Data processing method and device, electronic equipment and storage medium

Abstract

The application provides a data processing method and device, electronic equipment and storage medium, wherein the method comprises the following steps: constructing a first knowledge graph based on case entities extracted from first work order data of a first fault; constructing a second knowledge graph based on case entities extracted from behavior data of each processing stage of the first fault; then, performing keyword extraction and screening on case summary entities in the first knowledge graph, so as to determine a first fault type corresponding to the first fault based on the screened keywords; then, adding a type entity in the first knowledge graph based on the first fault type, and associating the first knowledge graph and the second knowledge graph based on a question number entity, so as to generate a historical knowledge graph corresponding to the first fault. The fault behavior data and the fault work order data are standardized, and the readability of the fault data is improved. High-quality data support is provided for identifying fault reasons and mining optimal network fault solutions.

Description

Technical Field

[0001] This application relates to the field of communication technology, and in particular to a data processing method, apparatus, electronic device and storage medium. Background Technology

[0002] In large-scale networks, due to the complexity of network failure causes, the lack of standardized problem descriptions in wireless network work orders, and the disorganized data across the entire business process, it is difficult to extract effective data information from network failure work orders and troubleshooting records, making it difficult to accurately identify the cause of the failure.

[0003] Therefore, there is an urgent need for a data processing method to obtain standardized and highly readable network fault-related data. Summary of the Invention

[0004] This application aims to at least partially address one of the technical problems in the related art.

[0005] Therefore, the first objective of this application is to propose a data processing method to improve the readability of fault-related data.

[0006] The second objective of this application is to provide a data processing apparatus.

[0007] The third objective of this application is to propose an electronic device.

[0008] The fourth objective of this application is to provide a computer-readable storage medium.

[0009] The fifth objective of this application is to provide a computer program product.

[0010] To achieve the above objectives, a data processing method is proposed in the first aspect of this application, comprising:

[0011] A first knowledge graph is constructed based on case entities extracted from the first work order data of the first fault, and a second knowledge graph is constructed based on case entities extracted from the behavioral data of each processing stage of the first fault. The second knowledge graph is the same as or related to the problem number entity in the first knowledge graph.

[0012] Keyword extraction and filtering are performed on the case summary entity in the first knowledge graph to determine the first fault type corresponding to the first fault based on the filtered keywords. After adding the type entity based on the first fault type in the first knowledge graph, the first knowledge graph and the second knowledge graph are associated based on the question number entity to generate the historical knowledge graph corresponding to the first fault.

[0013] To achieve the above objectives, a second aspect of this application provides a data processing apparatus, comprising:

[0014] The module is used to construct a first knowledge graph based on case entities extracted from the first work order data of the first fault, and to construct a second knowledge graph based on case entities extracted from the behavioral data of each processing stage of the first fault, wherein the second knowledge graph is the same as or related to the problem number entity in the first knowledge graph.

[0015] The determination module is used to extract and filter keywords from the problem description entities in the first knowledge graph, so as to determine the first fault type corresponding to the first fault based on the filtered keywords.

[0016] The generation module is used to add a type entity to the first knowledge graph based on the first fault type, and then associate the first knowledge graph and the second knowledge graph based on the question number entity to generate a historical knowledge graph corresponding to the first fault.

[0017] To achieve the above objectives, a third aspect of this application provides an electronic device comprising:

[0018] At least one processor; and

[0019] A memory that is communicatively connected to at least one processor; wherein,

[0020] The memory stores instructions that can be executed by at least one processor, which enables the at least one processor to perform the methods of the above embodiments.

[0021] To achieve the above objectives, a fourth aspect of this application provides a computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to perform the method according to the above embodiments.

[0022] To achieve the above objectives, a fifth aspect of this application provides a computer program product, including a computer program that, when executed by a processor, implements the methods of the above embodiments.

[0023] The data processing method, apparatus, electronic device, and storage medium provided in this application construct a first knowledge graph based on case entities extracted from the first work order data of the first fault, and a second knowledge graph based on case entities extracted from the behavioral data of each processing stage of the first fault. The second knowledge graph is identical to or related to the issue number entity in the first knowledge graph. Then, keyword extraction and filtering are performed on the case summary entity in the first knowledge graph to determine the first fault type corresponding to the first fault based on the filtered keywords. Next, a type entity is added to the first knowledge graph based on the first fault type. Finally, the first and second knowledge graphs are linked based on the issue number entity to generate a historical knowledge graph corresponding to the first fault. Thus, fault work order data, behavioral data of each processing stage of the fault, and the relationships between fault work order data and behavioral data are presented in the form of a knowledge graph, standardizing fault behavioral data and fault work order data, and improving the readability of fault data. This provides high-quality data support for identifying fault causes and discovering optimal network fault solutions.

[0024] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0025] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0026] Figure 1 This is a schematic flowchart illustrating a data processing method provided in an embodiment of this application.

[0027] Figure 2 A schematic diagram of a first knowledge graph provided in an embodiment of this application;

[0028] Figure 3 A schematic diagram of a second knowledge graph corresponding to data query behavior data provided in an embodiment of this application;

[0029] Figure 4 A schematic diagram of a second knowledge graph corresponding to data analysis behavioral data provided in an embodiment of this application;

[0030] Figure 5 A schematic diagram of a second knowledge graph corresponding to parameter adjustment behavior data provided in an embodiment of this application;

[0031] Figure 6 A schematic diagram of a second knowledge graph corresponding to evaluation behavior data provided in an embodiment of this application;

[0032] Figure 7A flowchart illustrating another data processing method provided in an embodiment of this application;

[0033] Figure 8 A flowchart illustrating another data processing method provided in an embodiment of this application;

[0034] Figure 9 A flowchart illustrating another data processing method provided in an embodiment of this application;

[0035] Figure 10 This is a schematic diagram of the structure of a data processing device provided in an embodiment of this application. Detailed Implementation

[0036] The embodiments of this application are described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0037] The data processing method and apparatus of embodiments of this application are described below with reference to the accompanying drawings.

[0038] The data processing method of this application embodiment is executed by the data processing device (hereinafter referred to as the optimization device) provided in this application embodiment. The device can be configured in computer equipment or terminal equipment to improve the readability of fault-related data.

[0039] Figure 1 This is a schematic flowchart of a data processing method provided in an embodiment of this application.

[0040] like Figure 1 As shown, the data processing method includes the following steps:

[0041] Step 101: Construct a first knowledge graph based on the case entities extracted from the first work order data of the first fault, and construct a second knowledge graph based on the case entities extracted from the behavioral data of each processing stage of the first fault, wherein the second knowledge graph is the same as or related to the problem number entity in the first knowledge graph.

[0042] The behavioral data includes data query behavior data, data analysis behavior data, parameter adjustment behavior data, and evaluation behavior data. The first fault refers to historical faults reported at a historical time. The attributes corresponding to each case entity include problem level, specialty, case name, case summary, case keywords, case submission time, submission city, and problem discovery method, etc., which are not limited in this application. The specific attribute values ​​corresponding to each case entity can be directly extracted from the first work order data or determined by parsing the first work order data.

[0043] The "Issue Level" describes the issue level to which the content (each case entity) involved in the first work order data belongs. The "Professional Attribute" describes the profession to which the case entity belongs. The "Case Name" describes the name of the first fault. The "Case Summary" describes the key information of the first fault. The "Case Keywords" describes the keywords in the case summary. The "Case Submission Time" describes the submission time of the first fault. The "Submission City" describes the city where the first fault was submitted. In this application, users can create fault work orders in the management platform, which can then acquire and save the fault work order data for maintenance personnel to troubleshoot and handle based on the work order data. During the troubleshooting process, maintenance personnel will also report the processing records and results of each stage of fault handling to the management platform, forming behavioral data for each stage of fault handling.

[0044] The work order data includes a problem number (also known as a work order identifier). This problem number can be any information uniquely identifying a work order, such as a work order number. It can be user-defined or automatically generated by the management platform. The problem number in the behavior data is used to identify the work order data corresponding to the processed fault. The problem number in the behavior data for a given fault and the problem number in the corresponding work order data are the same or related. For example, if a pre-defined character in the problem number in the behavior data is the problem number in the work order data, then the problem number in the work order data is related to the problem number in the behavior data. Alternatively, if multiple faults correspond to the same fault object and fault cause, the problem numbers in the behavior data and the corresponding problem numbers in the work order data for these multiple faults can be related.

[0045] Furthermore, the process of troubleshooting and handling faults by operations and maintenance personnel mainly includes the following stages: fault cause localization, fault repair plan formulation and execution, and fault repair evaluation. The fault cause localization stage further includes the current status query stage and the data analysis stage. The behavioral data generated in the current status query stage is data query behavioral data; the behavioral data generated in the data analysis stage is data analysis behavioral data; the behavioral data generated in the fault repair plan formulation and execution stage is parameter adjustment behavioral data; and the behavioral data generated in the fault repair evaluation stage is evaluation behavioral data.

[0046] In this application, case entities can be extracted from the first work order data of the first fault using an arbitrary entity extraction method. Based on these case entities, an arbitrary knowledge graph construction method is then used to construct a first knowledge graph corresponding to the first work order data. Similarly, case entities are extracted from the behavioral data of each processing stage corresponding to the first fault, and a second knowledge graph corresponding to the behavioral data of each processing stage is generated based on the case entities contained in the behavioral data of each processing stage. Thus, the first work order data and behavioral data are described using a triple representation of entity-relationship-entity or entity-relationship-attribute, thereby achieving a standardized representation of fault-related data.

[0047] The first work order data includes a problem number, problem description information (i.e., a case summary), the faulty object, and the attribute information of the faulty object. The faulty object can be any device that has malfunctioned, etc., and this application does not impose any restrictions on this. Taking the first work order data corresponding to a network fault as an example, the generated first knowledge graph is as follows: Figure 2 As shown. Figure 2 The first knowledge graph shown contains the problem number entity "FJSM100015", the case summary entity "×× City-×× County-×× Coal Mine_5G Low Wireless Connection Rate", the professional entity "Community", the fault object entity "400-00-××", the fault object attribute information entity ("Outdoor", "Urban Road", "Suburban Rural Area", "×× Manufacturer", etc.), and the association relationships between entities or between entities and attributes.

[0048] When troubleshooting, it's necessary to query performance data related to the faulty object to determine the cause of the fault. Therefore, data query behavior data includes information such as the query tools used and the query content. Taking data query behavior data corresponding to network faults as an example, the generated second knowledge graph would look like this: Figure 3 As shown. Figure 3 The second knowledge graph shown includes the issue number entity "FJSM100015", the query tool entity "DataTao", the query module entity "For Performance Parameters-5G-Low Connectivity-Data Acquisition-SQL", the query content entities ("WORK_FRQBAND:700M|KPI_PRBASSNRATEUL:5.24625", "NRCELL_CM; NRCELL_PM_DAY", "Date between '2023-04-14' and '2023-04-17'|NCI='×××-××-×××××-×'"), and the relationships between entities or between entities and attributes. The query content entities include the metrics queried to investigate the cause of a fault when the first fault occurs. The queried metrics can include performance metrics, etc., and this application does not impose any restrictions on this.

[0049] After obtaining the status data of the faulty object, fault diagnosis tools can be used to analyze the status data and determine the cause of the fault. Therefore, data analysis behavioral data includes information such as fault diagnosis tools, data input into the diagnostic tools, and the fault causes output by the diagnostic tools. Taking data analysis behavioral data corresponding to network faults as an example, the generated second knowledge graph would look like this: Figure 4 As shown. Figure 4 The second knowledge graph shown contains the problem number entity "FJSM100015", the fault diagnosis tool entity "fault cause location tool", the input data entity "coverage type: outdoor | coverage scenario: urban road | operating frequency band: 700M | KPI_PRBASSNRATEUL:5.24625 | KPI_PRBASSNRATEDL:7.43985 | CDFG_RATE:15.2678", the fault cause entity "over-coverage - over-distance access_TA", and the relationships between the entities.

[0050] After determining the cause of the fault, maintenance personnel can use their experience to determine the optimization parameters needed to repair the fault and the corrected values ​​for those parameters, and then execute the corrections to fix the fault. Therefore, the parameter adjustment behavior data includes the optimization parameters, the original values ​​of the optimization parameters before correction, and the corrected values ​​after correction. Taking the parameter adjustment behavior data corresponding to a network fault as an example, the generated second knowledge graph is as follows: Figure 5 As shown. Figure 5 The second knowledge graph shown contains the entity with the question number "FJSM100015", the correction tool entity "Operation and Maintenance Center OMC Parameter Correction", the parameter correction content entity "Maximum Transmit Power: 478->448 | Downtilt Angle: 9->12 | Reference Signal Power: 132", and the relationships between these entities. Within the parameter correction content entity, multiple optimization parameters are separated by "|". The part before the ":" is the optimization parameter (e.g., maximum transmit power, downtilt angle, reference signal power, reference signal power), and the part before the ":" is the corresponding optimization method. The part before the "->" indicates the original value of the optimization parameter before correction, and the part after the "->" indicates the corrected value of the optimization parameter after correction.

[0051] After a fault is corrected, the repair status needs to be evaluated to determine if the fault has been effectively repaired. Evaluation behavior data may include evaluation metrics, the metric values ​​before fault repair, the metric values ​​after fault repair, and the evaluation results. Taking the evaluation behavior data corresponding to a network fault as an example, the generated second knowledge graph would look like this: Figure 6 As shown. Figure 6The second knowledge graph shown contains the problem number entity "FJSM100015", the evaluation tool entity "parameter query module", the pre - fault repair index value entity "radio connection rate: 93.41|handover success rate: 92.88|radio drop - off rate: 0.42", the post - fault repair index value entity "radio connection rate: 99.67|handover success rate: 99.02|radio drop - off rate: 0.01", the evaluation result entity "passed", and the association relationships between each entity. In the pre - fault repair index value entity and the post - fault repair index value entity, multiple evaluation indicators are separated by "|". Before ":", it is the evaluation indicator (such as radio connection rate, handover success rate, radio drop - off rate), and after ":", it is the parameter value corresponding to the evaluation indicator. Among them, the evaluation indicators can include performance indicators, etc., and this application does not limit this.

[0052] Step 102: Extract and screen keywords from the case description entity in the first knowledge graph, and determine the first fault type corresponding to the first fault based on the screened keywords.

[0053] In this application, the case description entity in the first knowledge graph is pre - processed (the pre - processing includes word - segmentation processing, removing stop words (such as special symbols like '_', auxiliary words like 'de', etc.), merging synonyms / near - synonyms (such as merging "low connection rate" and "wireless low connection rate", etc.)), to obtain the keywords (i.e., case keywords) contained in the case description entity. Then, through manual or rule - matching methods, remove the keywords in all the keywords contained in the case description entity of the first knowledge graph that do not contribute to locating the fault cause. Then, determine the screened keywords as the first fault type corresponding to the first fault.

[0054] Among them, the specific process of removing the keywords in all the keywords contained in the case description entity of the first knowledge graph that do not contribute to locating the fault cause by rule - matching method is as follows: When the type of a certain keyword is a preset type, remove the keyword. The preset type can be geographical nouns (such as "×× Province", "×× Coal Mine", etc.), equipment names, etc., and this application does not limit this.

[0055] Alternatively, any semantic recognition algorithm can also be used to process the case description entity in the first knowledge graph to determine the first fault type corresponding to the first fault.

[0056] Step 103: After adding a type entity to the first knowledge graph based on the first fault type, associate the first knowledge graph and the second knowledge graph based on the problem number entity to generate a historical knowledge graph corresponding to the first fault.

[0057] Among them, the type entity is used to describe the fault type (also known as the problem type) of the first fault.

[0058] Understandably, after expanding the first knowledge graph based on the first fault type, the first knowledge graph contains the type entities corresponding to the first fault type. Subsequently, the first and second knowledge graphs with the same or related problem number entities can be merged, realizing the association between the first and second knowledge graphs. This establishes the association between behavioral data and work order data at each stage of fault handling (including constructing a "profession to which the problem belongs" relationship through the association between case entities under the problem number concept and case entities under the specialty concept; and constructing a "type to which the problem belongs" relationship through the association between case entities under the problem number concept and type entities under the fault type concept, etc.). This provides high-quality data support for identifying fault causes and discovering the best network fault solutions. In this application, a first knowledge graph is constructed based on case entities extracted from the first work order data of the first fault, and a second knowledge graph is constructed based on case entities extracted from the behavioral data of each processing stage of the first fault. The second knowledge graph is identical to or related to the issue number entity in the first knowledge graph. Then, keyword extraction and filtering are performed on the case summary entity in the first knowledge graph to determine the first fault type corresponding to the first fault. Next, a type entity is added to the first knowledge graph based on the first fault type. Finally, the first and second knowledge graphs are linked based on the issue number entity to generate a historical knowledge graph corresponding to the first fault. Thus, fault work order data, behavioral data of each processing stage of the fault, and the relationships between fault work order data and behavioral data are presented in the form of a knowledge graph, standardizing fault behavioral data and fault work order data and improving the readability of fault data. This provides high-quality data support for identifying fault causes and discovering optimal network fault solutions.

[0059] Figure 7 This is a schematic flowchart of a data processing method provided in an embodiment of this application.

[0060] like Figure 7 As shown, the data processing method includes the following steps:

[0061] Step 701: Construct a first knowledge graph based on the case entities extracted from the first work order data of the first fault, and construct a second knowledge graph based on the case entities extracted from the behavioral data of each processing stage of the first fault, wherein the second knowledge graph is the same as or related to the problem number entity in the first knowledge graph.

[0062] Step 702: Extract and filter keywords from the case summary entity in the first knowledge graph to determine the first fault type corresponding to the first fault based on the filtered keywords.

[0063] Step 703: After adding a type entity to the first knowledge graph based on the first fault type, associate the first knowledge graph and the second knowledge graph based on the question number entity to generate the historical knowledge graph corresponding to the first fault.

[0064] The specific implementation process of steps 701-703 in this application can be found in the detailed description of any embodiment of this application, and will not be repeated here.

[0065] Step 704: In response to obtaining the second work order data of the second fault, determine the third knowledge graph corresponding to the second work order data and the second fault type corresponding to the third knowledge graph.

[0066] In this application, when the management platform obtains the second work order data of a newly reported second fault from a user, a third knowledge graph corresponding to the second work order data can be constructed, and the second fault type corresponding to the third knowledge graph can be determined based on the case summary entity in the third knowledge graph. This facilitates subsequent determination of fault causes, fault solutions, etc., based on the third knowledge graph and the second fault type.

[0067] The specific implementation process for determining the second fault type can be found in the detailed description of determining the first fault type, and will not be repeated here.

[0068] Step 705: Match the attribute information of the second fault type and the fault object in the third knowledge graph with the attribute information of the first fault type and the fault object in each historical knowledge graph to determine the reference knowledge graph in the historical knowledge graph.

[0069] In this application, the historical knowledge graph describes the relationship between fault types, attribute information of fault objects, and queried indicators using triples. Therefore, the second fault type can be matched with the first fault type in each historical knowledge graph, and the attribute information of the fault object in the third knowledge graph can be matched with the attribute information of the fault object in each historical knowledge graph. If the first fault type and the second fault type are the same in a certain historical knowledge graph, and the attribute information of the fault object in that historical knowledge graph is the same as the attribute information of the fault object in the third knowledge graph, it indicates that the first fault and the second fault corresponding to that historical knowledge graph are likely the same. This historical knowledge graph can be designated as a reference knowledge graph to provide a reference for resolving the second fault.

[0070] Step 706: Based on the query content entities of the second knowledge graph corresponding to the data query behavior data in the reference knowledge graph, determine the reference indicator set corresponding to the second fault.

[0071] In this application, query metrics can be extracted from the query content entities of the second knowledge graph corresponding to the data query behavior data in the reference knowledge graph, and these metrics can be determined as reference metrics corresponding to the second fault, thereby obtaining the reference metric set corresponding to the second fault. This achieves the function of inferring the reference metric set to be queried when the fault object corresponding to the second work order data, based on historical knowledge graph reasoning, experiences a first fault. For less experienced maintenance personnel who do not know which metrics to query for troubleshooting the second fault, they can perform troubleshooting based on this reference metric set, thus improving the efficiency of troubleshooting.

[0072] Understandably, using a set of reference indicators based on the relationships between work order data and data query behavior data contained in historical knowledge graphs can help improve the accuracy of determining the reference indicator set.

[0073] Figure 8 This is a schematic flowchart of a data processing method provided in an embodiment of this application.

[0074] like Figure 8 As shown, the data processing method includes the following steps:

[0075] Step 801: Construct a first knowledge graph based on case entities extracted from the first work order data of the first fault, and construct a second knowledge graph based on case entities extracted from the behavioral data of each processing stage of the first fault, wherein the second knowledge graph is the same as or related to the problem number entity in the first knowledge graph.

[0076] Step 802: Extract and filter keywords from the case summary entity in the first knowledge graph to determine the first fault type corresponding to the first fault based on the filtered keywords.

[0077] Step 803: After adding a type entity to the first knowledge graph based on the first fault type, associate the first knowledge graph and the second knowledge graph based on the problem number entity to generate the historical knowledge graph corresponding to the first fault.

[0078] Step 804: In response to obtaining the second work order data of the second fault, determine the third knowledge graph corresponding to the second work order data and the second fault type corresponding to the third knowledge graph.

[0079] Step 805: Match the attribute information of the second fault type and the fault object in the third knowledge graph with the attribute information of the first fault type and the fault object in each historical knowledge graph to determine the reference knowledge graph in the historical knowledge graph.

[0080] Step 806: Based on the query content entities of the second knowledge graph corresponding to the data query behavior data in the reference knowledge graph, determine the reference indicator set corresponding to the second fault.

[0081] The specific implementation process of steps 801-806 in this application can be found in the detailed description of any embodiment of this application, and will not be repeated here.

[0082] Step 807: Obtain the indicator value of each reference indicator in the reference indicator set.

[0083] In this application, faulty objects in a third knowledge graph can be monitored, and the index values ​​of the faulty objects under each reference index can be obtained.

[0084] Step 808: Based on the index value of each reference index, the attribute information of the faulty object in the third knowledge graph, and the case summary entity, determine the cause of the second fault.

[0085] In this application, the index values ​​of the faulty object in the third knowledge graph under each reference index, the attribute information of the faulty object in the third knowledge graph, and the case summary entity can be input into the fault cause localization tool to obtain the fault cause of the second fault output by the fault cause localization tool. This improves the efficiency and accuracy of determining the fault cause.

[0086] The fault cause localization tool can be a pre-set algorithm for determining the fault cause, and this application does not impose any restrictions on it.

[0087] Optionally, the historical knowledge graph describes the relationship between the faulty object's indicator value, fault type, attribute information, and fault cause under each reference indicator in the form of triples. Therefore, the original value before fault repair in the second knowledge graph corresponding to the data analysis behavior data contained in each reference knowledge graph can also be determined. Then, the indicator value of the faulty object under each reference indicator in the third knowledge graph can be matched with the original value before fault repair corresponding to each reference indicator in each reference knowledge graph. When the difference between the indicator value of the faulty object in the third knowledge graph and the original value before fault repair corresponding to each reference indicator in a certain reference knowledge graph is less than a preset threshold, the fault cause contained in the second knowledge graph corresponding to the data analysis behavior data in that reference knowledge graph is determined as the fault cause of the second fault. This realizes the function of reasoning based on the historical knowledge graph to determine the fault cause of the first fault in the faulty object corresponding to the first work order data, thereby improving the efficiency of fault diagnosis.

[0088] Understandably, mining the causes of second faults based on the correlation between work order data and data analysis behavior data contained in historical knowledge graphs can help improve the accuracy of determining the causes of faults.

[0089] Figure 9 This is a schematic flowchart of a data processing method provided in an embodiment of this application.

[0090] like Figure 9 As shown, the data processing method includes the following steps:

[0091] Step 901: Construct a first knowledge graph based on case entities extracted from the first work order data of the first fault, and construct a second knowledge graph based on case entities extracted from the behavioral data of each processing stage of the first fault, wherein the second knowledge graph is the same as or related to the problem number entity in the first knowledge graph.

[0092] Step 902: Extract and filter keywords from the case summary entity in the first knowledge graph to determine the first fault type corresponding to the first fault based on the filtered keywords.

[0093] Step 903: After adding a type entity to the first knowledge graph based on the first fault type, associate the first knowledge graph and the second knowledge graph based on the problem number entity to generate the historical knowledge graph corresponding to the first fault.

[0094] Step 904: In response to obtaining the second work order data of the second fault, determine the third knowledge graph corresponding to the second work order data and the second fault type corresponding to the third knowledge graph.

[0095] Step 905: Match the attribute information of the second fault type and the fault object in the third knowledge graph with the attribute information of the first fault type and the fault object in each historical knowledge graph to determine the reference knowledge graph in the historical knowledge graph.

[0096] Step 906: Based on the query content entities of the second knowledge graph corresponding to the data query behavior data in the reference knowledge graph, determine the reference indicator set corresponding to the second fault.

[0097] Step 907: Obtain the indicator value of each reference indicator in the reference indicator set.

[0098] Step 908: Based on the index value of each reference index, the attribute information of the faulty object in the third knowledge graph, and the case summary entity, determine the cause of the second fault.

[0099] The specific implementation process of steps 901-908 in this application can be found in the detailed description of any embodiment of this application, and will not be repeated here.

[0100] Step 909: Match the fault cause and the case summary entity in the third knowledge graph with the fault cause in the second knowledge graph and the case summary entity in the reference knowledge graph corresponding to the data analysis behavior data in each reference knowledge graph to determine the target knowledge graph in the reference knowledge graph.

[0101] In this application, the historical knowledge graph describes the relationship between fault type, fault cause, attribute information of the fault object, and adjusted parameters using triples. Therefore, the fault cause of the second fault can be matched with the fault cause in the second knowledge graph corresponding to the data analysis behavior data in each reference knowledge graph, and the case summary entity in the third knowledge graph can be matched with the case description entity in each reference knowledge graph. If the fault cause of the second fault is the same as the fault cause in the second knowledge graph corresponding to the data analysis behavior data in a certain reference knowledge graph, and the similarity between the case entity in the third knowledge graph and the case entity in that reference knowledge graph is greater than a threshold, then that reference knowledge graph is determined as the target knowledge graph.

[0102] Step 910: Generate a solution based on the optimized parameter entities and reference values ​​of the optimized parameters in the second knowledge graph corresponding to the parameter adjustment behavior data in the target knowledge graph. The reference values ​​are determined based on the original values ​​and correction values ​​of the optimized parameters in the target knowledge graph.

[0103] In this application, a solution corresponding to the second fault can be generated based on a preset format and the optimized parameter entities and reference values ​​of the optimized parameters in the second knowledge graph corresponding to the parameter adjustment behavior data in the target knowledge graph. This provides a reference for resolving the second fault.

[0104] The process for determining the reference value is as follows: If the original value of the optimization parameter in the target knowledge graph is the same as the current actual value of the optimization parameter in the faulty object, the corrected value of the optimization parameter in the target knowledge graph is determined as the reference value.

[0105] Understandably, mining solutions for second faults based on the correlation between work order data and parameter adjustment behavior data contained in historical knowledge graphs can help improve the accuracy of generated solutions.

[0106] Optionally, the historical knowledge graph describes the relationship between basic fault data (attribute information of the fault object, fault type) and evaluation metrics in the form of triples. Therefore, the evaluation metrics contained in the second knowledge graph corresponding to the evaluation behavior data in the target knowledge graph can be extracted and determined as the reference evaluation metrics for the second fault. This provides a reference for evaluating whether the second fault has been repaired.

[0107] Understandably, mining reference evaluation indicators based on the correlation between work order data and evaluation behavior data contained in historical knowledge graphs is beneficial to improving the accuracy of reference evaluation indicators.

[0108] To implement the above embodiments, this application also proposes a data processing apparatus.

[0109] Figure 10 This is a schematic diagram of the structure of a data processing device provided in an embodiment of this application.

[0110] like Figure 10 As shown, the data processing device includes a construction module 1010, a determination module 1020, and a generation module 1030.

[0111] The construction module 1010 is used to construct a first knowledge graph based on case entities extracted from the first work order data of the first fault, and to construct a second knowledge graph based on case entities extracted from the behavioral data of each processing stage of the first fault, wherein the second knowledge graph is the same as or related to the problem number entity in the first knowledge graph.

[0112] The determination module 1020 is used to extract and filter keywords from the case summary entity in the first knowledge graph, so as to determine the first fault type corresponding to the first fault based on the filtered keywords.

[0113] The generation module 1030 is used to add a type entity to the first knowledge graph based on the first fault type, and then associate the first knowledge graph and the second knowledge graph based on the problem number entity to generate a historical knowledge graph corresponding to the first fault.

[0114] Furthermore, in one possible implementation of this application embodiment, the behavioral data includes data query behavioral data, data analysis behavioral data, parameter adjustment behavioral data, and evaluation behavioral data.

[0115] Furthermore, in one possible implementation of this application embodiment, a processing module is further included, for:

[0116] In response to obtaining the second work order data of the second fault, determine the third knowledge graph corresponding to the second work order data and the second fault type corresponding to the third knowledge graph;

[0117] The attribute information of the second fault type and the fault object in the third knowledge graph is matched with the attribute information of the first fault type and the fault object in each historical knowledge graph to determine the reference knowledge graph in the historical knowledge graph.

[0118] Based on the query content entities of the second knowledge graph corresponding to the data query behavior data in the reference knowledge graph, the reference indicator set corresponding to the second fault is determined.

[0119] Furthermore, in one possible implementation of this application embodiment, the above-mentioned processing module is used for:

[0120] Obtain the indicator value for each reference indicator in the reference indicator set;

[0121] Based on the index value of each reference index, the attribute information of the faulty object in the third knowledge graph, and the case summary entity, the cause of the second fault is determined.

[0122] Furthermore, in one possible implementation of this application embodiment, the above-mentioned processing module is used for:

[0123] The fault cause and the case summary entity in the third knowledge graph are matched with the fault cause in the second knowledge graph and the case summary entity in the reference knowledge graph corresponding to the data analysis behavior data in each reference knowledge graph to determine the target knowledge graph in the reference knowledge graph.

[0124] A solution is generated based on the optimization parameter entities and reference values ​​of the optimization parameters in the second knowledge graph corresponding to the parameter adjustment behavior data in the target knowledge graph. The reference values ​​are determined based on the original values ​​and correction values ​​of the optimization parameters in the target knowledge graph.

[0125] Furthermore, in one possible implementation of this application embodiment, the above-mentioned processing module is used for:

[0126] The evaluation indicators contained in the second knowledge graph corresponding to the evaluation behavior data in the target knowledge graph are determined as reference evaluation indicators.

[0127] Furthermore, in one possible implementation of this application embodiment, the attributes corresponding to each case entity include problem level, specialty, case name, case summary, case keywords, case submission time, submission city, and problem discovery method.

[0128] It should be noted that the foregoing explanation of the data processing method embodiments also applies to the data processing apparatus of this embodiment, and will not be repeated here.

[0129] In this application, a first knowledge graph is constructed based on case entities extracted from the first work order data of the first fault, and a second knowledge graph is constructed based on case entities extracted from the behavioral data of each processing stage of the first fault. The second knowledge graph is identical to or related to the issue number entity in the first knowledge graph. Then, keyword extraction and filtering are performed on the case summary entity in the first knowledge graph to determine the first fault type corresponding to the first fault. Next, a type entity is added to the first knowledge graph based on the first fault type. Finally, the first and second knowledge graphs are linked based on the issue number entity to generate a historical knowledge graph corresponding to the first fault. Thus, fault work order data, behavioral data of each processing stage of the fault, and the relationships between fault work order data and behavioral data are presented in the form of a knowledge graph, standardizing fault behavioral data and fault work order data and improving the readability of fault data. This provides high-quality data support for identifying fault causes and discovering optimal network fault solutions.

[0130] To implement the above embodiments, this application also proposes an electronic device, including: a processor and a memory communicatively connected to the processor; the memory stores computer execution instructions; the processor executes the computer execution instructions stored in the memory to implement the method provided in the foregoing embodiments.

[0131] To implement the above embodiments, this application also proposes a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the methods provided in the foregoing embodiments.

[0132] To implement the above embodiments, this application also proposes a computer program product, including a computer program that, when executed by a processor, implements the methods provided in the foregoing embodiments.

[0133] The collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in this application all comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0134] It should be noted that personal information collected from users should be used for legitimate and reasonable purposes and should not be shared or sold outside of these legitimate uses. Furthermore, such collection / sharing should only be conducted after receiving the user's informed consent, including but not limited to notifying the user to read the user agreement / user notice and sign an agreement / authorization that includes authorization of relevant user information before the user uses the function. In addition, any necessary steps must be taken to protect and safeguard access to such personal information data and ensure that others with access to personal information data comply with their privacy policies and procedures.

[0135] This application is intended to provide an implementation scheme for users to selectively prevent the use or access to their personal information data. Specifically, this application is intended to provide hardware and / or software to prevent or block access to such personal information data. Once personal information data is no longer needed, risks can be minimized by restricting data collection and deleting data. Furthermore, where applicable, such personal information is de-identified to protect user privacy.

[0136] In the foregoing descriptions of the embodiments, the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0137] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0138] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0139] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0140] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0141] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0142] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0143] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A data processing method, characterized in that, The method includes: A first knowledge graph is constructed based on case entities extracted from the first work order data of the first fault, and a second knowledge graph is constructed based on case entities extracted from the behavioral data of each processing stage of the first fault, wherein the second knowledge graph is the same as or related to the problem number entity in the first knowledge graph. Keyword extraction and filtering are performed on the case summary entity in the first knowledge graph to determine the first fault type corresponding to the first fault based on the filtered keywords; After adding a type entity to the first knowledge graph based on the first fault type, the first knowledge graph and the second knowledge graph are associated based on the question number entity to generate a historical knowledge graph corresponding to the first fault. In response to obtaining the second work order data of the second fault, a third knowledge graph corresponding to the second work order data and the second fault type corresponding to the third knowledge graph are determined; The attribute information of the second fault type and the fault object in the third knowledge graph is matched with the attribute information of the first fault type and the fault object in each of the historical knowledge graphs to determine the reference knowledge graph in the historical knowledge graph. Based on the query content entities of the second knowledge graph corresponding to the data query behavior data in the reference knowledge graph, the reference indicator set corresponding to the second fault is determined. Obtain the index value of each reference index in the reference index set; Based on the index value of each reference index, the attribute information of the faulty object in the third knowledge graph, and the case summary entity, the cause of the second fault is determined.

2. The method as described in claim 1, characterized in that, The behavioral data includes data query behavioral data, data analysis behavioral data, parameter adjustment behavioral data, and evaluation behavioral data.

3. The method as described in claim 1, characterized in that, Also includes: The fault cause and the case summary entity in the third knowledge graph are matched with the fault cause in the second knowledge graph corresponding to the data analysis behavior data in each reference knowledge graph and the case summary entity in the reference knowledge graph, respectively, to determine the target knowledge graph in the reference knowledge graph. A solution is generated based on the optimization parameter entities and reference values ​​of the optimization parameters in the second knowledge graph corresponding to the parameter adjustment behavior data in the target knowledge graph, wherein the reference values ​​are determined based on the original values ​​and correction values ​​of the optimization parameters in the target knowledge graph.

4. The method as described in claim 3, characterized in that, Also includes: The evaluation indicators contained in the second knowledge graph corresponding to the evaluation behavior data in the target knowledge graph are determined as reference evaluation indicators.

5. The method as described in claim 1, characterized in that, The attributes corresponding to each case entity include issue level, specialty, case name, case summary, case keywords, case submission time, submission city, and issue discovery method.

6. A data processing apparatus, characterized in that, The device includes: The construction module is used to construct a first knowledge graph based on case entities extracted from the first work order data of the first fault, and to construct a second knowledge graph based on case entities extracted from the behavioral data of each processing stage of the first fault, wherein the second knowledge graph is the same as or related to the problem number entity in the first knowledge graph. The determination module is used to extract and filter keywords from the problem description entities in the first knowledge graph, so as to determine the first fault type corresponding to the first fault based on the filtered keywords. The generation module is used to add a type entity to the first knowledge graph based on the first fault type, and then associate the first knowledge graph and the second knowledge graph based on the problem number entity to generate a historical knowledge graph corresponding to the first fault. The processing module is configured to, in response to obtaining second work order data for a second fault, determine the third knowledge graph corresponding to the second work order data and the second fault type corresponding to the third knowledge graph; match the second fault type and the attribute information of the fault object in the third knowledge graph with the attribute information of the first fault type and the fault object in each historical knowledge graph to determine a reference knowledge graph in the historical knowledge graph; determine a reference indicator set corresponding to the second fault based on each query content entity of the second knowledge graph corresponding to the data query behavior data in the reference knowledge graph; obtain the indicator value of each reference indicator in the reference indicator set; and determine the fault cause of the second fault based on the indicator value of each reference indicator, the attribute information of the fault object in the third knowledge graph, and the case summary entity.

7. An electronic device, characterized in that, include: processor; The memory that is communicatively connected to the processor The memory stores computer-executed instructions. The processor executes computer execution instructions stored in the memory to implement the method as described in any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-5.

9. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method of any one of claims 1-5.

Images