阅读说明：本技术 电网调控运行知识库的构建方法及装置 (Method and device for constructing power grid regulation and control operation knowledge base ) 是由 张雨璇 李�杰 王海云 刘辉 陈茜 沙立成 张再驰 张印宝 杨莉萍 王永 汪伟 于 2021-09-07 设计创作，主要内容包括：本申请公开了一种电网调控运行知识库的构建方法及装置。其中,该方法包括：获取构建电网调控运行知识库所需的知识材料；确定知识材料的类型,其中,类型包括：问答形式、标题加描述形式以及纯文本形式；依据知识材料的类型确定将知识材料导入电网调控运行知识库的导入方式；按照导入方式将知识材料导入电网调控运行知识库。本申请解决了目前电力系统调控人员的工作效率较低的技术问题。(The application discloses a method and a device for constructing a power grid regulation and control operation knowledge base. Wherein, the method comprises the following steps: acquiring knowledge materials required for constructing a power grid regulation and control operation knowledge base; determining a type of knowledge material, wherein the type comprises: question-answer form, title plus description form and plain text form; determining an importing mode for importing the knowledge materials into a power grid regulation and control operation knowledge base according to the types of the knowledge materials; and importing the knowledge material into a power grid regulation and control operation knowledge base according to an importing mode. The technical problem that the work efficiency of the current power system regulating personnel is low is solved.)

1. A method for constructing a power grid regulation and control operation knowledge base is characterized by comprising the following steps:

acquiring knowledge materials required for constructing a power grid regulation and control operation knowledge base;

determining a type of the knowledge material, wherein the type comprises: question-answer form, title plus description form and plain text form;

determining an importing mode for importing the knowledge materials into the power grid regulation and control operation knowledge base according to the types of the knowledge materials;

and importing the knowledge material into the power grid regulation and control operation knowledge base according to the importing mode.

2. The method according to claim 1, wherein determining an importing manner for importing the knowledge material into the power grid regulation operation knowledge base according to the type of the knowledge material comprises:

and if the type of the knowledge material is in the question-answer form, taking the questions included in the knowledge material as basic questions of knowledge items led into the power grid regulation and control operation knowledge base, and taking the answers of the questions as answers of the knowledge items led into the power grid regulation and control operation knowledge base.

3. The method according to claim 1, wherein determining an importing manner for importing the knowledge material into the power grid regulation operation knowledge base according to the type of the knowledge material comprises:

and if the type of the knowledge material is in the form of the title plus description, converting the title included in the knowledge material into a basic question of a knowledge item imported into the power grid regulation and control operation knowledge base, and taking a description paragraph corresponding to the title as an answer of the knowledge item imported into the power grid regulation and control operation knowledge base.

4. The method of claim 2 or 3, wherein after determining the basic question of the knowledge item imported into the grid regulation operation knowledge base, the method further comprises:

and converting the basic questions into a plurality of extended questions by using a natural language understanding model, wherein the extended questions and the basic questions are different in description mode and identical in semantics.

5. The method according to claim 4, wherein determining an importing mode for importing the knowledge material into the power grid regulation operation knowledge base according to the type of the knowledge material comprises:

and if the type of the knowledge material is in the plain text form, counting the frequency of the occurrence of preset key words in the knowledge material, and taking the frequency, the number of sentences in the knowledge material and the text information included in the knowledge material as a knowledge item imported into the power grid regulation and control operation knowledge base.

6. The method of claim 5, wherein prior to counting the frequency of occurrence of a predetermined keyword in the knowledge material, the method further comprises:

dividing all the knowledge materials according to natural segments;

analyzing each natural segment by using a word segmentation tool, and extracting a plurality of key words from each natural segment;

the TF-IDF value of each key word is calculated according to the following formula:

and taking the key words with the TF-IDF numerical values higher than a first preset threshold value as the preset key words.

7. The method of claim 5, wherein after importing the knowledge material into the grid regulation operation knowledge base according to the importing manner, the method further comprises:

acquiring a retrieval instruction for searching knowledge items from the power grid regulation and control operation knowledge base;

and searching the expansion question corresponding to the retrieval instruction from the power grid regulation and control operation knowledge base, and returning an answer corresponding to the expansion question.

8. The method according to claim 7, wherein if the matching degree of the returned answer and the retrieval instruction is lower than a second preset threshold value, the preset keyword corresponding to the retrieval instruction is searched from the power grid regulation and control operation knowledge base, and the knowledge item where the preset keyword is located is returned.

9. The utility model provides a device for constructing power grid regulation and control operation knowledge base which characterized in that includes:

the acquisition module is used for acquiring knowledge materials required by constructing a power grid regulation and control operation knowledge base;

a first determining module for determining a type of the knowledge material, wherein the type comprises: question-answer form, title plus description form and plain text form;

the second determination module is used for determining an importing mode of importing the knowledge material into the power grid regulation and control operation knowledge base according to the type of the knowledge material;

and the import module is used for importing the knowledge material into the power grid regulation and control operation knowledge base according to the import mode.

10. A non-volatile storage medium, characterized in that the non-volatile storage medium includes a stored program, and when the program runs, a device where the non-volatile storage medium is located is controlled to execute the method for constructing the power grid regulation and operation knowledge base according to any one of claims 1 to 8.

Technical Field

The application relates to the field of power grid dispatching operation, in particular to a method and a device for constructing a power grid regulation and control operation knowledge base.

Background

The power system regulation and control personnel are important factors for ensuring the stable operation of the power grid, the post has extremely high requirements on the personnel, and the working strength is also high. On one hand, knowledge and skills in the aspect of power regulation are different day by day, and a regulation and control person needs to quickly acquire and master a large amount of relevant knowledge of a power system due to the particularity of the post and the urgency of working properties, while the existing regulation and control application system does not completely have relevant capacity, and the channel for the regulation and control person to acquire the knowledge is relatively narrow and not standard; on the other hand, the regulating personnel needs to quickly, comprehensively and accurately master the current operating state of the power grid and simultaneously needs to compare with the operating state which appears historically, namely, the regulating personnel needs to search and analyze a large amount of information, and the regulating personnel only depends on manpower, thus wasting time and labor and having low efficiency.

The contradiction between increasingly heavy daily work of regulators and the maintenance of safe and stable operation and correct control and regulation of the power grid is more and more prominent, if the intentions of the regulators can be mastered by analyzing the voice input of the regulators, relevant information can be automatically retrieved and corresponding feedback can be given, the working quality and efficiency of the regulators can be greatly improved, and therefore, the research on the intelligent question-answering technology for regulating and controlling the power grid is very necessary.

Aiming at the problem that the work efficiency of the current power system regulating personnel is low, an effective solution is not provided at present.

Disclosure of Invention

The embodiment of the application provides a method and a device for constructing a power grid regulation and control operation knowledge base, and the method and the device are used for at least solving the technical problem that the work efficiency of the current power system regulation and control personnel is low.

According to an aspect of an embodiment of the present application, a method for constructing a power grid regulation and control operation knowledge base is provided, including: acquiring knowledge materials required for constructing a power grid regulation and control operation knowledge base; determining a type of knowledge material, wherein the type comprises: question-answer form, title plus description form and plain text form; determining an importing mode for importing the knowledge materials into a power grid regulation and control operation knowledge base according to the types of the knowledge materials; and importing the knowledge material into a power grid regulation and control operation knowledge base according to an importing mode.

Optionally, determining an importing mode of importing the knowledge material into the power grid regulation and control operation knowledge base according to the type of the knowledge material, including: and if the type of the knowledge material is in a question-answer form, taking the questions included in the knowledge material as basic questions of knowledge items led into the power grid regulation and control operation knowledge base, and taking answers of the questions as answers of the knowledge items led into the power grid regulation and control operation knowledge base.

Optionally, determining an importing mode of importing the knowledge material into the power grid regulation and control operation knowledge base according to the type of the knowledge material, including: and if the type of the knowledge material is in a title plus description form, converting the titles comprising the knowledge material into basic questions of the knowledge items imported into the power grid regulation and control operation knowledge base, and taking description paragraphs corresponding to the titles as answers of the knowledge items imported into the power grid regulation and control operation knowledge base.

Optionally, after determining a basic question of a knowledge item imported into the power grid regulation and control operation knowledge base, the method further includes: and converting the basic questions into a plurality of extended questions by using the natural language understanding model, wherein the extended questions and the basic questions are different in description mode and identical in semantics.

Optionally, determining an importing mode of importing the knowledge material into the power grid regulation and control operation knowledge base according to the type of the knowledge material, including: and if the type of the knowledge material is in a plain text form, counting the frequency of the preset key words in the knowledge material, and taking the frequency, the number of sentences in the knowledge material and the text information included in the knowledge material as a knowledge item led into a power grid regulation and control operation knowledge base.

Optionally, before counting the frequency of the preset keyword appearing in the knowledge material, the method further includes: dividing all knowledge materials according to natural segments; analyzing each natural segment by using a word segmentation tool, and extracting a plurality of key words from each natural segment; the TF-IDF value of each key word is calculated according to the following formula:

and taking the key words with the TF-IDF numerical value higher than the first preset threshold value as preset key words.

Optionally, after the knowledge material is imported into the power grid regulation and control operation knowledge base according to an import mode, the method further includes: acquiring a retrieval instruction for searching knowledge items from a power grid regulation and control operation knowledge base; and searching an expansion question corresponding to the retrieval instruction from the power grid regulation and control operation knowledge base, and returning an answer corresponding to the expansion question.

Optionally, if the matching degree of the returned answer and the retrieval instruction is lower than a second preset threshold, searching a preset keyword corresponding to the retrieval instruction from the power grid regulation and control operation knowledge base, and returning a knowledge item where the preset keyword is located.

According to another aspect of the embodiments of the present application, there is also provided a device for constructing a power grid regulation and control operation knowledge base, including: the acquisition module is used for acquiring knowledge materials required by constructing a power grid regulation and control operation knowledge base; a first determining module for determining a type of knowledge material, wherein the type comprises: question-answer form, title plus description form and plain text form; the second determination module is used for determining an importing mode of importing the knowledge materials into the power grid regulation and control operation knowledge base according to the types of the knowledge materials; and the import module is used for importing the knowledge materials into the power grid regulation and control operation knowledge base according to an import mode.

According to another aspect of the embodiments of the present application, a non-volatile storage medium is further provided, where the non-volatile storage medium includes a stored program, and when the program runs, the device where the non-volatile storage medium is located is controlled to execute the above method for building the power grid regulation and control operation knowledge base.

According to still another aspect of the embodiments of the present application, there is provided a processor, where the processor is configured to run a program stored in a memory, and the program performs the above method for constructing a power grid regulation operation knowledge base when running.

In the embodiment of the application, knowledge materials required for constructing a power grid regulation and control operation knowledge base are obtained; determining a type of knowledge material, wherein the type comprises: question-answer form, title plus description form and plain text form; determining an importing mode for importing the knowledge materials into a power grid regulation and control operation knowledge base according to the types of the knowledge materials; according to the method for importing the knowledge materials into the power grid regulation and control operation knowledge base, the power grid regulation and control operation knowledge base is constructed by providing basic forms of two kinds of power grid regulation and control knowledge, such as question and answer items, knowledge texts and the like, and adopting three knowledge importing modes, such as direct importing, title transfer problem, keyword retrieval and the like, in the face of different types of power grid knowledge text materials, so that the technical effects of rapidly collecting and displaying information required by power grid regulation and control personnel, replacing manual work for information retrieval, assisting power grid regulation and control operation, improving the working efficiency of the regulation and control personnel are achieved, and the technical problem that the working efficiency of the existing power system regulation and control personnel is low is solved.

Drawings

The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:

fig. 1 is a flowchart of a method for constructing a power grid regulation operation knowledge base according to an embodiment of the present application;

FIG. 2 is a schematic diagram of a knowledge item in the form of a question and answer in accordance with an embodiment of the present application;

fig. 3 is a schematic diagram of a construction method and an application method of a power grid regulation and control operation knowledge base according to an embodiment of the application;

fig. 4 is a structural block diagram of a device for constructing a power grid regulation and control operation knowledge base according to an embodiment of the present application.

Detailed Description

In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only partial embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

According to an embodiment of the present application, there is provided an embodiment of a method for constructing a power grid regulation operation knowledge base, where it is to be noted that the steps shown in the flowchart of the drawings may be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in an order different from the order shown.

Fig. 1 is a flowchart of a method for constructing a power grid regulation and control operation knowledge base according to an embodiment of the present application, and as shown in fig. 1, the method includes the following steps:

step S102, acquiring knowledge materials required for constructing a power grid regulation and control operation knowledge base;

the most important daily work of power grid regulation and control personnel is to perform the next regulation and control operation on the power grid according to the current state or the occurrence event of the power grid and regulation and control management regulations. The power grid regulation knowledge base mainly aims to solve the problem of quick retrieval of regulation basis, comprises regulation management regulations, basic knowledge of a power system and the like, and is derived from existing word materials of a dispatching center.

Knowledge materials of the power grid regulation knowledge base can be divided into two types according to the storage form:

1) the knowledge items in the form of question and answer are the content needed by the regulatory personnel once the information is hit, the matching degree is high, but the materials suitable for the information are generally few, and the manual entry is too labor-consuming. The problems of the knowledge items are text information, the text information comprises a basic problem and a plurality of expansion problems, and the expansion problems mainly serve to provide a plurality of dialect expression modes of the problems and improve the hit rate of the problems; the answers of the knowledge items can be in the forms of texts, tables, pictures and the like, and the texts can also comprise broadcast texts and display texts which respectively give brief and detailed descriptions so as to facilitate the user to extract effective information in the texts. FIG. 2 is a schematic diagram of a knowledge item in the form of a question and answer in accordance with an embodiment of the application.

2) Knowledge items in text form have wide sources and large amount of materials, can cover all links of regulation and control operation, and can achieve better application effect only by matching with the intention of regulation and control personnel.

Since such knowledge items are mainly searched by means of keywords, the knowledge base mainly includes 3 components such as numbers, keyword frequencies, and knowledge texts.

Step S104, determining the type of the knowledge material, wherein the type comprises: question-answer form, title plus description form and plain text form;

step S106, determining an importing mode for importing the knowledge materials into a power grid regulation and control operation knowledge base according to the types of the knowledge materials;

the power grid knowledge materials are very many, if the materials are input by a manual mode, the workload is very large and is difficult to complete, and the materials with different characteristics and different forms must be automatically introduced by a program. Meanwhile, the knowledge base is formed in a form and has characteristics that all knowledge should be stored in a question-answer form as much as possible. The knowledge material in the field of existing power grid regulation and control mainly takes character information as a main body, and specifically comprises three forms, and the embodiment provided by the application adopts different modes for leading in.

And step S108, importing the knowledge materials into a power grid regulation and control operation knowledge base according to an importing mode.

Through the steps, the power grid regulation and control operation knowledge base is constructed by providing basic forms of two power grid regulation and control knowledge such as question and answer items and knowledge texts and adopting three knowledge import modes such as direct import, title transfer problem and keyword retrieval in the face of different types of power grid knowledge text materials, so that the technical effects of quickly collecting and displaying information required by power grid regulation and control personnel, replacing manual work for information retrieval, assisting power grid regulation and control operation and improving the work efficiency of the regulation and control personnel are achieved.

According to an alternative embodiment of the present application, step S106 may be implemented by: and if the type of the knowledge material is in a question-answer form, taking the questions included in the knowledge material as basic questions of knowledge items led into the power grid regulation and control operation knowledge base, and taking answers of the questions as answers of the knowledge items led into the power grid regulation and control operation knowledge base.

Knowledge material is in the form of questions and answers, typically containing 1 question and 1 answer, where the questions are in the form of text. The embodiment provided by the application leads the questions into basic questions as knowledge items and leads the answers into the answers as knowledge items; meanwhile, a natural language understanding model (NLU) is adopted to automatically convert the basic questions into 5 expansion questions with similar meanings, and in addition, the user is allowed to manually expand or modify.

According to another alternative embodiment of the present application, step S106 may be implemented by: and if the type of the knowledge material is in a title plus description form, converting the titles comprising the knowledge material into basic questions of the knowledge items imported into the power grid regulation and control operation knowledge base, and taking description paragraphs corresponding to the titles as answers of the knowledge items imported into the power grid regulation and control operation knowledge base.

The knowledge material is in a form of adding description to a title, and comprises 1 title and 1 segment of text description, the knowledge material is commonly found in documents such as a power grid regulation and control management rule, a power grid dispatching and operation stability regulation rule and the like, the title of the knowledge material has definite significance, and the knowledge material is convenient to convert into a problem form through an NLU (line language unit) model, such as what is a power grid fault and exception handling principle, which can be converted into a power grid fault and exception handling principle in the following examples? ". The embodiment provided by the application can automatically read the materials, convert the title into the question and serve as the basic question of the knowledge item, and take the corresponding description paragraph as the answer of the knowledge item, and simultaneously perform the question expansion.

Examples of knowledge material in title plus description form:

11.1 principles of grid Fault and Exception handling

11.1.1 the on-duty dispatcher is a director for processing the grid faults and abnormalities and is responsible for the correctness of the processing.

11.1.2 when dealing with failure, the main task of the on-duty controller is to make correct judgment to the failure condition, limit the failure development, remove the root cause of the failure, and remove the threat to the personal and equipment safety.

In some optional embodiments of the present application, after determining a basic question of a knowledge item imported into a power grid regulation and control operation knowledge base, the basic question is converted into a plurality of extended questions by using a natural language understanding model, wherein the extended questions are different from the basic question in description mode and have the same semantics.

It was mentioned above that the natural language understanding model (NLU) is used to automatically convert the basic questions into 5 (or other numbers of) extended questions with similar meanings. By the method, the accuracy rate of subsequently retrieving the related knowledge items from the power grid control operation knowledge base can be improved.

In the embodiments provided in the present application, automatic question Generation is required in the steps of performing the title translation question, the basic question translation extension question, and the like, and mainly relates to key technologies such as Natural Language Understanding (NLU) and automatic Language Generation (NLG).

Natural language understanding means that the user's dialog intention and the information delivered are obtained from the user input (the user actively asks or answers). The method adopts an algorithm based on deep learning to finish vectorization representation of the title or the basic question, namely each text (user question or knowledge similarity question and the like) is converted into a vector with the same dimension by a model (coding process). These vectors have the characteristic that the semantic proximity problem, and the vector distances will also be close. Therefore, in the calculation, the semantic similarity is represented by the similarity (cosine distance) of the vectors.

The natural language generation is a process of automatically generating a corresponding text according to the selected action and the context information. Firstly, constructing and training a decoding model corresponding to the coding model in the last step; then, on the basis of vector representation of the problem, carrying out random fine adjustment on the vector to generate a new representation vector as the input of a decoding model; and finally, automatically generating a new extension question through a decoding model. The process of generating the question in this step can be completed automatically, but in order to improve the effectiveness of the generated text, the generated text can be further screened or modified manually.

In other alternative embodiments of the present application, step S106 can also be implemented by the following method: and if the type of the knowledge material is in a plain text form, counting the frequency of the preset key words in the knowledge material, and taking the frequency, the number of sentences in the knowledge material and the text information included in the knowledge material as a knowledge item led into a power grid regulation and control operation knowledge base.

The knowledge material is in a simple text form, and in the importing process of the knowledge material, word frequency statistics needs to be carried out according to keywords defined in advance, and then automatically generated numbers, word frequency statistics and text information are imported into a power grid regulation knowledge base as a knowledge item.

According to an alternative embodiment of the present application, before counting the frequency of the preset keyword, the preset keyword is determined by the following method: dividing all knowledge materials according to natural segments; analyzing each natural segment by using a word segmentation tool, and extracting a plurality of key words from each natural segment; the TF-IDF value of each key word is calculated according to the following formula:

and taking the key words with the TF-IDF numerical value higher than the first preset threshold value as preset key words.

For a simple text material, the frequency of occurrence of the keywords in each paragraph can be counted, and then the paragraphs with high degree of fitting (high keyword frequency) are selected for pushing. The keywords include important power grid equipment, plant names and manually specified keywords, and also include common words in power grid regulation knowledge materials. The selection of the common words can be completed through the following steps:

A. dividing and storing all the character materials according to the natural segments, wherein each natural segment is used as an input document;

B. analyzing all text materials by adopting a word segmentation tool, and removing meaningless words in the text materials;

C. performing word frequency statistics by adopting a TF-IDF algorithm:

and taking the words with higher numerical values of the TF-IDF as key words, storing the key words into a knowledge base, and carrying out word frequency statistics and recording on the existing text material according to the new key words.

TF-IDF (term frequency-inverse document frequency) is a weighting technique for information retrieval and data mining, TF is the word frequency and IDF is the inverse text frequency index.

In another optional embodiment of the present application, after the step S108 is completed, a retrieval instruction for searching a knowledge item from a power grid regulation and control operation knowledge base is obtained; and searching an expansion question corresponding to the retrieval instruction from the power grid regulation and control operation knowledge base, and returning an answer corresponding to the expansion question.

According to an optional embodiment of the application, if the matching degree of the returned answer and the retrieval instruction is lower than a second preset threshold value, a preset keyword corresponding to the retrieval instruction is searched from the power grid regulation and control operation knowledge base, and a knowledge item where the preset keyword is located is returned.

The search command may be a text command or a voice command.

Fig. 3 is a schematic diagram of a method for constructing and applying a power grid regulation operation knowledge base according to an embodiment of the present application, and as shown in fig. 3, 2000 QA knowledge entries related to power grid services have been completed in a current system, where 1900 are derived from question and answer entries, and 100 are derived from title to question; 200 keywords are defined in advance, and about 300 sections of character entries are extracted from various power grid text data to jointly form a power grid regulation knowledge base.

And when the problem matching degree meets a threshold value, returning and broadcasting, otherwise, continuing to perform keyword matching. The two-stage searching method can improve the hit rate and avoid the mismatch condition.

The method provided by the application constructs a knowledge base for regulating and controlling the operation of the power grid, and the knowledge base comprises question and answer items and text items; aiming at different forms of power grid knowledge materials, three importing methods such as direct importing, title to problem and keyword indexing are provided; in practical application, a problem matching and keyword matching two-stage searching method is adopted, and the effectiveness of knowledge hit is improved. Through the knowledge base established by the method, the retrieval of the power grid regulation knowledge taking characters as input can be conveniently completed, the retrieval is in butt joint with functional modules such as voice recognition and the like in the future, and the functions of efficient and convenient power grid regulation knowledge question answering and the like are realized.

Fig. 4 is a block diagram of a structure of a device for constructing a power grid regulation operation knowledge base according to an embodiment of the present application, and as shown in fig. 4, the device includes:

the acquisition module 40 is used for acquiring knowledge materials required for constructing a power grid regulation and control operation knowledge base;

a first determining module 42, configured to determine a type of the knowledge material, wherein the type includes: question-answer form, title plus description form and plain text form;

the second determination module 44 is configured to determine an importing mode for importing the knowledge material into the power grid regulation and control operation knowledge base according to the type of the knowledge material;

and the importing module 46 is used for importing the knowledge materials into the power grid regulation and control operation knowledge base according to an importing mode.

It should be noted that, reference may be made to the description related to the embodiment shown in fig. 1 for a preferred implementation of the embodiment shown in fig. 4, and details are not described here again.

The embodiment of the application also provides a nonvolatile storage medium, wherein the nonvolatile storage medium comprises a stored program, and the device where the nonvolatile storage medium is located is controlled to execute the method for constructing the power grid regulation and control operation knowledge base during program operation.

The nonvolatile storage medium stores a program for executing the following functions: acquiring knowledge materials required for constructing a power grid regulation and control operation knowledge base; determining a type of knowledge material, wherein the type comprises: question-answer form, title plus description form and plain text form; determining an importing mode for importing the knowledge materials into a power grid regulation and control operation knowledge base according to the types of the knowledge materials; and importing the knowledge material into a power grid regulation and control operation knowledge base according to an importing mode.

The embodiment of the application also provides a processor, wherein the processor is used for operating the program stored in the memory, and the method for constructing the power grid regulation and operation knowledge base is executed when the program is operated.

The processor is used for running a program for executing the following functions: acquiring knowledge materials required for constructing a power grid regulation and control operation knowledge base; determining a type of knowledge material, wherein the type comprises: question-answer form, title plus description form and plain text form; determining an importing mode for importing the knowledge materials into a power grid regulation and control operation knowledge base according to the types of the knowledge materials; and importing the knowledge material into a power grid regulation and control operation knowledge base according to an importing mode.

The above-mentioned serial numbers of the embodiments of the present application are merely for description and do not represent the merits of the embodiments.

In the above embodiments of the present application, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.

In the embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units may be a logical division, and in actual implementation, there may be another division, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.

The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.

The foregoing is only a preferred embodiment of the present application and it should be noted that those skilled in the art can make several improvements and modifications without departing from the principle of the present application, and these improvements and modifications should also be considered as the protection scope of the present application.