CN112527982A - Equipment management system, method, equipment and storage medium - Google Patents
Equipment management system, method, equipment and storage medium Download PDFInfo
- Publication number
- CN112527982A CN112527982A CN202011354445.1A CN202011354445A CN112527982A CN 112527982 A CN112527982 A CN 112527982A CN 202011354445 A CN202011354445 A CN 202011354445A CN 112527982 A CN112527982 A CN 112527982A
- Authority
- CN
- China
- Prior art keywords
- information
- knowledge
- target
- equipment
- query information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title abstract description 18
- 238000007726 management method Methods 0.000 claims description 82
- 238000012549 training Methods 0.000 claims description 34
- 238000004422 calculation algorithm Methods 0.000 claims description 28
- 238000012545 processing Methods 0.000 claims description 27
- 238000000605 extraction Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 6
- 230000006870 function Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 4
- 239000000463 material Substances 0.000 description 4
- 230000002787 reinforcement Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000012552 review Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000001556 precipitation Methods 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- 238000013024 troubleshooting Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
- G06F40/295—Named entity recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
Abstract
The embodiment of the invention discloses a device management system, a method, a device and a storage medium, wherein the system comprises: the knowledge pushing module is used for determining target query information according to the received equipment query information and sending the target query information to the equipment management module; the equipment management module is used for determining at least one piece of feedback information and the probability of each piece of feedback information according to the target query information and the pre-trained target knowledge base model; the result pushing module is used for displaying the received feedback information according to the corresponding probability, the problem that the information cannot be effectively inquired when the quantity of the equipment information is too large is solved, the target inquiry information is determined, then the feedback information is determined according to the target inquiry information and the target knowledge base model, the staff do not need to learn the equipment knowledge, the working intensity of the staff is reduced, the working efficiency is improved, the equipment knowledge is automatically learned through the target knowledge base model, when the user inquires data, the feedback information is automatically matched for the user, and the quick inquiry of the equipment knowledge is realized.
Description
Technical Field
The present invention relates to the field of device management technologies, and in particular, to a device management system, method, device, and storage medium.
Background
The following difficulties are often faced in the device management process: 1) the equipment data, the overhaul records, the reports and the standard quantity are large, and the understanding cost is high; 2) the long-term operation equipment maintenance history records are distributed at various places, and the analysis difficulty is high; 3) defects, troubleshooting and scheme making are slow, and thinking decision difficulty is high; 4) the knowledge amount of the equipment is larger and larger, and the people are overlapped to cause that the knowledge learning is difficult to accumulate. Therefore, a set of equipment knowledge base system is established to manage relevant data texts of the equipment, assist equipment fault diagnosis and promote equipment experience knowledge precipitation, and the method has important significance for improving the long-term operation safety and economy of the equipment.
Disclosure of Invention
The invention provides a device management system, a device management method, a device and a storage medium, which are used for realizing efficient management of the device.
In a first aspect, an embodiment of the present invention provides an apparatus management system, including:
the knowledge pushing module is used for determining target query information according to the received equipment query information and sending the target query information to the equipment management module;
the equipment management module is used for determining at least one piece of feedback information and the probability of each piece of feedback information according to the target query information and a pre-trained target knowledge base model;
and the result pushing module is used for displaying the received feedback information according to the corresponding probability.
In a second aspect, an embodiment of the present invention further provides a device management method, where the device management method is executed by the device management system described in any one of the embodiments of the present invention, and includes:
the knowledge pushing module determines target query information according to the received equipment query information and sends the target query information to the equipment management module;
the equipment management module determines at least one piece of feedback information and the probability of each piece of feedback information according to the target query information and a pre-trained target knowledge base model;
and the result pushing module displays the received feedback information according to the corresponding probability.
In a third aspect, an embodiment of the present invention further provides a computer device, including:
one or more processors;
a storage device for storing one or more programs,
when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement a device management method as described in an embodiment of the present invention.
In a fourth aspect, the embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the computer program implements a device management method as described in the embodiment of the present invention.
The embodiment of the invention provides a device management system, a device management method, a device and a storage medium, wherein the system comprises a fault management module, a device management module and a result pushing module, wherein the knowledge pushing module is used for determining target query information according to the received device query information and sending the target query information to the device management module; the equipment management module is used for determining at least one piece of feedback information and the probability of each piece of feedback information according to the target query information and a pre-trained target knowledge base model; the result pushing module is used for displaying the received feedback information according to the corresponding probability, the problem that the information cannot be effectively inquired when the quantity of the equipment information is too large is solved, the target inquiry information is determined through the equipment inquiry information input by the user, then the feedback information is determined according to the target inquiry information and the target knowledge base model, the staff does not need to learn the equipment knowledge, the working intensity of the staff is reduced, the working efficiency is improved, the equipment knowledge is automatically learned through the target knowledge base model, when the user inquires the data, the corresponding feedback information is automatically matched for the user, and the quick inquiry of the equipment knowledge is realized.
Drawings
Fig. 1 is a schematic structural diagram of a device management system in a first embodiment of the present invention;
fig. 2 is a schematic structural diagram of a device management system in the second embodiment of the present invention;
fig. 3 is a flowchart of a device management method in a third embodiment of the present invention;
fig. 4 is a schematic structural diagram of a computer device in the fourth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Example one
Fig. 1 is a schematic structural diagram of an apparatus management system according to an embodiment of the present invention, where the embodiment is applicable to a case of managing an apparatus, and the system includes: a knowledge pushing module 11, a device management module 12 and a result pushing module 13.
The knowledge pushing module 11 is configured to determine target query information according to the received device query information, and send the target query information to the device management module 12;
the equipment management module 12 is used for determining at least one piece of feedback information and the probability of each piece of feedback information according to the target query information and the pre-trained target knowledge base model;
and the result pushing module 13 is configured to display the received feedback information according to the corresponding probability.
In this embodiment, the knowledge pushing module 11 may be understood as a virtual module that performs corresponding processing according to the received information input by the user and sends the processed information to other processing modules, for example, the information input by the user is a related problem of a fault query, and the knowledge pushing module 11 performs corresponding processing and then determines a specific problem input by the user, and pushes the corresponding problem to a next processing module. The device query information can be understood as related information input by a user for querying the device; the target query information may be understood as standard query information that the device query system can recognize. For example, the device query information may be: how well the compressor temperature is too high; correspondingly, the target query information is: the reason why the compressor temperature is high is. The device query information may be: how the temperature of the compressor is too high; correspondingly, the target query information is: how to reduce the temperature of the compressor. The device management module 21 may be understood as a module that manages information related to devices in a unified manner.
The knowledge pushing module 11 receives device query information triggered or input by a user, performs semantic analysis on the device query information to obtain target query information recognizable by the system, and sends the target query information to the device management module. The device management system of the embodiment of the application can be deployed on a computer device, and accordingly, a user can input a problem to be queried, namely device query information, on a display interface of the computer device, or can set several commonly used problems in advance as the device query information, the user only needs to select one of the problems as the device query information through a triggering mode such as a button, and the computer device sends the device query information to the knowledge push module 11 after receiving the device query information input by the user.
In this embodiment, the target knowledge base model may be understood as a pre-trained knowledge question-answer model, and after the question is input into the model, the answer and the probability of the answer being accurate may be output accordingly. The feedback information may be understood as information corresponding to the target query information, which is used to respond to the target query information, such as failure cause analysis, failure handling measure suggestions, similar failure cases, equipment ledger information, equipment overhaul information, and the like.
The device management module 12 trains a target knowledge base model in advance, inputs target query information into the trained target knowledge base model, and queries the target query information according to learned experience by the target knowledge base model to obtain one or more feedback information matched with the target query information and the probability corresponding to each feedback information. When pushing the feedback information, the device management module 12 may select the first n pieces of feedback information with high probability for feedback according to the preset feedback number n.
In this embodiment, the result pushing module 13 may be understood as a module that presents corresponding feedback information to the user. After receiving the feedback information and the probability corresponding to the feedback information sent by the device management module 12, the result pushing module 13 displays the feedback information, which may be displayed from high to low according to the probability or from low to high according to the probability. For example, the device queries for information 1 (question 1), and the corresponding feedback information (answer) is: feedback information 1 (answer 1), probability 95%, feedback information 2 (answer 2) probability 92%, feedback information 3 (answer 3), probability 70%; and displaying the feedback information 1, the feedback information 2 and the feedback information 3 in sequence from high to low according to the probability.
The embodiment of the invention provides a device management system, which comprises a fault management module, a device management module and a result pushing module, wherein the knowledge pushing module is used for determining target query information according to the received device query information and sending the target query information to the device management module; the equipment management module is used for determining at least one piece of feedback information and the probability of each piece of feedback information according to the target query information and a pre-trained target knowledge base model; the result pushing module is used for displaying the received feedback information according to the corresponding probability, the problem that the information cannot be effectively inquired when the quantity of the equipment information is too large is solved, the target inquiry information is determined through the equipment inquiry information input by the user, then the feedback information is determined according to the target inquiry information and the target knowledge base model, the staff does not need to learn the equipment knowledge, the working intensity of the staff is reduced, the working efficiency is improved, the equipment knowledge is automatically learned through the target knowledge base model, when the user inquires the data, the corresponding feedback information is automatically matched for the user, and the quick inquiry of the equipment knowledge is realized.
Example two
Fig. 2 is a schematic structural diagram of a device management system according to a second embodiment of the present invention. The technical scheme of the embodiment is further refined on the basis of the technical scheme, and the system specifically comprises: a knowledge push module 21, a device management module 22 and a result push module 23, wherein the knowledge push module 21 comprises an information receiving unit 211 and an information determining unit 212.
An information receiving unit 211, configured to receive device query information input by a user;
and an information determining unit 212, configured to determine target query information according to the device query information in combination with a preset semantic processing algorithm, and send the target query information to the device management module 22.
In the present embodiment, the information receiving unit 211 may be understood as a data processing unit that receives user input information; the preset semantic processing algorithm may be understood as a preset algorithm for analyzing sentences, and may analyze the intention of the user, for example, algorithms such as similar semantic search, word disambiguation, multi-turn dialog, intention recognition, and the like, and the preset semantic processing algorithm may be one or more of the above algorithms.
The information receiving unit 211 receives the device query information input by the user, and sends the device query information to the information determining unit 212, and the information determining unit 212 processes the device query information according to a preset semantic processing algorithm, for example, identifies wrongly written characters in the device query information and corrects the wrongly written characters, and then determines target query information by searching similar semantics for the device query information.
Further, the information determining unit 211 is specifically configured to: determining the correlation degree of the equipment query information and each standard query information in a preset standard information table according to a preset semantic processing algorithm, and determining the maximum correlation degree; and judging whether the maximum correlation degree is greater than a preset correlation degree threshold value, if so, determining the standard query information corresponding to the maximum correlation degree as the target query information.
In this embodiment, the standard query information may be understood as query information set in advance according to an actual application situation, the device management module 22 and the target repository may identify the standard query information, and the standard information table may be understood as a data table storing a plurality of standard query information. The degree of correlation may be understood as a degree of correlation between two kinds of information, for example, the degree of correlation between a and B is 30%, the degree of correlation between a and B is considered to be low, the degree of correlation between a and B is 90%, the degree of correlation between a and B is considered to be high, and the degree of correlation in this embodiment is used to describe the degree of correlation between the device query information and the standard query information. The correlation threshold can be understood as a preset value used for measuring the degree of correlation.
Processing equipment query information according to a preset semantic processing algorithm, wherein the equipment query information may be related to one or more standard query information in a standard information table, determining the correlation degree corresponding to each piece of standard query information related to the equipment query information, then comparing the correlation degrees, determining the maximum correlation degree, judging whether the maximum correlation degree is greater than a correlation degree threshold value, if so, taking the standard query information corresponding to the maximum correlation degree as target query information, otherwise, determining that the correlation degree between the equipment query information and the standard query information is too low, and the equipment query information does not have the corresponding standard query information, so that query cannot be performed.
Further, the device management module 22 is further configured to:
a corpus training sample is obtained through the query-answer pair determining unit 221, and at least one knowledge query-answer pair is determined according to the corpus training sample, wherein the knowledge query-answer pair comprises a question and a corresponding answer;
each knowledge question-answer pair is input to the knowledge base model to be trained as a training sample through the training unit 222, and the knowledge base model to be trained is trained to obtain a target knowledge base model.
In the present embodiment, the question-answer pair determination unit 221 may be understood as a processing unit that generates a pair of intellectual questions and answers including answers corresponding to questions and questions. A corpus training sample may be understood as text used to train a knowledge base model, e.g., a piece of equipment's instructions, a fault analysis document, etc.
The method comprises the steps of obtaining text data related to equipment, using the text data as a corpus training sample, analyzing the obtained corpus training sample by the question-answer pair determining unit 221, decomposing the corpus training sample into a single information form, determining knowledge question-answer pairs according to each piece of information, and determining one or more knowledge question-answer pairs according to one piece of information.
In the present embodiment, the training unit 222 may be understood as a processing unit for training a model; the knowledge base model to be trained can be understood as a knowledge base model which is not trained, the knowledge base combines the traditional database technology and the artificial intelligence technology, knowledge representation and storage can be realized simultaneously, the knowledge base model is a reasonably organized set of declarative knowledge and procedural knowledge about a certain field, and after training is completed, the knowledge base model can obtain corresponding answers according to input problems.
The training unit 222 receives at least one knowledge question-answer pair sent by the question-answer pair determination unit 221, inputs each knowledge question-answer pair as a training sample into the knowledge base model to be trained, performs training of the knowledge base model to be trained, and takes the trained model as a target knowledge base model. The training knowledge base model to be trained can adopt modes such as elastic search recall, chapter sequencing, machine reading understanding algorithm and the like. Visualization tools can be provided for the target knowledge base model, the display of the incidence relation of the structured data is realized, and the graph exploration is supported.
Further, the question-answer pair determining unit 221 is specifically configured to:
performing text disassembly, paragraph extraction and basic knowledge item extraction on the text training sample to obtain at least one basic knowledge item; and determining knowledge question-answer pairs according to the basic knowledge items and the corpus processing algorithm.
In this embodiment, the basic knowledge item may be understood as a basic sentence constituting the text material, for example, the text material is a book, the basic knowledge item may be a sentence, and the text material is composed of a plurality of sentences. The corpus processing algorithm can be understood as an algorithm for processing sentences and generating knowledge question-answer pairs, such as Chinese word segmentation, named entity recognition, intention recognition, machine reading understanding, question generation and the like.
And processing the corpus training samples through a natural language algorithm, and sequentially performing text disassembly, paragraph extraction and basic knowledge item extraction. For example, the corpus training samples are respectively disassembled according to characters, tables and pictures, and divided into different texts, then each text is subjected to paragraph extraction, for example, a certain page of the text has 3 paragraphs of characters, the paragraph extraction is performed to obtain 3 paragraphs of characters, then basic knowledge item extraction is performed to each paragraph of characters to obtain basic knowledge items of a single sentence, and finally the basic knowledge items are processed through a corpus processing algorithm to obtain knowledge question and answer pairs. When the material training samples are processed and corresponding knowledge question-answer pairs are determined, corresponding manual standards and auditing functions can be provided, so that manual checking is facilitated, and the accuracy of the knowledge question-answer pairs is improved. The basic knowledge items are extracted automatically, the common knowledge question and answer pairs are generated, the artificial labeling amount can be effectively reduced, and the working efficiency is improved. The corresponding feedback information of the equipment query information input by the user is queried through the target knowledge base model, the calculation speed is high, and the accuracy is high.
Further, the result pushing module 23 is further configured to:
and receiving the relevancy ranking and/or the supplementary information fed back by the user, and feeding back the relevancy ranking and/or the supplementary information to the equipment management module, wherein the relevancy ranking is determined according to each piece of feedback information.
In this embodiment, the relevancy ranking may be understood as an arrangement order of the association degree between each piece of feedback information and the device query information. For example, the display order of the feedback information is: feedback information A, feedback information B and feedback information C, wherein the relevancy is sequenced as follows: feedback information B, feedback information A and feedback information C. The supplementary information may be understood as supplementing and/or modifying errors or deficiencies of the feedback information by the user according to the work experience.
When the result pushing module 23 displays the feedback information to the user according to the corresponding probability, the user can feed back whether the feedback information is related according to the experience of the user, that is, whether the feedback information and the probability displayed by the result pushing module are in accordance with the actual situation is determined. The feedback mode of the relevancy ranking can be as follows: the user reorders the feedback information according to his own work experience, may order the feedback information by means of buttons, sliding, or the like, and triggers the relevance ranking by means of buttons or other means, and the result pushing module 23 obtains the relevance ranking fed back by the user through a computer program or component. The feedback mode of the supplementary information may be: the user modifies and supplements the feedback information by adding, deleting and the like according to the work experience to form supplementary information, and the result pushing module 23 acquires the supplementary information fed back by the user through a computer program or a component.
Further, the device management module 22 is further configured to:
and optimizing the target knowledge base model according to the relevancy sorting and the reinforcement learning algorithm and/or updating the target knowledge base model according to the supplementary information.
In this embodiment, the reinforcement learning algorithm may select an optimal action capable of achieving its target through learning, cause a change in state through the action, obtain a delay report value, update an evaluation function, complete a learning process, enter a next round of learning training, repeat loop iteration until a condition for the entire learning is satisfied, and terminate the learning. Optimizing the recommendation function of the target knowledge base model according to the relevance ranking by the reinforcement learning algorithm; and updating the target knowledge base model according to the supplementary information, and updating the corpus training sample according to the supplementary information. When the update of the related content is completed according to the supplementary information, an update condition can be set, for example, the supplementary information is submitted to manual review, the related update is automatically performed when the review passes, and the update is not performed when the review fails.
The embodiment of the invention provides a device management system, which solves the problem that information cannot be effectively inquired when the quantity of device information is too large, determines target inquiry information through the device inquiry information input by a user, then determines feedback information according to the target inquiry information and a target knowledge base model, does not need staff to learn device knowledge, reduces the working intensity of the staff, improves the working efficiency, automatically learns the device knowledge through the target knowledge base model, and automatically matches the corresponding feedback information for the user when the user inquires data, thereby realizing the rapid inquiry of the device knowledge. Meanwhile, the problem that the existing equipment knowledge base system cannot perform model optimization and content updating according to user feedback is solved, and relevance sequencing and supplementary information fed back by the user are received; and optimizing the recommendation function of the target knowledge base model by using a reinforcement learning algorithm and relevance ranking fed back by the user, and meanwhile, automatically updating the target knowledge base model according to the supplementary information, so that the recommendation accuracy of the target knowledge base model is improved.
EXAMPLE III
Fig. 3 is a flowchart of a device management method according to a third embodiment of the present invention, where the method includes the following steps:
and step S31, the knowledge pushing module determines target query information according to the received device query information and sends the target query information to the device management module.
Step S32, the device management module determines at least one piece of feedback information and the probability of each piece of feedback information according to the target query information and the pre-trained target knowledge base model.
And step S33, the result pushing module displays the received feedback information according to the corresponding probability.
The embodiment of the invention provides a device management method, which solves the problem that information cannot be effectively inquired when the quantity of device information is too large, determines target inquiry information through the device inquiry information input by a user, then determines feedback information according to the target inquiry information and a target knowledge base model, does not need staff to learn device knowledge, reduces the working intensity of the staff, improves the working efficiency, automatically learns the device knowledge through the target knowledge base model, and automatically matches the corresponding feedback information for the user when the user inquires data, thereby realizing the rapid inquiry of the device knowledge.
Further, the knowledge pushing module determines target query information according to the received device query information, and sends the target query information to the device management module, and the method includes:
the information receiving unit receives equipment inquiry information input by a user;
and the information determining unit determines target query information according to the equipment query information by combining a preset semantic processing algorithm and sends the target query information to the equipment management module.
Further, the information determining unit determines target query information according to the device query information by combining a preset semantic processing algorithm, and the method comprises the following steps:
determining the correlation degree of the equipment query information and each standard query information in a preset standard information table according to the preset semantic processing algorithm, and determining the maximum correlation degree;
and judging whether the maximum correlation degree is greater than a preset correlation degree threshold value, if so, determining the standard query information corresponding to the maximum correlation degree as target query information.
Further, the method further comprises:
the equipment management module acquires a corpus training sample through a question-answer pair determining unit and determines at least one knowledge question-answer pair according to the corpus training sample, wherein the knowledge question-answer pair comprises a question and a corresponding answer;
and the equipment management module inputs each knowledge question-answer pair into a knowledge base model to be trained as a training sample through a training unit, trains the knowledge base model to be trained, and obtains the target knowledge base model.
Further, the device management module obtains a corpus training sample through a query-answer pair determining unit, and determines at least one knowledge query-answer pair according to the corpus training sample, including:
performing text disassembly, paragraph extraction and basic knowledge item extraction on the corpus training sample to obtain at least one basic knowledge item;
and determining at least one knowledge question-answer pair according to each basic knowledge item and the corpus processing algorithm.
Further, the method further comprises:
and the result pushing module receives the relevancy ranking and/or the supplementary information fed back by the user and feeds the relevancy ranking and/or the supplementary information back to the equipment management module, wherein the relevancy ranking is determined according to the feedback information.
Further, the method further comprises:
and the equipment management module optimizes the target knowledge base model according to the relevancy sorting and an enhanced learning algorithm and/or updates the target knowledge base model according to the supplementary information.
The device management method provided by the embodiment of the invention can be executed by executing the device management system provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method.
Example four
Fig. 4 is a schematic structural diagram of a computer apparatus according to a fourth embodiment of the present invention, as shown in fig. 4, the apparatus includes a processor 40, a memory 41, an input device 42, and an output device 43; the number of processors 40 in the device may be one or more, and one processor 40 is taken as an example in fig. 4; the processor 40, the memory 41, the input means 42 and the output means 43 in the device may be connected by a bus or other means, as exemplified by the bus connection in fig. 4.
The memory 41 is a computer-readable storage medium, and can be used for storing software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the device management method in the embodiment of the present invention. The processor 40 executes various functional applications and data processing of the device by executing software programs, instructions, and modules stored in the memory 41, that is, implements the device management method described above.
The memory 41 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal, and the like. Further, the memory 41 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, memory 41 may further include memory located remotely from processor 40, which may be connected to the device over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input device 42 is operable to receive input numeric or character information and to generate key signal inputs relating to user settings and function controls of the apparatus. The output device 43 may include a display device such as a display screen.
EXAMPLE five
An embodiment of the present invention further provides a storage medium containing computer-executable instructions, which when executed by a computer processor, perform a device management method, including:
the knowledge pushing module determines target query information according to the received equipment query information and sends the target query information to the equipment management module;
the equipment management module determines at least one piece of feedback information and the probability of each piece of feedback information according to the target query information and a pre-trained target knowledge base model;
and the result pushing module displays the received feedback information according to the corresponding probability.
Of course, the storage medium provided by the embodiment of the present invention contains computer-executable instructions, and the computer-executable instructions are not limited to the method operations described above, and may also perform related operations in the device management method provided by any embodiment of the present invention.
From the above description of the embodiments, it is obvious for those skilled in the art that the present invention can be implemented by software and necessary general hardware, and certainly, can also be implemented by hardware, but the former is a better embodiment in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a FLASH Memory (FLASH), a hard disk or an optical disk of a computer, and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device) to execute the methods according to the embodiments of the present invention.
It should be noted that, in the embodiment of the device management apparatus, each included unit and module are only divided according to functional logic, but are not limited to the above division as long as the corresponding functions can be implemented; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (10)
1. A device management system, comprising:
the knowledge pushing module is used for determining target query information according to the received equipment query information and sending the target query information to the equipment management module;
the equipment management module is used for determining at least one piece of feedback information and the probability of each piece of feedback information according to the target query information and a pre-trained target knowledge base model;
and the result pushing module is used for displaying the received feedback information according to the corresponding probability.
2. The system of claim 1, wherein the knowledge push module comprises:
the information receiving unit is used for receiving equipment inquiry information input by a user;
and the information determining unit is used for determining target query information according to the equipment query information by combining a preset semantic processing algorithm and sending the target query information to the equipment management module.
3. The system according to claim 2, wherein the information determining unit is specifically configured to:
determining the correlation degree of the equipment query information and each standard query information in a preset standard information table according to the preset semantic processing algorithm, and determining the maximum correlation degree;
and judging whether the maximum correlation degree is greater than a preset correlation degree threshold value, if so, determining the standard query information corresponding to the maximum correlation degree as target query information.
4. The system of claim 1, wherein the device management module is further configured to:
obtaining a corpus training sample through a question-answer pair determining unit, and determining at least one knowledge question-answer pair according to the corpus training sample, wherein the knowledge question-answer pair comprises a question and a corresponding answer;
and inputting the knowledge question-answer pairs serving as training samples into a knowledge base model to be trained through a training unit, and training the knowledge base model to be trained to obtain the target knowledge base model.
5. The system according to claim 4, wherein the question-answer pair determining unit is specifically configured to:
performing text disassembly, paragraph extraction and basic knowledge item extraction on the corpus training sample to obtain at least one basic knowledge item;
and determining at least one knowledge question-answer pair according to each basic knowledge item and the corpus processing algorithm.
6. The system of claim 1, wherein the result pushing module is further configured to:
receiving relevance ranking and/or supplementary information fed back by a user, and feeding back the relevance ranking and/or supplementary information to an equipment management module, wherein the relevance ranking is determined according to the feedback information.
7. The system of claim 6, wherein the device management module is further configured to:
and optimizing the target knowledge base model according to the relevancy sorting and an enhanced learning algorithm and/or updating the target knowledge base model according to the supplementary information.
8. A device management method, performed by the device management system of any one of claims 1-7, comprising:
the knowledge pushing module determines target query information according to the received equipment query information and sends the target query information to the equipment management module;
the equipment management module determines at least one piece of feedback information and the probability of each piece of feedback information according to the target query information and a pre-trained target knowledge base model;
and the result pushing module displays the received feedback information according to the corresponding probability.
9. A computer device, comprising:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the device management method of claim 8.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the device management method according to claim 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011354445.1A CN112527982A (en) | 2020-11-26 | 2020-11-26 | Equipment management system, method, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011354445.1A CN112527982A (en) | 2020-11-26 | 2020-11-26 | Equipment management system, method, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112527982A true CN112527982A (en) | 2021-03-19 |
Family
ID=74994264
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011354445.1A Pending CN112527982A (en) | 2020-11-26 | 2020-11-26 | Equipment management system, method, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112527982A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113468425A (en) * | 2021-06-30 | 2021-10-01 | 北京百度网讯科技有限公司 | Knowledge content distribution method and device, electronic equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109492077A (en) * | 2018-09-29 | 2019-03-19 | 北明智通（北京）科技有限公司 | The petrochemical field answering method and system of knowledge based map |
| CN109710772A (en) * | 2018-11-13 | 2019-05-03 | 国云科技股份有限公司 | A kind of question and answer library Knowledge Management System and its implementation based on deep learning |
| CN110717018A (en) * | 2019-04-15 | 2020-01-21 | 中国石油大学(华东) | Industrial equipment fault maintenance question-answering system based on knowledge graph |
| CN111708867A (en) * | 2020-01-10 | 2020-09-25 | 国网浙江省电力有限公司杭州供电公司 | Question and answer query method, device and equipment applied to electric power operation and inspection |
-
2020
- 2020-11-26 CN CN202011354445.1A patent/CN112527982A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109492077A (en) * | 2018-09-29 | 2019-03-19 | 北明智通（北京）科技有限公司 | The petrochemical field answering method and system of knowledge based map |
| CN109710772A (en) * | 2018-11-13 | 2019-05-03 | 国云科技股份有限公司 | A kind of question and answer library Knowledge Management System and its implementation based on deep learning |
| CN110717018A (en) * | 2019-04-15 | 2020-01-21 | 中国石油大学(华东) | Industrial equipment fault maintenance question-answering system based on knowledge graph |
| CN111708867A (en) * | 2020-01-10 | 2020-09-25 | 国网浙江省电力有限公司杭州供电公司 | Question and answer query method, device and equipment applied to electric power operation and inspection |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113468425A (en) * | 2021-06-30 | 2021-10-01 | 北京百度网讯科技有限公司 | Knowledge content distribution method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110968699B (en) | Logic map construction and early warning method and device based on fact recommendation | |
| CN109240901B (en) | Performance analysis method, performance analysis device, storage medium, and electronic apparatus | |
| CN106776532B (en) | Knowledge question-answering method and device | |
| CN105094368B (en) | A kind of control method and control device that frequency modulation sequence is carried out to candidates of input method | |
| WO2014155209A1 (en) | User collaboration for answer generation in question and answer system | |
| Zou et al. | Learning to rank for question-oriented software text retrieval (t) | |
| CN112163424A (en) | Data labeling method, device, equipment and medium | |
| CN111488466B (en) | Chinese language marking error corpus generating method, computing device and storage medium | |
| CN104331449A (en) | Method and device for determining similarity between inquiry sentence and webpage, terminal and server | |
| CN108932218B (en) | Instance extension method, device, equipment and medium | |
| CN109492081B (en) | Text information searching and information interaction method, device, equipment and storage medium | |
| US20210073216A1 (en) | Business intelligence system based on artificial intelligence and analysis method thereof | |
| CN112182145A (en) | Text similarity determination method, device, equipment and storage medium | |
| CN108776677B (en) | Parallel sentence library creating method and device and computer readable storage medium | |
| CN111767334A (en) | Information extraction method and device, electronic equipment and storage medium | |
| CN111325018A (en) | Domain dictionary construction method based on web retrieval and new word discovery | |
| JP2012243125A (en) | Causal word pair extraction device, causal word pair extraction method and program for causal word pair extraction | |
| CN114372122A (en) | Information acquisition method, computing device and storage medium | |
| CN112527982A (en) | Equipment management system, method, equipment and storage medium | |
| CN116049376B (en) | Method, device and system for retrieving and replying information and creating knowledge | |
| CN110851584B (en) | Legal provision accurate recommendation system and method | |
| CN115757720A (en) | Project information searching method, device, equipment and medium based on knowledge graph | |
| KR102298397B1 (en) | Citation Relationship Analysis Method and System Based on Citation Type | |
| CN115017271A (en) | Method and system for intelligently generating RPA flow component block | |
| CN114860901A (en) | Knowledge graph construction method based on ancient book information and question and answer system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210319 |