Work order sending method and device

Abstract

The present disclosure relates to the technical field of communication, and particularly relates to a work order sending method and device. The work order sending method comprises the following steps: obtaining a first fault error code; in the case that the fault error code library does not include the first fault error code, adopting a target extreme gradient boosting tree (XGBoost) classification algorithm model to perform fault root cause bounding on the first fault error code, and obtaining first error code bounding information corresponding to the first fault error code; and according to the first error code bounding information, sending a fault work order corresponding to the first fault error code to a target terminal. The present disclosure can improve the security of smart home devices while improving the convenience of smart work order sending.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of communication, and in particular, to a work order sending method and device. BACKGROUND

[0002] With the development of communication technology, the life of users can be facilitated. However, in the process of providing services to users, faults may occur, and fault work orders can be generated so that terminals corresponding to the faults can process the faults to improve the quality of services. However, due to the electronic work order pipeline operation mode, the fault probability of the work order process is high, and the fault processing efficiency is low. SUMMARY

[0003] The present disclosure provides a work order sending method and device, which can reduce the fault probability of the work order process while improving the fault processing efficiency. The technical solutions of the present disclosure are as follows:

[0004] According to a first aspect of an embodiment of the present disclosure, a work order sending method is provided, comprising:

[0005] obtaining a first fault error code;

[0006] in a case where the fault error code library does not include the first fault error code, performing fault root cause bounding on the first fault error code by using an eXtreme Gradient Boosting (XGBoost) classification algorithm model to obtain first error code bounding information corresponding to the first fault error code;

[0007] According to the first error code bounding information, sending a fault work order corresponding to the first fault error code to a target terminal.

[0008] According to some embodiments, the method further comprises:

[0009] performing data preprocessing on the obtained historical fault processing work order and fault error log information to obtain a fault sample information set;

[0010] performing XGBoost operation by using the fault sample information set to obtain a target eXtreme Gradient Boosting (XGBoost) classification algorithm model.

[0011] According to some embodiments, the fault sample information set comprises processed fault error log information, and the data preprocessing on the obtained fault error log information to obtain a fault sample information set comprises:

[0012] in a case where the fault error log information is text information, performing text vectorization processing on the fault error log information by using term frequency-inverse document frequency, and obtaining a keyword set according to keyword selection requirements.

[0013] The digital mapping of any keyword in the keyword set is performed to obtain a digital mapping table corresponding to the any keyword, and the digital mapping table is taken as the fault sample information set.

[0014] According to some embodiments, the XGBoost operation is performed by using the fault sample information set to obtain a target extreme gradient boosting tree XGBoost classification algorithm model.

[0015] The XGBoost operation is performed by using the processed fault handling order and the processed fault error log information to obtain an initial extreme gradient boosting tree XGBoost classification algorithm model.

[0016] The second error code boundary information corresponding to the second fault error code of the fault error log information is obtained by performing calculation on the second fault error code of the fault error log information by using the initial extreme gradient boosting tree XGBoost classification algorithm model.

[0017] In a case where a confirmation instruction for the second error code boundary information is received, it is determined that a target extreme gradient boosting tree XGBoost classification algorithm model is obtained.

[0018] According to some embodiments, the XGBoost operation is performed by using the fault sample information set to obtain a target extreme gradient boosting tree XGBoost classification algorithm model.

[0019] The prediction value of the prediction boundary of the (i-1)th classification and regression tree CARTs and the prediction value of the prediction boundary of the tth classification and regression tree CART are obtained from the i-1th fault sample information in the fault sample information set, where i is a positive integer.

[0020] The target function is obtained according to the prediction value of the prediction boundary of the (i-1)th classification and regression tree CARTs and the prediction value of the prediction boundary of the tth classification and regression tree CART.

[0021] The target extreme gradient boosting tree XGBoost classification algorithm model is obtained by performing parameterization operation on the target function.

[0022] According to some embodiments, the method further comprises:

[0023] In a case where the first fault error code is included in the fault error code library, third error code boundary information corresponding to the first fault error code is obtained.

[0024] According to the third error code boundary information, the fault order corresponding to the first fault error code is sent to a target terminal.

[0025] According to some embodiments, the method further comprises:

[0026] obtaining a confidence degree corresponding to the first error code definition information;

[0027] in a case where the confidence degree is less than a confidence degree threshold, sending a short message information to the target terminal, wherein the short message information comprises a fault work order corresponding to the first fault error code;

[0028] in a case where the confidence degree is greater than the confidence degree threshold, updating the fault error code library by using the first fault error code and the first error code definition information, to obtain an updated fault error code library.

[0029] According to a second aspect of embodiments of the present disclosure, a work order sending device is provided, comprising:

[0030] an error code obtaining unit, configured to obtain a first fault error code;

[0031] an information obtaining unit, configured to, in a case where a fault error code library does not comprise the fault error code, perform fault root cause definition on the first fault error code by using an extreme gradient boosting tree XGBoost classification algorithm model, to obtain first error code definition information corresponding to the first fault error code;

[0032] a work order sending unit, configured to send a fault work order corresponding to the first fault error code to a target terminal according to the first error code definition information.

[0033] According to a third aspect of embodiments of the present disclosure, a network device is provided, comprising:

[0034] a processor;

[0035] a memory for storing instructions executable by the processor;

[0036] wherein the processor is configured to execute the instructions to implement the work order sending method of any one of the preceding aspects.

[0037] According to a fourth aspect of embodiments of the present disclosure, a storage medium is provided, when instructions in the storage medium are executed by a processor of a network device, the network device is enabled to perform the work order sending method of any one of the preceding aspects.

[0038] According to a fifth aspect of embodiments of the present disclosure, a storage medium is provided, when instructions in the storage medium are executed by a processor of a terminal, the terminal is enabled to perform the work order sending method of any one of the preceding aspects.

[0039] According to a sixth aspect of the embodiments of the present disclosure, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the method of any one of the preceding aspects.

[0040] The technical solutions provided by the embodiments of the present disclosure at least have the following beneficial effects:

[0041] In some or related embodiments, by acquiring a first fault error code; in the case that the fault error code library does not include the first fault error code, using a target extreme gradient boosting tree XGBoost classification algorithm model to perform fault root cause bounding on the first fault error code, to acquire first error code bounding information corresponding to the first fault error code; according to the first error code bounding information, sending a fault work order corresponding to the first fault error code to a target terminal. Therefore, the target extreme gradient boosting tree XGBoost classification algorithm model can be used to perform fault root cause bounding on the fault error code, which can reduce the situation that the electronic work order pipeline operation mode leads to a high fault probability of the work order process, can reduce the situation that the fault work order is stuck, and does not require manual work order sending, reduces the manual processing cost, reduces the processing time of the fault work order, reduces the time length of the task in the fault state, can reduce the fault probability of the work order process while improving the fault processing efficiency.

[0042] It should be understood that the foregoing general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. BRIEF DESCRIPTION OF DRAWINGS

[0043] The accompanying drawings, which are incorporated into and form part of the specification, illustrate embodiments consistent with the present disclosure and, together with the specification, serve to explain the principles of the present disclosure, and do not constitute an undue limitation on the present disclosure.

[0044] Figure 1 is a background schematic diagram of a work order sending method according to an exemplary embodiment;

[0045] Figure 2 is a flowchart of a work order sending method according to an exemplary embodiment;

[0046] Figure 3 is a flowchart of a work order sending method according to an exemplary embodiment;

[0047] Figure 4 is a block diagram of a work order sending device according to an exemplary embodiment;

[0048] Figure 5 is a block diagram of a network device according to an exemplary embodiment. DETAILED DESCRIPTION

[0049] In order for those skilled in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the drawings.

[0050] The present disclosure provides a work order sending method and device. In some embodiments, the work order sending method, information processing method, and communication method can be replaced with each other, the work order sending device, information processing device, and communication device can be replaced with each other, and the information processing system and communication system can be replaced with each other.

[0051] The embodiments of the present disclosure are not exhaustive, but only illustrate some embodiments, and are not specific limitations on the protection scope of the present disclosure. In the case of no contradiction, each step in an embodiment can be implemented as an independent embodiment, and the steps can be combined arbitrarily, for example, the scheme after removing some steps in an embodiment can be implemented as an independent embodiment, and the order of the steps in an embodiment can be exchanged arbitrarily, in addition, the optional implementation manners in an embodiment can be combined arbitrarily; in addition, the embodiments can be combined arbitrarily, for example, the steps of different embodiments or some or all steps of different embodiments can be combined arbitrarily, an embodiment can be combined with the optional implementation manners of other embodiments.

[0052] In the embodiments of the present disclosure, the terms and / or descriptions of the embodiments are consistent and can be referred to each other if there is no special description and logical conflict, and the technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationship.

[0053] The terms used in the embodiments of the present disclosure are only for the purpose of describing the specific embodiments, and not as a limitation on the present disclosure.

[0054] In the embodiments of the present disclosure, unless otherwise specified, the elements expressed in singular form, such as “one”, “a”, “the”, “above”, “said”, “preceding”, “this” and the like, can represent “one and only one”, or “one or more”, “at least one” and the like. For example, in the case of using articles such as “a”, “an”, “the” and the like in English, the noun after the article can be understood as singular expression, or can be understood as plural expression.

[0055] In the embodiments of the present disclosure, “a plurality of” means two or more.

[0056] In some embodiments, the terms “at least one of,” “one or more of,” “a plurality of,” “multiple,” and the like can be used interchangeably.

[0057] The prefix words “first,” “second,” and the like in the embodiments of the present disclosure are merely used to distinguish different description objects, and do not constitute a limitation on the position, order, priority, quantity, or content of the description objects. The description of the description objects should refer to the description in the claims or embodiments, and should not constitute an additional limitation because of the use of the prefix words. For example, the description objects are “fields,” and the ordinal words before “fields” in “first field” and “second field” do not limit the position or order between “fields.” “First” and “second” do not limit whether the “fields” modified thereby are in the same message, nor do they limit the order of “first field” and “second field.” For another example, the description objects are “levels,” and the ordinal words before “levels” in “first level” and “second level” do not limit the priority between “levels.” For another example, the quantity of the description objects is not limited by the ordinal words, and can be one or more. For example, “first device,” where the quantity of “devices” can be one or more. In addition, the objects modified by different prefix words can be the same or different, for example, the description objects are “devices,” and “first device” and “second device” can be the same device or different devices, and their types can be the same or different. For another example, the description objects are “information,” and “first information” and “second information” can be the same information or different information, and their contents can be the same or different.

[0058] In some embodiments, a "terminal" or "terminal device" can be referred to as a "user equipment" (UE), a "user terminal," a "mobile station" (MS), a "mobile terminal" (MT), a subscriber station, a mobile unit, a subscriber unit, a wireless unit, a remote unit, a mobile device, a wireless device, a wireless communication device, a remote device, a mobile subscriber station, an access terminal, a mobile terminal, a wireless terminal, a remote terminal, a handset, a user agent, a mobile client, a client, etc.

[0059] In some embodiments, data, information, etc. can be acquired after getting user consent.

[0060] It should be noted that the terms "first", "second", and the like in the description and in the claims of the present disclosure and above-described figures are used to distinguish similar objects and are not necessarily used to describe a specific sequential or chronological order. It should be understood that the data thus used can be interchanged, where appropriate, so that the embodiments of the present disclosure described herein can be carried out in sequences other than those illustrated or described herein. The implementations described in the following example embodiments do not represent all implementations consistent with the present disclosure. Instead, they are merely examples of apparatuses and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0061] According to some embodiments, Figure 1 A background schematic diagram of work order sending is shown. As shown in Figure 1 5G private network service opening is a long process work order task involving multiple departments and multiple specialties, and as shown in Figure 1As shown, the 5G private network work order activation adopts the conventional electronic work order pipeline operation method. Each step of the work order activation follows the pre-set process steps 1 to 9. However, during the automatic operation and flow of the system, process failures are prone to occur, resulting in work order flow interruption, timeouts in 5G private network work order activation, and reduced customer satisfaction.

[0062] Figure 2 This is a flowchart illustrating a work order sending method according to an exemplary embodiment, such as... Figure 2 As shown, this work order sending method can be used in work order sending scenarios, and includes the following steps:

[0063] In step S11, the first fault error code is obtained;

[0064] According to some embodiments, the technical solutions of this disclosure can be applied to the field of communication technology, specifically wireless communication, vertical industries, and work order operation and maintenance management technology. The executing entity of this disclosure can be, for example, a network device. The name of the network device is not limited. For example, the network device can be a server. This disclosure does not limit this.

[0065] In some embodiments, an error code refers to an error code corresponding to a specific fault. Different faults may correspond to different error codes. The term "first" in "first fault error code" is used to distinguish it from other fault error codes and does not specifically refer to a fixed fault error code. For example, the fault error code may change accordingly when the system fault changes.

[0066] According to some embodiments, a first fault error code can be obtained when executing the work order sending method.

[0067] In step S12, if the fault error code is not included in the fault error code library, the target extreme gradient boosting tree XGBoost classification algorithm model is used to perform fault root cause delimitation on the first fault error code to obtain the first error code definition information corresponding to the first fault error code.

[0068] According to some embodiments, the fault error code library may include, for example, at least one fault error code. This at least one fault error code may be established from known fault error codes and known processing suggestions from historical work orders. The known processing suggestions may include, for example, suggestions on how to process historical work orders, or processing strategies on which terminal to send historical work orders to. This disclosure does not limit this aspect.

[0069] In some embodiments, the target eXtreme Gradient Boosting (XGBoost) classification algorithm model can be trained and can be a model for fault root cause definition. The target XGBoost classification algorithm model is not a fixed model. For example, when the training data changes, the target XGBoost classification algorithm model can also change accordingly. For example, when a parameter in the model changes, the target XGBoost classification algorithm model can also change accordingly.

[0070] According to some embodiments, fault root cause definition can refer to determining the root cause corresponding to a fault. The disclosure is an embodiment of fault root cause definition, for example, determining a target terminal corresponding to a fault, and the target terminal processes the fault.

[0071] In some embodiments, the first error code definition information in the first error code definition information is used to distinguish from the remaining error code definition information, and is not a fixed error code definition information. For example, when the first fault error code changes, the first error code definition information can also change accordingly. For example, when the target XGBoost classification algorithm model changes, that is, the fault root cause definition method changes, the first error code definition information can also change accordingly.

[0072] According to some embodiments, in the case that the fault error code is not included in the fault error code library, the target eXtreme Gradient Boosting (XGBoost) classification algorithm model is used to perform fault root cause definition on the first fault error code, and first error code definition information corresponding to the first fault error code is obtained.

[0073] In step S13, according to the first error code definition information, a fault work order corresponding to the first fault error code is sent to a target terminal.

[0074] In some embodiments, the fault work order refers to a work order corresponding to the first fault error code. The fault work order is not a fixed work order, for example, when the fault work order generation time changes, the fault work order can also change accordingly. For example, when the first fault error code changes, the fault work order can also change accordingly. The fault work order can be a 5G private network work order.

[0075] According to some embodiments, the target terminal refers to a receiving terminal of the fault work order, and the target terminal can process the fault corresponding to the first fault error code according to the fault work order. The target terminal is not a fixed terminal, for example, when the terminal identifier corresponding to the terminal changes, the target terminal can also change accordingly.

[0076] In some embodiments, the first fault error code corresponding fault work order can be sent to the target terminal according to the first error code definition information.

[0077] In some or related embodiments, by acquiring a first fault error code, if the fault error code is not included in the fault error code library, a target extreme gradient boosting tree XGBoost classification algorithm model is used to perform fault root cause definition on the first fault error code, to acquire first error code definition information corresponding to the first fault error code; and according to the first error code definition information, the first fault error code corresponding fault work order is sent to the target terminal. Therefore, the target extreme gradient boosting tree XGBoost classification algorithm model can be used to perform fault root cause definition on the fault error code, which can reduce the high probability of work order process failure caused by electronic work order pipeline operation mode, reduce the fault work order card situation, and does not require manual work order sending, reducing manual processing cost, reducing fault work order processing time, reducing the time of tasks in a fault state, and reducing the probability of work order process failure while improving fault processing efficiency.

[0078] Figure 3 is a flow chart of a work order sending method according to an exemplary embodiment, as shown in Figure 3 The work order sending method can be used in a work order sending scenario, including the following steps:

[0079] In step S21, the acquired historical fault processing work order and fault error log information are preprocessed to obtain a fault sample information set;

[0080] According to some embodiments, historical work order data can be acquired and a basic database can be established, which can specifically include:

[0081] Acquiring 5G private network opening historical work order data: acquiring historical work order data according to 5G private network work order, performing normalization cleaning and warehousing, which can include, for example, the currently defined fault error code information, and establishing an initial fault error code library.

[0082] In some embodiments, fault original error log information is acquired, for example, the respective intelligent production system error log information can be collected and added to the fault error code library.

[0083] In some embodiments, fault work order processing feedback information is acquired, for example, the fault work order processing feedback information can be collected and added to the fault error code library.

[0084] In some embodiments, the fault sample information set may, for example, be a collective formed by aggregation of at least one fault sample information. The fault sample information set does not refer to a fixed set, and may, for example, change accordingly when the amount of information corresponding to the fault sample information set changes. For example, the fault sample information set may also change accordingly when any fault sample information in the fault sample information set changes.

[0085] For example, a fault error code library may be established first, and then the fault sample information set may be obtained from the fault error code library.

[0086] According to some embodiments, historical 5G private network service work order fault error codes, cause positioning and processing suggestions, and other information are used to construct an initial fault error code library for fault rapid matching. For example, the fault error code library may be as shown in Table 1.

[0087] Table 1

[0088]

[0089] In some embodiments, the preprocessing includes, but is not limited to, data cleaning, format processing, and other preprocessing. The format processing may, for example, be to unify the format to a preset format. The preprocessing may process the data into a form that can be processed by an algorithm.

[0090] The fault sample information set includes processed fault error log information, and the data preprocessing of the obtained fault error log information to obtain the fault sample information set includes:

[0091] In the case where the fault error log information is text information, the fault error log information is processed by text vectorization using Term Frequency-Inverse Document Frequency (Tf-idf), and a keyword set is obtained according to keyword selection requirements;

[0092] Any keyword in the keyword set is digitally mapped to obtain a digital mapping table corresponding to the keyword, and the digital mapping table is taken as the fault sample information set.

[0093] According to some embodiments, in the preprocessing process of fault error log information, the error log data may, for example, be text data composed of a timestamp, an error code, and a text message. Tf-idf may be used for text vectorization calculation, and a number of keywords may be selected in descending order so that the text data is converted into numerical data.

[0094] In the input information, the Tf-idf corresponding table may, for example, be as shown in Table 2.

[0095] Table 2

[0096]

[0097] In step S22, the XGBoost operation is performed on the set of fault sample information to obtain a target extreme gradient boosting tree XGBoost classification algorithm model.

[0098] According to some embodiments, when the set of fault sample information is obtained, the XGBoost operation is performed on the set of fault sample information to obtain a target extreme gradient boosting tree XGBoost classification algorithm model.

[0099] In some embodiments, the XGBoost machine learning algorithm can be used to construct a fault root cause bounding model. The XGBoost algorithm is an ensemble learning algorithm based on decision trees, which generates multiple weak learners (decision trees) through iteration to cumulatively establish a strong learner, and has high accuracy and good interpretability.

[0100] The error log keywords (input values) may, for example, include interface name, error code name, error code belonging system, and error code meaning description, and the Tf-idf mapping may, for example, be as shown in Tables 3-5. Table 3 may, for example, be a table for numerically mapping interface name features, Table 4 may, for example, be a table for numerically mapping error code name features, and Table 5 may, for example, be a table for numerically mapping error code belonging system features. Specifically:

[0101] Table 3

[0102]

[0103] Table 4

[0104]

[0105] Table 5

[0106]

[0107]

[0108] According to some embodiments, the error code meaning description features may, for example, be numerically mapped, specifically including: according to the “error code meaning” field in the initial fault error code library, the appeared reasons are classified, and 33 contents such as data format error, missing required parameter, network or opposite system exception, and system execution exception have been sorted out. In order to cooperate with machine learning and operation, the 33 known reasons are numerically mapped, and the mapping values are 1, 2, 3, …, 32, and 33 in turn.

[0109] According to some embodiments, the XGBoost operation is performed on the set of fault sample information to obtain a target extreme gradient boosting tree XGBoost classification algorithm model, including:

[0110] The XGBoost operation is performed on the processed fault handling order and the processed fault error log information to obtain an initial extreme gradient boosting tree XGBoost classification algorithm model.

[0111] The second fault error code of the fault error log information is calculated using the initial extreme gradient boosting tree XGBoost classification algorithm model to obtain second error code definition information corresponding to the second fault error code.

[0112] In the case where the confirmation instruction for the second error code definition information is received, it is determined that the target extreme gradient boosting tree XGBoost classification algorithm model is obtained.

[0113] According to some embodiments, the XGBoost operation is performed on the set of fault sample information to obtain a target extreme gradient boosting tree XGBoost classification algorithm model, including:

[0114] The prediction value of the prediction boundary of the first t classification and regression tree CARTs and the prediction value of the prediction boundary of the t classification and regression tree CART are obtained from the i-1th fault sample information in the set of fault sample information, where i is a positive integer.

[0115] The target function is obtained according to the prediction value of the prediction boundary of the first t classification and regression tree CARTs and the prediction value of the prediction boundary of the t classification and regression tree CART from the i-1th fault sample information.

[0116] The parameterized operation is performed on the target function to obtain a target extreme gradient boosting tree XGBoost classification algorithm model.

[0117] According to some embodiments, the XGBoost operation is performed on the processed fault handling order and the processed fault error log information. XGBoost is a CARTs series sequence using boosting integration. Since the error information classification is a categorical variable, the classification tree in CART is used here. The CART classification tree sequence is as follows:

[0118]

[0119] wherein, f represents the prediction value of the prediction bound of the ith fault event sample, i.e., the error code bound, assigned system value; f represents the prediction value of the prediction bound of the tth CART. t (x i ) represents the prediction value of the prediction bound of the tth CART.

[0120] Then the objective function is constructed, which is composed of a loss function part and a regularization part, and the formula is as follows:

[0121]

[0122] Wherein, is the loss function part, is the regularization part; Ω(f k ) represents the complexity of the kth CART.

[0123] Parameterize the above formula, and finally obtain the following equation:

[0124]

[0125] Wherein, parameters G j and H j are as follows:

[0126]

[0127] Finally, the objective function is derived with respect to the leaf score, and the first order derivative is set to 0, to obtain:

[0128]

[0129] Wherein, is the best weight score, obj * is the minimum value of the objective function under the best weight score. Through the above objective function, the new branch after each split can be evaluated, and the optimal branch can be found.

[0130] All branches of all features are traversed, and the node with the maximum information gain is selected for branching. For a single leaf node, the structure score difference after branching is as follows:

[0131]

[0132] Wherein, G split represents the structure score difference, which is the information gain after splitting into left and right branches; G L represents the left node G value, G R represents the right node G value, H L represents the left node H value, H R represents the right node H value.

[0133] According to some embodiments, a fault error code boundary including confidence information can be output, for example, as shown in Table 6.

[0134] Table 6

[0135]

[0136]

[0137] For example, the "error code name", "fault description", "treatment measures", "fault root cause classification" can be selected by type through the table. If there is no corresponding type in the table, a filling instruction can be received and filled according to the filling instruction. If the content format of the filling instruction is inconsistent, an expert-level operation and maintenance personnel can refine and arrange it into a standard table to ensure accuracy and standardization. Therefore, the artificial experience and system rules can be decoupled to improve the self-intelligence level. Without manual analysis, time and effort can be saved, costs can be saved, time limits can be reduced, and opening efficiency can be improved. The decentralized system can be centralized controlled.

[0138] According to some embodiments, through the above process of continuously collecting data, retraining the model, and optimizing the algorithm, a fault error code boundary list with a confidence greater than or equal to 0.8 (configurable) is finally screened, and those that can be included in the "fault error code library" table are evaluated, and the fault error code library is continuously optimized and improved.

[0139] According to some embodiments, the fault error code boundary and the content of the "assignment system" field output by the fault error code library and the target XGBoost algorithm are logically judged to determine the error code boundary information corresponding to the fault error code, and the system sends a fault work order to the target terminal.

[0140] In step S23, a first fault error code is obtained.

[0141] The specific process is as described above, which will not be repeated here.

[0142] According to some embodiments, the technical solutions of the embodiments of the present disclosure can be applied to the definition of 5G private network work orders.

[0143] In step S24, if the fault error code is not included in the fault error code library, a target extreme gradient boosting tree XGBoost classification algorithm model is used to perform fault root cause boundary on the first fault error code, and first error code boundary information corresponding to the first fault error code is obtained.

[0144] The specific process is as described above, which will not be repeated here.

[0145] In step S25, according to the first error code definition information, the fault work order corresponding to the first fault error code is sent to the target terminal.

[0146] The specific process is as described above, which will not be repeated here.

[0147] In the case where the confidence degree is less than the confidence degree threshold, the “one-ticket” function can be started, and the target terminal corresponding to the fault work order can be determined through the received selection instruction or the input information, so as to reduce the processing time of the fault work order and improve the timeliness of the fault work order processing.

[0148] In step S26, in the case where the first fault error code is included in the fault error code library, third error code definition information corresponding to the first fault error code is obtained.

[0149] According to some embodiments, the third error code definition information may, for example, be error code definition information determined in the case where the first fault error code is included in the fault error code library. The third error code definition information is not specific to a fixed information, and the third error code definition information is distinguished from the rest of the error code definition information. For example, when the first fault error code changes, the third error code definition information can also change accordingly.

[0150] In some embodiments, when the first error code is obtained, it can be determined whether the first fault error code is included in the fault error code library. In the case where the first fault error code is included in the fault error code library, third error code definition information corresponding to the first fault error code is obtained. For example, the fault error code library can be pre-set with a correspondence between fault error codes and error code definition information.

[0151] According to some embodiments, in the case where the first fault error code is included in the fault error code library, third error code definition information corresponding to the first fault error code is obtained.

[0152] In step S27, according to the third error code definition information, the fault work order corresponding to the first fault error code is assigned to the target terminal.

[0153] According to some embodiments, according to the third error code definition information, the fault work order corresponding to the first fault error code can be assigned to the target terminal.

[0154] According to some embodiments, the method further comprises:

[0155] Obtaining a confidence degree corresponding to the first error code definition information;

[0156] In a case where the confidence is less than a confidence threshold, a short message information is sent to the target terminal, wherein the short message information comprises a fault work order corresponding to the first fault error code;

[0157] In a case where the confidence is greater than the confidence threshold, the fault error code library is updated using the first fault error code and the first error code boundary information, to obtain an updated fault error code library.

[0158] The manner of the process of sending to the target terminal is not limited. For example, the fault work order can be sent to the target terminal through a short message. For example, the fault work order can be sent to the target terminal in a voice manner.

[0159] In some or related embodiments, the obtained historical fault processing work order and fault error log information are subjected to data preprocessing to obtain a fault sample information set; the target extreme gradient boosting tree XGBoost classification algorithm model is obtained by performing XGBoost operation using the fault sample information set. The target XGBoost classification algorithm model can be obtained by training, which can improve the accuracy of the XGBoost classification algorithm model and improve the accuracy of fault root cause boundary determination. The target extreme gradient boosting tree XGBoost classification algorithm model can determine the fault root cause of the fault error code, which can reduce the high fault probability of the electronic work order flow line operation mode, reduce the fault work order carding situation, and does not require manual work order sending, thereby reducing the manual processing cost, reducing the fault work order processing time, reducing the time of the task in the fault state, and improving the fault processing efficiency while reducing the work order flow fault probability. Secondly, in a case where the first fault error code is included in the fault error code library, third error code boundary information corresponding to the first fault error code is obtained; and the fault work order corresponding to the first fault error code is dispatched to the target terminal according to the third error code boundary information, which can directly send the fault work order and reduce the determination time of the error code boundary information, thereby improving the fault processing efficiency.

[0160] Figure 4 is a block diagram of a work order sending device according to an exemplary embodiment. Referring to Figure 4 The device 400 comprises:

[0161] An error code acquisition unit 401 is configured to acquire a first fault error code.

[0162] An information acquisition unit 402 is configured to, in a case where the fault error code is not included in the fault error code library, determine a fault root cause of the first fault error code using a target extreme gradient boosting tree XGBoost classification algorithm model, and acquire first error code boundary information corresponding to the first fault error code.

[0163] The work order sending unit 403 is configured to send a fault work order corresponding to the first error code to a target terminal according to the first error code boundary information.

[0164] According to some embodiments, the information acquisition unit 402 is further specifically configured to:

[0165] perform data preprocessing on the acquired historical fault processing work order and fault error log information to obtain a fault sample information set;

[0166] perform XGBoost operation on the fault sample information set to obtain a target extreme gradient boosting tree XGBoost classification algorithm model.

[0167] According to some embodiments, the fault sample information set includes the processed fault error log information, and the information acquisition unit 402, when performing data preprocessing on the acquired fault error log information to obtain a fault sample information set, is specifically configured to:

[0168] when the fault error log information is text information, perform text vectorization processing on the fault error log information by using term frequency-inverse document frequency, and obtain a keyword set according to keyword selection requirements;

[0169] perform digital mapping on any keyword in the keyword set to obtain a digital mapping table corresponding to the any keyword, and use the digital mapping table as the fault sample information set.

[0170] According to some embodiments, the information acquisition unit 402, when performing XGBoost operation on the fault sample information set to obtain a target extreme gradient boosting tree XGBoost classification algorithm model, is specifically configured to:

[0171] perform XGBoost operation on the processed fault processing work order and the processed fault error log information to obtain an initial extreme gradient boosting tree XGBoost classification algorithm model;

[0172] perform calculation on a second fault error code of the fault error log information by using the initial extreme gradient boosting tree XGBoost classification algorithm model to obtain second error code boundary information corresponding to the second fault error code;

[0173] when a confirmation instruction for the second error code boundary information is received, determine that a target extreme gradient boosting tree XGBoost classification algorithm model is obtained.

[0174] According to some embodiments, the information obtaining unit 402 is configured to perform XGBoost operation on the set of failure sample information to obtain a target eXtreme Gradient Boosting Tree (XGBoost) classification algorithm model, and is specifically configured to:

[0175] obtain a predicted value of a prediction bound of a tth classification and regression tree (CART) before an (i-1)th failure sample information in the set of failure sample information and a predicted value of a prediction bound of a (t+1)th CART;

[0176] obtain a target function according to the predicted value of the prediction bound of the tth CART before the (i-1)th failure sample information and the predicted value of the prediction bound of the (t+1)th CART;

[0177] perform parameterization operation on the target function to obtain the target eXtreme Gradient Boosting Tree (XGBoost) classification algorithm model.

[0178] According to some embodiments, the work order sending unit 403 is further configured to:

[0179] in a case where the first failure error code is included in the failure error code library, obtain third error code bound information corresponding to the first failure error code;

[0180] send a failure work order corresponding to the first failure error code to a target terminal according to the third error code bound information.

[0181] According to some embodiments, the work order sending unit 403 is further configured to:

[0182] obtain a confidence degree corresponding to the first error code bound information;

[0183] in a case where the confidence degree is less than a confidence degree threshold, send a short message information to the target terminal, wherein the short message information includes a failure work order corresponding to the first failure error code;

[0184] in a case where the confidence degree is greater than the confidence degree threshold, update the failure error code library by using the first failure error code and the first error code bound information to obtain an updated failure error code library.

[0185] As to the apparatus in the above embodiments, the specific manners in which various modules perform operations have been described in details in the embodiments of the method, and will not be described in details here.

[0186] In some or related embodiments, by an error code acquisition unit, a first fault error code is acquired; an information acquisition unit is configured to, in the case that the fault error code library does not include the fault error code, perform fault root cause bounding on the first fault error code by using an extreme gradient boosting tree XGBoost classification algorithm model, and acquire first error code bounding information corresponding to the first fault error code; and a work order sending unit is configured to send a fault work order corresponding to the first fault error code to a target terminal according to the first error code bounding information. Therefore, the fault root cause of the fault error code can be bounded by the extreme gradient boosting tree XGBoost classification algorithm model, the situation that the work order process fault probability is high due to the electronic work order flow line operation mode can be reduced, the situation that the fault work order is stuck can be reduced, manual work order sending is not required, the manual processing cost is reduced, the fault work order processing time is reduced, the time that the task is in a fault state is reduced, the fault processing efficiency can be improved while the work order process fault probability is reduced.

[0187] Figure 5 is a block diagram of a network device 500 provided by an embodiment of the present disclosure. For example, the network device 500 can be provided as a network device. Referring to Figure 5 , the network device 500 includes a processing component 522, which further includes at least one processor, and a memory resource represented by a memory 532, for storing instructions executable by the processing component 522, such as an application program. The application program stored in the memory 532 can include one or more than one module each corresponding to a set of instructions. In addition, the processing component 522 is configured to execute the instructions to perform any method of the above-described method or the application program on the network device.

[0188] The network device 500 can also include a power supply component 527 configured to perform power management of the network device 500, a wired or wireless network interface 550 configured to connect the network device 500 to a network, and an input / output (I / O) interface 558. The network device 500 can operate based on an operating system stored in the memory 532, such as Windows Server TM, Mac OS X TM, Unix TM, Linux TM, Free BSD TM or the like.

[0189] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, specially designed application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0190] Program code for carrying out methods of the present disclosure can be written in any combination of one or more programming languages. This program code can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the program code, when executed by the processor or controller, produces a means for implementing the functions / acts specified in the flowcharts and / or block diagrams. The program code can be executed entirely on a machine, partially on a machine, partially on a machine and partially on a remote machine or entirely on a remote machine or server.

[0191] In the context of the present disclosure, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can 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. More specific examples of the machine-readable storage medium will include one or more lines of electrical connections, portable computer disks, hard disk drives, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or Flash memory), optical fibers, portable compact disc read-only memories (CD-ROMs), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0192] To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; 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 can be received in any form, including acoustic, speech, or tactile input.

[0193] 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 a local area network (LAN), a wide area network (WAN), the Internet, and a blockchain network.

[0194] The computer system can 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. A server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system, to solve the defects of large management difficulty and weak business scalability in traditional physical host and VPS service ("Virtual Private Server", or simply "VPS"). The server can also be a server of a distributed system, or a server combined with a blockchain.

[0195] It should be understood that various forms of flow shown above can be used, with steps reordered, added, or removed. For example, the steps recited in the present disclosure can be performed in parallel, in series, or in a different order, without limitation herein, as long as the desired results of the technical solutions of the present disclosure can be achieved.

[0196] The above detailed description does not limit the scope of the disclosure. Various modifications, combinations, sub-combinations and alternatives can be made to the detailed description. Any modification, equivalent replacement and improvement etc. made within the spirit and principle of the disclosure shall be included in the scope of the disclosure.

Claims

1. A work order sending method, characterized by, The method comprises: acquiring a first fault error code; in the case that the fault error code is not included in a fault error code library, using an extreme gradient boosting tree XGBoost classification algorithm model to perform fault root cause bounding on the first fault error code, and acquiring first error code bounding information corresponding to the first fault error code; according to the first error code bounding information, sending a fault work order corresponding to the first fault error code to a target terminal; wherein the method further comprises: using a fault sample information set to perform XGBoost operation to obtain a target extreme gradient boosting tree XGBoost classification algorithm model; wherein the using the fault sample information set to perform XGBoost operation to obtain the target extreme gradient boosting tree XGBoost classification algorithm model comprises: using the processed error sending processing work order and the processed fault error log information to perform XGBoost operation to obtain an initial extreme gradient boosting tree XGBoost classification algorithm model; using the initial extreme gradient boosting tree XGBoost classification algorithm model to perform calculation on a second fault error code of the fault error log information, and acquiring second error code bounding information corresponding to the second fault error code; in the case that a confirmation instruction for the second error code bounding information is received, it is determined that a target extreme gradient boosting tree XGBoost classification algorithm model is obtained; wherein the using the fault sample information set to perform XGBoost operation to obtain the target extreme gradient boosting tree XGBoost classification algorithm model comprises: acquiring a prediction value of a prediction bound of a first (i-1)th fault sample information of the fault sample information set and a prediction value of a prediction bound of a first (i)th fault sample information, wherein i is a positive integer; according to the prediction value of the prediction bound of the first (i-1)th fault sample information and the prediction value of the prediction bound of the first (i)th fault sample information, a target function is acquired; performing parameterized operation on the target function to obtain a target extreme gradient boosting tree XGBoost classification algorithm model.

2. The method of claim 1, wherein, The method further comprises: performing data preprocessing on the acquired historical error sending processing work order and fault error log information to obtain the fault sample information set.

3. The method of claim 2, wherein, wherein the fault sample information set comprises processed fault error log information, and the performing data preprocessing on the acquired fault error log information to obtain the fault sample information set comprises: in the case that the fault error log information is text information, using term frequency-inverse document frequency to perform text vectorization processing on the fault error log information, and acquiring a keyword set according to keyword selection requirements; performing digital mapping on any keyword in the keyword set to obtain a digital mapping table corresponding to the any keyword, and taking the digital mapping table as the fault sample information set.

4. The method of claim 1, wherein, The method further comprises: In a case where the first fault error code is included in the fault error code library, third error code definition information corresponding to the first fault error code is acquired; According to the third error code definition information, a fault work order corresponding to the first fault error code is sent to a target terminal.

5. The method of claim 1, wherein, The method further includes: acquiring a confidence degree corresponding to the first error code definition information; in a case where the confidence degree is less than a confidence degree threshold, sending a short message information to the target terminal, wherein the short message information includes a fault work order corresponding to the first fault error code; in a case where the confidence degree is greater than the confidence degree threshold, updating the fault error code library by using the first fault error code and the first error code definition information to obtain an updated fault error code library.

6. A work order sending apparatus characterized by comprising: includes: an error code acquisition unit configured to acquire a first fault error code; an information acquisition unit configured to, in a case where the fault error code is not included in a fault error code library, perform fault root cause definition on the first fault error code by using a target extreme gradient boosting tree XGBoost classification algorithm model to acquire first error code definition information corresponding to the first fault error code; a work order sending unit configured to, according to the first error code definition information, send a fault work order corresponding to the first fault error code to a target terminal; wherein the information acquisition unit is further configured to: perform XGBoost operation by using a fault sample information set to obtain a target extreme gradient boosting tree XGBoost classification algorithm model; wherein, when the information acquisition unit is configured to perform XGBoost operation by using the fault sample information set to obtain a target extreme gradient boosting tree XGBoost classification algorithm model, it is specifically configured to: perform XGBoost operation by using the processed error sending processing work order and the processed fault error log information to obtain an initial extreme gradient boosting tree XGBoost classification algorithm model; perform calculation on a second fault error code of the fault error log information by using the initial extreme gradient boosting tree XGBoost classification algorithm model to acquire second error code definition information corresponding to the second fault error code; in a case where a confirmation instruction for the second error code definition information is received, it is determined that a target extreme gradient boosting tree XGBoost classification algorithm model is acquired; wherein, when the information acquisition unit is configured to perform XGBoost operation by using the fault sample information set to obtain a target extreme gradient boosting tree XGBoost classification algorithm model, it is specifically configured to: acquire a prediction value of prediction definition of a first (i-1)th fault sample information of the fault sample information set and a prediction value of prediction definition of a first (i)th fault sample information, wherein i is a positive integer; acquire a target function according to the prediction value of prediction definition of the first (i-1)th fault sample information and the prediction value of prediction definition of the first (i)th fault sample information; The target function is subjected to a parameterization operation to obtain a target extreme gradient boosting tree XGBoost classification algorithm model.

7. A network device, comprising: Comprise: a processor; a memory for storing instructions executable by the processor; wherein the processor is configured to execute the instructions to implement the work order sending method of any one of claims 1 to 5.

8. A storage medium, the storage medium storing instructions, wherein, When the instructions run on a communication device, the communication device is caused to perform the work order sending method of any one of claims 1 to 5.

Images