the practicability of the error reporting identification method is improved.
Further, in some possible embodiments, in the above step S20: after the error classification is output through the error recognition model, the error recognition method further includes:
step S50: if the error category corresponding to the service error reporting information is an unknown category, receiving an uploading category and an uploading solution uploaded by service personnel;
in this embodiment, the error category that does not appear in the error reporting identification model is referred to as an unknown category, and if the service error reporting feature corresponding to the service error reporting information does not conform to any classification condition in the error reporting identification model, the error category corresponding to the service error reporting information is determined to be the unknown category.
In a specific embodiment, after the error category is output through the error reporting identification model, if the error category corresponding to the service error reporting information is an unknown category, the service staff is notified to process the service error reporting information, specifically, the service staff may analyze and process the error reporting according to the service error reporting information and the service log, which is not limited herein. After the service personnel processes the service error reporting information, the service error reporting information can be divided into error categories and uploaded with the error categories and the solutions.
In this embodiment, if the error type corresponding to the service error reporting information is an unknown type, the error type (hereinafter referred to as an upload type to indicate differentiation) and the resolution (hereinafter referred to as an upload solution to indicate differentiation) uploaded by the service staff are received.
Step S60: and updating model parameters of the error reporting identification model based on the service error reporting information, the uploading category and the uploading solution to obtain an updated model, and taking the updated model as the error reporting identification model.
In this embodiment, after receiving the upload category and the upload solution uploaded by the service staff, the error recognition model is updated based on the service error reporting information, the upload category, and the upload solution to obtain an updated error recognition model (hereinafter referred to as an update model to show distinction), and the update model is used as the error recognition model to perform error recognition.
It should be noted that, if the error category corresponding to the service error reporting information is an unknown category, the upload category and the upload solution uploaded by the service staff are received, model parameters of the error reporting identification model are updated based on the service error reporting information, the upload category and the upload solution to obtain an updated model, and the updated model is used as the error reporting identification model. The embodiment increases the recognizable error categories of the error reporting recognition model, and improves the accuracy and the practicability of the error reporting recognition model.
In this embodiment, the service error reporting information in the service development process is acquired, the service error reporting information is analyzed to obtain a service error reporting characteristic, the service error reporting characteristic is input to an error reporting identification model constructed based on a decision tree algorithm, an error category is output through the error reporting identification model, and the error category output by the error reporting identification model is used as a target error category corresponding to the service error reporting information. Compared with the method that the service personnel can locate the problem according to the service error reporting information by means of log records and historical experience, the method and the device have the advantages that the error reporting identification model constructed based on the decision tree algorithm outputs the target error category corresponding to the service error information according to the service error reporting information, so that the service personnel can directly process the service error according to the target error category, the time for the service personnel to search the service error is shortened, the error is quickly located, and the efficiency of searching the service error is improved.
Further, a second embodiment of the present invention is proposed based on the first embodiment, in which the step S10: before the step of obtaining the service error reporting information in the service development process, the error reporting identification method further comprises the following steps:
step S70: acquiring a plurality of historical error reporting information of known error categories;
in this embodiment, the error reporting information that has occurred in the development process and has known error categories is referred to as historical error reporting information, multiple pieces of historical error reporting information of the known error categories are obtained, and an error reporting identification model is obtained based on the multiple pieces of historical error reporting information of the known error categories.
Step S80: analyzing each historical error reporting information to obtain the respective historical error reporting characteristics of each historical error reporting information, and establishing a node data set based on each historical error reporting characteristic;
in the present embodiment, after acquiring a plurality of pieces of historical error reporting information of known error types, each piece of historical error reporting information is analyzed to obtain the characteristic of each piece of historical error reporting information (hereinafter, referred to as a historical error reporting characteristic to be distinguished). In a specific embodiment, the step S10 may be referred to as a manner of extracting the history error reporting feature, which is not described herein again.
In this embodiment, after analyzing each piece of historical error reporting information to obtain the respective historical error reporting characteristics of each piece of historical error reporting information, a node data set for constructing an error reporting identification model is established based on the respective historical error reporting characteristics of each piece of historical error reporting information.
Step S90: and constructing a decision tree based on the node data set and a decision tree algorithm, and taking the decision tree as an error reporting identification model.
In this embodiment, a decision tree is constructed based on a node data set and a CART (classification and regression tree) algorithm, that is, a decision tree algorithm, and the decision tree is used as an error reporting recognition model.
Further, in some possible embodiments, the step S90: constructing a decision tree based on the node data set and a decision tree algorithm, comprising:
step S901: determining the node data set as a data set of root nodes, and calculating root node damping coefficients corresponding to each keyword of each historical error reporting characteristic in the node data set;
in this embodiment, a decision tree is constructed based on a node data set and a decision tree algorithm, specifically, the node data set is determined as a root node of the decision tree, and a kini coefficient corresponding to each keyword of each historical error reporting feature in the node data set is calculated (hereinafter, referred to as root node kini coefficient for distinction).
Specifically, the root node kini coefficient may be calculated according to the following calculation formula:
wherein, two sub-nodes after one node is divided can be called as a left node and a right node, N _L Number of samples drawn to the left node, N R Is the number of samples divided into right nodes, and N is the total number of divided samples, i.e. N L +N R ，
To the left node belonging to C K The number of the classes is such that, device for combining or screening>
To the right node belonging to C k The number of classes.
Step S902: taking the historical error reporting characteristic corresponding to the minimum root node kiney coefficient in each root node kiney coefficient as an optimal characteristic, and taking the keyword corresponding to the minimum root node kiney coefficient as an optimal segmentation point;
according to the calculation formula of the kiney coefficient, the kiney coefficient can represent the probability that two samples are randomly extracted from the left node or the right node, and the two samples do not belong to the same class, so that the smaller the kiney coefficient is, the smaller the probability that any two samples in the same sub-node (namely, the left node or the right node) do not belong to the same class is, which indicates that the smaller the impurities on the sub-node are, the better the segmentation effect of the node is. Therefore, the smaller the kini coefficient is, the better the segmentation effect on the root node is.
Specifically, in this embodiment, the historical error-reporting feature corresponding to the minimum root node kiney coefficient in each root node kiney coefficient is used as the optimal feature, and the keyword corresponding to the minimum root node kiney coefficient is used as the optimal segmentation point, so as to segment the root node based on the optimal feature and the optimal segmentation point.
Step S903: dividing the root node into two sub-nodes based on the optimal feature and the optimal segmentation point, and dividing the node data set into respective data sets of the two sub-nodes based on the optimal feature and the optimal segmentation point;
in this embodiment, after the optimal feature and the optimal segmentation point are determined, the root node is divided into two child nodes based on the optimal feature and the optimal segmentation point, and the node data set is divided into respective data sets of the two child nodes based on the optimal feature and the optimal segmentation point.
Step S904: detecting whether nodes to be segmented exist in the two child nodes;
in this embodiment, the child nodes that can be continuously divided are referred to as nodes to be divided, and after the root node is divided into two child nodes, whether the two child nodes have nodes to be divided is detected.
In a specific embodiment, detecting whether a node to be segmented exists in two child nodes may be detecting whether the child nodes meet a condition for continuous segmentation, and in an embodiment, detecting whether samples on the child nodes belong to the same category, and if the samples on the child nodes all belong to the same category, determining that the child nodes do not meet the condition for continuous segmentation; in another embodiment, it may also be detected whether the number of samples on the child node is less than a preset number, and if the number of samples on the child node is less than the preset number, the child node is considered not to satisfy the condition of continuing to segment; in another embodiment, it may also be detected whether the number of layers of the node is greater than a preset number of layers, and if the number of layers of the node is greater than the preset number of layers, the child node is considered not to satisfy the condition of continuing to partition; in another embodiment, it may also be detected whether the kini coefficient of the sample on the child node is smaller than a preset coefficient, and if the kini coefficient of the sample on the child node is smaller than the preset coefficient, the child node is considered not to satisfy the condition for continuing the segmentation, and the specific detection condition may be set according to an actual requirement, which is not limited herein.
Step S905: if the node to be segmented exists, segmenting the node to be segmented into two sub-nodes based on the data set of the node to be segmented, and executing the step of detecting whether the node to be segmented exists in the two sub-nodes;
in this embodiment, if there is a node to be segmented, the node to be segmented is continuously segmented, specifically, the node to be segmented is segmented into two sub-nodes based on the data set of the node to be segmented, and a step of detecting whether there is a node to be segmented in the two sub-nodes is performed, so as to determine whether there is a node to be segmented which can be continuously segmented in the sub-nodes of the node to be segmented.
Step S906: and if the node to be segmented does not exist, determining to finish constructing the decision tree.
In this embodiment, if there is no node to be segmented, it is determined that the construction of the decision tree is completed.
Further, in some possible embodiments, the step S904: detecting whether two child nodes have nodes to be segmented or not, comprising the following steps:
step S9041: for any child node to be detected in the two child nodes, calculating child node kini coefficients corresponding to each keyword of each historical error reporting characteristic in the data set of the child node to be detected;
in this embodiment, whether or not the child node can continue to be divided is determined based on the kini coefficient of the child node (hereinafter, referred to as child node kini coefficient to show distinction). Specifically, in this embodiment, for any child node (hereinafter referred to as a to-be-detected child node for distinguishing), the child node kini coefficient corresponding to each keyword of each history error-reporting feature in the data set of the to-be-detected child node is calculated.
Step S9042: detecting whether the kini coefficient of each child node is smaller than a preset coefficient threshold value;
in this embodiment, a kini coefficient threshold (hereinafter, referred to as a coefficient threshold for distinction) is preset, and the coefficient threshold may be set according to actual needs, which is not limited herein. And detecting whether the kini coefficient of each child node is smaller than a preset coefficient threshold value.
Step S9043: if the kini coefficient of each child node is smaller than the coefficient threshold value, determining that the child node to be detected is not the node to be segmented;
and if the Gini coefficient of each child node is smaller than the coefficient threshold, determining that the purity of the sample on the child node is higher, and determining that the child node to be detected is not the node to be segmented.
Step S9044: and if the kini coefficient of each child node is greater than or equal to the coefficient threshold value, determining the child node to be detected as the node to be segmented.
And if the Gini coefficient of each child node is greater than or equal to the coefficient threshold, determining that the purity of the sample on the child node is low, and continuously segmenting the child node, namely determining the child node to be detected as the node to be segmented.
In the embodiment, whether the child nodes can be continuously segmented is judged based on the size relationship between the child node kini coefficient and the coefficient threshold, so that the purity of each node in the obtained decision tree is high, and the recognition result of the error-reporting recognition model is more accurate.
Further, in an embodiment, referring to fig. 3, fig. 3 is a schematic flow chart related to an embodiment of the error reporting identification method of the present invention, in this embodiment, the service development platform may be a Hadoop (distributed system infrastructure) platform, the service error reporting information may be a code, and the error reporting identification process may be:
acquiring service error reporting information (i.e. inputting a service error reporting code shown in fig. 3) in a service development process;
analyzing the service error reporting information to obtain a service error reporting characteristic (i.e., analyzing the error information shown in fig. 3 to obtain a characteristic value);
inputting the service error reporting characteristics into an error reporting recognition model constructed based on a decision tree algorithm, outputting error categories through the error reporting recognition model, and determining descriptions and solutions corresponding to the target error categories as target descriptions and target solutions (namely, the system shown in fig. 3 identifies, classifies the same type of errors, outputs error description information and provides solutions);
error recognition ends (i.e., the task shown in fig. 3 ends).
In the embodiment, a plurality of historical error reporting information of known error categories are acquired, each piece of historical error reporting information is analyzed to obtain the respective historical error reporting characteristics of each piece of historical error reporting information, a node data set is established based on each historical error reporting characteristic, a decision tree is established based on the node data set and a decision tree algorithm, and the decision tree is used as an error reporting identification model to classify the business error reporting information through the error reporting identification model.
In addition, the present invention further provides an error recognition apparatus, referring to fig. 4, fig. 4 is a schematic diagram of functional modules of the error recognition apparatus according to the embodiment of the present invention. The error reporting identification device of the invention comprises:
the analysis module 10 is configured to obtain service error reporting information in a service development process, and analyze the service error reporting information to obtain a service error reporting characteristic;
the input module 20 is configured to input the service error reporting feature into an error reporting identification model constructed based on a decision tree algorithm, and output an error category through the error reporting identification model;
a determining module 30, configured to use the error category output by the error reporting identification model as a target error category corresponding to the service error reporting information.
Further, the error recognition apparatus further includes a construction module, where the construction module is configured to:
acquiring a plurality of historical error reporting information of known error categories;
analyzing each historical error reporting information to obtain the respective historical error reporting characteristics of each historical error reporting information, and establishing a node data set based on each historical error reporting characteristic;
and constructing a decision tree based on the node data set and a decision tree algorithm, and taking the decision tree as an error reporting identification model.
Further, the building module is further configured to:
determining the node data set as a data set of root nodes, and calculating a root node kini coefficient corresponding to each keyword of each historical error reporting characteristic in the node data set;
taking the historical error reporting characteristic corresponding to the minimum root node kiney coefficient in each root node kiney coefficient as an optimal characteristic, and taking the keyword corresponding to the minimum root node kiney coefficient as an optimal segmentation point;
dividing the root node into two sub-nodes based on the optimal feature and the optimal segmentation point, and dividing the node data set into respective data sets of the two sub-nodes based on the optimal feature and the optimal segmentation point;
detecting whether nodes to be segmented exist in the two child nodes;
if the node to be segmented exists, segmenting the node to be segmented into two sub-nodes based on the data set of the node to be segmented, and executing the step of detecting whether the node to be segmented exists in the two sub-nodes;
and if the node to be segmented does not exist, determining to finish constructing the decision tree.
Further, the building module is further configured to:
for any sub-node to be detected in the two sub-nodes, calculating a sub-node kini coefficient corresponding to each keyword of each historical error reporting characteristic in the data set of the sub-node to be detected;
detecting whether the kini coefficient of each child node is smaller than a preset coefficient threshold value;
if the kini coefficient of each child node is smaller than the coefficient threshold value, determining that the child node to be detected is not the node to be segmented;
and if the kini coefficient of each child node is greater than or equal to the coefficient threshold value, determining the child node to be detected as the node to be segmented.
Further, the determining module 30 is further configured to:
and determining the description and the solution corresponding to the target error category as a target description and a target scheme, and outputting and displaying the target description and the target scheme.
Further, the parsing module 10 is further configured to:
and extracting keywords from the service error reporting information, and taking the extracted keywords as service error reporting characteristics.
Further, the error recognition apparatus further includes an update module, where the update module is configured to:
if the error category corresponding to the service error reporting information is an unknown category, receiving an uploading category and an uploading solution uploaded by service personnel;
and updating model parameters of the error reporting identification model based on the service error reporting information, the uploading category and the uploading solution to obtain an updated model, and taking the updated model as the error reporting identification model.
The method for identifying the error is implemented when each functional module of the error identification device runs.
In addition, the invention also provides a computer readable storage medium. Referring to fig. 5, fig. 5 is a schematic structural diagram of a computer-readable storage medium according to an embodiment of the present invention. The computer readable storage medium has stored thereon an error recognition program, which when executed by the processor implements the steps of the error recognition method as described above.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrases "comprising one of 8230; \8230;" 8230; "does not exclude the presence of additional like elements in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention essentially or contributing to the prior art can be embodied in the form of a software product, which is stored in a computer-readable storage medium (such as ROM/RAM, magnetic disk, optical disk) as described above and includes instructions for enabling an error-reporting identifying device (which may be a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. An error reporting identification method, characterized in that the error reporting identification method comprises the following steps:
acquiring service error reporting information in a service development process, and analyzing the service error reporting information to obtain service error reporting characteristics;
inputting the service error reporting characteristics into an error reporting identification model constructed based on a decision tree algorithm, and outputting error categories through the error reporting identification model;
and taking the error category output by the error reporting identification model as a target error category corresponding to the service error reporting information.
2. The error reporting identification method of claim 1, wherein before the step of obtaining the service error reporting information in the service development process, the method further comprises:
acquiring a plurality of historical error reporting information of known error categories;
analyzing each historical error reporting information to obtain the respective historical error reporting characteristics of each historical error reporting information, and establishing a node data set based on each historical error reporting characteristic;
and constructing a decision tree based on the node data set and a decision tree algorithm, and taking the decision tree as an error reporting identification model.
3. The error-reporting identification method of claim 2 wherein the step of constructing a decision tree based on the node dataset and a decision tree algorithm comprises:
determining the node data set as a data set of root nodes, and calculating a root node kini coefficient corresponding to each keyword of each historical error reporting characteristic in the node data set;
taking the historical error reporting characteristic corresponding to the minimum root node kiney coefficient in each root node kiney coefficient as an optimal characteristic, and taking the keyword corresponding to the minimum root node kiney coefficient as an optimal segmentation point;
dividing the root node into two sub-nodes based on the optimal feature and the optimal segmentation point, and dividing the node data set into respective data sets of the two sub-nodes based on the optimal feature and the optimal segmentation point;
detecting whether nodes to be segmented exist in the two child nodes or not;
if the node to be segmented exists, segmenting the node to be segmented into two sub-nodes based on the data set of the node to be segmented, and executing the step of detecting whether the node to be segmented exists in the two sub-nodes;
and if the node to be segmented does not exist, determining to finish constructing the decision tree.
4. The error-reporting identification method as claimed in claim 3, wherein the step of detecting whether there are nodes to be partitioned in two child nodes comprises:
for any child node to be detected in the two child nodes, calculating child node kini coefficients corresponding to each keyword of each historical error reporting characteristic in the data set of the child node to be detected;
detecting whether the kini coefficient of each child node is smaller than a preset coefficient threshold value or not;
if the kini coefficient of each child node is smaller than the coefficient threshold value, determining that the child node to be detected is not the node to be segmented;
and if the kini coefficient of each child node is greater than or equal to the coefficient threshold value, determining the child node to be detected as the node to be segmented.
5. The error-reporting identification method as claimed in claim 1, wherein after the step of using the error category output by the error-reporting identification model as the target error category corresponding to the service error-reporting information, the method further comprises:
and determining the description and the solution corresponding to the target error category as a target description and a target scheme, and outputting and displaying the target description and the target scheme.
6. The error recognition method of claim 1, wherein the step of parsing the service error message to obtain service error characteristics comprises:
and extracting keywords from the service error reporting information, and taking the extracted keywords as service error reporting characteristics.
7. The error-reporting identification method of any one of claims 1 to 6, wherein after the step of outputting the error classification by the error-reporting identification model, the method further comprises:
if the error category corresponding to the service error reporting information is an unknown category, receiving an uploading category and an uploading solution uploaded by service personnel;
and updating model parameters of the error reporting identification model based on the service error reporting information, the uploading category and the uploading solution to obtain an updated model, and taking the updated model as the error reporting identification model.
8. An error recognition apparatus, comprising:
the analysis module is used for acquiring service error reporting information in a service development process and analyzing the service error reporting information to obtain service error reporting characteristics;
the input module is used for inputting the service error reporting characteristics into an error reporting identification model constructed based on a decision tree algorithm and outputting error categories through the error reporting identification model;
and the determining module is used for taking the error category output by the error reporting identification model as a target error category corresponding to the service error reporting information.
9. An error reporting identification device, characterized in that the error reporting identification device comprises: memory, a processor and an error recognition program stored on the memory and executable on the processor, the error recognition program being configured to implement the steps of the error recognition method according to any one of claims 1 to 7.
10. A computer-readable storage medium, on which an error recognition program is stored, which, when executed by a processor, implements the steps of the error recognition method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310031950.XA CN115952459A (en) | 2023-01-10 | 2023-01-10 | Error reporting identification method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310031950.XA CN115952459A (en) | 2023-01-10 | 2023-01-10 | Error reporting identification method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115952459A true CN115952459A (en) | 2023-04-11 |
Family
ID=87286036
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310031950.XA Pending CN115952459A (en) | 2023-01-10 | 2023-01-10 | Error reporting identification method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115952459A (en) |
-
2023
- 2023-01-10 CN CN202310031950.XA patent/CN115952459A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2018086470A1 (en) | Keyword extraction method and device, and server | |
| CN110008343B (en) | Text classification method, apparatus, device and computer readable storage medium | |
| US11132385B2 (en) | Information processing device and information processing method | |
| TW202020691A (en) | Feature word determination method and device and server | |
| CN113760891B (en) | Data table generation method, device, equipment and storage medium | |
| CN111160021A (en) | Log template extraction method and device | |
| CN110780965B (en) | Vision-based process automation method, equipment and readable storage medium | |
| CN114780746A (en) | Knowledge graph-based document retrieval method and related equipment thereof | |
| CN115098679A (en) | Method, device, equipment and medium for detecting abnormality of text classification labeling sample | |
| CN114327964A (en) | Method, device, equipment and storage medium for processing fault reasons of service system | |
| CN107291774B (en) | Error sample identification method and device | |
| CN110019193B (en) | Similar account number identification method, device, equipment, system and readable medium | |
| CN113326363B (en) | Searching method and device, prediction model training method and device and electronic equipment | |
| CN112686521B (en) | Wind control rule optimizing method and system | |
| CN112035668A (en) | Event subject recognition model optimization method, device and equipment and readable storage medium | |
| CN115146653B (en) | Dialogue scenario construction method, device, equipment and storage medium | |
| CN115952459A (en) | Error reporting identification method, device, equipment and storage medium | |
| CN113535458B (en) | Abnormal false alarm processing method and device, storage medium and terminal | |
| JP2023152270A (en) | Data labeling method by artificial intelligence, apparatus, electronic device, storage medium, and program | |
| CN115470034A (en) | Log analysis method, device and storage medium | |
| CN114528908A (en) | Network request data classification model training method, classification method and storage medium | |
| CN115269998A (en) | Information recommendation method and device, electronic equipment and storage medium | |
| CN115292506A (en) | Knowledge graph ontology construction method and device applied to office field | |
| CN111261165A (en) | Station name identification method, device, equipment and storage medium | |
| CN111611981A (en) | Information identification method and device and information identification neural network training method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |