Power equipment bidding and tendering method and device and computer readable storage medium
By using natural language processing models and multi-objective optimization algorithms, the problems of inconsistent evaluation and low efficiency in power equipment bidding have been solved, achieving efficient and accurate evaluation of bid documents.
Patent Information
- Application Number
- CN202411730674.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-29
- Publication Date
- 2025-11-07
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Existing bidding methods for power equipment suffer from incomplete evaluation of bid documents, time-consuming and labor-intensive bid evaluation processes, and inconsistent bid evaluation standards, resulting in low accuracy and efficiency of bidding results.
Natural language processing models are used to extract feature parameters from bid documents. A Transformer encoder and a multilayer perceptron module are used to represent semantic and numerical features. A multi-objective optimization algorithm is combined to construct the bidding objective function and constraint function. The optimal bid document is obtained through iterative training.
This improves the accuracy and efficiency of bid evaluation, avoids the influence of subjective human factors, ensures that bid documents are evaluated according to the same standard, and quickly finds the best bid documents that meet the requirements.
Smart Images
Figure CN120912302A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of electronic bidding, in particular to a power equipment bidding method and device and a computer readable storage medium. BACKGROUND
[0002] The power equipment bidding is an important form of power equipment procurement and a core link of power system construction. The tenderer specifies the required power equipment specifications, quantity and technical requirements through the publication of a bidding announcement. The tenderer provides the corresponding tender documents based on its own conditions. The tenderer determines the optimal tender document through public bidding, expert scoring and other ways, thereby determining the power equipment supplier.
[0003] The power equipment bidding method in the prior art needs to form an evaluation committee composed of tenderers, technical experts and economic experts after obtaining the tender documents provided by multiple tenderers. The evaluation committee analyzes and compares each tender document to finally select the winning document. Since the power equipment tender document usually contains a large number of technical parameters, for example, a tender document for a large substation equipment may be hundreds of pages long. To analyze the power equipment parameters and other contents in each tender document not only needs to consume a large amount of manpower and time, but also may cause information omission, affecting the comprehensiveness of the tender document evaluation. In addition, different evaluation subjects have different focuses in the evaluation process, which also leads to inconsistent evaluation standards, thereby affecting the accuracy of the bidding result.
[0004] In summary, the existing power equipment bidding method has the problems of insufficient evaluation of the evaluation document, consumption of manpower and time in the evaluation process, and inconsistent evaluation standards, resulting in low accuracy of the bidding result and low efficiency of the bidding. SUMMARY
[0005] Therefore, the technical problem to be solved by the present application is to overcome the problems of insufficient evaluation of the evaluation document, consumption of manpower and time in the evaluation process, and inconsistent evaluation standards in the existing power equipment bidding method, resulting in low accuracy of the bidding result and low efficiency of the bidding.
[0006] To solve the above technical problems, the present application provides a power equipment bidding method, comprising: obtaining power equipment bidding project information; wherein the power equipment bidding project information includes power equipment type, procurement quantity, power equipment parameter range and project budget; obtaining multiple tender documents and processing each tender document using a natural language processing model to extract feature parameters of each tender document; wherein the feature parameters include power equipment supplier, power equipment price and power equipment parameters; inputting the characteristic parameters of each bid document into a Transformer encoder module and a multilayer perceptron module in the trained bid document evaluation model, outputting semantic feature representation and numerical feature representation of the bid document; concatenating and inputting the semantic feature representation and the numerical feature representation into a fully connected layer in the trained bid document evaluation model, outputting the winning probability of the bid document; constructing a bidding target function and a constraint function based on the power equipment bidding project information, the characteristic parameters of each bid document and the winning probability by using a multi-objective optimization algorithm, solving the bidding target function and the constraint function, and obtaining an optimal bid document.
[0007] Preferably, each bid document is processed by using a natural language processing model, and the characteristic parameters of each bid document include: segmenting each bid document to obtain a word sequence of each bid document; inputting the word sequence of each bid document into a trained NER model, and outputting the supplier name, power equipment name, power equipment parameter and power equipment price in the bid document; integrating the supplier name, power equipment name, power equipment parameter and power equipment price in each bid document, and outputting the characteristic parameters of the bid document.
[0008] Preferably, the training process of the bid document evaluation model includes: obtaining a plurality of bid documents and an optimal bid document in a historical power equipment bidding project; and processing each bid document by using a natural language processing model to extract the characteristic parameters of each bid document; inputting the characteristic parameters of the bid document into a Transformer encoder module, and outputting semantic feature representation of the bid document; inputting the characteristic parameters of the bid document into a multilayer perceptron module, and outputting numerical feature representation of the bid document; concatenating and inputting the semantic feature representation and the numerical feature representation into a fully connected layer, constructing a cross-entropy loss function based on the output of the fully connected layer and the winning result of the bid document; iteratively training the Transformer encoder module, the multilayer perceptron module and the fully connected layer by using a plurality of bid documents until the value of the cross-entropy loss function is minimum, obtaining a trained Transformer encoder module, multilayer perceptron module and fully connected layer, and obtaining a trained bid document evaluation model based on the trained Transformer encoder module, multilayer perceptron module and fully connected layer.
[0009] Preferably, the cross-entropy loss function is represented as: , wherein, represents the cross-entropy loss function; represents the winning probability of the bid document of the full-connection layer output; represents the winning result of the bid document, if the bid document is the optimal bid document, then , if the bid document is not the optimal bid document, then .
[0010] Preferably, constructing the bidding and tendering objective function and the constraint function based on the power equipment bidding project information, the characteristic parameters and the winning probability of each bid document by using the multi-objective optimization algorithm comprises: constructing a power equipment procurement cost minimization objective function based on the power equipment price and the winning probability of all bid documents, and taking the power equipment procurement cost minimization objective function as the bidding and tendering objective function; constructing a first constraint function based on the power equipment price of the optimal bid document being less than or equal to the project budget in the power equipment bidding project information; constructing a second constraint function based on the power equipment parameters in the optimal bid document satisfying the power equipment parameter range in the power equipment bidding project information.
[0011] Preferably, the power equipment procurement cost minimization objective function is represented as: , wherein, represents the power equipment procurement cost minimization objective function; represents the power equipment price of the i-th bid document; represents the winning probability of the i-th bid document; represents the number of bid documents; the first constraint function is represented as: , wherein, is a binary variable, if , it represents that the i-th bid document wins, if , it represents that the i-th bid document does not win; represents the project budget in the power equipment bidding project information; the second constraint function is represented as: , wherein, represents the power equipment parameter range in the power equipment bidding project information; , wherein, represents the power equipment parameter in the i-th bid document. power equipment parameters of the bid file; representing a minimum value of a power equipment parameter range in the power equipment bidding project information; representing a maximum value of a power equipment parameter range in the power equipment bidding project information.
[0012] Preferably, the bidding constraint function and the constraint function are solved by using a particle swarm optimization algorithm to obtain an optimal bid file.
[0013] Preferably, the feature parameters of each bid file are input into an anomaly detection model for anomaly detection to determine whether the feature parameters of each bid file are abnormal, and the bid file with abnormal feature parameters is determined as a risk bid file.
[0014] The application further provides a power equipment bidding device, comprising: a bidding module, configured to obtain power equipment bidding project information, wherein the power equipment bidding project information comprises a power equipment type, a procurement quantity, a power equipment parameter range and a project budget; a bidding module, configured to obtain a plurality of bid files and process each bid file by using a natural language processing model to extract feature parameters of each bid file; wherein the feature parameters comprise a power equipment supplier, a power equipment price and a power equipment parameter; an evaluation module, configured to input the feature parameters of each bid file into a Transformer encoder module and a multi-layer perception module in a trained bid file evaluation model to output semantic feature representation and numerical feature representation of the bid file; and input the semantic feature representation and the numerical feature representation into a full connection layer in the trained bid file evaluation model to output a bid-winning probability of the bid file; a bidding module, configured to obtain a plurality of bid files and process each bid file by using a natural language processing model to extract feature parameters of each bid file; wherein the feature parameters comprise a power equipment supplier, a power equipment price and a power equipment parameter;
[0015] The application further provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the steps of the power equipment bidding method.
[0016] The power equipment bidding method provided in the application extracts feature parameters related to the bidding project information in each bidding document by using a natural language processing model. Since the feature parameters of the bidding document contain text and numerical information, a Transformer encoder is used to extract semantic features in the feature parameters, and a multi-layer perception is used to extract numerical features in the feature parameters. The bidding probability of the bidding document is evaluated based on the semantic features and the numerical features, which avoids the omission of feature parameters and the influence of subjective factors of the evaluation personnel on the evaluation results, ensures that the features of each bidding document are extracted and the bidding probability is calculated according to the same standard and rule, and finally, a multi-objective optimization algorithm is used to construct a bidding target function and a constraint function based on the bidding project information and the feature parameters and the bidding probability of each bidding document. By solving the target function and the constraint function, the optimal bidding document that meets the conditions can be found from a large number of bidding documents in a short time, which greatly improves the bidding efficiency, avoids the ambiguity of subjective judgment of human evaluation personnel, and improves the accuracy of the bidding result. BRIEF DESCRIPTION OF DRAWINGS
[0017] In order to make the content of the application more easily understood, the application will be further described in detail below according to specific embodiments of the application and in conjunction with the drawings, in which: Figure 1 The power equipment bidding method provided in the application is shown in the flowchart. Figure 2 The power equipment bidding device provided in the application is shown in the structural schematic diagram. DETAILED DESCRIPTION
[0018] The application will be further described below in conjunction with the drawings and specific embodiments, so that those skilled in the art can better understand the application and implement it. However, the embodiments are not limiting to the application.
[0019] Please refer to Figure 1 , Figure 1 The power equipment bidding method provided in the application is shown in the flowchart, which specifically includes: S10: Obtain power equipment bidding project information; wherein the power equipment bidding project information includes power equipment type, procurement quantity, power equipment parameter range and project budget; S20: Obtain a plurality of bidding documents, and process each bidding document by using a natural language processing model to extract feature parameters of each bidding document; wherein the feature parameters include power equipment supplier, power equipment offer and power equipment parameters; S30: input the feature parameters of each bid file into the Transformer encoder module and the multi-layer perception module in the trained bid file evaluation model respectively, output the semantic feature representation and the numerical feature representation of the bid file; splice the semantic feature representation and the numerical feature representation and input them into the full connection layer in the trained bid file evaluation model, output the winning probability of the bid file; S40: use a multi-objective optimization algorithm to construct a bidding target function and a constraint function based on the power equipment bidding project information, the feature parameters of each bid file and the winning probability, solve the bidding target function and the constraint function, and obtain the optimal bid file.
[0020] The power equipment bidding method provided in the application extracts the feature parameters related to the bidding project information in each bid file by using a natural language processing model. Since the feature parameters of the bid file contain text and numerical information, the semantic features in the feature parameters are extracted by using a Transformer encoder, and the numerical features in the feature parameters are extracted by using a multi-layer perception machine. The winning probability of the bid file is evaluated based on the semantic features and the numerical features. This avoids the problem of missing feature parameters and the influence of subjective factors of evaluators on the evaluation results, ensures that the features of each bid file are extracted and the winning probability is calculated according to the same standard and rule, and finally, the bidding target function and the constraint function are constructed based on the bidding project information and the feature parameters and the winning probability of each bid file by using a multi-objective optimization algorithm. By solving the target function and the constraint function, the optimal bid file that meets the conditions can be found from a large number of bid files in a short time, the efficiency of bid evaluation is greatly improved, the subjectivity of human bid evaluators is avoided, and the accuracy of the bidding result is improved.
[0021] Specifically, in some embodiments of the application, each bid file is processed by using a natural language processing model to extract the feature parameters of each bid file, including: Tokenizing each bid file to obtain a word sequence of each bid file; In an embodiment, a tokenization tool can be used to divide the continuous sentences in the bid file into multiple words.
[0022] Inputting the word sequence of each bid file into a trained NER model to output the supplier name, power equipment name, power equipment parameter and power equipment price in the bid file; In an embodiment, a dedicated NER model can be trained for the field of power equipment, for example: mobile phone power equipment related text data, annotated text data of supplier name, power equipment name, power equipment price and power equipment parameters, to obtain a training set, and the NER model is trained using the training set, so that the trained NER model can accurately extract supplier name, power equipment name, power equipment parameters and power equipment price and other parameters from the text data.
[0023] The supplier name, power equipment name, power equipment parameter and power equipment bid in each bid file are integrated, and the characteristic parameters of the bid file are output.
[0024] Further, since the bid file contains both text and numerical information, the present application uses two parallel modules of Transformer encoder and multilayer perceptron to extract features from the bid file. The Transformer encoder is used to extract semantic features in the file, and the multilayer perceptron can extract numerical features in the file.
[0025] Specifically, in some embodiments of the present application, the training process of the bid file evaluation model includes: Obtain a plurality of bid files and an optimal bid file in a historical power equipment bidding project; and process each bid file using a natural language processing model to extract the characteristic parameters of each bid file; Input the characteristic parameters of the bid file into the Transformer encoder module to output the semantic feature representation of the bid file; Input the characteristic parameters of the bid file into the multilayer perceptron module to output the numerical feature representation of the bid file; Concatenate and input the semantic feature representation and the numerical feature representation into a fully connected layer, and based on the output of the fully connected layer and the winning result of the bid file, construct a cross-entropy loss function; Specifically, the cross-entropy loss function is represented as: , Wherein, represents the cross-entropy loss function; represents the winning probability of the bid file output by the fully connected layer; represents the winning result of the bid file, if the bid file is the optimal bid file, then , if the bid file is not the optimal bid file, then .
[0026] The Transformer encoder module, the multi-layer perceptron module and the full connection layer are iteratively trained by using multiple bid documents until a value of the cross-entropy loss function is minimum, to obtain a trained Transformer encoder module, a multi-layer perceptron module and a full connection layer, and a trained bid document evaluation model is obtained based on the trained Transformer encoder module, the multi-layer perceptron module and the full connection layer.
[0027] Further, in some embodiments of the present application, the step S40 of constructing a bidding target function and a constraint function based on the power equipment bidding project information, the characteristic parameters of each bid document and the winning probability by using a multi-objective optimization algorithm comprises: Based on the power equipment price of all bid documents and the winning probability, a power equipment procurement cost minimization target function is constructed, and the power equipment procurement cost minimization target function is taken as the bidding target function; Specifically, the power equipment procurement cost minimization target function is expressed as: , Wherein, represents the power equipment procurement cost minimization target function; represents the power equipment price of the i-th bid document; represents the winning probability of the i-th bid document; represents the number of bid documents; Based on the power equipment price of the optimal bid document being less than or equal to the project budget in the power equipment bidding project information, a first constraint function is constructed; Specifically, the first constraint function is expressed as: , , Wherein, is a binary variable, if , indicates that the i-th bid document wins, if , indicates that the i-th bid document does not win; represents the project budget in the power equipment bidding project information; Based on the power equipment parameters in the optimal bid document satisfying the power equipment parameter range in the power equipment bidding project information, a second constraint function is constructed. Specifically, the second constraint function is expressed as:
[0028] , , Wherein, represents the i-th bid document; Power equipment parameters in the tender documents; This indicates the minimum range of power equipment parameters in the power equipment bidding project information; This indicates the maximum range of power equipment parameters in the power equipment bidding project information.
[0029] Furthermore, after constructing the bidding objective function and constraint function, the particle swarm optimization algorithm is used to solve the bidding objective function and constraint function, and the optimal bid document that satisfies the objective and constraint functions can be selected. This optimal bid document is the winning bid document in the bidding project.
[0030] Optionally, during the entire bidding process, there may be situations such as bid rigging, malicious bidding, or false bidding by bidders. Therefore, in some embodiments of this application, the bidding method for power equipment further includes: inputting the feature parameters of each bid document into an anomaly detection model for anomaly detection, determining whether there are any anomalies in the feature parameters of each bid document, and identifying bid documents with anomalies in feature parameters as risky bid documents.
[0031] Based on the power equipment bidding method provided in the above embodiments, this application also provides a power equipment bidding device, such as... Figure 2 As shown, the power equipment bidding device includes: The bidding module 10 is used to obtain information on power equipment bidding projects; wherein, the power equipment bidding project information includes the type of power equipment, the quantity to be purchased, the range of power equipment parameters, and the project budget; The bidding module 20 is used to acquire multiple bid documents and process each bid document using a natural language processing model to extract feature parameters of each bid document; wherein, the feature parameters include power equipment supplier, power equipment price and power equipment parameters; The bid evaluation module 30 is used to input the feature parameters of each bid document into the Transformer encoder module and the multilayer perceptron module in the trained bid document evaluation model, and output the semantic feature representation and the numerical feature representation of the bid document; concatenate the semantic feature representation and the numerical feature representation and input them into the fully connected layer in the trained bid document evaluation model, and output the winning probability of the bid document. The calibration module 40 is used to construct the bidding objective function and constraint function based on the information of the power equipment bidding project, the characteristic parameters of each bid document and the probability of winning the bid using a multi-objective optimization algorithm, and to solve the bidding objective function and constraint function to obtain the optimal bid document.
[0032] The embodiment of the present application further provides a computer readable storage medium, and the computer readable storage medium stores a computer program, and the computer program is executed by a processor to realize the steps of the power equipment bidding method.
[0033] Those skilled in the art should understand that the embodiment of the present application can be provided as a method, a system or a computer program product. Therefore, the present application can adopt a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware aspects. Moreover, the present application can adopt a computer program product implemented on one or more computer readable storage media containing computer usable program codes (including but not limited to disk storage, CD-ROM, optical storage, etc.).
[0034] The present application is described with reference to flowcharts and / or block diagrams of the method, device (system) and computer program product according to the embodiment of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams and the combination of the flows and / or blocks can be implemented by computer program instructions. These computer program instructions can be provided to a general purpose computer, a special purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the computer or other programmable data processing device produce a device implemented in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 an apparatus that performs the functions specified in the flow(s) or block(s).
[0035] These computer program instructions can also be stored in a computer readable memory that can direct the computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce a manufactured product including instruction apparatus, which realizes the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 an apparatus that performs the functions specified in the flow(s) or block(s).
[0036] These computer program instructions can also be loaded into a computer or other programmable data processing device, so that a series of operation steps are performed on the computer or other programmable device to produce a computer implemented process, so that the instructions executed on the computer or other programmable device provide steps for realizing the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 an apparatus that performs the functions specified in the flow(s) or block(s).
[0037] Obviously, the above embodiments are merely example for clearly illustrating, and are not limitation to the embodiments. Based on the above description, other different forms of changes or variations can be made by those skilled in the art. Here, all the embodiments are not required to be enumerated, and the obvious changes or variations derived from the above are still within the protection scope of the present application.
Claims
1. A power equipment bidding method characterized by comprising: The method comprises the following steps: obtaining power equipment bidding project information, wherein the power equipment bidding project information comprises power equipment type, procurement quantity, power equipment parameter range and project budget; obtaining a plurality of bid documents and processing each bid document by using a natural language processing model to extract feature parameters of each bid document, wherein the feature parameters comprise power equipment supplier, power equipment offer and power equipment parameters; inputting the feature parameters of each bid document into a Transformer encoder module and a multi-layer perception module of a trained bid document evaluation model respectively to output semantic feature representation and numerical feature representation of the bid document; and inputting the semantic feature representation and the numerical feature representation into a full connection layer of the trained bid document evaluation model to output a winning probability of the bid document; constructing a bidding target function and a constraint function based on the power equipment bidding project information, the feature parameters of each bid document and the winning probability by using a multi-objective optimization algorithm, solving the bidding target function and the constraint function, and obtaining an optimal bid document.
2. The electric power equipment tendering method according to claim 1, characterized by, The processing of each bid document by using the natural language processing model to extract the feature parameters of each bid document comprises the following steps: performing word segmentation on each bid document to obtain a word sequence of each bid document; inputting the word sequence of each bid document into a trained NER model to output a supplier name, a power equipment name, power equipment parameters and a power equipment price in the bid document; integrating the supplier name, the power equipment name, the power equipment parameters and the power equipment offer in each bid document to output the feature parameters of the bid document.
3. The electric power equipment bidding method according to claim 1, characterized by, The training process of the bid document evaluation model comprises the following steps: obtaining a plurality of bid documents and an optimal bid document in a historical power equipment bidding project, and processing each bid document by using a natural language processing model to extract feature parameters of each bid document; inputting the feature parameters of the bid document into a Transformer encoder module to output semantic feature representation of the bid document; inputting the feature parameters of the bid document into a multi-layer perception module to output numerical feature representation of the bid document; inputting the semantic feature representation and the numerical feature representation into a full connection layer, and constructing a cross-entropy loss function based on an output of the full connection layer and a winning result of the bid document; iteratively training the Transformer encoder module, the multi-layer perception module and the full connection layer by using a plurality of bid documents until a value of the cross-entropy loss function is minimum, obtaining a trained Transformer encoder module, a multi-layer perception module and a full connection layer, and obtaining a trained bid document evaluation model based on the trained Transformer encoder module, the multi-layer perception module and the full connection layer.
4. The electric power equipment tendering method according to claim 3, wherein The cross-entropy loss function is represented as: ， wherein, represents a cross-entropy loss function; represents the winning probability of the bid file output by the full connection layer; represents the winning result of the bid file, if the bid file is the optimal bid file, then , if the bid file is a non-optimal bid file, then .
5. The electric power equipment bidding method according to claim 1, wherein constructing a bidding target function and a constraint function based on the power equipment bidding project information, the feature parameters of each bid document and the winning probability by using a multi-objective optimization algorithm comprises the following steps: Based on the power equipment quotation of all the bidding documents and the winning probability, a power equipment procurement cost minimization objective function is constructed, and the power equipment procurement cost minimization objective function is taken as a bidding objective function; Based on the power equipment quotation of the optimal bidding document being less than or equal to the project budget in the power equipment bidding project information, a first constraint function is constructed; Based on the power equipment parameters in the optimal bidding document meeting the power equipment parameter range in the power equipment bidding project information, a second constraint function is constructed.
6. The electric power equipment bidding method according to claim 1, wherein The power equipment procurement cost minimization objective function is expressed as: ， wherein, represents a power equipment procurement cost minimization objective function; represents a power equipment bid price of the thbid document; represents a winning probability of the thbid document; represents a number of bid documents; The first constraint function is expressed as: ， wherein, is a binary variable, if , indicates that the th bid file is successful, if , indicates that the th bid file is unsuccessful; indicates the project budget in the power equipment bidding project information; The second constraint function is expressed as: ， wherein, represents the power equipment parameter of the represents the minimum value of the power equipment parameter range in the power equipment bidding project information; represents the maximum value of the power equipment parameter range in the power equipment bidding project information. 7. The electric power equipment bidding method according to claim 1, wherein The bidding constraint function and the constraint function are solved by using a particle swarm optimization algorithm to obtain the optimal bidding document.
8. The electric power equipment bidding method according to claim 1, wherein Further comprising inputting the characteristic parameters of each bidding document into an anomaly detection model for anomaly detection, judging whether the characteristic parameters of each bidding document are abnormal, and judging the bidding document with abnormal characteristic parameters as a risk bidding document.
9. An electric power equipment bidding device characterized by comprising: Comprise: The bidding module is used for obtaining a plurality of bidding documents, and processing each bidding document by using a natural language processing model to extract the characteristic parameters of each bidding document; wherein the characteristic parameters comprise a power equipment supplier, a power equipment price and a power equipment parameter; The evaluation module is used for inputting the characteristic parameters of each bidding document into a Transformer encoder module and a multi-layer perception module in a trained bidding document evaluation model respectively to output semantic feature representation and numerical feature representation of the bidding document; the semantic feature representation and the numerical feature representation are spliced and input into a full connection layer in the trained bidding document evaluation model to output a winning probability of the bidding document; The computer readable storage medium stores a computer program, and the computer program is executed by the processor to realize the steps of the power equipment bidding method in any one of claims 1-8. The computer readable storage medium stores a computer program, and the computer program is executed by the processor to realize the steps of the power equipment bidding method in any one of claims 1-8.
10. A computer-readable storage medium, characterized in that,