Methods, devices, equipment, and media for determining the operational efficiency loss information of generating units.

Abstract

This disclosure relates to a method, apparatus, equipment, and medium for determining the operation and maintenance efficiency loss information of a wind turbine unit. In response to a loss information query request, a named entity to be processed is obtained. From a pre-constructed loss information knowledge graph, target named entities matching the named entity to be processed, as well as target association relationships between different target named entities, are obtained. Nodes in the loss information knowledge graph are associated with named entities and their association relationships. Based on the identification information and loss information of the target turbine units corresponding to different target named entities, and the semantic information between different target named entities represented by the target association relationships, the operation and maintenance efficiency loss information of the target turbine unit is determined. This achieves the integration of named entities and their association relationships using a knowledge graph, and accurately and efficiently determines the operation and maintenance efficiency loss information of the turbine unit through named entity matching, which is beneficial for promoting the development of the wind power industry towards low cost and high efficiency.

Description

Technical Field

[0001] This disclosure relates to the field of wind farm operation and maintenance technology, and in particular to a method, apparatus, equipment and medium for determining the operation and maintenance efficiency loss information of a wind turbine unit. Background Technology

[0002] Tracing the operational efficiency loss information of wind turbines in wind farms provides an effective means to assess the operational level of wind farms, thereby promoting the production and operation activities of the wind power industry.

[0003] The operational efficiency loss information of wind turbines in wind farms mainly stems from various aspects, including decreased power generation performance, fault response time, and oversights in operation and maintenance. However, current operational efficiency loss information suffers from numerous problems, such as wide sources, diverse structures, and scattered storage, failing to be effectively integrated and posing a significant obstacle to tracing operational efficiency loss information. Therefore, it is necessary to provide a method for determining operational efficiency loss data of wind turbines to efficiently and accurately trace their operational efficiency loss information. Summary of the Invention

[0004] To address the aforementioned technical problems, this disclosure provides a method, apparatus, equipment, and medium for determining the operation and maintenance efficiency loss information of a generating unit.

[0005] Firstly, this disclosure provides a method for determining the operation and maintenance efficiency loss information of a generating unit, including:

[0006] In response to a request for loss information, retrieve the named entity to be processed;

[0007] From the pre-built loss information knowledge graph, target named entities that match the named entity to be processed and target association relationships between different target named entities are obtained. The nodes of the pre-built loss information knowledge graph are associated with named entities of historical operation and maintenance efficiency loss information of multiple units, and the connection relationship between different nodes of the pre-built loss information knowledge graph is the association relationship between different named entities.

[0008] Based on the identification information and loss information of the target units corresponding to different target named entities, and the semantic information between different target named entities represented by the target association relationship, the operation and maintenance efficiency loss information of the target units is determined.

[0009] Secondly, this disclosure provides a device for determining the operation and maintenance efficiency loss information of a generating unit, comprising:

[0010] The first acquisition module is used to acquire named entities to be processed in response to a request for loss information;

[0011] The second acquisition module is used to acquire target named entities that match the named entity to be processed and target association relationships between different target named entities from a pre-built loss information knowledge graph. The nodes of the pre-built loss information knowledge graph are associated with named entities of historical operation and maintenance efficiency loss information of multiple units, and the connection relationship between different nodes of the pre-built loss information knowledge graph is the association relationship between different named entities.

[0012] The determination module is used to determine the operation and maintenance efficiency loss information of the target unit based on the identification information and loss information of the target unit corresponding to different target named entities, as well as the semantic information between different target named entities represented by the target association relationship.

[0013] Thirdly, embodiments of this disclosure also provide an electronic device, the device comprising:

[0014] One or more processors;

[0015] Storage device for storing one or more programs.

[0016] When one or more programs are executed by one or more processors, the one or more processors implement the methods provided in the first aspect.

[0017] Fourthly, embodiments of this disclosure also provide a computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the method provided in the first aspect.

[0018] The technical solution provided in this disclosure has the following advantages compared with the prior art:

[0019] This disclosure discloses a method, apparatus, device, and medium for determining the operation and maintenance performance loss information of a wind turbine unit. The method includes: responding to a loss information query request by obtaining a named entity to be processed; obtaining target named entities matching the named entity to be processed and target association relationships between different target named entities from a pre-constructed loss information knowledge graph, wherein nodes in the pre-constructed loss information knowledge graph are associated with named entities representing historical operation and maintenance performance loss information of multiple wind turbine units, and the connection relationships between different nodes in the pre-constructed loss information knowledge graph represent association relationships between different named entities; and determining the operation and maintenance performance loss information of the target wind turbine unit based on the identification information and loss information of the target wind turbine units corresponding to different target named entities, and the semantic information between different target named entities represented by the target association relationships. Therefore, by integrating historical operation and maintenance performance loss data and their association relationships from a wide range of sources, with diverse structures and dispersed storage, and by matching named entities in the loss information query request with named entities in the loss information knowledge graph, accurate and efficient determination of the wind turbine unit's operation and maintenance performance loss information is achieved, which is beneficial for promoting the development of the wind power industry towards low cost and high efficiency. Attached Figure Description

[0020] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0021] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 A flowchart illustrating a method for determining operational efficiency loss information of a generating unit, provided in an embodiment of this disclosure;

[0023] Figure 2 A flowchart illustrating a method for generating a loss information knowledge graph provided in this embodiment of the disclosure;

[0024] Figure 3 This is a schematic diagram of the structure of a named entity extraction model provided in an embodiment of the present disclosure;

[0025] Figure 4 A schematic diagram of a device for determining the operation and maintenance efficiency loss information of a generating unit, provided in an embodiment of this disclosure;

[0026] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0027] To better understand the above-mentioned objectives, features, and advantages of this disclosure, the solutions disclosed herein will be further described below. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other.

[0028] Numerous specific details are set forth in the following description in order to provide a full understanding of this disclosure, but this disclosure may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only some, and not all, of the embodiments of this disclosure.

[0029] To solve the above problems, the following will be combined with... Figures 1-3 This disclosure describes a method for determining the operational efficiency loss information of a generating unit according to an embodiment. In this embodiment, the method for determining the operational efficiency loss information of the generating unit can be executed by an electronic device or a server. The electronic device may include devices with communication functions such as tablet computers, desktop computers, and laptop computers, or devices simulated by virtual machines or simulators. The server may include a single server or a server cluster. This embodiment uses an electronic device as the execution subject for specific explanation.

[0030] Figure 1 A flowchart illustrating a method for determining operational efficiency loss information of a generating unit according to an embodiment of this disclosure is shown.

[0031] like Figure 1 As shown, the method for determining the operation and maintenance efficiency loss information of this unit may include the following steps.

[0032] S110. In response to the loss information query request, obtain the named entity to be processed.

[0033] In this embodiment, when a user wants to query the unit's operation and maintenance efficiency loss information, the query function provided by the electronic device's interactive interface is triggered so that the electronic device can obtain the loss information query request. Alternatively, the user can input the loss information query request on the interactive interface, and the electronic device will parse the loss information query request to determine the named entity to be processed.

[0034] Optionally, the interactive interface can be a web interface for a wind turbine operation and maintenance efficiency loss tracing Q&A system built on the Grado framework. This interactive interface provides controls or search boxes for query functions to obtain loss information and ask questions.

[0035] Among them, the named entities to be processed are the nouns in the loss information query request.

[0036] The specific implementation methods of S110 include, but are not limited to, the following: extracting keywords from the loss information query request and determining the current keywords corresponding to the loss information query request; and obtaining the named entity to be processed from the current keywords based on the part of speech corresponding to the current keywords.

[0037] Specifically, the electronic device uses a string search algorithm (such as the Ahocorasick algorithm) to extract the current keyword from the loss query request, and then extracts the target keyword with the part of speech as a noun from the current keyword as the named entity to be processed.

[0038] For example, if the query request for loss information is "What was the power generation consumed by Unit 1 in July?", then the current keywords include "Unit 1", "July", "consumption", and "power generation", and the named entities to be processed include "Unit 1", "July", and "power generation".

[0039] In this way, by extracting keywords and performing part-of-speech analysis on loss information query requests, the named entities to be processed can be accurately obtained from the loss information query requests.

[0040] S120. Obtain target named entities that match the named entities to be processed and target association relationships between different target named entities from the pre-built loss information knowledge graph. The nodes of the pre-built loss information knowledge graph are associated with named entities of historical operation and maintenance efficiency loss information of multiple units, and the connection relationships between different nodes of the pre-built loss information knowledge graph are the association relationships between different named entities.

[0041] Understandably, the loss information knowledge graph integrates historical operation and maintenance performance loss data and their relationships from a wide range of sources, with diverse structures and scattered storage. The named entity to be processed is matched sequentially with the named entities of historical operation and maintenance performance loss information associated with the nodes of the loss information knowledge graph to obtain the target named entity that matches the named entity to be processed and the target relationship between different target named entities.

[0042] Among them, historical operational efficiency loss information includes a large amount of unstructured data and structured data.

[0043] Among them, the named entities of historical operation and maintenance performance loss information refer to the nouns in the historical operation and maintenance performance loss information.

[0044] The relationships between different named entities can be determined based on the semantic information between them.

[0045] In this way, by uniformly aggregating historical operational performance loss data onto a loss information knowledge graph, and leveraging the advantages of knowledge graphs such as high flexibility, good compatibility, and strong scalability, it is easy to quickly determine historical operational performance loss information, while also eliminating erroneous and redundant information.

[0046] S130. Based on the identification information and loss information of the target units corresponding to different target named entities, and the semantic information between different target named entities represented by the target association relationship, determine the operation and maintenance efficiency loss information of the target units.

[0047] In this embodiment, the electronic device obtains the identification information and loss information of the target unit from different target named entities, as well as the semantic information between different target named entities, and then generates the operation and maintenance efficiency loss data of the target unit based on the semantic information, identification information and loss information.

[0048] The target unit's identification information includes the name or code of the target named entity. Loss information includes the time and amount of loss.

[0049] For example, if the target named entity includes "Unit 1", "July", and "power generation", then the identification information of the target unit is "Unit 1", and the loss information includes "July" and "power generation".

[0050] The specific implementation methods of S130 include, but are not limited to, the following: based on semantic information, a statement is composed of the identification information and loss information of the target unit; the semantic information represented by the statement is used as the operation and maintenance efficiency loss information of the target unit.

[0051] Specifically, based on semantic information, the identification information and loss information of the target unit are connected to form a statement, and the semantic information represented by the statement is directly used as the operation and maintenance efficiency loss information of the target unit.

[0052] In this way, after determining the target named entities and target associations of the target unit, the statements are constructed in reverse through semantic analysis, thereby accurately and quickly determining the operational efficiency loss information of the target unit.

[0053] This disclosure discloses a method for determining the operation and maintenance performance loss information of a wind turbine unit, comprising: responding to a loss information query request and obtaining a named entity to be processed; obtaining target named entities matching the named entity to be processed and target association relationships between different target named entities from a pre-constructed loss information knowledge graph, wherein nodes of the pre-constructed loss information knowledge graph are associated with named entities representing historical operation and maintenance performance loss information of multiple wind turbine units, and the connection relationships between different nodes of the pre-constructed loss information knowledge graph represent association relationships between different named entities; determining the operation and maintenance performance loss information of the target wind turbine unit based on the identification information and loss information of the target wind turbine units corresponding to different target named entities, and the semantic information between different target named entities represented by the target association relationships. Thus, by integrating historical operation and maintenance performance loss data and their association relationships from a wide range of sources, with diverse structures and dispersed storage, and by matching the named entities in the loss information query request with the named entities in the loss information knowledge graph, accurate and efficient determination of the operation and maintenance performance loss information of the wind turbine unit is achieved, which is conducive to promoting the development of the wind power industry towards low cost and high efficiency.

[0054] In another embodiment of this disclosure, the method for creating a knowledge graph of loss information is explained in detail.

[0055] Figure 2 A flowchart illustrating a method for generating a loss information knowledge graph according to an embodiment of this disclosure is shown.

[0056] like Figure 2 As shown, the method for generating this loss information knowledge graph may include the following steps.

[0057] S210: Obtain historical operation and maintenance efficiency loss data for multiple units.

[0058] In this embodiment, the electronic device acquires historical operation and maintenance performance loss data of multiple units, including the target unit and other units, in order to integrate a large amount of structured and unstructured data.

[0059] Among them, historical operation and maintenance efficiency loss data refers to the actual operation and maintenance efficiency loss data of the unit over a period of time.

[0060] S220. Using a pre-trained named entity extraction model, process the historical operation and maintenance performance loss data to obtain the named entities of the historical operation and maintenance performance loss data.

[0061] In this embodiment, in order to improve the extraction accuracy of named entities in historical operation and maintenance performance loss data, the electronic device calls a pre-trained named entity extraction model to extract named entities from the historical operation and maintenance performance loss data.

[0062] The named entity extraction model is obtained by training the initial model using training samples. Specifically, the training samples include training operation and maintenance efficiency loss data and the classification labels of the training operation and maintenance efficiency loss data. The training operation and maintenance efficiency loss data in the training samples is input into the initial model to obtain predicted named entities. Then, the predicted named entities and classification labels are used to iteratively train the initial model until the model meets the iterative training conditions, thus obtaining the named entity extraction model.

[0063] The classification labels can be obtained by sequence labeling of named entities in the training operation and maintenance efficiency loss data using the BIOES annotation method. Specifically, the BIOES annotation method uses B-begin to label the beginning of named entities in the training operation and maintenance efficiency loss data, I-inside to label the middle named entities, O-outside to label the end of named entities, and S-single to label single-character entities.

[0064] Optionally, the named entity extraction model includes, but is not limited to, one of the following: a joint entity and relation extraction model based on a RoBERTa pre-trained deep learning model, a bidirectional long short-term memory network, and a conditional random field (RoBERTa-BiLSTM-CRF).

[0065] The specific implementation methods of S220 include, but are not limited to, the following methods:

[0066] S1. Based on the word vector extraction network in the pre-trained named entity extraction model, extract the first word vector sequence and the second word vector sequence from the historical operation and maintenance efficiency loss data, wherein the first word vector sequence and the second word vector sequence contain the same word vectors in reverse order.

[0067] S2. Based on the context extraction network in the pre-trained named entity extraction model, the first word vector sequence and the second word vector sequence are processed to obtain the context features of the historical operation and maintenance efficiency loss data.

[0068] S3. Based on the named entity prediction network in the pre-trained named entity extraction model, the context features are processed to obtain the named entities of historical operation and maintenance efficiency loss data.

[0069] Among them, the word vector extraction network is a pre-trained network, such as the RoBERTa network.

[0070] The specific implementation method of S1 includes, but is not limited to, the following methods: processing the historical operation and maintenance efficiency loss data based on the word embedding network in the word vector extraction network to obtain the word embedding features of the historical operation and maintenance efficiency loss data; processing the word embedding features based on the segment embedding network in the word vector extraction network to obtain the segment embedding features of the historical operation and maintenance efficiency loss data; and processing the segment embedding features based on the position embedding network in the word vector extraction network to obtain the first word vector sequence and the second word vector sequence.

[0071] The word embedding network can be Token Embeddings, used to extract the vector representation of the word itself as the word embedding feature. The segment embedding network can be Segment Embeddings, used to encode the positional information of words into feature vectors, thus obtaining the segment embedding feature. The position embedding network can be Position Embeddings, using vector representations that distinguish between two sentences, thus obtaining the first word vector sequence and the second word vector sequence.

[0072] The first and second word vector sequences contain the same word vectors in reverse order. For example, if the first word vector sequence is a forward sequence, the second word vector sequence is a reverse sequence; conversely, if the first word vector sequence is a reverse sequence, the second word vector sequence is a forward sequence.

[0073] Among them, the context extraction network is specifically a recurrent network, such as the Bidirectional Long Short-Term Memory (BiLSTM) network.

[0074] The specific implementation methods of S2 include, but are not limited to, the following: processing the first word vector sequence and the second word vector sequence based on the word vector processing network in the context extraction network to obtain the word vector bidirectional dependency features; processing the word vector bidirectional dependency features based on the linear layer in the context extraction network to obtain the linear features of the word vector bidirectional dependency features; and processing the linear features of the word vector bidirectional dependency features based on the output layer in the context extraction network to obtain the context features of the historical operation and maintenance efficiency loss data.

[0075] The word vector processing network can include an input layer and hidden layers to simultaneously capture both positive and negative information from the data, obtaining bidirectional dependency features of word vectors. Linear layers are used to map these bidirectional dependency features to a specific range, improving the model's fitting ability and the accuracy of contextual features.

[0076] Alternatively, the named entity prediction network is specifically a probabilistic model, such as a CRF network.

[0077] For ease of understanding, Figure 3 A schematic diagram of the named entity extraction model is shown. See also Figure 3 First, based on the RoBERTa network in the named entity extraction model, a first word vector sequence and a second word vector sequence are extracted from the historical operation and maintenance efficiency loss data. The first word vector sequence includes: The second word vector sequence includes: Then, the first and second word vector sequences are processed using the BiLSTM network in the named entity extraction model to obtain the contextual features of the historical operation and maintenance efficiency loss data. The contextual features include: h1, h2, ..., h n-1 h n Next, based on the CRF network in the named entity extraction model, the context features are processed to obtain named entities for historical operation and maintenance performance loss data. These named entities include C1, C2, ..., C... n-1 C n .

[0078] S230. Based on the semantic information between different named entities in the historical operation and maintenance efficiency loss data, determine the association between different named entities.

[0079] Since semantic information represents whether there is a relationship between different named entities, electronic devices can obtain named entities with semantic information and relationships from historical operation and maintenance efficiency loss data.

[0080] The above method enables the use of named entity extraction models to accurately identify named entities in historical operational efficiency loss data, and to quickly determine the relationships between different named entities based on semantic information between them.

[0081] S240. Using named entities of historical operation and maintenance efficiency loss data as nodes, and using the association relationships between different named entities as the connection relationships between different nodes, generate a loss information knowledge graph.

[0082] In this embodiment, after determining the named entities and the relationships between different named entities, the named entities of historical operation and maintenance efficiency loss data are used as nodes of the initial knowledge graph, and the relationships between different named entities are used as the connection relationships between different nodes on the initial knowledge graph, thereby generating a loss information knowledge graph.

[0083] Therefore, we first use the named entity extraction model to determine the named entities of historical operation and maintenance performance loss data, and then conduct semantic analysis on different named entities to accurately construct a knowledge graph of loss information, thereby improving the reliability of integrating historical operation and maintenance performance loss data and its relationships that are from a wide range of sources, have diverse structures, and are stored in a scattered manner.

[0084] This disclosure also provides a device for determining the operation and maintenance efficiency loss information of a unit, used to implement the above-described method for determining the operation and maintenance efficiency loss information of a unit. This device is configured in an electronic device or a server. The electronic device may include devices with communication functions such as tablet computers, desktop computers, and laptop computers, or devices simulated by virtual machines or simulators. The server may include a single server or a server cluster. This embodiment uses an electronic device as the device for determining the operation and maintenance efficiency loss information of a unit for specific explanation. The following is a detailed explanation in conjunction with... Figure 4 Please provide an explanation.

[0085] Figure 4 A schematic diagram of a device for determining the operation and maintenance efficiency loss information of a unit provided in an embodiment of this disclosure is shown.

[0086] like Figure 4 As shown, the unit's operation and maintenance efficiency loss information determination device 400 may include:

[0087] The first acquisition module 410 is used to acquire the named entity to be processed in response to the loss information query request;

[0088] The second acquisition module 420 is used to acquire target named entities that match the named entities to be processed and target association relationships between different target named entities from a pre-built loss information knowledge graph. The nodes of the pre-built loss information knowledge graph are associated with named entities containing historical operation and maintenance efficiency loss information of multiple units, and the connection relationships between different nodes of the pre-built loss information knowledge graph are association relationships between different named entities.

[0089] The determination module 430 is used to determine the operation and maintenance efficiency loss information of the target unit based on the identification information and loss information of the target unit corresponding to different target named entities, as well as the semantic information between different target named entities represented by the target association relationship.

[0090] This disclosure discloses a device for determining the operation and maintenance performance loss information of a wind turbine unit, comprising: in response to a loss information query request, acquiring a named entity to be processed; acquiring target named entities matching the named entity to be processed and target association relationships between different target named entities from a pre-constructed loss information knowledge graph, wherein nodes of the pre-constructed loss information knowledge graph are associated with named entities representing historical operation and maintenance performance loss information of multiple wind turbine units, and the connection relationships between different nodes of the pre-constructed loss information knowledge graph represent association relationships between different named entities; determining the operation and maintenance performance loss information of the target wind turbine unit based on the identification information and loss information of the target wind turbine units corresponding to different target named entities, and the semantic information between different target named entities represented by the target association relationships. Thus, by integrating historical operation and maintenance performance loss data and their association relationships from a wide range of sources, with diverse structures and dispersed storage, and by matching the named entities in the loss information query request with the named entities in the loss information knowledge graph, accurate and efficient determination of the operation and maintenance performance loss information of the wind turbine unit is achieved, which is conducive to promoting the development of the wind power industry towards low cost and high efficiency.

[0091] In some embodiments of this disclosure, the first acquisition module 410 includes:

[0092] The keyword extraction unit is used to extract keywords from the loss information query request and determine the current keywords corresponding to the loss information query request.

[0093] The first determining unit is used to obtain the named entity to be processed from the current keyword based on the part of speech corresponding to the current keyword.

[0094] In some embodiments of this disclosure, the determining module 430 includes:

[0095] The statement generation unit is used to compose a statement based on the semantic information, consisting of the identification information of the target unit and the loss information;

[0096] The second determining unit is used to use the semantic information represented by the statement as the operation and maintenance efficiency loss information of the target unit.

[0097] In some embodiments of this disclosure, the device further includes:

[0098] The third acquisition module is used to acquire historical operation and maintenance efficiency loss data of multiple units;

[0099] The fourth acquisition module is used to process the historical operation and maintenance efficiency loss data using a pre-trained named entity extraction model to obtain the named entities of the historical operation and maintenance efficiency loss data.

[0100] The association relationship determination module is used to determine the association relationship between different named entities based on the semantic information between different named entities in the historical operation and maintenance efficiency loss data;

[0101] The knowledge graph generation module is used to generate the loss information knowledge graph by using the named entities of the historical operation and maintenance efficiency loss data as nodes and the association relationships between different named entities as the connection relationships between different nodes.

[0102] In some embodiments of this disclosure, the fourth acquisition module includes:

[0103] The word vector extraction unit is used to extract a first word vector sequence and a second word vector sequence from the historical operation and maintenance efficiency loss data based on the word vector extraction network in the pre-trained named entity extraction model, wherein the first word vector sequence and the second word vector sequence contain the same word vectors in reverse order;

[0104] The context extraction unit is used to process the first word vector sequence and the second word vector sequence based on the context extraction network in the pre-trained named entity extraction model to obtain the context features of the historical operation and maintenance efficiency loss data.

[0105] The context processing unit is used to process the context features based on the named entity prediction network in the pre-trained named entity extraction model to obtain the named entities of the historical operation and maintenance efficiency loss data.

[0106] In some embodiments of this disclosure, the word vector extraction unit is specifically used for:

[0107] Based on the word embedding network in the word vector extraction network, the historical operation and maintenance efficiency loss data is processed to obtain the word embedding features of the historical operation and maintenance efficiency loss data;

[0108] Based on the segment embedding network in the word vector extraction network, the word embedding features are processed to obtain the segment embedding features of the historical operation and maintenance efficiency loss data;

[0109] Based on the position embedding network in the word vector extraction network, the segment embedding features are processed to obtain the first word vector sequence and the second word vector sequence.

[0110] In some embodiments of this disclosure, the context extraction unit is specifically used for:

[0111] Based on the word vector processing network in the context extraction network, the first word vector sequence and the second word vector sequence are processed to obtain bidirectional word vector dependency features;

[0112] Based on the linear layer in the context extraction network, the word vector bidirectional dependency features are processed to obtain the linear features of the word vector bidirectional dependency features;

[0113] Based on the output layer of the context extraction network, the linear features of the bidirectional dependency features of word vectors are processed to obtain the context features of the historical operation and maintenance efficiency loss data.

[0114] It should be noted that, Figure 4 The unit operation and maintenance efficiency loss information determination device 400 shown can perform... Figures 1-3 The various steps in the method embodiment shown are implemented. Figures 1-3 The processes and effects in the method embodiments shown are not described in detail here.

[0115] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure is shown.

[0116] like Figure 5 As shown, the electronic device may include a processor 501 and a memory 502 storing computer program instructions.

[0117] Specifically, the processor 501 may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0118] Memory 502 may include a large-capacity storage for information or instructions. For example, and not limitingly, memory 502 may include a hard disk drive (HDD), a floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or a Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 502 may include removable or non-removable (or fixed) media. Where appropriate, memory 502 may be internal or external to the integrated gateway device. In a particular embodiment, memory 502 is a non-volatile solid-state memory. In a particular embodiment, memory 502 includes read-only memory (ROM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (Electrically Programmable ROM, EPROM), an electrically erasable programmable PROM (EEPROM), an electrically alterable ROM (EAROM), or flash memory, or a combination of two or more of these.

[0119] The processor 501 reads and executes computer program instructions stored in the memory 502 to perform the steps of the unit operation and maintenance efficiency loss information determination method provided in the embodiments of this disclosure.

[0120] In one example, the electronic device may also include a transceiver 503 and a bus 504. Wherein, as... Figure 5 As shown, the processor 501, memory 502 and transceiver 503 are connected via bus 504 and communicate with each other.

[0121] Bus 504 may include hardware, software, or both. For example, and not limitingly, a bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industrial Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a MicroChannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses, or a combination of two or more of these. Where appropriate, bus 504 may include one or more buses. Although specific buses are described and illustrated in the embodiments of this application, this application considers any suitable bus or interconnection.

[0122] The following are embodiments of a computer-readable storage medium provided in this disclosure. This computer-readable storage medium and the method for determining the operation and maintenance efficiency loss information of the unit in the above embodiments belong to the same inventive concept. For details not described in detail in the embodiments of the computer-readable storage medium, please refer to the embodiments of the method for determining the operation and maintenance efficiency loss information of the unit described above.

[0123] This embodiment provides a storage medium containing computer-executable instructions. When executed by a computer processor, these instructions are used to perform a method for determining operational efficiency loss information of a unit. This method is applied to an electronic device corresponding to a robotic arm, wherein the end effector of the robotic arm is equipped with an external axis. The method includes:

[0124] In response to a request for loss information, retrieve the named entity to be processed;

[0125] From the pre-built loss information knowledge graph, target named entities that match the named entity to be processed and target association relationships between different target named entities are obtained. The nodes of the pre-built loss information knowledge graph are associated with named entities of historical operation and maintenance efficiency loss information of multiple units, and the connection relationship between different nodes of the pre-built loss information knowledge graph is the association relationship between different named entities.

[0126] Based on the identification information and loss information of the target units corresponding to different target named entities, and the semantic information between different target named entities represented by the target association relationship, the operation and maintenance efficiency loss information of the target units is determined.

[0127] Of course, the computer-executable instructions provided in the embodiments of this disclosure are not limited to the above-described method operations, but can also execute related operations in the unit operation and maintenance efficiency loss information determination method provided in any embodiment of this disclosure.

[0128] Based on the above description of the implementation methods, those skilled in the art can clearly understand that this disclosure can be implemented using software and necessary general-purpose hardware, and of course, it can also be implemented using hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this disclosure, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk, or optical disk, etc., including several instructions to cause a computer cloud platform (which may be a personal computer, server, or network cloud platform, etc.) to execute the unit operation and maintenance efficiency loss information determination method provided in the various embodiments of this disclosure.

[0129] Note that the above are merely preferred embodiments and technical principles of this disclosure. Those skilled in the art will understand that this disclosure is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of this disclosure. Therefore, although this disclosure has been described in detail through the above embodiments, this disclosure is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of this disclosure, the scope of which is determined by the scope of the appended claims.

Claims

1. A method for determining operation and maintenance efficiency loss information of a unit, characterized in that, The method comprises the following steps: acquiring historical operation and maintenance efficiency loss data of multiple units; processing the historical operation and maintenance efficiency loss data by using a pre-trained named entity extraction model to obtain named entities of the historical operation and maintenance efficiency loss data; determining an association relationship between different named entities based on semantic information between different named entities in the historical operation and maintenance efficiency loss data; generating a loss information knowledge graph by taking the named entities of the historical operation and maintenance efficiency loss data as nodes and taking the association relationship between different named entities as a connection relationship between different nodes; in response to a loss information query request, acquiring a to-be-processed named entity; from a pre-constructed loss information knowledge graph, acquiring target named entities matched with the to-be-processed named entity and a target association relationship between different target named entities, wherein the nodes of the pre-constructed loss information knowledge graph are associated with named entities of historical operation and maintenance efficiency loss information of multiple units, and the connection relationship between different nodes of the pre-constructed loss information knowledge graph is an association relationship between different named entities; determining operation and maintenance efficiency loss information of a target unit according to identification information and loss information of target units corresponding to different target named entities and semantic information between different target named entities represented by the target association relationship; the processing of the historical operation and maintenance efficiency loss data by using the pre-trained named entity extraction model to obtain the named entities of the historical operation and maintenance efficiency loss data comprises the following steps: based on a word vector extraction network in the pre-trained named entity extraction model, extracting a first word vector sequence and a second word vector sequence from the historical operation and maintenance efficiency loss data, wherein the first word vector sequence and the second word vector sequence contain the same word vectors in reverse order; based on a context extraction network in the pre-trained named entity extraction model, processing the first word vector sequence and the second word vector sequence to obtain context features of the historical operation and maintenance efficiency loss data; based on a named entity prediction network in the pre-trained named entity extraction model, processing the context features to obtain the named entities of the historical operation and maintenance efficiency loss data; the determination of operation and maintenance efficiency loss information of a target unit according to identification information and loss information of target units corresponding to different target named entities and semantic information between different target named entities represented by the target association relationship comprises the following steps: based on the semantic information, composing a sentence from the identification information of the target unit and the loss information; taking sentence meaning information represented by the sentence as the operation and maintenance efficiency loss information of the target unit.

2. The method of claim 1, wherein, the acquisition of a to-be-processed named entity in response to a loss information query request comprises the following steps: performing keyword extraction on the loss information query request to determine a current keyword corresponding to the loss information query request; based on a part of speech corresponding to the current keyword, acquiring the to-be-processed named entity from the current keyword.

3. The method of claim 1, wherein, The first word vector sequence and the second word vector sequence are extracted from the historical operation and maintenance efficiency loss data based on a word vector extraction network in the pre-trained named entity extraction model, including: The word embedding features of the historical operation and maintenance efficiency loss data are obtained by processing the historical operation and maintenance efficiency loss data based on a word embedding network in the word vector extraction network; The segment embedding features of the historical operation and maintenance efficiency loss data are obtained by processing the word embedding features based on a segment embedding network in the word vector extraction network; The first word vector sequence and the second word vector sequence are obtained by processing the segment embedding features based on a position embedding network in the word vector extraction network.

4. The method of claim 1, wherein, The context features of the historical operation and maintenance efficiency loss data are obtained by processing the first word vector sequence and the second word vector sequence based on a context extraction network in the pre-trained named entity extraction model, including: The word vector bidirectional dependency features are obtained by processing the first word vector sequence and the second word vector sequence based on a word vector processing network in the context extraction network; The linear features of the word vector bidirectional dependency features are obtained by processing the word vector bidirectional dependency features based on a linear layer in the context extraction network; The context features of the historical operation and maintenance efficiency loss data are obtained by processing the linear features of the word vector bidirectional dependency features based on an output layer in the context extraction network.

5. An apparatus for determining operation and maintenance efficiency loss information of a unit, the apparatus comprising: a unit operation and maintenance efficiency loss information determination unit configured to determine operation and maintenance efficiency loss information of the unit. Including: The third acquisition module is used for acquiring historical operation and maintenance efficiency loss data of multiple units; The fourth acquisition module is used for processing the historical operation and maintenance efficiency loss data by using a pre-trained named entity extraction model to obtain named entities of the historical operation and maintenance efficiency loss data; The association relationship determination module is used for determining the association relationship between different named entities based on semantic information between different named entities in the historical operation and maintenance efficiency loss data; The knowledge graph generation module is used for generating a loss information knowledge graph by taking the named entities of the historical operation and maintenance efficiency loss data as nodes and taking the association relationship between different named entities as connection relationships between different nodes; The first acquisition module is used for acquiring a to-be-processed named entity in response to a loss information query request; The second acquisition module is used for acquiring target named entities matched with the to-be-processed named entity and target association relationships between different target named entities from a pre-constructed loss information knowledge graph, wherein the nodes of the pre-constructed loss information knowledge graph are associated with named entities of historical operation and maintenance efficiency loss information of multiple units, and the connection relationships between different nodes of the pre-constructed loss information knowledge graph are association relationships between different named entities; The determination module is used for determining operation and maintenance efficiency loss information of a target unit according to identification information and loss information of different target units corresponding to different target named entities and semantic information between different target named entities represented by the target association relationship; The fourth acquisition module includes: The word vector extraction unit is configured to extract a first word vector sequence and a second word vector sequence from the historical operation and maintenance efficiency loss data based on a word vector extraction network in the pre-trained named entity extraction model, wherein the first word vector sequence and the second word vector sequence contain the same word vectors in reverse order; The context extraction unit is configured to process the first word vector sequence and the second word vector sequence to obtain context features of the historical operation and maintenance efficiency loss data based on a context extraction network in the pre-trained named entity extraction model; The context processing unit is configured to process the context features to obtain named entities of the historical operation and maintenance efficiency loss data based on a named entity prediction network in the pre-trained named entity extraction model; The determining module comprises: The sentence generation unit is configured to generate a sentence based on the semantic information, the sentence being composed of the identification information of the target unit and the loss information; The second determining unit is configured to take the sentence meaning information represented by the sentence as the operation and maintenance efficiency loss information of the target unit.

6. An electronic device, comprising: comprise: a processor; a memory configured to store executable instructions; wherein the processor is configured to read the executable instructions from the memory and execute the executable instructions to implement the method of any one of claims 1-4.

7. A computer-readable storage medium having stored thereon a computer program, characterized in that The storage medium stores a computer program, and when the computer program is executed by the processor, the processor implements the method of any one of claims 1-4.

Images