Alarm information processing method and device, electronic equipment, chip and storage medium

Abstract

The present disclosure provides an alarm information processing method and device, electronic equipment, chip and medium. The method is executed by a control system, which comprises an alarm automation acquisition module, a data cleaning module, an information scheduling function module, an optical distribution resource management remote control and recovery module. The method comprises: the alarm automation acquisition module acquires alarm information of a device and loads the alarm information into the data cleaning module; the data cleaning module pre-processes the alarm information to obtain alarm fields; the information scheduling function module processes the alarm fields to obtain scheduling information, and sends the scheduling information to designated maintenance personnel and / or the optical distribution resource management remote control and recovery module when a first preset condition is met, wherein the scheduling information at least comprises an alarm root cause and a scheduling instruction, and the scheduling information is used to instruct the designated maintenance personnel or the optical distribution resource management remote control and recovery module to process the alarm information of the device. The processing efficiency of the alarm information can be improved.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the field of data processing, and in particular, to an alarm information processing method and device, electronic equipment, chip and storage medium. BACKGROUND

[0002] The existing device withdrawal management and control mainly adopts manual management and control, such as manual notification of faults, manual supervision of processing, manual summary of reasons, manual establishment of fault account books, and manual review and analysis, which has the problem of low efficiency and benefit. SUMMARY

[0003] The present disclosure provides an alarm information processing method and device, electronic equipment, chip and storage medium.

[0004] The first aspect embodiment of the present disclosure provides an alarm information processing method, which is executed by a control system including an alarm automatic collection module, a data cleaning module, an information scheduling function module, and an optical distribution resource management remote control and recovery module. The method comprises: the alarm automatic collection module collects alarm information of a device and loads the alarm information into the data cleaning module; the data cleaning module pre-processes the alarm information to obtain an alarm field; the information scheduling function module processes the alarm field to obtain scheduling information, and sends the scheduling information to a designated maintenance personnel and / or the optical distribution resource management remote control and recovery module when a first preset condition is met, wherein the scheduling information at least includes an alarm root cause and a scheduling instruction, and the scheduling information is used to instruct the designated maintenance personnel or the optical distribution resource management remote control and recovery module to process the alarm information of the device.

[0005] In some embodiments of the present disclosure, the alarm automatic collection module collecting the alarm information of the device comprises: the alarm automatic collection module identifying an export button of a current alarm module of an operation and maintenance center; and the alarm automatic collection module triggering the export button to obtain the alarm information of the device.

[0006] In some embodiments of the present disclosure, the data cleaning module processing the alarm information to obtain the alarm field comprises: the data cleaning module determining a positioning information field of the alarm information; the data cleaning module inserting the positioning information field into the alarm information to obtain a to-be-processed field; and the data cleaning module obtaining the alarm field after performing data cleaning, standardization processing, and normalization processing on the to-be-processed field.

[0007] In some embodiments of the present disclosure, before the information scheduling function module processes the alarm field to obtain the scheduling information, the method further comprises: the data cleaning module extracting and performing entity recognition on the alarm field to determine at least one response semantic label of the alarm field; and the data cleaning module determining an alarm type of the alarm field.

[0008] In some embodiments of the present disclosure, the information scheduling function module processes the alarm field to obtain the scheduling information, including: the information scheduling function module determines a function function corresponding to the alarm type according to the alarm type of the alarm field; and the information scheduling function module processes the alarm field by using the function function corresponding to the alarm type to obtain the scheduling information.

[0009] In some embodiments of the present disclosure, the first preset condition can include at least one of the following: the value of the sending state field of the scheduling information is a first value; and the matching degree between the keyword and the at least one response semantic label received by the information scheduling function module is greater than a matching degree threshold, wherein the keyword is obtained by the information scheduling function module by analyzing the received query instruction.

[0010] In some embodiments of the present disclosure, the optical distribution resource management remote control and recovery module processes the alarm information of the device, including: the optical distribution resource management remote control and recovery module determines a fault point based on the scheduling information; and the optical distribution resource management remote control and recovery module remotely controls the manipulator to process the fault point according to the scheduling instruction.

[0011] The second aspect embodiment of the present disclosure proposes a control system, including: an alarm automatic acquisition module, configured to acquire alarm information of a device and load the alarm information into a data cleaning module; the data cleaning module, configured to pre-process the alarm information to obtain an alarm field; an information scheduling function module, configured to process the alarm field to obtain scheduling information, and send the scheduling information to a designated maintenance personnel and / or an optical distribution resource management remote control and recovery module when a first preset condition is met, wherein the scheduling information at least includes an alarm root cause and a scheduling instruction, and the scheduling information is used to instruct the designated maintenance personnel or the optical distribution resource management remote control and recovery module to process the alarm information of the device; and the optical distribution resource management remote control and recovery module, configured to process the alarm information of the device.

[0012] The third aspect embodiment of the present disclosure proposes an electronic device, including: at least one processor; and a memory connected with the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method described in the first aspect embodiment of the present disclosure.

[0013] The fourth aspect embodiment of the present disclosure proposes a non-transitory computer readable storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to execute the method described in the first aspect embodiment of the present disclosure.

[0014] The fifth aspect of the present disclosure provides a computer program product comprising a computer program which, when executed by a processor, performs the method described in the first aspect of the present disclosure.

[0015] The sixth aspect of the present disclosure provides a chip comprising one or more interfaces and one or more processors; the interface is configured to receive a signal from a memory of an electronic device and send a signal to the processor, the signal comprising computer instructions stored in the memory, when the processor executes the computer instructions, causing the electronic device to perform the method described in the first aspect of the present disclosure.

[0016] In summary, the alarm information processing method, device, electronic device, chip and storage medium provided by the present disclosure can process alarm information to obtain scheduling information, so as to determine the root cause of the fault and the scheduling instruction, and can send the scheduling information directly to the designated maintenance personnel, so as to facilitate the designated maintenance personnel to process the alarm information as soon as possible, and improve the processing efficiency of the alarm information.

[0017] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. BRIEF DESCRIPTION OF DRAWINGS

[0018] The accompanying drawings incorporated in the specification and forming a part of the specification illustrate embodiments consistent with the present disclosure and serve to explain the principles of the present disclosure, and do not constitute an improper limitation on the present disclosure.

[0019] Figure 1 A flowchart of an alarm information processing method provided by an embodiment of the present disclosure is shown in the following figure;

[0020] Figure 2 A flowchart of an alarm information processing method provided by an embodiment of the present disclosure is shown in the following figure;

[0021] Figure 3 A flowchart of an alarm information processing method provided by an embodiment of the present disclosure is shown in the following figure;

[0022] Figure 4 A flowchart of a network alarm information processing method provided by an embodiment of the present disclosure is shown in the following figure;

[0023] Figure 5 A flowchart of a network alarm information processing method provided by an embodiment of the present disclosure is shown in the following figure;

[0024] Figure 6 A flowchart of a network alarm information processing method provided by an embodiment of the present disclosure is shown in the following figure;

[0025] Figure 7 A flowchart of a network alarm information processing method provided by an embodiment of the present disclosure is shown in the following figure;

[0026] Figure 8 A flowchart of a network alarm information processing method provided by an embodiment of the present disclosure is shown in FIG. 1.

[0027] Figure 9 A structural diagram of a control system provided by an embodiment of the present disclosure is shown in FIG. 2.

[0028] Figure 10 A structural diagram of an electronic device provided by an embodiment of the present disclosure is shown in FIG. 3.

[0029] Figure 11 A structural diagram of a chip provided by an embodiment of the present disclosure is shown in FIG. 4. DETAILED DESCRIPTION

[0030] Embodiments of the present disclosure are described in detail below, and examples of the embodiments are shown in the accompanying drawings, in which the same or similar notations represent the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by reference to the accompanying drawings are exemplary and are intended to explain the present disclosure, and cannot be understood as a limitation of the present disclosure.

[0031] The existing service withdrawal management mainly relies on manual notification of faults, manual supervision and processing, manual summary of reasons, manual establishment of fault account books, and manual review and analysis, which is low in efficiency and benefit, prone to errors, and unable to realize full-process, full-automatic and intelligent management.

[0032] Therefore, in order to solve the above technical problems, the present disclosure provides an alarm information processing method, which focuses on the rapid processing and information transmission of alarm information, realizes the matching of place names and fault categories based on the Bidirectional Encoder Representations from Transformers (BERT) algorithm, and provides an automatic fiber jump processing scheme for transmission faults on this basis, and realizes full-process information tracking and scheduling closed loop.

[0033] Figure 1 A flowchart of an alarm information processing method provided by an embodiment of the present disclosure is shown in FIG. 1. Figure 1 As shown in FIG. 1, the method is executed by a control system, the control system includes an alarm automation acquisition module, a data cleaning module, an information scheduling function module, and an optical distribution resource management remote control and recovery module, and the method can include the following steps.

[0034] In step 101, the alarm automation acquisition module acquires the alarm information of the device and loads the alarm information into the data cleaning module.

[0035] In some embodiments, the alarm automatic collection module collecting alarm information of the device comprises: the alarm automatic collection module identifying an export button of a current alarm module of the operation and maintenance center; the alarm automatic collection module triggering the export button to obtain the alarm information of the device. For example, the device can be a network device, such as a base station; and the alarm automatic collection module can be a separate server.

[0036] In some embodiments, for example, the alarm information can include the name of the base station, the alarm content, etc. of the base station, such as disconnection information = port handshake timeout.

[0037] In some embodiments, for example, the alarm automatic collection module can obtain data of the device from multiple platforms, such as unstructured data of faults, power outages, power generation, etc. obtained from wireless network management, transmission network management, fault management systems, maintenance management systems, tower centralized dispatch platforms, and optical fiber resource management systems.

[0038] Specifically, the alarm automatic collection module can write an image recognition and clicking program based on the locateCenterOnScreen and Click methods in the PyAutoGui library. The image recognition and clicking program can identify the “export” button on the “current alarm” function module of the operation and maintenance center, i.e., identify the location of the “export” button on the page. Then the image recognition and clicking program can periodically trigger the identified “export” button. For example, the periodic collection of alarm information can be achieved by using a loop function and a time sleep function, such as triggering the export button every 60 seconds, which can update the alarm information every 60 seconds. By triggering the button, real-time alarm information affecting the business can be obtained, and the alarm information can be downloaded in Excel format and saved to the server.

[0039] In some embodiments, for example, the saved alarm information in Excel format can be loaded into the data cleaning module by the read_csv method, which can facilitate the data cleaning module to process the alarm information.

[0040] In step 102, the data cleaning module pre-processes the alarm information to obtain alarm fields.

[0041] In some embodiments, the data cleaning module can process the alarm information, such as converting the alarm information in Excel format into a two-dimensional data table structure; for example, deleting useless field columns by using the drop method, such as deleting invalid field data such as “level” and “level”; for example, converting table headers into a list by using the columns.tolist method, etc.

[0042] In some embodiments, the data cleaning module can determine a location information field of the alarm information, and insert the location information field into the alarm information to obtain a to-be-processed field, wherein the location information field can include a district and county field, an alarm duration field, an alarm source attribution field, an alarm cause field, and the like.

[0043] In some embodiments, the data cleaning module can perform data cleaning, standardization processing, and normalization processing on the processing field to obtain an alarm field.

[0044] In step 103, the information scheduling function module processes the alarm field to obtain scheduling information, and sends the scheduling information to the designated maintenance personnel and / or the optical distribution resource management remote control and recovery module when a first preset condition is met.

[0045] In some embodiments, the scheduling information at least includes an alarm root cause and a scheduling instruction, and the scheduling information is used to instruct the designated maintenance personnel or the optical distribution resource management remote control and recovery module to process the alarm information of the device. The alarm root cause can include a fault point of the device alarm information, i.e., an alarm source, and the alarm root cause can also include a cause of the alarm information, i.e., an alarm cause, and the like. For example, the scheduling information can also include other indication fields, and the scheduling information fields can be added or deleted according to actual use scenarios, and the present disclosure is not limited thereto.

[0046] In other words, the scheduling information can indicate the location and cause of the alarm information through the alarm root cause, and the alarm information can indicate how to process the alarm information through the scheduling instruction. For example, the scheduling instruction can instruct the designated maintenance personnel to go to the scene to maintain the device, or can instruct the designated maintenance personnel to remotely control a mechanical hand to maintain the device, or the scheduling instruction can directly instruct the optical distribution resource management remote control and recovery module to process the alarm information of the device, i.e., can instruct the optical distribution resource management remote control and recovery module to control the mechanical hand to maintain the device, at which time the user does not need to send an instruction to control the mechanical hand, and at which time the scheduling instruction can directly include an instruction to control the mechanical hand to maintain the device.

[0047] For example, when the scheduling information is that the intelligent optical distribution - the optical distribution fiber core loss is large, and it is necessary to switch to a standby fiber core at the intelligent optical distribution side, a fault work order can be issued to instruct the maintenance personnel to perform a corresponding fiber core jump at the optical distribution side, so as to quickly recover the service; when the scheduling information is that the intelligent optical distribution - the optical distribution cable is interrupted, a fault work order can be issued to instruct the maintenance personnel to modify the fault on site.

[0048] For example, when the dispatch information determines the faulty device and the fault location, the optical distribution resource management remote control and recovery module can detect and analyze the slot information of the faulty device, and the optical distribution resource management remote control and recovery module can directly control the manipulator to realize automatic fiber jump recovery of the faulty slot core according to the dispatch instruction; or the optical distribution resource management remote control and recovery module can control the manipulator to realize automatic fiber jump recovery of the faulty slot core according to the dispatch instruction contained in the dispatch information after receiving the determination instruction of the designated maintenance personnel; or the optical distribution resource management remote control and recovery module can not receive the dispatch information, and the designated maintenance personnel can manually remotely control the manipulator to realize automatic fiber jump recovery of the faulty slot core according to the dispatch instruction contained in the dispatch information after receiving the dispatch information, and so on.

[0049] In the above embodiment, the designated maintenance personnel can be the responsible person corresponding to the faulty device, for example, the person in charge of the first base station in B district of A county is A, and the person in charge of the second base station in C district of A county is B. When the first base station fails and sends an alarm information, the dispatch information can be sent to A only, or can be sent to the group of persons in charge of A county, that is, the office group containing A and B, and A is reminded through @ and the like.

[0050] In other words, the dispatch information can be directly sent to the responsible person corresponding to the faulty device. For example, the dispatch information can be directly sent to the terminal of the designated maintenance personnel, or the dispatch information can be directly sent to the mobile office APP of the designated maintenance personnel to notify the designated maintenance personnel, without layer-by-layer searching for the relevant responsible person, so as to improve the transmission efficiency of the alarm information, facilitate the designated maintenance personnel to process the faulty device as soon as possible, and improve the processing efficiency of the fault information.

[0051] In some embodiments, the first preset condition can include at least one of the following:

[0052] The value of the sending state field of the dispatch information is the first value;

[0053] The matching degree between the keyword received by the information dispatch function module and the at least one response semantic label is greater than a matching degree threshold, wherein the keyword is obtained by the information dispatch function module by analyzing the received query instruction.

[0054] Optionally, the scheduling information can further include a sending state field, the name of the sending state field can be "whether to send information field", "sending indication field", etc., and the disclosure does not limit this. The sending state field can be used to indicate the sending state of the scheduling information. For example, the sending state can be an "is sent" field. The value of the "is sent" field can be 0 by default, indicating that the scheduling information needs to be sent. The scheduling information has not been sent. When the scheduling information is sent, the value of the "is sent" field can be updated to 1. That is, when the value of the "is sent" field is 0, the corresponding information needs to be sent. When the value of the "is sent" field is 1, the corresponding information does not need to be sent, and the corresponding information is ignored.

[0055] In other words, the information scheduling function module can automatically send the scheduling information according to the sending state field of the scheduling information, that is, the information scheduling function module can actively send the scheduling information. For example, the information scheduling function module can include an information pushing sub-module and a query sub-module. The pushing sub-module can be used to actively send the scheduling information according to the sending state of the scheduling information.

[0056] In some embodiments, the information scheduling module can execute the sending of the scheduling information through a loop function and a sleep time function. For example, the sending state field of the scheduling information can be queried every 30 seconds. When the sending state field indicates that the scheduling information needs to be sent, the scheduling information is sent.

[0057] Optionally, the information scheduling function module can receive a query instruction. The query instruction can be sent by a maintenance personnel. For example, the maintenance personnel can query the alarm information of a certain device. After receiving the query instruction, the information scheduling function module can analyze the query instruction. For example, the query sub-module can generate a keyword through BERT semantic analysis. The query sub-module can match the keyword in the collected alarm information. For example, when the matching degree of the keyword and at least one semantic label of the alarm information is high, it can be determined that the alarm information is the information that the maintenance personnel wants to query. For example, the matching degree threshold can be specified according to actual conditions, and the disclosure does not limit this.

[0058] For example, the information scheduling module can determine the scheduling information corresponding to the alarm information according to the queried alarm information. At this time, the scheduling information is the active query information. The active query information can be sent to the user who initiates the query, and the user actively acquires the state of the base station is completed. For example, the user can not only query the alarm information and the scheduling information of the device, but also can acquire the state information of the device, such as the physical state of the device, such as routing, business, quality, etc.

[0059] In some embodiments, when the user actively inquires about the device status, the text content input by the user can be identified by using a BERT-BiLSTM-CRF model-based text classification and entity recognition tasks. The model encodes the text into the sum of three embedding features, including word embedding, position embedding, and segmentation embedding. After encoding, a cls identifier is added at the first position to form the input vector of the model, and then the input text features are obtained through a multi-layer encoder with multiple attention mechanisms. The output data contains the information of the entire sentence at the first position and the information of each character at the other positions. In this way, the first position can be used for classification tasks, and the subsequent data can be used for entity recognition. Through text classification, the type of inquiry can be quickly located, and then combined with the extracted entity content, the instruction and the next reply can be better determined. For example, if the user inputs "Xicheng County base station refund", the analysis first locates it as an information query type, and identifies the entities "Xicheng County" and "base station refund". Then, the corresponding real-time information of Xicheng County base station refund can be pushed. If the inquiry is "base station refund processing method", it is analyzed as a fault assistance type, and then the entity "base station refund" is identified. The next step is to push the common processing method of base station refund to assist the front-line in handling quickly.

[0060] In some embodiments, when the information scheduling module initiates scheduling information in a group, the information can be copied to the clipboard through the copy instruction in the pyperclip library. The group name instruction to be sent is defined through the uiautomation in the mobile office message processing module. The group is clicked through the click instruction. The information to be sent in the clipboard is pasted into the above message sending window through the positioning mobile office APP message sending window instruction and the pasting instruction. The message is sent to the mobile office group through the enter instruction to realize the enter function.

[0061] In some embodiments, the optical distribution resource management remote control and recovery module processes the alarm information of the device, including:

[0062] The optical distribution resource management remote control and recovery module determines the fault point based on the scheduling information.

[0063] The optical distribution resource management remote control and recovery module remotely controls the manipulator to process the fault point according to the scheduling instruction.

[0064] In other words, when the information scheduling function module can directly send the scheduling information to the optical distribution resource management remote control and recovery module, the optical distribution resource management remote control and recovery module can determine the fault point, i.e., the location of the fault, based on the alarm cause in the scheduling information, and then can process the fault point according to the scheduling instruction, for example, can control the mechanical hand to realize automatic fiber jump recovery of the fault slot core and the like.

[0065] In some embodiments, when the scheduling instruction indicates that the mechanical hand realizes automatic fiber jump recovery of the fault slot core, optionally, the fiber jump recovery scheme can select a preset special design fiber tray, such as a circular ring or a vertical bar, based on the anti-winding fiber jump technology, the system can recommend different physical paths according to the intelligent routing algorithm when the service is one-key opened or the fault is recovered, for example, can determine the path with the shortest recovery time, or the least number of nodes, or the minimum link loss as the optimal physical path. When performing automatic fiber jump recovery of the fault slot core, the system provides multiple recovery schemes according to different physical paths recommended by the access optical cable, and can perform automatic Optical Time Domain Reflectometer (OTDR) testing to obtain the core quality before confirming the switching, and can be manually confirmed by the mobile office APP (i.e., indicated or determined by the designated maintenance personnel), or based on the scheduling instruction, all devices on the entire link jump at the same time, and complete the rapid recovery of the service. For different fault scenarios, different scheduling instructions can be used to quickly recover the service or send a single maintenance order for timely processing of the fault.

[0066] In summary, the above-mentioned embodiments of the present application can determine the scheduling information according to the alarm information, i.e., can determine the location of the alarm source and the alarm cause and the like, and by directly sending the scheduling information to the designated maintenance personnel or the optical distribution resource management remote control and recovery module, the designated maintenance personnel or the optical distribution resource management remote control and recovery module can be facilitated to process the alarm information as soon as possible, and the normal operation of the equipment can be ensured.

[0067] Figure 2 A flowchart of an alarm information processing method provided by an embodiment of the present disclosure is shown in FIG. 1. Figure 2 As shown in FIG. 1, the method can include the following steps.

[0068] In step 201, a data cleaning module determines the positioning information field of the alarm information.

[0069] In some embodiments, for example, the positioning information field can include a county field, an alarm duration field, an alarm source attribution field, an alarm cause field and the like.

[0070] In some embodiments, the county and district field can be used to indicate the county and district where the device issuing the alarm information is located, the alarm source can be determined according to the alarm information, for example, the base station name indicated by the alarm information can be used to determine the county and district where the base station is located, that is, the county and district where the base station alarm belongs to, and after determining the county and district field, the county and district field can be inserted into the alarm information by the list insertion method.

[0071] In some embodiments, the alarm duration field can be used to indicate the time elapsed from the generation of the alarm information to the current time, the alarm duration can be determined according to the latest occurrence time of the alarm information and the current time, and the alarm duration field can be generated.

[0072] In some embodiments, the alarm source can be the device issuing the alarm information, and the alarm source attribution field can be used to indicate the machine room, property right, coverage scenario, maintenance responsibility unit, and designated maintenance personnel to which the device issuing the alarm belongs, and the like. For example, the alarm source attribution field can be determined by matching the base station name in the alarm information with the management data, the alarm source attribution field can be used to locate the responsible unit and the person in charge more quickly when the device fails, and the related responsible unit or the person in charge can be facilitated to handle the device failure as soon as possible.

[0073] In some embodiments, the data cleaning module can determine the preliminary cause of the alarm. For example, the preliminary cause of the alarm can be determined according to the characteristics of the alarm information of the device, such as when the alarm information is a device disconnection and the characteristic value is identified as a port handshake timeout, the preliminary cause of the alarm can be determined as a device transmission interruption, and when the characteristic value is identified as a possible abnormal power supply state, the preliminary cause can be determined as a base station power interruption. For alarm information with a preliminary cause of transmission interruption, it can be further matched whether the power failure keyword is contained in the machine room power failure information or the radio frequency unit alarm information of the base station, and the comparison can be performed to determine that the transmission interruption is not caused by the power supply.

[0074] Step 202, the data cleaning module inserts the positioning information field into the alarm information to obtain a to-be-processed field.

[0075] In some embodiments, the data cleaning module can insert the above-mentioned positioning information field into the alarm information by the list insertion method to obtain the to-be-processed field.

[0076] Step 203, the data cleaning module performs data cleaning, standardization processing, and normalization processing on the to-be-processed field to obtain an alarm field.

[0077] In some embodiments, when the data cleaning module performs data cleaning on the to-be-processed field, the key words can be extracted, and the useless fields can be further removed, for example, the designated maintenance personnel corresponding to the faulty device, the fault cause, and the like can be determined as the key words.

[0078] In some embodiments, the data cleaning module can also normalize the to-be-processed field to obtain the alarm field.

[0079] In some embodiments, the data cleaning module can also extract and perform entity recognition on the alarm field to determine at least one response semantic label of the alarm field. For example, the data cleaning module can extract and perform entity recognition on the alarm information based on a BERT-BiLSTM-CRF model, and automatically match n response semantic labels for each alarm of the base station.

[0080] For example, the data cleaning module can determine the keyword of the alarm field as the response semantic label. For example, the semantic label can be "Xichong OLT" and "query OLT service information". The semantic label can be used to indicate the main content included in the alarm field, which can facilitate the user to find the corresponding information through the semantic label when actively querying the device status.

[0081] In some embodiments, the data cleaning module can determine the alarm type of the alarm field. For example, the data cleaning module can determine the alarm type according to the alarm name of the alarm information, the keyword of the alarm field, the alarm reason field, etc. The alarm type can be, for example, a definition service alarm, a radio unit alarm, a resource insufficient alarm, a high temperature alarm, a transmission service alarm, a power-off service alarm, a clock alarm, etc.

[0082] In summary, the above embodiments of the present application can obtain the alarm field by processing the alarm information, can determine the alarm root cause and attribution of the alarm device, can facilitate the determination of the dispatch information, can facilitate the designated maintenance personnel to determine the fault point and process the fault device, and can improve the processing efficiency of the alarm information.

[0083] Figure 3 A flowchart of an alarm information processing method provided by an embodiment of the present disclosure is shown in FIG. 3. As shown in FIG. 3, the method can include the following steps. Figure 3

[0084] Step 301: The information scheduling function module determines a function function corresponding to the alarm type of the alarm field according to the alarm type of the alarm field.

[0085] In some embodiments, the information scheduling module can include function function sub-modules of different alarm types, and can determine the function function sub-module for processing the alarm field according to the alarm type of the alarm field.

[0086] Step 302: The information scheduling function module processes the alarm field by using the function function corresponding to the alarm type to obtain the dispatch information.

[0087] ​In some embodiments, a specific functional submodule can be used to process the alarm field, and scheduling information can be generated based on the information in the alarm field. The information in the alarm field may include alarm time, base station name, alarm name, alarm reason, and related information, etc. In other words, the alarm time, base station name, alarm name, alarm reason, and related information can be input into the functional submodule and processed by the corresponding functional function to generate scheduling information.

[0088] In some embodiments, the generated scheduling information may include alarm root causes and scheduling instructions. For example, when the scheduling information is "Dear customer, 2023-01-01 02:27, Baofeng Village-HLH ​​[Rural], Tongchuan District, Xichong, network element connection interrupted (1 time, 1 time this month, 1 time this year, specific problem = power outage, 0 sensitive customers), number of affected customers: 69, it is recommended to restore the power supply system on-site, please arrange for processing in time!", the alarm root cause may be "specific problem = power outage", and the scheduling instruction may be "it is recommended to restore the power supply system on-site".

[0089] In summary, the above embodiments of this application, by processing the alarm fields to obtain scheduling information, can determine the root cause of the alarm and the scheduling instructions, which can facilitate the identification of the fault point and the scheduling of designated maintenance personnel to handle the fault point.

[0090] For the foregoing method embodiments, in order to simplify the description, they are all described as a series of actions. However, those skilled in the art should know that this disclosure is not limited to the described order of actions, because according to this disclosure, some steps may be performed in other orders or simultaneously.

[0091] Secondly, those skilled in the art should also know that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by this disclosure.

[0092] The technical solutions of this disclosure will be further described in detail below with reference to specific application embodiments.

[0093] This disclosure provides a network alarm information processing method. In order to achieve "zero outage" of the network (i.e., zero outage of base stations, home broadband, and dedicated lines) and reduce the outage rate, this proposal puts forward a network zero outage robot servo system based on a mobile office APP (WeChat group).

[0094] The method obtains unstructured data such as faults, power outages, power generation, etc. from wireless network management, transmission network management, fault management system, maintenance management system, tower centralized dispatch platform, optical fiber resource management system, etc. and inputs them into a pre-trained network domain structured data model to realize visual management, intelligent operation and maintenance, automatic fiber switching, cross-regional, cross-scene, cross-business network equipment, system state and maintenance personnel and "intelligent robots (such as zero withdrawal service assistants)" operation and maintenance scheduling action output, covering various capabilities such as anomaly detection, causal inference, root cause positioning, scheduling action, dynamic interactive tracking, fault one-key (automatic) recovery, etc. Real-time generation of scheduling information is pushed to the mobile office group in time, and the responsible unit and the responsible person are accurately matched with the "zero withdrawal service assistant" to carry out operation and maintenance scheduling and fault healing in real time.

[0095] The method changes the artificial process management into intelligent machine assistant, which helps to realize the following functions:

[0096] 1. Mobile office operation and maintenance scheduling based on internal communication tool platform, mobile office platform SMS reminder;

[0097] 2. Accurate matching of different county groups, personal accounts, and group notification of responsible persons or units to realize hierarchical scheduling, fault cause boundary, timely processing and assessment statistics;

[0098] 3. Scheduling information action second-level response, active scheduling and passive inquiry second-level response;

[0099] 4. In addition to text scheduling information, support for picture, Excel, Word file and other briefing information capabilities;

[0100] 5. Interactive action execution data collection and evaluation;

[0101] 6. Aggregating various platform data such as wireless, transmission, dynamic environment, tower, power generation, etc. to dig digital capabilities and realize digital transformation operation and maintenance goals;

[0102] 7. Mobile office scheduling production information visualization, realizing the goal of visual, controllable and controllable scheduling information of backup machine room;

[0103] 8. Data source faces platform grabbing, accurate custom data requirement field, data cleaning, high data collection effectiveness and efficiency, and low hardware requirements.

[0104] 9. The physical state of the optical cable, including routing, business, quality, fault point, is visualized and intelligently presented on the gateway platform, and the optical cable is regularly automatically detected and automatically switched by the remote control robot arm, optimizing the traditional manual operation and maintenance mode and improving the efficiency of operation and maintenance.

[0105] The present proposal realizes intelligent scheduling and tracking of fault alarm information by collecting alarm information in network management, cleaning alarm information data, and matching different alarm information and county name information through Long Short-Term Memory (LSTM) and BERT algorithms. The flowchart is shown in Figure 4 .

[0106] 1. Network fault information automatic acquisition technology - alarm automatic collection module and server

[0107] The alarm automatic collection module mainly writes an image recognition and clicking program based on the locate Center On Screen and Click methods in the PyAutoGui library (a cross-platform GUI automation Python module for programmatically controlling the mouse and keyboard). The program automatically triggers the "export" button of the "current alarm" function module of the Operation and Maintenance Center (OMC) at regular intervals, downloads the real-time alarm information generated by the service impact in Excel format to the server, and saves it to the server.

[0108] 2. Fault information intelligent delimiting and positioning technology - data cleaning module and server

[0109] The data cleaning module mainly based on Pandas library (Python's core data analysis support library, provides fast, flexible, clear data structure, aims to simply and intuitively process relational, labeled data) will load the above Excel file into the computer system through the read_csv method to convert the alarm data into a two-dimensional data table structure, then delete the useless field column through the drop method, convert the table header to a list using the columns.tolist method, based on the district and county names contained in the "alarm source" base station name, increase the district and county field through the list insertion method, used to identify the responsibility district and county of each base station alarm, the same method based on the "latest occurrence time" of the alarm to calculate the current alarm duration in real time, increase the alarm "duration" field, based on the "alarm source" base station name matching management data to obtain the alarm base station belonging to the machine room, property, coverage scenario, maintenance responsibility unit and other information and increase the corresponding field through the list insertion method, based on "positioning information" to obtain the characteristic value of base station disconnection information to analyze the preliminary cause of the alarm, when the characteristic value is identified as port handshake timeout, the preliminary cause is judged as base station transmission interruption, when the characteristic value is identified as possible abnormal power supply state, the preliminary cause is judged as base station power interruption, for the preliminary cause of transmission interruption, further match whether the machine room power failure information or the base station radio unit alarm information contains the keyword "power down", through the list insertion method to increase the alarm reason field, then further data cleaning, standardization and normalization, as the base station running state alarm data set at a certain moment. Based on the alarm name in the above alarm data set, define 15 alarm types such as service recovery alarm, radio unit alarm, resource insufficient alarm, high temperature alarm, transmission service recovery alarm, power failure service recovery alarm, clock alarm, etc., based on BERT-BiLSTM-CRF model to extract and identify entities, automatically match n response semantic labels for each alarm of the base station.

[0110] The specific semantic tags implemented are: XiChong OLT, query OLT service information; XiChong or TongChuan 4G, obtain 4G service information; XiChong or TongChuan 5G, obtain 5G service information; XiChong or QuXian high-speed rail (tunnel), query 4G high-speed rail alarm; XiChong or TongChuan standing wave, query 4G standing wave alarm; XiChong or TongChuan hardware, query 4G hardware failure alarm; XiChong or TongChuan radio frequency unit, query 4G radio frequency unit alarm; XiChong or TongChuan aau or XiChong 5G radio frequency unit, query 5G radio frequency unit alarm; WDM alarm, query WDM current fault; Ptn alarm, query Ptn / spn current fault; XiChong complaint details, obtain Excel home broadband complaint details table; XiChong power generation, obtain the current city oil machine power generation online situation; XiChong cumulative power generation, obtain the city's new cumulative oil machine power generation situation; XiChong iron tower power generation, obtain the current city iron tower oil machine power generation online situation; XiChong iron tower cumulative power generation, obtain the city's new cumulative iron tower oil machine power generation situation; XiChong power outage service, obtain 4G service caused by power outage; XiChong cumulative power outage in April, obtain April cumulative power outage details; XiChong cumulative power outage in 2023, obtain 2023 cumulative power outage details; XiChong transmission service, obtain 4G service caused by transmission interruption; Ring network fault, obtain heavy protection transmission ring network situation; XiChong high temperature alarm, obtain 4G high temperature alarm situation; Battery hidden danger reporting, push battery hidden danger reporting template, report battery hidden danger through the template; XiChong alarm details, obtain Excel alarm details table; XiChong service details, obtain Excel service details table; Today's service daily report, query today's service statistics; XiChong or TongChuan inspection, one-time query OLT, 4G service, 4G radio frequency unit fault, 4G hardware fault, 4G resource shortage alarm; XiChong installation, query the installation situation of each county; Dachuan Tingzi installation, installation Dachuan Tingzi installation situation; Dachun to be installed, installation Dachun to be installed warning, etc.

[0111] 3. Fault responsibility division and information automatic distribution technology - information dispatching function module

[0112] The information scheduling function module is constructed based on a mobile office APP (or WeChat) + uiautomation library (a UI automation framework based on Windows) to construct an information pushing, querying submodule and an information processing scheduling method submodule. The information pushing, querying submodule locates the mobile office APP displayed to the front end of the computer system by the Document Control (Class Name = 'Chrome_RenderWidgetHostHWND', Name = "mobile office") method in the uiautomation library, locates the group name to which the information is to be pushed by the Text Control (Name = "group name") method, and sends the produced scheduling information by the Send Keys method. The information processing scheduling method submodule encapsulates k different alarm type function modules, inputs the alarm time, base station name, alarm name, alarm reason and associated information into each function module from the alarm data set in the database one by one, outputs a corresponding piece of pushing scheduling information, and labels it as to be pushed. When the produced scheduling information is successfully pushed by the pushing submodule, it is labeled as having been pushed. When a mobile office group member initiates a query to the zero retreat service assistant, the querying submodule finds the corresponding alarm information by generating key prompt words to match response semantic labels after BERT semantic analysis, obtains the alarm data set in the semantic command from the database according to the above method, inputs the alarm time, base station name, alarm name, alarm reason and associated information into each function module one by one, outputs a corresponding piece of active query information, and sends the information to the above mobile office group (WeChat group) by the querying submodule.

[0113] In analyzing the text content of the group friend asking the zero service assistant, both text classification and entity recognition based on the BERT-BiLSTM-CRF model are used. The model encodes the text into three embedded feature units, including word embedding, position embedding, and segmentation embedding. After encoding, a cls identifier is added to the first position to form the input vector of the model. Then, the input text features are obtained through a multi-layer encoder with multiple attention mechanisms. The output data contains the information of the entire sentence in the first position and the information of each character in the other positions. In this way, the first position can be used for classification tasks, and the subsequent data can be used for entity recognition. Through text classification, the type of inquiry can be quickly located, and then combined with the extracted entity content, the instruction can be better clarified, and the next reply can be better determined. For example, if the group friend sends a query instruction "Xicheng County base station service withdrawal" to the zero service assistant, the analysis first locates the information query type, and then identifies the entities "Xicheng County" and "base station service withdrawal". The next step is to push the real-time information of the corresponding Xicheng County base station service withdrawal. If the inquiry is "base station service withdrawal processing method", the analysis is of the fault assistance type, and then the entity "base station service withdrawal" is identified. The next step is to push the common processing method of base station service withdrawal to assist the front-line in quick processing.

[0114] The above method is illustrated by an example as follows.

[0115] (1) This embodiment takes the information scheduling of the "zero service assistant" after the power failure event of a base station causes the base station equipment to power off and service withdrawal as an example. Based on an x86 server platform, a windows10 operating system is installed and connected to the network. The base station network management system is logged in through the mobile 4A platform, and the data source collection is completed.

[0116] (2) As shown in Figure 5 , a data collection module is developed based on the image recognition and click instructions in the PYATUOGUI library of the Python development language. The base station alarm list is automatically clicked to export, and through the loop function and time sleep function, the base station alarm list export is executed every 60 seconds, and the base station alarm data source is updated every 60 seconds.

[0117] (3) As shown in Figure 6As shown, based on the PANDAS library of the Python development language, the system loads the exported base station alarm list file through an EXCEL file reading command. Further, a "data cleaning module" is constructed using a field deletion command to remove invalid fields such as "level" and "grade". A "msg" information field and an "issent" field indicating whether to send information are added using a serialized column field insertion command. The issent value defaults to 0. When a message is sent, the issent field value is reassigned to 1 using a database table update command in the pymongo library. That is, when the issent value is 0, the corresponding information needs to be sent; when the issent value is 1, the corresponding information does not need to be sent and is ignored. A fault association module constructs sending information for different fields of base station fault information and assigns it to the msg field. The most critical innovation is the acquisition of the "location information" field. When the content includes "disconnection information = power supply status may be abnormal," it is initially determined to be a base station baseband processing unit (Building Baseband). If a power outage occurs in the BBU (Building Unit), and the message "Disconnection information = Port handshake timeout" appears in the message, it is initially determined to be caused by a transmission interruption. For example: "Dear customer, 2023-01-01 02:27, Baofeng Village-HLH ​​[Rural], Tongchuan District, Xichong, network element connection interrupted (1 time, 1 time this month, 1 time this year, specific problem = power outage, 0 sensitive customers), number of affected customers: 69, please arrange for handling in time!" The valid alarm information is written to the MongoDB database collection overalarmmsg and stored by inserting commands in the pymongo library.

[0118] (4) Figure 7 As shown, the message scheduling module uses a loop function and a timed sleep function to query the issent field value of the scheduling information in the overalarmmsg alarm information sending set in the MongoDB database every 30 seconds. When the issent value is 0, the module retrieves the field ("msg") of the outage alarm named "Network Element Connection Interruption" using the command to retrieve the field ("alarm_name"). Further, the module uses the copy command from the pyperclip library to copy the information to the clipboard. Then, using the uiautomation function in the mobile office message processing module, it defines the group name to be sent to, clicks the group, and pastes the information from the clipboard into the message sending window using the command to locate the mobile office APP message sending window. Finally, it uses the Enter command to send the message to the mobile office group.

[0119] 4. Remote-controlled robotic arm for automatic fiber optic patching and fault recovery technology – Remote control and recovery system for optical distribution network resource management

[0120] The optical distribution resource management system is based on artificial intelligence, accurate sensing, accurate electromechanical control, machine vision and other technologies, realizes the digitization, visualization, automation and intelligentization of network resource management, establishes a dumb resource scheduling management system with panoramic visualization and intelligent control from end to end, and has functions such as optical fiber resource visualization management, fault rapid recovery and automatic detection of fiber core state, etc. By comprehensively using AI+ technology, the operation and maintenance efficiency is improved, the business guarantee capability is improved, and the operation and maintenance cost is reduced.

[0121] Through intelligent research and judgment of faults in dumb resource network and operation risk early warning, auxiliary decision analysis and other work, intelligent monitoring of dumb resources is realized. Based on the above alarm information processing, the present proposal forms an end-to-end panoramic visual dumb resource scheduling management system in combination with mobile office APP (WeChat group), operation and maintenance management platform and intelligent optical distribution management system and other related systems, realizes remote management control and automatic recovery of optical distribution resources. After the occurrence of a fault in the transmission network, the fault position is automatically detected and judged based on the collected network management information, the fault device slot information is detected and analyzed, and after confirmation and feedback by the corresponding regional transmission maintenance personnel in the mobile office APP (WeChat group), the mechanical hand is remotely controlled to realize automatic fiber recovery of the fault slot, and the system related framework process is as shown in Figure 8

[0122] Optionally, the fiber core fiber recovery scheme can select a pre-set special design fiber tray, such as a circular ring or a vertical bar, based on the anti-winding fiber recovery technology. When the service is opened or recovered, the system can recommend different physical paths according to the intelligent routing algorithm, such as the shortest recovery time, the least number of nodes, the minimum link loss, etc. When the service is interrupted, the intelligent recovery option appears on the network management platform. The system recommends different physical paths to provide multiple recovery schemes according to the access cable conditions, and the fiber core quality can be automatically tested by OTDR before the switching is confirmed. After the manual confirmation in the mobile office APP, all devices in the whole link are simultaneously fiber-jumped to complete the rapid recovery of the service. The following fault scenarios can be quickly recovered by issuing instructions through the network management system or assigning maintenance to handle the fault in time, as follows:

[0123] If the system finds that the intelligent optical exchange - community optical exchange fiber core loss is large, the network management system will switch to the standby fiber core on the intelligent optical exchange side, and assign a fault work order to the maintenance unit. The maintenance personnel need to perform fiber-jumping of the corresponding fiber core on the community optical exchange side to quickly recover the service;

[0124] If the system finds that the intelligent optical exchange - community optical exchange optical cable is interrupted, the network management system will assign a fault work order to the maintenance unit, and the maintenance personnel will modify the fault on site;

[0125] ​The anti-tangling technology refers to determining the spatial relationship between two spatially skewed straight optical fibers within a limited range based on the spatial relationship of spatially skewed straight fibers and knot theory, forming a tangled wiring path with high penetration and low span. This enables autonomous management of massive cable paths, automatic cable patching, and prevents tangling at any two fiber cross-connections or any number of fiber patching operations.

[0126] 5. A method for network alarm information extraction and entity recognition based on the BERT-BiLSTM-CRF model

[0127] The BERT layer of this model pre-trains the input text to generate dynamic word vectors. These word vectors are then used as input to a BiLSTM layer for bidirectional training, further extracting text features. Weight checks directly evaluate which embeddings are preferred for specific downstream tasks. Finally, a CRF layer effectively constrains the dependencies between predicted labels, models the label sequence, and thus obtains the globally optimal sequence.

[0128] 5.1 BERT Model

[0129] The BERT model employs a bidirectional Transformer neural network as its encoder, allowing it to predict the next word by referencing both preceding and following input information. This is primarily achieved using a multi-head attention mechanism.

[0130]

[0131] MultiHead(Q,K,V)=Concat(head1,…,head n W o

[0132] head i =Attention(QW Q ,KW K VW V )

[0133] On the other hand, a "MASK language model" is used for model pre-training, masking 15% of the words in a sentence and predicting the masked words based on the context. During prediction,

[0134]

[0135] Where P(x) represents the target probability distribution, m i Indicates whether the i-th token is masked, x ＜i This represents all tokens preceding the i-th token.

[0136] When performing sentence-by-sentence relevance prediction

[0137]

[0138] where s and t represent two sentences respectively, denotes the vector representation of the sentence pair, t rand denotes a random sentence from a different document as s.

[0139] For example:

[0140] Input = "[cls] Jinshan computer room stop [mask1] alarm [sep] cause transmission [mask2] interrupt [sep]", where mask1 = "electricity", mask2 = "input", sentence_label = 1 (is the context relationship)

[0141] Therefore, the BERT model has strong semantic acquisition ability and entity relationship identification ability, and can effectively solve the problem of polysemy, and quickly attract the attention of researchers. The word vector output by the BERT model is composed of three parts: word vector, sentence vector and position vector.

[0142] 5.2 Bi-directional Long Short-Term Memory (Bi LSTM) model

[0143] Although BERT can extract text features, in order to more accurately extract entity classification and understand the context of text information on small sample data, the BiLSTM structure is introduced in this model. The BiLSTM structure is composed of forward LSTM and backward LSTM.

[0144] LSTM mainly realizes through controlling three gates:

[0145] forget gate: f t = σ(W f .[a t-1 ,x t ]+b f )

[0146] memory gate: i t = σ(W i .[a t-1 ,x t ]+b f )

[0147]

[0148] output gate: O t = σ(W o .[a t-1 ,x t ]+b o)

[0149] h t =O t *tanh(C t )

[0150] 5.2 CRF model

[0151] CRF model is a classical discriminative probabilistic undirected graph model, which mainly guarantees that the labels of adjacent words or characters in sequence labeling tasks follow certain rules, such as the BIO label used in named entity recognition (NER) model. The entity label starts with B, followed by I, and the non-entity label is O. The I label is followed by B label, not O label.

[0152] For example, “power failure alarm occurs in the comprehensive machine room of Xichong Gold Mountain”, which can be labeled as “B-CT (Xichong) I-CT (Chong) B-CT (Gold) I-MR (Mountain) I-MR (comprehensive) I-MR (integrated) I-MR (machine) I-MR (room) O (occurs) O (occurs) B-BD (stop) I-BD (power) I-BD (announcement) I-BD (warning)” (CT: county, MR: machine room, BD: fault).

[0153] The conditional probability distribution formula of CRF is:

[0154]

[0155] Where Y is the value of the output random variable, X is the value of the input random variable, Z(c) is the normalization factor, W k is the weight vector, and f k (y, c) is the feature function. As long as they can represent the relationship between the output random variable and the input random variable.

[0156] The feature function f k (y, c) is an indicator function, which takes the value 1 when (y, c) satisfies certain conditions, and 0 otherwise. The feature function can be any function,

[0157] The normalization factor Z(c) is a normalization constant, which makes the sum of the conditional probability distribution equal to 1. The calculation of Z(c) requires summing over all possible output sequences.

[0158] In summary, the above examples of the present disclosure use mobile office (WeChat group) as an innovative human-computer interaction method, which provides a more personalized user experience for operation and maintenance personnel. Even more personalized interactive information can be implanted in the operation and maintenance process, injecting vitality into the originally dull network operation and maintenance work, which is of great benefit to efficiency improvement.

[0159] This example makes the mobile office (WeChat group) robot a link between various operations and maintenance personnel. The previous method of operations and maintenance personnel working alone by receiving network management system fault information will be greatly improved. By forming an operations and maintenance group that includes the robot, information can be transmitted over a wide area, shared and discussed, and joint operations and maintenance can be carried out, thereby promoting the improvement of operations and maintenance efficiency.

[0160] This example demonstrates how remotely controlled automatic fiber optic jumper functionality can significantly reduce recovery time from accidents and faults, decrease customer complaints, and provide safety assurance for maintenance personnel in hazardous scenarios.

[0161] Figure 9 This is a block diagram of a control system 900 provided in an embodiment of this disclosure. Figure 9 As shown, the system 900 includes: an automatic alarm acquisition module 910, used to collect alarm information from the device and load the alarm information into a data cleaning module; a data cleaning module 920, used to preprocess the alarm information to obtain alarm fields; an information scheduling function module 930, used to process the alarm fields to obtain scheduling information, and when a first preset condition is met, to send the scheduling information to designated maintenance personnel and / or the optical distribution resource management remote control and recovery module, wherein the scheduling information includes at least the alarm root cause and scheduling instructions, and the scheduling information is used to instruct the designated maintenance personnel or the optical distribution resource management remote control and recovery module to process the alarm information of the device; and an optical distribution resource management remote control and recovery module 940, used to process the alarm information of the device.

[0162] In some embodiments, the alarm automation acquisition module 910 can also be used to identify the export button of the current alarm module in the operation and maintenance center; trigger the export button to obtain the alarm information of the device.

[0163] In some embodiments, the data cleaning module 920 can also be used to determine the location information field of the alarm information; insert the location information field into the alarm information to obtain the field to be processed; and perform data cleaning, standardization, and normalization on the field to be processed to obtain the alarm field.

[0164] In some embodiments, the data cleaning module 920 can also be used to extract and identify entities from alarm fields, determine at least one response semantic label of the alarm field, and determine the alarm type of the alarm field.

[0165] In some embodiments, the information scheduling function module 930 can also be used to determine the function corresponding to the alarm type based on the alarm type of the alarm field; and use the function corresponding to the alarm type to process the alarm field to obtain scheduling information.

[0166] In some embodiments, the first preset condition can include at least one of the following: the value of the sending state field of the scheduling information is a first value; the matching degree between the keyword received by the information scheduling function module and the at least one response semantic label is greater than a matching degree threshold, wherein the keyword is obtained by parsing the received query instruction by the information scheduling function module.

[0167] In some embodiments, the optical wiring resource management remote control and recovery module 940 can also be configured to determine the fault point based on the scheduling information, and remotely control the manipulator to process the fault point according to the scheduling instruction.

[0168] In summary, the control system 900 can determine the alarm root cause and the scheduling instruction by collecting the alarm information and determining the scheduling information according to the alarm information, and can facilitate the designated maintenance personnel or the optical wiring resource management remote control and recovery module to process the alarm information as soon as possible and improve the processing efficiency of the alarm information by sending the scheduling information to the designated maintenance personnel and / or the optical wiring resource management remote control and recovery module under the premise of meeting the first preset condition.

[0169] Figure 10 A block diagram of an electronic device 1000 for implementing the above method according to an embodiment of the present disclosure is provided.

[0170] Based on the hardware implementation of the above program modules, and in order to implement the method of the embodiment of the present disclosure, the embodiment of the present disclosure also provides an electronic device, as shown in the following. Figure 10 As shown in the following, the electronic device 1000 includes:

[0171] The communication interface 1001 can interact with other devices for information exchange;

[0172] The processor 1002 is connected with the communication interface 1001 to realize information exchange with other devices, and is used to run the computer program to execute the method provided by one or more technical solutions described above;

[0173] The memory 1003 stores the computer program.

[0174] Specifically, the processor 1002 can be configured to determine a first family to which a first object belongs according to the communication data of the first object, determine a target family in a case where the first family meets a first preset condition, and push target information to the target family.

[0175] It should be noted that the specific processing process of the processor 1002 can be understood with reference to the above method.

[0176] Of course, in actual applications, various components in the electronic device 1000 are coupled together through the bus system 1004. It can be understood that the bus system 1004 is used to realize the connection and communication between the components. In addition to including a data bus, the bus system 1004 also includes a power supply bus, a control bus, and a status signal bus. However, for the purpose of clear illustration, all the buses are marked as the bus system 1004 in the Figure 10

[0177] The memory 1003 in the embodiments of the present application is used to store various types of data to support the operation of the electronic device 1000. Examples of the data include any computer programs used for operation on the electronic device 1000.

[0178] The method disclosed in the embodiments of the present application can be applied to the processor 1002 or implemented by the processor 1002. The processor 1002 can be an integrated circuit chip with a processing capability. In the implementation process, each step of the above method can be completed by the integrated logic circuit or the instruction in the form of software in the processor 1002. The first processor 1002 described above can be a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The processor 1002 can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor can be a microprocessor or any conventional processor, etc. In combination with the steps of the method disclosed in the embodiments of the present application, the hardware decoding processor can be directly embodied to complete the execution, or the combination of hardware and software modules in the decoding processor can be used to complete the execution. The software module can be located in the storage medium, which is located in the memory 1003. The processor 1002 reads the information in the memory 1003 and combines the hardware to complete the steps of the above method.

[0179] In the exemplary embodiments, the electronic device 1000 can be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, micro-controllers, microprocessors, or other electronic elements for executing the above method.

[0180] In the exemplary embodiments, a non-transitory computer-readable storage medium including instructions, such as the memory 1004 including instructions, is also provided. The above instructions can be executed by the processor 1020 of the electronic device 1000 to complete the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, and an optical data storage device, etc.​

[0181] An embodiment of the present disclosure also provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to execute the method described in the above embodiments of the present disclosure.

[0182] An embodiment of the present disclosure also provides a chip, such as Figure 11 As shown, the chip includes a processor 1110 and an interface 1120. Wherein the number of the processor 1110 can be one or more, and the number of the interface 1120 can be multiple, the interface circuit is used to receive a signal from the memory of the electronic device, and send a signal to the processor, the signal includes the computer instructions stored in the memory, when the processor executes the computer instructions, so that the electronic device executes the method described in the above embodiments of the present disclosure.

[0183] It should be noted that, for the convenience of description, only the parts related to the application are shown in the drawings. The embodiments in the present application and the features in the embodiments can be combined with each other without conflict.

[0184] It should be understood that the "system", "device", "unit" and / or "module" used in the present application is a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0185] As shown in the present application and claims, unless the context clearly indicates otherwise, "one", "a", "an" and / or "the" do not refer to the singular, but also include the plural. Generally speaking, the terms "include" and "contain" only indicate the inclusion of the steps and elements explicitly identified, and these steps and elements do not constitute an exclusive list, and the method or device can also include other steps or elements. The element defined by the statement "including a" does not exclude the presence of another identical element in the process, method, product or device including the element.

[0186] In the description of the embodiments of the present application, unless otherwise specified, " / " represents the meaning of or, for example, A / B can represent A or B; "and / or" in this paper is only a description of the association between the associated objects, which means that there can be three kinds of relationships, for example, A and / or B, which can represent: A exists alone, A and B exist together, and B exists alone. In addition, in the description of the embodiments of the present application, "multiple" means two or more than two.

[0187] Hereinafter, the terms "first", "second", etc. are used only for the purpose of description, and are not to be construed as indicating or implying relative importance or a specific number of the technical features indicated. Thus, the features defined with "first", "second", etc. can explicitly or implicitly include one or more of the features.

[0188] Flow diagrams have been used herein to illustrate the operations according to embodiments of the present application in a particular order. It should be understood that the operations can not necessarily be performed in the order shown or in sequential order. Rather, various steps can be handled in reverse order or in substantially simultaneous order, or in some cases, the steps can be handled in another order.

[0189] In the description of the specification, the description of the terms "one embodiment", "some embodiments", "exemplary embodiment", "example", "specific example" or "some examples" etc. means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the present specification, the exemplary description of the above terms does not necessarily refer to the same embodiment or example. Also, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in an appropriate manner.

[0190] Any process or method descriptions or descriptions of the flow diagrams described herein or otherwise described herein can be understood as representing modules, segments, or portions of code that include one or more executable instructions for implementing specific logical functions or steps in the process, and that the alternate implementations of the preferred embodiments of the present application can perform these functions or steps in different sequences, in different orders, or in an overlapping manner, and that these alternate implementations can be appropriately implemented in hardware, software, or a combination thereof, as will be apparent to one skilled in the art.

[0191] The logic and / or steps represented in the flowcharts and / or described herein, for example, can be considered as a sequence of instructions to implement logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, apparatus, or device, such as a computer-based system, a system including a processing module, or other systems that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For purposes of this specification, a "computer-readable medium" can be any apparatus that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. The computer-readable medium can be a computer- readable storage medium or a computer-readable signal medium. The computer-readable storage medium can be, for example, but 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 (a non-exhaustive list) of the computer-readable storage medium include the following: an electrical connection having one or more wires (control method), a portable computer diskette (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, and a portable compact disc read-only memory (CD-ROM). In addition, the computer-readable medium can even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, for example, via the optical scanner of a device or device, then compiled, interpreted, or otherwise processed in a suitable manner, if necessary, and stored in a computer memory.

[0192] It should be understood that each part of the embodiments of the present application can be realized by hardware, software, firmware or a combination thereof. In the above embodiments, a plurality of steps or methods can be realized by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if realized by hardware, and as in another embodiment, any one or a combination of the following technologies known in the art can be used: discrete logic circuit with logic gate circuit for implementing logical functions on data signals, application specific integrated circuit with suitable combination logic gate circuit, programmable gate array (PGA), field programmable gate array (FPGA), etc.

[0193] Those skilled in the art of the present technology can understand that all or part of the steps carried out by the above-mentioned embodiment method can be completed by a program instructing the relevant hardware, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one of the steps of the method embodiment or a combination thereof.

[0194] In addition, each function unit in each embodiment of the present application can be integrated in one processing module, or each unit can exist physically separately, or two or more units can be integrated in one module. The integrated module can be realized in the form of hardware, or in the form of software function module. When the integrated module is realized in the form of software function module and sold or used as an independent product, it can also be stored in a computer readable storage medium. The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc.

[0195] Although the embodiments of the present application have been shown and described above, it should be understood by those skilled in the art that the above embodiments are exemplary and cannot be understood as limiting the present application, and those skilled in the art can make changes, modifications, replacements and variations to the above embodiments within the scope of the present application.

Claims

1. An alarm information processing method characterized by comprising: The method is executed by a control system, the control system comprising an alarm automatic collection module, a data cleaning module, an information scheduling function module, an optical wiring resource management remote control and recovery module, and the method comprising: The alarm automatic collection module collects alarm information of a device and loads the alarm information into the data cleaning module; The data cleaning module pre-processes the alarm information to obtain an alarm field; The information scheduling function module processes the alarm field to obtain scheduling information, and sends the scheduling information to a designated maintenance personnel and / or the optical wiring resource management remote control and recovery module when a first preset condition is met, wherein the scheduling information at least comprises an alarm root cause and a scheduling instruction, and the scheduling information is used to instruct the designated maintenance personnel or the optical wiring resource management remote control and recovery module to process the alarm information of the device.

2. The method of claim 1, wherein, The alarm automatic collection module collects alarm information of a device comprises: The alarm automatic collection module identifies an export button of a current alarm module of an operation and maintenance center; The alarm automatic collection module triggers the export button to obtain the alarm information of the device.

3. The method of claim 1, wherein, The data cleaning module processes the alarm information to obtain an alarm field comprises: The data cleaning module determines a positioning information field of the alarm information; The data cleaning module inserts the positioning information field into the alarm information to obtain a to-be-processed field; The data cleaning module performs data cleaning, standardization processing and normalization processing on the to-be-processed field to obtain the alarm field.

4. The method of claim 1, wherein, Before the information scheduling function module processes the alarm field to obtain scheduling information, the method further comprises: The data cleaning module extracts and identifies entities of the alarm field to determine at least one response semantic label of the alarm field; The data cleaning module determines an alarm type of the alarm field.

5. The method of claim 4, wherein, The information scheduling function module processes the alarm field to obtain scheduling information comprises: The information scheduling function module determines a function function corresponding to the alarm type of the alarm field according to the alarm type; The information scheduling function module processes the alarm field by using the function function corresponding to the alarm type to obtain the scheduling information.

6. The method of claim 4, wherein, The first preset condition can comprise at least one of the following: A value of a sending state field of the scheduling information is a first value; A keyword received by the information scheduling function module matches the at least one response semantic label by more than a matching threshold, wherein the keyword is obtained by the information scheduling function module by analyzing a received query instruction.

7. The method of claim 1, wherein, The optical wiring resource management remote control and recovery module processes the alarm information of the device comprises: The optical wiring resource management remote control and recovery module determines a fault point based on the scheduling information; The optical wiring resource management remote control and recovery module remotely controls a manipulator to process the fault point according to the scheduling instruction.

8. A control system characterized by, The system comprises: An alarm automatic collection module is configured to collect alarm information of the device and load the alarm information into a data cleaning module; The data cleaning module is configured to pre-process the alarm information to obtain alarm fields; An information scheduling function module is configured to process the alarm fields to obtain scheduling information, and send the scheduling information to a designated maintenance personnel and / or an optical distribution resource management remote control and recovery module when a first preset condition is met, wherein the scheduling information at least includes an alarm root cause and a scheduling instruction, and the scheduling information is used to instruct the designated maintenance personnel or the optical distribution resource management remote control and recovery module to process the alarm information of the device. The optical distribution resource management remote control and recovery module is configured to process the alarm information of the device.

9. An electronic device, comprising: comprise: one or more processors; a storage device in communication with the one or more processors and having one or more programs stored thereon; when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the method according to any one of claims 1-7.

10. A computer program product, characterised in that, comprise a computer program which, when executed by a processor, implements the method according to any one of claims 1-7.

Images