CN117235219A - Reservoir knowledge intelligent question-answering system based on flood prevention demands - Google Patents
Reservoir knowledge intelligent question-answering system based on flood prevention demands Download PDFInfo
- Publication number
- CN117235219A CN117235219A CN202311193081.7A CN202311193081A CN117235219A CN 117235219 A CN117235219 A CN 117235219A CN 202311193081 A CN202311193081 A CN 202311193081A CN 117235219 A CN117235219 A CN 117235219A
- Authority
- CN
- China
- Prior art keywords
- reservoir
- question
- knowledge
- natural sentence
- intelligent
- 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
- 230000002265 prevention Effects 0.000 title claims abstract description 24
- 238000007781 pre-processing Methods 0.000 claims description 4
- 230000003068 static effect Effects 0.000 abstract description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 31
- 239000008186 active pharmaceutical agent Substances 0.000 description 13
- 238000000034 method Methods 0.000 description 12
- 238000010586 diagram Methods 0.000 description 9
- 238000012544 monitoring process Methods 0.000 description 6
- 238000005457 optimization Methods 0.000 description 6
- 238000010276 construction Methods 0.000 description 5
- 230000011218 segmentation Effects 0.000 description 5
- 230000008901 benefit Effects 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 239000010985 leather Substances 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000009430 construction management Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A10/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE at coastal zones; at river basins
- Y02A10/40—Controlling or monitoring, e.g. of flood or hurricane; Forecasting, e.g. risk assessment or mapping
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a reservoir knowledge intelligent question-answering system based on flood control demands, which comprises the following steps: the knowledge base unit at least comprises reservoir knowledge in various flood prevention aspects; the intelligent question-answering unit can obtain answers of natural sentence questions based on the natural sentence questions in the aspect of flood prevention, and achieves dynamic and static question-answering of the reservoir; the display unit is used for displaying reservoir knowledge in terms of flood prevention on a set interface, and is also used for displaying answers of question phases of the natural sentences on the set interface.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a reservoir knowledge intelligent question-answering system based on flood prevention requirements.
Background
The economic development and social stability bureau of flood control work, the personal benefit of the masses of the business and the life and property safety of the masses of the business and the people, so that the flood control work is very important when the flood control work is carried out in the flood season. The reservoir is used as a controlled hydraulic engineering for flood control in a river basin, and can play an important role in disaster prevention and reduction by means of peak clipping, peak shifting, flood storage, flood retention and other measures. The digital twin drainage basin construction serves as a foundation and a core of an intelligent water conservancy system and becomes an important point for industry development; the intelligent flood prevention application is used as an entry point to study the construction management and the safe operation of reservoir engineering, and has great significance for the economic and social development of national people in China.
The knowledge platform is an important component in the digital twin-basin platform; compared with the traditional digital watershed platform, the digital twin watershed integrates various water conservancy professional models and multi-source data by means of the knowledge platform. Introducing the knowledge graph into the water conservancy industry is one of the necessary means for constructing the digital twin drainage basin; it is an important branching technique of artificial intelligence, essentially a semantic knowledge base, which stores knowledge information in the form of a structured semantic network and graphically describes entities and concepts and their relationships. And the knowledge map is utilized to realize extraction, management and combined application of knowledge such as water conservancy object association relation, water conservancy rule and the like, and meanwhile, an intelligent kernel is provided for the digital twin river basin by combining a forecast scheduling scheme, business rules, historical scenes, expert experience and the like.
The construction of water conservancy knowledge platform still is in the start stage in intelligent water conservancy field, exists following not enough at present: (1) The water conservancy informatization system has rich knowledge information, but has various problems of bar segmentation, repeated construction, information sharing, application coordination difficulty and the like due to the fact that unstructured information is large and knowledge is dispersed. (2) The traditional water conservancy knowledge graph is generally carried out by a method for storing a static data ternary relation, and real-time data is difficult to obtain through the traditional water conservancy knowledge graph; the reservoir flood control situation is high in timeliness, and the requirements of hydraulic engineering on dynamic data and professional analysis results are not met.
Disclosure of Invention
The invention provides a reservoir knowledge intelligent question-answering system, a reservoir knowledge intelligent question-answering method and a computer storage medium based on flood control requirements, which can at least partially solve the technical problems.
In order to solve the technical problems, the invention provides a reservoir knowledge intelligent question-answering system based on flood prevention requirements, which comprises the following steps:
the knowledge base unit at least comprises reservoir knowledge in various flood prevention aspects;
the intelligent question-answering unit can obtain answers of natural sentence questions based on the natural sentence questions in the aspect of flood prevention;
the display unit is used for displaying reservoir knowledge in terms of flood prevention on a set interface, and is also used for displaying answers of question phases of the natural sentences on the set interface.
As the optimization of the technical scheme, the reservoir knowledge intelligent system further comprises a reservoir map unit, wherein the reservoir map unit at least comprises a plurality of reservoir entities and information related to the reservoir entities to form a multi-dimensional reservoir knowledge map, the display unit is further used for displaying the multi-dimensional reservoir knowledge map, and the display unit is further used for displaying the multi-dimensional reservoir knowledge map.
As an optimization of the above technical solution, the intelligent question-answering unit includes an input module, a processing module, a query matching module and an answer processing module, where the input module is configured to input a natural sentence question in terms of flood prevention, the processing module is configured to perform question processing on the input natural sentence question to obtain key information in the natural sentence question, the query matching module is configured to obtain, from the reservoir map unit, a node corresponding to the key information in the natural sentence question based on the key information in the natural sentence question, and the answer processing module is configured to process information of the node and generate an answer to be displayed.
As a preferable mode of the above technical solution, the query matching module is further configured to determine a search mode based on the key information in the natural sentence question, and select whether to search in the reservoir map unit based on the search mode.
As an preference of the above technical solution, the search mode specifically includes a first search mode and a second search mode, and the query matching module is further configured to determine a search mode based on key information in the natural sentence question, and select whether to perform the search in the reservoir map unit based on the search mode specifically includes: the query matching module is further used for judging whether to enter a first retrieval mode or a second retrieval mode based on the key information in the natural sentence question, searching is carried out in the reservoir map unit when judging that the first retrieval mode is entered so as to obtain nodes corresponding to the key information in the natural sentence question, the second retrieval mode is an API calling mode, the network is connected through an API interface when judging that the second retrieval mode is entered, the query matching module is further used for obtaining real-time dynamic information corresponding to the key information in the natural sentence question from the network knowledge base based on the key information in the natural sentence question, and the answer processing unit is correspondingly used for processing the real-time dynamic information and generating an answer to be displayed.
As an optimization of the above technical solution, the question processing the input natural sentence question to obtain the key information in the natural sentence question specifically includes: firstly, preprocessing the input natural sentence question to extract keywords in the natural sentence question, and performing part-of-speech analysis on the keywords in the natural sentence question.
As an optimization of the above technical scheme, the reservoir map unit further comprises a map retrieval module, wherein the map retrieval module is used for displaying the reservoir knowledge map on a set interface according to a preset mode.
As a preferable mode of the above technical solution, the knowledge base unit specifically includes: a forecast scheduling scheme library, a business rule library, an expert experience library, a historical scene library, an engineering safety knowledge library and a shared knowledge library.
As the optimization of the technical scheme, the service rule base comprises reservoir dispatching operation rules, reservoir waterproof early warning rules, electromechanical equipment operation rules, reservoir safety emergency operation rules, emergency grading rules and standard specifications, the historical scene base at least comprises a historical flood knowledge base, and the engineering safety knowledge base comprises engineering historical leather, a technical file base and an engineering case base.
As an optimization of the above technical solution, the map retrieval module specifically includes a tag retrieval module and an entity retrieval module, where the tag retrieval module is configured to display a reservoir knowledge map formed by all entities under a certain concept level on a set interface, and the entity retrieval module is configured to highlight the reservoir knowledge map formed by a specific entity on the set interface.
The intelligent reservoir knowledge question-answering system based on the flood control requirements comprises a knowledge base unit, an intelligent question-answering unit and a display unit, wherein the knowledge base unit is provided with reservoir knowledge in various flood control aspects, the intelligent question-answering unit can obtain answers of natural sentence question sentences based on input of natural sentence question sentences in the flood control aspects, and the display unit can display reservoir knowledge in the flood control aspects or answers of intelligent question-answering according to specific requirements, so that the reservoir knowledge in the associated flood control aspects can be rapidly and intelligently obtained.
The foregoing description is only an overview of the present invention, and is intended to be implemented in accordance with the teachings of the present invention in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present invention more readily apparent.
Drawings
FIG. 1 shows a schematic diagram of a reservoir knowledge intelligent question-answering system based on flood control requirements;
FIG. 2 is a schematic diagram showing the structure of the intelligent question-answering unit in the embodiment of the present invention;
FIG. 3 shows a schematic diagram of a water reservoir map unit in an embodiment of the present invention;
FIG. 4 is a schematic flow chart of question processing in an embodiment of the invention;
FIG. 5 is a schematic diagram showing the construction of a knowledge base unit in an embodiment of the invention;
FIG. 6 is a schematic diagram of a display interface of a knowledge base unit in an embodiment of the invention;
FIG. 7 is a schematic diagram of a display interface of answers in a basic information question-answering process according to an embodiment of the present invention;
FIG. 8 is a schematic diagram of a display interface for monitoring answers in real-time during question answering according to an embodiment of the present invention;
FIG. 9 is an interface schematic diagram of the reservoir knowledge graph displayed by the label retrieval module in the embodiment of the invention;
FIG. 10 is an interface schematic diagram of a reservoir knowledge graph displayed by an entity retrieval module in an embodiment of the invention;
in the figure: 10. a knowledge base unit; 20. a display unit; 30. an intelligent question-answering unit; 40. a reservoir map unit; 301. an input module; 302. a processing module; 303. a query matching module; 304. an answer processing module; 401. a tag retrieval module; 402. and an entity retrieval module.
Detailed Description
In order to make the objects, features and advantages of the present invention more comprehensible, the technical solutions according to the embodiments of the present invention will be clearly described in the following with reference to the accompanying drawings, and it is obvious that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, an embodiment of the present invention provides a reservoir knowledge intelligent question-answering system based on flood prevention requirements, including:
a knowledge base unit 10, wherein the knowledge base unit 10 at least comprises reservoir knowledge in various flood prevention aspects;
the intelligent question-answering unit 30, the intelligent question-answering unit 30 can obtain the answer of the natural sentence question based on the natural sentence question in the aspect of input flood prevention;
the display unit 20, the display unit 20 is used for displaying reservoir knowledge in terms of flood prevention on a set interface, and the display unit 20 is also used for displaying answers of natural sentence question phases on the set interface.
The intelligent reservoir knowledge question-answering system based on flood control requirements comprises a knowledge base unit 10, an intelligent question-answering unit 30 and a display unit 20, wherein the knowledge base unit 10 is provided with reservoir knowledge in various flood control aspects, the intelligent question-answering unit 30 can obtain answers of natural sentence questions based on natural sentence questions in the input flood control aspects, and the display unit 20 can display reservoir knowledge in the flood control aspects or answers of intelligent questions according to specific requirements, and can rapidly and intelligently obtain reservoir knowledge in the flood control aspects of relevance.
In a further implementation manner of this embodiment, the reservoir knowledge intelligent system further includes a reservoir map unit 40, where the reservoir map unit 40 includes at least a plurality of reservoir entities and information related to the reservoir entities to form a multi-dimensional reservoir knowledge map, and the display unit 20 is further configured to display the multi-dimensional reservoir knowledge map.
The display unit 20 in this embodiment is further configured to display a multi-dimensional reservoir knowledge graph, which may deeply represent a hierarchical relationship between knowledge.
Referring to fig. 2, in a further implementation manner of the present embodiment, the intelligent question-answering unit 30 includes an input module 301, a processing module 302, a query matching module 303, and an answer processing module 304, where the input module 301 is configured to input a natural sentence question in terms of flood prevention, the processing module 302 is configured to perform question processing on the input natural sentence question to obtain key information in the natural sentence question, the query matching module 303 is configured to obtain, from the reservoir map unit 40, a node corresponding to the key information in the natural sentence question based on the key information in the natural sentence question, and the answer processing module 304 is configured to process information of the node and generate an answer to be displayed.
Specifically, the intelligent question-answering unit 30 in this embodiment may perform a basic information question-answering, which may obtain important basic data of the entity object through the basic information question-answering, including reservoir engineering basic data (for example, such as reservoir position, longitude and latitude, the basin to which the intelligent question-answering unit belongs, reservoir type, level, dam type, rain area, etc.), reservoir engineering characteristic information, reservoir downstream important section information, monitoring station information, basic information of the embankment, characteristic information of the sluice engineering, etc.
For example, the question "what is the flood control high water level of the peri-public reservoir? The processing module 302 processes the inputted question to extract key information of the question, such as the entity name: week residence reservoir, attribute name: flood control high water level, numerical problem: how much, the query matching module 303 searches for the first location node based on the reservoir knowledge graph of the entity name of the pericycle reservoir in the reservoir graph unit 40, and first according to the word segmentation result: the method comprises the steps of determining the number of the flood control high water level (attribute name) of a week residence reservoir (entity name), determining the number of the flood control high water level (attribute name) by a part-of-speech matching search mode (first search mode), searching the map for the entity of the week residence reservoir, searching each attribute under the entity, searching the attribute of the flood control high water level, returning an attribute value 237.12m, and processing information of each position node by an answer processing module 304 to obtain an answer to be displayed, wherein the answer is described as follows: entity name + attribute name + value, then the specific answer is displayed by the display unit 20 see fig. 7: "around house reservoir flood control high water level 237.12m".
In a further implementation manner of this embodiment, the query matching module 303 is further configured to determine a search pattern based on the key information in the natural sentence question, and select whether to perform the search in the reservoir map unit 40 based on the search pattern.
In this embodiment, a specific search mode may be determined according to key information in a specific natural sentence question, and a specific direction or position for performing search may be selected according to the specific search mode.
In a further implementation manner of this embodiment, the search mode specifically includes a first search mode and a second search mode, and the query matching module 303 is further configured to determine the search mode based on the key information in the natural sentence question, and select whether to perform the search in the reservoir map unit 40 based on the search mode specifically includes: the query matching module 303 is further configured to determine whether to enter a first search mode or a second search mode based on the key information in the natural sentence question, perform search in the reservoir map unit 40 to obtain a node corresponding to the key information in the natural sentence question when determining that the first search mode is entered, the second search mode is an API call mode, connect to a network through a connection API interface when determining that the second search mode is entered, and the query matching module 303 is further configured to obtain real-time dynamic information corresponding to the key information in the natural sentence question from a network knowledge base based on the key information in the natural sentence question, and the answer processing unit is configured to process the real-time dynamic information and generate an answer to be displayed accordingly.
The intelligent question-answering unit 30 in this embodiment may also implement real-time monitoring question-answering and forecast scheduling question-answering, for example, the real-time monitoring question-answering may implement real-time monitoring of important data of entity objects, including rain condition data (for example, such as current rainfall condition of reservoirs, rainfall condition of important sites, past rainfall condition of reservoirs and intervals, etc.), water condition data, industrial condition data, typhoon data, etc., and construct a real-time monitoring question-answering mode, such as "what is the current water level of the reservoir of the surrounding public house? "according to data search (water level station time-by-time water level inquiry service), search conditions (water level station code+time condition+hydrologic element), data result (water level time sequence), answer description (ObjectID 2name (water level station code) +time condition+water level is+water level), output answer text see fig. 8: the current water level of the pericycle reservoir is 207.94m and a standardized window is displayed.
The forecast scheduling questions and answers can realize forecast scheduling of important data of the entity object, including future rainfall data, reservoir rainfall (flood bearing capacity) condition, real-time forecast data and the like.
In a further implementation manner of the present embodiment, performing question processing on an input natural sentence question to obtain key information in the natural sentence question specifically includes: firstly, preprocessing an input natural sentence question to extract keywords in the natural sentence question, and performing part-of-speech analysis on the keywords in the natural sentence question.
For example, referring to FIG. 4, a natural language question is preprocessed into a machine-understood query language. Loading a custom dictionary in the LAC word segmentation tool, and carrying out word segmentation processing and special name recognition on an input question; correcting the wrong special name by a Jaro-Winkler Distance algorithm based on the dictionary; finally, performing word removal and stopping operation on the word sequence after word segmentation to generate a characteristic word sequence, wherein the step of performing part-of-speech analysis on the keywords in the natural sentence question specifically comprises the following steps: and matching the characteristic word sequence generated by question preprocessing with a custom part-of-speech dictionary library to generate a first-level part-of-speech combination sequence and a second-level part-of-speech combination sequence corresponding to the characteristic word. Determining query modes by the first-level part-of-speech combination sequence, and dividing the query modes into a map query mode and an API query mode; the method comprises the steps of directly matching the pattern query types according to the first-level part-of-speech combination results of the feature words, further matching the second-level part-of-speech combination sequences of the feature words with a mode-API type table, determining specific APIs to complete matching of question query templates, and dividing the pattern query modes into three query types, namely entity node query, node attribute query and node relation query, respectively corresponding to different Cypher query statement templates, filling the feature word sequences into corresponding positions to generate specific Cypher query statements, and executing the retrieval of answers from a water conservancy knowledge pattern in Neo4 j. For an API call mode, firstly acquiring an API address of a specific API corresponding to question inquiry; then, according to the built standardized conversion function library of the input conditions, converting the feature words into the input conditions required by API inquiry; and then requesting an address to call an API by using a spelling API, acquiring dynamic data in real time, finally writing an answer description function to process answers of different search models, matching with the answer description function to establish an automatic answer text generation scheme, returning a text answer with clear semantics and condensed content to a user, and finally displaying the text answer on an interface.
In a further implementation manner of this embodiment, the reservoir map unit 40 further includes a map retrieval module, where the map retrieval module is configured to display the reservoir knowledge map on a set interface according to a preset mode.
Referring to fig. 5 and 6, in a further implementation manner of the present embodiment, the knowledge base unit 10 specifically includes: a forecast scheduling scheme library, a business rule library, an expert experience library, a historical scene library, an engineering safety knowledge library and a shared knowledge library.
In a further implementation manner of this embodiment, the service rule base includes a reservoir dispatching operation rule, a reservoir waterproof early warning rule, an electromechanical device operation rule, a reservoir safety emergency operation rule, an emergency grading rule and a standard specification, the historical scene base includes at least a historical flood knowledge base, and the engineering safety knowledge base includes an engineering history leather, a technical file base and an engineering case base.
In the embodiment, various unstructured information is managed and integrated, a forecast scheduling scheme library, a business rule library, a historical scene library, an expert experience library, a hydraulic engineering safety knowledge library and a shared knowledge library are constructed, a data kernel is provided for intelligent question and answer of reservoir knowledge, and knowledge support is provided for intellectualization and precision of flood prevention decisions.
Referring to fig. 3, in a further implementation manner of this embodiment, the map searching module specifically includes a tag searching module 401 and an entity searching module 402, referring to fig. 9, the tag searching module 401 is configured to display a reservoir knowledge map formed by all entities under a certain concept level on a set interface, referring to fig. 10, and the entity searching module 402 is configured to highlight a reservoir knowledge map formed by a certain specific entity on the set interface.
Specifically, the reservoir map unit 40 in this embodiment utilizes a dynamic and static fusion technology of knowledge map data to aggregate various common important data, specifically, (1) the construction of a conceptual model structure of the reservoir knowledge map is completed by means of a Neo4j platform, wherein entity attribute information is stored through nodes, and the relationship between the nodes is represented through directed edges; and analyzing the relationship among the water conservancy object concepts and designing the relationship based on the constructed water conservancy object relationship table. Thereby forming a reservoir knowledge graph concept model, namely a concept layer. The method comprises the steps of (2) carrying out the hooking of an entity layer and a concept layer, namely writing SQL sentences to convert a water conservancy object entity information table and an entity object relation table constructed in a MySql database into CSV files, and importing the CSV files into a map database Neo4 j; and constructing a dynamic and static combined hydraulic engineering knowledge graph by utilizing a hydraulic engineering knowledge graph data dynamic fusion technology.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present invention, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. Reservoir knowledge intelligent question-answering system based on flood prevention demand, which is characterized by comprising:
the knowledge base unit at least comprises reservoir knowledge in various flood prevention aspects;
the intelligent question-answering unit can obtain answers of natural sentence questions based on the natural sentence questions in the aspect of flood prevention;
the display unit is used for displaying reservoir knowledge in terms of flood prevention on a set interface, and is also used for displaying answers of question phases of the natural sentences on the set interface.
2. The intelligent question-answering system for reservoir knowledge based on flood control demands according to claim 1, wherein the intelligent question-answering system for reservoir knowledge further comprises a reservoir map unit, the reservoir map unit at least comprises a plurality of reservoir entities and information related to the reservoir entities to form a multidimensional reservoir knowledge map, and the display unit is further used for displaying the multidimensional reservoir knowledge map.
3. The reservoir knowledge intelligent question-answering system based on flood control requirements according to claim 2, wherein the intelligent question-answering unit comprises an input module, a processing module, a query matching module and an answer processing module, wherein the input module is used for inputting natural sentence questions in flood control, the processing module is used for carrying out question processing on the input natural sentence questions to obtain key information in the natural sentence questions, the query matching module is used for obtaining nodes corresponding to the key information in the natural sentence questions from the reservoir map unit based on the key information in the natural sentence questions, and the answer processing module is used for processing the information of the nodes and generating answers to be displayed.
4. The flood control demand based reservoir knowledge intelligent question-answering system according to claim 3, wherein the query matching module is further configured to determine a search pattern based on key information in the natural sentence question, and select whether to search in the reservoir atlas unit based on the search pattern.
5. The intelligent reservoir knowledge question-answering system based on flood control requirements according to claim 4, wherein the search mode specifically comprises a first search mode and a second search mode, the query matching module is further configured to determine a search mode based on key information in the natural sentence question, and select whether to search in the reservoir map unit based on the search mode specifically comprises: the query matching module is further used for judging whether to enter a first retrieval mode or a second retrieval mode based on the key information in the natural sentence question, searching is carried out in the reservoir map unit when judging that the first retrieval mode is entered so as to obtain nodes corresponding to the key information in the natural sentence question, the second retrieval mode is an API calling mode, the network is connected through an API interface when judging that the second retrieval mode is entered, the query matching module is further used for obtaining real-time dynamic information corresponding to the key information in the natural sentence question from the network knowledge base based on the key information in the natural sentence question, and the answer processing unit is correspondingly used for processing the real-time dynamic information and generating an answer to be displayed.
6. The intelligent reservoir knowledge question-answering system based on flood prevention requirements according to claim 3, wherein the question processing the input natural sentence question to obtain key information in the natural sentence question specifically comprises: firstly, preprocessing the input natural sentence question to extract keywords in the natural sentence question, and performing part-of-speech analysis on the keywords in the natural sentence question.
7. The intelligent reservoir knowledge question-answering system based on flood control requirements according to claim 2, wherein the reservoir map unit further comprises a map retrieval module for displaying a reservoir knowledge map on a set interface according to a preset mode.
8. The intelligent reservoir knowledge question-answering system based on flood control demands according to claim 1, wherein the knowledge base unit specifically comprises: a forecast scheduling scheme library, a business rule library, an expert experience library, a historical scene library, an engineering safety knowledge library and a shared knowledge library.
9. The flood control demand based reservoir knowledge intelligent question-answering system according to claim 8, wherein the business rule base comprises reservoir scheduling operation rules, reservoir waterproof early warning rules, electromechanical equipment operation rules, reservoir safety emergency operation rules, emergency class classification rules and standard specifications, the historical scene base at least comprises a historical flood knowledge base, and the engineering safety knowledge base comprises engineering histories, technical file bases and engineering case bases.
10. The intelligent reservoir knowledge question-answering system based on flood control requirements according to claim 2, wherein the map retrieval module specifically comprises a tag retrieval module and an entity retrieval module, the tag retrieval module is used for displaying reservoir knowledge maps formed by all entities under a certain concept level on a set interface, and the entity retrieval module is used for highlighting reservoir knowledge maps formed by a certain specific entity on the set interface.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311193081.7A CN117235219A (en) | 2023-09-15 | 2023-09-15 | Reservoir knowledge intelligent question-answering system based on flood prevention demands |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311193081.7A CN117235219A (en) | 2023-09-15 | 2023-09-15 | Reservoir knowledge intelligent question-answering system based on flood prevention demands |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117235219A true CN117235219A (en) | 2023-12-15 |
Family
ID=89083790
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311193081.7A Pending CN117235219A (en) | 2023-09-15 | 2023-09-15 | Reservoir knowledge intelligent question-answering system based on flood prevention demands |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117235219A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117668204A (en) * | 2024-01-31 | 2024-03-08 | 暗物智能科技(广州)有限公司 | Intelligent question-answering system, method, equipment and medium of emergency management platform |
| CN117668204B (en) * | 2024-01-31 | 2024-06-11 | 暗物智能科技(广州)有限公司 | Intelligent question-answering system, method, equipment and medium of emergency management platform |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112765322A (en) * | 2021-01-25 | 2021-05-07 | 河海大学 | Remote sensing image search recommendation method based on water conservancy domain knowledge graph |
| CN113190663A (en) * | 2021-04-22 | 2021-07-30 | 宁波弘泰水利信息科技有限公司 | Intelligent interaction method and device applied to water conservancy scene, storage medium and computer equipment |
| CN114780742A (en) * | 2022-04-19 | 2022-07-22 | 中国水利水电科学研究院 | Construction and use method of flow scheduling knowledge-graph question-answering system of irrigation area |
-
2023
- 2023-09-15 CN CN202311193081.7A patent/CN117235219A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112765322A (en) * | 2021-01-25 | 2021-05-07 | 河海大学 | Remote sensing image search recommendation method based on water conservancy domain knowledge graph |
| CN113190663A (en) * | 2021-04-22 | 2021-07-30 | 宁波弘泰水利信息科技有限公司 | Intelligent interaction method and device applied to water conservancy scene, storage medium and computer equipment |
| CN114780742A (en) * | 2022-04-19 | 2022-07-22 | 中国水利水电科学研究院 | Construction and use method of flow scheduling knowledge-graph question-answering system of irrigation area |
Non-Patent Citations (1)
| Title |
|---|
| 张紫璇;陆佳民;姜笑;冯钧;: "面向水利信息资源的智能问答系统构建与应用", 计算机与现代化, no. 03, 15 March 2020 (2020-03-15), pages 65 - 71 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117668204A (en) * | 2024-01-31 | 2024-03-08 | 暗物智能科技(广州)有限公司 | Intelligent question-answering system, method, equipment and medium of emergency management platform |
| CN117668204B (en) * | 2024-01-31 | 2024-06-11 | 暗物智能科技(广州)有限公司 | Intelligent question-answering system, method, equipment and medium of emergency management platform |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101799835B (en) | Ontology-driven geographic information retrieval system and method | |
| CN109657074B (en) | News knowledge graph construction method based on address tree | |
| CN110188979A (en) | Water industry Emergency decision generation method and device | |
| CN112347222A (en) | Method and system for converting non-standard address into standard address based on knowledge base reasoning | |
| CN113392986A (en) | Highway bridge information extraction method based on big data and management maintenance system | |
| CN113377966B (en) | Water conservancy project scheduling regulation reasoning method based on knowledge graph | |
| CN112765300B (en) | Water conservancy object relation map construction method based on ArcGIS spatial data | |
| CN116010612A (en) | River basin flood control knowledge graph construction method and device and electronic equipment | |
| CN115525766A (en) | Method and device for constructing knowledge graph of polluted site | |
| CN111475604A (en) | Data processing method and device | |
| CN117763155A (en) | Knowledge graph construction method and related equipment for multi-source heterogeneous data of power distribution network planning | |
| CN116701648A (en) | Mapping knowledge graph and schema design method based on standard specification | |
| CN114510583B (en) | Flood control dispatching knowledge graph construction method | |
| CN111784192A (en) | Industrial park emergency plan executable system based on dynamic evolution | |
| CN117235219A (en) | Reservoir knowledge intelligent question-answering system based on flood prevention demands | |
| CN115952339A (en) | NGboost-based geographic space-time knowledge extraction and map representation method | |
| CN113360480B (en) | Earthquake prevention and control subject library construction method and system, electronic equipment and storage medium | |
| CN110348691A (en) | A kind of appraisal and spatial decision support system based on river ecological environment | |
| CN115495594A (en) | Knowledge graph fusion method and system based on urban public facility decision case | |
| CN113505233B (en) | Extraction method of ecological civilized geographic knowledge based on open domain | |
| CN106156181A (en) | A kind of another name acquisition methods and device | |
| Leung et al. | An environmental decision‐support system for the management of water pollution in a tidal river network | |
| Li et al. | A method of constructing geo-object ontology in disaster system for prevention and decrease | |
| Zhang et al. | Construction of geo-ontology knowledge base about spatial relations | |
| CN115269500B (en) | Ecological environment data storage method, ecological environment data retrieval method and electronic equipment |
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 |