CN113554291A - Electric energy meter supply chain monitoring and management method and device based on demand prediction - Google Patents

Electric energy meter supply chain monitoring and management method and device based on demand prediction Download PDF

Info

Publication number
CN113554291A
CN113554291A CN202110793546.7A CN202110793546A CN113554291A CN 113554291 A CN113554291 A CN 113554291A CN 202110793546 A CN202110793546 A CN 202110793546A CN 113554291 A CN113554291 A CN 113554291A
Authority
CN
China
Prior art keywords
demand
energy meter
electric energy
supply chain
inventory
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
Application number
CN202110793546.7A
Other languages
Chinese (zh)
Inventor
贺青
张洪红
庄葛巍
顾臻
李蕊
戴玉艳
章瑶易
陆柳
李鑫
李冰融
高常恺
任婵娟
章才杰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai Hengnengtai Enterprise Management Co ltd
State Grid Shanghai Electric Power Co Ltd
Original Assignee
Shanghai Hengnengtai Enterprise Management Co ltd
State Grid Shanghai Electric Power Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shanghai Hengnengtai Enterprise Management Co ltd, State Grid Shanghai Electric Power Co Ltd filed Critical Shanghai Hengnengtai Enterprise Management Co ltd
Priority to CN202110793546.7A priority Critical patent/CN113554291A/en
Publication of CN113554291A publication Critical patent/CN113554291A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q30/00Commerce
    • G06Q30/02Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201Market modelling; Market analysis; Collecting market data
    • G06Q30/0202Market predictions or forecasting for commercial activities
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q10/00Administration; Management
    • G06Q10/06Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063Operations research, analysis or management
    • G06Q10/0631Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G06Q10/06315Needs-based resource requirements planning or analysis
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q10/00Administration; Management
    • G06Q10/06Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063Operations research, analysis or management
    • G06Q10/0635Risk analysis of enterprise or organisation activities
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q10/00Administration; Management
    • G06Q10/08Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
    • G06Q10/087Inventory or stock management, e.g. order filling, procurement or balancing against orders
    • G06Q10/0875Itemisation or classification of parts, supplies or services, e.g. bill of materials
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q30/00Commerce
    • G06Q30/02Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201Market modelling; Market analysis; Collecting market data

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Strategic Management (AREA)
  • Human Resources & Organizations (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Development Economics (AREA)
  • Economics (AREA)
  • Finance (AREA)
  • Accounting & Taxation (AREA)
  • General Physics & Mathematics (AREA)
  • Marketing (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • Game Theory and Decision Science (AREA)
  • Operations Research (AREA)
  • Tourism & Hospitality (AREA)
  • Quality & Reliability (AREA)
  • Data Mining & Analysis (AREA)
  • Educational Administration (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention relates to a demand prediction-based electric energy meter supply chain monitoring and management method and equipment, wherein the method comprises the following steps: establishing an electric energy meter demand prediction model; acquiring electric energy meter planning data, and acquiring a demand prediction value based on the electric energy meter demand prediction model; and judging whether the supply chain fracture risk exists or not based on the demand predicted value, identifying a supply chain fracture link and generating an early warning signal. Compared with the prior art, the invention has the advantages of improving the efficiency, improving the response speed and the like.

Description

Electric energy meter supply chain monitoring and management method and device based on demand prediction
Technical Field
The invention relates to the technical field of electric energy meter resource control, in particular to a method and equipment for monitoring and managing an electric energy meter supply chain based on demand prediction.
Background
With the increasing popularity of digital technology and the introduction of digital transformation, more and more data and intelligent models can assist in making better operation decisions.
For uncertainty in business process and influence of external factors, collection of risk amount and evaluation and analysis of risk and trend are basically performed manually.
This mode generally has two problems:
(1) the manual newspaper reporting efficiency is low
The consideration factors of the service personnel are not comprehensive enough, and the offline demand reporting is carried out by means of respective management experience and subjective judgment, so that the efficiency is not high.
(2) Demand forecast is not ideal
Demand forecasting is subject to large deviations in the accuracy of the forecasting results, in addition to being influenced by policy or temporary factors.
(3) The interlinkage of the links is weaker
The business connection between the demand forecasting link and the subsequent link is not tight enough, so that the equipment purchase is repeated, the central production pressure, the stock overstock or exhaustion and the old stock are difficult to be stored, and finally the cost waste and the distribution cannot be high in quality and quick in response are caused.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide a method and equipment for monitoring and managing an electric energy meter supply chain based on demand prediction, which improve the efficiency and the response speed.
The purpose of the invention can be realized by the following technical scheme:
a demand prediction-based electric energy meter supply chain monitoring and management method comprises the following steps:
establishing an electric energy meter demand prediction model;
acquiring electric energy meter planning data, and acquiring a demand prediction value based on the electric energy meter demand prediction model;
and judging whether the supply chain fracture risk exists or not based on the demand predicted value, identifying a supply chain fracture link and generating an early warning signal.
Further, the electric energy meter demand prediction model is established through the following steps:
acquiring historical installation data;
performing data preprocessing on the historical installation data;
extracting installation quantity change influence characteristics through characteristic engineering;
and learning and predicting the future demand of the material codes of the electric energy meter by adopting an artificial intelligence algorithm, and constructing and obtaining an electric energy meter demand prediction model.
Further, the data preprocessing comprises data cleaning, data processing, data calculation and data storage.
Further, the supply chain disruption links include a reasonable safety assurance inventory disruption, a protocol inventory disruption, an ordered disruption, an in-transit shipment disruption, a certification disruption, a qualified inventory disruption, and a distribution disruption.
Further, the method further comprises:
and adjusting the inventory quantity based on the demand forecast value, wherein the adjustment comprises the adjustment of an inventory upper limit value and the adjustment of the replenishment quantity. The formula adopted by the inventory upper limit value adjustment is as follows:
Max=SafetyStock+Dpred+Z0.95
wherein Max is the upper limit value of the stock, SafetyStock is the safety stock value, DpredFor demand forecast, Z0.95And the quantile is 0.95 quantile corresponding to the prediction error of the demand prediction model of the electric energy meter.
Further, the adjustment of the replenishment quantity is specifically as follows:
and taking the monthly arrival period, the monthly demand predicted value, the monthly demand predicted deviation rate, the preset demand satisfaction rate and weight, the preset inventory backlog value and weight as data input, and outputting the optimal replenishment time and replenishment quantity of the materials through optimal model processing.
Further, the early warning signal comprises a supply chain fracture link, a guaranteed month number and a gap number.
The present invention also provides an electronic device comprising:
one or more processors;
a memory; and
one or more programs stored in the memory, the one or more programs including instructions for performing a method of power meter supply chain monitoring management based on demand forecasting as described above.
The present invention also provides a computer readable storage medium including one or more programs for execution by one or more processors of an electronic device, the one or more programs including instructions for performing a method for power meter supply chain monitoring management based on demand forecasting as described above.
Compared with the prior art, the invention has the following beneficial effects:
1. aiming at the conditions that the key services such as the existing plan submission, the arrival verification, the storage and delivery are not smooth, the follow-up process is blocked due to the stagnation of the front service, the service cooperation information is not enough, and the like, the method uses big data to enable the demand prediction and the node planning of the supply chain, constructs a demand prediction model, reasonably and accurately predicts the demand of the future electric energy meter, guides the purchase, the arrival, the verification and the delivery of the electric energy meter, and assists in making a decision on the quality improvement management of the supply chain, thereby reducing the inventory cost and improving the asset operation management efficiency.
2. According to the invention, the effective management and monitoring of the supply chain are realized by predicting the demand of the future electric energy meter, and the uncertainty and other difficulties of the supply chain caused by mankind and information island are fundamentally solved.
3. According to the invention, through the key factors of the full link and the characteristics of multiple characteristics and multiple targets, the fracture risk is reduced, the smooth production of the electric energy meter is ensured, the demand requirements can be quickly responded and satisfied, the supply chain operation efficiency is improved, the complex data arrangement work of business personnel is effectively reduced, and the purposes of optimizing the flow and improving the efficiency are achieved.
4. The invention monitors assets in the whole process by means of a demand forecasting and inventory control model, sends early warning signals to all related terminals, and if the early warning signals inform a shipper of possible delay, improves the on-time delivery rate of orders, ensures timely delivery of materials, reduces production delay, is flexible and can perfectly execute delivery demands without stopping.
5. The invention visually finds key problems through the data of the early warning signal, determines the priority decision and solves the problem, improves the interruption prediction capability and can take action according to the insight obtained from the data.
Drawings
FIG. 1 is a schematic diagram of the framework of the present invention;
FIG. 2 is a schematic flow chart of the method of the present invention.
Detailed Description
The invention is described in detail below with reference to the figures and specific embodiments. The present embodiment is implemented on the premise of the technical solution of the present invention, and a detailed implementation manner and a specific operation process are given, but the scope of the present invention is not limited to the following embodiments.
Example 1
Referring to fig. 1 and fig. 2, the present embodiment provides a method for monitoring and managing supply chain of an electric energy meter based on demand prediction, including the following steps: establishing an electric energy meter demand prediction model; acquiring electric energy meter planning data, and acquiring a demand prediction value based on the electric energy meter demand prediction model; and judging whether the supply chain fracture risk exists or not based on the demand predicted value, identifying a supply chain fracture link and generating an early warning signal.
Aiming at the conditions that the existing key business links such as plan submission, arrival verification, storage and delivery are not smooth, the follow-up process is blocked due to the fact that the front business is stopped, and business cooperation information is not shared sufficiently, on the basis of a production scheduling platform (MDS system), a demand forecasting and inventory control module is constructed, business data such as purchasing, arrival, verification and delivery are fully utilized, business thinking is supported by data, a business link rule is deeply mined, support is provided for purchasing measurement and calculation, functions such as fracture analysis, high-age library profit, auxiliary decision making and the like are provided for businesses such as arrival, verification, delivery and inventory, efficient and smooth metering supply chain processes are built, business cooperation, information sharing and process communication are accelerated, and supply chain closed-loop management of intelligent decision making and quality improvement and efficiency enhancement is realized.
As shown in fig. 1, the method is implemented based on a distributed multi-layer data structure, which is a data source, a data processing layer, a service layer, and an application layer.
(1) A data source: the business data source system for providing the electric energy meter demand prediction analysis comprises an MDS system, a marketing business application system, an electricity utilization information acquisition system, external related data and the like.
(2) A data processing layer: and providing a process for processing the quality data required by the electric energy meter demand prediction model, wherein the process comprises cleaning, processing, calculating, storing data and the like.
(3) A data service layer: the method mainly analyzes the service type and the equipment code type related to the requirement of the electric energy meter, and provides external system data interface service and the like.
(4) Application of the display layer: the method provides a result interface of user operation and function display, and has the main functions of demand prediction, supply chain fracture analysis, inventory control, auxiliary decision making and the like, and the risk of supply chain fracture is pre-judged and controlled in advance, so that the fracture possibility of each link is reduced, and the risk of supply chain fracture is reduced.
The electric energy meter demand prediction model is established through the following steps: obtaining historical installation data from a data source; performing data preprocessing on the historical installation data; extracting installation quantity change influence characteristics through characteristic engineering; and learning and predicting the future demand of the material codes of the electric energy meter by adopting an artificial intelligence algorithm, and constructing and obtaining an electric energy meter demand prediction model.
Judging whether the supply chain fracture risk exists or not based on the demand forecast value can be divided into three steps:
a) judging whether a reasonable safety guarantee inventory gap needs to be supplemented or arranged for verification;
b) analyzing the fracture condition of each link and calculating and recommending the number of guaranteed months of each link;
c) and (4) analyzing, positioning fracture links and calculating the number of gaps under the principle of meeting distribution requirements.
The main functions that can be achieved based on the above supply chain break risk analysis include:
a) displaying the supply chain fracture condition according to the material code dimension of the electric energy meter, positioning the fracture link, prompting by using a gap number message, and early warning of fracture and warning of fracture in advance by using an auxiliary center;
b) inquiring according to the configuration of the guaranteed month number of each link, and supporting the selection of the guaranteed month number of each link to display the fracture condition;
c) displaying the consumption condition of the electric energy meter and the recommended replenishment quantity according to each business fracture link, and reminding business messages;
d) and displaying the breakage condition of the central supply chain and the suggested quantity of adopted restocks and the like by adopting a visualization technology.
Supply chain disruptions include reasonable safety assurance inventory disruptions, protocol inventory disruptions, placed order disruptions, in-transit cargo disruptions, certification disruptions, qualified inventory disruptions, and distribution disruptions.
1. Reasonable safety guarantee of stock fracture
Insufficient inventory or overstocked inventory is caused by variations in demand forecast, ordering, supplier supply, verification production, material storage, and the like. To prevent this, reasonable upper and lower stock limits need to be set. The minimum stock (reasonable safety guarantee stock) is a monitoring means for preventing shortage of stock, and the maximum stock (upper limit quantity of stock) is a monitoring means for preventing excessive stock. In addition, the upper limit of the inventory is as low as possible while balancing the risk of backlog and outage.
The input of the reasonable safety guarantee inventory breaking algorithm comprises an electric energy meter demand predicted value (guarantee month N), a service level, a quantity of arrived cargos, a supplier, a period of arrived cargos and a quantity of delivery demand, the output is a reasonable safety guarantee inventory value, a guarantee month number, a margin and a gap number, and the business process is divided into four steps:
a) calculating the reasonable safety guarantee inventory of each material according to the reasonable safety guarantee inventory model;
b) calculating the number of months for ensuring reasonable safety guarantee inventory;
c) on the basis of meeting distribution requirements, calculating the number of gaps in the reasonable safety guarantee inventory, judging whether a chain is broken or not, and judging whether auxiliary services need to carry out replenishment or arrange verification, arrival notification and the like;
d) and monitoring the consumption condition of the reasonable safety guarantee inventory, and judging that the consumed inventory is not lower than the quantity of the reasonable safety guarantee inventory.
Calculating the formula:
different devices have different reasonable safety and security inventories. Reasonable security guarantees inventory will dynamically adjust with time, equipment backlog rate, service level. The calculation method is as follows:
Figure BDA0003161955570000051
wherein: SafetyStock is the safety stock value, Z is the service level, ALT is the mean of the arrival period over a period of time, DSD is the standard deviation of the demand for material pickup over a period of time, AS is the mean demand for material pickup over a period of time, and LTSD is the standard deviation of the arrival period over a period of time.
2. Agreement inventory fragmentation
The input of the protocol inventory fragmentation algorithm comprises an electric energy meter demand prediction value (guarantee month N), a winning number, an executable proportion, an in-transit number, an inventory number and a scheduling number, the inventory number comprises qualified inventory, to-be-checked, newly purchased and the like, the output is a protocol inventory guarantee month number, a protocol inventory margin and a protocol inventory gap number, and the business process is divided into four steps:
a) calculating the inventory quantity of the protocols required to be matched in the month on the basis of the residual inventory quantity of the matchable protocols and the execution proportion of the medium standard suppliers by combining the demand prediction result;
b) calculating the inventory margin and the guaranteed month number of the protocol by combining the demand prediction result, the matching surplus number of the inventory of the protocol, the in-transit and other relevant factors;
c) on the basis of meeting distribution requirements, calculating the number of gaps in the protocol inventory, judging whether the gaps are broken or not, and assisting business whether replenishment or arrangement verification, arrival notification and the like are needed or not;
d) and monitoring the protocol inventory consumption condition, and judging that the consumed protocol inventory is not lower than the reasonable safety guarantee inventory number.
3. Ordered splitting
The input of the placed order breakage algorithm comprises an electric energy meter demand predicted value (guarantee month N), a bid amount, an order amount, an in-transit amount and an inventory amount, the output is a guaranteed month number of placed orders, a margin of placed orders and a gap number of placed orders, and the business process is divided into three steps:
a) calculating the margin of the placed order and the number of guaranteed months by combining the demand prediction result and associating factors such as on-the-way and qualified inventory on the basis of order placing data;
b) on the basis of meeting the distribution demand, calculating the number of gaps of the placed order, judging whether the order is broken or not, and whether the auxiliary business needs to carry out replenishment or arrange verification, arrival notice and the like;
c) and monitoring the consumption condition of the placed order, and judging that the consumed inventory number is not lower than the inventory number of the reasonable safety guarantee.
The logic for calculating the ordered fractures is as follows:
Figure BDA0003161955570000061
calculating margin of placed order
Order margin is as much as order margin + quantity of goods in transit + SUM (qualified in stock + qualified in stock and overdue + to-be-checked + newly-purchased) -SUM (N month demand forecast)
Remarking: the predicted number of N required months needs to be configured by considering the actual service
Figure BDA0003161955570000062
Determining the number of guaranteed months of the placed order
Firstly, calculating (SUM of primary stock and stock in transit + ordered number) ═ SUM { (qualified stock + qualified stock in transit + to be verified + newly purchased + to be verified for overrun) + transit + ordered number };
then, IF (sum of primary library inventory + number of orders in transit + number of orders placed-demand predicted value of future 1 month) is less than or equal to 0, IF true, judging whether (predicted value of future 1 month) is equal to 0, IF true, ensuring the number of months to be 0; if not, ensuring the number of months as [ sum of first-level stock + in transit + number of orders placed/predicted value of the 1 st month in the future ];
then, IF (sum of primary library inventory + number of orders placed on the way-demand predicted value of future month 1) is greater than 0, judging whether (sum of primary library inventory + number of orders placed on the way-demand predicted value of future month 1-demand predicted value of future month 2) is less than or equal to 0, IF true, ensuring that the number of months is 1+ (sum of primary library inventory + number of orders placed on the way-demand predicted value of future month 1)/demand predicted value of future month 2; if the number of the first-level warehouse stocks is false, judging whether the sum of the first-level warehouse stocks, the number of orders in transit, the demand predicted value of the future 1 month, the demand predicted value of the future 2 months, the demand predicted value of the future 3 months is less than or equal to 0, and if the sum of the first-level warehouse stocks, the number of orders in transit, the demand predicted value of the future 1 month, the demand predicted value of the future 2 months, or the demand predicted value of the future 3 months;
and so on.
Figure BDA0003161955570000071
Determining an ordered outage
IF (order guarantee month < n, yes, no);
remarking: the distribution requirement can be guaranteed only by guaranteeing the number of months and at least n months for the center to enter a qualified state after orders are placed, and configuration can be carried out.
4. Breaking of goods on the way
The input of the in-transit goods-arrival breakage algorithm comprises an electric energy meter demand predicted value (guarantee month N), a winning number, an arrival number, an in-transit number and an inventory number, the output is the in-transit goods guarantee month number, the in-transit goods margin and the in-transit goods gap number, and the business process is divided into three steps:
a) combining a demand prediction result, on the basis of supply plan data and under the conditions of relevant qualified inventory and other factors, counting the in-transit goods margin and the guaranteed month number;
b) on the basis of meeting distribution requirements, calculating the number of the on-the-way goods arriving gaps, judging whether the on-the-way goods arriving gaps are broken or not, and assisting business whether goods supplement or arrangement detection is needed or not;
c) and monitoring the goods in transit consumption condition, and judging that the stock number after consumption is not lower than the stock number of the reasonable safety guarantee.
The logic for calculating the break in transit is as follows:
Figure BDA0003161955570000081
calculating the in-transit arrival margin
In-transit freight margin is the in-transit freight quantity plus SUM (qualified in stock + qualified in stock and overdue + to-be-checked and newly purchased) -SUM (N month demand prediction value)
Remarking: n month demand forecast value, which needs to be configured by considering actual service
Figure BDA0003161955570000082
Determining the number of guaranteed months in transit
Firstly, calculating the SUM of first-level stock and in-transit, namely SUM { (qualified stock + qualified in-stock super + to-be-checked + newly purchased + to-be-checked overtime) + in-transit);
then, IF (sum of primary library inventory + predicted value of demand in the future at month 1) is less than or equal to 0, IF true, judging whether (predicted value of future at month 1) is equal to 0, IF true, ensuring that the number of months is 0; if not, ensuring the number of months as (sum of first-level stock of the storehouse + predicted value of the 1 st month in the way/future);
then, IF (sum of primary warehouse inventory + demand forecast value of on-way to future month 1) is greater than 0, judging whether (sum of primary warehouse inventory + demand forecast value of on-way to future month 1-demand forecast value of future month 2) is less than or equal to 0, IF true, ensuring that the number of months is 1+ (sum of primary warehouse inventory + demand forecast value of on-way to future month 1)/demand forecast value of future month 2; if the predicted value is false, judging whether the sum of the first-level warehouse inventory, the demand predicted value of the future 1 month, the demand predicted value of the future 2 months, the demand predicted value of the future 3 months is less than or equal to 0, and if the predicted value is true, ensuring that the number of months is 2+ (the sum of the first-level warehouse inventory, the demand predicted value of the future 1 month, the demand predicted value of the future 2 months)/the demand predicted value of the future 3 months;
and so on.
Figure BDA0003161955570000083
Judging the situation of the breakage of the procurement
IF break in the inbound supply chain occurs (guaranteed number of months < n, yes, no)
Remarking: the distribution requirement can be guaranteed only by at least n months for guaranteeing the number of months and the central arrival goods entering the qualified state, and configuration can be carried out.
5. Verification of fracture
The input of the verification fracture algorithm comprises an electric energy meter demand predicted value (guaranteed month N), the quantity of arriving goods, daily verification parameters, monthly verification parameters and the quantity of inventory, the output is verification guaranteed month number, verification margin and verification gap number, and the business process is divided into three steps:
a) combining a demand prediction result, and counting a verification margin and a guaranteed month number on the basis of verification tasks and under the relevant factors of qualified stock and the like;
b) on the basis of meeting distribution requirements, calculating the number of verification notches, displaying the number of fractures, assisting business whether to carry out replenishment or scheduling detection and the like;
c) and monitoring the verification consumption condition, and judging that the number of the consumed inventory is not lower than the number of the inventory with reasonable safety guarantee.
The computational logic for identifying a fracture is as follows:
Figure BDA0003161955570000091
calculating the verification margin
Verification margin is SUM (qualified in stock, qualified in stock and overdue, to-be-verified and overdue), to-be-verified and newly purchased) -SUM (predicted value of N-month demand)
Remarking: n month demand forecast value, which needs to be configured by considering actual service
Figure BDA0003161955570000092
Determining the number of months for verification guarantee
Firstly, calculating the SUM of primary Stock (SUM) (qualified stock + qualified stock in stock super + to be checked + newly purchased + to be checked super);
then, IF (sum of primary library inventory-predicted value of demand in the 1 st month in the future) is less than or equal to 0, IF true, judging whether (predicted value in the 1 st month in the future) is equal to 0, IF true, ensuring that the number of months is 0; if not, ensuring the number of months as [ sum of first-level stock/predicted value of future 1 month ];
then, IF (sum of primary library inventory-demand predicted value of future month 1) is greater than 0, judging whether (sum of primary library inventory-demand predicted value of future month 1-demand predicted value of future month 2) is less than or equal to 0, IF true, ensuring that the number of months is 1+ (sum of primary library inventory-demand predicted value of future month 1)/demand predicted value of future month 2; if the predicted value is false, judging whether the sum of the first-level warehouse inventory, the demand predicted value of the future 1 st month, the demand predicted value of the future 2 nd month and the demand predicted value of the future 3 rd month is less than or equal to 0, and if the predicted value is true, ensuring that the number of months is 2+ (the sum of the first-level warehouse inventory, the demand predicted value of the future 1 st month, the demand predicted value of the future 2 nd month) and the demand predicted value of the future 3 rd month;
and so on.
Figure BDA0003161955570000093
Judging the verification fracture condition
IF (verification guarantee month < n, yes, no)
Remarking: the distribution requirement can be guaranteed only by ensuring that the number of months and the central equipment to be detected need to enter a qualified state at least n months, and configuration can be carried out.
6. Breakage of qualified stock
The input of the qualified inventory fragmentation algorithm comprises an electric energy meter demand prediction value (guarantee month N), inventory to be determined, newly purchased inventory and actual distribution demand quantity, the output is the number of guarantee months, the qualification margin and the qualification gap number of the qualified inventory, and the business process is divided into three steps:
a) calculating the margin of qualified stock and the number of guaranteed months by combining a demand prediction result on the basis of the statistics of the qualified stock and under the association of factors such as reasonable safety guarantee stock and the like;
b) on the basis of meeting distribution requirements, calculating the number of gaps of qualified stock, displaying the number of fractures, assisting whether the business needs to carry out replenishment or scheduling detection and the like;
c) and monitoring the consumption condition of the qualified inventory, and judging that the inventory number after consumption is not lower than the inventory number of the reasonable safety guarantee.
The calculation logic for a qualified inventory break is as follows:
Figure BDA0003161955570000101
calculating the qualified inventory margin, namely ensuring that the inventory meets the abundant quantity required by the business in the previous link
And the qualified stock margin is qualified stock + qualified stock in stock exceeding time-the demand prediction value of the next N months.
Remarking: n months demand forecast value, and configuration needs to be carried out by considering actual service;
Figure BDA0003161955570000102
determining the number of months for qualified stock
Firstly, IF (qualified stock value-predicted value of demand in the 1 st month in the future) is less than or equal to 0, IF true, judging whether the (predicted value in the 1 st month in the future) is equal to 0, IF true, ensuring that the number of months is 0; if not, ensuring the number of months as (qualified stock value/predicted value of the future 1 st month);
then, IF (qualified stock value-demand predicted value of the next 1 month) is greater than 0, judging whether (qualified stock value-demand predicted value of the next 1 month-demand predicted value of the next 2 months) is less than or equal to 0, IF true, ensuring that the number of months is 1+ (qualified stock value-demand predicted value of the next 1 month)/demand predicted value of the next 2 months; if the predicted value is false, judging whether the [ qualified inventory value-demand predicted value of the future 1 st month-demand predicted value of the future 2 nd month-demand predicted value of the future 3 rd month ] is less than or equal to 0, and if the predicted value is true, ensuring that the number of months is 2+ (qualified inventory value-demand predicted value of the future 1 st month-demand predicted value of the future 2 nd month)/demand predicted value of the future 3 rd month;
and so on.
Figure BDA0003161955570000103
Judging the fracture condition of qualified stock
IF the qualified stock supply chain is broken (qualified stock guarantee month number < n, yes, no)
Remarking: the distribution requirement can be guaranteed only by guaranteeing that the equipment in the warehouse needs at least n months after the number of months and the central qualification are guaranteed, and configuration can be carried out.
7. Delivery break
The input of the distribution breakage algorithm comprises an electric energy meter demand predicted value (guarantee month N), an actual distribution quantity, qualified inventory, reasonable safety guarantee inventory, a distribution date, a replenishment quantity and an over-age reexamination qualified library, the output is a weekly distribution task, and the business process specifically comprises the following steps: based on the current distribution management service condition, the planning management and analysis are carried out on the distribution process, the distribution service flow is optimized, the distribution rhythm is influenced by early warning, key problem points are positioned, service personnel are reminded to carry out advanced management and control, the smoothness of the service at the front end of the distribution service is guaranteed, and the distribution requirement can be met
In another embodiment, the method further comprises: and calibrating automatic management based on the demand predicted value, wherein the automatic management comprises automatic calibration link, automatic distribution control and automatic inventory control, and the automatic regulation of inventory comprises inventory upper limit regulation, replenishment quantity regulation and over-age inventory management.
(1) Upper limit of stock
Each material has its own upper limit of inventory, which should be as low as possible while keeping the inventory level no lower than safe inventory. The upper inventory limit is affected by the accuracy of the safety inventory values, demand forecast values, and demand forecast models. Different materials have different stock upper limit values, and quantiles are dynamically adjusted according to demand prediction errors.
The formula adopted by the upper limit value adjustment is as follows:
Max=SafetyStock+Dpred+Z0.95
wherein Max is the upper limit value of the stock, SafetyStock is the safety stock value, DpredFor demand forecast, Z0.95The error between the predicted value and the true value of the demand prediction model is smaller than Z for the 0.95 quantile corresponding to the prediction error of the demand prediction model of the electric energy meter0.95The probability of (a) is 95%.
(2) Adjustment of replenishment quantity
The adjustment of the replenishment quantity is specifically as follows: and taking the monthly arrival period, the monthly demand predicted value, the monthly demand predicted deviation rate, the preset demand satisfaction rate and weight, the preset inventory backlog value and weight as data input, and outputting the optimal replenishment time and replenishment quantity of the materials through optimal model processing.
Calculating the formula: BC ═ - (T-D-SS)
BC: monthly bin filling value of materials
T: total inventory present + inventory in transit-inventory to be delivered
D: the required quantity of materials in the time period from the current day to the end of the next month
And SS: safety stock value of next month of material
(3) Ultra-aged inventory management
The high-age equipment with the storage age of more than 2 years is subjected to preferential, rapid and reasonable storage benefiting, so that the overstock of the inventory is avoided, and the turnover efficiency of the inventory is improved.
The above functions, if implemented in the form of software functional units and sold or used as a separate product, may be stored in a computer-readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
Example 2
The present embodiments provide an electronic device comprising one or more processors, memory, and one or more programs stored in the memory, the one or more programs including instructions for performing the electric energy meter supply chain monitoring management method based on demand forecasting of embodiment 1.
The foregoing detailed description of the preferred embodiments of the invention has been presented. It should be understood that numerous modifications and variations could be devised by those skilled in the art in light of the present teachings without departing from the inventive concepts. Therefore, the technical solutions available to those skilled in the art through logic analysis, reasoning and limited experiments based on the prior art according to the concept of the present invention should be within the scope of protection defined by the claims.

Claims (10)

1. A demand prediction-based electric energy meter supply chain monitoring and management method is characterized by comprising the following steps:
establishing an electric energy meter demand prediction model;
acquiring electric energy meter planning data, and acquiring a demand prediction value based on the electric energy meter demand prediction model;
and judging whether the supply chain fracture risk exists or not based on the demand predicted value, identifying a supply chain fracture link and generating an early warning signal.
2. The demand prediction based monitoring and management method for the supply chain of the electric energy meter according to claim 1, wherein the demand prediction model of the electric energy meter is established by the following steps:
acquiring historical installation data;
performing data preprocessing on the historical installation data;
extracting installation quantity change influence characteristics through characteristic engineering;
and learning and predicting the future demand of the material codes of the electric energy meter by adopting an artificial intelligence algorithm, and constructing and obtaining an electric energy meter demand prediction model.
3. The demand forecast based electric energy meter supply chain monitoring and management method according to claim 2, characterized in that the data preprocessing comprises data cleaning, data processing, data calculation and data storage.
4. The method for monitoring and managing the supply chain of the electric energy meter based on the demand forecast of claim 1, wherein the supply chain breaking links comprise a reasonable safety guarantee inventory breaking, a protocol inventory breaking, an order made breaking, an in-transit cargo breaking, a certification breaking, a qualified inventory breaking and a delivery breaking.
5. The method for monitoring and managing the supply chain of an electric energy meter based on demand prediction according to claim 1, further comprising:
and adjusting the inventory quantity based on the demand forecast value, wherein the adjustment comprises the adjustment of an inventory upper limit value and the adjustment of the replenishment quantity.
6. The demand forecast based energy meter supply chain monitoring and management method according to claim 5, wherein the inventory upper limit value is adjusted by the formula:
Max=SafetyStock+Dpred+Z0.95
wherein Max is the upper limit value of the stock, SafetyStock is the safety stock value, DpredFor demand forecast, Z0.95And the quantile is 0.95 quantile corresponding to the prediction error of the demand prediction model of the electric energy meter.
7. The method for monitoring and managing the supply chain of the electric energy meter based on the demand forecasting as recited in claim 5, wherein the adjustment of the replenishment quantity is specifically as follows:
and taking the monthly arrival period, the monthly demand predicted value, the monthly demand predicted deviation rate, the preset demand satisfaction rate and weight, the preset inventory backlog value and weight as data input, and outputting the optimal replenishment time and replenishment quantity of the materials through optimal model processing.
8. The method for monitoring and managing the supply chain of the electric energy meter based on the demand forecasting according to claim 1, wherein the early warning signals comprise supply chain breaking links, guaranteed months and gaps.
9. An electronic device, comprising:
one or more processors;
a memory; and
one or more programs stored in the memory, the one or more programs including instructions for performing the method for demand prediction based supply chain monitoring management of an electric energy meter according to any of claims 1-8.
10. A computer readable storage medium including one or more programs for execution by one or more processors of an electronic device, the one or more programs including instructions for performing a method for demand prediction based supply chain monitoring management of an electric energy meter according to any of claims 1-8.
CN202110793546.7A 2021-07-14 2021-07-14 Electric energy meter supply chain monitoring and management method and device based on demand prediction Pending CN113554291A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110793546.7A CN113554291A (en) 2021-07-14 2021-07-14 Electric energy meter supply chain monitoring and management method and device based on demand prediction

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110793546.7A CN113554291A (en) 2021-07-14 2021-07-14 Electric energy meter supply chain monitoring and management method and device based on demand prediction

Publications (1)

Publication Number Publication Date
CN113554291A true CN113554291A (en) 2021-10-26

Family

ID=78131700

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110793546.7A Pending CN113554291A (en) 2021-07-14 2021-07-14 Electric energy meter supply chain monitoring and management method and device based on demand prediction

Country Status (1)

Country Link
CN (1) CN113554291A (en)

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
ES2529816A2 (en) * 2013-03-05 2015-02-25 Antonio Madueño Luna System and procedure based on a synchronism sensor for the detection of malfunctions in pitting machines/olive fillers and fillers, quantification and optimization of performance, signaling, monitoring and remote control (Machine-translation by Google Translate, not legally binding)
CN105139090A (en) * 2015-08-25 2015-12-09 国网天津市电力公司 Power industry safety stock decision analysis method based on consumption prediction
US20180075401A1 (en) * 2016-09-13 2018-03-15 International Business Machines Corporation Allocating a product inventory to an omnichannel distribution supply chain
CN108108938A (en) * 2017-12-12 2018-06-01 广东电网有限责任公司江门供电局 A kind of electric energy meter demand Forecast of Inventory system and method
CN108241343A (en) * 2016-12-24 2018-07-03 青岛海尔模具有限公司 A kind of intelligent plant management platform system
CN110334849A (en) * 2019-05-30 2019-10-15 深圳壹账通智能科技有限公司 Resource method for early warning, device and computer equipment based on data monitoring
CN110516998A (en) * 2019-08-14 2019-11-29 广州淘通科技股份有限公司 One kind is based on the associated intelligent replenishment system of supply chain demand
CN111915254A (en) * 2020-07-30 2020-11-10 上海数策软件股份有限公司 Inventory optimization control method and system suitable for automobile after-sales accessories
CN112053082A (en) * 2020-09-15 2020-12-08 四川创客知佳科技有限公司 Material management system based on cloud computing
CN112950267A (en) * 2021-02-26 2021-06-11 北京京东乾石科技有限公司 Information generation method and device, terminal equipment and storage medium

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
ES2529816A2 (en) * 2013-03-05 2015-02-25 Antonio Madueño Luna System and procedure based on a synchronism sensor for the detection of malfunctions in pitting machines/olive fillers and fillers, quantification and optimization of performance, signaling, monitoring and remote control (Machine-translation by Google Translate, not legally binding)
CN105139090A (en) * 2015-08-25 2015-12-09 国网天津市电力公司 Power industry safety stock decision analysis method based on consumption prediction
US20180075401A1 (en) * 2016-09-13 2018-03-15 International Business Machines Corporation Allocating a product inventory to an omnichannel distribution supply chain
CN108241343A (en) * 2016-12-24 2018-07-03 青岛海尔模具有限公司 A kind of intelligent plant management platform system
CN108108938A (en) * 2017-12-12 2018-06-01 广东电网有限责任公司江门供电局 A kind of electric energy meter demand Forecast of Inventory system and method
CN110334849A (en) * 2019-05-30 2019-10-15 深圳壹账通智能科技有限公司 Resource method for early warning, device and computer equipment based on data monitoring
CN110516998A (en) * 2019-08-14 2019-11-29 广州淘通科技股份有限公司 One kind is based on the associated intelligent replenishment system of supply chain demand
CN111915254A (en) * 2020-07-30 2020-11-10 上海数策软件股份有限公司 Inventory optimization control method and system suitable for automobile after-sales accessories
CN112053082A (en) * 2020-09-15 2020-12-08 四川创客知佳科技有限公司 Material management system based on cloud computing
CN112950267A (en) * 2021-02-26 2021-06-11 北京京东乾石科技有限公司 Information generation method and device, terminal equipment and storage medium

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
周建亨;周剑;: "一种基于风险因子的供应链模型分析", 东华大学学报(自然科学版), no. 02, pages 202 - 207 *
温翔: "供应链风险种类及预防措施", 《铁道货运》, no. 4, pages 9 - 11 *

Similar Documents

Publication Publication Date Title
CN107516175B (en) Inventory allocation method and device
CN109272276B (en) Inventory replenishment management method and device
CN117114583B (en) Supply chain management system based on cloud service platform
CN112200394B (en) Logistics distribution system and method for electronic trading platform
CN111199309A (en) Early warning management and control system of electric power material supply chain operation
CN112529491B (en) Inventory management method and device
CN107705056A (en) Inventory state monitoring method and device, server and client
CN109658010A (en) The management method and device of food materials
CN112330255B (en) warehouse management system
CN111144632A (en) Prediction management and control model for power storage materials
US20200327626A1 (en) Reducing the cost of electrical energy in a manufacturing plant
CN109508885A (en) Concocting method and device, storage medium, the processor of spare part
CN110210946A (en) Data processing method and device, medium and calculating equipment
CN102073940A (en) Station platform dynamic distribution method and system during on-line reservation of supplier
CN109409791A (en) A kind of industry supply chain intelligent management system
CN113538028A (en) Advertisement putting method and device
CN114676881A (en) Spare part inventory prediction method and device
KR102518108B1 (en) system and method for Appropriate inventory prediction through big data
CN113554291A (en) Electric energy meter supply chain monitoring and management method and device based on demand prediction
CN117219242A (en) Medical service supply chain platform and method
CN113850448B (en) Management method and system for consumption and scheduling of spare parts
Udayakumar et al. Supply chain coordination with controllable lead time under imperfect production process
Jianfeng et al. Research on the optimization strategy of maintenance spare parts inventory management for petrochemical vehicle
KR20220135435A (en) Big data-based order quantity prediction system
JP2006318254A (en) Automatic inventory management system

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