Power material replenishment method and device based on supply source material quality evaluation
Through the quality evaluation and screening of power material supply sources, the problem of insufficient supply capacity and quality considerations in power material replenishment has been solved, and the project safety and resource utilization efficiency have been improved.
Patent Information
- Application Number
- CN202311528730.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-11-16
- Publication Date
- 2024-11-22
- Estimated Expiration
- 2043-11-16
AI Technical Summary
During the process of replenishing power materials, the existing technology lacks consideration of the supply source supply capacity and the quality of power materials, resulting in untimely or low quality of material supply, which in turn leads to stagnation of project progress and a decrease in safety, and insufficient supplementary quantity leads to waste of transportation resources .
By responding to the power supply material quality evaluation request, screening candidate supply sources, generating quality evaluation information, determining the target supply source, and controlling the dispatching equipment to replenish power materials to ensure the matching of quality and quantity.
It reduces the frequency of project progress stagnation, improves the safety of power projects, reduces the risks caused by untimely supply of materials and low quality, and optimizes the utilization of transportation resources.
Smart Images

Figure CN117689241B_ABST
Abstract
Description
Technical Field
[0001] Embodiments of the present disclosure relate to the field of computer technology, and in particular to a method and device for replenishing electric power materials based on supply source material quality evaluation. Background Art
[0002] Power materials often have an important impact on the orderly advancement of power projects. Power material replenishment refers to the method of dispatching and replenishing the missing power materials during the construction of power projects. At present, when replenishing power materials, the commonly used method is to dispatch and replenish power materials directly from the fixed power material supply source according to the amount of power materials missing in the current power project construction.
[0003] However, the inventors have found that when the above method is used to replenish power materials, the following technical problems often occur:
[0004] First, directly replenishing power materials from fixed supply sources lacks consideration of the supply capacity and quality of power materials, resulting in frequent stagnation of project progress due to untimely material supply or reduced project safety due to low quality of power materials provided.
[0005] Second, when evaluating the quality of power materials, people often only test their physical properties, without considering the impact of external faults of some power materials on their quality, which leads to a decline in the quality of supplemented power materials and a decline in project safety.
[0006] Third, the power supplies are directly replenished according to the current shortage, without considering the project's consumption of supplies during the replenishment period, resulting in insufficient replenished power supplies, which in turn requires further replenishment and wastes transportation resources.
[0007] The above information disclosed in this Background section is only for enhancement of understanding of the background of the inventive concept and therefore it may contain information that does not form the prior art that is already known in this country to a person of ordinary skill in the art. Summary of the invention
[0008] The content of this disclosure is used to introduce concepts in a brief form, which will be described in detail in the detailed implementation section below. The content of this disclosure is not intended to identify the key features or essential features of the technical solution claimed for protection, nor is it intended to limit the scope of the technical solution claimed for protection.
[0009] Some embodiments of the present disclosure propose a method, device, electronic device and computer-readable medium for replenishing electric power materials based on the quality evaluation of supply source materials to solve one or more of the technical problems mentioned in the above background technology section.
[0010] In a first aspect, some embodiments of the present disclosure provide a method for replenishing electric power materials based on supply source material quality evaluation, the method comprising: in response to an electric power material replenishment request sent by a target terminal, updating the number of request receptions, wherein the number of request receptions is the number of times the electric power material replenishment request is received; in response to determining that the number of request receptions is a preset number of receptions, determining identification information of each candidate electric power material supply source; sending each supply source electric power material information request to each electric power material supply source corresponding to each determined candidate electric power material supply source identification information to obtain a supply source electric power material information group set, wherein each supply source electric power material information included in the supply source electric power material information group in the supply source electric power material information group set corresponds to the same candidate electric power material supply source identification information; generating an electric power material quality evaluation information group set based on the supply source electric power material information group set; determining each target electric power material supply source identification information based on the electric power material quality evaluation information group set and each candidate electric power material supply source identification information, and controlling each associated dispatching device to dispatch electric power materials from each target electric power material supply source corresponding to each target electric power material supply source identification information to replenish electric power materials.
[0011] Optionally, the above-mentioned determination of identification information of each candidate power material supply source includes: receiving business information of each supply source sent by each power material supply source, wherein the above-mentioned supply source business information includes power material supply source identification information, supply source fixed value information, supply source negative value information, material turnover rate, material delayed turnover rate, material reverse turnover rate and total material turnover volume; inputting the received business information of each supply source into a pre-trained supply source classification model to obtain classification labels of each supply source; and determining the identification information of each power material supply source included in the business information of each supply source corresponding to each supply source classification label that meets the supply source screening condition among the above-mentioned supply source classification labels as the identification information of each candidate power material supply source.
[0012] Optionally, the supply source classification model is trained through the following steps: obtaining a historical supply source business information set and a historical supply source classification label set, wherein the historical supply source business information in the historical supply source business information set corresponds to the historical supply source classification label in the historical supply source classification label set; dividing the historical supply source business information set according to the historical supply source classification label set to obtain various supply source business information groups, wherein the classification results represented by the various historical supply source classification labels corresponding to the various supply source business information included in each of the various supply source business information groups are the same; in response to determining that the various supply source business information groups satisfy the oversampling condition, oversampling the historical supply source business information set to update The above-mentioned historical supply source business information set and historical supply source classification label set; based on the historical supply source business information set and the historical supply source classification label set, perform the following model training steps: input at least one historical supply source business information in the historical supply source business information set into the initial supply source classification model, and obtain the verification supply source classification label corresponding to each historical supply source business information in the at least one historical supply source business information; compare the verification supply source classification label corresponding to each historical supply source business information in the at least one historical supply source business information with the corresponding historical supply source classification label; determine the classification accuracy of the initial supply source classification model according to the comparison result; in response to determining that the classification accuracy is greater than or equal to the preset classification accuracy, determine the initial supply source classification model as the supply source classification model.
[0013] Optionally, the above-mentioned model training step also includes: in response to determining that the classification accuracy is less than the above-mentioned preset classification accuracy, adjusting the initial supply source classification model, forming a historical supply source business information set with unused historical supply source business information, determining the adjusted initial supply source classification model as the initial supply source classification model, and executing the above-mentioned model training step again.
[0014] Optionally, the supply source power material information in the above-mentioned supply source power material information group set includes: power material type information, power material value information and each power material attribute information; and before generating the power material quality evaluation information group set according to the above-mentioned supply source power material information group set, the above-mentioned method also includes: obtaining a material evaluation attribute group set and an evaluation attribute weight group set, wherein the material evaluation attributes in the above-mentioned material evaluation attribute group set correspond to the attribute weights in the above-mentioned evaluation attribute weight group set; for each supply source power material information group in the above-mentioned supply source power material information group set, performing the following steps: according to the power material included in the above-mentioned supply source power material information group, resource type information, selecting a material evaluation attribute group that meets the material type matching condition from the above-mentioned material evaluation attribute group set as the target material evaluation attribute group; for each supply source power material information in the above-mentioned supply source power material information group, performing the following data cleaning steps: in response to determining that the above-mentioned supply source power material information does not meet the necessary information conditions corresponding to the above-mentioned target material evaluation attribute group, removing the above-mentioned supply source power material information from the above-mentioned supply source power material information group set to update the above-mentioned supply source power material information group set; in response to determining that the above-mentioned supply source power material information is semi-structured information or unstructured information, structuring the above-mentioned supply source power material information.
[0015] Optionally, each of the candidate power material supply source identification information corresponds to a weighted coefficient of each supply source; and the generation of the power material quality evaluation information group set according to the supply source power material information group set includes: re-dividing the supply source power material information group set according to the power material type information included in each supply source power material information in the supply source power material information group set to update the supply source power material information group set; for each supply source power material information group in the updated supply source power material information group set, performing the following quality evaluation steps: selecting a power material attribute detection model that meets the above material type matching condition from a preset power material attribute evaluation model set as a target material attribute detection model; An evaluation attribute weight group that satisfies the above-mentioned material type matching condition is selected from the above-mentioned evaluation attribute weight group set as a target evaluation attribute weight group; for each supply source power material information in the above-mentioned supply source power material information group, the following steps are performed: the above-mentioned supply source power material information is input into the above-mentioned target material attribute detection model to generate power material attribute detection information; according to the above-mentioned power material attribute detection information, the above-mentioned target evaluation attribute weight group and the supply source weighting coefficient corresponding to the above-mentioned power material attribute detection information, power material quality evaluation information is generated; each generated power material quality evaluation information is determined as a power material quality evaluation information group; and the determined power material quality evaluation information group is determined as a power material quality evaluation information group set.
[0016] Optionally, the method further includes: storing the electric power material quality evaluation information group set in a pre-constructed electric power material supply source evaluation information knowledge graph.
[0017] In a second aspect, some embodiments of the present disclosure provide an electric power material replenishment device based on supply source material quality evaluation, the device comprising: an updating unit, configured to update the number of request receptions in response to an electric power material replenishment request sent by a target terminal, wherein the number of request receptions is the number of times the electric power material replenishment request is received; a determining unit, configured to determine identification information of each candidate electric power material supply source in response to determining that the number of request receptions is a preset number of receptions; a sending unit, configured to send each supply source electric power material information request to each electric power material supply source end corresponding to each determined candidate electric power material supply source identification information, so as to obtain a supply source electric power material information group set, wherein In the above-mentioned supply source power material information group, each supply source power material information included in the supply source power material information group set corresponds to the same candidate power material supply source identification information; the generating unit is configured to generate a power material quality evaluation information group set according to the above-mentioned supply source power material information group set; the dispatching unit is configured to determine each target power material supply source identification information according to the above-mentioned power material quality evaluation information group set and each candidate power material supply source identification information, and control each associated dispatching device to dispatch power materials from each target power material supply source corresponding to each target power material supply source identification information to replenish power materials.
[0018] Optionally, the determination unit is further configured to: receive business information of each supply source sent by each power material supply source, wherein the above-mentioned supply source business information includes power material supply source identification information, supply source fixed value information, supply source negative value information, material turnover rate, material delayed turnover rate, material reverse turnover rate and total material turnover volume; input the received business information of each supply source into a pre-trained supply source classification model to obtain each supply source classification label; determine each power material supply source identification information included in each supply source business information corresponding to each supply source classification label that meets the supply source screening condition among the above-mentioned supply source classification labels as each candidate power material supply source identification information.
[0019] Optionally, the device further includes: a first acquisition unit, a division unit, an oversampling unit and a first execution unit. The first acquisition unit is configured to acquire a historical supply source business information set and a historical supply source classification label set, wherein the historical supply source business information in the historical supply source business information set corresponds to the historical supply source classification label in the historical supply source classification label set. The division unit is configured to divide the historical supply source business information set according to the historical supply source classification label set to obtain various supply source business information groups, wherein the classification results represented by the various historical supply source classification labels corresponding to the various supply source business information included in each of the various supply source business information groups are the same. The oversampling unit is configured to perform oversampling processing on the historical supply source business information set in response to determining that the various supply source business information groups meet the oversampling condition, so as to update the historical supply source business information set and the historical supply source classification label set. The first execution unit is configured to perform the following model training steps based on the historical supply source business information set and the historical supply source classification label set: input at least one historical supply source business information in the historical supply source business information set into the initial supply source classification model to obtain a verification supply source classification label corresponding to each historical supply source business information in the at least one historical supply source business information; compare the verification supply source classification label corresponding to each historical supply source business information in the at least one historical supply source business information with the corresponding historical supply source classification label; determine the classification accuracy of the initial supply source classification model based on the comparison result; in response to determining that the classification accuracy is greater than or equal to the preset classification accuracy, determine the initial supply source classification model as the supply source classification model.
[0020] Optionally, the above-mentioned device also includes: an adjustment unit, configured to adjust the initial supply source classification model in response to determining that the classification accuracy is less than the above-mentioned preset classification accuracy, combine unused historical supply source business information into a historical supply source business information set, determine the adjusted initial supply source classification model as the initial supply source classification model, and execute the above-mentioned model training step again.
[0021] Optionally, the supply source power material information in the supply source power material information group set includes: power material type information, power material value information and attribute information of each power material.
[0022] Optionally, the device further includes: a second acquisition unit and a second execution unit. The second acquisition unit is configured to acquire a material evaluation attribute group set and an evaluation attribute weight group set, wherein the material evaluation attribute in the material evaluation attribute group set corresponds to the attribute weight in the evaluation attribute weight group set. The second execution unit is configured to perform the following steps for each supply source power material information group in the supply source power material information group set: according to the power material type information included in the supply source power material information group, select a material evaluation attribute group that meets the material type matching condition from the material evaluation attribute group set as the target material evaluation attribute group; for each supply source power material information in the supply source power material information group, perform the following data cleaning steps: in response to determining that the supply source power material information does not meet the necessary information condition corresponding to the target material evaluation attribute group, remove the supply source power material information from the supply source power material information group set to update the supply source power material information group set; in response to determining that the supply source power material information is semi-structured information or unstructured information, perform structured processing on the supply source power material information.
[0023] Optionally, each of the above-mentioned candidate power material supply source identification information corresponds to a weighting coefficient of each supply source.
[0024] Optionally, the generating unit is further configured to: re-divide the above-mentioned supply source power material information group set according to the power material type information included in each supply source power material information in the above-mentioned supply source power material information group set to update the above-mentioned supply source power material information group set; for each supply source power material information group in the updated supply source power material information group set, perform the following quality evaluation steps: select the power material attribute detection model that meets the above-mentioned material type matching condition from the preset power material attribute evaluation model set as the target material attribute detection model; select the power material attribute detection model that meets the above-mentioned material type matching condition from the above-mentioned evaluation attribute weight group set The attribute weight group is used as the target evaluation attribute weight group; for each supply source power material information in the above-mentioned supply source power material information group, the following steps are performed: the above-mentioned supply source power material information is input into the above-mentioned target material attribute detection model to generate power material attribute detection information; according to the above-mentioned power material attribute detection information, the above-mentioned target evaluation attribute weight group and the supply source weighting coefficient corresponding to the above-mentioned power material attribute detection information, the power material quality evaluation information is generated; each generated power material quality evaluation information is determined as a power material quality evaluation information group; and the determined power material quality evaluation information group is determined as a power material quality evaluation information group set.
[0025] Optionally, the above-mentioned device also includes: a storage unit, configured to store the above-mentioned power material quality evaluation information group set in a pre-constructed power material supply source evaluation information knowledge graph.
[0026] In a third aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device on which one or more programs are stored, and when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation manner of the above-mentioned first aspect.
[0027] In a fourth aspect, some embodiments of the present disclosure provide a computer-readable medium having a computer program stored thereon, wherein when the program is executed by a processor, the method described in any implementation manner of the above-mentioned first aspect is implemented.
[0028] The above-mentioned embodiments of the present disclosure have the following beneficial effects: through the power material replenishment method based on the supply source material quality evaluation of some embodiments of the present disclosure, the frequency of project progress stagnation can be reduced and the safety of the power project can be improved. Specifically, the reason for the frequent stagnation of project progress or the decline in project quality is that the power material is replenished directly from the fixed supply source, lacking consideration of the supply capacity and power material quality of the supply source, resulting in frequent stagnation of project progress due to untimely material supply or a decline in project safety due to the low quality of the power materials provided. Based on this, the power material replenishment method based on the supply source material quality evaluation of some embodiments of the present disclosure, first, in response to the power material replenishment request sent by the target terminal, the request reception number is updated. Among them, the above request reception number is the number of times the power material replenishment request is received. Then, in response to determining that the above request reception number is the preset reception number, the identification information of each candidate power material supply source is determined. Therefore, when the request reception number is the preset acceptance number, each power material supply source can be initially screened to determine the identification information of each candidate power material supply source. Afterwards, each supply source power material information request is sent to each power material supply source end corresponding to each determined candidate power material supply source identification information to obtain a supply source power material information group set. Among them, each supply source power material information included in the supply source power material information group in the above supply source power material information group set corresponds to the same candidate power material supply source identification information. Thus, various types of power material information of each screened power material supply source can be obtained for subsequent power material quality evaluation. Then, according to the above supply source power material information group set, a power material quality evaluation information group set is generated. Thus, different types of power materials can be evaluated one by one through the above supply source power material information group set, power material quality evaluation information is generated, and a power material quality evaluation information group set is obtained. Finally, according to the above power material quality evaluation information group set and the above candidate power material supply source identification information, each target power material supply source identification information is determined, and each associated dispatching device is controlled to dispatch power materials from each target power material supply source corresponding to the above target power material supply source identification information to replenish power materials. Therefore, the power material supply sources corresponding to the identification information of each candidate power material supply source can be screened again through each power material quality evaluation information to determine the identification information of each target power material supply source. And power material dispatch is performed from each target power material supply source corresponding to the identification information of each target power material supply source to complete the power material replenishment.Because the method of screening each power material supply source to determine each candidate power material supply source is adopted, each power material supply source with a predicted material supply delay rate that may be high can be screened out, thereby reducing the frequency of untimely supply of supply sources, thereby reducing the frequency of stagnation of project progress due to material shortages. Then, the quality of different types of power materials at each candidate power material supply source can be evaluated. As a result, each power material supply source whose provided power materials meet the quality conditions can be determined as the target power material supply source, so as to realize the re-screening of each power material supply source, thereby ensuring the quality of power materials in power engineering construction, and then improving the safety of power engineering. BRIEF DESCRIPTION OF THE DRAWINGS
[0029] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that components and elements are not necessarily drawn to scale.
[0030] Figure 1 is a flow chart of some embodiments of a method for replenishing electric power materials based on supply source material quality evaluation according to the present disclosure;
[0031] Figure 2 It is a structural schematic diagram of some embodiments of the power material replenishment device based on the supply source material quality evaluation according to the present disclosure;
[0032] Figure 3 It is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION
[0033] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.
[0034] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present disclosure can be combined with each other.
[0035] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.
[0036] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".
[0037] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.
[0038] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.
[0039] Figure 1 The flowchart 100 of some embodiments of the method for replenishing electric power materials based on the quality evaluation of supply source materials according to the present disclosure is shown. The method for replenishing electric power materials based on the quality evaluation of supply source materials includes the following steps:
[0040] Step 101, in response to a power material replenishment request sent by a target terminal, updating the number of request reception times.
[0041] In some embodiments, in response to receiving a request for replenishment of electric power materials sent by a target terminal, the execution subject (e.g., a computing device) of the method for replenishing electric power materials based on the quality evaluation of supply source materials may update the number of request receptions. The number of request receptions is the number of times requests for replenishment of electric power materials are received. The number of request receptions may be 0 initially. The execution subject may be a service end. The target terminal may be a terminal device for monitoring electric power projects. The request for replenishment of electric power materials may be an interface call request for replenishment of electric power materials. The electric power materials requested for replenishment may include, but are not limited to, at least one of the following: cables, total stations, insulators, voltmeters, transformers, and test pens. In practice, upon receiving a request for replenishment of electric power materials sent by a target terminal, the execution subject may add one to the number of request receptions to update the number of request receptions.
[0042] It should be noted that the above-mentioned computing device can be hardware or software. When the computing device is hardware, it can be implemented as a distributed cluster consisting of multiple servers or terminal devices, or it can be implemented as a single server or a single terminal device. When the computing device is embodied as software, it can be installed in the hardware devices listed above. It can be implemented as multiple software or software modules for providing distributed services, for example, or it can be implemented as a single software or software module. No specific limitation is made here.
[0043] Step 102, in response to determining that the number of request receptions is a preset number of receptions, determining identification information of each candidate power material supply source.
[0044] In some embodiments, the above-mentioned execution subject may determine the identification information of each candidate power material supply source in response to determining that the number of times the above-mentioned request is received is a preset number of times. The above-mentioned candidate power material supply source identification information may be the power material supply source identification information of the screened power material supply source. The above-mentioned power material supply source identification information may be a character string representing the corresponding power material supply source. In practice, first, the above-mentioned execution subject may receive the material turnover rate and the power material supply source identification information sent by each power material supply source. Then, the above-mentioned execution subject may determine the identification information of each power material supply source corresponding to each material turnover rate that is greater than or equal to the preset turnover rate as the candidate power material supply source identification information.
[0045] As an example, the above preset number of receiving times may be 1.
[0046] In some optional implementations of some embodiments, the above-mentioned execution subject may determine the identification information of each candidate power material supply source through the following steps:
[0047] The first step is to receive the business information of each supply source sent by each power material supply source. Among them, the supply source business information may include power material supply source identification information, supply source fixed value information, supply source negative value information, material turnover rate, material delayed turnover rate, material reverse turnover rate and total material turnover. The above-mentioned power material supply source ends may be the terminal devices corresponding to each power material supply source. The above-mentioned power material supply sources may be each power material supply organization. Each supply source business information in the above-mentioned supply source business information may be the information of the relevant business of the corresponding power material supply source. The above-mentioned supply source fixed value information may be the fixed value (gross production value) of the corresponding power material supply source. The above-mentioned supply source negative value information may be the negative value (total liabilities) of the corresponding power material supply source. The above-mentioned material turnover rate may be the average turnover rate (average supply and marketing rate) of various types of power materials of the corresponding power material supply source. The above-mentioned material delayed turnover rate may be the average delayed turnover rate (average delayed supply rate) of various types of power materials of the corresponding power material supply source. The reverse material circulation rate may be the average reverse material circulation rate (average return rate) of various types of power materials of the corresponding power material supply source. The total material circulation volume may be the total circulation volume (total sales volume) of various types of power materials of the corresponding power material supply source.
[0048] In the second step, the received business information of each supply source is input into a pre-trained supply source classification model to obtain classification labels for each supply source. The supply source classification model may be a neural network model that takes the supply source business information as input and the supply source classification label as output and is used to perform classification tasks. The supply source classification label may be a label that characterizes the material supply capacity of the corresponding power material supply source. For example, the supply source classification label may include "strong material supply capacity", "relatively strong material supply capacity", "average material supply capacity", "relatively weak material supply capacity" and "weak material supply capacity". Supply source classification labels that characterize different classification results correspond to different supply source weighting coefficients. The supply source weighting coefficients may be used to evaluate the quality of various types of power materials of the corresponding power material supply source.
[0049] As an example, the supply source classification model may be a GAT (Graph Attention Network) model or a GAN (Generative Adversarial Networks) model.
[0050] In the third step, each power material supply source identification information included in each supply source business information corresponding to each supply source classification label that meets the supply source screening condition among the above-mentioned supply source classification labels is determined as each candidate power material supply source identification information. The above-mentioned supply source screening condition may be that the obtained supply source classification label is the same as a target classification label in a preset target classification label set. For example, the above-mentioned preset target classification label set may be ("strong material supply capacity", "relatively strong material supply capacity", "average material supply capacity"). Thus, each power material supply source can be screened according to its business information to ensure that each supply source can supply power materials in a timely manner.
[0051] Optionally, the supply source classification model can be trained through the following steps:
[0052] The first step is to obtain a historical supply source business information set and a historical supply source classification label set. The historical supply source business information in the historical supply source business information set corresponds to the historical supply source classification label in the historical supply source classification label set. In practice, the execution subject can obtain the historical supply source business information set and the historical supply source classification label set from a target database. The target database can be a database corresponding to the execution subject.
[0053] The second step is to divide the above-mentioned historical supply source business information set according to the above-mentioned historical supply source classification label set to obtain various supply source business information groups. Among them, the classification results represented by the various historical supply source classification labels corresponding to the various supply source business information included in each supply source business information group are the same. In practice, the above-mentioned execution entity can divide the various historical supply source business information corresponding to the various historical supply source classification labels representing the same classification results into the same supply source business information group according to the classification results represented by the historical supply source classification labels corresponding to each historical supply source business information in the above-mentioned historical supply source business information set, to obtain various supply source business information groups.
[0054] In the third step, in response to determining that each of the above-mentioned supply source business information groups meets the oversampling condition, the above-mentioned historical supply source business information set is oversampled to update the above-mentioned historical supply source business information set and the historical supply source classification label set. The above-mentioned oversampling condition may be that the difference in the number of supply source business information between the supply source business information group with the largest number of supply source business information and the supply source business information group with the smallest number of supply source business information among the above-mentioned supply source business information groups is greater than a preset difference. In practice, the above-mentioned execution subject may oversample the above-mentioned historical supply source business information set through an oversampling algorithm so that the information quantity difference between the above-mentioned each supply source business information group is less than or equal to the above-mentioned preset difference.
[0055] As an example, the above oversampling algorithm may be a BorderLine-SMOTE algorithm or a SMOTE-Tomek algorithm.
[0056] Step 4: Based on the historical supply source business information set and the historical supply source classification label set, perform the following model training steps:
[0057] In a first sub-step, at least one historical supply source business information in the historical supply source business information set is input into an initial supply source classification model to obtain a verification supply source classification label corresponding to each historical supply source business information in the at least one historical supply source business information.
[0058] The second sub-step is to compare the verification supply source classification label corresponding to each historical supply source business information in the at least one historical supply source business information with the corresponding historical supply source classification label. In practice, the execution subject may compare the verification supply source classification label corresponding to each historical supply source business information in the at least one historical supply source business information with the corresponding historical supply source classification label to determine whether the classification results represented by the two labels are the same.
[0059] The third sub-step is to determine the classification accuracy of the initial supply source classification model based on the comparison result. In practice, the execution entity may determine the classification accuracy of the initial supply source classification model as the sum of the number of historical supply source business information with the same classification result in the at least one historical supply source business information and the number of historical supply source business information input into the initial supply source classification model.
[0060] In a fourth sub-step, in response to determining that the classification accuracy is greater than or equal to a preset classification accuracy, the initial supply source classification model is determined as the supply source classification model.
[0061] Optionally, the model training step may further include the following steps: in response to determining that the classification accuracy is less than the preset classification accuracy, adjusting the initial supply source classification model, forming a historical supply source business information set with unused historical supply source business information, determining the adjusted initial supply source classification model as the initial supply source classification model, and performing the model training step again. In practice, the initial supply source classification model may be adjusted by adjusting the model parameters of the initial supply source classification model using a back propagation algorithm and a gradient descent algorithm.
[0062] Step 103 : sending power material information requests of respective supply sources to respective power material supply source terminals corresponding to respective determined identification information of respective candidate power material supply sources, so as to obtain a set of power material information groups of the supply sources.
[0063] In some embodiments, the execution subject may send each supply source power material information request to each power material supply source end corresponding to each determined candidate power material supply source identification information to obtain a supply source power material information group set. The supply source power material information request may be a request to obtain a supply source power material information group. Each supply source power material information included in the supply source power material information group in the supply source power material information group set corresponds to the same candidate power material supply source identification information. The supply source power material information in the supply source power material information group set may include: power material type information, power material value information and each power material attribute information. The power material type information may be a character string representing the power material type. The power material value information may be the unit price of the corresponding power material. The each power material attribute information may represent each physical property of the corresponding power material. For example, the power material type information included in one supply source power material information in the supply source power material information group set may be "EE-1001", and the power material type represented may be "cable". The power material attribute information included in the above-mentioned power material information of the supply source may be ("material ratio (insulating material / conductor material)": 0.85), ("wear index": 0.12), ("bending radius": 30) and ("tensile strength": 30). The above-mentioned power material attribute information corresponds to various default units, which will not be repeated here.
[0064] Step 104: Generate an electric power material quality evaluation information group set according to the supply source electric power material information group set.
[0065] In some embodiments, the execution entity may generate a power material quality evaluation information group set according to the supply source power material information group set. Each power material quality rating information group in the power material quality rating information group set may correspond to a different power material type. The power material quality rating information in the power material quality rating information group set may be a quality evaluation score.
[0066] Optionally, before generating the power material quality evaluation information group set according to the supply source power material information group set, the execution subject may further perform the following steps:
[0067] The first step is to obtain a material evaluation attribute group set and an evaluation attribute weight group set. Among them, the material evaluation attributes in the above material evaluation attribute group set correspond to the attribute weights in the above evaluation attribute weight group set. Each material evaluation attribute group in the above material evaluation attribute group set can represent a set of evaluation dimensions for quality evaluation of the corresponding power material. Each evaluation attribute weight in each evaluation attribute weight group in the above evaluation attribute weight group set can be the weight of each material evaluation attribute in the corresponding material evaluation attribute group, so as to represent the degree of influence of the corresponding material evaluation attribute on the material quality. For example, a material evaluation attribute group in the above material evaluation attribute group set can be ("EE-1001", "wear index", "bending radius", "material ratio"), which represents the quality evaluation of the cable from the three evaluation dimensions of wear index, bending radius and material ratio. An evaluation attribute weight group corresponding to the above material evaluation attribute group in the above evaluation attribute weight group set can be ("EE-1001", "wear index": 0.29, "bending radius": 0.41, "material ratio": 0.3). Therefore, by configuring different material evaluation attribute groups and different evaluation attribute weight groups, it is possible to implement biased quality evaluation of the same type of power materials in different power project scenarios, thereby improving the applicability of power material quality evaluation.
[0068] In the second step, for each supply source power material information group in the above supply source power material information group set, the following steps are performed:
[0069] In a first sub-step, according to the power material type information included in the power material information group of the supply source, a material evaluation attribute group that satisfies a material type matching condition is selected from the material evaluation attribute group set as a target material evaluation attribute group. The material type matching condition may be that the power material type corresponding to the material evaluation attribute group in the material evaluation attribute group set is the same as the power material type represented by the power material type information included in the power material information group of the supply source.
[0070] In the second sub-step, for each supply source power material information in the supply source power material information group, the following data cleaning steps are performed:
[0071] Sub-step 1: In response to determining that the supply source power material information does not meet the necessary information condition corresponding to the target material evaluation attribute group, the supply source power material information is removed from the supply source power material information group set to update the supply source power material information group set. The necessary information condition may be that the supply source power material information does not lack each power material attribute information corresponding to each target material evaluation attribute in the target material evaluation attribute group. For example, the target material evaluation attribute group may be ("EE-1001", "wear index", "bending radius", "material ratio"), and each power material attribute information in the supply source power material information may be ("material ratio (insulating material / conductor material)": 0.85), ("wear index": 0.12), ("tensile strength": 30), and the execution subject may determine that the supply source power material information does not meet the necessary information condition corresponding to the target material evaluation attribute group by determining that the supply source power material information lacks the power material attribute information corresponding to the "bending radius" in the target material evaluation attribute group.
[0072] Sub-step two, in response to determining that the above-mentioned supply source power material information is semi-structured information or unstructured information, the above-mentioned supply source power material information is structured. In practice, first, the above-mentioned execution subject can determine that the above-mentioned supply source power material information is unstructured data or semi-structured data according to the format of the above-mentioned supply source power material information. Then, the above-mentioned execution subject can convert the semi-structured data into structured data by extracting JSON attributes as fields or extracting XML tags as fields. The above-mentioned execution subject can convert unstructured data into structured data through a natural language processing library (such as the Stanford CoreNLP library or the NTLK library).
[0073] In some optional implementations of some embodiments, the execution subject may generate the power material quality evaluation information group set according to the supply source power material information group set through the following steps:
[0074] The first step is to re-divide the above supply source power material information group set according to the power material type information included in each supply source power material information in the above supply source power material information group set to update the above supply source power material information group set. In practice, the above execution entity can re-divide each supply source power material information including the same power material type information into the same group according to the power material type information included in each supply source power material information in the above supply source power material information group set to update the above supply source power material information group set.
[0075] In the second step, for each supply source power material information group in the updated supply source power material information group set, the following quality evaluation steps are performed:
[0076] In the first sub-step, a power material attribute detection model that satisfies the above-mentioned material type matching condition is selected from a preset power material attribute evaluation model set as a target material attribute detection model. Each power material attribute evaluation model in the above-mentioned power material attribute evaluation model set corresponds to power material type information to characterize the type of power material for quality evaluation. The above-mentioned material type matching condition may be that the power material type information corresponding to the power material attribute evaluation model is the same as the power material type information included in the above-mentioned supply source power material information group. The power material attribute evaluation model in the above-mentioned power material attribute evaluation model set may be a classification model that takes the supply source power material information as input and takes the power material attribute detection information as output.
[0077] In the second sub-step, an evaluation attribute weight group that satisfies the material type matching condition is selected from the evaluation attribute weight group set as a target evaluation attribute weight group. The material type matching condition may be that the power material type corresponding to the evaluation attribute weight group in the evaluation attribute weight group set is the same as the power material type represented by the power material type information included in the supply source power material information group.
[0078] The third sub-step is to perform the following steps for each supply source power material information in the supply source power material information group:
[0079] Sub-step 1: Input the above-mentioned supply source power material information into the above-mentioned target material attribute detection model to generate power material attribute detection information. The above-mentioned target material attribute detection model can compare the value of the power material value information included in the input supply source power material information with the value of each preset power material value information in the preset power material value information table in turn to determine whether the above-mentioned input power material value information is equal to the preset power material value information in the above-mentioned preset power material value information table. The above-mentioned target material attribute detection model can also compare each power material attribute information in each power material attribute information included in the above-mentioned input supply source power material information with each power material attribute information in the corresponding preset power material attribute information table in turn to determine whether each input power material attribute information is the same as the power material attribute information in the corresponding preset power material attribute information table. The above-mentioned preset power material value information table can be established based on a preset power material value information sequence. The above-mentioned preset power material value information sequence can be obtained by sorting each preset power material value information. Each preset power material value information in each preset power material value information in the above-mentioned preset power material value information table corresponds to a preset evaluation score. In practice, the target material attribute detection model may determine the preset evaluation score corresponding to the preset power material value information equal to the input power material value information in the preset power material value information table as the value evaluation score. The preset power material attribute information table may be created based on the preset power material attribute information sequence. The preset power material attribute information sequence may be obtained by sorting each preset power material attribute information. In practice, the target material attribute detection model may determine the preset evaluation score corresponding to the preset power material attribute information equal to the power material attribute information in the corresponding preset power material attribute information table as the attribute evaluation score. The power material attribute detection information may be composed of the determined value evaluation score and each attribute evaluation score. For example, the power material type information that may be included in the power material information input into the target power material attribute detection model may be "EE-1001". The type of power material represented may be a cable. The power material attribute detection information may be ("power material value": a1, "wear index": a2, "bending radius": a3, "material ratio": a4), and the a1 may be the determined value evaluation score. The above a2, a3 and a4 may be corresponding attribute evaluation scores.
[0080] Sub-step 2: Generate power material quality evaluation information based on the power material attribute detection information, the target evaluation attribute weight group and the supply source weight coefficient corresponding to the power material attribute detection information. In practice, first, the execution entity may determine the product of each evaluation score in the power material attribute detection information and the target evaluation attribute weight corresponding to the evaluation score in the target evaluation attribute weight group as a quality score. Then, the product of the sum of the quality scores and the supply source weight coefficient may be determined as the power material quality score as the power material quality evaluation information.
[0081] It should be noted that the above-mentioned power material attribute detection information corresponds to the candidate power material supply source identification information. The candidate power material supply source identification information corresponds to the supply source classification label, and the supply source classification label corresponds to the supply source weighting coefficient.
[0082] The fourth sub-step is to determine the generated individual electric power material quality evaluation information as an electric power material quality evaluation information group.
[0083] The third step is to determine the determined electric power material quality evaluation information group as an electric power material quality evaluation information group set.
[0084] Optionally, the above quality evaluation step may further include the following steps:
[0085] The first step is, in response to determining that the power material type information included in the supply source power material information group is the same as one of the target power material type information in the target power material type information set, sending each power material appearance image request to each candidate power material supply source corresponding to each supply source power material information included in the supply source power material information group, so as to obtain each power material appearance image set. The power material image request includes the power material type information included in the supply source power material information group. The above-mentioned candidate power material supply sources are each power material supply source corresponding to each candidate power material supply source identification information. Each target power material type information in the target power material type information set may be power material type information corresponding to different types of power materials that need to be inspected for appearance. The power material appearance image request may be a request for obtaining a power material appearance image. Each power material appearance image set in the above-mentioned power material appearance image set may be sent by the power material supply source corresponding to the corresponding candidate power material supply source identification information. Each power material type represented by each target power material type information in the target power material type information set may include a cable, a transformer, an insulator and a voltmeter.
[0086] The second step is to obtain an electric material appearance defect feature extraction model corresponding to the electric material type information included in the above-mentioned supply source electric material information group and an appearance defect feature information set corresponding to the electric material type information included in the above-mentioned supply source electric material information group. The above-mentioned corresponding electric material appearance defect feature extraction model may be a neural network model for extracting appearance defect features of the corresponding electric material. The above-mentioned corresponding appearance defect feature information set may be an electric material appearance defect feature vector set of the corresponding electric material. For example, the electric material type information included in the above-mentioned supply source electric material information group may be "EE-1001", and the electric material appearance defect feature extraction model corresponding to the above-mentioned electric material type information may be a cable appearance defect feature extraction model. The appearance defect feature information set corresponding to the above-mentioned electric material type information may be a cable appearance defect feature vector set.
[0087] In the third step, for each set of electric power material appearance images in the received sets of electric power material appearance images, the following steps are performed:
[0088] In the first sub-step, for each electric material appearance image in the electric material appearance image set, the following appearance defect detection steps are performed:
[0089] Sub-step 1: Perform image enhancement on the electric power material appearance image to obtain an enhanced electric power material appearance image. In practice, the execution subject may perform image enhancement on the electric power material appearance image by using an image enhancement algorithm.
[0090] As an example, the above image enhancement algorithm may be a CLAHE (Contrast Limited Adaptive Histogram Equalization) algorithm.
[0091] Sub-step 2: performing region segmentation processing on the enhanced electric power material appearance image to generate a mask image. In practice, the execution subject may perform region segmentation processing on the enhanced electric power material appearance image using a pre-trained image segmentation model to generate a mask image.
[0092] As an example, the above image segmentation model may be a DeepLab v3 model or a U-Net++ model.
[0093] Sub-step three, perform morphological denoising on the mask image to obtain a denoised mask image. In practice, first, the execution subject can perform erosion on the mask image using methods in related library functions (e.g., cv2.erode() function). Then, the processed mask image can be expanded using methods in related library functions (e.g., cv2.dilate()) to complete the morphological denoising.
[0094] Sub-step 4: edge detection is performed on the denoised mask image to generate the contour information of the power material. In practice, the execution subject can perform edge detection on the denoised mask image through methods in related library functions (such as cv2.findContours()), and use the returned contour coordinate point set as the contour information of the power material.
[0095] Sub-step 5: cropping the electric power material appearance image according to the electric power material contour information to obtain a target area image. In practice, the execution subject may crop the electric power material appearance image according to the electric power material contour information to obtain a target area image.
[0096] Sub-step six: input the target area image into the power material appearance defect feature extraction model to generate material appearance feature information. The material appearance feature information may be a feature vector characterizing the appearance of the power material in the corresponding target area image. The power material appearance defect feature extraction model may be a neural network model that takes the target area image as input and the material appearance feature information as output.
[0097] As an example, the above-mentioned power material appearance defect feature extraction model can be a dense neural network model or a residual neural network model.
[0098] Sub-step seven, generating an appearance defect detection result based on the above-mentioned material appearance feature information and the above-mentioned appearance defect feature information set. In practice, first, the above-mentioned execution subject can determine the feature similarity between the above-mentioned material appearance feature information and each appearance defect feature information in the above-mentioned appearance defect feature information set through a similarity algorithm. Then, in response to determining that there is at least one feature similarity greater than or equal to a preset similarity among the various feature similarities, the above-mentioned execution subject can determine the appearance defect detection result as indicating that the corresponding power material has an appearance defect.
[0099] As an example, the similarity algorithm may be a cosine similarity algorithm.
[0100] The second sub-step is to generate an appearance defect rate based on each appearance defect detection result generated. In practice, the above-mentioned execution entity can determine the appearance defect rate as the ratio of the number of appearance defect detection results that indicate that the corresponding power material has no defects in appearance to the total number of appearance defect detection results generated.
[0101] The third sub-step is to add the appearance defect rate to the corresponding power material attribute detection information to update the corresponding power material attribute detection information. In practice, the execution subject may insert the appearance defect rate into the power material attribute detection information that is identical to the candidate power material supply source identification information corresponding to the material appearance image set.
[0102] The first to third steps mentioned above are an inventive point of an embodiment of the present disclosure, which solves the technical problem 2 mentioned in the background technology, "directly replenishing power materials from a fixed supply source, lacking consideration of the supply capacity and quality of the supply source, resulting in frequent stagnation of project progress due to untimely supply of materials or reduced project safety due to low quality of the power materials provided". The factors that lead to reduced safety of power projects are often as follows: directly replenishing power materials from a fixed supply source, lacking consideration of the supply capacity and quality of the supply source, resulting in frequent stagnation of project progress due to untimely supply of materials or reduced project safety due to low quality of the power materials provided. If the above factors are solved, the reduction in project safety caused by the reduction in the quality of the supplemented power materials can be avoided as much as possible. In order to achieve this effect, the present disclosure introduces a power material appearance defect feature extraction model and an appearance defect feature information set. First, a material appearance image set of various types of power materials that need to be inspected can be obtained from each candidate power material supply source corresponding to the identification information of each candidate power material supply source. Then, each appearance image of each type of power material can be preprocessed to obtain a target area image. Thus, the influence of redundant image information on subsequent appearance feature extraction can be reduced. Afterwards, the feature information of the appearance of the power materials in the target area image is extracted through the corresponding power material appearance defect feature extraction model to obtain the material appearance feature information. Then, the appearance defect detection result can be determined by the above-mentioned material appearance feature information and the above-mentioned preset appearance defect feature information set. Thus, the appearance of power materials can be detected through feature extraction and the preset appearance defect feature information set, reducing the large amount of calculation and long processing time brought by the complex defect recognition model. Therefore, the appearance of some power materials can be quickly detected through the above-mentioned power material appearance defect feature extraction model and the preset appearance defect feature information set, reducing the decline in project safety caused by the decline in the quality of the supplemented power materials, thereby providing the safety of the project.
[0103] Step 105, according to the electric power material quality evaluation information group set and the identification information of each candidate electric power material supply source, determine the identification information of each target electric power material supply source, and control the associated dispatching equipment to dispatch electric power materials from each target electric power material supply source corresponding to the identification information of each target electric power material supply source to replenish electric power materials.
[0104] In some embodiments, the above-mentioned execution entity can determine the identification information of each target power material supply source based on the power material quality evaluation information group set and the identification information of each candidate power material supply source, and control the associated dispatching equipment to dispatch power materials from each target power material supply source corresponding to the identification information of each target power material supply source to replenish power materials.
[0105] In some optional implementations of some embodiments, the above-mentioned execution subject may determine the identification information of each target power material supply source according to the power material quality evaluation information group set and the identification information of each candidate power material supply source through the following steps, and control each associated dispatching device to dispatch power materials from each target power material supply source corresponding to each target power material supply source identification information to replenish power materials:
[0106] The first step is to obtain each power material inventory record from the power material database. Among them, each of the above-mentioned power material inventory records is an inventory record of different types of power materials. The above-mentioned power material database may be a database that stores data related to power materials. Each of the above-mentioned power material inventory records may represent the inventory of the corresponding power material at different times. For example, an power material inventory record may be ("EE-1001", "2023-07-01":96, "2023-07-01":61, "2023-09-01":20), and each inventory quantity corresponds to an inventory unit, which will not be repeated here.
[0107] In the second step, based on each power material quality evaluation information group in the above power material quality evaluation information group set, the following steps are performed:
[0108] In a first sub-step, according to the power material type information included in the power material quality evaluation information group, a power material inventory record that meets the material type matching condition is selected from the above-mentioned power material inventory records as a target power material inventory record. The above-mentioned material type matching condition may be that the power material type information included in the power material quality evaluation information group is the same as the power material type information included in the power material inventory record.
[0109] The second sub-step is to determine the material consumption rate based on the above-mentioned target power material inventory record. In practice, the above-mentioned execution entity can determine the material consumption rate as the ratio of the time distance between the last two time points in the above-mentioned target power material inventory record (in days by default) and the difference between the two corresponding material inventory quantities. For example, the last two time points and the corresponding material inventory quantities in the above-mentioned target power material inventory record are ("2023-07-01": 61) and ("2023-09-01": 20), respectively. The determined material consumption rate can be (61-20) / 62=0.66 (km / day).
[0110] It should be noted that when determining the material consumption rate, two decimal places are retained by default and rounding is not used.
[0111] The third sub-step is to sort the individual power material quality evaluation information in the above power material quality evaluation information group to obtain a power material quality evaluation information sequence. In practice, the above-mentioned execution entity can sort the individual power material quality evaluation information in the above power material quality evaluation information group from large to small according to the numerical value to obtain a power material quality evaluation information sequence.
[0112] In a fourth sub-step, the candidate electric material supply source identification information corresponding to the first electric material quality evaluation information in the electric material quality evaluation information sequence is determined as the target electric material supply source identification information.
[0113] The fifth sub-step is to determine the material replenishment quantity according to the above-mentioned target power material inventory record and the above-mentioned material consumption rate. In practice, first, the above-mentioned execution entity may determine the difference between the material inventory quantity corresponding to the last time point in the above-mentioned target power material inventory record and the material inventory quantity corresponding to the first time point in the above-mentioned target power material inventory record as the first material replenishment quantity. Then, the above-mentioned execution entity may determine the product of the above-mentioned material consumption rate and the preset scheduling time as the second material replenishment quantity. Finally, the above-mentioned execution entity may determine the sum of the first material replenishment quantity and the second material replenishment quantity as the material replenishment quantity.
[0114] The sixth sub-step is to control the associated dispatching device to dispatch the target power material corresponding to the power material type information included in the power material quality evaluation information group from the target power material supply source corresponding to the target power material supply source identification information. The quantity of the dispatched target power material is the same as the replenishment quantity of the material. The dispatching device can be an AVG (Automated Guided Vehicle) dispatching vehicle.
[0115] The first and second steps mentioned above are an inventive point of an embodiment of the present disclosure, which solves the technical problem three mentioned in the background technology, "directly replenishing materials according to the current lack of power materials, without considering the consumption of materials by the project during the replenishment period, resulting in insufficient replenished power materials, which leads to the need to replenish materials again and wastes transportation resources". The factors that lead to waste of transportation resources are often as follows: directly replenishing materials according to the current lack of power materials, without considering the consumption of materials by the project during the replenishment period, resulting in insufficient replenished power materials, which leads to the need to replenish materials again and wastes transportation resources. If the above factors are solved, the effect of reducing the waste of transportation resources can be achieved. In order to achieve this effect, the present disclosure can obtain each power material inventory record from the power material database. Then, the material consumption rate of each type of power material can be determined through the above-mentioned each power material inventory record. After that, the additional consumption of each type of power material during the replenishment period can be predicted through each material consumption rate and scheduling time. Finally, the additional material consumption and the material shortage can be added as the final scheduling quantity of this type of power material. Therefore, the additional consumption of materials by the project during the replenishment period can be taken into account, which can effectively reduce the frequency of insufficient replenished power materials, thereby reducing the number of times that materials need to be replenished again, and further reducing the waste of transportation resources.
[0116] Optionally, the above-mentioned execution entity may also store the above-mentioned electric power material quality evaluation information group set into a pre-constructed electric power material supply source evaluation information knowledge graph. The above-mentioned electric power material supply source evaluation information knowledge graph may be a knowledge graph constructed based on the electric power material supply source evaluation information. The above-mentioned electric power material supply source evaluation information knowledge graph may be stored in a graph database. In practice, for each electric power material quality evaluation information in the above-mentioned electric power material quality evaluation information group set, the above-mentioned execution entity may use the electric power material type information corresponding to the above-mentioned electric power material quality evaluation information as the first entity, and the candidate electric power material supply source identification information corresponding to the above-mentioned electric power material quality evaluation information as the second entity, and store the above-mentioned electric power material quality evaluation information as an entity relationship in the electric power material supply source evaluation information knowledge graph.
[0117] The above-mentioned embodiments of the present disclosure have the following beneficial effects: through the power material replenishment method based on the supply source material quality evaluation of some embodiments of the present disclosure, the frequency of project progress stagnation can be reduced and the safety of the power project can be improved. Specifically, the reason for the frequent stagnation of project progress or the decline in project quality is that the power material is replenished directly from the fixed supply source, lacking consideration of the supply capacity and power material quality of the supply source, resulting in frequent stagnation of project progress caused by untimely material supply or a decline in project safety caused by the low quality of the power materials provided. Based on this, the power material replenishment method based on the supply source material quality evaluation of some embodiments of the present disclosure, first, in response to receiving the power material replenishment request sent by the target terminal, the request reception number is updated. Among them, the above request reception number is the number of times the power material replenishment request is received. Then, in response to determining that the above request reception number is the preset reception number, the identification information of each candidate power material supply source is determined. Therefore, when the request reception number is the preset acceptance number, each power material supply source can be initially screened to determine the identification information of each candidate power material supply source. Afterwards, each supply source power material information request is sent to each power material supply source end corresponding to each determined candidate power material supply source identification information to obtain a supply source power material information group set. Among them, each supply source power material information included in the supply source power material information group in the above supply source power material information group set corresponds to the same candidate power material supply source identification information. Thus, various types of power material information of each screened power material supply source can be obtained for subsequent power material quality evaluation. Then, according to the above supply source power material information group set, a power material quality evaluation information group set is generated. Thus, different types of power materials can be evaluated one by one through the above supply source power material information group set, power material quality evaluation information is generated, and a power material quality evaluation information group set is obtained. Finally, according to the above power material quality evaluation information group set and the above candidate power material supply source identification information, each target power material supply source identification information is determined, and each associated dispatching device is controlled to dispatch power materials from each target power material supply source corresponding to the above target power material supply source identification information to replenish power materials. Therefore, the power material supply sources corresponding to the identification information of each candidate power material supply source can be screened again through each power material quality evaluation information to determine the identification information of each target power material supply source. And power material dispatch is performed from each target power material supply source corresponding to the identification information of each target power material supply source to complete the power material replenishment.Because the method of screening each power material supply source to determine each candidate power material supply source is adopted, each power material supply source with a predicted material supply delay rate that may be high can be screened out, thereby reducing the frequency of untimely supply of supply sources, thereby reducing the frequency of stagnation of project progress due to material shortages. Then, the quality of different types of power materials at each candidate power material supply source can be evaluated. As a result, each power material supply source whose provided power materials meet the quality conditions can be determined as the target power material supply source, so as to realize the re-screening of each power material supply source, thereby ensuring the quality of power materials in power engineering construction, and then improving the safety of power engineering.
[0118] Further references Figure 2 As an implementation of the methods shown in the figures, the present disclosure provides some embodiments of a power material replenishment device based on the supply source material quality evaluation. These device embodiments are similar to Figure 1 Corresponding to the method embodiments shown, the device can be specifically applied to various electronic devices.
[0119] like Figure 2 As shown, some embodiments of the power material replenishment device 200 based on supply source material quality evaluation include: an updating unit 201, a determining unit 202, a sending unit 203, a generating unit 204 and a scheduling unit 205. The updating unit 201 is configured to update the number of request receptions in response to the power material replenishment request sent by the target terminal, wherein the above-mentioned request reception number is the number of times the power material replenishment request is received; the determining unit 202 is configured to determine the identification information of each candidate power material supply source in response to determining that the above-mentioned request reception number is a preset reception number; the sending unit 203 is configured to send each supply source power material information request to each power material supply source end corresponding to each determined candidate power material supply source identification information, so as to obtain a supply source power material information group set, wherein the supply source in the above-mentioned supply source power material information group set is The power material information group includes power material information of each supply source corresponding to the same candidate power material supply source identification information; the generation unit 204 is configured to generate a power material quality evaluation information group set based on the above-mentioned supply source power material information group set; the scheduling unit 205 is configured to determine the identification information of each target power material supply source based on the above-mentioned power material quality evaluation information group set and the above-mentioned candidate power material supply source identification information, and control the associated scheduling equipment to perform power material scheduling from each target power material supply source corresponding to the above-mentioned target power material supply source identification information to replenish power materials.
[0120] In some optional implementations of some embodiments, the determination unit 202 may be further configured to: receive business information of each supply source sent by each power material supply source, wherein the above-mentioned supply source business information includes power material supply source identification information, supply source fixed value information, supply source negative value information, material turnover rate, material delayed turnover rate, material reverse turnover rate and total material turnover volume; input the received business information of each supply source into a pre-trained supply source classification model to obtain classification labels of each supply source; determine the identification information of each power material supply source included in the business information of each supply source that meets the supply source screening conditions in the above-mentioned each supply source classification label as the identification information of each candidate power material supply source.
[0121] In some optional implementations of some embodiments, the above-mentioned power material replenishment device 200 based on the supply source material quality evaluation may further include: a first acquisition unit, a division unit, an oversampling unit and a first execution unit (not shown in the figure). The first acquisition unit is configured to acquire a historical supply source business information set and a historical supply source classification label set, wherein the historical supply source business information in the above-mentioned historical supply source business information set corresponds to the historical supply source classification label in the above-mentioned historical supply source classification label set. The division unit is configured to divide the above-mentioned historical supply source business information set according to the above-mentioned historical supply source classification label set to obtain various supply source business information groups, wherein the classification results represented by the various historical supply source classification labels corresponding to the various supply source business information included in each of the above-mentioned various supply source business information groups are the same. The oversampling unit is configured to perform oversampling processing on the above-mentioned historical supply source business information set in response to determining that the above-mentioned various supply source business information groups meet the oversampling condition, so as to update the above-mentioned historical supply source business information set and the historical supply source classification label set. The first execution unit is configured to perform the following model training steps based on a historical supply source business information set and a historical supply source classification label set: input at least one historical supply source business information in the historical supply source business information set into an initial supply source classification model to obtain a verification supply source classification label corresponding to each historical supply source business information in the at least one historical supply source business information; compare the verification supply source classification label corresponding to each historical supply source business information in the at least one historical supply source business information with the corresponding historical supply source classification label; determine the classification accuracy of the initial supply source classification model based on the comparison result; in response to determining that the classification accuracy is greater than or equal to a preset classification accuracy, determine the initial supply source classification model as the supply source classification model.
[0122] In some optional implementations of some embodiments, the above-mentioned power material replenishment device 200 based on supply source material quality evaluation may also include: an adjustment unit (not shown in the figure), which is configured to adjust the initial supply source classification model in response to determining that the classification accuracy is less than the above-mentioned preset classification accuracy, and form a historical supply source business information set with unused historical supply source business information, determine the adjusted initial supply source classification model as the initial supply source classification model, and execute the above-mentioned model training step again.
[0123] In some optional implementations of some embodiments, the supply source power material information in the above supply source power material information group set includes: power material type information, power material value information and attribute information of each power material.
[0124] In some optional implementations of some embodiments, the above-mentioned power material replenishment device 200 based on the supply source material quality evaluation may further include: a second acquisition unit and a second execution unit (not shown in the figure). The second acquisition unit is configured to acquire a material evaluation attribute group set and an evaluation attribute weight group set, wherein the material evaluation attribute in the above-mentioned material evaluation attribute group set corresponds to the attribute weight in the above-mentioned evaluation attribute weight group set. The second execution unit is configured to perform the following steps for each supply source power material information group in the above-mentioned supply source power material information group set: according to the power material type information included in the above-mentioned supply source power material information group, select the material evaluation attribute group that meets the material type matching condition from the above-mentioned material evaluation attribute group set as the target material evaluation attribute group; for each supply source power material information in the above-mentioned supply source power material information group, perform the following data cleaning steps: in response to determining that the above-mentioned supply source power material information does not meet the necessary information conditions corresponding to the above-mentioned target material evaluation attribute group, remove the above-mentioned supply source power material information from the above-mentioned supply source power material information group set to update the above-mentioned supply source power material information group set; in response to determining that the above-mentioned supply source power material information is semi-structured information or unstructured information, structure the above-mentioned supply source power material information.
[0125] In some optional implementations of some embodiments, each of the candidate power material supply source identification information corresponds to a weighting coefficient of each supply source.
[0126] In some optional implementations of some embodiments, the generation unit 204 may be further configured to: re-divide the supply source power material information group set according to the power material type information included in each supply source power material information in the supply source power material information group set to update the supply source power material information group set; for each supply source power material information group in the updated supply source power material information group set, perform the following quality evaluation steps: select a power material attribute detection model that meets the above-mentioned material type matching condition from a preset power material attribute evaluation model set as a target material attribute detection model; select a power material attribute detection model that meets the above-mentioned material type matching condition from the above-mentioned evaluation attribute weight group set. The material type matching condition evaluation attribute weight group is used as the target evaluation attribute weight group; for each supply source power material information in the above-mentioned supply source power material information group, the following steps are performed: the above-mentioned supply source power material information is input into the above-mentioned target material attribute detection model to generate power material attribute detection information; according to the above-mentioned power material attribute detection information, the above-mentioned target evaluation attribute weight group and the supply source weighting coefficient corresponding to the above-mentioned power material attribute detection information, the power material quality evaluation information is generated; each generated power material quality evaluation information is determined as a power material quality evaluation information group; and the determined power material quality evaluation information group is determined as a power material quality evaluation information group set.
[0127] In some optional implementations of some embodiments, the above-mentioned power material replenishment device 200 based on supply source material quality evaluation may also include: a storage unit (not shown in the figure), configured to store the above-mentioned power material quality evaluation information group set in a pre-constructed power material supply source evaluation information knowledge graph.
[0128] It is understood that the units described in the device 200 are similar to those described in the reference Figure 1 Therefore, the operations, features and beneficial effects described above for the method are also applicable to the device 200 and the units contained therein, and will not be described in detail here.
[0129] Reference below Figure 3 , which shows a structural schematic diagram of an electronic device 300 suitable for implementing some embodiments of the present disclosure. Figure 3 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.
[0130] like Figure 3As shown, the electronic device 300 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 into a random access memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the electronic device 300 are also stored. The processing device 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.
[0131] Typically, the following devices may be connected to the I / O interface 305: input devices 306 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 308 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 309. The communication devices 309 may allow the electronic device 300 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 3 The electronic device 300 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead. Figure 3 Each block shown in the figure may represent one device, or may represent multiple devices as required.
[0132] In particular, according to some embodiments of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, some embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In some such embodiments, the computer program can be downloaded and installed from the network through the communication device 309, or installed from the storage device 308, or installed from the ROM 302. When the computer program is executed by the processing device 301, the functions defined in the method of some embodiments of the present disclosure are executed.
[0133] It should be noted that the computer-readable medium recorded in some embodiments of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In some embodiments of the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, device or device. In some embodiments of the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof.
[0134] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.
[0135] The computer-readable medium may be included in the electronic device; or may exist separately without being incorporated into the electronic device. The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: updates the number of request receptions in response to receiving a request for replenishment of electric materials sent by a target terminal, wherein the number of request receptions is the number of times the request for replenishment of electric materials is received; determines identification information of each candidate electric material supply source in response to determining that the number of request receptions is a preset number of receptions; sends each supply source electric material information request to each electric material supply source corresponding to each determined candidate electric material supply source identification information to obtain a supply source electric material information group set, wherein each supply source electric material information included in the supply source electric material information group in the supply source electric material information group set corresponds to the same candidate electric material supply source identification information; generates an electric material quality evaluation information group set based on the supply source electric material information group set; determines identification information of each target electric material supply source based on the electric material quality evaluation information group set and the identification information of each candidate electric material supply source, and controls each associated dispatching device to dispatch electric materials from each target electric material supply source corresponding to the identification information of each target electric material supply source to replenish electric materials.
[0136] Computer program code for performing the operations of some embodiments of the present disclosure may be written in one or more programming languages or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0137] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0138] The units described in some embodiments of the present disclosure may be implemented by software or by hardware. The described units may also be provided in a processor, for example, may be described as: a processor including an update unit, a determination unit, a sending unit, a generation unit, and a scheduling unit. The names of these units do not constitute limitations on the units themselves in certain circumstances, for example, the update unit may also be described as "a unit for updating the number of request receptions in response to receiving a request for replenishment of electric power materials sent by a target terminal".
[0139] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.
[0140] The above descriptions are only some preferred embodiments of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by a specific combination of technical features, but should also cover other technical solutions formed by any combination of technical features or their equivalent features without departing from the inventive concept. For example, a technical solution formed by replacing the features with (but not limited to) the technical features with similar functions disclosed in the embodiments of the present disclosure.
Claims
1. A method for replenishing power materials based on the quality evaluation of supply source materials, comprising: In response to the electric power material replenishment request sent by the target terminal, updating the number of request receptions, wherein the number of request receptions is the number of times the electric power material replenishment request is received; In response to determining that the number of request receptions is a preset number of receptions, determining identification information of each candidate power material supply source, wherein determining identification information of each candidate power material supply source includes: Receive business information of each supply source sent by each power material supply source, wherein the supply source business information includes power material supply source identification information, supply source fixed value information, supply source negative value information, material turnover rate, material delayed turnover rate, material reverse turnover rate and total material turnover volume; Input the received business information of each supply source into a pre-trained supply source classification model to obtain a classification label of each supply source, wherein the obtained supply source classification label is a label that characterizes the material supply capacity of the corresponding power material supply source, and the supply source classification model is trained by the following steps: Acquire a historical supply source business information set and a historical supply source classification label set, wherein the historical supply source business information in the historical supply source business information set corresponds to the historical supply source classification label in the historical supply source classification label set; According to the historical supply source classification label set, the historical supply source business information set is divided to obtain various supply source business information groups, wherein the classification results represented by various historical supply source classification labels corresponding to various supply source business information included in each supply source business information group are the same; In response to determining that each supply source business information group meets an oversampling condition, oversampling processing is performed on the historical supply source business information set to update the historical supply source business information set and the historical supply source classification label set; Based on the historical supply source business information set and the historical supply source classification label set, the following model training steps are performed: Inputting at least one historical supply source business information in the historical supply source business information set into the initial supply source classification model to obtain a verification supply source classification label corresponding to each historical supply source business information in the at least one historical supply source business information; comparing the verification supply source classification tag corresponding to each historical supply source business information in at least one historical supply source business information with the corresponding historical supply source classification tag; Determine the classification accuracy of the initial supply source classification model according to the comparison result; In response to determining that the classification accuracy is greater than or equal to a preset classification accuracy, determining the initial supply source classification model as the supply source classification model; In response to determining that the classification accuracy is less than the preset classification accuracy, adjusting the initial supply source classification model, forming a historical supply source business information set with unused historical supply source business information, determining the adjusted initial supply source classification model as the initial supply source classification model, and performing the model training step again; Determine each power material supply source identification information included in each supply source business information corresponding to each supply source classification label that meets the supply source screening condition among the supply source classification labels as each candidate power material supply source identification information; Sending each supply source power material information request to each power material supply source end corresponding to each determined candidate power material supply source identification information to obtain a supply source power material information group set, wherein each supply source power material information included in the supply source power material information group in the supply source power material information group set corresponds to the same candidate power material supply source identification information, the supply source power material information in the supply source power material information group set includes: power material type information, power material value information and each power material attribute information, and each candidate power material supply source identification information corresponds to each supply source weighting coefficient; Generate an electric power material quality evaluation information group set according to the supply source electric power material information group set, wherein before generating the electric power material quality evaluation information group set according to the supply source electric power material information group set, the method further comprises the following steps: Acquire a material evaluation attribute group set and an evaluation attribute weight group set, wherein the material evaluation attributes in the material evaluation attribute group set correspond to the attribute weights in the evaluation attribute weight group set, and each material evaluation attribute group in the material evaluation attribute group set is a set of evaluation dimensions that characterize the quality evaluation of the corresponding power material; For each supply source power material information group in the supply source power material information group set, the following steps are performed: According to the power material type information included in the supply source power material information group, selecting a material evaluation attribute group that meets the material type matching condition from the material evaluation attribute group set as a target material evaluation attribute group; For each supply source power material information in the supply source power material information group, the following data cleaning steps are performed: In response to determining that the supply source power material information does not satisfy the necessary information condition corresponding to the target material evaluation attribute group, removing the supply source power material information from the supply source power material information group set to update the supply source power material information group set; In response to determining that the supply source power material information is semi-structured information or unstructured information, the supply source power material information is structured, wherein the generating the power material quality evaluation information group set according to the supply source power material information group set includes: Re-dividing the supply source power material information group set according to the power material type information included in each supply source power material information in the supply source power material information group set to update the supply source power material information group set; For each supply source power material information group in the updated supply source power material information group set, the following quality evaluation steps are performed: Selecting an electric power material attribute detection model that meets the material type matching condition from a preset electric power material attribute evaluation model set as a target material attribute detection model; Selecting an evaluation attribute weight group that meets the material type matching condition from the evaluation attribute weight group set as a target evaluation attribute weight group; For each supply source power material information in the supply source power material information group, the following steps are performed: Inputting the supply source power material information into the target material attribute detection model to generate power material attribute detection information; generating power material quality evaluation information according to the power material attribute detection information, the target evaluation attribute weight group, and the supply source weight coefficient corresponding to the power material attribute detection information; The generated individual power material quality evaluation information is determined as a power material quality evaluation information group In response to determining that the power material type information included in the supply source power material information group is the same as one of the target power material type information in the target power material type information set, sending each power material appearance image request to each candidate power material supply source corresponding to each supply source power material information included in the supply source power material information group to obtain each power material appearance image set, wherein the power material image request includes the power material type information included in the supply source power material information group, and each candidate power material supply source is each power material supply source corresponding to each candidate power material supply source identification information; Acquire an electric power material appearance defect feature extraction model corresponding to the electric power material type information included in the supply source electric power material information group and an appearance defect feature information set corresponding to the electric power material type information included in the supply source electric power material information group; For each of the received electric power material appearance image sets, the following steps are performed: For each electric material appearance image in the electric material appearance image set, the following appearance defect detection steps are performed: Performing image enhancement on the electric power material appearance image to obtain an enhanced electric power material appearance image; Performing a region segmentation process on the enhanced electric power material appearance image to generate a mask image; Performing morphological denoising on the mask image to obtain a denoised mask image; Performing edge detection processing on the noise reduction mask image to generate power material contour information; According to the electric power material contour information, the electric power material appearance image is cropped to obtain a target area image; Inputting the target area image into the power material appearance defect feature extraction model to generate material appearance feature information; Generating an appearance defect detection result according to the material appearance feature information and the appearance defect feature information set; Generate an appearance defect rate according to each appearance defect detection result generated; Adding the appearance defect rate to the corresponding power material attribute detection information to update the corresponding power material attribute detection information; Determining the determined electric power material quality evaluation information group as an electric power material quality evaluation information group set; According to the electric power material quality evaluation information group set and the identification information of each candidate electric power material supply source, the identification information of each target electric power material supply source is determined, and each associated dispatching device is controlled to dispatch electric power materials from each target electric power material supply source corresponding to the identification information of each target electric power material supply source, so as to replenish electric power materials, wherein, according to the electric power material quality evaluation information group set and the identification information of each candidate electric power material supply source, the identification information of each target electric power material supply source is determined, and each associated dispatching device is controlled to dispatch electric power materials from each target electric power material supply source corresponding to the identification information of each target electric power material supply source, including: Acquire each power material inventory record from the power material database, wherein each power material inventory record is an inventory quantity record of different types of power materials; Based on each electric power material quality evaluation information group in the electric power material quality evaluation information group set, performing the following steps: According to the electric power material type information included in the electric power material quality evaluation information group, selecting an electric power material inventory record that meets the material type matching condition from the various electric power material inventory records as a target electric power material inventory record; Determining the material consumption rate based on the target power material inventory record; Sorting each piece of electric power material quality evaluation information in the electric power material quality evaluation information group to obtain an electric power material quality evaluation information sequence; Determine the candidate power material supply source identification information corresponding to the first power material quality evaluation information in the power material quality evaluation information sequence as the target power material supply source identification information; Determine the quantity of materials to be replenished according to the target power material inventory record and the material consumption rate; Controlling the associated dispatching equipment to dispatch the target electric power materials corresponding to the electric power material type information included in the electric power material quality evaluation information group from the electric power material supply source corresponding to the target electric power material supply source identification information, wherein the quantity of the dispatched target electric power materials is the same as the material replenishment quantity, and the method also includes the following steps: storing the electric power material quality evaluation information group set in a pre-constructed electric power material supply source evaluation information knowledge graph.
2. A power material replenishment device based on supply source material quality evaluation, comprising: A receiving unit, configured to update a request reception number in response to a power material replenishment request sent by a target terminal, wherein the request reception number is a number of times the power material replenishment request is received; The determination unit is configured to determine the identification information of each candidate power material supply source in response to determining that the number of request receptions is a preset number of receptions, wherein the determination of the identification information of each candidate power material supply source includes: receiving each supply source business information sent by each power material supply source end, wherein the supply source business information includes power material supply source identification information, supply source fixed value information, supply source negative value information, material turnover rate, material delayed turnover rate, material reverse turnover rate and total material turnover volume; inputting the received business information of each supply source into a pre-trained supply source classification model to obtain each supply source classification label, wherein the obtained supply source classification label is a label that characterizes the corresponding power material supply source. The supply source classification model is trained by the following steps: obtaining a historical supply source business information set and a historical supply source classification label set, wherein the historical supply source business information in the historical supply source business information set corresponds to the historical supply source classification label in the historical supply source classification label set; dividing the historical supply source business information set according to the historical supply source classification label set to obtain various supply source business information groups, wherein the classification results represented by the various historical supply source classification labels corresponding to the various supply source business information included in each supply source business information group are the same; in response to determining the various supply source business information The group satisfies the oversampling condition, and the historical supply source business information set is oversampled to update the historical supply source business information set and the historical supply source classification label set; based on the historical supply source business information set and the historical supply source classification label set, the following model training steps are performed: at least one historical supply source business information in the historical supply source business information set is input into the initial supply source classification model to obtain the verification supply source classification label corresponding to each historical supply source business information in the at least one historical supply source business information; the verification supply source classification label corresponding to each historical supply source business information in the at least one historical supply source business information is compared with the corresponding historical supply source classification label; and the verification supply source classification label corresponding to each historical supply source business information in the at least one historical supply source business information is determined according to the comparison result. Determine the classification accuracy of the initial supply source classification model; in response to determining that the classification accuracy is greater than or equal to the preset classification accuracy, determine the initial supply source classification model as the supply source classification model; in response to determining that the classification accuracy is less than the preset classification accuracy, adjust the initial supply source classification model, form the historical supply source business information set with the unused historical supply source business information, determine the adjusted initial supply source classification model as the initial supply source classification model, and perform the model training step again; determine each power material supply source identification information included in each supply source business information corresponding to each supply source classification label that meets the supply source screening condition in the each supply source classification label as each candidate power material supply source identification information; a sending unit configured to send each supply source power material information request to each power material supply source end corresponding to each determined candidate power material supply source identification information, so as to obtain a supply source power material information group set, wherein each supply source power material information included in the supply source power material information group in the supply source power material information group set corresponds to the same candidate power material supply source identification information, the supply source power material information in the supply source power material information group set includes: power material type information, power material value information and each power material attribute information, and each candidate power material supply source identification information corresponds to each supply source weighting coefficient; A generating unit is configured to generate a power material quality evaluation information group set according to the supply source power material information group set, wherein before generating the power material quality evaluation information group set according to the supply source power material information group set, the method further comprises the following steps: obtaining a material evaluation attribute group set and an evaluation attribute weight group set, wherein the material evaluation attributes in the material evaluation attribute group set correspond to the attribute weights in the evaluation attribute weight group set, and each material evaluation attribute group in the material evaluation attribute group set is a set of evaluation dimensions that characterize the quality evaluation of the corresponding power material; for each of the supply source power material information group sets The supply source power material information group performs the following steps: according to the power material type information included in the supply source power material information group, select the material evaluation attribute group that meets the material type matching condition from the material evaluation attribute group set as the target material evaluation attribute group; for each supply source power material information in the supply source power material information group, perform the following data cleaning steps: in response to determining that the supply source power material information does not meet the necessary information condition corresponding to the target material evaluation attribute group, remove the supply source power material information from the supply source power material information group set to update the supply source power material information group set; in response to determining that the supply source power material information does not meet the necessary information condition corresponding to the target material evaluation attribute group, remove the supply source power material information from the supply source power material information group set to update the supply source power material information group set. The supply source power material information is semi-structured information or unstructured information, and the supply source power material information is structured, wherein the generation of the power material quality evaluation information group set according to the supply source power material information group set includes: re-dividing the supply source power material information group set according to the power material type information included in each supply source power material information in the supply source power material information group set to update the supply source power material information group set; for each supply source power material information group in the updated supply source power material information group set, performing the following quality evaluation steps: selecting a preset power material attribute evaluation model set from the power material attribute evaluation model set; Selecting an electric power material attribute detection model that meets the material type matching condition as a target material attribute detection model; selecting an evaluation attribute weight group that meets the material type matching condition from the evaluation attribute weight group set as a target evaluation attribute weight group; for each supply source electric power material information in the supply source electric power material information group, performing the following steps: inputting the supply source electric power material information into the target material attribute detection model to generate electric power material attribute detection information; generating electric power material quality evaluation information according to the electric power material attribute detection information, the target evaluation attribute weight group and the supply source weighting coefficient corresponding to the electric power material attribute detection information;Determine each generated electric material quality evaluation information as an electric material quality evaluation information group; in response to determining that the electric material type information included in the supply source electric material information group is the same as one of the target electric material type information in the target electric material type information set, send each electric material appearance image request to each candidate electric material supply source corresponding to each supply source electric material information included in the supply source electric material information group, so as to obtain each electric material appearance image set, wherein the electric material image request contains the electric material type information included in the supply source electric material information group, and each candidate electric material supply source is each electric material supply source corresponding to the identification information of each candidate electric material supply source; obtain an electric material appearance defect feature extraction model corresponding to the electric material type information included in the supply source electric material information group and an appearance defect feature information set corresponding to the electric material type information included in the supply source electric material information group; for each electric material appearance image set in each received electric material appearance image set, perform the following steps: For each electric material appearance image in the electric material appearance image set, the following appearance defect detection steps are performed: performing image enhancement on the electric material appearance image to obtain an enhanced electric material appearance image; performing region segmentation processing on the enhanced electric material appearance image to generate a mask image; performing morphological denoising processing on the mask image to obtain a denoised mask image; performing edge detection processing on the denoised mask image to generate electric material contour information; according to the electric material contour information, the electric material appearance image is cropped to obtain a target area image; the target area image is input into the electric material appearance defect feature extraction model to generate material appearance feature information; according to the material appearance feature information and the appearance defect feature information set, an appearance defect detection result is generated; according to each generated appearance defect detection result, an appearance defect rate is generated; the appearance defect rate is added to the corresponding electric material attribute detection information to update the corresponding electric material attribute detection information; the determined electric material quality evaluation information group is determined as the electric material quality evaluation information group set; A dispatching unit is configured to determine the identification information of each target power material supply source according to the power material quality evaluation information group set and the identification information of each candidate power material supply source, and control each associated dispatching device to dispatch power materials from each target power material supply source corresponding to the identification information of each target power material supply source to replenish power materials, wherein the determination of each target power material supply source identification information according to the power material quality evaluation information group set and the identification information of each candidate power material supply source, and control each associated dispatching device to dispatch power materials from each target power material supply source corresponding to the identification information of each target power material supply source comprises: obtaining each power material inventory record from a power material database, wherein each power material inventory record is an inventory quantity record of different types of power materials; based on each power material quality evaluation information group in the power material quality evaluation information group set, performing the following steps: according to the power material type information included in the power material quality evaluation information group, The method further comprises the steps of: selecting an electric power material inventory record that meets the material type matching condition from among the electric power material inventory records as a target electric power material inventory record; determining a material consumption rate according to the target electric power material inventory record; sorting each electric power material quality evaluation information in the electric power material quality evaluation information group to obtain an electric power material quality evaluation information sequence; determining the candidate electric power material supply source identification information corresponding to the first electric power material quality evaluation information in the electric power material quality evaluation information sequence as the target electric power material supply source identification information; determining a material replenishment quantity according to the target electric power material inventory record and the material consumption rate; and controlling an associated dispatching device to dispatch a target electric power material corresponding to the electric power material type information included in the electric power material quality evaluation information group from the electric power material supply source corresponding to the target electric power material supply source identification information, wherein the quantity of the dispatched target electric power materials is the same as the material replenishment quantity. The method further comprises the following steps: storing the electric power material quality evaluation information group set in a pre-constructed electric power material supply source evaluation information knowledge graph.
3. An electronic device, comprising: one or more processors; a storage device having one or more programs stored thereon; A camera is configured to capture images; When the one or more programs are executed by the one or more processors, the one or more processors implement the method as claimed in claim 1.
4. A computer readable medium having a computer program stored thereon, wherein: When the computer program is executed by a processor, the method according to claim 1 is implemented.
Citation Information
Patent Citations
Electric power material supply whole-course early-warning supervise system and method
CN105608541A
Electric power material sampling inspection method and device, electronic equipment and computer readable medium
CN113379335A
Intelligent material allocation method and device
CN114154745A
Smart allocation method for electric emergency response supplies
WO2016034142A1
