CN118195590A

CN118195590A - Equipment maintenance method, device, equipment and storage medium

Info

Publication number: CN118195590A
Application number: CN202410429340.XA
Authority: CN
Inventors: 夏雨
Original assignee: China Construction Bank Corp; CCB Finetech Co Ltd
Current assignee: China Construction Bank Corp; CCB Finetech Co Ltd
Priority date: 2024-04-10
Filing date: 2024-04-10
Publication date: 2024-06-14

Abstract

The specification relates to the technical field of computers, and provides a device maintenance method, a device and a storage medium. The method comprises the following steps: receiving a device maintenance request; determining target maintenance equipment information corresponding to the equipment maintenance request; determining associated equipment information according to the network topology information corresponding to the target maintenance equipment information; analyzing historical operation data and real-time operation data of the target maintenance equipment information and the associated equipment information in a preset time period to obtain an abnormal problem; judging whether the abnormal problem is associated with the associated equipment information; searching for alternative maintenance personnel according to the association condition; and selecting a target maintainer from the alternative maintainers according to the emergency degree of the abnormal problem so as to dispatch a corresponding equipment maintenance task to the target maintainer. According to the embodiment of the specification, the target maintainer can be determined efficiently and accurately, so that the equipment maintenance efficiency is improved.

Description

Equipment maintenance method, device, equipment and storage medium

Technical Field

The present disclosure relates to the field of computer technologies, and in particular, to a method, an apparatus, a device, and a storage medium for maintaining a device.

Background

When the machine equipment of the large data center needs to be maintained, the traditional mode is to remotely call the professional maintainer to go to the field for operation, so that the maintenance is performed by looking for the professional maintainer, looking for equipment problems from the arrival of the maintainer, feeding back maintenance results from the maintainer, and the maintenance is long in time consumption, slow in response and low in maintenance efficiency.

Disclosure of Invention

In view of the above, the present solution is proposed in order to overcome or at least partially solve the above-mentioned problems.

In one aspect, some embodiments of the present specification aim to provide a method of equipment maintenance, the method comprising:

receiving a device maintenance request;

Determining target maintenance equipment information corresponding to the equipment maintenance request;

determining associated equipment information according to the network topology information corresponding to the target maintenance equipment information;

Analyzing historical operation data and real-time operation data of the target maintenance equipment information and the associated equipment information in a preset time period to obtain an abnormal problem;

judging whether the abnormal problem is associated with the associated equipment information;

If the abnormal problem is associated with the associated equipment information, searching for an alternative maintainer with a business label of the abnormal problem, the target maintenance equipment information and the associated equipment information from a historical experience library according to the abnormal problem, the target maintenance equipment information and the associated equipment information;

If the abnormal problem is not associated with the associated equipment information, searching an alternative maintainer with a business label of the abnormal problem and the target maintenance equipment information from a historical experience library according to the abnormal problem and the target maintenance equipment information;

And selecting a target maintainer from the alternative maintainers according to the emergency degree of the abnormal problem so as to dispatch a corresponding equipment maintenance task to the target maintainer.

Further, before receiving the equipment maintenance request, the method further comprises:

acquiring real-time environment data monitored by a plurality of sensors arranged in a current data center;

identifying abnormal environment data from the real-time environment data;

and generating an equipment maintenance request according to the abnormal environment data.

Further, identifying abnormal environment data from the real-time environment data includes:

Extracting environmental index data corresponding to a target environmental index from the real-time environmental data;

and taking the environment index data reaching a first threshold value as abnormal environment data.

Further, after identifying the abnormal environmental data from the real-time environmental data, the method further includes:

classifying the real-time environment data based on the abnormal environment data to obtain normal environment data;

Inputting the abnormal environment data and the normal environment data into a pre-trained state estimation model to predict the normal environment data which needs preventive maintenance in the current environment according to a model output result;

and generating a device maintenance request according to the normal environment data which needs preventive maintenance and the abnormal environment data.

Further, the state estimation model is obtained by training based on historical environment data by the following steps:

Classifying the historical environment data to obtain historical normal environment data and historical abnormal data; the historical environment data are obtained through monitoring by sensors arranged in a current data center;

Establishing a first vector and a second vector corresponding to the historical normal data and the historical abnormal data based on a target environment index;

performing feature engineering processing on the first vector and the second vector to enable normal state features or abnormal state features to be added to the first vector and the second vector respectively, and splicing the first vector and the second vector after the features are added to obtain a third vector;

clustering the third vector by using a clustering algorithm according to the target environment index;

Performing unsupervised training according to the clustering result to obtain state estimation models of different categories, and calculating a state estimation value corresponding to each third vector by using the state estimation models;

Judging whether the state estimation value is positioned in a maintenance state interval which is evaluated in advance;

if the state estimation value is located in a pre-estimated maintenance state interval, training of the state estimation model is completed;

If the state estimation value is not located in the pre-estimated maintenance state interval, repeating the step of clustering the third vector by using a clustering algorithm, so as to retrain the state estimation model until the state estimation value and the pre-estimated maintenance state interval.

Further, determining associated device information according to the target maintenance device information and network topology information corresponding to the target maintenance device information includes:

Determining upstream and downstream devices corresponding to the target maintenance device in the current data center according to the target maintenance device information and the network topology information;

and selecting a plurality of first devices communicated with the target maintenance device from the upstream and downstream devices as associated devices to obtain associated device information.

Further, determining associated device information according to the target maintenance device information and the network topology information corresponding to the target maintenance device information, further includes:

determining the position of the target maintenance equipment according to the target maintenance equipment information;

searching peripheral equipment of the target maintenance equipment by using the position of the target maintenance equipment;

Selecting a plurality of first devices communicated with the target maintenance device from the upstream and downstream devices, and selecting a plurality of second devices with the physical distance smaller than a second threshold value from the peripheral devices;

And using the first equipment and the second equipment as associated equipment to obtain associated equipment information.

Further, analyzing the historical operation data and the real-time operation data of the target maintenance equipment information and the associated equipment information in a preset time period to obtain an abnormal problem, including:

performing feature extraction on historical operation data and real-time operation data of the target maintenance equipment information and the associated equipment information in a preset time period;

And inputting the feature extraction result into an anomaly classifier to obtain an anomaly problem.

Furthermore, the anomaly classifier takes the historical feature extraction result as input, takes the historical anomaly problem as target output, and is obtained by utilizing a sequential neural network to conduct supervised training.

Further, determining whether the anomaly issue is associated with the associated device information includes:

Judging whether the abnormal category corresponding to the abnormal problem belongs to a historical fault set corresponding to the associated equipment information;

if the abnormal problem does not belong to the equipment information, the abnormal problem is not associated with the associated equipment information;

if so, searching historical abnormal data of the associated equipment information, and judging whether the historical abnormal data has the problem that the degree of similarity or the degree of similarity with the abnormal problem reaches a third threshold value;

If so, the abnormal problem is associated with the associated equipment information;

If the abnormal problem does not exist, evaluating the influence range of the abnormal problem;

if the influence range is larger than a fourth threshold value, the abnormal problem is associated with the associated equipment information;

And if the influence range is not greater than a fourth threshold value, the abnormal problem is not associated with the associated equipment information.

Further, according to the emergency degree of the abnormal problem, selecting a target maintainer from the candidate maintainers to dispatch a corresponding equipment maintenance task to the target maintainer, including:

Acquiring historical maintenance experience of the alternative maintenance personnel;

calculating the standardized time consumption of each alternative maintainer for completing the maintenance task of the single equipment according to the time consumption, the number and the difficulty of the maintenance tasks of the historical equipment in the historical maintenance experience;

ranking the normalized time consumption from low to high and ranking the alternative maintenance personnel based on the order of the normalized time consumption;

If the emergency degree of the abnormal problem is greater than a fifth threshold value, selecting a plurality of alternative maintainers which are ranked in front as target maintainers;

and if the emergency degree of the abnormal problem is not greater than a fifth threshold, selecting a plurality of alternative maintenance personnel from the alternative maintenance personnel with the standardized time consumption less than a sixth threshold as target maintenance personnel.

In another aspect, some embodiments of the present specification further provide an apparatus for maintaining a device, the apparatus including:

The receiving module is used for receiving the equipment maintenance request;

the determining module is used for determining target maintenance equipment information corresponding to the equipment maintenance request;

The prediction module is used for determining associated equipment information according to the target maintenance equipment information and the network topology information corresponding to the target maintenance equipment information;

the abnormality analysis module is used for inputting historical operation data and real-time operation data of the target maintenance equipment information and the associated equipment information in a preset time period into an abnormality classifier to obtain an abnormality problem;

The judging module is used for judging whether the abnormal problem is associated with the associated equipment information;

The first matching module is used for searching for an alternative maintainer with business labels of the abnormal problem, the target maintenance equipment information and the associated equipment information from a historical experience library according to the abnormal problem, the target maintenance equipment information and the associated equipment information if the abnormal problem is associated with the associated equipment information;

The second matching module is used for searching for alternative maintenance personnel with business labels of the abnormal problems and the target maintenance equipment information from a historical experience library according to the abnormal problems and the target maintenance equipment information if the abnormal problems are not associated with the associated equipment information;

And the selecting module is used for selecting a target maintainer from the alternative maintainers according to the emergency degree of the abnormal problem so as to dispatch a corresponding equipment maintenance task to the target maintainer.

In another aspect, some embodiments of the present description also provide a computer device including a memory, a processor, and a computer program stored on the memory, which when executed by the processor, performs the instructions of the above method.

In another aspect, some embodiments of the present description also provide a computer storage medium having stored thereon a computer program which, when executed by a processor of a computer device, performs instructions of the above method.

In another aspect, some embodiments of the present description also provide a computer program product comprising a computer program which, when executed by a processor of a computer device, performs instructions of the above method.

One or more technical solutions provided in some embodiments of the present disclosure at least have the following technical effects:

According to the embodiment of the specification, firstly, an equipment maintenance request is automatically received, then target maintenance equipment information corresponding to the equipment maintenance request is determined, as faults are possibly caused not only by the target maintenance equipment but also by associated equipment of the target maintenance equipment or by the target maintenance equipment and the associated equipment together, therefore, the associated equipment information is determined through the target maintenance equipment information and network topology information corresponding to the target maintenance equipment information, historical operation data and real-time operation data of the target maintenance equipment information and the associated equipment information in a preset time period are analyzed, abnormal problems are determined, whether the current abnormal problems are associated with the associated equipment information or not is judged, candidate maintenance personnel with different service labels are matched from a historical experience library according to the associated conditions so as to ensure that the candidate maintenance personnel can efficiently maintain the equipment, and then, in order to further ensure a maintenance effect, the emergency of the abnormal problems is considered, the target maintenance personnel are selected from the candidate maintenance personnel, and corresponding equipment maintenance tasks are sent to the target maintenance personnel.

The foregoing description is merely an overview of some embodiments of the present disclosure, which may be practiced in accordance with the disclosure of the present disclosure, for the purpose of making the foregoing and other objects, features, and advantages of some embodiments of the present disclosure more readily apparent, and for the purpose of providing a more complete understanding of the present disclosure's technical means.

Drawings

In order to more clearly illustrate some embodiments of the present description or technical solutions in the prior art, the following description will briefly explain the embodiments or drawings needed in the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments described in the present description, and other drawings may be obtained according to these drawings without inventive effort to a person skilled in the art. In the drawings:

FIG. 1 illustrates a schematic diagram of an implementation system of a method of equipment maintenance in some embodiments of the present description;

FIG. 2 illustrates a flow chart of a method of equipment maintenance in some embodiments of the present description;

FIG. 3 is a schematic diagram illustrating steps for determining whether an anomaly issue is associated with associated device information according to some embodiments of the present disclosure;

FIG. 4 is a schematic diagram of an apparatus maintenance device according to some embodiments of the present disclosure;

Fig. 5 is a schematic diagram of a computer device provided in some embodiments of the present disclosure.

[ Reference numerals description ]

101. A terminal;

102. a server;

1201. a receiving module;

1202. A determining module;

1203. a prediction module;

1204. An anomaly analysis module;

1205. a judging module;

1206. a first matching module;

1207. A second matching module;

1208. selecting a module;

1302. a computer device;

1304. A processor;

1306. a memory;

1308. A driving mechanism;

1310. An input/output interface;

1312. An input device;

1314. An output device;

1316. A presentation device;

1318. A graphical user interface;

1320. a network interface;

1322. A communication link;

1324. A communication bus.

Detailed Description

In order to make the technical solutions in the present specification better understood by those skilled in the art, the technical solutions in the embodiments of the present specification will be clearly and completely described below with reference to the drawings in some embodiments of the present specification, and it is obvious that the described embodiments are only some embodiments of the present specification, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are intended to be within the scope of the present disclosure based on some embodiments in the present disclosure.

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

It should be noted that, in the technical scheme of the application, the acquisition, storage, use, processing and the like of the data all conform to the relevant regulations of the relevant laws and regulations.

It should be noted that, in the embodiments of the present application, some existing solutions in the industry such as software, components, models, etc. may be mentioned, and they should be regarded as exemplary only for illustrating the feasibility of implementing the technical solution of the present application, but it does not mean that the applicant has or must not use the "related matters" of the solution.

Fig. 1 is a schematic diagram of an implementation system of a method for maintaining equipment according to an embodiment of the present invention, which may include: the terminal 101 and the server 102 communicate with each other via a network, which may include a local area network (Local Area Network, abbreviated as LAN), a wide area network (Wide Area Network, abbreviated as WAN), the internet, or a combination thereof, and are connected to a website, user equipment (e.g., a computing device), and a back-end system. The staff can send the equipment maintenance request to the server 102 through the terminal 101, after the server 102 receives the equipment maintenance request, the data in the database is called for calculation processing, a calculation result is obtained, and the calculation result is sent to the terminal 101, so that the staff processes the service according to the calculation result.

In this embodiment of the present disclosure, the server 102 may be an independent physical server, or may be a server cluster or a distributed system formed by a plurality of physical servers, or may be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN, content Delivery Network), and basic cloud computing services such as big data and an artificial intelligence platform.

In an alternative embodiment, terminal 101 may include, but is not limited to, a self-service terminal device, a desktop computer, a tablet computer, a notebook computer, a smart wearable device, and the like. Alternatively, the operating system running on the electronic device may include, but is not limited to, an android system, an IOS system, linux, windows, and the like. Of course, the terminal 101 is not limited to the above-mentioned electronic device having a certain entity, and may be software running in the above-mentioned electronic device.

In addition, it should be noted that, fig. 1 is only an application environment provided by the present disclosure, and in practical application, a plurality of terminals 101 may also be included, which is not limited in this specification.

Fig. 2 is a flow chart of a method of equipment maintenance provided in accordance with an embodiment of the present invention, the present specification provides method operational steps as described in the examples or flow charts, but may include more or fewer operational steps based on conventional or non-inventive labor. The order of steps recited in the embodiments is merely one way of performing the order of steps and does not represent a unique order of execution. When a system or apparatus product in practice is executed, it may be executed sequentially or in parallel according to the method shown in the embodiments or the drawings. As shown in fig. 2, the method may include:

S201: receiving a device maintenance request;

S202: determining target maintenance equipment information corresponding to the equipment maintenance request;

s203: determining associated equipment information according to the network topology information corresponding to the target maintenance equipment information;

s204: analyzing historical operation data and real-time operation data of the target maintenance equipment information and the associated equipment information in a preset time period to obtain an abnormal problem;

s205: judging whether the abnormal problem is associated with the associated equipment information;

S206: if the abnormal problem is associated with the associated equipment information, searching for an alternative maintainer with a business label of the abnormal problem, the target maintenance equipment information and the associated equipment information from a historical experience library according to the abnormal problem, the target maintenance equipment information and the associated equipment information;

S207: if the abnormal problem is not associated with the associated equipment information, searching an alternative maintainer with a business label of the abnormal problem and the target maintenance equipment information from a historical experience library according to the abnormal problem and the target maintenance equipment information;

s208: and selecting a target maintainer from the alternative maintainers according to the emergency degree of the abnormal problem so as to dispatch a corresponding equipment maintenance task to the target maintainer.

It may be understood that in some embodiments, the devices may be machines located in a large data center, complex network topology relationships exist between the devices, the target maintenance device information includes an identity, a position, an effect, power consumption, a heat dissipation capacity in a unit time, and the like of the target maintenance device, corresponding historical operation data and real-time operation data may be called through the target maintenance device information and associated device information, so as to be used for analyzing the historical operation condition and the real-time operation condition of the target maintenance device and associated device, each maintainer in the historical experience library characterizes based on a user portrait manner, each maintainer establishes a corresponding service tag through the historical maintenance record, the service tag at least includes an anomaly problem that is successfully solved, a device that is successfully maintained, a maintenance duration, an anomaly problem that is not solved, an ID of the device that is not successfully maintained, an idle state, and the like, and by matching of the service tags, candidate maintainers with designated tags can be selected from the historical experience library, so that the candidate maintainers can effectively solve the anomaly problem.

In some embodiments, before receiving the device maintenance request, further comprising:

s301: acquiring real-time environment data monitored by a plurality of sensors arranged in a current data center;

S302: identifying abnormal environment data from the real-time environment data;

s303: and generating an equipment maintenance request according to the abnormal environment data.

It can be understood that in some embodiments, a plurality of types of sensors are distributed in a large data center and are used for monitoring temperature, humidity, harmful gas concentration, dust concentration and security conditions in the environment, and the sensors can monitor abnormal environmental data in a real-time environment, so that equipment maintenance requests can be quickly and accurately generated, and response speed of subsequent maintenance personnel can be improved.

In some embodiments, identifying abnormal environmental data from the real-time environmental data may include:

S401: extracting environmental index data corresponding to a target environmental index from the real-time environmental data;

s402: and taking the environment index data reaching a first threshold value as abnormal environment data.

It may be understood that in some embodiments, the target environmental indicator may include temperature, humidity, water leakage, concentration of harmful gas, dust concentration, noise, suspicious personnel conditions, and nonstandard operation conditions, and the corresponding environmental indicator data is extracted from the real-time environmental data through the target environmental indicator, so that the environmental indicator data reaching the first threshold is taken as abnormal environmental data, where the first threshold is not represented as a single value, but represents the first threshold corresponding to the target environmental indicator, that is, the first threshold is a critical standard for judging whether the environmental indicator data reaches an abnormal value, and for the suspicious personnel conditions and the nonstandard operation conditions, the environmental indicator data that cannot be represented directly and quantitatively may be represented by "0" to represent the normal conditions, and "1" represents the abnormal conditions, and at this time, the corresponding first threshold may be 1, so as to rapidly identify and obtain the abnormal environmental data.

In some embodiments, after identifying the abnormal environmental data from the real-time environmental data, the method may further include:

s501: classifying the real-time environment data based on the abnormal environment data to obtain normal environment data;

S502: inputting the abnormal environment data and the normal environment data into a pre-trained state estimation model to predict the normal environment data which needs preventive maintenance in the current environment according to a model output result;

S503: and generating a device maintenance request according to the normal environment data which needs preventive maintenance and the abnormal environment data.

Further, in some embodiments, the state estimation model is trained based on historical environmental data using the following steps:

s601: classifying the historical environment data to obtain historical normal environment data and historical abnormal data; the historical environment data are obtained through monitoring by sensors arranged in a current data center;

S602: establishing a first vector and a second vector corresponding to the historical normal data and the historical abnormal data based on a target environment index;

S603: performing feature engineering processing on the first vector and the second vector to enable normal state features or abnormal state features to be added to the first vector and the second vector respectively, and splicing the first vector and the second vector after the features are added to obtain a third vector;

S604: clustering the third vector by using a clustering algorithm according to the target environment index;

s605: performing unsupervised training according to the clustering result to obtain state estimation models of different categories, and calculating a state estimation value corresponding to each third vector by using the state estimation models;

s606: judging whether the state estimation value is positioned in a maintenance state interval which is evaluated in advance;

s607: if the state estimation value is located in a pre-estimated maintenance state interval, training of the state estimation model is completed;

S608: if the state estimation value is not located in the pre-estimated maintenance state interval, repeating the step of clustering the third vector by using a clustering algorithm, so as to retrain the state estimation model until the state estimation value and the pre-estimated maintenance state interval.

It may be understood that in some embodiments, besides performing equipment maintenance only when an abnormal situation occurs, preventative maintenance may be performed under normal conditions, specifically, training a state estimation model through historical environment data, establishing a third vector with state information (normal state feature and/or abnormal state feature) corresponding to the historical normal environment data and the historical abnormal environment data, and clustering the third vector to implement classification of the historical environment data, and respectively establishing different state estimation models based on clustering results, taking the different state estimation models as a whole, that is, obtaining the pre-trained state estimation model, then, in some embodiments, inputting the abnormal environment data and the normal environment data into the pre-trained state estimation model, first determining a clustering category corresponding to the abnormal environment data and the normal environment data, thereby obtaining state estimation values corresponding to the abnormal environment data and the normal environment data, comparing with a preset preventative maintenance threshold, if the state estimation values corresponding to the abnormal environment data and the normal environment data are greater than the preset preventative maintenance threshold, indicating that the current normal environment data needs to be subjected to preventative maintenance, further, in some embodiments, further, the first embodiment may further reduce the corresponding state index corresponding to the first environmental data and the normal environment data, and then, if the first environmental index corresponding to the first environmental index needs to be reduced, and the normal environment data may be subjected to preventative maintenance according to the first environmental index and the first environmental index is required to the normal environment data, thereby generating equipment maintenance requests according to the normal environment data and the abnormal environment data which are required to be subjected to preventive maintenance, so as to further improve the equipment stability.

In some embodiments, determining the associated device information according to the target maintenance device information and the network topology information corresponding to the target maintenance device information may include:

s701: determining upstream and downstream devices corresponding to the target maintenance device in the current data center according to the target maintenance device information and the network topology information;

S702: and selecting a plurality of first devices communicated with the target maintenance device from the upstream and downstream devices as associated devices to obtain associated device information.

It may be understood that in some embodiments, the associated device of the target maintenance device may be an upstream device and a downstream device that are directly connected to the target maintenance device, all devices in the data center communicate with each other to form a complex topology network, and the upstream device and the downstream device may be quickly and accurately determined according to the target maintenance device information and the network topology information of the target maintenance device information, so that a specified number of first devices are selected from the upstream device and the downstream device to obtain the associated device information.

In some embodiments, determining the associated device information according to the target maintenance device information and the network topology information corresponding to the target maintenance device information may further include:

s801: determining upstream and downstream devices corresponding to the target maintenance device according to the target maintenance device information and the network topology information;

s802: determining the position of the target maintenance equipment according to the target maintenance equipment information;

S803: searching peripheral equipment of the target maintenance equipment by using the position of the target maintenance equipment;

S804: selecting a plurality of first devices communicated with the target maintenance device from the upstream and downstream devices, and selecting a plurality of second devices with the physical distance smaller than a second threshold value from the peripheral devices;

s805: and using the first equipment and the second equipment as associated equipment to obtain associated equipment information.

It may be understood that in some embodiments, in addition to obtaining the associated device through the network topology information, the associated device may be determined according to the peripheral device where the target maintenance device is located, for example, when the target maintenance device has a hyperthermia abnormality, possibly due to a problem of a heat dissipation device around the target maintenance device, at this time, an appropriate associated device needs to be selected based on a physical distance angle, so as to obtain more comprehensive associated device information.

In some embodiments, analyzing the historical operation data and the real-time operation data of the target maintenance device information and the associated device information in the preset time period to obtain the abnormal problem may include:

s901: performing feature extraction on historical operation data and real-time operation data of the target maintenance equipment information and the associated equipment information in a preset time period;

s902: and inputting the feature extraction result into an anomaly classifier to obtain an anomaly problem.

Further, in some embodiments, the anomaly classifier takes the historical feature extraction result as input, takes the historical anomaly issue as target output, and uses the sequential neural network to perform supervised training to obtain the anomaly classifier.

It may be understood that in some embodiments, the anomaly problem is analyzed by using a pre-established anomaly classifier, so that the anomaly problem can be quickly and accurately determined, the anomaly classifier is trained by using a sequential neural network, the sequential neural network can effectively capture time sequence information and modes in the historical feature extraction result, and perform effective prediction and classification, and since the training process of the sequential neural network is not an important point of the present application, a specific training method is not repeated here.

Further, in some embodiments, since the anomaly classifier is a prediction model of a "blind box" and the situation of the maintenance of the actual device is very complex, only the anomaly problem can be obtained through the anomaly classifier, and the specific device corresponding to the anomaly problem cannot be located, so that it is further required to determine and analyze whether the anomaly problem is related to the associated device or not.

Referring to fig. 3, in some embodiments, determining whether the anomaly issue is associated with the associated device information may include:

s1001: judging whether the abnormal category corresponding to the abnormal problem belongs to a historical fault set corresponding to the associated equipment information;

S1002: if the abnormal problem does not belong to the equipment information, the abnormal problem is not associated with the associated equipment information;

S1003: if so, searching historical abnormal data of the associated equipment information, and judging whether the historical abnormal data has the problem that the degree of similarity or the degree of similarity with the abnormal problem reaches a third threshold value;

S1004: if so, the abnormal problem is associated with the associated equipment information;

s1005: if the abnormal problem does not exist, evaluating the influence range of the abnormal problem;

s1006: if the influence range is larger than a fourth threshold value, the abnormal problem is associated with the associated equipment information;

s1007: and if the influence range is not greater than a fourth threshold value, the abnormal problem is not associated with the associated equipment information.

It may be understood that in some embodiments, it is first determined whether an anomaly class corresponding to an anomaly problem belongs to a fault set corresponding to the associated device information, if the anomaly class does not belong to the fault set corresponding to the associated device information, it is stated that the associated device cannot have a current anomaly problem at all, and the anomaly problem is not associated with the associated device information, if the anomaly class does not belong to the fault set corresponding to the associated device information, historical anomaly data of the associated device information is further searched, and it is determined whether there is a problem that is too much anomaly problem in the historical anomaly data, if the anomaly problem is present, it is stated that the anomaly problem is possibly caused by the associated device, if the anomaly problem is not present, it is necessary to evaluate an influence range of the anomaly problem, specifically, the influence range includes both a physical influence range and a communication influence range, where the physical influence range refers to an influence range of physical environment index such as temperature, humidity, and concentration of harmful gas, the communication influence range refers to the influence range when the network communication environment is abnormal, layered evaluation can be carried out according to the network communication structure, meanwhile, the evaluation accuracy degree can be improved by combining the historical network communication data, when the communication influence range is specifically determined, the current communication influence range can be obtained based on the communication influence range matching table established by the historical network communication data, then if the influence range is larger and exceeds a fourth threshold value, the abnormal problem is indicated to have high association degree with the information of the associated equipment, in order to ensure the maintenance effect of the detection, the abnormal problem is considered to be associated with the information of the associated equipment at the moment, but if the influence range is smaller and does not exceed the fourth threshold value, the abnormal problem is indicated to have low association degree with the information of the associated equipment, in order to avoid the waste of human resources, the abnormal problem is not associated with the information of the associated equipment at the moment, thereby facilitating the accurate and effective determination of appropriate alternative maintenance personnel subsequently.

In some embodiments, selecting a target maintainer from the candidate maintainers according to the emergency degree of the abnormal problem, so as to dispatch a corresponding equipment maintenance task to the target maintainer may include:

s1101: acquiring historical maintenance experience of the alternative maintenance personnel;

s1102: calculating the standardized time consumption of each alternative maintainer for completing the maintenance task of the single equipment according to the time consumption, the number and the difficulty of the maintenance tasks of the historical equipment in the historical maintenance experience;

S1103: ranking the normalized time consumption from low to high and ranking the alternative maintenance personnel based on the order of the normalized time consumption;

S1104: if the emergency degree of the abnormal problem is greater than a fifth threshold value, selecting a plurality of alternative maintainers which are ranked in front as target maintainers;

S1105: and if the emergency degree of the abnormal problem is not greater than a fifth threshold, selecting a plurality of alternative maintenance personnel from the alternative maintenance personnel with the standardized time consumption less than a sixth threshold as target maintenance personnel.

It may be appreciated that in some embodiments, when the number of alternative maintenance personnel is greater, a screening work may be performed at this time to select a target maintenance personnel with high efficiency and suitability, specifically, according to the historical maintenance experience of the alternative maintenance personnel, the normalized time consumed for each alternative maintenance personnel to averagely complete a single equipment maintenance task may be calculated using the following formula:

Where t _s is the normalized time consumption, n is the total number of maintenance tasks completed by the current candidate maintenance personnel, t _i is the time consumption of the ith maintenance task, and D _i is the difficulty of the ith maintenance task.

Further, in some embodiments, the emergency degree of the abnormal problem may be determined according to the abnormal category to which the abnormal problem belongs, or may be determined according to a historical experience model, when the emergency degree of the abnormal problem is high, the abnormal problem is preferentially solved at this time, the candidate maintenance personnel are ranked from low to high in the standardized time consumption, the candidate maintenance personnel ranked in front are ranked based on the standardized time consumption sequence, a plurality of candidate maintenance personnel ranked in front are selected as target maintenance personnel, so as to accelerate the problem solving efficiency, when the emergency degree of the abnormal problem is low, the target maintenance personnel tend to be selected from the candidate maintenance personnel with the maintenance efficiency reaching the preset requirement (that is, the standardized time consumption is smaller than the sixth threshold), so as to reduce the possibility that the situation of shortage of the staff occurs when the emergency abnormal problem occurs later, and meanwhile, the current abnormal problem can be solved timely and efficiently.

It should be noted that although the operations of the method of the present invention are described in a particular order in the above embodiments and the accompanying drawings, this does not require or imply that the operations must be performed in the particular order or that all of the illustrated operations be performed in order to achieve desirable results. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step to perform, and/or one step decomposed into multiple steps to perform.

Corresponding to the above-mentioned equipment maintenance method, some embodiments of the present disclosure further provide an equipment maintenance device, as shown in fig. 4, and in some embodiments, the device may include:

a receiving module 1201, configured to receive a device maintenance request;

a determining module 1202, configured to determine target maintenance device information corresponding to the device maintenance request;

A prediction module 1203, configured to determine associated device information according to the target maintenance device information and network topology information corresponding to the target maintenance device information;

The anomaly analysis module 1204 is configured to input historical operation data and real-time operation data of the target maintenance device information and the associated device information in a preset time period into an anomaly classifier to obtain an anomaly problem;

a judging module 1205, configured to judge whether the abnormal problem is associated with the associated device information;

A first matching module 1206, configured to, if the abnormal problem is associated with the associated device information, search, from a historical experience library, for an alternative maintainer having a service tag of the abnormal problem, the target maintenance device information, and the associated device information according to the abnormal problem, the target maintenance device information, and the associated device information;

a second matching module 1207, configured to, if the abnormal problem is not associated with the associated device information, search, according to the abnormal problem and the target maintenance device information, for an alternative maintenance person having a service tag of the abnormal problem and the target maintenance device information from a historical experience library;

And a selecting module 1208, configured to select a target maintainer from the candidate maintainers according to the emergency degree of the abnormal problem, so as to dispatch a corresponding equipment maintenance task to the target maintainer.

For convenience of description, the above devices are described as being functionally divided into various units, respectively. Of course, the functions of each element may be implemented in one or more software and/or hardware elements when implemented in the present specification.

In the embodiments of the present disclosure, the user information (including, but not limited to, user device information, user personal information, etc.) and the data (including, but not limited to, data for analysis, stored data, presented data, etc.) are information and data that are authorized by the user and are sufficiently authorized by each party.

All steps of the method described in the present specification (the present application) may be implemented by a computer or the like.

The computer program product according to the present application is a software product for implementing the method according to the present application mainly by a computer program.

Embodiments of the present description also provide a computer device. As shown in fig. 5, in some embodiments of the present description, the computer device 1302 may include one or more processors 1304, such as one or more Central Processing Units (CPUs) or Graphics Processors (GPUs), each of which may implement one or more hardware threads. The computer device 1302 may also include any memory 1306 for storing any kind of information, such as code, settings, data, etc., and in a particular embodiment, a computer program on the memory 1306 and executable on the processor 1304, which when executed by the processor 1304, may perform the instructions of the method described in any of the embodiments above. For example, and without limitation, memory 1306 may include any one or more of the following combinations: any type of RAM, any type of ROM, flash memory devices, hard disks, optical disks, etc. More generally, any memory may store information using any technique. Further, any memory may provide volatile or non-volatile retention of information. Further, any memory may represent fixed or removable components of computer device 1302. In one case, when the processor 1304 executes associated instructions stored in any memory or combination of memories, the computer device 1302 can perform any of the operations of the associated instructions. The computer device 1302 also includes one or more drive mechanisms 1308 for interacting with any memory, such as a hard disk drive mechanism, optical disk drive mechanism, and the like.

Computer device 1302 can also include an input/output interface 1310 (I/O) for receiving various inputs (via input device 1312) and for providing various outputs (via output device 1314). One particular output mechanism may include a presentation device 1316 and an associated graphical user interface 1318 (GUI). In other embodiments, input/output interface 1310 (I/O), input device 1312, and output device 1314 may not be included, but merely as a computer device in a network. Computer device 1302 can also include one or more network interfaces 1320 for exchanging data with other devices via one or more communication links 1322. One or more communication buses 1324 couple the above-described components together.

The communication link 1322 may be implemented in any manner, for example, through a local area network, a wide area network (e.g., the internet), a point-to-point connection, etc., or any combination thereof. Communication link 1322 may include any combination of hardwired links, wireless links, routers, gateway functions, name servers, etc., governed by any protocol or combination of protocols.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), computer-readable storage media and computer program products according to some embodiments of the specification. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processor to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processor, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processor to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processor to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In a typical configuration, a computer device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.

Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Disks (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computer device. Computer readable media, as defined in the specification, does not include transitory computer readable media (transmission media), such as modulated data signals and carrier waves.

It will be appreciated by those skilled in the art that embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, the present specification embodiments may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present description embodiments may take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

The present embodiments may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The embodiments of the specification may also be practiced in distributed computing environments where tasks are performed by remote processors that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.

It should also be understood that, in the embodiments of the present specification, the term "and/or" is merely one association relationship describing the association object, meaning that three relationships may exist. For example, a and/or B may represent: a exists alone, A and B exist together, and B exists alone. In addition, the character "/" herein generally indicates that the front and rear associated objects are an "or" relationship.

In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for system embodiments, since they are substantially similar to method embodiments, the description is relatively simple, as relevant to see a section of the description of method embodiments.

In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the embodiments of the present specification. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.

The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and variations of the present application will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the application are to be included in the scope of the claims of the present application.

Claims

1. A method of equipment maintenance, the method comprising:

receiving a device maintenance request;

2. The apparatus maintenance method according to claim 1, further comprising, before receiving the apparatus maintenance request:

identifying abnormal environment data from the real-time environment data;

3. The apparatus maintenance method according to claim 2, wherein identifying abnormal environmental data from the real-time environmental data comprises:

4. The apparatus maintenance method according to claim 2, further comprising, after identifying abnormal environmental data from the real-time environmental data:

5. The equipment maintenance method according to claim 4, wherein the state estimation model is trained based on historical environmental data by:

6. The apparatus maintenance method according to claim 1, wherein determining associated apparatus information according to the target maintenance apparatus information and network topology information corresponding to the target maintenance apparatus information, comprises:

7. The apparatus maintenance method according to claim 1, wherein determining associated apparatus information according to the target maintenance apparatus information and network topology information corresponding to the target maintenance apparatus information, further comprises:

8. The apparatus maintenance method according to claim 1, wherein analyzing the historical operation data and the real-time operation data of the target maintenance apparatus information and the associated apparatus information in a preset period of time to obtain the abnormal problem includes:

9. The apparatus maintenance method according to claim 8, wherein the anomaly classifier takes a history feature extraction result as an input, takes a history anomaly problem as a target output, and is obtained by performing supervised training using a sequential neural network.

10. The apparatus maintenance method according to claim 1, wherein determining whether the abnormality problem is associated with the associated apparatus information comprises:

11. The equipment maintenance method according to claim 1, wherein selecting a target maintenance person from the candidate maintenance persons according to the degree of urgency of the abnormal problem to dispatch a corresponding equipment maintenance task to the target maintenance person, comprises:

12. An equipment maintenance device, the device comprising:

The receiving module is used for receiving the equipment maintenance request;

13. A computer device comprising a memory, a processor, and a computer program stored on the memory, characterized in that the computer program, when being executed by the processor, performs the instructions of the method according to any of claims 1-11.

14. A computer storage medium having stored thereon a computer program, which, when executed by a processor of a computer device, performs the instructions of the method according to any of claims 1-11.

15. A computer program product, characterized in that the computer program product comprises a computer program which, when being executed by a processor, executes instructions of the method according to any of claims 1-11.