Structured data intelligent query method and device
By constructing a dedicated word segmentation lexicon and a word order parsing rule base for power grids, the problems of inaccurate identification of indivisible terms and high word order flexibility in power grid data queries have been solved, thereby improving the accuracy and efficiency of power grid data queries.
Patent Information
- Application Number
- CN202511828411.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-05
- Publication Date
- 2026-03-13
AI Technical Summary
In power grid data queries, there are issues such as inaccurate identification of indivisible technical terms and high flexibility in sentence order, leading to query errors and redundant results.
We construct a dedicated word segmentation lexicon and word order parsing rule base for the power grid, identify and retain indivisible power grid professional terms, judge their rationality through a standard semantic framework, and reorder the word order to generate accurate query instructions when they do not conform to the standard semantic framework.
It improves the accuracy and efficiency of power grid data query, avoids query errors and redundant results, and enhances the accuracy of query results.
Smart Images
Figure CN121658620A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of power grid data processing and intelligent query technology, and in particular to a method and apparatus for intelligent querying structured data. Background Technology
[0002] In today's era of technological advancement and rapid digital development, enterprises are increasingly reliant on data, and the amount of data stored is growing exponentially. Related professionals often need to retrieve specific information from massive amounts of data.
[0003] However, when querying power grid data, due to the complexity of the data, which typically includes multiple terms such as equipment, parameters, conditions, and time, the following shortcomings may easily occur during the query:
[0004] 1. The power grid industry contains indivisible technical terms, such as SF6 circuit breaker and 10kV line. Commonly used word segmentation tools have difficulty accurately identifying and retaining such indivisible power grid technical terms, which leads to matching errors when querying. For example, the query may return all 10kV equipment or all circuit breakers, resulting in query errors.
[0005] 2. When matching words, the matching is usually performed according to the order of word appearance. However, the word order of power grid data is highly flexible. For example, the content expressed by a 10kV line exceeding 50MW is different from that of a 10kV line exceeding 50MW. If the matching is performed simply according to the order of word appearance, it is impossible to determine whether the parameter condition of exceeding 50MW is the same as that of a 10kV line. It is easy to separate the data information into queries such as "all equipment exceeding 50MW" and "10kV line", which will lead to errors in the query results and redundancy.
[0006] Therefore, designing a structured data intelligent query method and device that can solve the above-mentioned technical problems is a technical problem that needs to be solved. Summary of the Invention
[0007] To address the aforementioned problems, the present invention aims to provide a structured data intelligent query method and apparatus to achieve accurate semantic parsing of power grid data query statements and improve the accuracy of query results.
[0008] In a first aspect, the present invention provides a method for intelligent querying of structured data, characterized by comprising the following steps:
[0009] Step S1: Construct a dedicated word segmentation lexicon and a word order parsing rule base for the power grid;
[0010] Step S2: Combining the power grid-specific word segmentation lexicon and the word order parsing rule library, obtain the first query statement input by the user, identify and retain relevant information, wherein the relevant information is indivisible power grid professional terminology;
[0011] Step S3: Based on the relevant information representation results, determine whether they conform to the standard semantic framework; if they conform to the standard semantic framework, generate a structured query instruction by querying the fields in the power grid structured database, and generate the answer result for the corresponding question; if they do not conform to the standard semantic framework, re-segment and sort the relevant information using the word order parsing rule base.
[0012] Furthermore, the power grid-specific word segmentation lexicon includes equipment terms, parameter terms, condition terms, and time terms.
[0013] Furthermore, the word order parsing rule base includes a standard semantic framework and word order correction rules;
[0014] The standard semantic framework includes time, device subject, parameter type, and numerical conditions;
[0015] The word order correction rules include various word segmentation rules of the standard semantic framework. When the parameter type word is before the device subject word, the device subject word is moved before the parameter type word; when the time word is after the device subject word, the time word is moved before the device subject word.
[0016] Furthermore, in the power grid-specific word segmentation lexicon, equipment terms have a higher priority than parameter terms, and multi-character terms have a higher priority than single-character terms.
[0017] Secondly, the present invention provides a structured data intelligent query device, characterized in that it includes a database module, a word segmentation processing module, a word order parsing module, a query instruction generation module, and a query module;
[0018] The database module is used to construct a dedicated word segmentation lexicon and a word order parsing rule library for power grids;
[0019] The word segmentation module is used to obtain user input information, retain and split relevant information;
[0020] The word order parsing module is used to parse and determine whether the relevant information conforms to the standard semantic framework;
[0021] The query instruction generation module is used to generate structured query instructions by querying relevant information through fields in the power grid structured database.
[0022] The query module is used to generate answers to corresponding questions using structured query instructions.
[0023] The present invention has the following beneficial effects:
[0024] 1- This invention sets up a power grid-specific word segmentation lexicon that includes equipment terms, parameter terms, conditional terms, and time terms. Upon receiving the first query statement input by the user, the invention identifies and retains indivisible power grid professional terms based on the power grid-specific word segmentation lexicon. Equipment terms have a higher priority than parameter terms, and multi-character terms have a higher priority than single-character terms, thus avoiding the splitting of long terms into shorter terms and improving word segmentation accuracy. At the same time, the invention corrects disordered or incorrect word order according to the standard semantic framework through a word order parsing rule base, reducing semantic parsing bias and improving query accuracy and efficiency. Attached Figure Description
[0025] Figure 1 This is a schematic diagram of Embodiment 1 of the present invention;
[0026] Figure 2 This is a schematic diagram of Embodiment 2 of the present invention. Detailed Implementation
[0027] The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments:
[0028] Example 1
[0029] like Figure 1 As shown, a structured data intelligent query method is characterized by the following steps:
[0030] Step S1: Construct a dedicated word segmentation lexicon and a word order parsing rule base for the power grid;
[0031] Step S2: Combining the power grid-specific word segmentation lexicon and the word order parsing rule library, obtain the first query statement input by the user, identify and retain relevant information, wherein the relevant information is indivisible power grid professional terminology;
[0032] Step S3: Based on the relevant information representation results, determine whether they conform to the standard semantic framework. If they conform, generate a structured query instruction by querying the relevant information through fields in the power grid structured database, and generate the answer to the corresponding question. If they do not conform to the standard semantic framework, re-segment and sort the relevant information using the word order parsing rule base. For example, if the parameter conditions are over 50MW, the parameter type is load, the equipment is a 10kV line, and the time is the last 5 days, perform word order verification. If the current sequence does not conform to the standard semantic framework sequence (time, equipment, parameter type, and numerical conditions), re-segment and sort the relevant information using the word order parsing rule base to reorder the sequence: last 5 days, 10kV line, load, over 50MW, generating the semantic expression: "time is the last 5 days, equipment is a 10kV line, load > 50MW".
[0033] Furthermore, the power grid-specific word segmentation lexicon includes equipment terms, parameter terms, condition terms, and time terms. The equipment terms include 10kV lines, 220kV main transformers, SF6 circuit breakers, etc.; parameter terms include load, oil temperature, zero-sequence current, etc.; condition terms include exceeding, surpassing, below, ≥, etc.; and time terms include recent days, the past month, monthly, etc. Each term is indivisible (e.g., SF6 circuit breaker cannot be separated into SF6 and circuit breaker).
[0034] Furthermore, the word order parsing rule base includes a standard semantic framework and word order correction rules;
[0035] The standard semantic framework includes time, device subject, parameter type, and numerical conditions;
[0036] The word order correction rules include various word segmentation rules of the standard semantic framework. When the parameter type word is before the device subject word, the device subject word is moved before the parameter type word; when the time word is after the device subject word, the time word is moved before the device subject word.
[0037] Furthermore, in the power grid-specific word segmentation lexicon, equipment terms have a higher priority than parameter terms, and multi-character terms have a higher priority than single-character terms. For example, "10kV line" has a higher priority than "line," avoiding the splitting of long terms into shorter terms.
[0038] Example 2
[0039] See Figure 2 As shown, this embodiment provides a structured data intelligent query device, characterized in that it includes a database module, a word segmentation processing module, a word order parsing module, a query instruction generation module, and a query module;
[0040] The database module is used to construct a dedicated word segmentation lexicon and a word order parsing rule library for power grids;
[0041] The word segmentation module is used to obtain user input information, retain and split relevant information;
[0042] The word order parsing module is used to parse and determine whether the relevant information conforms to the standard semantic framework;
[0043] The query instruction generation module is used to generate structured query instructions by querying relevant information through fields in the power grid structured database.
[0044] The query module is used to generate answers to corresponding questions using structured query instructions.
[0045] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can 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, etc.) containing computer-usable program code.
[0046] This 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 block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can 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, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0047] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0048] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0049] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any other way. Any person skilled in the art may make changes or modifications to the above-disclosed technical content to create equivalent embodiments. However, any simple modifications, equivalent changes, and modifications made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the protection scope of the present invention.
Claims
1. A method for intelligent querying structured data, characterized in that, Includes the following steps: Step S1: Construct a dedicated word segmentation lexicon and a word order parsing rule base for the power grid; Step S2: Combining the power grid-specific word segmentation lexicon and the word order parsing rule library, obtain the first query statement input by the user, identify and retain relevant information, wherein the relevant information is indivisible power grid professional terminology; Step S3: Based on the relevant information representation results, determine whether they conform to the standard semantic framework; if they conform to the standard semantic framework, generate a structured query instruction by querying the fields in the power grid structured database, and generate the answer result for the corresponding question; if they do not conform to the standard semantic framework, re-segment and sort the relevant information using the word order parsing rule base.
2. The intelligent query method for structured data according to claim 1, characterized in that: The power grid-specific word segmentation lexicon includes equipment terms, parameter terms, condition terms, and time terms.
3. The intelligent query method for structured data according to claim 1, characterized in that: The word order parsing rule base includes a standard semantic framework and word order correction rules; The standard semantic framework includes time, device subject, parameter type, and numerical conditions; The word order correction rules include various word segmentation rules of the standard semantic framework. When the parameter type word is before the device subject word, the device subject word is moved before the parameter type word; when the time word is after the device subject word, the time word is moved before the device subject word.
4. The intelligent query method for structured data according to claim 2, characterized in that: In the power grid-specific word segmentation lexicon, equipment terms have a higher priority than parameter terms, and multi-character terms have a higher priority than single-character terms.
5. A structured data intelligent query device, characterized in that: It includes a database module, a word segmentation module, a word order parsing module, a query command generation module, and a query module; The database module is used to construct a dedicated word segmentation lexicon and a word order parsing rule library for power grids; The word segmentation module is used to obtain user input information, retain and split relevant information; The word order parsing module is used to parse and determine whether the relevant information conforms to the standard semantic framework; The query instruction generation module is used to generate structured query instructions by querying relevant information through fields in the power grid structured database. The query module is used to generate answers to corresponding questions using structured query instructions.