CN110866656A - Power material demand prediction method and device, computer equipment and storage medium - Google Patents
Power material demand prediction method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110866656A CN110866656A CN201911170813.4A CN201911170813A CN110866656A CN 110866656 A CN110866656 A CN 110866656A CN 201911170813 A CN201911170813 A CN 201911170813A CN 110866656 A CN110866656 A CN 110866656A
- Authority
- CN
- China
- Prior art keywords
- historical
- data
- electric power
- demand
- text
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The application discloses a method and a device for forecasting demand of electric power materials, computer equipment and a storage medium, and relates to the technical field of demand forecasting. The method for predicting the demand of the electric power materials comprises the steps of obtaining a historical demand data set and a text information set of a target electric power material, wherein the text information set comprises historical project information of the target electric power material, and the historical demand data set comprises historical demand quantity and historical purchase amount of the target electric power material; acquiring historical text data of the target electric power material according to the text information set; acquiring text data to be predicted corresponding to a time interval to be predicted according to project information corresponding to the time interval to be predicted; and predicting the material demand quantity of the target power material in the time interval to be predicted according to the historical text data, the text data to be predicted and the historical demand data set. The power material demand prediction method can improve the accuracy of the prediction result.
Description
Technical Field
The present application relates to the field of demand forecasting technologies, and in particular, to a demand forecasting method and apparatus for electric power materials, a computer device, and a storage medium.
Background
Research has shown that in the power industry, adequate supply of power supplies is a necessary condition for the proper operation of electrical facilities. When the electric power supplies can not be supplied in time, the normal operation of the electric power facilities can be threatened greatly. When the predicted amount of the demand of the electric power materials is too large, the inventory cost is increased. Therefore, accurately predicting the demand of the electric power materials has great significance for guaranteeing the normal operation of the electric power facilities.
The related technology provides a demand forecasting method for electric power materials, which comprises the steps of obtaining historical material demand data of an object to be forecasted, establishing a forecasting model according to the historical material demand data, and forecasting the material demand of the object to be forecasted through the forecasting model.
However, the method establishes the prediction model only according to one dimension of the historical material demand data, and the angle is single, so that the problem of inaccurate prediction result exists.
Disclosure of Invention
In view of the above, it is necessary to provide a method, an apparatus, a computer device and a storage medium for predicting demand of electric power materials, in order to solve the above-mentioned problem that prediction results are inaccurate.
In a first aspect, an embodiment of the present application provides a method for predicting demand of electric power materials, where the method includes:
acquiring a historical demand data set and a text information set of a target electric power material, wherein the text information set comprises historical item information of the target electric power material, and the historical demand data set comprises historical demand quantity and historical purchase amount of the target electric power material;
acquiring historical text data of the target electric power material according to the text information set, wherein the historical text data is numerical data corresponding to historical project information;
acquiring text data to be predicted corresponding to the time interval to be predicted according to the project information corresponding to the time interval to be predicted, wherein the text data to be predicted is numerical data of the project information corresponding to the time interval to be predicted;
and predicting the material demand of the target power material in the time interval to be predicted according to the historical text data, the text data to be predicted and the historical demand data set.
In one embodiment, predicting the material demand amount of the target electric power material according to the historical text data, the text data to be predicted and the historical demand data set comprises the following steps:
acquiring mathematical and physical characteristic data, periodic characteristic data and category characteristic data of the target electric power material according to a historical demand data set of the target electric power material, wherein the mathematical and physical characteristic data represent the historical demand quantity of the target electric power material, the periodic data represent the periodic characteristic of the use demand of the target electric power material, and the category characteristic data represent the material category of the target electric power material;
and predicting the material demand of the target power material according to the historical text data, the text data to be predicted, the mathematical characteristic data, the periodic characteristic data and the category characteristic data.
In one embodiment, predicting the material demand amount of the target electric power material according to the historical text data, the text data to be predicted and the historical demand data set comprises the following steps:
and inputting the historical text data, the text data to be predicted and the historical demand data into a material demand prediction model in a gathering manner, and predicting the material demand of the target electric power material through the material demand prediction model.
In one embodiment, predicting the material demand amount of the target electric power material according to the historical text data, the text data to be predicted and the historical demand data set comprises the following steps:
acquiring historical prediction accuracy of each prediction model in the prediction model group on the target electric power material;
and inputting the historical text data, the text data to be predicted and the historical demand data into a prediction model with the highest historical prediction accuracy, and predicting the material demand of the target electric power material through the prediction model with the highest historical prediction accuracy.
In one embodiment, the historical item information includes: project name, project remarks, project type and undertaking units.
In one embodiment, before acquiring the historical demand data set and the text information set of the target electric power material, the method further includes:
acquiring original data, wherein the original data comprises historical project material demand and historical project material text information;
establishing a material catalog according to the original data, wherein the material catalog comprises various electric power materials, historical material demand of each electric power material and historical material text information;
normalizing the historical material demand of each electric power material to obtain a historical demand data set of each electric power material;
and performing text extraction on the historical material text information of each electric power material to obtain a text information set of each electric power material.
In a second aspect, an embodiment of the present application provides an electric power material demand prediction apparatus, including:
the acquisition module is used for acquiring a historical demand data set and a text information set of the target electric power material, wherein the text information set comprises historical item information of the target electric power material, and the historical demand data set comprises historical demand quantity and historical purchase amount of the target electric power material;
the first text processing module is used for acquiring historical text data of the target electric power material according to the text information set, wherein the historical text data is numerical data corresponding to historical project information;
the second text processing module is used for acquiring text data to be predicted corresponding to the time interval to be predicted according to the project information corresponding to the time interval to be predicted, and the text data to be predicted is numerical data of the project information corresponding to the time interval to be predicted;
and the prediction module is used for predicting the material demand of the target power material in the time interval to be predicted according to the historical text data, the text data to be predicted and the historical demand data set.
In one embodiment, the obtaining module is further configured to obtain mathematical and physical characteristic data, periodic characteristic data and category characteristic data of the target electric power material according to the historical demand data set of the target electric power material, the mathematical and physical characteristic data represents the historical demand quantity of the target electric power material, the periodic data represents the periodic characteristic of the use demand of the target electric power material, and the category characteristic data represents the material category of the target electric power material;
the prediction module is further used for predicting the material demand of the target electric power material according to the historical text data, the text data to be predicted, the mathematical characteristic data, the periodic characteristic data and the category characteristic data.
In a third aspect, there is provided a computer device comprising a memory and a processor, the memory storing a computer program which, when executed by the processor, performs the steps of the method of the first aspect described above.
In a fourth aspect, there is provided a computer readable storage medium having stored thereon a computer program which, when executed by a processor, carries out the steps of the method of the first aspect described above.
The beneficial effects brought by the technical scheme provided by the embodiment of the application at least comprise:
the power material demand prediction method, the device, the computer equipment and the storage medium can improve the accuracy of the prediction result. The historical demand data set and the text information set of the target electric power material are obtained, and the historical text data of the target electric power material are obtained according to the text information set. And acquiring text data to be predicted corresponding to the time interval to be predicted according to the item information corresponding to the time interval to be predicted. And predicting the material demand of the target power material in the time interval to be predicted according to the historical demand data set, the historical text data and the text data to be predicted. The text information set comprises historical item information of the target electric power material, and the historical demand data set comprises historical demand quantity and historical purchase amount of the target electric power material. The historical text data is digitalized data corresponding to historical item information, and the text data to be predicted is digitalized data corresponding to item information corresponding to a time interval to be predicted. Therefore, in the embodiment of the present application, the prediction basis for the demand prediction includes not only the demand quantity of the target electric power material, but also information of a project which uses the target electric power material historically and information of a project which needs to use the target electric power material in the future. According to the embodiment of the application, more and more detailed text information of the target electric power material is obtained, the text information is converted into quantifiable numerical data, and then the corresponding various information data of the target electric power material are integrated for prediction, so that the accuracy of a prediction result is improved.
Drawings
Fig. 1 is a schematic diagram of an implementation environment of a demand forecasting method for power supplies according to an embodiment of the present disclosure;
fig. 2 is a flowchart of a method for predicting demand for electric power supplies according to an embodiment of the present disclosure;
fig. 3 is a flowchart of another method for predicting demand for electric power supplies according to an embodiment of the present disclosure;
fig. 4 is a flowchart of another method for predicting demand for electric power supplies according to an embodiment of the present disclosure;
fig. 5 is a block diagram of an electric power material demand prediction apparatus according to an embodiment of the present application.
Detailed Description
To make the objects, technical solutions and advantages of the present application more clear, embodiments of the present application will be described in further detail below with reference to the accompanying drawings.
Research has shown that in the power industry, adequate supply of power supplies is a necessary condition for the proper operation of electrical facilities. Wherein, the guarantee material for guaranteeing the normal operation of the society accounts for more than 80 percent of the electric power material. When the forecast quantity of the material demand is too small, the material shortage and the production project delay are easily caused to have adverse effects, when the forecast quantity of the material demand is too large, the audit risk and the inventory cost are easily caused to increase, and the timely and sufficient material supply is required to be ensured, so that the accurate material demand forecast is very necessary.
The related technology provides a demand forecasting method for electric power materials, which comprises the steps of obtaining historical material demand data of an object to be forecasted, establishing a forecasting model according to the historical material demand data, and forecasting the material demand of the object to be forecasted through the forecasting model.
However, the above method performs demand prediction based on the numerical characteristic of the historical material demand data, and omits the analysis and utilization of the information contained in the text information corresponding to the material. The angle is single, so the problem of inaccurate prediction results exists.
The power material demand prediction method, the device, the computer equipment and the storage medium can improve the accuracy of the prediction result. The historical demand data set and the text information set of the target electric power material are obtained, and the historical text data of the target electric power material are obtained according to the text information set. And acquiring text data to be predicted corresponding to the time interval to be predicted according to the item information corresponding to the time interval to be predicted. And predicting the material demand of the target power material in the time interval to be predicted according to the historical demand data set, the historical text data and the text data to be predicted. The text information set comprises historical item information of the target electric power material, and the historical demand data set comprises historical demand quantity and historical purchase amount of the target electric power material. The historical text data is digitalized data corresponding to historical item information, and the text data to be predicted is digitalized data corresponding to item information corresponding to a time interval to be predicted. Therefore, in the embodiment of the present application, the prediction basis for the demand prediction includes not only the demand quantity of the target electric power material, but also information of a project which uses the target electric power material historically and information of a project which needs to use the target electric power material in the future. According to the embodiment of the application, more and more detailed text information of the target electric power material is obtained, the text information is converted into quantifiable numerical data, and then the corresponding various information data of the target electric power material are integrated for prediction, so that the accuracy of a prediction result is improved.
Next, a brief description will be given of an implementation environment related to the power supply demand prediction method provided in the embodiment of the present application.
Referring to fig. 1, the method for predicting demand of electric power supplies provided by the present application may be applied to a computer device shown in fig. 1, where the computer device may be a server, and its internal structure diagram may be as shown in fig. 1. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a power material demand prediction method.
Those skilled in the art will appreciate that the architecture shown in fig. 1 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as a particular computing device may include more or less components than those shown in fig. 1, or may combine certain components, or have a different arrangement of components.
Referring to fig. 2, a flowchart of a method for forecasting demand for electric power supplies according to an embodiment of the present application is shown, where the method for forecasting demand for electric power supplies can be applied to the computer device shown in fig. 1. As shown in fig. 1, the method for forecasting demand of electric power supplies may include the following steps:
The text information set comprises historical item information of the target electric power material, and the historical demand data set comprises historical demand quantity and historical purchase amount of the target electric power material.
In the embodiment of the present application, the history item information refers to item information in which a history period has been completed. The historical period may refer to the previous year or years of the time interval to be predicted. For convenience of description, in the embodiment of the present application, the historical time is taken as the previous year of the time interval to be predicted. For example, the time interval to be predicted is 2020, the historical item information may be item information corresponding to 2019, and the historical demand data set is a demand data set of 2019.
Optionally, the historical project information of the target power material may include a project name, a project remark, a project type and a undertaking unit. The history item information is text information presented in a text form.
The historical demand quantity and the historical purchase amount of the target electric power material refer to the purchase quantity and the purchase amount of the previous year.
In an optional implementation manner, before the computer device obtains the historical demand data set and the text information set of the target electric power material, the method for predicting demand of electric power materials provided in the embodiment of the present application further includes:
the computer device obtains raw data.
The raw data comprises historical project material demand and historical project material text information. The historical project material demand can refer to the demand of each original material used in the project of 2019, and the demand can include the quantity of the original materials and the purchase amount of the original materials.
The historical project material text information may refer to text information corresponding to each original material used in the project of 2019. The text information corresponding to each original material can refer to text information such as the type of the original material, the location of the project, the type of the project, and the like.
The computer device may create a inventory of materials from the raw data.
The raw materials in the raw data can be classified into thousands of types according to material names and procedure models. In the embodiment of the application, a plurality of similar original materials can be divided into a large class, so that the categories of electric power materials are reduced. For example, raw materials such as bolts, studs, screws, rivets, etc. may be classified into the electric power material category of screws. So that the four kinds of original materials are divided into one kind of electric power material.
Based on the same principle, other original materials in the original data can be classified to obtain various electric power materials, and the various electric power materials can form a material catalog.
In the embodiment of the application, the historical project material demand amount and the historical project material text information of each original material can still be reserved in the material catalog. The historical item material demand of the electric power material can be obtained by summing the historical item material demand of a plurality of original materials belonging to the same electric power material. And merging the historical item material text information of a plurality of original materials belonging to the same electric power material to obtain the historical material text information of the electric power material.
The computer equipment can normalize the historical material demand of each electric power material to obtain the historical demand data set of each electric power material.
In the embodiment of the present application, because the measurement units of various electric power materials are different, in the embodiment of the present application, the required quantity and the purchase amount of each electric power material can be respectively standardized, so that the required quantity and the purchase amount of the electric power materials after being processed can be represented by numerical values between [0,1 ].
For example, the historical demand quantity of the electric power material screws is 120 tons, and the historical purchase amount is 120 ten thousand. After the normalization process, the historical demand quantity of the power material screws can be represented by 0.12, and the historical purchase amount can be represented by 0.12.
Correspondingly, after the demand prediction is carried out on the electric power material screw, the obtained prediction result is as follows: the predicted required quantity is 0.21, which means that the predicted required quantity of the power material screws is 210 tons. If the predicted purchase amount is 0.23, the predicted purchase amount of the electric power material screw is 230 ten thousands.
In the embodiment of the application, the historical material demand of the electric power material after the normalization processing is a historical demand data set of the electric power material. Based on the same principle, historical demand data sets of the various power supplies can be obtained.
The computer equipment can extract texts from the historical material text information of each electric power material to obtain a text information set of each electric power material.
In the embodiment of the application, the historical material text information of the electric power material may be a large segment of characters. In order to simplify the text information of the historical material, in the embodiment of the application, key fields in the text information can be extracted, and each key field can represent an important semantic meaning in the text information.
Text extraction is carried out on the historical material text information of each electric power material to obtain a key field corresponding to each electric power material, and the key fields of the plurality of electric power materials are combined to form a text information set of the electric power materials. Based on the principle, in the embodiment of the application, the text information set of each electric power material can be obtained.
The historical text data is numerical data corresponding to the historical item information.
In the embodiment of the application, the text information set of the target electric power material comprises a plurality of key fields of historical project information corresponding to the electric power material, each key field can be coded in a numerical mode, and historical text data of the target electric power material is obtained and is represented in numerical values.
Optionally, in this embodiment of the application, the process of acquiring, by the computer device, the historical text data of the target electric power material according to the text information set may be:
when the text information is the category information, for example, the text information is the item type and the undertaking unit, the One-Hot (Chinese: One-bit effective coding) coding method and the Labeleencoding (Chinese: tag coding) coding method can be respectively adopted to convert the text information into the numerical type data.
In the embodiment of the application, the coding results obtained by adopting the One-Hot coding method and the LabeleEncoding coding method are used as the historical text data of the target power material together.
When the text information is non-category information, for example, when the text information is a project name and a project remark, a text topic model LDA (english: text topic model Allocation; chinese: text topic model) algorithm may be adopted to extract the text information and convert the text information into a data matrix feature, and each element in the data matrix is respectively numerical data corresponding to the text information.
The LDA algorithm may identify topics and convert the document-vocabulary matrix into a document-topic matrix and a topic-vocabulary matrix. Text information such as the project name and the project remark can be mined and analyzed and converted into quantitative characteristics.
And step 203, the computer equipment acquires text data to be predicted corresponding to the time interval to be predicted according to the item information corresponding to the time interval to be predicted.
The text data to be predicted is numerical data of the item information corresponding to the time interval to be predicted.
In the embodiment of the application, the project information corresponding to the time interval to be predicted may include a project name, a project remark, a project type, a undertaking unit, and the like. Meanwhile, the project information corresponding to the time interval to be predicted can also comprise the name of the electric power material. Namely, the material name of each electric power material required to be used by the project corresponding to the time interval to be predicted.
In the embodiment of the present application, the process of acquiring, by the computer device, the text data to be predicted corresponding to the time interval to be predicted according to the item information corresponding to the time interval to be predicted is the same as the process of acquiring, by the computer device, the historical text data of the target electric power material according to the text information set in step 202, and is not described again.
And 204, predicting the material demand quantity of the target power material in the time interval to be predicted by the computer equipment according to the historical text data, the text data to be predicted and the historical demand data set.
In the embodiment of the present application, the process of predicting the material demand of the target electric power material in the time interval to be predicted by the computer device may be:
the computer equipment inputs the historical text data, the text data to be predicted and the historical demand data into the material demand prediction model in a set mode, and the material demand of the target electric power material is predicted through the material demand prediction model.
In the embodiment of the application, the material requirement prediction model is a trained model.
Optionally, in this embodiment of the application, the material requirement prediction model may be an exponential smoothing model.
In an optional implementation manner, the process of predicting, by the computer device, the material demand of the target electric power material in the time interval to be predicted may further include the following steps:
In this embodiment of the present application, a prediction model group may be pre-established, and multiple prediction models may be set in the prediction model group, optionally, in this embodiment of the present application, the prediction model group may include three prediction models, where the three prediction models may be: random forest models, extreme random tree models, and LightGBM models.
In the embodiment of the application, different prediction models have different data sensitivities, so that the data sensitivities of the same prediction model to different power supplies are possibly different, and the demand prediction accuracy of the same prediction model to partial power supplies is higher, and the demand prediction accuracy of the same prediction model to other partial power supplies is lower. In order to avoid the situation that the prediction accuracy is unstable when one prediction model is adopted to predict the demand of all the electric power materials, the embodiment of the application provides a scheme adopting a prediction model group.
In the embodiment of the application, the prediction model can be checked according to historical data, for example, 2015-2019, the actual usage amount of each electric power material, historical text data, text data to be predicted and a historical demand data set corresponding to each electric power material.
Namely, historical text data, text data to be predicted and a historical demand data set in 2015 are adopted for a certain electric power material, and the predicted demand of the electric power material in 2016 is predicted. Then, comparing the obtained prediction result with the actual usage amount in 2016, wherein the smaller the difference is, the higher the accuracy of the prediction result is; the larger the difference, the lower the accuracy of the prediction.
In the embodiment of the application, the computer device can determine the prediction accuracy of each prediction model on the electric power materials according to the historical data of the electric power materials.
When the target electric power material is predicted, the computer device can obtain the prediction accuracy of each prediction model on the target electric power material.
In the embodiment of the application, the computer device may select a prediction model with the highest historical prediction accuracy from the plurality of prediction models. The highest historical prediction accuracy rate indicates that the more accurate the prediction model is in the prediction result of the material demand of the target electric power material.
Therefore, the computer equipment inputs the historical text data, the text data to be predicted and the historical demand data set into the prediction model with the highest historical prediction accuracy, the obtained prediction result is most accurate, and the accuracy of the prediction result can be improved.
According to the method for predicting the demand of the electric power materials, the historical demand data set and the text information set of the target electric power materials are obtained, and the historical text data of the target electric power materials are obtained according to the text information set. And acquiring text data to be predicted corresponding to the time interval to be predicted according to the item information corresponding to the time interval to be predicted. And predicting the material demand of the target power material in the time interval to be predicted according to the historical demand data set, the historical text data and the text data to be predicted. Therefore, in the embodiment of the present application, the prediction basis for the demand prediction includes not only the demand quantity of the target electric power material, but also information of a project which uses the target electric power material historically and information of a project which needs to use the target electric power material in the future. According to the embodiment of the application, more and more detailed text information of the target electric power material is obtained, the text information is converted into quantifiable numerical data, and then the corresponding various information data of the target electric power material are integrated for prediction, so that the accuracy of a prediction result is improved.
Furthermore, in the embodiment of the application, the original data component material catalog contains most of original materials, so that the generalization capability of the prediction model is effectively improved, the electric power material demand prediction method is not limited by the type of the electric power materials,
referring to fig. 4, a flowchart of another method for predicting demand for electric power supplies according to an embodiment of the present disclosure is shown, where the method for predicting demand for electric power supplies can be applied to the computer device shown in fig. 1. As shown in fig. 4, the method for forecasting demand of electric power supplies may include the following steps:
The mathematical characteristic data represent the historical demand quantity of the target electric power material, the periodic data represent the periodic characteristics of the use demand of the target electric power material, and the category characteristic data represent the material category of the target electric power material.
Optionally, the mathematical characteristic data of the target power material refers to numerical type data such as a mean value, a total value, a fluctuation rate and the like generated by applying a mathematical statistical method to numerical type data included in the historical demand data set of the target power material. It should be noted that the mathematical characteristic data of different power supplies may include different types. For example, the mathematical characteristic data of the power supply a may be a mean value, and the mathematical characteristic data of the power supply B may be a total value and a fluctuation rate. The mathematical characteristic data represents the historical demand quantity of the target power material.
Optionally, in the embodiment of the present application, historical demand data sets of four consecutive years from 2015 to 2019 may be obtained. For example, there are 20 tons in actual use for an electric power material screw in 2015, 120 tons in actual use for 2016, 23 tons in actual use for 2017, 130 tons in actual use for 2018, and 25 tons in actual use for 2019. This indicates that the use of the power material screw has a periodic characteristic, namely that the actual usage amount every other year is equivalent. In the embodiment of the application, a differential integration Moving Average autoregressive model ARIMA (english: autoregressive integrated Moving Average model; ARIMA for short) can be adopted to analyze the actual usage amount of the power material screw for continuous four years from 2015 to 2019, so that the characteristics of the data trend, the periodic characteristic and the like of the power material screw can be obtained, and the periodic characteristic is expressed by a quantifiable numerical value. The periodic data represents periodic characteristics of usage demand of the target power material.
Based on the same principle, in the embodiment of the application, data analysis can be performed on historical data of each electric power material by using an ARIMA model, so that the data trend or the periodic characteristic of each electric power material is obtained.
The computer device may obtain periodic characteristics of the target power supply.
Further, it is possible to set: different periodic characteristics can be represented by different numerical values, the periodic characteristics of the target power material are determined, and the numerical value corresponding to the periodic characteristics, namely the periodic characteristic data, is correspondingly acquired.
Optionally, the category characteristic data of the target electric power material represents a material category of the target electric power material. Specifically, the material name of the target electric power material can be converted into numerical value type data by adopting an One-Hot coding method and a LabeleEncoding coding method respectively.
It should be noted that, in the embodiment of the present application, One encoding result may be obtained by encoding the names of the materials by using the One-Hot encoding method, and another encoding result may be obtained by encoding the names of the materials by using the LabeleEncoding encoding method.
In the embodiment of the application, the computer equipment can input historical text data, text data to be predicted, mathematical characteristic data, periodic characteristic data and category characteristic data into the material demand prediction model, and predict the material demand of the target electric power material through the material demand prediction model.
In an optional implementation manner, the method for predicting the material demand amount of the target electric power material by the computer device may further include the following steps:
and step A, the computer equipment obtains the historical prediction accuracy of each prediction model in the prediction model group to the target power material.
And step B, inputting the historical text data, the text data to be predicted, the mathematical characteristic data, the periodic characteristic data and the category characteristic data into a prediction model with the highest historical prediction accuracy by the computer equipment, and predicting the material demand of the target electric power material through the prediction model with the highest historical prediction accuracy.
In the embodiment of the application, the mathematical characteristic data, the periodic characteristic data and the category characteristic data of the target electric power material are obtained, so that the characteristics of data difference, periodic characteristics, item types and the like can be converted into numerical value type data, quantitative processing of the interrelation between the materials is realized, and the accuracy of a prediction result can be improved.
Referring to fig. 5, a block diagram of an electric power material demand forecasting apparatus provided in an embodiment of the present application is shown, where the electric power material demand forecasting apparatus may be configured in a computer device in the implementation environment shown in fig. 1. As shown in fig. 5, the demand forecasting apparatus for electric power supplies may include an obtaining module 501, a first text processing module 502, a second text processing module 503, and a forecasting module 504, wherein,
the acquiring module 501 is configured to acquire a historical demand data set and a text information set of the target electric power material, where the text information set includes historical item information of the target electric power material, and the historical demand data set includes historical demand quantity and historical purchase amount of the target electric power material;
the first text processing module 502 is configured to obtain historical text data of the target electric power material according to the text information set, where the historical text data is digitized data corresponding to historical project information;
the second text processing module 503 is configured to obtain text data to be predicted corresponding to the time interval to be predicted according to the item information corresponding to the time interval to be predicted, where the text data to be predicted is digitized data of the item information corresponding to the time interval to be predicted;
the prediction module 504 is configured to predict the material demand amount of the target power material in the time interval to be predicted according to the historical text data, the text data to be predicted, and the historical demand data set.
In an embodiment of the application, the obtaining module 501 is further configured to obtain mathematical characteristic data, periodic characteristic data and category characteristic data of the target electric power material according to the historical demand data set of the target electric power material, where the mathematical characteristic data represents the historical demand quantity of the target electric power material, the periodic data represents the periodic characteristic of the usage demand of the target electric power material, and the category characteristic data represents a material category of the target electric power material;
the prediction module 504 is further configured to predict the material demand of the target power material according to the historical text data, the text data to be predicted, the mathematical characteristic data, the periodic characteristic data, and the category characteristic data.
In an embodiment of the application, the prediction module 504 is further configured to input the historical text data, the text data to be predicted, and the historical demand data set into a material demand prediction model, and predict the material demand of the target power material through the material demand prediction model
In an embodiment of the present application, the prediction module 504 is further configured to obtain a historical prediction accuracy of each prediction model included in the prediction model group on the target electric power material; and inputting the historical text data, the text data to be predicted and the historical demand data into a prediction model with the highest historical prediction accuracy, and predicting the material demand of the target electric power material through the prediction model with the highest historical prediction accuracy.
In an embodiment of the present application, the obtaining module 501 is further configured to obtain raw data, where the raw data includes historical project material demand and historical project material text information; establishing a material catalog according to the original data, wherein the material catalog comprises various electric power materials, historical material demand of each electric power material and historical material text information; normalizing the historical material demand of each electric power material to obtain a historical demand data set of each electric power material; and performing text extraction on the historical material text information of each electric power material to obtain a text information set of each electric power material.
For specific limitations of the power supply demand prediction device, reference may be made to the above limitations of the power supply demand prediction method, which are not described herein again. All or part of the modules in the power material demand forecasting device can be realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment of the present application, there is provided a computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:
acquiring a historical demand data set and a text information set of a target electric power material, wherein the text information set comprises historical item information of the target electric power material, and the historical demand data set comprises historical demand quantity and historical purchase amount of the target electric power material; acquiring historical text data of the target electric power material according to the text information set, wherein the historical text data is numerical data corresponding to historical project information; acquiring text data to be predicted corresponding to the time interval to be predicted according to the project information corresponding to the time interval to be predicted, wherein the text data to be predicted is numerical data of the project information corresponding to the time interval to be predicted; and predicting the material demand of the target power material in the time interval to be predicted according to the historical text data, the text data to be predicted and the historical demand data set.
In one embodiment of the application, the processor when executing the computer program may further implement the steps of: acquiring mathematical and physical characteristic data, periodic characteristic data and category characteristic data of the target electric power material according to a historical demand data set of the target electric power material, wherein the mathematical and physical characteristic data represent the historical demand quantity of the target electric power material, the periodic data represent the periodic characteristic of the use demand of the target electric power material, and the category characteristic data represent the material category of the target electric power material; and predicting the material demand of the target power material according to the historical text data, the text data to be predicted, the mathematical characteristic data, the periodic characteristic data and the category characteristic data.
In one embodiment of the application, the processor when executing the computer program may further implement the steps of: and inputting the historical text data, the text data to be predicted and the historical demand data into a material demand prediction model in a gathering manner, and predicting the material demand of the target electric power material through the material demand prediction model.
In one embodiment of the application, the processor when executing the computer program may further implement the steps of: acquiring historical prediction accuracy of each prediction model in the prediction model group on the target electric power material; and inputting the historical text data, the text data to be predicted and the historical demand data into a prediction model with the highest historical prediction accuracy, and predicting the material demand of the target electric power material through the prediction model with the highest historical prediction accuracy.
In one embodiment of the application, the processor when executing the computer program may further implement the steps of: acquiring original data, wherein the original data comprises historical project material demand and historical project material text information; establishing a material catalog according to the original data, wherein the material catalog comprises various electric power materials, historical material demand of each electric power material and historical material text information; normalizing the historical material demand of each electric power material to obtain a historical demand data set of each electric power material; and performing text extraction on the historical material text information of each electric power material to obtain a text information set of each electric power material.
The implementation principle and technical effect of the computer device provided by the embodiment of the present application are similar to those of the method embodiment described above, and are not described herein again.
In an embodiment of the application, a computer-readable storage medium is provided, on which a computer program is stored, which computer program, when being executed by a processor, carries out the steps of:
acquiring a historical demand data set and a text information set of a target electric power material, wherein the text information set comprises historical item information of the target electric power material, and the historical demand data set comprises historical demand quantity and historical purchase amount of the target electric power material; acquiring historical text data of the target electric power material according to the text information set, wherein the historical text data is numerical data corresponding to historical project information; acquiring text data to be predicted corresponding to the time interval to be predicted according to the project information corresponding to the time interval to be predicted, wherein the text data to be predicted is numerical data of the project information corresponding to the time interval to be predicted; and predicting the material demand of the target power material in the time interval to be predicted according to the historical text data, the text data to be predicted and the historical demand data set.
In one embodiment of the application, the computer program, when executed by the processor, may further implement the steps of: acquiring mathematical and physical characteristic data, periodic characteristic data and category characteristic data of the target electric power material according to a historical demand data set of the target electric power material, wherein the mathematical and physical characteristic data represent the historical demand quantity of the target electric power material, the periodic data represent the periodic characteristic of the use demand of the target electric power material, and the category characteristic data represent the material category of the target electric power material; and predicting the material demand of the target power material according to the historical text data, the text data to be predicted, the mathematical characteristic data, the periodic characteristic data and the category characteristic data.
In one embodiment of the application, the computer program, when executed by the processor, may further implement the steps of: and inputting the historical text data, the text data to be predicted and the historical demand data into a material demand prediction model in a gathering manner, and predicting the material demand of the target electric power material through the material demand prediction model.
In one embodiment of the application, the computer program, when executed by the processor, may further implement the steps of: acquiring historical prediction accuracy of each prediction model in the prediction model group on the target electric power material; and inputting the historical text data, the text data to be predicted and the historical demand data into a prediction model with the highest historical prediction accuracy, and predicting the material demand of the target electric power material through the prediction model with the highest historical prediction accuracy.
In one embodiment of the application, the computer program, when executed by the processor, may further implement the steps of: acquiring original data, wherein the original data comprises historical project material demand and historical project material text information; establishing a material catalog according to the original data, wherein the material catalog comprises various electric power materials, historical material demand of each electric power material and historical material text information; normalizing the historical material demand of each electric power material to obtain a historical demand data set of each electric power material; and performing text extraction on the historical material text information of each electric power material to obtain a text information set of each electric power material.
The implementation principle and technical effect of the computer-readable storage medium provided in the embodiment of the present application are similar to those of the method embodiment described above, and are not described herein again.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the claims. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A method for forecasting demand of electric power supplies, the method comprising:
acquiring a historical demand data set and a text information set of a target electric power material, wherein the text information set comprises historical item information of the target electric power material, and the historical demand data set comprises historical demand quantity and historical purchase amount of the target electric power material;
acquiring historical text data of the target electric power material according to the text information set, wherein the historical text data is numerical data corresponding to the historical project information;
acquiring text data to be predicted corresponding to a time interval to be predicted according to project information corresponding to the time interval to be predicted, wherein the text data to be predicted is numerical data of the project information corresponding to the time interval to be predicted;
and predicting the material demand quantity of the target power material in the time interval to be predicted according to the historical text data, the text data to be predicted and the historical demand data set.
2. The method of claim 1, wherein predicting the material demand amount of the target electrical material according to the historical text data, the text data to be predicted and the historical demand data set comprises:
acquiring mathematical and physical characteristic data, periodic characteristic data and category characteristic data of the target electric power material according to the historical demand data set of the target electric power material, wherein the mathematical and physical characteristic data represent the historical demand quantity of the target electric power material, the periodic data represent the periodic characteristic of the use demand of the target electric power material, and the category characteristic data represent the material category of the target electric power material;
predicting the material demand of the target electric power material according to the historical text data, the text data to be predicted, the mathematical characteristic data, the periodic characteristic data and the category characteristic data.
3. The method of claim 1, wherein predicting the material demand amount of the target electrical material according to the historical text data, the text data to be predicted and the historical demand data set comprises:
and inputting the historical text data, the text data to be predicted and the historical demand data into a material demand prediction model in a gathering manner, and predicting the material demand of the target electric power material through the material demand prediction model.
4. The method of claim 1, wherein predicting the material demand amount of the target electrical material according to the historical text data, the text data to be predicted and the historical demand data set comprises:
acquiring historical prediction accuracy of each prediction model in the prediction model group on the target electric power material;
and inputting the set of the historical text data, the text data to be predicted and the historical demand data into a prediction model with the highest historical prediction accuracy, and predicting the material demand of the target electric power material through the prediction model with the highest historical prediction accuracy.
5. The method of claim 1, wherein the historical item information comprises: project name, project remarks, project type and undertaking units.
6. The method of claim 1, wherein prior to obtaining the set of historical demand data and the set of textual information for the target electrical property, the method further comprises:
acquiring original data, wherein the original data comprises historical project material demand and historical project material text information;
establishing a material catalog according to the original data, wherein the material catalog comprises a plurality of electric power materials, historical material demand and historical material text information of each electric power material;
normalizing the historical material demand of each electric power material to obtain a historical demand data set of each electric power material;
and performing text extraction on the historical material text information of each electric power material to obtain a text information set of each electric power material.
7. An electric power material demand prediction apparatus, characterized in that the apparatus comprises:
the acquisition module is used for acquiring a historical demand data set and a text information set of a target electric power material, wherein the text information set comprises historical project information of the target electric power material, and the historical demand data set comprises historical demand quantity and historical purchase amount of the target electric power material;
the first text processing module is used for acquiring historical text data of the target electric power material according to the text information set, wherein the historical text data is numerical data corresponding to the historical project information;
the second text processing module is used for acquiring text data to be predicted corresponding to the time interval to be predicted according to the item information corresponding to the time interval to be predicted, and the text data to be predicted is numerical data of the item information corresponding to the time interval to be predicted;
and the prediction module is used for predicting the material demand of the target electric power material in the time interval to be predicted according to the historical text data, the text data to be predicted and the historical demand data set.
8. The apparatus of claim 7,
the acquisition module is further used for acquiring mathematical and physical characteristic data, periodic characteristic data and category characteristic data of the target electric power material according to the historical demand data set of the target electric power material, wherein the mathematical and physical characteristic data represent the historical demand quantity of the target electric power material, the periodic data represent the periodic characteristic of the use demand of the target electric power material, and the category characteristic data represent the material category of the target electric power material;
the prediction module is further used for predicting the material demand of the target electric power material according to the historical text data, the text data to be predicted, the mathematical characteristic data, the periodic characteristic data and the category characteristic data.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 6.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911170813.4A CN110866656A (en) | 2019-11-26 | 2019-11-26 | Power material demand prediction method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911170813.4A CN110866656A (en) | 2019-11-26 | 2019-11-26 | Power material demand prediction method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110866656A true CN110866656A (en) | 2020-03-06 |
Family
ID=69655353
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911170813.4A Pending CN110866656A (en) | 2019-11-26 | 2019-11-26 | Power material demand prediction method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110866656A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113361745A (en) * | 2021-05-07 | 2021-09-07 | 云南电网有限责任公司曲靖供电局 | Power distribution network material demand prediction method and system |
| CN116502771A (en) * | 2023-06-21 | 2023-07-28 | 国网浙江省电力有限公司宁波供电公司 | Power distribution method and system based on electric power material prediction |
| CN116629754A (en) * | 2023-07-24 | 2023-08-22 | 广东电网有限责任公司广州供电局 | Electric power storage material storage capacity tension time section and inventory peak prediction method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060178927A1 (en) * | 2005-02-04 | 2006-08-10 | Taiwan Semiconductor Manufacturing Co., Ltd. | Demand forecast system and method |
| CN107292428A (en) * | 2017-06-07 | 2017-10-24 | 国网浙江省电力公司物资分公司 | A kind of distribution Power Material procurement demand forecasting system |
| CN108288108A (en) * | 2017-12-25 | 2018-07-17 | 沈阳大学 | A kind of flood emergency materials dynamic need prediction technique |
| CN109886445A (en) * | 2018-12-13 | 2019-06-14 | 国网浙江省电力有限公司衢州供电公司 | A kind of tomorrow requirement prediction technique based on material requirements property quantification |
-
2019
- 2019-11-26 CN CN201911170813.4A patent/CN110866656A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060178927A1 (en) * | 2005-02-04 | 2006-08-10 | Taiwan Semiconductor Manufacturing Co., Ltd. | Demand forecast system and method |
| CN107292428A (en) * | 2017-06-07 | 2017-10-24 | 国网浙江省电力公司物资分公司 | A kind of distribution Power Material procurement demand forecasting system |
| CN108288108A (en) * | 2017-12-25 | 2018-07-17 | 沈阳大学 | A kind of flood emergency materials dynamic need prediction technique |
| CN109886445A (en) * | 2018-12-13 | 2019-06-14 | 国网浙江省电力有限公司衢州供电公司 | A kind of tomorrow requirement prediction technique based on material requirements property quantification |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113361745A (en) * | 2021-05-07 | 2021-09-07 | 云南电网有限责任公司曲靖供电局 | Power distribution network material demand prediction method and system |
| CN116502771A (en) * | 2023-06-21 | 2023-07-28 | 国网浙江省电力有限公司宁波供电公司 | Power distribution method and system based on electric power material prediction |
| CN116502771B (en) * | 2023-06-21 | 2023-12-01 | 国网浙江省电力有限公司宁波供电公司 | Power distribution method and system based on electric power material prediction |
| CN116629754A (en) * | 2023-07-24 | 2023-08-22 | 广东电网有限责任公司广州供电局 | Electric power storage material storage capacity tension time section and inventory peak prediction method |
| CN116629754B (en) * | 2023-07-24 | 2023-12-22 | 广东电网有限责任公司广州供电局 | Electric power storage material storage capacity tension time section and inventory peak prediction method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108711110B (en) | Insurance product recommendation method, apparatus, computer device and storage medium | |
| CN110866656A (en) | Power material demand prediction method and device, computer equipment and storage medium | |
| CN109446511B (en) | Referee document processing method, referee document processing device, computer equipment and storage medium | |
| CN109871597B (en) | Method, apparatus, computer device and storage medium for solving potential complaints | |
| CN109783785B (en) | Method and device for generating experiment detection report and computer equipment | |
| CN110929954A (en) | Load prediction method, load prediction device, computer equipment and storage medium | |
| CN109359866B (en) | Risk hidden danger monitoring method and device based on leasing equipment and computer equipment | |
| CN110109750B (en) | Virtual resource acquisition method, device, computer equipment and storage medium | |
| CN110751533A (en) | Product portrait generation method and device, computer equipment and storage medium | |
| CN110888625B (en) | Method for controlling code quality based on demand change and project risk | |
| CN112231224A (en) | Business system testing method, device, equipment and medium based on artificial intelligence | |
| CN113537850A (en) | Storage optimization method and device, computer equipment and storage medium | |
| CN111353286A (en) | Table file processing method and device, computer equipment and storage medium | |
| CN113256108A (en) | Human resource allocation method, device, electronic equipment and storage medium | |
| CN108764553B (en) | User scale prediction method and device and computer equipment | |
| CN113110961B (en) | Equipment abnormality detection method and device, computer equipment and readable storage medium | |
| CN113947076A (en) | Policy data detection method and device, computer equipment and storage medium | |
| CN109992778B (en) | Resume document distinguishing method and device based on machine learning | |
| CN109800975B (en) | Resource evaluation method and device, computer equipment and storage medium | |
| CN112949885A (en) | Method and device for predicting delivery mode, storage medium and electronic equipment | |
| CN113742187A (en) | Capacity prediction method, device, equipment and storage medium of application system | |
| CN113780673A (en) | Training method and device of job leaving prediction model and job leaving prediction method and device | |
| CN110442780B (en) | Vehicle owner portrait generation method and device based on intelligent park and computer equipment | |
| CN114676868A (en) | Logistics cargo quantity prediction method and device, computer equipment and storage medium | |
| CN112416785A (en) | Word cutting tool version difference testing method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200924 Address after: 510620 Tianhe District, Guangzhou, Tianhe South Road, No. two, No. 2, No. Applicant after: Guangzhou Power Supply Bureau of Guangdong Power Grid Co.,Ltd. Address before: 510620 Tianhe District, Guangzhou, Tianhe South Road, No. two, No. 2, No. Applicant before: GUANGZHOU POWER SUPPLY Co.,Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200306 |