CN116452156A - Digital power supply station platform based on big data - Google Patents
Digital power supply station platform based on big data Download PDFInfo
- Publication number
- CN116452156A CN116452156A CN202310713004.3A CN202310713004A CN116452156A CN 116452156 A CN116452156 A CN 116452156A CN 202310713004 A CN202310713004 A CN 202310713004A CN 116452156 A CN116452156 A CN 116452156A
- Authority
- CN
- China
- Prior art keywords
- work order
- classification model
- classification
- power supply
- order set
- 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
- 238000013499 data model Methods 0.000 claims abstract description 18
- 238000007781 pre-processing Methods 0.000 claims abstract description 7
- 238000013145 classification model Methods 0.000 claims description 80
- 239000013598 vector Substances 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000000034 method Methods 0.000 claims description 8
- 238000012549 training Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 6
- 238000007726 management method Methods 0.000 abstract description 6
- 238000011156 evaluation Methods 0.000 abstract description 3
- 230000006978 adaptation Effects 0.000 abstract description 2
- 238000011835 investigation Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
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
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Engineering & Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Evolutionary Computation (AREA)
- Entrepreneurship & Innovation (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Tourism & Hospitality (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of power supply station management, and discloses a digital power supply station platform based on big data, which comprises the following components: the work order preprocessing module is used for extracting entities in the work order; the entity feature generation module is used for generating a work order feature for each work order; the error generation module is used for calculating the main data similarity of the reference work order set and the current work order set; the multiplexing module is used for extracting the main data of the reference work order set with the maximum similarity with the main data of the current work order set, taking a data model of the main data as a data model of the main data of the current work order set, and generating the main data of the current work order set based on the data model; the invention can automatically generate the unified data model with high adaptation degree for the work order data, and can conveniently acquire related contents under the condition of the unified data model so as to perform performance evaluation or scoring and other works on staff.
Description
Technical Field
The invention relates to the technical field of power supply station management, in particular to a digital power supply station platform based on big data.
Background
The power supply station worksheet comprises business charging, business expansion and reporting, line loss management, metering operation and maintenance, anti-theft check and violating, marketing inspection, customer service, equipment overhaul, fault first-aid repair and the like, and is derived from a plurality of departments of the power supply station such as business expansion, metering, electric charge, service, market, synthesis and the like, a unified data model and a unified standard are lacking, related data are difficult to collect through retrieval when staff is subjected to performance evaluation or scoring and the like through worksheet content, and independent statistics of the related data are required.
Disclosure of Invention
The invention provides a digital power supply station platform based on big data, which solves the technical problem that related contents are difficult to obtain through retrieval for staff management in the power supply station worksheet data in the related technology.
The invention provides a digital power supply station platform based on big data, which comprises:
the work order preprocessing module is used for extracting entities in the work order; the entity feature generation module is used for generating a work order feature for each work order; the first classification model generation module is used for training the basic classification model through the reference work order set to generate a first classification model; the second classification model generation module is used for extracting A times from the reference work order set, and extracting B work orders from the reference work order set each time to generate a second work order set; training the basic classification model through the second work order set respectively to generate a second classification model; a third classification model generation module, configured to circularly execute the generating step until an error of the intermediate classification model is smaller than a set first error threshold, and take the intermediate classification model when the execution is terminated as a third classification model, where the generating step includes:
s101, extracting N worksheets from a reference worksheet set to generate a second worksheet set, and training a basic classification model through the second worksheet set to obtain an intermediate classification model;
step S102, classifying all worksheets in a reference worksheet set through an intermediate classification model, and calculating errors of the intermediate classification model;
the error generation module is used for calculating the main data similarity of the reference work order set and the current work order set, and the calculation formula of the main data similarity of the j-th reference work order set and the current work order set is as follows:，/>classification error weight representing the u-th classification model, adjustable parameter, default 1,/-for the classification error weight>And->Respectively representing classification errors of the u-th classification model on the reference work order set and the current work order set; classification error of the second classification model for a set of worksheets>The calculation formula of (2) is as follows:；/>the method comprises the steps of carrying out a first treatment on the surface of the Wherein F represents the total number of second classification models, < >>The number of worksheets representing the set of worksheets classified by the second classification model, +.>Representing the classification result of the r second classification model on the a-th work order in the work order set,/I>Representing the actual classification result of the a-th work order,an intermediate parameter representing an a-th work order;
and the multiplexing module is used for extracting the main data of the reference work order set with the maximum similarity with the main data of the current work order set, taking the data model of the main data as the data model of the main data of the current work order set, and generating the main data of the current work order set based on the data model.
Further, the entity name of the entity includes: customer name, customer address, sponsor name, sponsor address, business type, power business name.
Further, the work order feature is generated by processing the extracted entity through a Skip-Gram model (Skip model) to obtain a word vector, and then combining the generated word vectors to generate the work order feature.
Further, the word vector merging method comprises the following steps: the word vectors are arranged according to a fixed sequence and then used as work order features.
Further, one reference work order set is a set of all work orders that need to use common master data.
Further, the calculation formula of the error of the intermediate classification model generated in the t-th execution generation step is as follows:
where n represents the number of worksheets in the reference worksheet set,representing an indication function->Representing the classification result of the classification model generated at the time of the t-th execution of the generating step on the i-th work order,/and->Representing the actual classification result of the ith work order,representing the error weight of the ith work order when the generating step is executed for the t time,/for the ith work order>，/>，，t≥1。
Further, the value of the first error threshold is proportional to the size of n, and the default value is 0.3.
Further, the basic classification model is a multi-layer perceptron, the basic classification model inputs the work order characteristics of the work order, then the classification result of the work order is output, and one label of the classification space corresponds to the classification result of one work order for the multi-layer perceptron.
Further, the classification errors of the first classification model and the third classification model for one set of work orders are equal to the ratio of the number of work orders with wrong classification to the total number of work orders of the set of work orders.
Further, the system also comprises an employee scoring module which retrieves the sponsor identification card number corresponding to the target employee from the main data of the current work order set to extract the customer scores of all work orders transacted by the target employee, and scores the target employee based on the extracted customer scores.
The invention has the beneficial effects that:
the invention can automatically generate the unified data model with high adaptation degree for the work order data, and can conveniently acquire related contents under the condition of the unified data model so as to perform performance evaluation or scoring and other works on staff.
Drawings
FIG. 1 is a schematic diagram of a digital power supply station platform based on big data;
FIG. 2 is a flow chart of the generating steps of the present invention;
fig. 3 is a schematic diagram of a module of the digital power supply station platform based on big data.
In the figure: the system comprises a work order preprocessing module 101, an entity characteristic generating module 102, a first classification model generating module 103, a second classification model generating module 104, a third classification model generating module 105, an error generating module 106, a multiplexing module 107 and an employee scoring module 108.
Description of the embodiments
The subject matter described herein will now be discussed with reference to example embodiments. It is to be understood that these embodiments are merely discussed so that those skilled in the art may better understand and implement the subject matter described herein and that changes may be made in the function and arrangement of the elements discussed without departing from the scope of the disclosure herein. Various examples may omit, replace, or add various procedures or components as desired. In addition, features described with respect to some examples may be combined in other examples as well.
As shown in fig. 1 and 2, a digital power supply station platform based on big data includes:
the work order preprocessing module 101 is configured to extract entities in a work order, where entity names of the entities include: customer name, customer address, sponsor name, sponsor address, business type, power company name, etc.
For example, for a daily business worksheet, the entity named business type is the business type;
for example, for a power supply office on-site operation investigation work order, an entity with an entity name of a business type is an investigation task.
For example, for a daily business worksheet, the entity named power supply enterprise name is the power supply enterprise;
for example, for a power supply office field work investigation work order, an entity whose entity name is the power supply enterprise name is an operation unit.
In a special case, if an entity cannot be extracted from a work order based on one entity name, the entity corresponding to the entity name is set to be "blank" for interpolation.
The work order preprocessing module 101 processes the work order after the data processing, and the paper work order needs to be firstly recorded for the data processing.
In one embodiment of the invention, the work order pre-processing module 101 includes a work order entry module for entering work orders.
The unified extraction is carried out on the entities in the worksheet through the unified entity names, and the quantity of the entities extracted from the worksheet after the unification is also consistent, so that the subsequent processing is facilitated;
an entity feature generation module 102 for generating a work order feature for each work order;
the method for generating the work order features comprises the steps of obtaining word vectors from an extracted entity through Skip-Gram model (Skip model), and then merging the generated word vectors to generate the work order features;
the word vector merging method comprises the following steps: the word vectors are arranged according to a fixed sequence and then used as work order features;
for example for two word vectorsAnd->The combined worksheet is characterized by；
A first classification model generation module 103 that trains the basic classification model by referring to the work order set to generate a first classification model;
in one embodiment of the invention, a reference worksheet set is a set of all worksheets that require the use of common master data. As a reference worksheet set, it has built up master data.
A second classification model generation module 104 that extracts a times from the reference work order set, each extraction extracting B work orders from the reference work order set to generate a second work order set;
training the basic classification model through the A second work order sets respectively to generate A second classification models;
a third classification model generation module 105 for circularly executing the generation step until the error of the intermediate classification model is smaller than the set first error threshold, and taking the intermediate classification model at the time of terminating the execution as the third classification model, the generation step including:
s101, extracting N worksheets from a reference worksheet set to generate a second worksheet set, and training a basic classification model through the second worksheet set to obtain an intermediate classification model;
step S102, classifying all worksheets in a reference worksheet set through an intermediate classification model, and calculating errors of the intermediate classification model;
the calculation formula of the error of the intermediate classification model generated in the t-th execution generation step is as follows:
where n represents the number of worksheets in the reference worksheet set,representing an indication function->Representing the classification result of the classification model generated at the time of the t-th execution of the generating step on the i-th work order,/and->Representing the actual classification result of the ith work order,representing the error weight of the ith work order when the generating step is executed for the t time,/for the ith work order>，/>，，t≥1；
The value of the first error threshold is proportional to the size of n, and the default value is 0.3.
In one embodiment of the invention, the basic classification model is a multi-layer perceptron, the basic classification model inputs the work order features of the work order and then outputs the classification result of the work order, and one label of the classification space corresponds to the classification result of one work order for the multi-layer perceptron.
For example, a work order is categorized as a daily business work order.
The error generating module 106 is configured to calculate a similarity of the main data of the reference worksheet set and the current worksheet set, where a calculation formula of the similarity of the main data of the jth reference worksheet set and the current worksheet set is as follows:，/>classification error weight representing the u-th classification model, adjustable parameter, default 1,/-for the classification error weight>And->Respectively representing classification errors of the u-th classification model on the reference work order set and the current work order set;
classification errors of a second classification model for a set of worksheetsThe calculation formula of (2) is as follows:
wherein F represents the total number of second classification models,the number of worksheets representing the set of worksheets classified by the second classification model, +.>Representing the classification result of the r second classification model on the a-th work order in the work order set,/I>Representing the actual sorting result of the a-th work order,/->Representing the intermediate parameters of the a-th work order.
Representing an indication function->And the value is 1, otherwise, the value is 0.
Representing an indication function->And the value is 1, otherwise, the value is 0.
Representing an indication function->And the value is 1, otherwise, the value is 0.
For a reference work order set, the number of the first classification models is 1, and the classification error is equal to the ratio of the number of work orders with wrong classification to the total number of work orders in the work order set.
In the above embodiment, the worksheet features are generated based on the content entity of the worksheet to classify the worksheet, and the degree to which the data sets of the reference worksheet set and the current worksheet set can share the main data is measured based on the classification error of the classifier generated by the reference worksheet set on the current worksheet set.
The multiplexing module 107 extracts the main data of the reference work order set having the greatest similarity with the main data of the current work order set, uses the data model of the main data as the data model of the main data of the current work order set, and generates the main data of the current work order set based on the data model.
An example of a data model as one main data is shown in the following table:
the main data obtained based on the work order data processing can unify the work order data with multiple sources, so that the work order management and the staff management are facilitated.
As shown in FIG. 3, in one embodiment of the present invention, a big data based digital power supply facility platform further includes an employee scoring module 108 that retrieves a sponsor identification number corresponding to a target employee from the main data of the current work order set to extract a customer score for all work orders handled by the target employee, and scores the target employee based on the extracted customer score.
The formula for providing a score is as follows:
wherein P represents the score of the target employee, G represents the total number of customer scores extracted, ++>Value of the c-th customer score.
The embodiment has been described above with reference to the embodiment, but the embodiment is not limited to the above-described specific implementation, which is only illustrative and not restrictive, and many forms can be made by those of ordinary skill in the art, given the benefit of this disclosure, are within the scope of this embodiment.
Claims (10)
1. A digital power supply station platform based on big data, comprising:
the work order preprocessing module is used for extracting entities in the work order; the entity feature generation module is used for generating a work order feature for each work order; the first classification model generation module is used for training the basic classification model through the reference work order set to generate a first classification model; the second classification model generation module is used for extracting A times from the reference work order set, and extracting B work orders from the reference work order set each time to generate a second work order set; training the basic classification model through the second work order set respectively to generate a second classification model; a third classification model generation module, configured to circularly execute the generating step until an error of the intermediate classification model is smaller than a set first error threshold, and take the intermediate classification model when the execution is terminated as a third classification model, where the generating step includes:
s101, extracting N worksheets from a reference worksheet set to generate a second worksheet set, and training a basic classification model through the second worksheet set to obtain an intermediate classification model;
step S102, classifying all worksheets in a reference worksheet set through an intermediate classification model, and calculating errors of the intermediate classification model;
the error generation module is used for calculating the main data similarity of the reference work order set and the current work order set, and the calculation formula of the main data similarity of the j-th reference work order set and the current work order set is as follows:，/>classification error weight representing the u-th classification model, adjustable parameter, default 1,/-for the classification error weight>And->Respectively representing classification errors of the u-th classification model on the reference work order set and the current work order set; classification error of the second classification model for a set of worksheets>The calculation formula of (2) is as follows:；/>the method comprises the steps of carrying out a first treatment on the surface of the Wherein F represents the total number of second classification models, < >>The number of worksheets representing the set of worksheets classified by the second classification model, +.>Representing the classification result of the r second classification model on the a-th work order in the work order set,/I>Representing the actual classification result of the a-th work order,an intermediate parameter representing an a-th work order;
and the multiplexing module is used for extracting the main data of the reference work order set with the maximum similarity with the main data of the current work order set, taking the data model of the main data as the data model of the main data of the current work order set, and generating the main data of the current work order set based on the data model.
2. The digital power supply station platform based on big data of claim 1, wherein the entity name of the entity comprises: customer name, customer address, sponsor name, sponsor address, business type, power business name.
3. The digital power supply station platform based on big data according to claim 1, wherein the work order feature is generated by processing the extracted entity through a Skip-Gram model to obtain word vectors, and then combining the generated word vectors to generate the work order feature.
4. A digital power supply station platform based on big data according to claim 3, wherein the word vector merging method comprises: the word vectors are arranged according to a fixed sequence and then used as work order features.
5. A digital power supply station platform based on big data according to claim 1, characterized in that a reference work order set is a set of all work orders that need to use common main data.
6. The digital power supply station platform based on big data according to claim 1, wherein the calculation formula of the error of the intermediate classification model generated in the t-th execution generation step is as follows:
wherein n represents the number of worksheets in the reference worksheet set, < >>Representing an indication function->Representing the classification result of the classification model generated at the time of the t-th execution of the generating step on the i-th work order,/and->Representing the actual sorting result of the ith work order,/->Representing the error weight of the ith work order at the time of the t-th execution of the generating step,，/>，/>，t≥1。
7. the digital power supply station platform based on big data according to claim 6, wherein the value of the first error threshold is proportional to the size of n, and the default value is 0.3.
8. The digital power supply station platform based on big data according to claim 1, wherein the basic classification model is a multi-layer perceptron, the basic classification model inputs the work order characteristics of the work order and outputs the classification result of the work order, and one label of the classification space corresponds to the classification result of one work order for the multi-layer perceptron.
9. The digital power supply station platform based on big data according to claim 1, wherein the classification errors of the first classification model and the third classification model for one work order set are equal to the ratio of the number of work orders with wrong classification to the total number of work orders of the work order set.
10. The digital power supply post platform based on big data of claim 1, further comprising an employee scoring module that retrieves a sponsor identification number corresponding to a target employee from the main data of the current set of work orders to extract customer scores for all work orders handled by the target employee, and scores the target employee based on the extracted customer scores.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310713004.3A CN116452156A (en) | 2023-06-16 | 2023-06-16 | Digital power supply station platform based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310713004.3A CN116452156A (en) | 2023-06-16 | 2023-06-16 | Digital power supply station platform based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116452156A true CN116452156A (en) | 2023-07-18 |
Family
ID=87122300
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310713004.3A Pending CN116452156A (en) | 2023-06-16 | 2023-06-16 | Digital power supply station platform based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116452156A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190156680A1 (en) * | 2017-11-17 | 2019-05-23 | Fleetmatics Ireland Limited | Stop purpose classification for vehicle fleets |
| CN111737552A (en) * | 2020-06-04 | 2020-10-02 | 中国科学院自动化研究所 | Method, device and equipment for extracting training information model and acquiring knowledge graph |
| CN113434627A (en) * | 2020-03-18 | 2021-09-24 | 中国电信股份有限公司 | Work order processing method and device and computer readable storage medium |
-
2023
- 2023-06-16 CN CN202310713004.3A patent/CN116452156A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190156680A1 (en) * | 2017-11-17 | 2019-05-23 | Fleetmatics Ireland Limited | Stop purpose classification for vehicle fleets |
| CN113434627A (en) * | 2020-03-18 | 2021-09-24 | 中国电信股份有限公司 | Work order processing method and device and computer readable storage medium |
| CN111737552A (en) * | 2020-06-04 | 2020-10-02 | 中国科学院自动化研究所 | Method, device and equipment for extracting training information model and acquiring knowledge graph |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108256074B (en) | Verification processing method and device, electronic equipment and storage medium | |
| CN109872162B (en) | Wind control classification and identification method and system for processing user complaint information | |
| CN111861366A (en) | Project-ground intelligent auditing system and computer | |
| CN112200465B (en) | Electric power AI method and system based on multimedia information intelligent analysis | |
| CN111626331B (en) | Automatic industry classification device and working method thereof | |
| CN111429292A (en) | Intelligent matching system for insurance industry service personnel and service objects | |
| CN109766416A (en) | A kind of new energy policy information abstracting method and system | |
| CN114140013A (en) | Scoring card generation method, device and equipment based on xgboost | |
| CN115409018A (en) | Company public opinion monitoring system and method based on big data | |
| CN109583773A (en) | A kind of method, system and relevant apparatus that taxpaying credit integral is determining | |
| CN110287495A (en) | A kind of power marketing profession word recognition method and system | |
| CN116452156A (en) | Digital power supply station platform based on big data | |
| GV et al. | Document Classification and Information Extraction framework for Insurance Applications | |
| CN116452054A (en) | Method and device for managing material spot check of electric power system | |
| CN112992156B (en) | Power distribution network dispatching identity authentication system based on voiceprint authentication | |
| CN115130924A (en) | Microgrid power equipment asset evaluation method and system under source grid storage background | |
| CN115482075A (en) | Financial data anomaly analysis method and device, electronic equipment and storage medium | |
| CN114742412A (en) | Software technology service system and method | |
| CN113779998A (en) | Structured processing method, device and equipment of service information and storage medium | |
| CN114118672A (en) | Method and system for automatically generating project requirements of power system | |
| Wang et al. | Prediction of accrual expenses in balance sheet using decision trees and linear regression | |
| Wujec | Sentiment analysis of current reports texts with use of cumulative abnormal return and deep neural network | |
| KR20210057437A (en) | Approval rating prediction system using news data | |
| CN116468255B (en) | Configurable main data management system | |
| TWI783605B (en) | Solar power generation prediction method |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20230718 |