Power distribution network engineering technical review method, device, terminal and storage medium

Abstract

The present invention relates to the field of engineering technology information processing technology, and in particular to a power distribution network engineering technology review method, device, terminal and storage medium. The method of the present invention obtains the overview, discussion, multiple project indicators and multiple certification documents of the distribution network engineering project, and then obtains the review model, inputs the overview, multiple project indicators and multiple keywords into the review model, and obtains the total score, the discussion score and the multiple indicator scores. The method of the present invention reviews the power distribution network engineering technology through the review model verified by expert experience. The materials that need to be prepared are mostly digitized materials, which have a basis to rely on, and the review model is established based on expert experience. When applied to the computing terminal, the power distribution network project can be quickly reviewed and scored. The review process is fast, less materials need to be prepared, and the opinions of multiple experts can be balanced. Therefore, less human resources are consumed, and the review conclusion is more accurate and closer to reality, which is worth promoting.

Description

Technical Field

[0001] The present invention relates to the field of engineering technology information processing technology, and in particular to a power grid distribution network engineering technology review method, device, terminal and storage medium. Background Art

[0002] Distribution network planning is a complex system engineering with multiple objectives, full process and multiple dimensions. Therefore, the evaluation index system of distribution network planning is also a multi-level index system. Introducing technical review and evaluation methods in distribution network asset management, improving the necessary database, and establishing a technical index evaluation system for distribution networks can not only provide a basis for distribution network planning and maintenance, and provide important information for grid risk control and equipment management strategies, but also ensure the overall reliability of the power system, reduce operation and maintenance costs, and improve the return on investment, thus laying a solid foundation for the construction of smart grids.

[0003] In terms of technical review, a number of goals, indicators and parameters are usually introduced to evaluate the quality of design and construction of a power distribution network project based on these goals, indicators and parameters.

[0004] A commonly used review technology solution is that experts participate in the review, weight each data, and then summarize the opinions of experts to evaluate the design and construction quality of a power distribution network project. This review method is more professional and the conclusions drawn are very trustworthy. However, the expert review method has problems such as a lot of preparation materials, a large number of people to be convened, and a long review cycle, and the time, manpower and financial costs are high.

[0005] In addition, there are often differences of opinion among experts. For example, when it comes to data preferences, experts in various fields will give biased opinions. How to balance the opinions of all parties is also an issue that needs to be paid attention to during the review.

[0006] Based on this, it is necessary for technical personnel in this field to develop a new review and evaluation method to reduce the excessive consumption of manpower and time in the review process, and balance the opinions of experts from all aspects, so that the final review conclusion of the power grid distribution project is more accurate and closer to reality, so that the power grid distribution project can better serve the construction personnel, production and life, and the entire society. Summary of the invention

[0007] The embodiments of the present invention provide a method, device, terminal and storage medium for technical review of power distribution network engineering, which are used to solve the problem that technical review of power distribution network engineering in the prior art requires more human resources.

[0008] In a first aspect, an embodiment of the present invention provides a method for evaluating power distribution network engineering technology, including:

[0009] Obtaining an overview, a discussion, a plurality of project indicators, and a plurality of supporting documents of a distribution network project, wherein the supporting documents correspond to the project indicators;

[0010] Perform semantic analysis on the discussion and extract multiple keywords;

[0011] Acquire multiple review sub-models, input the overview, the multiple project indicators, and the multiple keywords into the multiple review sub-models, obtain a discussion score and multiple indicator scores, and determine a total score based on the discussion score and the multiple indicator scores, wherein the review sub-model is an artificial neural network model verified by expert experience, and each review sub-model scores one of the multiple project indicators or the multiple keywords;

[0012] If the total score is higher than a first threshold, the project indicators are verified based on the multiple certification documents.

[0013] In a possible implementation, the discussion is semantically analyzed to extract multiple keywords, including:

[0014] Acquire a semantic library, wherein the semantic library includes a plurality of entries;

[0015] The discussion is matched with each term in the semantic library, and if the matching degree reaches a threshold, the term is selected as the keyword.

[0016] In a possible implementation, the obtaining of multiple review sub-models includes:

[0017] Perform the following steps for each review sub-model:

[0018] Acquire multiple historical samples, wherein the historical samples include: project indicators of historical projects and historical scores corresponding to the project indicators of the historical projects, or the historical samples include: project indicators of historical projects, profiles related to the project indicators of the historical projects, and historical scores corresponding to the project indicators of the historical projects, or the historical samples include: multiple keywords of historical projects and historical scores corresponding to the multiple keywords of the historical projects, wherein the historical scores are obtained by review by an expert group;

[0019] Inputting the multiple historical samples into the review sub-model, and training the review sub-model until the deviation between the score output by the review sub-model and the historical score is less than a third threshold;

[0020] The parameters of the review sub-model are fixed, and the review sub-model is used as a review sub-model verified by expert experience.

[0021] In a possible implementation, inputting the multiple historical samples into the review sub-model and training the review sub-model until the deviation between the score output by the review sub-model and the historical score is less than a third threshold includes:

[0022] Divide multiple historical samples into training sets and validation sets;

[0023] Training steps:

[0024] Input each sample in the training set into the review sub-model until the deviation between the score output by the review sub-model and the score of the sample in the training set is less than a fourth threshold;

[0025] Verification steps:

[0026] Fix the parameters of the review sub-model, input each sample in the validation set into the review sub-model, and obtain the deviation between the score output by the review sub-model and the score of the sample in the validation set as the validation deviation;

[0027] If the verification deviation is less than the third threshold, the review sub-model is used as the review sub-model verified by expert experience;

[0028] If the verification deviation is greater than or equal to the third threshold, the parameters of the review sub-model are not fixed and the process returns to the training step.

[0029] In a possible implementation, the historical score is scored by each member of the expert group, including technical experts and actual users of the distribution network project, and is calculated according to a first formula, wherein:

[0030]

[0031] In the formula, Score is the historical score, S i is the score of the technical experts, S j is the score of the actual users of the distribution network engineering project, n is the number of technical experts participating in the scoring, m is the number of actual users of the distribution network engineering project participating in the scoring, and the number of actual users of the distribution network engineering project participating in the scoring is twice the number of technical experts participating in the scoring.

[0032] In a possible implementation, the verifying the project indicators according to the multiple certification documents includes:

[0033] Selecting an indicator to be verified from the multiple project indicators, wherein the indicator to be verified is a project indicator whose indicator score is higher than a second threshold;

[0034] Outputting the indicator to be verified and the certification document to be verified, wherein the certification document to be verified is a certification document corresponding to the indicator to be verified;

[0035] The correctness of the indicator to be verified is determined according to the certification document to be verified.

[0036] In one possible implementation, the ratio of the discussion score to the total score is less than 10%.

[0037] In a second aspect, an embodiment of the present invention provides a power distribution network engineering technology review device, including:

[0038] A project data acquisition module, used to acquire an overview, discussion, multiple project indicators and multiple certification documents of a distribution network project, wherein the certification documents correspond to the project indicators;

[0039] A semantic analysis module, used to perform semantic analysis on the discussion and extract multiple keywords;

[0040] A review module, used to obtain a plurality of review sub-models, input the overview, the plurality of project indicators and the plurality of keywords into the plurality of review sub-models, obtain a discussion score and a plurality of indicator scores, and determine a total score according to the discussion score and the plurality of indicator scores, wherein the review sub-model is an artificial neural network model verified by expert experience, and each review sub-model scores one of the plurality of project indicators or the plurality of keywords; and

[0041] A verification module is used to verify the project indicators according to the multiple certification documents if the total score is higher than a first threshold.

[0042] In a third aspect, an embodiment of the present invention provides a terminal, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the method described in the first aspect or any possible implementation of the first aspect are implemented.

[0043] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method described in the first aspect or any possible implementation of the first aspect are implemented.

[0044] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0045] The embodiment of the present invention discloses a method for reviewing the technology of power distribution network engineering. The method obtains the overview, discussion, multiple project indicators and multiple certification documents of the distribution network engineering project, performs semantic analysis on the discussion, extracts multiple keywords, and then obtains multiple review sub-models, inputs the overview, the multiple project indicators and the multiple keywords into the multiple review sub-models, obtains the discussion score and the multiple indicator scores, and determines the total score according to the discussion score and the multiple indicator scores, wherein the review sub-model is an artificial neural network model verified by expert experience, and each review sub-model scores one of the multiple project indicators or the multiple keywords. The method of the present invention reviews the power distribution network engineering technology through the review model verified by expert experience, and the materials that need to be prepared are mostly digitized materials, which have a basis to rely on, and the review model is established based on expert experience. When applied to the computing terminal, the power distribution network engineering can be quickly reviewed and scored, the review process is fast, less materials need to be prepared, and the opinions of multiple experts can be balanced. Therefore, less human resources are consumed, and the review conclusion is more accurate and closer to reality, which is worth promoting. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0047] Figure 1 It is a flow chart of a power distribution network engineering technology review method provided by an embodiment of the present invention;

[0048] Figure 2 is a topological diagram of an artificial neural network model provided by an embodiment of the present invention;

[0049] Figure 3 It is a functional block diagram of a power grid distribution engineering technology review device provided by an embodiment of the present invention;

[0050] Figure 4 It is a functional block diagram of a terminal provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0051] In the following description, specific details such as specific system structures and technologies are provided for the purpose of illustration rather than limitation so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, and methods are omitted so as not to obscure the description of the present invention with unnecessary details.

[0052] In order to make the purpose, technical solutions and advantages of the present invention more clear, a specific implementation method will be described below in conjunction with the accompanying drawings.

[0053] The following is a detailed description of an embodiment of the present invention. This example is implemented based on the technical solution of the present invention, and provides a detailed implementation method and a specific operation process, but the protection scope of the present invention is not limited to the following embodiments.

[0054] Figure 1 A flow chart of a power grid distribution engineering technical review method provided in an embodiment of the present invention.

[0055] like Figure 1 As shown, it shows a flowchart of the implementation method of the power distribution network engineering technology review method provided by the embodiment of the present invention, which is described in detail as follows:

[0056] In step 101, an overview, discussion, multiple project indicators and multiple certification documents of a distribution network project are obtained, wherein the certification documents correspond to the project indicators.

[0057] For example, in the prior art, the expert group's review of distribution network engineering projects is mainly carried out from the aspects of the project overview, discussion, and project indicators. Therefore, as an empirical model, it should also be carried out from the above aspects.

[0058] Specifically, as the most important condition project indicator for evaluating a distribution network project, it refers to a quantifiable and data-based indicator. The current regulations and specifications are quantified into specific indicators, and the distribution network quality engineering indicator standards are established. The distribution network engineering design review indicators are sorted out and improved. The sorting content includes indicator items, indicator value standard range, indicator application scope, indicator rationality verification rules, and finally a set of standard indicator systems are formed. Indicator categories include value range type, description type, other types, etc. Table 1 shows an example of a distribution network engineering design review project indicator.

[0059] Table 1 Example of indicators for distribution network engineering design review items

[0060] Serial number Indicator name Upper limit of standard value Standard value lower limit Calculation formula illustrate 1 Line tortuosity 1.4 1 2 Branch conductor cross section 95mm 3 Average distribution capacity per household-rural power grid 3KVA 4 Cost of a single distribution transformer 200,000 yuan 5 Low voltage line power supply radius 500m 6 Number of households served by distribution transformer 100 households 7 10kV distribution transformer expected load factor 30％ 8 Average distribution capacity per household - urban network 6KVA 9 Concrete pole compensation unit price 300 yuan / unit 10 More than 3 steel poles 3 11 10kV main conductor cross section 185mm 12 0.4kV conductor cross section 70mm 13 Steel rod compensation unit price 3000 yuan / place 14 Cable over 1km 1km 15 Equipment problems Each single circuit circuit breaker equipment 5 units 16 Cost per kilometer of overhead line 250,000 yuan 17 Wire pulling compensation unit price 300 yuan / place 18 Judgment of odd and even return distance 80m 19 Cost per kilometer of cable 300,000 20 Tree Compensation Unit Price 292.5 yuan 21 10kV transformer capacity 200KVA

[0061] In a system applying the present method, a server and a terminal are provided. The server receives data uploaded by the terminal, and on the terminal side, an application software is run to upload the overview, discussion, multiple project indicators and multiple certification documents of the distribution network project to the server; the operator inputs the file filled with the overview, discussion and indicators of the project that meets the server's reception specifications into the terminal, which is transmitted to the server by the terminal, and finally the server reviews the power distribution network project according to the method of the present invention.

[0062] In step 102, semantic analysis is performed on the discussion to extract multiple keywords.

[0063] In some implementations, step 102 includes:

[0064] Acquire a semantic library, wherein the semantic library includes a plurality of entries;

[0065] The discussion is matched with each term in the semantic library, and if the matching degree reaches a threshold, the term is selected as the keyword.

[0066] Exemplarily, the review of the discussion is mainly through the recognition of keywords, and the discussion is reviewed based on the recognition of keywords.

[0067] As for the extraction of keywords, the embodiment of the present invention adopts the method of performing semantic analysis on the discussion to obtain keywords. In some application scenarios, the discussion is matched with the closest part of the semantic library by traversing the prepared semantic library.

[0068] Since the entries in the semantic library are standardized entries, after matching the discussion with the standardized entries, it is easier to review the discussion based on semantics.

[0069] In step 103, a plurality of review sub-models are obtained, the overview, the plurality of project indicators, and the plurality of keywords are input into the plurality of review sub-models, a discussion score and a plurality of indicator scores are obtained, and a total score is determined based on the discussion score and the plurality of indicator scores, wherein the review sub-model is an artificial neural network model verified by expert experience, and each review sub-model scores one of the plurality of project indicators or the plurality of keywords.

[0070] In some embodiments, in step 103,

[0071] The obtaining of multiple review sub-models includes:

[0072] Perform the following steps for each review sub-model:

[0073] Acquire multiple historical samples, wherein the historical samples include: project indicators of historical projects and historical scores corresponding to the project indicators of the historical projects, or the historical samples include: project indicators of historical projects, profiles related to the project indicators of the historical projects, and historical scores corresponding to the project indicators of the historical projects, or the historical samples include: multiple keywords of historical projects and historical scores corresponding to the multiple keywords of the historical projects, wherein the historical scores are obtained by review by an expert group;

[0074] Inputting the multiple historical samples into the review sub-model, and training the review sub-model until the deviation between the score output by the review sub-model and the historical score is less than a third threshold;

[0075] The parameters of the review sub-model are fixed, and the review sub-model is used as a review sub-model verified by expert experience.

[0076] In some implementations, inputting the plurality of historical samples into the review sub-model and training the review sub-model until the deviation between the score output by the review sub-model and the historical score is less than a third threshold value comprises:

[0077] Divide multiple historical samples into training sets and validation sets;

[0078] Training steps:

[0079] Input each sample in the training set into the review sub-model until the deviation between the score output by the review sub-model and the score of the sample in the training set is less than a fourth threshold;

[0080] Verification steps:

[0081] Fix the parameters of the review sub-model, input each sample in the validation set into the review sub-model, and obtain the deviation between the score output by the review sub-model and the score of the sample in the validation set as the validation deviation;

[0082] If the verification deviation is less than the third threshold, the review sub-model is used as the review sub-model verified by expert experience;

[0083] If the verification deviation is greater than or equal to the third threshold, the parameters of the review sub-model are not fixed and the training step is returned to step

[0084] In some implementations, the historical score is scored by each member of the expert group, including technical experts and actual users of the distribution network engineering project, and is calculated according to a first formula, wherein:

[0085]

[0086] In the formula, Score is the historical score, S i is the score of the technical experts, S j is the score of the actual users of the distribution network engineering project, n is the number of technical experts participating in the scoring, m is the number of actual users of the distribution network engineering project participating in the scoring, and the number of actual users of the distribution network engineering project participating in the scoring is twice the number of technical experts participating in the scoring.

[0087] In some embodiments, the ratio of the discussion score to the total score is less than 10%.

[0088] Exemplarily, the review model is used to score based on the overview, indicators and keywords. Specifically, an indicator score is output for each project indicator, and for multiple keywords, a discussion score is output based on multiple keywords. The review model is a review model established based on the experience of the expert group and is a summary of the expert experience.

[0089] In one application scenario, the review model establishes a model for each project indicator and a model for multiple keywords, and these models are sub-models of the review model. These sub-models are artificial neural network models.

[0090] like Figure 2 As shown, artificial neural network (ANN) is an abstraction of the human brain neural network from the perspective of information processing, establishing a simple model, and forming different networks according to different connection methods. In engineering and academia, it is often simply referred to as neural network or neural network-like. Neural network is a computing model composed of a large number of nodes (or neurons) connected to each other. Each node represents a specific output function, called an activation function. The connection between each two nodes represents a weighted value for the signal passing through the connection, called the weight, which is equivalent to the memory of the artificial neural network. The output of the network varies depending on the connection method of the network, the weight value and the activation function. The network itself is usually an approximation of a certain algorithm or function in nature, or it may be an expression of a logical strategy. Unless otherwise specified in the patent application of this invention, neural network refers to artificial neural network.

[0091] like Figure 2 As shown in the figure, the most basic neural network consists of an input layer, a hidden layer, and an output layer. Given an input, a set of output results can be obtained. Figure 2 The figure shows a neural network with two hidden layers. In practical applications, the number of hidden layers is determined according to the needs. Neural networks are effective in classification problems, especially for nonlinear separable problems.

[0092] As for the training of neural networks, the samples used for training are historical samples reviewed by expert groups. Specifically, they are historical scores of multiple historical power grid distribution network projects. Each project indicator corresponds to a historical score given by an expert group, and each discussion corresponds to a historical score given by an expert group. For the specific first historical power grid distribution network project indicator A1, there is an expert group score a1, for the specific second historical power grid distribution network project indicator A2, there is an expert group score a2, for the specific third historical power grid distribution network project indicator A3, there is an expert group score a3, and so on. By analogy, you can obtain multiple samples of project indicator A with score labels. By training the neural network with this sample, you can fit the expert's score for project indicator A. Similarly, project indicators B, C, etc. can all be fitted to learn from the expert group's review experience.

[0093] Specifically for training, multiple samples are divided into two sets, a training set and a validation set. The training set is used to adjust the parameters of the neural network through training. After the parameters are continuously adjusted, the effect of fitting the experience of the expert group is achieved. After training to a certain stage, the score output by the neural network based on the input sample is close to the score of the expert Zhu, which means that preliminary training has been achieved. Then the samples of the validation set are input to the neural network that has undergone preliminary training for verification. If the output score is close to the expert group score of the validation set sample, it means that the training is successful and the correct fit has been achieved. If the score deviation is large, it means that there is overfitting and regularization should be performed, such as adjusting the neural network model (one implementation method is to reduce the number of hidden layers) and training again through the training set, and verifying with the validation set, and so on, until the validation set is verified.

[0094] The trained review sub-models implement the review method of the fitting expert group and can be used to review project indicators.

[0095] The composition of the expert group is usually composed of technical experts in various fields and actual users of distribution network projects. The ratio of the two is one to two, and the weight of their scoring is two to one. The total score divided by the number of people participating in the scoring is the historical score, which can be expressed as:

[0096]

[0097] In step 104, if the total score is higher than a first threshold, the project indicators are verified based on the multiple certification documents.

[0098] In some implementations, step 104 includes: selecting an indicator to be verified from the plurality of project indicators, wherein the indicator to be verified is a project indicator having an indicator score higher than a second threshold;

[0099] Outputting the indicator to be verified and the certification document to be verified, wherein the certification document to be verified is a certification document corresponding to the indicator to be verified;

[0100] The correctness of the indicator to be verified is determined according to the certification document to be verified.

[0101] For example, for projects with a high total score, manual verification is required, usually to verify the authenticity of the project indicators. In some application scenarios, only the project indicators with high scores are selected for review. The system will output the high-scoring project indicators and the corresponding supporting documents. The staff will verify the authenticity, correctness and effectiveness of the project indicators based on the supporting documents.

[0102] In an embodiment of the present invention, a method for evaluating the technology of a power distribution network project is provided. The method obtains the overview, discussion, multiple project indicators and multiple certification documents of the distribution network project, performs semantic analysis on the discussion, extracts multiple keywords, and then obtains multiple review sub-models, inputs the overview, the multiple project indicators and the multiple keywords into the multiple review sub-models, obtains the discussion score and the multiple indicator scores, and determines the total score according to the discussion score and the multiple indicator scores, wherein the review sub-model is an artificial neural network model verified by expert experience, and each review sub-model scores one of the multiple project indicators or the multiple keywords. The method of the present invention reviews the technology of the power distribution network project through the review model verified by expert experience, and the materials that need to be prepared are mostly digitized materials, which have a basis to rely on, and the review model is established based on expert experience. When applied to the computing terminal, the power distribution network project can be quickly reviewed and scored, the review process is fast, less materials need to be prepared, and the opinions of multiple experts can be balanced. Therefore, less human resources are consumed, and the review conclusion is more accurate and closer to reality, which is worth promoting.

[0103] It should be understood that the size of the serial numbers of the steps in the above implementation does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the implementation method of the present invention.

[0104] The following is an implementation of the device of the present invention. For details not described in detail, reference may be made to the corresponding method implementation described above.

[0105] Figure 3 This is a functional block diagram of a power distribution network engineering technology review device provided by an embodiment of the present invention, referring to Figure 3 The power grid distribution engineering technical review device includes: a project data acquisition module 301, a semantic analysis module 302, a review module 303 and a verification module 304.

[0106] The project data acquisition module 301 is used to acquire an overview, a discussion, a plurality of project indicators and a plurality of certification documents of a distribution network project, wherein the certification documents correspond to the project indicators;

[0107] A semantic analysis module 302, for performing semantic analysis on the discussion and extracting a plurality of keywords;

[0108] The review module 303 is used to obtain multiple review sub-models, input the overview, the multiple project indicators and the multiple keywords into the multiple review sub-models, obtain the discussion score and the multiple indicator scores, and determine the total score according to the discussion score and the multiple indicator scores, wherein the review sub-model is an artificial neural network model verified by expert experience, and each review sub-model scores one of the multiple project indicators or the multiple keywords;

[0109] The verification module 304 is configured to verify the project indicators according to the multiple certification documents if the total score is higher than a first threshold.

[0110] Figure 4 is a functional block diagram of a terminal provided by an embodiment of the present invention. Figure 4 As shown, the terminal 4 of this embodiment includes: a processor 400, a memory 401, and a computer program 402 stored in the memory 401 and executable on the processor 400. When the processor 400 executes the computer program 402, the steps in the above-mentioned power grid distribution engineering technology review method and implementation method are implemented, for example Figure 1 Steps 101 to 104 are shown.

[0111] Exemplarily, the computer program 402 may be divided into one or more modules / units, and the one or more modules / units are stored in the memory 401 and executed by the processor 400 to implement the present invention.

[0112] The terminal 4 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The terminal 4 may include, but is not limited to, a processor 400 and a memory 401. Those skilled in the art will appreciate that Figure 4 It is only an example of terminal 4 and does not constitute a limitation on terminal 4. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the terminal may also include input and output devices, network access devices, buses, etc.

[0113] The processor 400 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0114] The memory 401 may be an internal storage unit of the terminal 4, such as a hard disk or memory of the terminal 4. The memory 401 may also be an external storage device of the terminal 4, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the terminal 4. Further, the memory 401 may also include both an internal storage unit and an external storage device of the terminal 4. The memory 401 is used to store the computer program and other programs and data required by the terminal. The memory 401 may also be used to temporarily store data that has been output or is to be output.

[0115] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the implementation method can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method implementation method, which will not be repeated here.

[0116] In the above-mentioned embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0117] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0118] In the embodiments provided by the present invention, it should be understood that the disclosed devices / terminals and methods can be implemented in other ways. For example, the device / terminal embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0119] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0120] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0121] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned implementation method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various power distribution network engineering technology review methods and power distribution network engineering technology review device implementation methods can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practices in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practices, computer-readable media does not include electrical carrier signals and telecommunication signals.

[0122] The above-described embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for evaluating the technology of power distribution network engineering, characterized in that: include: Obtaining an overview, a discussion, a plurality of project indicators, and a plurality of supporting documents of a distribution network project, wherein the supporting documents correspond to the project indicators; Perform semantic analysis on the discussion and extract multiple keywords; Acquire multiple review sub-models, input the overview, the multiple project indicators, and the multiple keywords into the multiple review sub-models, obtain a discussion score and multiple indicator scores, and determine a total score based on the discussion score and the multiple indicator scores, wherein the review sub-model is an artificial neural network model verified by expert experience, and each review sub-model scores one of the multiple project indicators or the multiple keywords; If the total score is higher than a first threshold, verifying the project indicators based on the multiple certification documents; in, The semantic analysis of the discussion is performed to extract multiple keywords, including: Acquire a semantic library, wherein the semantic library includes a plurality of entries; Matching the discussion with each term in the semantic library, if the matching degree reaches a threshold, the term is selected as the keyword; in, The obtaining of multiple review sub-models includes: Perform the following steps for each review sub-model: Acquire multiple historical samples, wherein the historical samples include: project indicators of historical projects and historical scores corresponding to the project indicators of the historical projects, or the historical samples include: project indicators of historical projects, profiles related to the project indicators of the historical projects, and historical scores corresponding to the project indicators of the historical projects, or the historical samples include: multiple keywords of historical projects and historical scores corresponding to the multiple keywords of the historical projects, wherein the historical scores are obtained by review by an expert group; Inputting the multiple historical samples into the review sub-model, and training the review sub-model until the deviation between the score output by the review sub-model and the historical score is less than a third threshold; Fixing the parameters of the review sub-model and using the review sub-model as a review sub-model verified by expert experience; in, The historical score is scored by each member of the expert group, including technical experts and actual users of the distribution network project, and is calculated according to a first formula, wherein: In the formula, Score is the historical score, S i is the score of the technical experts, S j is the score of the actual users of the distribution network engineering project, n is the number of technical experts participating in the scoring, m is the number of actual users of the distribution network engineering project participating in the scoring, and the number of actual users of the distribution network engineering project participating in the scoring is twice the number of technical experts participating in the scoring.

2. The power distribution network engineering technology review method according to claim 1, characterized in that: The step of inputting the plurality of historical samples into the review sub-model and training the review sub-model until the deviation between the score output by the review sub-model and the historical score is less than a third threshold value includes: Divide multiple historical samples into training sets and validation sets; Training steps: Input each sample in the training set into the review sub-model until the deviation between the score output by the review sub-model and the score of the sample in the training set is less than a fourth threshold; Verification steps: Fix the parameters of the review sub-model, input each sample in the validation set into the review sub-model, and obtain the deviation between the score output by the review sub-model and the score of the sample in the validation set as the validation deviation; If the verification deviation is less than the third threshold, the review sub-model is used as the review sub-model verified by expert experience; If the verification deviation is greater than or equal to the third threshold, the parameters of the review sub-model are not fixed and the process returns to the training step.

3. The power distribution network engineering technology review method according to any one of claims 1-2, characterized in that: The verifying of the project indicators according to the multiple certification documents includes: Selecting an indicator to be verified from the multiple project indicators, wherein the indicator to be verified is a project indicator whose indicator score is higher than a second threshold; Outputting the indicator to be verified and the certification document to be verified, wherein the certification document to be verified is a certification document corresponding to the indicator to be verified; The correctness of the indicator to be verified is determined according to the certification document to be verified.

4. The power distribution network engineering technology review method according to any one of claims 1-2, characterized in that: The ratio of the discussion score to the total score is less than 10%.

5. A power distribution network engineering technology review device, characterized in that: Used to implement the power distribution network engineering technology review method according to any one of claims 1 to 4, the power distribution network engineering technology review device comprises: A project data acquisition module, used to acquire an overview, discussion, multiple project indicators and multiple certification documents of a distribution network project, wherein the certification documents correspond to the project indicators; A semantic analysis module, used to perform semantic analysis on the discussion and extract multiple keywords; A review module, used to obtain a plurality of review sub-models, input the overview, the plurality of project indicators and the plurality of keywords into the plurality of review sub-models, obtain a discussion score and a plurality of indicator scores, and determine a total score according to the discussion score and the plurality of indicator scores, wherein the review sub-model is an artificial neural network model verified by expert experience, and each review sub-model scores one of the plurality of project indicators or the plurality of keywords; and A verification module is used to verify the project indicators according to the multiple certification documents if the total score is higher than a first threshold.

6. A terminal comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 4 are implemented.

7. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

Images