CN111126055A - Power grid equipment name matching method and system - Google Patents
Power grid equipment name matching method and system Download PDFInfo
- Publication number
- CN111126055A CN111126055A CN201911029137.9A CN201911029137A CN111126055A CN 111126055 A CN111126055 A CN 111126055A CN 201911029137 A CN201911029137 A CN 201911029137A CN 111126055 A CN111126055 A CN 111126055A
- Authority
- CN
- China
- Prior art keywords
- power grid
- grid equipment
- names
- equipment
- name
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a power grid equipment name matching method which comprises the steps of splicing collected power grid equipment names to be matched again according to a preset splicing rule; based on the electric power operation language library, performing word segmentation on the rejoined power grid equipment name; performing initial matching on the name of the power grid equipment based on the attribute constraint rule; and performing word segmentation similarity calculation on the preliminarily matched power grid equipment names to obtain a final matching result. A corresponding system is also disclosed. The method accurately divides the newly spliced power grid equipment names, and on the basis, similarity calculation is carried out through the vocabulary entry set after word division, so that accurate matching of the power grid equipment names in the multi-source heterogeneous power grid is realized, and the efficiency and the matching rate are high.
Description
Technical Field
The invention relates to a power grid equipment name matching method and a power grid equipment name matching system, and belongs to the technical field of research and application of intelligent power grid power transmission and transformation equipment model matching.
Background
With the deepening of the construction of the national grid regulation and control cloud platform system, equipment account ID relation mapping needs to be carried out on a cloud power grid model and an equipment model in a home EMS system, equipment account matching is carried out among multi-source systems, the uniqueness of equipment is determined, and the mapping relation of the equipment accounts in the multi-source systems is established. The mapping of the ID relationship of the equipment account is mainly carried out by matching the names of the power grid equipment, and because the naming modes of the EMS systems of all the places in the power grid equipment are different, the names of the same power grid equipment in the cloud end and the EMS systems of the places are different, and the ID mapping of the equipment account cannot be carried out quickly and accurately.
The existing matching method mainly comprises the following two methods:
1. through manual screening and comparison. Although the matching degree is high, the efficiency is low in the implementation process, and the labor is consumed;
2. by means of mutual inclusion of device names. Although the labor cost is reduced by the method, the normalization of the equipment name needs higher requirements, naming rules of the equipment names in different systems are different, and the matching rate of the mutual inclusion method is lower.
Disclosure of Invention
The invention provides a power grid equipment name matching method and a power grid equipment name matching system, which solve the problems disclosed in the background technology.
In order to solve the technical problems, the technical scheme adopted by the invention is as follows:
the power grid equipment name matching method comprises the following steps,
according to a preset splicing rule, splicing the collected names of the power grid equipment to be matched again;
based on the electric power operation language library, performing word segmentation on the rejoined power grid equipment name;
performing initial matching on the name of the power grid equipment based on the attribute constraint rule;
and performing word segmentation similarity calculation on the preliminarily matched power grid equipment names to obtain a final matching result.
The splicing rules comprise an in-station equipment name splicing rule and an inter-station equipment name splicing rule;
and (3) splicing rules of the names of the devices in the station: the equipment names sequentially comprise the belonged area, the belonged station, the voltage grade, the equipment number and the equipment type from front to back;
splicing rules of equipment names between stations: the equipment names are the affiliated area, the head end station, the tail end station, the equipment number and the equipment type in sequence from front to back.
And performing word segmentation on the rejoined power grid equipment name by adopting a forward iteration finest granularity segmentation algorithm, wherein entries in the power operation language library are preferentially matched during word segmentation.
The attribute constraint rule is that a plurality of power grid equipment names with the same attribute are screened out from all the power grid equipment names which are spliced again.
And calculating the similarity between the word segmentation results of the names of the power grid devices pairwise in sequence, wherein the names of the two power grid devices corresponding to the highest similarity are matched.
The similarity calculation process is that,
calculating word frequency vectors according to the word segmentation results of the power grid equipment names;
and calculating the similarity of the word segmentation results of the two power grid equipment names by adopting a cosine similarity calculation method.
The power grid equipment name matching system comprises a power grid equipment name matching module,
the re-splicing module: according to a preset splicing rule, splicing the collected names of the power grid equipment to be matched again;
a word segmentation module: based on the electric power operation language library, performing word segmentation on the rejoined power grid equipment name;
a preliminary matching module: performing initial matching on the name of the power grid equipment based on the attribute constraint rule;
a similarity calculation module: and performing word segmentation similarity calculation on the preliminarily matched power grid equipment names to obtain a final matching result.
The similarity calculation module includes a similarity calculation module,
the word frequency vector calculation module: calculating word frequency vectors according to the word segmentation results of the power grid equipment names;
a cosine similarity module: and calculating the similarity of the word segmentation results of the two power grid equipment names by adopting a cosine similarity calculation method.
A computer readable storage medium storing one or more programs, the one or more programs comprising instructions, which when executed by a computing device, cause the computing device to perform a grid device name matching method.
A computing device comprising one or more processors, memory, and one or more programs stored in the memory and configured to be executed by the one or more processors, the one or more programs including instructions for performing a grid device name matching method.
The invention achieves the following beneficial effects: the method accurately divides the newly spliced power grid equipment names, and on the basis, similarity calculation is carried out through the vocabulary entry set after word division, so that accurate matching of the power grid equipment names in the multi-source heterogeneous power grid is realized, and the efficiency and the matching rate are high.
Drawings
FIG. 1 is a flow chart of the present invention.
Detailed Description
The invention is further described below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and the protection scope of the present invention is not limited thereby.
Example 1
As shown in fig. 1, the method for matching names of power grid devices includes the following steps:
step 1, according to a preset splicing rule, splicing the collected names of the power grid equipment to be matched again.
The naming modes of the EMS systems of all the places are different in the power grid equipment, all the power grid equipment have names or numbers and the like, and the uniqueness of the equipment in the whole network cannot be ensured by singly using the names or the numbers, so that a plurality of attributes need to be reasonably selected and spliced into a new name again, and the matching efficiency and the matching accuracy can be effectively improved.
And 2, based on the electric power term library, performing word segmentation on the rejoined power grid equipment name.
The natural language participle can carry out effective division with the electric wire netting equipment name of splicing again, because contain a lot of electric power terms in the electric wire netting equipment name, often will divide into a plurality of word with a professional term when the participle, be unfavorable for semantic understanding like this, therefore the participle will combine electric power term bank, and the preferred word segmentation according to electric power term bank improves the participle accuracy.
And 3, performing initial matching on the name of the power grid equipment based on the attribute constraint rule.
In different systems, the same power grid equipment naming rules are different, but the same power grid equipment naming rules have a plurality of same attributes, invalid matching calculation is reduced through the attribute constraint rules, namely, some obvious mismatching is eliminated, and therefore the calculation efficiency and the matching degree are improved.
And 4, performing word segmentation similarity calculation on the preliminarily matched power grid equipment name to obtain a final matching result.
According to the method, the rejoined power grid equipment names are subjected to accurate word segmentation, similarity calculation is performed through the entry set after word segmentation on the basis, accurate matching of the power grid equipment names in the multi-source heterogeneous power grid is achieved, and efficiency and matching rate are high.
Example 2
The power grid equipment name matching method adds a specific splicing rule on the basis of the embodiment 1, and specifically comprises the following steps:
the power grid equipment in the station mainly comprises a transformer, a bus, a switch, a disconnecting link and the like, and the power grid equipment across the station is mainly a power transmission line connecting stations on two sides. All kinds of power grid equipment have names (old names) or numbers, such as 50331 disconnecting link, #1 main transformer, I line/II line. However, the uniqueness of the power grid equipment in the whole network cannot be ensured by singly using the name or the number of the power grid equipment, so that a new name needs to be spliced by a plurality of attribute characteristics, the uniqueness of the name of the power grid equipment is realized, and the matching efficiency and the matching accuracy are effectively improved.
The splicing rules comprise an in-station equipment name splicing rule and an inter-station equipment name splicing rule.
And (3) splicing rules of the names of the devices in the station: the device names sequentially comprise the belonged region, the belonged station, the voltage grade, the device number and the device type from front to back, and are specifically shown in table 1;
TABLE 1 in-station device name splicing rules
| Belonging to area | Station to which it belongs | Voltage class | Device numbering | Type of device |
For example: shandong, Binzhou station/500 kV. #1 bus, and Neze, giant camping station/10 kV #1 grounding transformer.
Splicing rules of equipment names between stations: the equipment names are the belonged area, the head end station, the tail end station, the equipment number and the equipment type in sequence from front to back, and are specifically shown in table 2;
table 1 rules for equipment name splicing between stations
| Belonging to area | Head end station | Terminal station | Device numbering | Type of device |
For example: shandong, city spoon I line, Shandong, cang rock line.
Example 3
The matching method of the power grid equipment names adds a specific word segmentation method on the basis of the embodiment 1, and specifically comprises the following steps: performing word segmentation on the newly spliced power grid equipment name by adopting a forward iteration finest granularity segmentation algorithm, and preferentially matching entries in the power operation language library during word segmentation; through preferential matching of electric power terms, word segmentation accuracy is improved.
For example: the Shandong, Jiaodong converter station/500 kV. polar I converter transformer 5061 switch, the name of the power grid equipment does not use the power technology library for word segmentation, and the result is: [ Shandong, Jiaodong, Shi, Liu, station, 500kv, Ji, I, Shi, Liu, Shi, 5061, switch ], wherein "converter station" and "Shi Tu Liu" are commonly used terms of electric power, and the word segmentation results after adding to the electric power term library: [ Shandong, Jiaodong, converter station, 500kv, Pole, I, converter flow, 5061, switch ]. The power grid equipment names are segmented through the power operation language library, so that the equipment names are correctly divided.
Example 4
The power grid equipment name matching method adds a specific attribute constraint rule on the basis of the embodiment 1, and specifically comprises the following steps:
the attribute constraint rules are: screening out a plurality of power grid equipment names with the same attribute from all the power grid equipment names which are spliced again; such as: the station and the voltage class.
In different systems, the same grid device has several same attributes, such as: and the same station and the same voltage level are obtained, so that the prior preliminary matching can be performed by taking the same attribute as constraint, the subsequent similarity calculation can be performed only when the constraint rule is established, and otherwise, the matching is quitted and the next equipment matching is continued. Thus, the time complexity of the matching calculation is reduced.
Taking mapping of a regulation cloud model and a D5000 system transformer model as an example, the number of transformer equipment in the regulation cloud is M, the number of D5000 system transformers is N, and the complexity of comparison time is M x N in the traditional comparison mapping; by adding an attribute constraint rule, the regulation and control of the cloud-side main transformer only needs to be compared with the D5000-side main transformer equipment under the same station, so that the time complexity is far less than M x N.
Example 5
The method for matching the names of the power grid devices adds a specific process of the step 4 on the basis of the embodiment 1, and comprises the following steps: and calculating the similarity between the word segmentation results of the names of the power grid equipment pairwise in sequence, wherein the higher the similarity is, the smaller the difference between the names of the power grid equipment is, and therefore the names of the two power grid equipment corresponding to the highest value of the similarity are matched.
Example 6
The matching method of the names of the power grid devices adds a similarity calculation process on the basis of the embodiment 1 or 5, and specifically comprises the following steps:
41) and calculating word frequency vectors according to the word segmentation result of the power grid equipment name.
42) And calculating the similarity of the word segmentation results of the two power grid equipment names by adopting a cosine similarity calculation method.
The cosine value between the included angles of the two vectors is used for measuring the difference between the two individuals, the cosine value is close to 1, the included angle tends to 0, the more similar the two vectors are, the cosine value is close to 0, the included angle tends to 90 degrees, and the more dissimilar the two vectors are.
The cosine function calculation formula is as follows:
wherein, XiIs the i-th element, Y, of the word frequency vector XiIs the ith element of the word frequency vector Y, and n is the number of the elements of the word frequency vector.
Taking the matching of "Shandong Binzhou station/500 kV. Binzhii line 5041-1 disconnecting link" with "500 kV Binzhii line 5041-1 disconnecting link" as an example:
1. device name word segmentation
"Shandong Binzhou station/500 kV. Binzhii line 5041-1 knife brake" results in the word segmentation: [ Shandong, Bin, standing, 500kv, shore, oil, line II, 5041,1, knife brake ]
The word segmentation result of the 500kV Bianbi oil II line 5041-1 disconnecting link is as follows: [500kv, shore, oil, line II, 5041,1, knife);
2. all word segmentation: [1, knife gate, 500kv, Shandong, standing, line II, oil, shore, 5041, Binzhou ];
3. calculating word frequency
[ Shandong, Bin, standing, 500kv, shore, oil, line II, 5041,1, knife brake ]
Calculating word frequency: [1,1,1,1,1,1,1,1,1,1]
[500kv, shore, oil, line II, 5041,1, knife switch ]
Calculating word frequency: [1,1,1,0,0,1,1,1,1,0 ];
4. similarity calculation
And (4) conclusion: "Shandong Binzhou station/500 kV. Binzhii line 5041-1 disconnecting link" has a similarity of 0.836 to "500 kV Binzhii line 5041-1 disconnecting link".
Example 7
The power grid equipment name matching method comprises the following steps:
step 1, according to a preset splicing rule, splicing the collected names of the power grid equipment to be matched again.
The naming modes of the EMS systems of all the places are different in the power grid equipment, all the power grid equipment have names or numbers and the like, and the uniqueness of the equipment in the whole network cannot be ensured by singly using the names or the numbers, so that a plurality of attributes need to be reasonably selected and spliced into a new name again, and the matching efficiency and the matching accuracy can be effectively improved.
The power grid equipment in the station mainly comprises a transformer, a bus, a switch, a disconnecting link and the like, and the power grid equipment across the station is mainly a power transmission line connecting stations on two sides. All kinds of power grid equipment have names (old names) or numbers, such as 50331 disconnecting link, #1 main transformer, I line/II line. However, the uniqueness of the power grid equipment in the whole network cannot be ensured by singly using the name or the number of the power grid equipment, so that a new name needs to be spliced by a plurality of attribute characteristics, the uniqueness of the name of the power grid equipment is realized, and the matching efficiency and the matching accuracy are effectively improved.
The splicing rules comprise an in-station equipment name splicing rule and an inter-station equipment name splicing rule.
And (3) splicing rules of the names of the devices in the station: the device names sequentially comprise the belonged region, the belonged station, the voltage grade, the device number and the device type from front to back, and are specifically shown in table 1;
TABLE 1 in-station device name splicing rules
| Belonging to area | Station to which it belongs | Voltage class | Device numbering | Type of device |
For example: shandong, Binzhou station/500 kV. #1 bus, and Neze, giant camping station/10 kV #1 grounding transformer.
Splicing rules of equipment names between stations: the equipment names are the belonged area, the head end station, the tail end station, the equipment number and the equipment type in sequence from front to back, and are specifically shown in table 2;
table 2 rules for splicing names of devices between stations
| Belonging to area | Head end station | End tipStation | Device numbering | Type of device |
For example: shandong, city spoon I line, Shandong, cang rock line.
And 2, based on the electric power term library, performing word segmentation on the rejoined power grid equipment name.
The natural language participle can carry out effective division with the electric wire netting equipment name of splicing again, because contain a lot of electric power terms in the electric wire netting equipment name, often will divide into a plurality of word with a professional term when the participle, be unfavorable for semantic understanding like this, therefore the participle will combine electric power term bank, and the preferred word segmentation according to electric power term bank improves the participle accuracy.
Performing word segmentation on the newly spliced power grid equipment name by adopting a forward iteration finest granularity segmentation algorithm, and preferentially matching entries in the power operation language library during word segmentation; through preferential matching of electric power terms, word segmentation accuracy is improved.
For example: the Shandong, Jiaodong converter station/500 kV. polar I converter transformer 5061 switch, the name of the power grid equipment does not use the power technology library for word segmentation, and the result is: [ Shandong, Jiaodong, Shi, Liu, station, 500kv, Ji, I, Shi, Liu, Shi, 5061, switch ], wherein "converter station" and "Shi Tu Liu" are commonly used terms of electric power, and the word segmentation results after adding to the electric power term library: [ Shandong, Jiaodong, converter station, 500kv, Pole, I, converter flow, 5061, switch ]. The power grid equipment names are segmented through the power operation language library, so that the equipment names are correctly divided.
And 3, performing initial matching on the name of the power grid equipment based on the attribute constraint rule.
The attribute constraint rules are: screening out a plurality of power grid equipment names with the same attribute from all the power grid equipment names which are spliced again; such as: the station and the voltage class.
In different systems, the same power grid equipment has a plurality of same attributes, invalid matching calculation is reduced through an attribute constraint rule, namely, some obvious mismatching is eliminated, and therefore calculation efficiency and matching degree are improved.
Such as: and the same station and the same voltage level are obtained, so that the prior preliminary matching can be performed by taking the same attribute as constraint, the subsequent similarity calculation can be performed only when the constraint rule is established, and otherwise, the matching is quitted and the next equipment matching is continued. Thus, the time complexity of the matching calculation is reduced.
Taking mapping of a regulation cloud model and a D5000 system transformer model as an example, the number of transformer equipment in the regulation cloud is M, the number of D5000 system transformers is N, and the complexity of comparison time is M x N in the traditional comparison mapping; by adding an attribute constraint rule, the regulation and control of the cloud-side main transformer only needs to be compared with the D5000-side main transformer equipment under the same station, so that the time complexity is far less than M x N.
And 4, performing word segmentation similarity calculation on the preliminarily matched power grid equipment name to obtain a final matching result.
And calculating the similarity between the word segmentation results of the names of the power grid equipment pairwise in sequence, wherein the higher the similarity is, the smaller the difference between the names of the power grid equipment is, and therefore the names of the two power grid equipment corresponding to the highest value of the similarity are matched.
The similarity calculation process specifically includes:
41) and calculating word frequency vectors according to the word segmentation result of the power grid equipment name.
42) And calculating the similarity of the word segmentation results of the two power grid equipment names by adopting a cosine similarity calculation method.
The cosine value between the included angles of the two vectors is used for measuring the difference between the two individuals, the cosine value is close to 1, the included angle tends to 0, the more similar the two vectors are, the cosine value is close to 0, the included angle tends to 90 degrees, and the more dissimilar the two vectors are.
The cosine function calculation formula is as follows:
wherein, XiIs the i-th element, Y, of the word frequency vector XiIs the first of the word frequency vector Yi elements and n is the number of elements of the word frequency vector.
Taking the matching of "Shandong Binzhou station/500 kV. Binzhii line 5041-1 disconnecting link" with "500 kV Binzhii line 5041-1 disconnecting link" as an example:
1. device name word segmentation
"Shandong Binzhou station/500 kV. Binzhii line 5041-1 knife brake" results in the word segmentation: [ Shandong, Bin, standing, 500kv, shore, oil, line II, 5041,1, knife brake ]
The word segmentation result of the 500kV Bianbi oil II line 5041-1 disconnecting link is as follows: [500kv, shore, oil, line II, 5041,1, knife);
2. all word segmentation: [1, knife gate, 500kv, Shandong, standing, line II, oil, shore, 5041, Binzhou ];
3. calculating word frequency
[ Shandong, Bin, standing, 500kv, shore, oil, line II, 5041,1, knife brake ]
Calculating word frequency: [1,1,1,1,1,1,1,1,1,1]
[500kv, shore, oil, line II, 5041,1, knife switch ]
Calculating word frequency: [1,1,1,0,0,1,1,1,1,0 ];
4. similarity calculation
And (4) conclusion: "Shandong Binzhou station/500 kV. Binzhii line 5041-1 disconnecting link" has a similarity of 0.836 to "500 kV Binzhii line 5041-1 disconnecting link".
The results of comparing the above method with the commonly used method are as follows:
TABLE 3 three sets of data
For the three groups of data, the traditional splitting and matching method and the segmentation and matching method without constraint are adopted to be compared with the method as follows.
TABLE 4 comparison results
Remarking:
the splitting and matching method comprises the following steps: the device name of the system A is called as a main (#2 bus), whether the device name is contained in the system B is judged, and if the device name is contained in the system B, the device name is considered to be matched.
The method for matching the word segmentation without constraint comprises the following steps: and (4) not performing constraint before matching according to the equipment attribute, and performing word segmentation matching on all data.
According to the method, the rejoined power grid equipment names are subjected to accurate word segmentation, similarity calculation is performed through the entry set after word segmentation on the basis, accurate matching of the power grid equipment names in the multi-source heterogeneous power grid is achieved, and efficiency and matching rate are high.
Example 8
The power grid equipment name matching system comprises a power grid equipment name matching module,
the re-splicing module: according to a preset splicing rule, splicing the collected names of the power grid equipment to be matched again;
a word segmentation module: based on the electric power operation language library, performing word segmentation on the rejoined power grid equipment name;
a preliminary matching module: performing initial matching on the name of the power grid equipment based on the attribute constraint rule;
a similarity calculation module: and performing word segmentation similarity calculation on the preliminarily matched power grid equipment names to obtain a final matching result.
Example 9
The power grid equipment name matching system adds a structure of a similarity calculation module on the basis of the embodiment 1 or 5, and specifically includes:
the word frequency vector calculation module: calculating word frequency vectors according to the word segmentation results of the power grid equipment names;
a cosine similarity module: and calculating the similarity of the word segmentation results of the two power grid equipment names by adopting a cosine similarity calculation method.
Example 10
A computer readable storage medium storing one or more programs, the one or more programs comprising instructions, which when executed by a computing device, cause the computing device to perform a grid device name matching method.
Example 11
A computing device comprising one or more processors, memory, and one or more programs stored in the memory and configured to be executed by the one or more processors, the one or more programs including instructions for performing a grid device name matching method.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The present invention is not limited to the above embodiments, and any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention are included in the scope of the claims of the present invention which are filed as the application.
Claims (10)
1. The power grid equipment name matching method is characterized by comprising the following steps: comprises the steps of (a) preparing a mixture of a plurality of raw materials,
according to a preset splicing rule, splicing the collected names of the power grid equipment to be matched again;
based on the electric power operation language library, performing word segmentation on the rejoined power grid equipment name;
performing initial matching on the name of the power grid equipment based on the attribute constraint rule;
and performing word segmentation similarity calculation on the preliminarily matched power grid equipment names to obtain a final matching result.
2. The power grid equipment name matching method according to claim 1, wherein: the splicing rules comprise an in-station equipment name splicing rule and an inter-station equipment name splicing rule;
and (3) splicing rules of the names of the devices in the station: the equipment names sequentially comprise the belonged area, the belonged station, the voltage grade, the equipment number and the equipment type from front to back;
splicing rules of equipment names between stations: the equipment names are the affiliated area, the head end station, the tail end station, the equipment number and the equipment type in sequence from front to back.
3. The power grid equipment name matching method according to claim 1, wherein: and performing word segmentation on the rejoined power grid equipment name by adopting a forward iteration finest granularity segmentation algorithm, wherein entries in the power operation language library are preferentially matched during word segmentation.
4. The power grid equipment name matching method according to claim 1, wherein: the attribute constraint rule is that a plurality of power grid equipment names with the same attribute are screened out from all the power grid equipment names which are spliced again.
5. The power grid equipment name matching method according to claim 1, wherein: and calculating the similarity between the word segmentation results of the names of the power grid devices pairwise in sequence, wherein the names of the two power grid devices corresponding to the highest similarity are matched.
6. The grid device name matching method according to claim 1 or 5, wherein: the similarity calculation process is that,
calculating word frequency vectors according to the word segmentation results of the power grid equipment names;
and calculating the similarity of the word segmentation results of the two power grid equipment names by adopting a cosine similarity calculation method.
7. Power grid equipment name matching system, its characterized in that: comprises the steps of (a) preparing a mixture of a plurality of raw materials,
the re-splicing module: according to a preset splicing rule, splicing the collected names of the power grid equipment to be matched again;
a word segmentation module: based on the electric power operation language library, performing word segmentation on the rejoined power grid equipment name;
a preliminary matching module: performing initial matching on the name of the power grid equipment based on the attribute constraint rule;
a similarity calculation module: and performing word segmentation similarity calculation on the preliminarily matched power grid equipment names to obtain a final matching result.
8. The grid device name matching system according to claim 7, wherein: the similarity calculation module includes a similarity calculation module,
the word frequency vector calculation module: calculating word frequency vectors according to the word segmentation results of the power grid equipment names;
a cosine similarity module: and calculating the similarity of the word segmentation results of the two power grid equipment names by adopting a cosine similarity calculation method.
9. A computer readable storage medium storing one or more programs, characterized in that: the one or more programs include instructions that, when executed by a computing device, cause the computing device to perform any of the methods of claims 1-6.
10. A computing device, characterized by: comprises the steps of (a) preparing a mixture of a plurality of raw materials,
one or more processors, memory, and one or more programs stored in the memory and configured to be executed by the one or more processors, the one or more programs including instructions for performing any of the methods of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911029137.9A CN111126055A (en) | 2019-10-28 | 2019-10-28 | Power grid equipment name matching method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911029137.9A CN111126055A (en) | 2019-10-28 | 2019-10-28 | Power grid equipment name matching method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111126055A true CN111126055A (en) | 2020-05-08 |
Family
ID=70495431
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911029137.9A Pending CN111126055A (en) | 2019-10-28 | 2019-10-28 | Power grid equipment name matching method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111126055A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111625596A (en) * | 2020-05-14 | 2020-09-04 | 国网辽宁省电力有限公司 | Multi-source data synchronous sharing method and system for real-time consumption scheduling of new energy |
| CN112182019A (en) * | 2020-10-20 | 2021-01-05 | 国网福建省电力有限公司经济技术研究院 | Semantic parsing search method for power grid statistics professional index feature extraction |
| CN112818012A (en) * | 2021-01-26 | 2021-05-18 | 深圳力维智联技术有限公司 | Equipment data matching method, device, equipment and storage medium |
| CN116521852A (en) * | 2023-06-26 | 2023-08-01 | 南京实创信息技术有限公司 | Power equipment intelligent mapping tool and mapping method based on deep learning |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105354224A (en) * | 2015-09-30 | 2016-02-24 | 百度在线网络技术（北京）有限公司 | Knowledge data processing method and apparatus |
| CN107844559A (en) * | 2017-10-31 | 2018-03-27 | 国信优易数据有限公司 | A kind of file classifying method, device and electronic equipment |
| CN108021553A (en) * | 2017-09-30 | 2018-05-11 | 北京颐圣智能科技有限公司 | Word treatment method, device and the computer equipment of disease term |
| CN108802768A (en) * | 2018-06-04 | 2018-11-13 | 中国空间技术研究院 | A kind of more rail multifrequency satellite signal efficient matchings receiving handling methods |
-
2019
- 2019-10-28 CN CN201911029137.9A patent/CN111126055A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105354224A (en) * | 2015-09-30 | 2016-02-24 | 百度在线网络技术（北京）有限公司 | Knowledge data processing method and apparatus |
| CN108021553A (en) * | 2017-09-30 | 2018-05-11 | 北京颐圣智能科技有限公司 | Word treatment method, device and the computer equipment of disease term |
| CN107844559A (en) * | 2017-10-31 | 2018-03-27 | 国信优易数据有限公司 | A kind of file classifying method, device and electronic equipment |
| CN108802768A (en) * | 2018-06-04 | 2018-11-13 | 中国空间技术研究院 | A kind of more rail multifrequency satellite signal efficient matchings receiving handling methods |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111625596A (en) * | 2020-05-14 | 2020-09-04 | 国网辽宁省电力有限公司 | Multi-source data synchronous sharing method and system for real-time consumption scheduling of new energy |
| CN111625596B (en) * | 2020-05-14 | 2023-12-26 | 国网辽宁省电力有限公司 | Multi-source data synchronous sharing method and system for real-time new energy consumption scheduling |
| CN112182019A (en) * | 2020-10-20 | 2021-01-05 | 国网福建省电力有限公司经济技术研究院 | Semantic parsing search method for power grid statistics professional index feature extraction |
| CN112818012A (en) * | 2021-01-26 | 2021-05-18 | 深圳力维智联技术有限公司 | Equipment data matching method, device, equipment and storage medium |
| CN116521852A (en) * | 2023-06-26 | 2023-08-01 | 南京实创信息技术有限公司 | Power equipment intelligent mapping tool and mapping method based on deep learning |
| CN116521852B (en) * | 2023-06-26 | 2023-09-19 | 南京实创信息技术有限公司 | Deep learning-based intelligent mapping device and mapping method for power equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111126055A (en) | Power grid equipment name matching method and system | |
| CN103218398B (en) | Intelligent substation SCL (substation configuration description language) file difference comparison method | |
| CN109193948B (en) | Automatic virtual circuit connection method for intelligent substation | |
| CN109857885B (en) | Intelligent substation main wiring diagram automatic generation method based on SCD file | |
| CN115441448B (en) | Power conversion and supply verification method, device and equipment for power distribution network line and storage medium | |
| CN115618249A (en) | Low-voltage power distribution station area phase identification method based on LargeVis dimension reduction and DBSCAN clustering | |
| CN109586281B (en) | Power distribution network reliability assessment method, device and medium based on node optimization number | |
| Grigoras et al. | Energy losses estimation in electrical distribution networks with a decision trees-based algorithm | |
| CN112235146A (en) | Automatic association method and device for primary and secondary equipment models of intelligent substation | |
| CN115544033B (en) | Method, device, equipment and medium for updating check repeat vector library and checking repeat data | |
| CN116780648A (en) | Method, system and equipment for analyzing bearing capacity of distributed power technology of power distribution network | |
| CN111078683A (en) | Interpolation search-based power grid ledger data filling and counting method and device | |
| CN108108584B (en) | Short-circuit parameter acquisition method and system for three-phase asymmetric equipment of power system | |
| CN116109440A (en) | Automatic generation method and device for power outage overhaul mode adjustment scheme based on graph search | |
| CN111697607A (en) | Multi-terminal flexible direct-current transmission receiving-end power grid access method and system | |
| CN115345457A (en) | Transformer substation primary and secondary equipment automatic association method and device based on predefined information | |
| CN107818414B (en) | Method for generating N-2 expected accident set of large-scale alternating current-direct current hybrid power grid | |
| CN112214859A (en) | Integrated integration method and system for main network model and distribution network model | |
| CN111553040A (en) | Power grid topology analysis high-performance computing method and device based on GPU acceleration | |
| CN112200406B (en) | Park power distribution network energy router access planning method and device | |
| CN112464416B (en) | Method and system for generating all-station fixed value of one-key transformer substation | |
| CN103473615A (en) | Method and device for automatically selecting extra-high voltage alternating-current and direct-current drop points | |
| CN110311384B (en) | Dynamic reactive power compensation method, device, equipment and storage medium for electric power system | |
| CN111308168B (en) | Method, device and equipment for automatically generating line current limiting value | |
| CN112952797B (en) | Power distribution station low-voltage cause identification method and device |
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 |