CN116610810A - Intelligent searching method and system based on regulation and control of cloud knowledge graph blood relationship - Google Patents
Intelligent searching method and system based on regulation and control of cloud knowledge graph blood relationship Download PDFInfo
- Publication number
- CN116610810A CN116610810A CN202310430048.5A CN202310430048A CN116610810A CN 116610810 A CN116610810 A CN 116610810A CN 202310430048 A CN202310430048 A CN 202310430048A CN 116610810 A CN116610810 A CN 116610810A
- Authority
- CN
- China
- Prior art keywords
- knowledge graph
- data
- entity
- regulation
- query
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 239000008280 blood Substances 0.000 title claims abstract description 27
- 210000004369 blood Anatomy 0.000 title claims abstract description 27
- 238000004458 analytical method Methods 0.000 claims abstract description 40
- 230000000875 corresponding effect Effects 0.000 claims description 25
- 238000004422 calculation algorithm Methods 0.000 claims description 19
- 238000004364 calculation method Methods 0.000 claims description 19
- 238000004590 computer program Methods 0.000 claims description 19
- 230000001105 regulatory effect Effects 0.000 claims description 17
- 238000012216 screening Methods 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 12
- 230000001276 controlling effect Effects 0.000 claims description 10
- 238000000605 extraction Methods 0.000 claims description 8
- 230000002596 correlated effect Effects 0.000 claims description 5
- 238000013135 deep learning Methods 0.000 claims description 5
- 230000011218 segmentation Effects 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 13
- 230000006870 function Effects 0.000 description 7
- 230000008569 process Effects 0.000 description 5
- 230000008520 organization Effects 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
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
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- 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
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- 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
- G06F16/35—Clustering; Classification
- G06F16/355—Class or cluster creation or modification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention belongs to the technical field of intelligent power grids, and discloses an intelligent searching method and system based on regulation and control of cloud knowledge graph blood relationship, wherein the intelligent searching method comprises the following steps: acquiring power grid operation data; converting the acquired power grid operation data into a knowledge graph, and storing the knowledge graph into a regulation and control cloud knowledge graph; acquiring a user query statement; carrying out search intention analysis on the user query statement to obtain a processed query statement; and inquiring data in the regulation cloud knowledge graph according to the processed inquiry statement and returning the data to the user. The invention uses data blood-edge analysis to repeat redundant data for multiple sources of data in the power grid, judges the hidden relations among the data in different maps, and can simultaneously search the data of multiple knowledge maps, so that the search content is more comprehensive.
Description
Technical Field
The invention belongs to the technical field of intelligent power grids, and particularly relates to an intelligent searching method and system based on regulation and control of cloud knowledge graph blood relationship.
Background
The smart grid and the large power data are key to realizing green sustainable development due to limited resources and environmental pressure in the construction of a new generation power system. The power regulation and control data penetrate through all links of power production, transmission, scheduling and management, and along with the continuous expansion of the power grid scale, a large amount of power data is accumulated in a power grid system, wherein precious experience of power grid operation and safe production is included. However, due to the characteristics of multiple power grid data and complex power grid relation, although the power industry has unified standards on data formats, certain differences still exist in data storage of all stages of platforms and different fields in the power grid. When the massive power grid data are faced, how to collect and manage the data uniformly discovers the hidden relation among the data, and when the massive power grid data are faced, how to quickly and accurately retrieve the data needed by the user is important to utilizing the large power grid data.
Disclosure of Invention
The invention aims to provide an intelligent searching method and system based on regulation and control of cloud knowledge graph blood relationship, which are used for solving the technical problem that the prior art cannot quickly and accurately search data needed by a user.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
in a first aspect, the invention provides an intelligent searching method based on regulation and control of cloud knowledge graph blood relationship, which comprises the following steps:
acquiring power grid operation data; converting the acquired power grid operation data into a knowledge graph, and storing the knowledge graph into a regulation and control cloud knowledge graph;
acquiring a user query statement; carrying out search intention analysis on the user query statement to obtain a processed query statement; and inquiring data in the regulation cloud knowledge graph according to the processed inquiry statement and returning the data to the user.
The invention is further improved in that: the step of analyzing the search intention of the user query sentence to obtain the processed query sentence specifically comprises the following steps:
the method comprises the steps of word segmentation of a user query sentence, classification of parts of speech through a trained classifier, extraction of an entity and a relation description phrase from the obtained user query sentence, and obtaining a processed query sentence.
The invention is further improved in that: the step of inquiring data in the regulation cloud knowledge graph according to the processed inquiry statement and returning the data to the user specifically comprises the following steps:
generating a corresponding knowledge graph query statement from the processed query statement; inquiring corresponding data from the regulation cloud knowledge graph by utilizing the knowledge graph inquiry statement to obtain a preliminary inquiry result; and screening data with a hidden relation with the primary query result according to the result of the data blood-edge analysis to obtain a comprehensive query result.
The invention is further improved in that: the step of generating the corresponding knowledge graph query statement from the processed query statement specifically comprises the following steps:
identifying an entity in the processed query statement, and screening candidate templates which are possibly matched from the predefined templates;
combining the identified entity with the screened candidate template, judging whether the entity can be matched, and forming a subgraph in the knowledge graph by the successfully matched entity and template; if the subgraphs in the knowledge graph cannot be formed, the matching cannot be considered;
if the template matching is successful, sorting the successfully matched templates according to the matching degree; selecting a template with highest matching degree, and converting the template into a corresponding knowledge graph query statement;
if no template matching is successful, acquiring a grammar dependency tree of the query statement after processing; finding out relation phrases in the grammar dependency tree, identifying entities in the search statement by utilizing grammar rules according to the relation phrases, and generating a triplet of < entities, relations and entities >; and converting the generated (entity, relation, entity) triples into corresponding knowledge-graph query sentences.
The invention is further improved in that: the method also comprises the step of carrying out result organization on the comprehensive query result and feeding back to the user, and specifically comprises the following steps:
for the comprehensive query results, before returning to the user, the results are ranked, and the result with the highest matching degree with the query statement of the user is displayed at the front.
The invention is further improved in that: the degree of matching is calculated from the following formula:
f(p)＝αf 1 (p)+βf 2 (p)
wherein f 1 (p) is the result of a weighted calculation based on the degree of matching of the hit entity attributes, f 2 (p) is the result of the correlation calculation based on the hit entity, F is the attribute set of the hit entity, F i Is a matching value calculated for attribute i, R (i, j) is the correlation of entities i and j, R (i, j) =1 if i and j are correlated, otherwise R (i, j) =0.
The invention is further improved in that: the step of screening the data with the hidden relation with the preliminary query result according to the result of the data blood-edge analysis specifically comprises the following steps:
the calculation formula of the implicit relation is as follows:
f(e i ，e j )＝(α·R 1 (e i ,e j )+β·R 2 (e i ,e j ))·γ
wherein R is 1 Entity e calculated according to graph calculation algorithm and deep learning algorithm i And entity e j Degree of relationship between R 2 Entity e calculated by blood-edge analysis i And entity e j R is the set of all considered blood-edge relationships, for the relationship R in R, R (i, j) =1 if i and j have a relationship, otherwise R (i, j) =0, λ r Is the weight of the relation r, Σλ=1, α and β are weights, α+β=1, γ is the coefficient added taking into account the regional and grid relation, 0<γ<1。
In a second aspect, the invention provides an intelligent search system based on regulating and controlling cloud knowledge graph blood relationship, comprising:
the knowledge graph data blood-margin analysis module is used for acquiring power grid operation data; converting the acquired power grid operation data into a knowledge graph, and storing the knowledge graph into a regulation and control cloud knowledge graph;
the intelligent search module is used for acquiring a user query statement; carrying out search intention analysis on the user query statement to obtain a processed query statement; and inquiring data in the regulation cloud knowledge graph according to the processed inquiry statement and returning the data to the user.
In a third aspect, the present invention provides an electronic device, including a processor and a memory, where the processor is configured to execute a computer program stored in the memory to implement the intelligent search method based on regulating and controlling a cloud knowledge graph blood-edge relationship.
In a fourth aspect, the present invention provides a computer readable storage medium, where at least one instruction is stored, where the at least one instruction, when executed by a processor, implements the intelligent search method based on regulating cloud knowledge graph blood-edge relationships.
Compared with the prior art, the invention has the following beneficial effects:
the invention provides an intelligent searching method and system based on regulation and control cloud knowledge graph blood relationship, which acquire power grid operation data; converting the acquired power grid operation data into a knowledge graph, and storing the knowledge graph into a regulation and control cloud knowledge graph; acquiring a user query statement; carrying out search intention analysis on the user query statement to obtain a processed query statement; and inquiring data in the regulation cloud knowledge graph according to the processed inquiry statement and returning the data to the user. The invention uses data blood-edge analysis to repeat redundant data for multiple sources of data in the power grid, judges the hidden relations among the data in different maps, and can simultaneously search the data of multiple knowledge maps, so that the search content is more comprehensive.
The invention designs a semantic understanding method combining semantic classification and historical search logs, preliminarily judges the search intention of the user through the keywords queried by the user, and further judges the potential search intention or interested content of the user by combining the historical data of the user search and browsing, thereby solving the problem that the search problem input by the user possibly contains too little information and avoiding the trouble of secondary interaction with the user.
The invention designs a search statement generation method with a predefined template as a main part and semantic extraction as an auxiliary part, presets a common query template for the knowledge graph in the specific field, preferentially uses a preset template matching mode to generate the query statement when searching is carried out, and uses the semantic extraction method to generate the query statement when the template matching is unsuccessful, thereby saving the system cost and improving the specialization and accuracy of the query statement to a certain extent.
According to the method, the implicit relation of the data in the different knowledge maps of the regulation cloud is found by utilizing the data blood-source analysis, so that the collaborative search of the different knowledge maps of the regulation cloud is realized. In the invention, the sentence intention classification module judges the search intention of the user by using the history search and the browse log as auxiliary information. According to the invention, intelligent search is realized based on regulating and controlling the blood-related relationship of the cloud knowledge graph, and the matching degree of the search results is comprehensively calculated by utilizing the matching degree of the hit entities and the search segmentation and the correlation relationship between the hit entities in the result sorting.
According to the intelligent search method, intelligent search based on the blood-relation of the regulation and control cloud knowledge graph is studied, data blood-relation analysis is carried out on the entity and the data of the regulation and control cloud knowledge graph, the implicit relation among the data is found out from the complex power grid topological relation, more comprehensive search content is provided for intelligent search, the problems of various regulation and control cloud data and information dispersion are solved, the information acquisition breadth of a user is widened, and the information acquisition precision is improved. Further improving the intelligent level of the regulation and control operation of the power grid.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention. In the drawings:
FIG. 1 is a general schematic diagram of an intelligent search system based on regulating and controlling cloud knowledge graph blood relationship;
FIG. 2 is a schematic diagram of a data blood-lineage analysis module;
FIG. 3 is a schematic diagram of a sentence intent classification module;
FIG. 4 is a schematic diagram of an intelligent search matching module;
FIG. 5 is a schematic diagram of an intelligent search method based on regulation and control of cloud knowledge graph blood relationship;
FIG. 6 is a block diagram of an intelligent search system based on regulating and controlling cloud knowledge graph blood relationship;
fig. 7 is a block diagram of an electronic device according to the present invention.
Detailed Description
The invention will be described in detail below with reference to the drawings in connection with embodiments. It should be noted that, without conflict, the embodiments of the present invention and features of the embodiments may be combined with each other.
The following detailed description is exemplary and is intended to provide further details of the invention. Unless defined otherwise, all technical terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments in accordance with the invention.
Knowledge graph (knowledgegraph): is a semantic network that typically represents attributes of things and relationships between things in the form of < entities, relationships, entity > triples.
Data blood relationship (Data line): refers to a relationship similar to the relationship of human society blood edges formed between data in the process of generating, processing and transferring the data to death.
Example 1
Referring to fig. 1, the invention provides an intelligent search system based on regulation and control cloud knowledge graph blood-edge relationship, which mainly comprises a knowledge graph data blood-edge analysis module and an intelligent search module, wherein the knowledge graph data blood-edge analysis module is used for analyzing by utilizing regulation and control cloud knowledge graph and power grid operation data, normalizing the implicit relationship between data and judging data and supporting intelligent search; and the intelligent searching module is used for removing query data in the knowledge graph according to the content to be queried by the user and returning the query data to the user.
1. Knowledge-graph data blood-margin analysis module
The knowledge graph data blood-source analysis module is used for analyzing by utilizing the regulation and control cloud knowledge graph and the power grid operation data, normalizing the data and judging the hidden relation between the data and is used for supporting intelligent search.
The knowledge graph data blood-source analysis module can find out the hidden relation among the entities as much as possible, remove repeated redundant data of different data sources, normalize the data, and search all relevant data in different graphs as much as possible.
Referring to fig. 2, the knowledge-graph data blood-margin analysis module converts the power grid operation data into a knowledge graph and stores the knowledge graph into the regulation cloud knowledge graph. For regulating and controlling data in a cloud knowledge graph, firstly calculating the relation between the data by using a graph calculation algorithm (shortest path algorithm) and a deep learning algorithm (Apriori algorithm), calculating the distance of an entity in the graph by using the shortest path algorithm, taking the reciprocal as the result of the graph calculation algorithm, calculating the support degree relation between the entities in the graph according to the Apriori algorithm, marking the support degree as 0 which is lower than a threshold value, and carrying out weighted summation on relation values calculated by the two algorithms to preliminarily judge whether the relation exists between the data; through a similarity algorithm, definition and attribute of the entity are subjected to similarity calculation, if the similarity exceeds a threshold value, the entity is judged to belong to the same entity, complementary contents are combined, and redundancy is achievedRemoving the duplication of the rest content; according to the characteristics of the data in the circulation process, such as data sources, data producers, data processing flows and the like, the blood-edge relation of the data is calculated (the calculation process is shown as R 2 )。
In addition, due to the fact that the regulation cloud state, province, region and county nodes are numerous and have superior-subordinate relations, the characteristic that the power grid structure is complex is considered, and the implicit relations between data of different levels of regulation clouds from the same region and data from the same power grid are considered. The specific calculation is as follows:
wherein R is 1 Entity e calculated according to graph calculation algorithm and deep learning algorithm i And entity e j Degree of relationship between R 2 Entity e calculated by blood-edge analysis i And entity e j R is the set of all considered blood-edge relationships, for the relationship R in R, R (i, j) =1 if i and j have a relationship, otherwise R (i, j) =0, λ r Is the weight of the relation r, Σλ=1, α and β are the weights of the relation calculated by both ways, α+β=1, γ is the coefficient added taking into account the geographical and grid relation, 0<γ<1。
2. Intelligent search module
And the intelligent searching module is used for removing query data in the knowledge graph according to the content to be queried by the user and returning the query data to the user.
The intelligent search based on regulating and controlling the cloud knowledge graph blood relationship mainly comprises three modules: the system comprises a statement intention classification module, a knowledge search matching module and a result organization module. The sentence intention classification module is used for carrying out semantic understanding on the acquired user query sentences and extracting key information. And the knowledge search matching module is used for generating a corresponding query sentence by using the extracted key information and querying in the knowledge graph. And the result organization module is used for sorting and ordering the information searched by the knowledge search matching module and displaying the result to the user.
2.1 sentence intention classifying module
Referring to fig. 3, the sentence intent classification module analyzes the content that the user wants to query through the classifier classification alone or the classifier classification in combination with the search log. On one hand, preprocessing a user query sentence, segmenting the user query sentence, classifying parts of speech through a trained classifier, extracting an entity and a relation description phrase from the obtained user query sentence, and obtaining the preprocessed query sentence; on the other hand, the search log is queried, according to the interaction process of the user and the search engine, the content concerned when the user queries the related entity is found out from the historical query record and the browse record of the user, the information possibly to be queried by the user is presumed, the query statement after preprocessing is revised, for example, when the user searches the longkou hydropower plant, the equipment information of the longkou hydropower plant can be clicked most of the time when the user is recorded in the log, and at the moment, besides the related information of the entity of the ' longkou hydropower plant ', what equipment ' is needed to be queried, namely < station, belongs to equipment >, the situation that the acquired information amount is limited due to the fact that the input content of the user is too reduced is avoided, and the result which is difficult to be matched with the user to be searched is avoided.
2.2, knowledge search matching module
Referring to fig. 4, the core of the knowledge search matching module is the generation of query sentences, and since the data are all stored in the form of triples of < entity, relationship, entity >, the key point of the query sentences generation is to generate the corresponding knowledge graph query sentences by using the processed query sentences described by natural language. The generation of query statements is accomplished using a pre-defined template-based, semantic-based extraction-based approach. Templates can be broadly divided into three types based on entity, relationship, and attributes: (1) "entity" templates like "what is a circuit breaker? ", for viewing relevant information of the device; (2) "entity+relationship" templates, such as "what devices are in a Longkou hydropower plant? "matched relationship triplets are < station, belongs to, device >," records of step-down transformer 001? "matched relationship triples are < device, related record, record >; (3) "entity+attribute" template, "voltage class of step-down transformer 001? ", which can be used to view specific attribute information of an entity.
The specific flow of query statement generation is as follows:
1) Identifying entities in the processed query sentences according to the obtained processed query sentences of the sentence intention classification module, and screening candidate templates which are possibly matched from the predefined templates;
2) Combining the identified entity with the screened candidate template, judging whether the entity can be matched, and enabling the successfully matched entity and template to form a subgraph in the knowledge graph; if the subgraphs in the knowledge graph cannot be formed, the matching cannot be considered.
3) If the template matching is successful, sorting the successfully matched templates according to the matching degree, wherein the matching degree is obtained by calculating the correlation between the templates and the search sentences;
where I is a set of entities and relationships in the identified query statement, R i Indicating whether the element I in I is contained in the template successfully matched, if so, R i =1, otherwise R i ＝0，λ i Representing the weight of element i, λ if i is an entity i =1, otherwise λ i ＝0.5。
4) Selecting the template with the highest matching degree, converting the template into a corresponding knowledge graph query sentence, and querying a result in the knowledge graph.
If a matching template cannot be found for a search term, a semantic extraction based approach is used to generate a query term.
1) Acquiring a grammar dependency tree of the processed query sentence by utilizing a sentence intention classification module;
2) Finding out relation phrases in the grammar dependency tree, identifying entities in the search statement by utilizing grammar rules according to the relation phrases, and generating a triplet of < entities, relations and entities >;
3) And converting the generated (entity, relation, entity) triples into corresponding knowledge graph query sentences, and querying in the knowledge graph.
After the search statement of the user is converted into a corresponding structured query statement, the required data is queried from the regulation cloud knowledge graph, and a preliminary query result is obtained; and screening data with hidden relations with the primary query results according to the results of the data blood-edge analysis, and searching the results of the user query contents as comprehensively as possible.
2.3, result organization Module
And (3) sequencing the accurate results obtained by searching from the knowledge graph before returning to the user, and displaying the result with the highest matching degree with the search statement. In the matching degree calculation, in addition to the matching degree between the query word and the entity, the relationship between hit entities needs to be considered. The score for the search result ranking is therefore composed primarily of two parts, one part being the matching value of the entity to the term and the other part being the relationship between the entities. The degree of matching is calculated from the following formula:
f(p)＝αf 1 (p)+βf 2 (p)
wherein f 1 (p) is the result of a weighted calculation based on the degree of matching of the hit entity attributes, f 2 (p) is the result of the correlation calculation based on the hit entity, F is the attribute set of the hit entity, F i Is a matching value calculated for attribute i, R (i, j) is the correlation of entities i and j, R (i, j) =1 if i and j are correlated, otherwise R (i, j) =0. According to the above formula, the specific steps of matching degree calculation are as follows:
1) Calculating the matching value F of each attribute of each hit entity and the search term i The similarity is calculated;
2) Weighting and summing the matching values of the hit entity attributes to obtain f 1 (p)；
3) Calculating the relation value among all hit entities, and if any two entities are related, adding 1 to the relation value, namely calculating how many pairs of related entities are in all hit entities;
4) And carrying out weighted summation on the matching value and the relation value to obtain a final matching degree score f (p) of the search result.
Example 2
Referring to fig. 5, the invention provides an intelligent searching method based on regulating and controlling cloud knowledge graph blood relationship, comprising the following steps:
acquiring power grid operation data; converting the acquired power grid operation data into a knowledge graph, and storing the knowledge graph into a regulation and control cloud knowledge graph;
acquiring a user query statement; carrying out search intention analysis on the user query statement to obtain a processed query statement; and inquiring data in the regulation cloud knowledge graph according to the processed inquiry statement and returning the data to the user.
In a specific embodiment, the step of performing search intention analysis on the user query sentence to obtain the processed query sentence specifically includes:
the method comprises the steps of word segmentation of a user query sentence, classification of parts of speech through a trained classifier, extraction of an entity and a relation description phrase from the obtained user query sentence, and obtaining a processed query sentence.
In a specific embodiment, the step of querying data in the regulatory cloud knowledge graph according to the processed query statement and returning the query data to the user specifically includes:
generating a corresponding knowledge graph query statement from the processed query statement; inquiring corresponding data from the regulation cloud knowledge graph by utilizing the knowledge graph inquiry statement to obtain a preliminary inquiry result; and screening data with a hidden relation with the primary query result according to the result of the data blood-edge analysis to obtain a comprehensive query result.
In a specific embodiment, the step of generating the processed query sentence into the corresponding knowledge-graph query sentence specifically includes:
identifying an entity in the processed query statement, and screening candidate templates which are possibly matched from the predefined templates;
combining the identified entity with the screened candidate template, judging whether the entity can be matched, and forming a subgraph in the knowledge graph by the successfully matched entity and template; if the subgraphs in the knowledge graph cannot be formed, the matching cannot be considered;
if the template matching is successful, sorting the successfully matched templates according to the matching degree; selecting a template with highest matching degree, and converting the template into a corresponding knowledge graph query statement;
if no template matching is successful, acquiring a grammar dependency tree of the query statement after processing; finding out relation phrases in the grammar dependency tree, identifying entities in the search statement by utilizing grammar rules according to the relation phrases, and generating a triplet of < entities, relations and entities >; and converting the generated (entity, relation, entity) triples into corresponding knowledge-graph query sentences.
In a specific embodiment, the method further includes a step of feeding back the user after organizing the comprehensive query results, and specifically includes:
for the comprehensive query results, before returning to the user, the results are ranked, and the result with the highest matching degree with the query statement of the user is displayed at the front.
In one embodiment, the matching degree is calculated by the following formula:
f(p)＝αf 1 (p)+βf 2 (p)
wherein f 1 (p) is the result of a weighted calculation based on the degree of matching of the hit entity attributes, f 2 (p) is the result of the correlation calculation based on the hit entity, F is the attribute set of the hit entity, F i Is a matching value calculated for attribute i, R (i, j) is the correlation of entities i and j, R (i, j) =1 if i and j are correlated, otherwise R (i, j) =0.
In a specific embodiment, the step of screening the data with the hidden relationship with the preliminary query result according to the result of the data blood-edge analysis specifically includes:
the calculation formula of the implicit relation is as follows:
f(e i ，e j )＝(α·R 1 (e i ，e j )+β·R 2 (e i ，e j ))·γ
wherein R is 1 Is based on graph calculation algorithm and depthEntity e calculated by learning algorithm i And entity e j Degree of relationship between R 2 Entity e calculated by blood-edge analysis i And entity e j R is the set of all considered blood-edge relationships, for the relationship R in R, R (i, j) =1 if i and j have a relationship, otherwise R (i, j) =0, λ r Is the weight of the relation r, Σλ=1, α and β are weights, α+β=1, r is the coefficient increased taking into account the regional and grid relations, 0<γ<1。
Example 3
Referring to fig. 6, the invention provides an intelligent search system based on regulating and controlling cloud knowledge graph blood relationship, comprising:
the knowledge graph data blood-margin analysis module is used for acquiring power grid operation data; converting the acquired power grid operation data into a knowledge graph, and storing the knowledge graph into a regulation and control cloud knowledge graph;
the intelligent search module is used for acquiring a user query statement; carrying out search intention analysis on the user query statement to obtain a processed query statement; and inquiring data in the regulation cloud knowledge graph according to the processed inquiry statement and returning the data to the user.
In a specific embodiment, the step of performing search intention analysis on the user query sentence to obtain the processed query sentence specifically includes:
the method comprises the steps of word segmentation of a user query sentence, classification of parts of speech through a trained classifier, extraction of an entity and a relation description phrase from the obtained user query sentence, and obtaining a processed query sentence.
In a specific embodiment, the step of querying data in the regulatory cloud knowledge graph according to the processed query statement and returning the query data to the user specifically includes:
generating a corresponding knowledge graph query statement from the processed query statement; inquiring corresponding data from the regulation cloud knowledge graph by utilizing the knowledge graph inquiry statement to obtain a preliminary inquiry result; and screening data with a hidden relation with the primary query result according to the result of the data blood-edge analysis to obtain a comprehensive query result.
In a specific embodiment, the step of generating the processed query sentence into the corresponding knowledge-graph query sentence specifically includes:
identifying an entity in the processed query statement, and screening candidate templates which are possibly matched from the predefined templates;
combining the identified entity with the screened candidate template, judging whether the entity can be matched, and forming a subgraph in the knowledge graph by the successfully matched entity and template; if the subgraphs in the knowledge graph cannot be formed, the matching cannot be considered;
if the template matching is successful, sorting the successfully matched templates according to the matching degree; selecting a template with highest matching degree, and converting the template into a corresponding knowledge graph query statement;
if no template matching is successful, acquiring a grammar dependency tree of the query statement after processing; finding out relation phrases in the grammar dependency tree, identifying entities in the search statement by utilizing grammar rules according to the relation phrases, and generating a triplet of < entities, relations and entities >; and converting the generated (entity, relation, entity) triples into corresponding knowledge-graph query sentences.
In a specific embodiment, the method further includes a step of feeding back the user after organizing the comprehensive query results, and specifically includes:
for the comprehensive query results, before returning to the user, the results are ranked, and the result with the highest matching degree with the query statement of the user is displayed at the front.
In one embodiment, the matching degree is calculated by the following formula:
f(p)＝αf 1 (p)+βf 2 (p)
wherein f 1 (p) is the result of a weighted calculation based on the degree of matching of the hit entity attributes, f 2 (p) is the result of the correlation calculation based on the hit entity, F is the attribute set of the hit entity, F i Is a matching value calculated for attribute i, R (i, j) is the correlation of entities i and j, R (i, j) =1 if i and j are correlated, otherwise R (i, j) =0.
In a specific embodiment, the step of screening the data with the hidden relationship with the preliminary query result according to the result of the data blood-edge analysis specifically includes:
the calculation formula of the implicit relation is as follows:
f(e i ，e j )＝(α·R 1 (e i ，e j )+β·R 2 (e i ，e j ))·γ
wherein R is 1 Entity e calculated according to graph calculation algorithm and deep learning algorithm i And entity e j Degree of relationship between R 2 Entity e calculated by blood-edge analysis i And entity e j R is the set of all considered blood-edge relationships, for the relationship R in R, R (i, h) =1 if i and j have a relationship, otherwise R (i, j) =0, λ r Is the weight of the relation r, Σλ=1, α and β are weights, α+β=1, γ is the coefficient added taking into account the regional and grid relation, 0<γ<1。
Example 4
Referring to fig. 7, the present invention further provides an electronic device 100 for implementing an intelligent searching method based on regulation and control of a cloud knowledge graph blood relationship; the electronic device 100 comprises a memory 101, at least one processor 102, a computer program 103 stored in the memory 101 and executable on the at least one processor 102, and at least one communication bus 104.
The memory 101 may be used to store the computer program 103, and the processor 102 implements the intelligent searching method steps described in embodiment 1 or 2 based on the regulated cloud knowledge graph blood edge relationship by running or executing the computer program stored in the memory 101 and calling the data stored in the memory 101. The memory 101 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like; the storage data area may store data (such as audio data) created according to the use of the electronic device 100, and the like. In addition, the memory 101 may include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash Card (Flash Card), at least one disk storage device, a Flash memory device, or other non-volatile solid state storage device.
The at least one processor 102 may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field-programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. The processor 102 may be a microprocessor or the processor 102 may be any conventional processor or the like, the processor 102 being a control center of the electronic device 100, the various interfaces and lines being utilized to connect various portions of the overall electronic device 100.
The memory 101 in the electronic device 100 stores a plurality of instructions to implement an intelligent search method based on regulating cloud knowledge graph blood-edge relationships, and the processor 102 may execute the plurality of instructions to implement:
acquiring power grid operation data; converting the acquired power grid operation data into a knowledge graph, and storing the knowledge graph into a regulation and control cloud knowledge graph;
acquiring a user query statement; carrying out search intention analysis on the user query statement to obtain a processed query statement; and inquiring data in the regulation cloud knowledge graph according to the processed inquiry statement and returning the data to the user.
Example 5
The modules/units integrated in the electronic device 100 may be stored in a computer readable storage medium if implemented in the form of software functional units and sold or used as a stand alone product. Based on such understanding, the present invention may implement all or part of the flow of the method of the above embodiment, or may be implemented by a computer program to instruct related hardware, where the computer program may be stored in a computer readable storage medium, and when the computer program is executed by a processor, the computer program may implement the steps of each of the method embodiments described above. Wherein the computer program comprises computer program code which may be in source code form, object code form, executable file or some intermediate form etc. The computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, and a Read-Only Memory (ROM).
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention 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 invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations 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.
Finally, it should be noted that: the above embodiments are only for illustrating the technical aspects of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the above embodiments, it should be understood by those of ordinary skill in the art that: modifications and equivalents may be made to the specific embodiments of the invention without departing from the spirit and scope of the invention, which is intended to be covered by the claims.
Claims (10)
1. The intelligent searching method based on regulating and controlling the blood relationship of the cloud knowledge graph is characterized by comprising the following steps:
acquiring power grid operation data; converting the acquired power grid operation data into a knowledge graph, and storing the knowledge graph into a regulation and control cloud knowledge graph;
acquiring a user query statement; carrying out search intention analysis on the user query statement to obtain a processed query statement; and inquiring data in the regulation cloud knowledge graph according to the processed inquiry statement and returning the data to the user.
2. The intelligent search method based on regulation and control cloud knowledge graph blood relationship according to claim 1, wherein the step of performing search intention analysis on the user query sentence to obtain the processed query sentence specifically comprises the following steps:
the method comprises the steps of word segmentation of a user query sentence, classification of parts of speech through a trained classifier, extraction of an entity and a relation description phrase from the obtained user query sentence, and obtaining a processed query sentence.
3. The intelligent searching method based on the blood relationship of the regulation and control cloud knowledge graph according to claim 1, wherein the step of inquiring data in the regulation and control cloud knowledge graph according to the processed inquiry statement and returning the data to the user specifically comprises the following steps:
generating a corresponding knowledge graph query statement from the processed query statement; inquiring corresponding data from the regulation cloud knowledge graph by utilizing the knowledge graph inquiry statement to obtain a preliminary inquiry result; and screening data with a hidden relation with the primary query result according to the result of the data blood-edge analysis to obtain a comprehensive query result.
4. The intelligent searching method based on the regulation and control cloud knowledge graph blood relationship according to claim 3, wherein the step of generating the processed query sentence into the corresponding knowledge graph query sentence specifically comprises the following steps:
identifying an entity in the processed query statement, and screening candidate templates which are possibly matched from the predefined templates;
combining the identified entity with the screened candidate template, judging whether the entity can be matched, and forming a subgraph in the knowledge graph by the successfully matched entity and template; if the subgraphs in the knowledge graph cannot be formed, the matching cannot be considered;
if the template matching is successful, sorting the successfully matched templates according to the matching degree; selecting a template with highest matching degree, and converting the template into a corresponding knowledge graph query statement;
if no template matching is successful, acquiring a grammar dependency tree of the query statement after processing; finding out relation phrases in the grammar dependency tree, identifying entities in the search statement by utilizing grammar rules according to the relation phrases, and generating a triplet of < entities, relations and entities >; and converting the generated (entity, relation, entity) triples into corresponding knowledge-graph query sentences.
5. The intelligent search method based on regulation and control cloud knowledge graph blood relationship according to claim 3, further comprising a step of organizing the overall query result and feeding back the result to the user, and specifically comprising:
for the comprehensive query results, before returning to the user, the results are ranked, and the result with the highest matching degree with the query statement of the user is displayed at the front.
6. The intelligent search method based on regulation and control cloud knowledge graph blood relationship according to claim 5, wherein the matching degree is calculated by the following formula:
f(p)＝αf 1 (p)+βf 2 (p)
wherein f 1 (p) is the result of a weighted calculation based on the degree of matching of the hit entity attributes, f 2 (p) is the result of the correlation calculation based on the hit entity, F is the attribute set of the hit entity, F i Is a matching value calculated for attribute i, R (i, j) is the correlation of entities i and j, R (i, j) =1 if i and j are correlated, otherwise R (i, j) =0.
7. The intelligent searching method based on the regulation and control cloud knowledge graph blood-edge relation according to claim 3, wherein the step of screening the data with the hidden relation with the preliminary query result according to the result of the data blood-edge analysis specifically comprises the following steps:
the calculation formula of the implicit relation is as follows:
f(e i ，e j )＝(α·R 1 (e i ，e j )+β·R 2 (e i ，e j ))·γ
wherein R is 1 Entity e calculated according to graph calculation algorithm and deep learning algorithm i And entity e j Degree of relationship between R 2 Entity e calculated by blood-edge analysis i And entity e j R is the set of all considered blood-edge relationships, for the relationship R in R, R (i, j) =1 if i and j have a relationship, otherwise R (i, j) =0, λ r Is the weight of the relation r, Σλ=1, α and β are weights, α+β=1, γ is the coefficient added taking into account the regional and grid relation, 0<γ<1。
8. Intelligent search system based on regulation and control cloud knowledge graph blood relationship, characterized by comprising:
the knowledge graph data blood-margin analysis module is used for acquiring power grid operation data; converting the acquired power grid operation data into a knowledge graph, and storing the knowledge graph into a regulation and control cloud knowledge graph;
the intelligent search module is used for acquiring a user query statement; carrying out search intention analysis on the user query statement to obtain a processed query statement; and inquiring data in the regulation cloud knowledge graph according to the processed inquiry statement and returning the data to the user.
9. An electronic device comprising a processor and a memory, wherein the processor is configured to execute a computer program stored in the memory to implement the intelligent search method based on regulating cloud knowledge graph blood-edge relationships according to any one of claims 1 to 7.
10. A computer-readable storage medium storing at least one instruction that when executed by a processor implements the intelligent search method based on regulating cloud knowledge graph blood edge relationships of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310430048.5A CN116610810A (en) | 2023-04-20 | 2023-04-20 | Intelligent searching method and system based on regulation and control of cloud knowledge graph blood relationship |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310430048.5A CN116610810A (en) | 2023-04-20 | 2023-04-20 | Intelligent searching method and system based on regulation and control of cloud knowledge graph blood relationship |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116610810A true CN116610810A (en) | 2023-08-18 |
Family
ID=87682640
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310430048.5A Pending CN116610810A (en) | 2023-04-20 | 2023-04-20 | Intelligent searching method and system based on regulation and control of cloud knowledge graph blood relationship |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116610810A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116910374A (en) * | 2023-09-13 | 2023-10-20 | 中电科大数据研究院有限公司 | Knowledge graph-based health care service recommendation method, device and storage medium |
-
2023
- 2023-04-20 CN CN202310430048.5A patent/CN116610810A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116910374A (en) * | 2023-09-13 | 2023-10-20 | 中电科大数据研究院有限公司 | Knowledge graph-based health care service recommendation method, device and storage medium |
| CN116910374B (en) * | 2023-09-13 | 2024-01-02 | 中电科大数据研究院有限公司 | Knowledge graph-based health care service recommendation method, device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108804521B (en) | Knowledge graph-based question-answering method and agricultural encyclopedia question-answering system | |
| CN108804641B (en) | Text similarity calculation method, device, equipment and storage medium | |
| WO2021093755A1 (en) | Matching method and apparatus for questions, and reply method and apparatus for questions | |
| US9563665B2 (en) | Product search method and system | |
| US8341112B2 (en) | Annotation by search | |
| CN104199965B (en) | Semantic information retrieval method | |
| CN105045875B (en) | Personalized search and device | |
| US20180341686A1 (en) | System and method for data search based on top-to-bottom similarity analysis | |
| CN112035599B (en) | Query method and device based on vertical search, computer equipment and storage medium | |
| CN111090771B (en) | Song searching method, device and computer storage medium | |
| CN109840532A (en) | A kind of law court's class case recommended method based on k-means | |
| WO2018227930A1 (en) | Method and device for intelligently prompting answers | |
| US20150205860A1 (en) | Information retrieval device, information retrieval method, and information retrieval program | |
| JP2018501540A (en) | Stopword identification method and apparatus | |
| CN109783638B (en) | User comment clustering method based on semi-supervised learning | |
| CN111078832A (en) | Auxiliary response method and system for intelligent customer service | |
| CN111339424B (en) | Method, device and equipment for searching based on keywords and storage medium | |
| KR20080041388A (en) | System and method for classifying document | |
| CN114997288A (en) | Design resource association method | |
| CN111159381B (en) | Data searching method and device | |
| CN116610810A (en) | Intelligent searching method and system based on regulation and control of cloud knowledge graph blood relationship | |
| CN111966899B (en) | Search ranking method, system and computer readable storage medium | |
| CN117076636A (en) | Information query method, system and equipment for intelligent customer service | |
| CN111460114A (en) | Retrieval method, device, equipment and computer readable storage medium | |
| CN110555199B (en) | Article generation method, device, equipment and storage medium based on hotspot materials |
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 |