CN115329774A - Intelligent building fault diagnosis rule generation method and device based on semantic matching - Google Patents
Intelligent building fault diagnosis rule generation method and device based on semantic matching Download PDFInfo
- Publication number
- CN115329774A CN115329774A CN202211257403.5A CN202211257403A CN115329774A CN 115329774 A CN115329774 A CN 115329774A CN 202211257403 A CN202211257403 A CN 202211257403A CN 115329774 A CN115329774 A CN 115329774A
- Authority
- CN
- China
- Prior art keywords
- rule
- macro
- semantic matching
- location information
- point location
- 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.)
- Granted
Links
Images
Classifications
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/194—Calculation of difference between files
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Test And Diagnosis Of Digital Computers (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a semantic matching-based intelligent building fault diagnosis rule generation method, a semantic matching-based intelligent building fault diagnosis rule generation device, electronic equipment and a storage medium, and relates to the technical field of intelligent buildings, wherein the semantic matching-based intelligent building fault diagnosis rule generation method comprises the steps of obtaining macro rules for describing building faults; wherein, the macro rule is a text with a preset structure; extracting a plurality of keywords in the macro rule; acquiring point location information corresponding to the keywords from the building projects based on the keywords; and carrying out semantic matching on the point location information and the macro rule to obtain a diagnosis rule of the building project. Through the mode, the fault diagnosis rule facing to the specific project can be automatically generated based on semantic similarity matching; unlike the conventional method, the fault diagnosis rule is automatically generated for the algorithm.
Description
Technical Field
The invention relates to the technical field of intelligent building data, in particular to a semantic matching-based intelligent building fault diagnosis rule generation method and device, electronic equipment and a storage medium.
Background
Compared with the rapid development of information technology in other fields such as the internet, shared economy, new retail and the like, the application and iteration speed of intellectualization in the building are slightly slow, and the problems of safety guarantee, convenience in use, environmental effect and the like are exposed in the process.
In the white paper of the research on the current application situation of the intelligent system for buildings, published by the institute of building science in 2021, the existing intelligent system has the defects that the integration difficulty of the existing intelligent system and third-party equipment or systems is high, the stability is not high, and the integration and interaction of data cannot be realized after the hardware system is integrated.
On the basis of the above, some people propose to use an intelligent building system to analyze building monitoring data, so as to realize fault diagnosis of a building electromechanical system. However, a great deal of research work is carried out by domestic and foreign scholars and enterprises on fault diagnosis of electromechanical systems based on building monitoring data, but at present, deep application of a fault diagnosis function is hardly seen in engineering practice. One of the main obstacles of the intelligent fault diagnosis function falling to the ground in the actual engineering is that in the busy and nervous system integration stage, a field engineer capable of quantitatively mastering fault diagnosis knowledge is not available to perform complex and detailed fault diagnosis algorithm configuration work.
Disclosure of Invention
The invention provides a semantic matching-based intelligent building fault diagnosis rule generation method, a semantic matching-based intelligent building fault diagnosis rule generation device, electronic equipment and a storage medium, which are used for solving the defect that intelligent fault diagnosis of a building in the prior art strongly depends on manual work.
The invention provides an intelligent building fault diagnosis rule generation method based on semantic matching, which comprises the following steps: acquiring macro rules for describing building faults; wherein, the macro rule is a text with a preset structure; extracting a plurality of keywords in the macro rule; acquiring point location information corresponding to the keywords from the building projects based on the keywords; and carrying out semantic matching on the point location information and the macro rule to obtain a diagnosis rule of the building project.
According to the intelligent building fault diagnosis rule generation method based on semantic matching, provided by the invention, point location information of corresponding keywords is obtained from building projects based on the keywords, and the method comprises the following steps: obtaining keyword derivatives based on the keywords, wherein the keyword derivatives comprise at least one of synonyms of the keywords, english words of the keywords, synonyms of the English words of the keywords and synonyms of the English words of the keywords; and acquiring point location information of the corresponding keywords from the building project based on the keywords and the keyword derivative words.
According to the intelligent building fault diagnosis rule generation method based on semantic matching, provided by the invention, the diagnosis rules of the building project comprise single-rule single-variable keyword matching, single-rule multivariate semantic matching and multi-rule multivariate semantic matching; wherein the variable refers to point location information in the building project; the macro rules include limits of physical quantities in the building, size relationships, statistical rules, and equation constraints.
According to the intelligent building fault diagnosis rule generation method based on semantic matching, when the diagnosis rule of the building project is single rule multivariable semantic matching or multi-rule multivariable semantic matching, the point location information and the macro rule are subjected to semantic matching to obtain the diagnosis rule of the building project, and the method comprises the following steps: segmenting the point location information to obtain key words and data objects of the point location information; carrying out similarity judgment on the data objects to obtain a similarity value; and when the similarity value is greater than or equal to the preset threshold value, judging that the point location information is matched with the macro rule.
According to the intelligent building fault diagnosis rule generation method based on semantic matching, provided by the invention, the similarity judgment is carried out on the data objects to obtain the similarity value, and the method comprises the following steps: deleting the matched keywords after word segmentation to obtain a data object; and reordering the data objects, and performing similarity function calculation on the reordered point location information to obtain a similarity value.
According to the intelligent building fault diagnosis rule generation method based on semantic matching, provided by the invention, similarity function calculation is carried out on the point location information after reordering, and the similarity value is obtained by the following steps: acquiring the number of words of point location information; carrying out similarity calculation on each participle of the point location information independently to obtain a similarity value of each participle; and superposing the similarity values of all the participles and then dividing the superposed participles by the similarity values to obtain the similarity values.
According to the intelligent building fault diagnosis rule generation method based on semantic matching, macro rules matched by single-rule single-variable keywords are expressed as follows:
y1 = f1(x1);
the macro-rule of the single-rule multivariate semantic matching is expressed as:
y2= f2(x1, x2..,xn);
the macro-rule of multi-rule multivariate semantic matching is expressed as:
y1 = f1(x1, x2,…, xn);
y2 = f2(x1,x2,…, xn);
…
yn = fn(x1,x2,…, xn);
z = f(y1, y2, y3,…, yn);
wherein x1, x2, \8230, xn is n variables; f1 (x), f2 (x), \8230, fn (x) is n preset rules, and y1 is a macro rule result of the uniregular univariate keyword matching; y2 is a macro rule result of the single rule multivariate semantic matching; z is the macro rule result of the multi-rule multivariate semantic matching.
The invention also provides an intelligent building fault diagnosis rule generation device based on semantic matching, which comprises the following steps: the macro rule module is used for acquiring macro rules for describing building faults; the keyword module is used for extracting a plurality of keywords in the macro rule; the point location information module is used for acquiring point location information corresponding to the keywords from the building project based on the keywords; and the diagnosis rule module is used for performing semantic matching on the point location information and the macro rule to obtain the diagnosis rule of the building project.
The invention also provides an electronic device, which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein when the processor executes the program, the intelligent building fault diagnosis rule generation method based on semantic matching is realized.
The present invention also provides a non-transitory computer readable storage medium, on which a computer program is stored, the computer program, when executed by a processor, implementing any one of the above methods for generating intelligent building fault diagnosis rules based on semantic matching.
The invention provides a semantic matching-based intelligent building fault diagnosis rule generation method, a semantic matching-based intelligent building fault diagnosis rule generation device, electronic equipment and a storage medium, wherein macro rules for describing building faults are obtained; wherein, the macro rule is a text with a preset structure; extracting a plurality of keywords in the macro rule; acquiring point location information of a corresponding keyword from a building project based on the keyword; and carrying out semantic matching on the point location information and the macro rule to obtain a diagnosis rule of the building project. Through the mode, the fault diagnosis rule facing to the specific project can be automatically generated based on semantic similarity matching; unlike the conventional method, the fault diagnosis rule is automatically generated for the algorithm.
Drawings
In order to more clearly illustrate the technical solutions of the present invention or the prior art, the drawings needed for the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart diagram of an embodiment of the intelligent building fault diagnosis rule generation method based on semantic matching according to the invention;
FIG. 2 is a schematic structural diagram of an embodiment of the intelligent building fault diagnosis rule generation system based on semantic matching according to the invention;
FIG. 3 is a schematic flow chart illustrating an embodiment of semantic matching step in the intelligent building fault diagnosis rule generation method based on semantic matching according to the present invention;
FIG. 4 is a flow diagram illustrating an embodiment of semantic matching in the intelligent building failure diagnosis rule generation system method based on semantic matching according to the present invention;
FIG. 5 is a schematic flow chart diagram illustrating an embodiment of a similarity determination process in the intelligent building fault diagnosis rule generation system method based on semantic matching according to the present invention;
fig. 6 is a schematic structural diagram of an embodiment of an electronic device of the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention provides a semantic matching-based intelligent building fault diagnosis rule generation method, please refer to fig. 1-2, fig. 1 is a flow diagram of an embodiment of the semantic matching-based intelligent building fault diagnosis rule generation method of the invention, and fig. 2 is a structural diagram of an embodiment of the semantic matching-based intelligent building fault diagnosis rule generation system of the invention. In this embodiment, the intelligent building fault diagnosis rule generation method based on semantic matching may include steps S110 to S140, where each step is specifically as follows:
s110: macro rules describing building faults are obtained.
The macro rule is a text with a preset structure. The macro rule contains expert knowledge, is recorded by industry experts in a natural language description mode based on domain knowledge and in a structured text mode and is used for follow-up program reading and rule generation.
Optionally, the macro rules include limits of physical quantities in the building, size relationships, statistical rules and equation constraints, and so on. The Macro rules may be stored in a Macro Rule base UMR (Union of Macro Rule).
S120: and extracting a plurality of keywords in the macro rule.
Each macro rule may include a plurality of keywords, and theoretically, all the keywords in the macro rule need to be extracted. The confirmation of the mapping relationship between the physical quantity in the macro rule and the point location in the actual item mainly depends on the keyword matching.
S130: and acquiring point location information corresponding to the keywords from the building projects based on the keywords.
And reading point location information of the corresponding project from a point location database of the building project for matching with the macro rule. Wherein, the point location information table is represented by X.
S140: and carrying out semantic matching on the point location information and the macro rule to obtain a diagnosis rule of the building project.
Semantic matching is one of the inventive points of the item. Semantic matching may include primary matching and advanced matching. The primary matching can be understood as keyword matching, that is, when a keyword in the point location information corresponds to a keyword in the macro rule, the keyword and the macro rule are considered to be matched, and the diagnosis rule of the corresponding building project is obtained based on the mapping relationship between the point location information and the macro rule.
The advanced matching is a semantic method based on word segmentation, keyword matching and data object similarity judgment, and simulates the process of reasoning carried out by experts to realize more accurate rule matching.
Optionally, the diagnostic rules of the construction project may include single-rule univariate keyword matching, single-rule multivariate semantic matching, and multi-rule multivariate semantic matching; wherein the variables refer to point location information in the construction project.
The intelligent building fault diagnosis rule generation system based on semantic matching comprises a macro rule base, a point location information base and a rule base, wherein macro rules for describing building faults are stored in the macro rule base, point location information of building projects is stored in the point location information base, and diagnosis rules corresponding to the building projects are stored in the rule base. The method of this embodiment may be implemented by means of an auto-configuration program.
According to the intelligent building fault diagnosis rule generation method based on semantic matching, macro rules for describing building faults are obtained; the macro rule is a text with a preset structure; extracting a plurality of key words in the macro rule; acquiring point location information corresponding to the keywords from the building projects based on the keywords; and performing semantic matching based on the point location information and the macro rule to obtain the diagnosis rule of the corresponding building project. Through the mode, the fault diagnosis rule facing to the specific project can be automatically generated based on semantic similarity matching; different from the conventional method, the fault diagnosis rule is automatically generated for the algorithm.
Optionally, obtaining point location information corresponding to the keyword from the building project based on the keyword includes:
obtaining keyword derivative words based on the keywords, wherein the keyword derivative words comprise at least one of synonyms of the keywords, english words of the keywords, synonyms of the English words of the keywords and synonyms of the English words of the keywords; and acquiring point location information of the corresponding keywords from the building project based on the keywords and the keyword derivative words.
Since the start name of the point location name in the project is determined by field workers according to personal working habits and enterprise requirements, and one hundred percent of standardization and consistency cannot be achieved, for the same physical quantity, a plurality of possible keywords and keyword derivatives including but not limited to Chinese and English keywords are provided in the embodiment so as to correspond to different working habits.
Optionally, for the ith macro rule MRi in the macro rule base UMR, the corresponding keyword is KW _ MRi.
Optionally, referring to fig. 3, fig. 3 is a schematic flowchart of an embodiment of a semantic matching step in the intelligent building fault diagnosis rule generation method based on semantic matching according to the present invention. When the diagnosis rule of the building project is single rule multivariable semantic matching or multi-rule multivariable semantic matching, performing semantic matching on the point location information and the macro rule to obtain the diagnosis rule of the building project, wherein the method comprises the following steps:
s141: and segmenting the point location information to obtain key words and data objects of the point location information.
S142: and carrying out similarity judgment on the data objects to obtain a similarity value.
Optionally, the determining similarity of the data object to obtain a similarity value includes: deleting the matched keywords after word segmentation to obtain a data object; and reordering the data objects, and performing similarity function calculation on the reordered point location information to obtain a similarity value.
Wherein, the similarity function calculation is carried out on the reordered point location information, and the obtaining of the similarity value comprises the following steps: acquiring the number of words of point location information; carrying out similarity calculation on each participle of the point location information independently to obtain a similarity value of each participle; and superposing the similarity values of all the participles and dividing the superposed participles by the similarity values to obtain the similarity value.
S143: and when the similarity value is greater than or equal to the preset threshold value, judging that the point location information is matched with the macro rule.
When the items are named after monitoring points, the sequence of different words in the names can be different, some shorthand abbreviations of the item convention are used, and a small amount of errors often occur. If keyword matching is simply used, a large number of macro rules cannot find corresponding point location information, and diagnostic rules which can be covered by the knowledge of the expert macro rule base cannot be generated. In the embodiment, the advanced matching is adopted, and the process of reasoning performed by experts is simulated based on a semantic method of word segmentation, keyword matching and data object similarity judgment, so that more accurate rule matching is realized.
Optionally, the single-rule single-variable keyword matching may adopt primary matching; the single rule multivariate semantic matching and the multi-rule multivariate semantic matching can adopt advanced matching. The macro rules for single-rule single-variable keyword matching may be expressed as:
y1 = f1(x1);
and (5) matching the monitoring point location name represented by the x with KW _ MRi of each rule MRi in the macro rule base UMR by using the method in (4) semantic matching, and if matching is found, generating a project rule Rj.
The macro-rules of single-rule multivariate semantic matching can be expressed as:
y2= f2(x1, x2..,xn);
the rule generation method is that monitoring point location names represented by n variables are matched with n key words KW _ MRi,1, KW \uMRi, 2, \8230, KW _ MRi, n of each rule MRi in a macro rule library UMR by using a method in semantic matching according to x1, x2, \8230, and if matching is found, item rules Rj are generated.
It is noted that unlike conventional keyword matching, here, in addition to matching keywords, data object verification is also required to obtain data object Ti.
The multi-rule multivariate semantic matched macro-rules can be expressed as:
y1 = f1(x1, x2,…, xn);
y2 = f2(x1,x2,…, xn);
…
yn = fn(x1,x2,…, xn);
z = f(y1, y2, y3,…, yn);
wherein x1, x2, \8230, xn is n variables; f1 (x), f2 (x), \8230, fn (x) is n preset rules, and y1 is a macro rule result matched with the uniregular univariate key words; y2 is a macro rule result of the single rule multi-variable semantic matching; z is the macro rule result of the multi-rule multivariate semantic matching.
During the simultaneous rule of the form, after the identification of the y1 rule is executed, a data object T1 is obtained, and then in the identification process of y2, y3 \8230andyn, besides keyword matching, judgment is carried out according to similarity to check whether the monitoring point position simultaneously accords with the matching of a keyword and a data object. If y1, y2, \8230, and yn meet the matching requirements, a multi-rule and multi-meaning matching rule base is generated.
The embodiment can be freely combined under the condition of no conflict, and the invention discloses an intelligent building fault diagnosis rule automatic generation method based on semantic matching, which can realize macro rules containing expert knowledge based on semantic similarity matching and automatically generate fault diagnosis rules facing specific projects.
Compared with the conventional method for manually configuring the fault diagnosis rule one by workers in combination with expert knowledge and a data point table of a specific project, the method has the following advantages:
(1) The time is short: the automatic rule generation is automatically realized by an algorithm program, about 5 minutes is taken for completing the automatic generation of 10000 rules, and about 41 working days is required if the automatic generation is completed manually by adopting a traditional method.
(2) The accuracy rate is high: due to the adoption of algorithm generation, manual intervention is not needed, and the problem of mismatching caused by manual processing of a large amount of data and complex logical relations can be avoided.
(3) More intelligent: for the conditions of multiple rules and multiple variables, the method introduces a semantic matching method, and for some occasions with the same meaning but not meeting the keyword matching, the method can more intelligently identify the relationship between the data and the knowledge macro rule, and realize intelligent matching.
The process of the present invention is further illustrated below with reference to specific examples.
1. Obtaining macro rules
1) Single rule univariate
2) Single rule multivariable
3) Multiple rule multivariable
2. Extracting keywords
For determining the mapping relationship between the physical quantity in the macro rule and the point position in the actual project. Usually done manually and without inspection mechanisms and standard principles, there is a certain degree of non-normalcy, often abbreviated, abbreviated. For the same physical quantity, a plurality of possible Chinese and English keywords should be given to correspond to different working habits.
Corresponding to the above example MR1, the keywords are:
KW _ MR1: { x1: (water supply temperature | SupplyWaterTemp | SupplyWaterT | water supply temperature | water outlet temperature) }.
Corresponding to the above example MR2, the keywords are:
KW _ MR2: { x1: (water supply temperature | supplywamp | supplywastert | water supply temperature), x2: (return water temperature | Return WaterTemp | Return WaterT | return water temperature) }.
Corresponding to the above example MR3, the keywords are:
KW _ MR3: { x1: (water supply temperature | supplywamp | supplywastert | water supply temperature), x2: (return water temperature | return water temp | return water temperature), x3: (Season mode | Season | SeasonMode | Season) }.
3. Item point location information reading
And the automatic configuration program reads the item point location information from the item point location database for matching with the macro rules. The point location information table is denoted by X. For a particular item, the point location information is similar to:
TABLE 1 Point location information Table
4. Semantic matching
Referring to fig. 4 and 5, fig. 4 is a schematic flow chart illustrating an embodiment of semantic matching in the intelligent building fault diagnosis rule generation system method based on semantic matching according to the present invention; FIG. 5 is a schematic flow chart showing an embodiment of a similarity determination process in the intelligent building fault diagnosis rule generation system method based on semantic matching according to the present invention
Corresponding to the example MR1 above, the keywords are:
KW _ MR1: { x1: (supply water temperature SupplyWaterTemp SupplyWaterT Water temperature Outlet Water temperature) }
Match(Name(1234),KW_MR1)=TRUE
Corresponding to the above example MR2, the keywords are:
KW _ MR2: { x1: (water supply temperature | SupplyWaterTemp | SupplyWaterT | water supply temperature | water outlet temperature), x2: (Return Water temperature | Return Water Temp | Return Water T | Return Water temperature) }
For the points ID =1234 and 1237, the matching process is performed according to fig. 5.
The first step is as follows: word segmentation
ID =1234: "freezing station 1# refrigerator outlet water temperature" - > "freezing station |1# | refrigerator | outlet water temperature"
ID =1237: "return water temperature of refrigerating station of 1# refrigerator" - > "return water temperature of refrigerating station | of 1# | refrigerator |)"
The second step: matching keyword deletion
ID =1234: "cold station 1# refrigerator leaving water temperature" - > "cold station |1# | refrigerator | leaving water temperature" = > ID =1234: "temperature of outflow Water of refrigerating station 1# refrigerator" - > "refrigerating station |1# | refrigerator"
ID =1237: "1# refrigerator cold station return water temperature" - > "1# | refrigerator | cold station | return water temperature" = > ID =1237: 'Return water temperature of freezing station 1# refrigerator' - > '1 # | refrigerator | freezing station'
The third step: sorting
Obtaining data objects, and ordering the data objects
Data object: ID =1234: "freezer station |1# | refrigerator" = > ID =1234: freezing station of 1# refrigerator "
Data object: ID =1237: "1# | refrigerator | freezer station" = > ID =1234: freezing station of 1# refrigerator "
The fourth step: similarity determination
SV = f (refrigerating station of 1# | refrigerator |, "refrigerating station of 1# |)
The similarity function SV can be defined as: (word segmentation similarity 1+ word segmentation similarity 2+ \ 8230; + word segmentation similarity n)/number of segmented words n
SV = f ("1 # | refrigerator | freezing station" ) = (1 +2/3+ 1)/3= 0.8888
If the similarity threshold is 0.8, the matching is judged, and the data object is (1 # | refrigerator | freezing station)
For MR3, the semantic matching process is similar to MR2, and the example is not repeated.
5. Rule generation
1) Single rule univariate keyword matching
Corresponding to y= f1 (x), x is a variable, f1 (x) is a rule, and y is a result. The rule generation method is that the name of the monitoring point position represented by x and each rule MR in the macro rule base UMR i KW _ MR i Matching by using the method in the semantic matching in the step (4), and if the matching is found, generating a project rule R j 。
Corresponding to MR1 exemplified above, since Match (Name (1234), KW _ MR 1) = TRUE, the generation rule is:
Value(ID(1234))<5
2) Single rule multivariate semantic matching
Corresponding to y = f2 (x 1, x2.., xn), x1, x2, \ 8230, where xn is n variables, f2 (x) is a rule, and y is the result. The rule generation method is according to x1, x2, \8230, where xn is the monitoring point location name represented by n variables and each rule MR in the macro rule base UMR i N number of keywords KW _ MR i,1 ,KW_MR i,2,,…, KW_MR i,n Matching by using the method in (4) semantic matching, and if matching is found, generating a project rule R j 。
It should be noted that, unlike the conventional keyword matching, in this case, in addition to matching the keyword, data object verification is also required to obtain the data object Ti, and the specific process is shown in fig. 2 and fig. 3.
For MR2, the matched data objects ID =1234 and ID =1237, the generated rule is:
Value(ID(1234))>Value(ID(1237))
3) Multi-rule multivariate semantic matching
When there are macro rules in the form of simultaneous multi-rules, that is:
y1=f1(x1,x2,…,xn)
y2=f2(x1,x2,…,xn)
…
yn=fn(x1,x2,…,xn)
z=f(y1,y2,y3,…,yn)
in the form of the simultaneous rule, after the y1 rule is identified, the data object T1 is obtained, and then in the y2, y3 \8230, in the process of identifying yn, besides keyword matching, judgment is carried out according to similarity, and whether the monitoring point position simultaneously accords with the matching of the keyword and the data object is checked. If y1, y2, \8230, and yn meet the matching requirements, a multi-rule and multi-meaning matching rule base is generated.
For MR3, the matching data objects ID =1234, ID =1237 and ID =1238, the rule generated is:
value (ID (1234)) > Value (ID (1237)) and Value (ID (1238)) = "summer"
The intelligent building fault diagnosis rule generation device based on semantic matching provided by the invention is described below, and the intelligent building fault diagnosis rule generation device based on semantic matching described below and the intelligent building fault diagnosis rule generation method based on semantic matching described above can be referred to correspondingly.
Referring to fig. 3, fig. 3 is a schematic structural diagram of an intelligent building fault diagnosis rule generating device based on semantic matching according to an embodiment of the present invention. In this embodiment, the intelligent building fault diagnosis rule generating device based on semantic matching may include: macro rule module, keyword module, point location information module and diagnosis rule module. Specifically, the method comprises the following steps:
and the macro rule module is used for acquiring macro rules for describing the building faults.
And the keyword module is used for extracting a plurality of keywords in the macro rule.
And the point location information module is used for obtaining point location information corresponding to the keywords from the building projects based on the keywords.
And the diagnosis rule module is used for carrying out semantic matching on the point location information and the macro rules to obtain the diagnosis rules of the building project.
In some embodiments, the keyword module is further to:
obtaining keyword derivative words based on the keywords, wherein the keyword derivative words comprise at least one of synonyms of the keywords, english words of the keywords, synonyms of the English words of the keywords and synonyms of the English words of the keywords; and acquiring point location information of the corresponding keyword from the building project based on the keyword and the keyword derivative word.
In some embodiments, the diagnostic rules for the construction project include single rule univariate keyword matching, single rule multivariate semantic matching, and multiple rule multivariate semantic matching; wherein the variable refers to point location information in the building project; the macro rules include limits of physical quantities in the building, size relationships, statistical rules, and equation constraints.
In some embodiments, the diagnostic rules module is further to:
segmenting the point location information to obtain key words and data objects of the point location information; carrying out similarity judgment on the data objects to obtain similarity values; and when the similarity value is greater than or equal to the preset threshold value, judging that the point location information is matched with the macro rule.
In some embodiments, the diagnostic rules module is further to:
deleting the matched keywords after word segmentation to obtain a data object; and reordering the data objects, and performing similarity function calculation on the reordered point location information to obtain a similarity value.
In some embodiments, the diagnostic rules module is further to:
acquiring the part word number of the point location information; carrying out similarity calculation on each participle of the point location information independently to obtain a similarity value of each participle; and superposing the similarity values of all the participles and then dividing the superposed participles by the similarity values to obtain the similarity values.
In some embodiments, the macro rules for a single-rule, single-variable keyword match are expressed as:
y1 = f1(x1);
the macro-rule of the single-rule multivariate semantic matching is expressed as:
y2= f2(x1, x2..,xn);
the macro-rule of multi-rule multivariate semantic matching is expressed as:
y1 = f1(x1, x2,…, xn);
y2 = f2(x1,x2,…, xn);
…
yn = fn(x1,x2,…, xn);
z = f(y1, y2, y3,…, yn);
wherein x1, x2, \8230, xn is n variables; f1 (x), f2 (x), \8230, fn (x) is n preset rules, and y1 is a macro rule result of the uniregular univariate keyword matching; y2 is a macro rule result of the single rule multi-variable semantic matching; and z is a macro rule result of multi-rule multi-variable semantic matching.
Fig. 6 shows an electronic device, where fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the invention. In this embodiment, the electronic device may include a memory (memory) 610, a processor (processor) 620, and a computer program stored on the memory 620 and executable on the processor 610. When the processor 610 executes the program, the intelligent building fault diagnosis rule generation method based on semantic matching provided by the above methods is implemented.
Optionally, the electronic device may further include a communication bus 630 and a communication Interface (Communications Interface) 640, wherein the processor 610, the communication Interface 640, and the memory 620 are in communication with each other through the communication bus 630. The processor 610 may invoke logic instructions in the memory 620 to perform a semantic matching based intelligent building troubleshooting rule generation method comprising:
acquiring macro rules for describing building faults; the macro rule is a text with a preset structure; extracting a plurality of keywords in the macro rule; acquiring point location information corresponding to the keywords from the building projects based on the keywords; and performing semantic matching based on the point location information and the macro rules to obtain diagnosis rules of corresponding building projects.
In addition, the logic instructions in the memory 620 may be implemented in the form of software functional units and stored in a computer readable storage medium when the logic instructions are sold or used as a stand-alone product. Based on such understanding, the technical solution of the present invention or a part thereof which substantially contributes to the prior art may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In another aspect, the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program is implemented to execute, by a processor, the method for generating the intelligent building fault diagnosis rule based on semantic matching provided by the foregoing methods, where the steps and principles of the method are described in detail in the foregoing method, and are not repeated herein.
The invention provides a semantic matching-based intelligent building fault diagnosis rule generation method, a semantic matching-based intelligent building fault diagnosis rule generation device, electronic equipment and a storage medium, wherein macro rules for describing building faults are obtained; wherein, the macro rule is a text with a preset structure; extracting a plurality of key words in the macro rule; acquiring point location information corresponding to the keywords from the building projects based on the keywords; and performing semantic matching based on the point location information and the macro rule to obtain the diagnosis rule of the corresponding building project. Through the mode, the fault diagnosis rule facing to the specific project can be automatically generated based on semantic similarity matching; different from the conventional method, the fault diagnosis rule is automatically generated for the algorithm.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one position, or may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment may be implemented by software plus a necessary general hardware platform, and may also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, and not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. An intelligent building fault diagnosis rule generation method based on semantic matching is characterized by comprising the following steps:
acquiring macro rules for describing building faults; the macro rule is a text with a preset structure;
extracting a plurality of keywords in the macro rule;
acquiring point location information corresponding to the keywords from the building projects based on the keywords;
and performing semantic matching on the point location information and the macro rule to obtain a diagnosis rule of the building project.
2. The intelligent building fault diagnosis rule generation method based on semantic matching according to claim 1, wherein the obtaining point location information corresponding to the keyword from a building project based on the keyword comprises:
obtaining a keyword derivative word based on the keyword, wherein the keyword derivative word comprises at least one of a synonym of the keyword, an English word of the keyword, a synonym of the English word of the keyword, and a synonym of the English word of the keyword;
and acquiring point location information corresponding to the keyword from the building project based on the keyword and the keyword derivative word.
3. The intelligent building fault diagnosis rule generation method based on semantic matching according to claim 1,
the diagnosis rules of the building project comprise single-rule single-variable keyword matching, single-rule multi-variable semantic matching and multi-rule multi-variable semantic matching;
wherein the variable refers to point location information in the building project; the macro rules include limits of physical quantities in the building, size relationships, statistical rules, and equation constraints.
4. The intelligent building fault diagnosis rule generation method based on semantic matching as claimed in claim 3, wherein when the diagnosis rule of a building project is single rule multivariate semantic matching or multi-rule multivariate semantic matching, the semantic matching is performed on the point location information and the macro rule to obtain the diagnosis rule of the building project, and the method comprises:
segmenting the point location information to obtain key words and data objects of the point location information;
carrying out similarity judgment on the data objects to obtain similarity values;
and when the similarity value is greater than or equal to a preset threshold value, judging that the point location information is matched with the macro rule.
5. The intelligent building fault diagnosis rule generation method based on semantic matching according to claim 4, wherein the similarity judgment of the data objects to obtain a similarity value comprises:
deleting the matched keywords after word segmentation to obtain the data object;
and reordering the data objects, and performing similarity function calculation on the reordered point location information to obtain a similarity value.
6. The intelligent building fault diagnosis rule generation method based on semantic matching according to claim 5, wherein the performing similarity function calculation on the point location information after reordering to obtain a similarity value comprises:
obtaining the number of words of the point location information; carrying out similarity calculation on each participle of the point location information independently to obtain a similarity value of each participle;
and superposing the similarity values of all the participles and then dividing the superposed participles by the similarity values to obtain the similarity values.
7. The intelligent building fault diagnosis rule generation method based on semantic matching according to claim 3,
the macro rule matched by the single-rule single-variable key words is expressed as follows:
y1 = f1(x1);
the macro rule of the single rule multivariate semantic matching is expressed as:
y2= f2(x1, x2..,xn);
the macro rule of the multi-rule multivariate semantic matching is expressed as follows:
y1 = f1(x1, x2,…, xn);
y2 = f2(x1,x2,…, xn);
…
yn = fn(x1,x2,…, xn);
z = f(y1, y2, y3,…, yn);
wherein x1, x2, \8230, xn is n variables; f1 (x), f2 (x), \8230, fn (x) is n preset rules, and y1 is a macro rule result matched with the uniregular univariate key words; y2 is a macro rule result of the single rule multivariate semantic matching; and z is a macro rule result of multi-rule multi-variable semantic matching.
8. An intelligent building fault diagnosis rule generation device based on semantic matching is characterized by comprising the following components:
the macro rule module is used for acquiring macro rules for describing building faults;
the keyword module is used for extracting a plurality of keywords in the macro rule;
the point location information module is used for acquiring point location information corresponding to the keyword from a building project based on the keyword;
and the diagnosis rule module is used for performing semantic matching on the point location information and the macro rule to obtain the diagnosis rule of the building project.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the intelligent building failure diagnosis rule generation method based on semantic matching according to any one of claims 1 to 7 when executing the program.
10. A non-transitory computer-readable storage medium, on which a computer program is stored, wherein the computer program, when executed by a processor, implements the intelligent building fault diagnosis rule generation method based on semantic matching according to any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211257403.5A CN115329774B (en) | 2022-10-14 | 2022-10-14 | Intelligent building fault diagnosis rule generation method and device based on semantic matching |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211257403.5A CN115329774B (en) | 2022-10-14 | 2022-10-14 | Intelligent building fault diagnosis rule generation method and device based on semantic matching |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115329774A true CN115329774A (en) | 2022-11-11 |
CN115329774B CN115329774B (en) | 2023-03-24 |
Family
ID=83913200
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211257403.5A Active CN115329774B (en) | 2022-10-14 | 2022-10-14 | Intelligent building fault diagnosis rule generation method and device based on semantic matching |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115329774B (en) |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104679828A (en) * | 2015-01-19 | 2015-06-03 | 云南电力调度控制中心 | Rules-based intelligent system for grid fault diagnosis |
US20170213303A1 (en) * | 2016-01-22 | 2017-07-27 | Johnson Controls Technology Company | Building fault triage system with crowdsourced feedback for fault diagnostics and suggested resolutions |
CN109270458A (en) * | 2018-11-08 | 2019-01-25 | 国电联合动力技术有限公司 | Intelligent failure diagnosis method, system, Wind turbines and storage medium |
CN109614469A (en) * | 2018-12-03 | 2019-04-12 | 郑州云海信息技术有限公司 | A kind of log analysis method and device |
CN109840157A (en) * | 2017-11-28 | 2019-06-04 | 中国移动通信集团浙江有限公司 | Method, apparatus, electronic equipment and the storage medium of fault diagnosis |
CN110399385A (en) * | 2019-06-24 | 2019-11-01 | 厦门市美亚柏科信息股份有限公司 | A kind of semantic analysis and system for small data set |
CN111061584A (en) * | 2019-11-21 | 2020-04-24 | 浪潮电子信息产业股份有限公司 | Fault diagnosis method, device, equipment and readable storage medium |
CN111931936A (en) * | 2020-06-17 | 2020-11-13 | 河海大学常州校区 | Equipment fault diagnosis method based on collaborative case reasoning and semantic model reasoning |
CN112433874A (en) * | 2020-11-05 | 2021-03-02 | 北京浪潮数据技术有限公司 | Fault positioning method, system, electronic equipment and storage medium |
CN112818008A (en) * | 2021-01-21 | 2021-05-18 | 中广核工程有限公司 | Intelligent diagnosis method, system, medium and electronic equipment for nuclear power debugging faults |
CN114266297A (en) * | 2021-12-15 | 2022-04-01 | 浙江大学 | Semantic knowledge base of thermal power equipment, construction method and zero sample fault diagnosis method |
-
2022
- 2022-10-14 CN CN202211257403.5A patent/CN115329774B/en active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104679828A (en) * | 2015-01-19 | 2015-06-03 | 云南电力调度控制中心 | Rules-based intelligent system for grid fault diagnosis |
US20170213303A1 (en) * | 2016-01-22 | 2017-07-27 | Johnson Controls Technology Company | Building fault triage system with crowdsourced feedback for fault diagnostics and suggested resolutions |
CN109840157A (en) * | 2017-11-28 | 2019-06-04 | 中国移动通信集团浙江有限公司 | Method, apparatus, electronic equipment and the storage medium of fault diagnosis |
CN109270458A (en) * | 2018-11-08 | 2019-01-25 | 国电联合动力技术有限公司 | Intelligent failure diagnosis method, system, Wind turbines and storage medium |
CN109614469A (en) * | 2018-12-03 | 2019-04-12 | 郑州云海信息技术有限公司 | A kind of log analysis method and device |
CN110399385A (en) * | 2019-06-24 | 2019-11-01 | 厦门市美亚柏科信息股份有限公司 | A kind of semantic analysis and system for small data set |
CN111061584A (en) * | 2019-11-21 | 2020-04-24 | 浪潮电子信息产业股份有限公司 | Fault diagnosis method, device, equipment and readable storage medium |
CN111931936A (en) * | 2020-06-17 | 2020-11-13 | 河海大学常州校区 | Equipment fault diagnosis method based on collaborative case reasoning and semantic model reasoning |
CN112433874A (en) * | 2020-11-05 | 2021-03-02 | 北京浪潮数据技术有限公司 | Fault positioning method, system, electronic equipment and storage medium |
CN112818008A (en) * | 2021-01-21 | 2021-05-18 | 中广核工程有限公司 | Intelligent diagnosis method, system, medium and electronic equipment for nuclear power debugging faults |
CN114266297A (en) * | 2021-12-15 | 2022-04-01 | 浙江大学 | Semantic knowledge base of thermal power equipment, construction method and zero sample fault diagnosis method |
Non-Patent Citations (1)
Title |
---|
孟祥朋等: "基于专家系统的建筑自动化系统故障诊断", 《计算机工程》 * |
Also Published As
Publication number | Publication date |
---|---|
CN115329774B (en) | 2023-03-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11315031B2 (en) | Using machine learning regression to estimate time for completing application lifecycle management work item | |
CN108197132B (en) | Graph database-based electric power asset portrait construction method and device | |
KR20200093441A (en) | Method for obtaining data model in knowledge graph, apparatus, device and medium | |
CN116821310B (en) | Enterprise knowledge base question-answering system based on large model and knowledge graph | |
CN115204536A (en) | Building equipment fault prediction method, device, equipment and storage medium | |
CN113487211A (en) | Nuclear power equipment quality tracing method and system, computer equipment and medium | |
CN114324368A (en) | Modified plastic production detection method and system based on mechanical vision detection | |
JP6733366B2 (en) | Task estimation device, task estimation method, and task estimation program | |
CN115329774B (en) | Intelligent building fault diagnosis rule generation method and device based on semantic matching | |
CN114765574B (en) | Network anomaly delimitation positioning method and device | |
McMillan et al. | Flow forecasting for leakage burst prediction in water distribution systems using long short-term memory neural networks and Kalman filtering | |
CN117252186A (en) | XAI-based information processing method, device, equipment and storage medium | |
CN115830419A (en) | Data-driven artificial intelligence technology evaluation system and method | |
CN115712842A (en) | BIM and business system association method and system based on fuzzy matching | |
US20080140364A1 (en) | Computer Program Product & Computer with Program to Execute a Well-Posed Mathematical Method | |
US11194966B1 (en) | Management of concepts and intents in conversational systems | |
Haiyan et al. | A rework reduction mechanism in complex projects using design structure matrix clustering methods | |
CN116635843A (en) | Apparatus, computing platform and method for analyzing log files of industrial plants | |
CN112434471A (en) | Method, system, electronic device and storage medium for improving model generalization capability | |
Saxena et al. | Realiability Assessment Model to Estimate Quality of the Effective E-Procurement Process in Adoption | |
Kim et al. | A hybrid failure diagnosis and prediction using natural language-based process map and rule-based expert system | |
Li et al. | A Bayesian nonparametric test for minimal repair | |
Jin et al. | Construction and application of knowledge graph of domestic operating system testing | |
CN116860227B (en) | Data development system and method based on big data ETL script arrangement | |
Sivaramakrishnan et al. | Application of a Hidden Markov Model for consistency checking of process plant facility tag numbers: A case study |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |