CN116467606A - Determination method, device, equipment and medium of decision suggestion information - Google Patents
Determination method, device, equipment and medium of decision suggestion information Download PDFInfo
- Publication number
- CN116467606A CN116467606A CN202310200387.4A CN202310200387A CN116467606A CN 116467606 A CN116467606 A CN 116467606A CN 202310200387 A CN202310200387 A CN 202310200387A CN 116467606 A CN116467606 A CN 116467606A
- Authority
- CN
- China
- Prior art keywords
- historical
- solution
- fault information
- determining
- target
- 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 claims abstract description 139
- 239000013598 vector Substances 0.000 claims description 54
- 230000008569 process Effects 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 16
- 238000003860 storage Methods 0.000 claims description 13
- 238000012549 training Methods 0.000 claims description 12
- 230000011218 segmentation Effects 0.000 claims description 11
- 238000012545 processing Methods 0.000 description 10
- 238000004891 communication Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 5
- 238000000605 extraction Methods 0.000 description 4
- 238000013145 classification model Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000003058 natural language processing Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000003672 processing method Methods 0.000 description 3
- 238000012163 sequencing technique Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000036651 mood Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000004321 preservation Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the application discloses a method, a device, equipment and a medium for determining decision suggestion information. Wherein the method comprises the following steps: according to the similarity of the target fault information and the historical fault information, determining similar historical fault information meeting a similarity condition from the historical fault information; determining a target method keyword corresponding to the target fault information based on a pre-trained keyword prediction model; and determining a history solution corresponding to the target method keyword as a first history solution, and determining decision suggestion information according to the similar history fault information and the first history solution. According to the technical scheme, the historical fault information similar to the target fault information and the solution method matched with the target fault information are determined through the decision suggestion information, the historical fault record text is fully analyzed and utilized, and the accuracy of the decision suggestion for locating the target fault information is improved.
Description
Technical Field
The present invention relates to the field of intelligent manufacturing technologies, and in particular, to a method, an apparatus, a device, and a medium for determining decision advice information.
Background
With the popularization and development of automation equipment, more and more manual operations are being replaced by automation equipment, and the historical fault information of the equipment recorded in the production management process is usually recorded in a text form, so that how to solve the current fault problem by using the historical fault record text is a problem to be solved.
The main scheme at present is to search a historical fault problem and a solution method which are similar to the current fault problem from a historical fault record text based on data (such as average repair time and average fault time) of a numerical value type.
However, the existing searching method has single searching dimension, does not fully analyze and utilize the historical fault record text, and influences the positioning accuracy of the specific solution of the current fault problem.
Disclosure of Invention
The invention provides a method, a device, equipment and a medium for determining decision suggestion information, which can determine a solution corresponding to a current fault from a historical fault record text. .
According to an aspect of the present invention, there is provided a method of determining decision advice information, the method comprising:
according to the similarity of the target fault information and the historical fault information, determining similar historical fault information meeting a similarity condition from the historical fault information;
Determining a target method keyword corresponding to the target fault information based on a pre-trained keyword prediction model;
and determining a history solution corresponding to the target method keyword as a first history solution, and determining decision suggestion information according to the similar history fault information and the first history solution.
According to another aspect of the present invention, there is provided a decision advice information determining apparatus including:
the similar historical fault information determining module is used for determining similar historical fault information meeting a similarity condition from the historical fault information according to the target fault information and the similarity of the historical fault information;
the target method keyword prediction module is used for determining target method keywords corresponding to the target fault information based on a pre-trained keyword prediction model;
and the decision suggestion information determining module is used for determining a historical solution corresponding to the target method keyword as a first historical solution and determining decision suggestion information according to the similar historical fault information and the first historical solution.
According to another aspect of the present invention, there is provided an electronic apparatus including:
At least one processor; and
a memory communicatively coupled to the at least one processor; wherein,,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the method of determining decision advice information according to any of the embodiments of the present invention.
According to another aspect of the present invention, there is provided a computer readable storage medium storing computer instructions for causing a processor to implement the method for determining decision advice information according to any of the embodiments of the present invention when executed.
The technical scheme of the embodiment of the application comprises the following steps: according to the similarity of the target fault information and the historical fault information, determining similar historical fault information meeting a similarity condition from the historical fault information; determining a target method keyword corresponding to the target fault information based on a pre-trained keyword prediction model; and determining a history solution corresponding to the target method keyword as a first history solution, and determining decision suggestion information according to the similar history fault information and the first history solution. According to the technical scheme, the historical fault information similar to the target fault information and the solution method matched with the target fault information are determined through the decision suggestion information, the historical fault record text is fully analyzed and utilized, and the accuracy of the decision suggestion for locating the target fault information is improved.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for determining decision advice information according to one embodiment of the present application;
FIG. 2 is a flow chart of a method for determining decision advice information according to a second embodiment of the present application;
fig. 3 is a schematic structural diagram of a determining device for decision advice information according to a third embodiment of the present application;
fig. 4 is a schematic structural diagram of an electronic device implementing a method for determining decision advice information according to an embodiment of the present application.
Detailed Description
In order to make the present invention better understood by those skilled in the art, the following description will be made in detail, with reference to the accompanying drawings, in which embodiments of the present invention are shown, and it is apparent that the described embodiments are only some, but not all, embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
It should be noted that the terms "first," "second," "target," and the like in the description and claims of the present invention and in the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example 1
Fig. 1 is a flowchart of a method for determining decision advice information according to an embodiment of the present application, where the method may be performed by decision advice information determining means, which may be implemented in hardware and/or software, and the decision advice information determining means may be configured in an electronic device with data processing capabilities. As shown in fig. 1, the method includes:
S110, according to the similarity of the target fault information and the historical fault information, determining similar historical fault information meeting the similarity condition from the historical fault information.
The target fault information may reflect a fault problem to be solved, and the target fault information may be fault information of various types such as equipment, products, and processes, for example, equipment abnormality information, a problem that a certain index of a product is unqualified, problem information of a certain abnormal node in a process, and the like. In one possible embodiment, the target fault information may be text of a worker recording the fault information, and in another possible embodiment, the target fault information may be fault detection information of the device itself, and may be generated by the device itself. The historical fault information can be recorded text of past fault information, the historical fault information can be fault information of various types such as equipment, products and processes, each piece of historical fault information corresponds to a historical solution method, for example, the historical fault information is that the A component leaks air to cause the B material to be grabbed to fail, and the corresponding historical solution method can be that the A component is replaced.
Further, the similarity condition may be determined according to an actual situation, which is not limited in this embodiment of the present application, for example, by comparing the similarity between the target fault information and the historical fault information through a natural language processing method, the historical fault information with the similarity reaching the similarity threshold is determined as the similar historical fault information; or determining the previous preset number of historical fault information as similar historical fault information according to the similarity of the historical fault information after the sorting from large to small; alternatively, the historical fault information, for which the similarity reaches the similarity threshold and the similarity rank is within a preset number, is determined as the similar historical fault information.
Specifically, since the target fault information and the historical fault information can be text-form information, the similarity between each historical fault information and the target fault information can be determined by a natural language processing method, the historical fault information meeting the similarity condition is determined to be similar historical fault information, and the similar historical fault information can be used as a reference when decision suggestion information is subsequently determined.
S120, determining target method keywords corresponding to the target fault information based on a pre-trained keyword prediction model.
The keyword prediction model may predict keywords in a solution method of the fault information, for example, input the target fault information to the keyword prediction model, and may output target method keywords, which may reflect keywords in respective methods of solving the target fault information. The keyword prediction model in the embodiment of the application can be obtained through the relation between the historical learning fault information and the keywords of the solution method of the historical fault information in the model training process.
In this embodiment of the present application, the determined target method keyword may be keywords of multiple solutions, because for the same fault information, there may be multiple solutions, for example, in the case that the fault is a component leakage, the solutions may have: replacement of the A part, screwing of the valve of the A part and the like.
In the embodiment of the application, the target method keywords are obtained according to the keyword prediction model, and a mode of treating the problem by historical staff can be reflected, and a large amount of practical experience is included, so that the target method keywords obtained through the keyword prediction model have important significance for accurately solving the target fault problem.
S130, determining a history solution corresponding to the target method keyword as a first history solution, and determining decision suggestion information according to the similar history fault information and the first history solution.
The first history solution may solve the problem described by the target fault information, and in the history solution, the first history solution may be determined according to the number of target method keywords included in each history solution, and specific conditions of the first history solution are determined, which is not limited in this embodiment, for example: determining solutions, which are included in each history solution and have the number of target method keywords reaching a first preset number, as first history solutions; or determining the first historical solution method as the first preset number of solution methods with a larger number of target method keywords in each historical solution method; or determining the number of the included target method keywords to reach the first preset number, and determining the first preset number of solutions containing the larger number of the target method keywords as the first historical solution.
In the embodiment of the present application, similar historical fault information is reflected on the historical fault information that is closer to the target fault information on the fault description, and the first historical solution is reflected on the solution method for solving the target fault information, so that both the similar historical fault information and the first historical solution can be decision suggestion information.
In one possible embodiment, similar historical fault information is determined directly with the first historical solution as decision suggestion information. In another possible embodiment, the similar historical fault information, the solutions corresponding to the similar historical fault information, and the first historical solution are determined directly as decision suggestion information. In yet another possible embodiment, at least one of the similar historical fault information, the solutions corresponding to the similar historical fault information, and the first historical solution is used to sort the above information and methods according to the matching degree of the similar historical fault information and the target fault information, and the number of target method keywords included in the first historical solution, and then determine the sorted information and methods as decision advice information, so that the staff can observe the decision advice information more matched with the target fault information. It is obvious that the embodiment of the application does not limit the specific determination manner of determining the decision suggestion information according to the similar historical fault information and the first historical solution.
The technical scheme of the embodiment of the application comprises the following steps: according to the similarity of the target fault information and the historical fault information, determining similar historical fault information meeting a similarity condition from the historical fault information; determining a target method keyword corresponding to the target fault information based on a pre-trained keyword prediction model; and determining a history solution corresponding to the target method keyword as a first history solution, and determining decision suggestion information according to the similar history fault information and the first history solution. According to the technical scheme, the historical fault information similar to the target fault information and the solution method matched with the target fault information are determined through the decision suggestion information, the historical fault record text is fully analyzed and utilized, and the accuracy of the decision suggestion for locating the target fault information is improved.
Example two
Fig. 2 is a flowchart of a method for determining decision advice information according to a second embodiment of the present application, where the process of determining decision advice information is implemented based on the above embodiments.
As shown in fig. 2, the method in the embodiment of the application specifically includes the following steps:
S210, according to the similarity of the target fault information and the historical fault information, determining similar historical fault information meeting the similarity condition from the historical fault information.
In this embodiment, optionally, according to the similarity between the target fault information and the historical fault information, determining similar historical fault information meeting a similarity condition from the historical fault information includes steps A1-A3:
a1, determining a target vector representation of the target fault information, and determining a history vector representation of the history fault information; wherein the types of the target vector representation and the history vector representation comprise word vectors and/or sentence vectors.
According to the method, the vector representation of the target fault information and the historical fault information can be obtained through a natural language processing method, the vector representation can reflect the similarity of the target fault information and the historical fault information, the vector representation can convert words and sentences which are difficult to quantitatively represent into numerical vectors in a continuous space, meanwhile, the similarity principle is kept unchanged, even though words with similar original word senses are still closer in distance in an embedding space, words with larger original word senses are larger in distance in the embedding space, and therefore the preservation of original text semantics after conversion is guaranteed. On the other hand, since between original text words and sentences, it is difficult to evaluate the similarity therebetween in a normalized manner, and after corpus embedding (after obtaining vector representation), it is in continuous space. The similarity between different texts can be quantitatively calculated and evaluated by a variety of available distance metric models. Therefore, for the target fault information and the historical fault information, the judgment on whether the fault phenomena are similar or not and whether the fault maintenance method is the same or not can be realized, and the subsequent intelligent decision function is supported by the judgment.
In this embodiment, optionally, determining the target vector representation of the target fault information and determining the history vector representation of the history fault information includes steps B1-B3:
step B1, word segmentation processing is carried out on fault information, and a word segmentation result is determined; wherein the fault information includes target fault information and historical fault information.
And B2, extracting the word segmentation result to obtain the keywords of the fault information.
And B3, determining sentence vectors of the target fault information according to semantic relations among the keywords.
For example, the fault information may be subjected to word segmentation based on a chinese BERT (Bidirectional Encoder Representations from Transformer, bi-directional coded representation from convertors) model, to obtain a segmented result, and then keyword extraction is performed on the segmented result according to the domain term of art and the abbreviation dictionary. In the keyword extraction process, irrelevant words (such as a mood word) in the word segmentation result can be removed according to the field technical terms and the abbreviation word dictionary, and keywords of fault information can be obtained.
Further, after obtaining the keywords of the fault information, determining the sentence vector of the target fault information according to the semantic relation among the keywords. The semantic relationship may be expressed as: the semantic association between keywords, e.g., the A-part is broken by the B-part, and the B-part breaks the A-part may be the same or similar.
It should be noted that, the determining process of the word vector may be any existing word vector determining method, which is not described in detail in the embodiments of the present application.
It should be noted that, since the embodiment of the present application needs to determine the historical solution keywords, the determining process of the historical solution keywords may be consistent with the determining process of the keywords of the target fault information, which is not described in detail in the embodiment of the present application.
And step A2, determining the similarity of the target vector representation and the history vector representation.
And A3, determining a history vector representation corresponding to the similarity greater than a preset similarity threshold, and taking the history fault information corresponding to the history vector representation as similar history fault information.
The preset similarity threshold may be determined according to practical situations, which is not limited in the embodiment of the present application.
S220, determining target method keywords corresponding to the target fault information based on a pre-trained keyword prediction model.
In this embodiment, optionally, the training process of the keyword prediction model includes: extracting historical solution keywords from a text of a historical solution corresponding to the historical fault information; and carrying out model training by taking the historical fault information and the historical solution keywords as training samples to obtain the keyword prediction model.
Specifically, in the historical solution corresponding to the historical fault information, the processing method adopted by the field maintenance personnel for the fault is recorded, and the processing method comprises the processing methods of replacing components, adjusting mechanisms, optimizing parameters, cleaning dirt and the like. In each history solving method, the keyword extraction method can be used for extracting the keyword, and the extracted keyword can be regarded as the output corresponding to the history fault information. Therefore, in the model training process, all keywords of the input and output parts in the training sample are extracted first, each keyword is regarded as a node in the graph structure, when a sentence contains a plurality of keywords, the keywords in the sample are considered to have links, namely edges in the graph, or the keywords of the input part and the output part in one sample can also be regarded as a link relation in the graph. Therefore, in the keyword prediction task, model input is target fault information, and the output target method keyword link prediction is realized based on the graph neural network model, namely, for a certain input text, a plurality of keywords possibly related to the input text are output.
S230, determining a history solution corresponding to the target method keyword as a first history solution.
S240, determining a second historical solution corresponding to the similar historical fault information.
Specifically, each similar history fault information corresponds to each history solution, and the history solution is determined as a second history solution.
S250, if the first historical solution is the same as the second historical solution, determining the first historical solution as a first part of decision suggestion information.
Since the first historical solution is obtained according to the target method keyword, and is one of solutions corresponding to the target fault information, and the second historical solution corresponds to similar historical fault information, that is, the second historical solution is associated with the target fault information, the first historical solution and the second historical solution may be the same historical solution.
In this embodiment, optionally, if the first historical solution is the same as the second historical solution, determining the first historical solution as the first part of the decision suggestion information includes: determining the product of the first matching degree corresponding to the first history solution and the second matching degree corresponding to the first history solution as the comprehensive matching degree corresponding to the first history solution; the first matching degree is the matching degree between the first historical solution and the target method keywords; the second matching degree is the matching degree between the second historical solution and the target fault information; and determining the ordering of the first part of the first historical solution in the decision suggestion information according to the magnitude relation of the comprehensive matching degree.
In this embodiment of the present application, optionally, the determining of the first matching degree includes: and determining a first matching degree of the first history solution and the target method keywords according to the number of the target method keywords contained in the first history solution.
For example, if the target method keywords are 4, determining the first matching degree of the first history solutions including 4 keywords as the highest matching degree, determining the first matching degree of the first history solutions including 3 keywords as the higher matching degree, and so on, determining the first matching degree of each first history solution; the highest matching degree may be represented by a value of 100%, and the higher matching degree may be represented by a value of 75%, which is obviously merely a specific example of the embodiment of the present application, and the embodiment of the present application is not limited to a specific representation of the first matching degree.
In this embodiment of the present application, optionally, the determining of the second matching degree includes: and taking the similarity between the similar history solving method and the target fault information as a second matching degree between the second solving method and the target fault information.
The similarity between the similar historical solving method and the target fault information is the similarity between the target vector representation and the historical vector representation.
In this embodiment of the present application, the comprehensive matching degree may reflect a matching degree between the first historical solution and the target fault information, and rank the first historical solution from large to small according to the comprehensive matching degree, and determine the ranked first historical solution as a first part of decision suggestion information.
And S260, if the first history solution is different from the second history solution, determining the first history solution and the second history solution as a second part of decision suggestion information.
Specifically, if the first historical solution is the same as the second historical solution, the matching degree between the first historical solution and the target fault information may be larger, and the first part of the decision suggestion information may be determined. If the first historical solution is different from the second historical solution, the degree of matching between the first historical solution and the second historical solution with the target fault information may be smaller, and may be determined as the second part of the decision suggestion information. Further, in the decision suggestion information, the solution of the first part is presented in preference to the solution of the second part.
In this embodiment, optionally, if the first history solution is different from the second history solution, determining the first history solution and the second history solution as the second part of the decision suggestion information includes: and sequencing the first matching degree corresponding to the first historical solution and the second matching degree corresponding to the second historical solution, and determining the sequencing of the second parts of the first historical solution and the second historical solution in the decision suggestion information according to the sequencing result.
For example, the first matching degree and the second matching degree may be unified into a percentage form, and further the first historical solution method and the second historical solution method may be ranked according to the unified first matching degree and second matching degree, and the ranking of the second parts of the first historical solution method and the second historical solution method in the decision suggestion information is determined according to the order from large to small.
In this embodiment, optionally, in the decision suggestion information, the solution of the first part is displayed in preference to the solution of the second part, including: and displaying the solutions of the first part according to the ordering of the first part in the decision suggestion information of the first historical solution, and displaying the solutions of the second part according to the ordering of the second part in the decision suggestion information of the first historical solution and the second historical solution.
According to the technical scheme, the sorting mode of each historical solution in the decision advice information is provided, and the sorted decision advice information is obtained, so that related personnel can determine the historical solution with higher association degree with the target fault information first, and the working efficiency is improved.
In the embodiment of the application, the decision proposal information matched with the target fault information is determined from the historical solution, the working experience and the processing mode of the former staff are obtained, the effective utilization is achieved, and the effect of inheritance experience is achieved.
In this embodiment of the present invention, optionally, the historical fault information is classified according to a word vector and/or a sentence vector of the historical fault information, so that each historical fault information can be displayed in a classified manner, which is convenient for subsequent use. The classification model may employ a conventional neural network, in one possible embodiment, the input of the classification model may be historical fault information and the output may be a fault type; in another possible embodiment, the input of the classification model may be a word vector and/or a sentence vector of the historical fault information and the output may be a fault type.
Example III
Fig. 3 is a schematic structural diagram of a decision suggestion information determining apparatus according to a third embodiment of the present application, where the apparatus may execute the decision suggestion information determining method according to any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the executing method. As shown in fig. 3, the apparatus includes:
A similar historical fault information determining module 310, configured to determine similar historical fault information that satisfies a similarity condition from the historical fault information according to the target fault information and the similarity of the historical fault information;
a target method keyword prediction module 320, configured to determine a target method keyword corresponding to the target fault information based on a pre-trained keyword prediction model;
the decision suggestion information determining module 330 is configured to determine a historical solution corresponding to the target method keyword as a first historical solution, and determine decision suggestion information according to the similar historical fault information and the first historical solution.
Optionally, the training process of the keyword prediction model includes:
extracting historical solution keywords from a text of a historical solution corresponding to the historical fault information;
and carrying out model training by taking the historical fault information and the historical solution keywords as training samples to obtain the keyword prediction model.
Optionally, the decision suggestion information determination module 330 includes:
a second history solution determining unit, configured to determine a second history solution corresponding to the similar history fault information;
A first part determining unit configured to determine a first history solution as a first part of decision advice information if the first history solution is the same as the second history solution;
a second part determining unit configured to determine the first history solution and the second history solution as a second part of decision advice information if the first history solution is different from the second history solution;
in the decision advice information, the solution of the first part is presented in preference to the solution of the second part.
Optionally, the first portion determining unit includes:
a comprehensive matching degree determining subunit, configured to determine, as a comprehensive matching degree corresponding to the first history solution, a product of a first matching degree corresponding to the first history solution and a second matching degree corresponding to the first history solution; the first matching degree is the matching degree between the first historical solution and the target method keywords; the second matching degree is the matching degree between the second historical solution and the target fault information;
a sorting subunit, configured to determine, according to the magnitude relation of the comprehensive matching degree, a sorting of the first part of the first historical solution in the decision suggestion information;
A second part determination unit including:
a second part sorting subunit, configured to sort a first matching degree corresponding to the first historical solution and a second matching degree corresponding to the second historical solution, and determine a sorting of a second part of the first historical solution and the second historical solution in the decision suggestion information according to a sorting result;
in the decision advice information, the solution of the first part is presented in preference to the solution of the second part, comprising:
and displaying the solutions of the first part according to the ordering of the first part in the decision suggestion information of the first historical solution, and displaying the solutions of the second part according to the ordering of the second part in the decision suggestion information of the first historical solution and the second historical solution.
Optionally, the determining of the first matching degree includes:
determining a first matching degree of the first history solution and the target method keywords according to the number of the target method keywords contained in the first history solution;
the second matching degree determining process comprises the following steps:
Taking the similarity between the similar history solving method and the target fault information as a second matching degree between the second solving method and the target fault information;
optionally, the similar historical fault information determination module 310 includes:
a vector representation determining unit configured to determine a target vector representation of the target fault information and determine a history vector representation of the history fault information; wherein the types of the target vector representation and the history vector representation comprise word vectors and/or sentence vectors;
a similarity determining unit configured to determine a similarity of the target vector representation and the history vector representation;
and the similar historical fault information determining unit is used for determining a historical vector representation corresponding to the similarity larger than a preset similarity threshold value, and taking the historical fault information corresponding to the historical vector representation as similar historical fault information.
Optionally, the vector representation determining unit includes:
the word segmentation subunit is used for carrying out word segmentation processing on the fault information and determining a word segmentation result; wherein the fault information includes target fault information and historical fault information;
the keyword extraction subunit is used for extracting the segmented result to obtain keywords of fault information;
And the sentence vector determining subunit is used for determining the sentence vector of the target fault information according to the semantic relation among the keywords.
The decision advice information determining device provided by the embodiment of the invention can execute the decision advice information determining method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the executing method.
Example IV
Fig. 4 shows a schematic diagram of the structure of an electronic device 10 that may be used to implement an embodiment of the invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Electronic equipment may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.
As shown in fig. 4, the electronic device 10 includes at least one processor 11, and a memory, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, etc., communicatively connected to the at least one processor 11, in which the memory stores a computer program executable by the at least one processor, and the processor 11 may perform various appropriate actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from the storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 may also be stored. The processor 11, the ROM 12 and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.
Various components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, etc.; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.
The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor 11 performs the various methods and processes described above, such as the determination of decision advice information.
In some embodiments, the method of determining decision advice information may be implemented as a computer program, which is tangibly embodied on a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the above-described method of determining decision advice information may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the method of determining the decision advice information in any other suitable way (e.g. by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), complex Programmable Logic Devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
A computer program for carrying out methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.
The computing system may include clients and servers. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.
The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.
Claims (10)
1. A method for determining decision advice information, comprising:
according to the similarity of the target fault information and the historical fault information, determining similar historical fault information meeting a similarity condition from the historical fault information;
determining a target method keyword corresponding to the target fault information based on a pre-trained keyword prediction model;
and determining a history solution corresponding to the target method keyword as a first history solution, and determining decision suggestion information according to the similar history fault information and the first history solution.
2. The method of claim 1, wherein the training process of the keyword predictive model comprises:
extracting historical solution keywords from a text of a historical solution corresponding to the historical fault information;
and carrying out model training by taking the historical fault information and the historical solution keywords as training samples to obtain the keyword prediction model.
3. The method of claim 1, wherein determining decision suggestion information based on the similar historical fault information and the first historical solution comprises:
determining a second historical solution corresponding to the similar historical fault information;
if the first historical solution is the same as the second historical solution, determining the first historical solution as a first part of decision suggestion information;
if the first historical solution is different from the second historical solution, determining the first historical solution and the second historical solution as a second part of decision suggestion information;
in the decision advice information, the solution of the first part is presented in preference to the solution of the second part.
4. The method of claim 3, wherein the step of,
If the first historical solution is the same as the second historical solution, determining the first historical solution as a first portion of decision suggestion information, comprising:
determining the product of the first matching degree corresponding to the first history solution and the second matching degree corresponding to the first history solution as the comprehensive matching degree corresponding to the first history solution; the first matching degree is the matching degree between the first historical solution and the target method keywords; the second matching degree is the matching degree between the second historical solution and the target fault information;
determining the ordering of a first part of the first historical solution in the decision proposal information according to the magnitude relation of the comprehensive matching degree;
if the first historical solution is different from the second historical solution, determining the first historical solution and the second historical solution as a second portion of decision suggestion information, comprising:
sorting the first matching degree corresponding to the first historical solution and the second matching degree corresponding to the second historical solution, and determining the sorting of the second parts of the first historical solution and the second historical solution in the decision suggestion information according to the sorting result;
In the decision advice information, the solution of the first part is presented in preference to the solution of the second part, comprising:
and displaying the solutions of the first part according to the ordering of the first part in the decision suggestion information of the first historical solution, and displaying the solutions of the second part according to the ordering of the second part in the decision suggestion information of the first historical solution and the second historical solution.
5. The method of claim 4, wherein the determining of the first degree of matching comprises:
determining a first matching degree of the first history solution and the target method keywords according to the number of the target method keywords contained in the first history solution;
the second matching degree determining process comprises the following steps:
and taking the similarity between the similar history solving method and the target fault information as a second matching degree between the second solving method and the target fault information.
6. The method of claim 1, wherein determining similar historical fault information satisfying a similarity condition from the historical fault information based on the similarity of the target fault information and the historical fault information, comprises:
Determining a target vector representation of the target fault information and determining a history vector representation of the history fault information; wherein the types of the target vector representation and the history vector representation comprise word vectors and/or sentence vectors;
determining a similarity of the target vector representation and the history vector representation;
and determining a history vector representation corresponding to the similarity greater than a preset similarity threshold, and taking the history fault information corresponding to the history vector representation as similar history fault information.
7. The method of claim 6, wherein determining the target vector representation of the target fault information and determining the history vector representation of the history fault information comprises:
performing word segmentation on the fault information, and determining a word segmentation result; wherein the fault information includes target fault information and historical fault information;
extracting the word segmentation result to obtain a keyword of fault information;
and determining sentence vectors of the target fault information according to semantic relations among the keywords.
8. A decision advice information determining apparatus, comprising:
the similar historical fault information determining module is used for determining similar historical fault information meeting a similarity condition from the historical fault information according to the target fault information and the similarity of the historical fault information;
The target method keyword prediction module is used for determining target method keywords corresponding to the target fault information based on a pre-trained keyword prediction model;
and the decision suggestion information determining module is used for determining a historical solution corresponding to the target method keyword as a first historical solution and determining decision suggestion information according to the similar historical fault information and the first historical solution.
9. An electronic device, the electronic device comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the method of determining decision advice information according to any one of claims 1-7.
10. A computer readable storage medium storing computer instructions for causing a processor to implement the method of determining decision advice information according to any one of claims 1-7 when executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310200387.4A CN116467606A (en) | 2023-03-03 | 2023-03-03 | Determination method, device, equipment and medium of decision suggestion information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310200387.4A CN116467606A (en) | 2023-03-03 | 2023-03-03 | Determination method, device, equipment and medium of decision suggestion information |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116467606A true CN116467606A (en) | 2023-07-21 |
Family
ID=87177749
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310200387.4A Pending CN116467606A (en) | 2023-03-03 | 2023-03-03 | Determination method, device, equipment and medium of decision suggestion information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116467606A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117112628A (en) * | 2023-09-08 | 2023-11-24 | 廊坊丛林科技有限公司 | Logistics data updating method and system |
-
2023
- 2023-03-03 CN CN202310200387.4A patent/CN116467606A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117112628A (en) * | 2023-09-08 | 2023-11-24 | 廊坊丛林科技有限公司 | Logistics data updating method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113722493B (en) | Text classification data processing method, apparatus and storage medium | |
| CN116629620B (en) | Risk level determining method and device, electronic equipment and storage medium | |
| CN116307672A (en) | Fault diagnosis method, device, electronic equipment and medium | |
| CN112560461A (en) | News clue generation method and device, electronic equipment and storage medium | |
| CN112989235A (en) | Knowledge base-based internal link construction method, device, equipment and storage medium | |
| CN116467606A (en) | Determination method, device, equipment and medium of decision suggestion information | |
| CN117216275A (en) | Text processing method, device, equipment and storage medium | |
| CN116975400B (en) | Data classification and classification method and device, electronic equipment and storage medium | |
| CN116755974A (en) | Cloud computing platform operation and maintenance method and device, electronic equipment and storage medium | |
| CN116401281A (en) | SQL query time prediction method, device, equipment and medium | |
| CN116225848A (en) | Log monitoring method, device, equipment and medium | |
| CN114647739B (en) | Entity chain finger method, device, electronic equipment and storage medium | |
| CN111985226A (en) | Method and device for generating labeled data | |
| CN115640399A (en) | Text classification method, device, equipment and storage medium | |
| CN115600607A (en) | Log detection method and device, electronic equipment and medium | |
| CN114461735A (en) | Industrial and mining data classification method and device and computer equipment | |
| GB2603594A (en) | Maintenance of a data glossary | |
| CN112528644A (en) | Entity mounting method, device, equipment and storage medium | |
| CN114037058B (en) | Pre-training model generation method and device, electronic equipment and storage medium | |
| US12050866B2 (en) | Maintenance of a data glossary | |
| CN117541366B (en) | Method and device for predicting winning probability, electronic equipment and storage medium | |
| Chen et al. | Test Case Reuse based on ESIM Model | |
| CN117708655A (en) | Cultural knowledge calculation method based on large language model | |
| CN118312623A (en) | Construction method, device, equipment and storage medium of fault identification knowledge graph | |
| CN118277916A (en) | Enterprise industry identification method, device, equipment and storage medium |
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 |