CN114169944B - User demand determination method and device, storage medium and electronic equipment - Google Patents
User demand determination method and device, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN114169944B CN114169944B CN202210090708.5A CN202210090708A CN114169944B CN 114169944 B CN114169944 B CN 114169944B CN 202210090708 A CN202210090708 A CN 202210090708A CN 114169944 B CN114169944 B CN 114169944B
- Authority
- CN
- China
- Prior art keywords
- user
- cost
- inventory
- determining
- vehicle transportation
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
- G06Q10/08355—Routing methods
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0206—Price or cost determination based on market factors
-
- 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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Human Resources & Organizations (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides a user demand determination method and device, a storage medium and electronic equipment, and relates to the technical field of logistics. The user demand determining method comprises the steps of firstly constructing a first inventory routing model for determining vehicle transportation cost and a second inventory routing model for determining user cost, then calculating corresponding vehicle transportation cost and user cost according to historical distribution data of each user in a preset period, finally judging whether the obtained vehicle transportation cost and the user cost meet preset conditions or not, if so, determining a target transportation route for each user according to the current vehicle transportation cost, and determining target commodity demands of each retail user according to the user cost, so that the demands of each user are determined. The technical problem that the feasibility of the existing routing inventory scheme is low in the prior art is solved, and the technical effect of improving the feasibility of the inventory route scheme is achieved.
Description
Technical Field
The present application relates to the field of logistics technologies, and in particular, to a method and an apparatus for determining a user demand, a storage medium, and an electronic device.
Background
In recent years, to reduce Inventory costs and integrate supply chain resources, a Vendor Managed Inventory (VMI) model has gradually entered into large enterprises, where Inventory decisions for retail merchant products are given to the Vendor, who then takes the right to exercise the Inventory decisions in place of its customers. In order to control the logistics and distribution cost of the supply chain as a whole, suppliers need to consider the inventory cost and the transportation and distribution cost of each retailer cooperatively, and make efficient decisions on inventory control and vehicle running paths, so as to provide a high-quality logistics distribution scheme, namely, provide the most scientific inventory routing scheme.
In the current research of the inventory routing distribution system of an enterprise, aiming at the commodity demands of customers, most of the research assumes that the deterministic demands or the demand probability distribution are known, and the feasibility of the optimal solution obtained by the traditional deterministic model is generally reduced or becomes infeasible in practice; the random fluctuation required in the random optimization model also makes it difficult to obtain probability distribution information of the random parameters of the system, so that the feasibility of the optimal solution of the model is reduced in practice.
Therefore, the feasibility of the current routing inventory scheme is low.
Disclosure of Invention
The application provides a user requirement determining method, a user requirement determining device, a storage medium and electronic equipment, and further improves feasibility of a current routing inventory scheme.
In a first aspect, an embodiment of the present application provides a user requirement determining method, including:
determining vehicle transportation cost based on historical distribution data of each user in a preset period and a pre-constructed first inventory routing model;
determining the user cost of each user based on historical distribution data, vehicle transportation cost and a pre-constructed second inventory routing model for each user in a preset period;
and if the vehicle transportation cost and the user cost meet the preset conditions, determining a target transportation route for each user according to the vehicle transportation cost, and determining the target commodity requirement of each user according to the user cost.
In an optional embodiment of the present application, the method for constructing the second inventory routing model includes:
dividing historical distribution data of each user into a plurality of uncertainty sets according to a preset distribution scene;
determining the conditional probability that the commodity demand of each user belongs to the uncertainty set in the historical distribution data of each user;
and constructing a second inventory routing model based on the conditional probability and the holding inventory cost and the stock shortage cost of each user in the historical distribution data of each user.
In an optional embodiment of the present application, dividing historical delivery data of each user into a plurality of uncertainty sets according to a preset delivery scenario includes:
clustering the historical distribution data of each user according to a preset distribution scene to obtain a plurality of cluster sets;
determining a plurality of sets of clusters as a plurality of sets of uncertainties; and the historical delivery data of the users in each cluster set belong to the same delivery scene.
In an optional embodiment of the present application, constructing the second inventory routing model based on the conditional probability and the holding inventory cost and the out-of-stock cost of each user in the historical distribution data of each user includes:
constructing an initial user cost model based on the inventory cost and the stock shortage cost of each user in the historical distribution data of each user;
constructing a Lagrange dual function of an initial user cost model to obtain a user cost model;
a second inventory routing model is constructed based on the conditional probability and the user cost model.
In an optional embodiment of the present application, the method further comprises:
determining an initial total inventory cost according to the vehicle transportation cost and the user cost under a first distribution constraint;
under the second distribution constraint, inputting the user cost into the first inventory routing model, and calculating new vehicle transportation cost based on a branch boundary shearing method; wherein the second delivery constraint has a constraint greater than the first delivery constraint;
determining a new total inventory cost based on the new vehicle transportation cost and the user cost;
and judging whether the difference value between the new inventory total cost and the initial inventory total cost is smaller than a preset threshold value.
In an optional embodiment of the present application, if the vehicle transportation cost and the user cost meet a preset condition, determining a target transportation route for each user according to the vehicle transportation cost, and determining a target commodity demand of each user according to the user cost includes:
and if the difference value between the new inventory total cost and the initial inventory total cost is smaller than a preset threshold value, determining a target transportation route for each user according to the vehicle transportation cost or the new vehicle transportation cost, and determining the target commodity requirement of each user according to the user cost.
In an optional embodiment of the present application, the method further comprises:
if the difference value between the new inventory total cost and the inventory total cost is not less than a preset threshold value, increasing a constraint condition of a second delivery constraint;
and under a new second delivery constraint, continuously determining new vehicle transportation cost based on historical delivery data of each user in a preset period and a pre-constructed first inventory routing model until the difference value between the new inventory total cost and the initial inventory total cost is smaller than a preset threshold value.
In a second aspect, an embodiment of the present application provides a user requirement determining apparatus, including:
the first determining module is used for determining vehicle transportation cost based on historical distribution data of each user in a preset period and a pre-constructed first inventory routing model;
the second determining module is used for determining the user cost of each user based on historical distribution data, vehicle transportation cost and a second pre-constructed inventory routing model for each user in a preset period;
and the third determining module is used for determining a target transportation route for each user according to the vehicle transportation cost and determining the target commodity requirement of each user according to the user cost if the vehicle transportation cost and the user cost meet preset conditions.
In a third aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored, which, when executed by a processor, implements the method as above.
In a fourth aspect, an embodiment of the present application provides an electronic device, including: a processor; and a memory for storing executable instructions for the processor; wherein the processor is configured to perform the above method via execution of the executable instructions.
The technical scheme of this application has following beneficial effect:
according to the user demand determining method, a first inventory routing model used for determining vehicle transportation cost and a second inventory routing model used for determining user cost are constructed, corresponding vehicle transportation cost and user cost are obtained through calculation according to historical distribution data of users in a preset period, and whether the obtained vehicle transportation cost and the user cost meet preset conditions or not is judged.
The method for determining the customer demand divides the solving process of the traditional inventory routing problem into two stages, firstly determines and obtains the vehicle transportation cost through the first inventory routing model, then determines and obtains the user cost of each retail user based on the obtained vehicle transportation cost and the second inventory routing model, does not need to introduce customer demands in the determining process, avoids the technical problems that the customer demands need to be introduced when a random optimization model is adopted in the traditional user demand determination process, the random fluctuation of the customer demands easily causes low feasibility of the actually obtained customer demands, does not need to introduce uncertainty of the customer demands, and can determine and obtain target transportation routes and target commodity demands through the historical distribution data of each user and the pre-constructed first inventory routing model and the second inventory routing model in two nodes, and the customer requirements are not introduced, so that the obtained target transportation route and the target commodity requirements are higher in feasibility in practical application.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and together with the description, serve to explain the principles of the application. It is obvious that the drawings in the following description are only some embodiments of the present application, and that for a person skilled in the art, other drawings can be derived from these drawings without inventive effort.
Fig. 1 is a schematic diagram illustrating an application scenario of a user requirement determining method in the exemplary embodiment;
FIG. 2 illustrates a flow chart of a user requirement determination method in the present exemplary embodiment;
FIG. 3 shows a flow chart of a user requirement determination method in the present exemplary embodiment;
FIG. 4 illustrates a flow chart of a user requirement determination method in the present exemplary embodiment;
FIG. 5 shows a flow chart of a user requirement determination method in the present exemplary embodiment;
FIG. 6 shows a flow chart of a user requirement determination method in the present exemplary embodiment;
FIG. 7 shows a flowchart of a user requirement determination method in the present exemplary embodiment;
FIG. 8 illustrates a flow chart of a user requirement determination method in the present exemplary embodiment;
FIG. 9 is a schematic diagram of a user requirement determining apparatus according to the exemplary embodiment;
fig. 10 shows a schematic configuration diagram of an electronic device in the present exemplary embodiment.
Detailed Description
Exemplary embodiments will now be described more fully with reference to the accompanying drawings. The exemplary embodiments, however, may be embodied in many different forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the application. One skilled in the relevant art will recognize, however, that the subject matter of the present application can be practiced without one or more of the specific details, or with other methods, components, devices, steps, and so forth. In other instances, well-known technical solutions have not been shown or described in detail to avoid obscuring aspects of the present application.
Furthermore, the drawings are merely schematic illustrations of the present application and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus their repetitive description will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor devices and/or microcontroller devices.
The flow charts shown in the drawings are merely illustrative and do not necessarily include all of the steps. For example, some steps may be decomposed, and some steps may be combined or partially combined, so that the actual execution sequence may be changed according to the actual situation.
In the related art, in order to reduce Inventory costs and integrate supply chain resources in recent years, a Vendor Managed Inventory (VMI) model, in which Inventory decision rights of retail store commodities are given to a Vendor and the Vendor exercises Inventory decision rights instead of its customers, has gradually entered into large enterprises. In order to control the logistics and distribution cost of the supply chain as a whole, suppliers need to consider the inventory cost and the transportation and distribution cost of each retailer cooperatively, and make efficient decisions on inventory control and vehicle running paths, so as to provide a high-quality logistics distribution scheme, namely, provide the most scientific inventory routing scheme. In the current research of the inventory routing distribution system of an enterprise, aiming at the commodity demands of customers, most of the research assumes that the deterministic demands or the demand probability distribution are known, and the feasibility of the optimal solution obtained by the traditional deterministic model is generally reduced or becomes infeasible in practice; the random fluctuation required in the random optimization model also makes it difficult to obtain probability distribution information of the random parameters of the system, so that the feasibility of the optimal solution of the model is reduced in practice. Therefore, the feasibility of the current routing inventory scheme is low.
In view of the foregoing problems, an embodiment of the present application provides a user demand determining method, where a first inventory routing model for determining vehicle transportation costs and a second inventory routing model for determining user costs are first constructed, then corresponding vehicle transportation costs and user costs are obtained through calculation for historical delivery data of each user in a preset period, and finally, whether the obtained vehicle transportation costs and user costs meet preset conditions is judged, if so, a target transportation route for each user is determined according to a current vehicle transportation cost, and a target commodity demand of each user is determined according to the user costs, so as to determine the demand of each user.
The method for determining the customer demand divides the solving process of the traditional inventory routing problem into two stages, firstly determines and obtains the vehicle transportation cost through the first inventory routing model, then determines and obtains the user cost of each retail user based on the obtained vehicle transportation cost and the second inventory routing model, does not need to introduce customer demands in the determining process, avoids the technical problems that the customer demands need to be introduced when a random optimization model is adopted in the traditional user demand determination process, the random fluctuation of the customer demands easily causes low feasibility of the actually obtained customer demands, does not need to introduce uncertainty of the customer demands, and can determine and obtain target transportation routes and target commodity demands through the historical distribution data of each user and the pre-constructed first inventory routing model and the second inventory routing model in two nodes, and the customer requirements are not introduced, so that the obtained target transportation route and the target commodity requirements are higher in feasibility in practical application.
The following briefly introduces an application environment of the user requirement determining method provided by the embodiment of the present application:
referring to fig. 1, a method for determining a user requirement provided by an embodiment of the present application is applied to a logistics distribution system 10, where the logistics distribution system 10 at least includes: a service terminal 101, a provider terminal 102 on the provider side, and a user terminal 103 on each user side. The supply terminal 102 is used for storing and updating the distribution data such as the types, the stock quantity, the types and the quantity of the commodities distributed to each user and the like of the commodities stored at the current supplier side; the user terminal 103 is used for storing information of received commodities of each user, such as the types, the quantities, the receiving time, the distribution vehicle identification and the like of the commodities, and the user can be a retailer user or a wholesaler user; the service terminal 101 is used for performing distribution management based on historical distribution data of the supply terminal 102 or the user terminal 103, for example, determining user requirements of each user based on each historical data, so as to provide an optimal inventory routing scheme for commodity distribution of each user.
Taking the service terminal 101 as an execution subject, the user demand determination method applied to the service terminal 101 is described as an example, and an optimal inventory routing scheme for commodity distribution for each user is described as an example. Referring to fig. 2, the method for determining user requirements according to the embodiment of the present application includes the following steps 201 to 203:
The historical distribution data obtaining method at least includes the following two methods: in the first mode, the service terminal acquires distribution data such as the type, the quantity, the time and the like of commodities received in each distribution through the user terminal of each retail user side; in the second method, the service terminal acquires delivery data such as the types, amounts, delivery routes, delivery times, and the like of the retail customers, the delivered commodities, and the like at each delivery through the provider-side supply terminal. The logistics management personnel can firstly fit a first inventory routing model used for determining and obtaining the current vehicle transportation cost based on the distribution routes and the like and the vehicle transportation cost in the massive historical distribution data, and store the first inventory routing model in the service terminal. The vehicle transportation cost refers to a cost generated in the process of delivering the commodities to each retail user by a delivery vehicle, and the influence factors of the vehicle transportation cost include: the type of the delivery vehicle, the delivery route, the number of delivery personnel, etc. And the service terminal inputs the acquired historical distribution data in the preset period into the first inventory routing model, and then the transportation cost of the vehicle can be output.
The user cost refers to a fee generated by the retail user due to storage of the received commodity, sale delay of the commodity, and the like. The logistics manager may first fit a second inventory routing model for determining customer costs based on the mass historical delivery data and store the second inventory routing model in the service terminal. The service terminal inputs the historical distribution data of each user in the preset period and the vehicle transportation cost obtained in the step 201 into the second inventory routing model, and the user cost of each user can be output.
And 203, if the vehicle transportation cost and the user cost meet preset conditions, the service terminal determines a target transportation route for each user according to the vehicle transportation cost, and determines a target commodity requirement of each user according to the user cost.
The solution of the traditional inventory routing problem is to formulate a final optimal delivery scheme, and the embodiment of the application combines the transportation cost of a supplier and the user cost of each retail user to comprehensively determine a target delivery scheme, wherein the target delivery scheme comprises delivery transportation routes and target commodity requirements of each retail user. Different transportation routes correspond to different vehicle transportation costs, and different commodity demand retail users correspondingly need to bear different user costs, so that the service terminal can determine to obtain the corresponding transportation route according to the current vehicle transportation cost, and determine to obtain the commodity demand corresponding to the retail user according to the current user cost. The preset condition in the embodiment of the present application may be any one of the following conditions: first, the sum of transportation costs and user costs is minimized; secondly, the transportation cost and the user cost reach a certain ratio, such as 1:1.2, 1:1.1 and the like; third, the weighted sum of the shipping cost and the user cost is minimized. Of course, the preset conditions include, but are not limited to, the above three conditions, which are not exhaustive and can be specifically set according to the actual situation.
After continuously calculating the current vehicle transportation cost and the user cost, the service terminal judges whether the current vehicle transportation cost and the user cost meet any one of the preset conditions, if so, determines a target transportation route for each retail user according to the current vehicle transportation cost, and determines the target commodity requirement of each user according to the current user cost. Otherwise, calculating new vehicle transportation cost and new user cost again according to the step 201 and the step 202 until the obtained new vehicle transportation cost and the new user cost meet preset conditions, and respectively determining a target transportation route and a target commodity demand according to the current, namely the new vehicle transportation cost and the new user cost.
The embodiment of the application provides a user demand determining method, a first inventory routing model used for determining vehicle transportation cost and a second inventory routing model used for determining user cost are constructed firstly, then corresponding vehicle transportation cost and user cost are obtained through calculation according to historical distribution data of users in a preset period, finally, whether the obtained vehicle transportation cost and the obtained user cost meet preset conditions or not is judged, if yes, a target transportation route for each retail user is determined according to the current vehicle transportation cost, and target commodity demands of the users are determined according to the user cost, so that the user demands are determined.
The method for determining the customer demand divides the solving process of the traditional inventory routing problem into two stages, firstly determines and obtains the vehicle transportation cost through the first inventory routing model, then determines and obtains the user cost of each retail user based on the obtained vehicle transportation cost and the second inventory routing model, does not need to introduce customer demands in the determining process, avoids the technical problems that the customer demands need to be introduced when a random optimization model is adopted in the traditional user demand determination process, the random fluctuation of the customer demands easily causes low feasibility of the actually obtained customer demands, does not need to introduce uncertainty of the customer demands, and can determine and obtain target transportation routes and target commodity demands through the historical distribution data of each user and the pre-constructed first inventory routing model and the second inventory routing model in two nodes, and the customer requirements are not introduced, so that the obtained target transportation route and the target commodity requirements are higher in feasibility in practical application.
Referring to fig. 3, in an alternative embodiment of the present application, the method for constructing the second inventory routing model includes the following steps 301 to 303:
In this embodiment, the service terminal may divide the historical distribution data of all the users according to a preset distribution scene, or may divide the commodity demand data in the historical distribution data of each user according to a preset distribution scene. The uncertainty set refers to a data set of all commodity demands in the same preset distribution scene. The preset distribution scene may include: the method comprises the steps of daily preset distribution scenes, holiday preset distribution scenes, intermittent preset distribution scenes and the like, wherein under different preset distribution scenes, the commodity demands corresponding to retail users are different. According to the method and the device, historical distribution data of each user are divided into different uncertainty sets through the preset distribution scenes, the preset distribution scenes of user demand data in each uncertainty set are the same, the problem that target commodity demands of retail users are difficult to predict due to large random fluctuation of customer demands can be effectively solved, the accuracy of the target commodity demands is improved, and the reliability of the user demand determination method provided by the embodiment of the application is further improved.
In a particular embodiment, the set of uncertaintiesD m Can be determined according to the following equation (1):
in the formula (1), the first and second groups,
The conditional probability of the uncertainty set refers to a ratio of the commodity demand of each retail user in each preset distribution scene to the total commodity demand in all scenes. The historical distribution data of (2) includes various data such as commodity demand data of each retail customer, route data of each distribution, commodity category data, commodity quantity data, and the like. After obtaining the uncertainty sets in step 301, the service terminal respectively determines the conditional probability that the obtained historical commodity requirement under each preset delivery scenario belongs to the corresponding uncertainty set, for example, the firstmHistorical commodity demand under individual preset delivery scened m Belonging to the corresponding uncertainty setCombination of Chinese herbsD m Conditional probability of (2)p m That is, the firstiA historical commodity demand top m Is in the uncertainty setD m 。
And step 303, the service terminal constructs a second inventory routing model based on the conditional probability and the holding inventory cost and the stock shortage cost of each user in the historical distribution data of each user.
After obtaining the conditional probability, the service terminal may construct a second inventory routing model based on the holding cost and the stock out cost of the retail customer. The inventory cost refers to the expenditure cost generated by storage, commodity sale delay, commodity expiration, damage and the like after the retail user receives the commodities delivered by the supplier; the out-of-stock cost refers to the loss of revenue to the retail customer due to out-of-stock due to the supply customer delivering less merchandise to the retailer than the actual merchandise demand of the retail customer.
In the embodiment of the present application, the service terminal comprehensively determines a second inventory routing model for determining the user cost based on the holding inventory cost and the stock out cost of the user and the conditional probability obtained in step 302, and constructs the second inventory routing model from multiple dimensions, so that the reliability of the second inventory routing model is greatly improved, and the accuracy and the reliability of the user demand determination method provided by the embodiment of the present application are further improved.
In a particular embodiment, the second inventory routing model may be the following equation (2):
in the formula (2), the first and second groups,Z 2a second inventory routing model is represented that,Mrepresents the total number of all the preset delivery scenarios,mis shown asmA preset delivery scenario is set up, and,p m denotes the firstmThe conditional probability under each preset delivery scenario,Q m (y,d) Denotes the firstmRetail sales under individual preset distribution scenarioThe user's holding inventory cost and backorder cost;D m is shown asmUncertainty set under each scene;dis shown asmHistorical commodity demand in the uncertainty set for an individual scenario.
In a particular embodiment, the first inventory routing model may be of the following formula (3):
in the formula (3), the first and second groups of the compound,Z 1a first inventory routing model is represented and,c ij represents from the firstiFrom a retail customer tojThe cost of the shipping line for the individual retail customer;x ij kt indicating delivery vehicleskIn thattWithin a time period fromiThe retail user arrives atjA retail customer, if passing through the linex ij kt Take 1, if not pass through the line, thenx ij kt Taking 0;vrepresents the collection of all of the retail users,Trepresenting a total period of the acquired historical delivery data; u denotes the set of all delivery vehicles.
Combining the above equation (2) and equation (3) to obtain the target inventory routing model (4) in the embodiment of the present application:
in the formula (4), the first and second groups of the chemical reaction are shown in the specification,Zrepresenting the target inventory routing model, the physical meaning of the other letters or symbols are as above equation (2) and equation (3).
Referring to fig. 4, in an alternative embodiment of the present application, as described in step 301 above, the service terminal divides the historical delivery data of each user into a plurality of uncertainty sets according to a preset delivery scenario, including the following steps 401 to 402:
After obtaining the historical distribution data of each user, the service terminal takes each preset distribution scene as a category characteristic, then carries out clustering processing on the historical distribution data of all users based on an internally pre-stored clustering algorithm, and then generates a plurality of clustering sets. It should be noted that the preset delivery scenarios in different cluster sets are different.
The historical distribution data of the users in each cluster set belong to the same distribution scene, and the service terminal divides the historical distribution data of the users belonging to the same distribution scene into one cluster set through step 401. In the embodiment of the application, the preset delivery scenes of the historical delivery data in the same cluster set are the same, and therefore, each cluster set is determined to be an uncertainty set.
According to the method and the device for determining the user demand, the historical distribution data of each user are clustered according to the preset distribution scene to obtain the plurality of cluster sets, then the cluster sets after clustering are determined to be the uncertain sets, the clustering method is simple, a large amount of data calculation can be avoided, the determining efficiency of the uncertain sets can be greatly improved, and the determining efficiency of the user demand determining method provided by the embodiment of the application is further improved.
Referring to fig. 5, in an alternative embodiment of the present application, the service terminal constructs a second inventory routing model based on the conditional probabilities and the holding inventory cost and the out-of-stock cost of each user in the historical distribution data of each user as in step 303, which includes the following steps 501-503:
For example, the service terminal may construct the following initial user cost model (5) based on the holding inventory cost and the stock out cost:
in the formula (5), the first and second groups,Q m (y,d) A model of the initial user cost is represented,h i representing retail usersiThe cost of the unit inventory holding of (c),I i t representing retail customersiIn thattThe amount of inventory in the time period,p i representing retail customersiThe unit stock out cost of (a) is,u i t representing retail usersiIn thattThe number of out-of-stock items in the time period,vrepresents the collection of all of the retail users,Trepresenting a total period of the acquired historical delivery data;D m is shown asmUncertainty set under each scenario.
The service terminal obtains the initial user cost model as in step 501 above, that is, obtains the cost model as in equation (3) aboveQ m (y,d) Then, a Lagrange multiplier is set first,α t ∈R，β it ∈R，γ it ≥0，ω it ≥0，ψ kit ≥0，ν kt and (3) more than or equal to 0, then introducing the constraint in other distribution through the Lagrangian multiplier, and constructing to obtain the Lagrangian function of the formula (6), namely obtaining the Lagrangian dual function of the following formula (6):
in the formula (6), the first and second groups,α t 、β it 、ω it 、ψ kit 、ν kt are all made oftIn time periods, with respect to different strips in the delivery processPart constraint which can be specifically set according to actual conditions;d i t representtWithin a time period, retail customersiHistorical commodity requirements of (2);C i representing retail usersiMaximum inventory holding amount of;r it to representtThe number of products available to the supplier during the time period;y i kt is shown intWithin a time period, retail customersiDistributed vehiclekThe access, if accessed,kget 1, if not accessed, thenkTaking 1;Q k indicating delivery vehicleskThe capacity of (a) is set to be,Kthe maximum capacity is indicated by the number of cells,y 0 kt is shown intThe retail customer at the delivery starting point is delivered the vehicle during the time periodkAccess, typically take 1;Nrepresenting a total number of retail users;Tindicating the total period of the acquired historical delivery data.
The service terminal obtains the conditional probability through the above step 302p m A second inventory routing model may then be constructed as follows: first, the probability that the service terminal will obtainp m The product calculation is carried out with the function in the formula (6), and then a second inventory routing model can be obtained; in the second way, the service terminal firstly converts the form, constraint and the like in the formula (6), and then the converted function and the probability that the service terminal will obtain are obtainedp m And performing product calculation to obtain a second inventory routing model.
According to the method and the device, an initial user cost model is constructed based on the held inventory cost and the stock shortage cost of each user in the historical distribution data of each user, then the user cost model is obtained by constructing the Lagrangian dual function of the initial user cost model, and the user cost which needs to be solved originally is usedQ m (y,d) The following equation (7):
the above formula (7)Q m (y,d) The minimum value problem is converted into a form of solving the maximum value (as shown in the formula (6)), so that the obtained second inventory routing model is converted into a form of linearly solving the maximum value from the original form of solving the minimum value first and then solving the maximum value, the calculation is simpler and more convenient, the calculation efficiency of the second inventory routing model can be greatly improved, and the determination efficiency of the user demand determination method provided by the embodiment of the application is further improved.
Referring to fig. 6, in an optional embodiment of the present application, the user requirement determining method provided in the embodiment of the present application further includes the following steps 601 to 604:
The first delivery constraint refers to some other delivery limiting conditions and calculation parameter settings in the delivery process that need to be introduced when calculating the vehicle transportation cost, such as the number of delivery vehicles, the maximum load capacity, and the like, and the number of retail customers is not 0. Different preset delivery scenes are preset at the service terminal, correspond to different historical commodity demands and then set different delivery routes, for example, the first delivery route is as follows: retail customer 0, retail customer 1, retail customer 2, retail customer 3, retail customer 4, second distribution line: retail customer 0, retail customer 2, retail customer 3, retail customer 1, retail customer 4; of course, all the distribution lines are not exhaustive, and different distribution lines may be specifically set according to actual conditions. Different distribution lines correspond to different vehicle transportation costs, the vehicle transportation costs are costs corresponding to the supplier side, and then the initial total inventory cost of the supplier side and the retail user side is determined and obtained by combining the user cost of the retail user side.
Similarly, the second delivery constraint refers to some other delivery limiting conditions and calculation parameter settings in the delivery process that need to be introduced when calculating the vehicle transportation cost, such as the number of delivery vehicles, the maximum load capacity, and the like, and the number of retail customers is not 0. Of course, the specific content of the first preset constraint is not limited in any way, and may be specifically set according to the actual situation. However, it should be noted that the second delivery constraint has a greater constraint than the first delivery constraint. Under the first distribution constraint, the service terminal inputs the user cost obtained in the step 601 as the initial user cost into the first inventory routing model again, and then recalculates the new vehicle transportation cost based on the branch cut boundary method.
And step 603, the service terminal determines a new inventory total cost according to the new vehicle transportation cost and the user cost.
After obtaining the new transportation cost of the vehicle based on step 602, the service terminal then calculates the sum of the new transportation cost and the user cost to obtain a new total inventory cost.
The service terminal calculates different total inventory costs under different distribution constraint conditions, and then calculates a difference value of the total inventory costs obtained by two adjacent calculations so as to judge whether the current total inventory cost meets a condition of finishing the calculation, namely whether the current difference value is smaller than a preset threshold value. The preset threshold may be specifically set according to actual conditions, and this embodiment is not limited at all.
Due to the fact that distribution constraint conditions are too many in the actual inventory total cost calculation process, the calculation amount is overlarge, the calculation capacity requirement on a service terminal is high, calculation failure caused by calculation failure due to the fact that calculation cannot be converged is prone to occur, and the optimal value or the target value cannot be obtained. In the embodiment of the application, the initial total inventory cost is obtained by calculating under the first distribution constraint, then the new initial total inventory cost is continuously calculated under the second distribution constraint more than the first distribution constraint, and finally whether the current total inventory cost reaches the target value is judged based on the difference value between the new total inventory cost and the initial total inventory cost. Constraint conditions are gradually increased, calculation robustness is introduced, no matter how many constraint conditions exist, an optimal inventory total cost or a target inventory total cost can be obtained finally, target commodity requirements can be obtained correspondingly, and feasibility and reliability of the user requirement determining method provided by the embodiment of the application are further improved.
In an optional embodiment of the present application, in step 203, if the vehicle transportation cost and the user cost meet the preset condition, the service terminal determines a target transportation route for each user according to the vehicle transportation cost, and determines a target commodity requirement for each user according to the user cost, including the following step a:
and step A, if the difference value between the new inventory total cost and the initial inventory total cost is smaller than a preset threshold value, the service terminal determines a target transportation route for each retail user according to the vehicle transportation cost or the new vehicle transportation cost, and determines the target commodity requirement of each user according to the user cost.
The preset threshold may be specifically set according to practical experience, and the implementation is not particularly limited. When the difference between the new total inventory cost and the initial total inventory cost is smaller than the preset threshold, it means that the upper and lower bounds of the total inventory cost obtained currently are infinitely close, that is, the current delivery constraint is infinitely close to the actual delivery constraint, that is, the total inventory cost obtained currently is optimal. As shown in step 201 and step 202, an inventory total cost corresponds to a vehicle transportation cost and a user cost, respectively, the service terminal determines a target transportation route for each retail user based on the current vehicle transportation cost or a new vehicle transportation cost, and determines a target commodity demand of each user according to the current user cost.
Referring to fig. 7, in an optional embodiment of the present application, the user requirement determining method provided in the embodiment of the present application further includes the following steps 701 to 702:
When the difference between the new total inventory cost and the initial total inventory cost is not less than the preset threshold, it means that the difference between the upper bound and the lower bound of the currently obtained total inventory cost is still large, the difference between the current delivery constraint and the actual delivery constraint is still large, and the currently obtained total inventory cost does not reach a better result, so the service terminal continues to increase the constraint condition in the second delivery constraint.
When the difference between the new total inventory cost and the initial total inventory cost is smaller than the preset threshold, it means that the upper and lower bounds of the total inventory cost obtained currently are infinitely close, that is, the current delivery constraint is infinitely close to the actual delivery constraint, that is, the total inventory cost obtained currently is optimal. Therefore, the service terminal determines a target transportation route for each retail user according to the vehicle transportation cost or the new vehicle transportation cost and determines a target commodity demand of each user according to the user cost in the step A.
The embodiment of the present application gradually increases the constraint condition of the second delivery constraint, and determines whether the current total inventory cost reaches the target value based on the difference between the new total inventory cost obtained each time and the last total inventory cost obtained last time. Constraint conditions are gradually increased, calculation robustness is introduced, no matter how many constraint conditions exist, an optimal inventory total cost or a target inventory total cost can be obtained finally, target commodity requirements can be obtained correspondingly, and feasibility and reliability of the user requirement determining method provided by the embodiment of the application are further improved.
In an optional embodiment, the target inventory model including the first inventory routing model and the second inventory routing model may be solved based on a column and constraint generation algorithm, and the second inventory routing model is solved based on a branch pruning method in the solving process, so that the convergence efficiency may be improved to the greatest extent, and the determination efficiency of the user demand determination method provided by the embodiment of the present application may be further improved. The specific solving process can be as shown in fig. 8:
the new total inventory cost refers to the sum of new user cost and initial transportation cost, and the initial total inventory cost refers to the sum of vehicle transportation cost and initial user cost;
and 805, if not, continuing to increase the constraint conditions of the first delivery constraint and the second delivery constraint, and re-solving the first inventory routing model and the second inventory routing model.
In a particular embodiment, the service terminal may make the transition based on constraints, e.g., for the set of uncertainties in equation (2) aboveD m Equation (1) of the constraint equation (a), i.e., the uncertainty can be collectedD m The form conversion was performed to the following indeterminate set (8):
in the formula (8), for the convenience of description, the delivery scenario will be presetmOmitted, the formula (8) is an uncertain set for a specific preset delivery scenario; wherein,
is shown asmUncertainty set under each scene;d i t to representtRetail customer within a time periodiHistorical commodity requirements of (2);
representtRetail customer within a time periodiThe intermediate decision variables of (a) are,z i t =d i t -μ i t and is made ofz i t ∈[0,δ i t ]；μ i t To representtRetail customer within a time periodiAverage of historical commodity demands of (1);δ i t to representtRetail customer within a time periodiStandard deviation of historical commodity demand of (a);V'representing a collection of retail users; u represents a set of historical time periods;bthe specific empirical value can be set independently according to actual conditions.
The embodiment of the application provides an uncertain set with numerical value interval constraint and absolute value constraint
Conversion to an indeterminate set with specific linear constraints only
Greatly simplifying the calculation process and greatly improving the calculation efficiency on the premise of ensuring the calculation result, thereby further improving the applicationPlease refer to the determination efficiency of the user requirement determining method provided by the embodiment.
Referring to fig. 9, in order to implement the service processing method, in an embodiment of the present application, a user requirement determining apparatus 900 is provided. Fig. 9 shows a schematic architecture diagram of a user demand determination apparatus.
The user requirement determining apparatus 900 includes: a first determining module 901, a second determining module 902 and a third determining module 903.
The first determining module 901 is configured to determine vehicle transportation costs based on historical distribution data for each user in a preset period and a first inventory routing model constructed in advance;
the second determining module 902 is configured to determine the user cost of each user based on the historical delivery data, the vehicle transportation cost, and a second inventory routing model that is pre-constructed for each user in a preset period;
the third determining module 903 is configured to determine a target transportation route for each user according to the vehicle transportation cost if the vehicle transportation cost and the user cost meet preset conditions, and determine a target commodity requirement of each user according to the user cost.
In an optional embodiment, the second determining module 902 is specifically configured to divide the historical distribution data of each user into a plurality of uncertainty sets according to a preset distribution scenario; determining the conditional probability that the commodity demand of each user belongs to the uncertainty set in the historical distribution data of each user; and constructing a second inventory routing model based on the conditional probability and the holding inventory cost and the stock shortage cost of each user in the historical distribution data of each user.
In an optional embodiment, the second determining module 902 is specifically configured to perform clustering processing on historical delivery data of each user according to a preset delivery scenario to obtain a plurality of cluster sets; determining a plurality of sets of clusters as a plurality of sets of uncertainties; and the historical delivery data of the users in each cluster set belong to the same delivery scene.
In an alternative embodiment, the second determining module 902 is specifically configured to construct an initial user cost model based on the inventory cost and the stock out cost of each user in the historical delivery data of each user; constructing a Lagrange dual function of an initial user cost model to obtain a user cost model; a second inventory routing model is constructed based on the conditional probability and the user cost model.
In an alternative embodiment, the third determining module 903 is further configured to determine an initial total inventory cost according to the vehicle transportation cost and the user cost under the first distribution constraint; under the second distribution constraint, inputting the user cost into the first inventory routing model, and calculating new vehicle transportation cost based on a branch boundary shearing method; wherein the second delivery constraint has a constraint greater than the first delivery constraint; determining a new total inventory cost based on the new vehicle transportation cost and the user cost; and judging whether the difference value between the new inventory total cost and the initial inventory total cost is smaller than a preset threshold value.
In an optional embodiment, the third determining module 903 is further configured to determine a target transportation route for each retail user according to the vehicle transportation cost or the new vehicle transportation cost and determine a target commodity demand of each user according to the user cost if the difference between the new total inventory cost and the initial total inventory cost is less than a preset threshold.
In an optional embodiment, the third determining module 903 is further configured to add a constraint condition of a second delivery constraint if a difference between the new total inventory cost and the total inventory cost is not less than a preset threshold; and under a new second delivery constraint, continuously determining new vehicle transportation cost based on historical delivery data of each user in a preset period and a pre-constructed first inventory routing model until the difference value between the new inventory total cost and the initial inventory total cost is smaller than a preset threshold value.
Exemplary embodiments of the present application also provide a computer-readable storage medium, which may be implemented in the form of a program product, comprising program code for causing an electronic device to perform the steps according to various exemplary embodiments of the present application described in the above-mentioned "exemplary methods" section of this specification, when the program product is run on the electronic device. In one embodiment, the program product may be embodied as a portable compact disc read only memory (CD-ROM) and include program code, and may be run on an electronic device, such as a personal computer. However, the program product of the present application is not so limited, and in this document, a readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
A computer readable signal medium may include a propagated data signal with readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A readable signal medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Program code for carrying out operations of the present application may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider). In one embodiment of the present application, the program code stored in the computer readable storage medium can implement the method of any one of the above steps when executed.
Referring to fig. 10, an exemplary embodiment of the present application further provides an electronic device 1000, which may be a background server of an information platform. The electronic device is explained below with reference to fig. 10. It should be understood that the electronic device 1000 shown in fig. 10 is only an example and should not bring any limitation to the function and the scope of the application of the embodiments.
As shown in fig. 10, the electronic device 1000 is embodied in the form of a general purpose computing device. The components of the electronic device 1000 may include, but are not limited to: at least one processing unit 1010, at least one memory unit 1020, and a bus 1030 that couples various system components including the memory unit 1020 and the processing unit 1010.
Where the storage unit stores program code that may be executed by the processing unit 1010 to cause the processing unit 1010 to perform the steps according to various exemplary embodiments of the present invention described in the "exemplary methods" section above in this specification. For example, the processing unit 1010 may perform the method steps as shown in fig. 2, and the like.
The memory unit 1020 may include volatile memory units such as a random access memory unit (RAM) 1021 and/or a cache memory unit 1022, and may further include a read only memory unit (ROM) 1023.
The electronic device 900 may also communicate with one or more external devices 1100 (e.g., keyboard, pointing device, bluetooth device, etc.) via input/output (I/O) interfaces 1040. The electronic device 900 may also communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network such as the internet) through the network adapter 1050. As shown, the network adapter 1050 communicates with the other modules of the electronic device 900 over a bus 1030. It should be appreciated that although not shown in the figures, other hardware and/or software modules may be used in conjunction with the electronic device 900, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.
It should be noted that although in the above detailed description several modules or units of the device for action execution are mentioned, such a division is not mandatory. Indeed, according to exemplary embodiments of the present application, the features and functions of two or more modules or units described above may be embodied in one module or unit. Conversely, the features and functions of one module or unit described above may be further divided into embodiments by a plurality of modules or units.
As will be appreciated by one skilled in the art, aspects of the present application may be embodied as a system, method or program product. Accordingly, various aspects of the present application may be embodied in the form of: an entirely hardware embodiment, an entirely software embodiment (including firmware, microcode, etc.) or an embodiment combining hardware and software aspects that may all generally be referred to herein as a "circuit," module "or" system. Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.
It will be understood that the present application is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the application is only limited by the appended claims.
Claims (9)
1. A method for determining user requirements, comprising:
determining vehicle transportation cost based on historical distribution data of each user in a preset period and a pre-constructed first inventory routing model;
determining the user cost of each user based on the historical distribution data of each user in the preset period, the vehicle transportation cost and a pre-constructed second inventory routing model; the method for constructing the second inventory routing model comprises the following steps:
dividing the historical distribution data of each user into a plurality of uncertainty sets according to a preset distribution scene;
determining the conditional probability that the commodity demand of each user belongs to the uncertainty set in the historical distribution data of each user;
constructing the second inventory routing model based on the conditional probability and the holding inventory cost and the stock shortage cost of each user in the historical distribution data of each user;
and if the vehicle transportation cost and the user cost meet preset conditions, determining a target transportation route for each user according to the vehicle transportation cost, and determining the target commodity requirement of each user according to the user cost.
2. The method according to claim 1, wherein the dividing historical distribution data of each user into a plurality of uncertainty sets according to a preset distribution scenario comprises:
clustering the historical distribution data of each user according to the preset distribution scene to obtain a plurality of cluster sets;
determining the plurality of sets of clusters as the plurality of sets of uncertainties; and the historical delivery data of the users in each cluster set belong to the same delivery scene.
3. The method as claimed in claim 1, wherein the constructing the second inventory routing model based on the conditional probability and the cost of inventory in possession and the cost of out-of-stock of each user in the historical delivery data of each user comprises:
constructing an initial user cost model based on the inventory holding cost and the stock shortage cost of each user in the historical distribution data of each user;
constructing a Lagrangian dual function of the initial user cost model to obtain the user cost model;
building the second inventory routing model based on the conditional probability and the user cost model.
4. The method of claim 1, further comprising:
determining an initial total inventory cost from the vehicle transportation cost and the user cost under a first delivery constraint;
under a second distribution constraint, inputting the user cost into the first inventory routing model, and calculating a new vehicle transportation cost based on a branch boundary shearing method; wherein a constraint of the second delivery constraint is greater than the first delivery constraint;
determining a new total inventory cost based on the new vehicle transportation cost and the user cost;
and judging whether the difference value between the new inventory total cost and the initial inventory total cost is smaller than a preset threshold value.
5. The method as claimed in claim 4, wherein if the vehicle transportation cost and the user cost satisfy a preset condition, determining a target transportation route for each user according to the vehicle transportation cost, and determining a target commodity demand for each user according to the user cost, comprises:
and if the difference value between the new inventory total cost and the initial inventory total cost is smaller than the preset threshold value, determining a target transportation route for each user according to the vehicle transportation cost or the new vehicle transportation cost, and determining the target commodity requirement of each user according to the user cost.
6. The method of claim 4, further comprising:
if the difference value between the new inventory total cost and the inventory total cost is not less than a preset threshold value, increasing a constraint condition of the second delivery constraint;
and under a new second delivery constraint, continuing to determine the new vehicle transportation cost based on the historical delivery data for each user in the preset period and the pre-constructed first inventory routing model until the difference between the new inventory total cost and the initial inventory total cost is smaller than the preset threshold value.
7. A user demand determination apparatus, characterized in that the apparatus comprises:
the first determining module is used for determining vehicle transportation cost based on historical distribution data of each user in a preset period and a pre-constructed first inventory routing model;
the second determining module is used for determining the user cost of each user based on the historical distribution data, the vehicle transportation cost and a second pre-constructed inventory routing model of each user in the preset period; the method for constructing the second inventory routing model comprises the following steps:
dividing the historical distribution data of each user into a plurality of uncertainty sets according to a preset distribution scene;
determining the conditional probability that the commodity demand of each user belongs to the uncertainty set in the historical distribution data of each user;
constructing the second inventory routing model based on the conditional probability and the holding inventory cost and the stock shortage cost of each user in the historical distribution data of each user;
and the third determining module is used for determining a target transportation route for each user according to the vehicle transportation cost and determining the target commodity requirement of each user according to the user cost if the vehicle transportation cost and the user cost meet preset conditions.
8. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the method of any one of claims 1 to 6.
9. An electronic device, comprising:
a processor; and
a memory for storing executable instructions of the processor;
wherein the processor is configured to perform the method of any of claims 1 to 6 via execution of the executable instructions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210090708.5A CN114169944B (en) | 2022-01-26 | 2022-01-26 | User demand determination method and device, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210090708.5A CN114169944B (en) | 2022-01-26 | 2022-01-26 | User demand determination method and device, storage medium and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114169944A CN114169944A (en) | 2022-03-11 |
| CN114169944B true CN114169944B (en) | 2022-07-05 |
Family
ID=80489522
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210090708.5A Active CN114169944B (en) | 2022-01-26 | 2022-01-26 | User demand determination method and device, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114169944B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115392826A (en) * | 2022-08-08 | 2022-11-25 | 重庆邮电大学 | Distribution network reliability assessment and optimization method considering inventory and transportation cost |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102184507A (en) * | 2011-05-16 | 2011-09-14 | 苏州两江科技有限公司 | Warehouse replenishing method |
| CN110782064A (en) * | 2019-09-10 | 2020-02-11 | 浙江工业大学 | Visualization method and system integrating vehicle scheduling optimization and task allocation |
| CN111401619A (en) * | 2020-03-10 | 2020-07-10 | 杭州网易再顾科技有限公司 | Purchase order processing method and device, electronic equipment and storage medium |
| CN112613701A (en) * | 2020-12-02 | 2021-04-06 | 红云红河烟草(集团)有限责任公司 | Finished cigarette logistics scheduling method |
| CN112700177A (en) * | 2019-10-22 | 2021-04-23 | 北京京东振世信息技术有限公司 | Warehouse selection method and device for transporting transportation center and storage medium |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7676404B2 (en) * | 2002-10-15 | 2010-03-09 | Rmr Associates Llc | Method for forecasting consumption and generating optimal delivery schedules for vehicles involved in delivering propane and other consumables to end consumers |
| CN109214731A (en) * | 2017-06-29 | 2019-01-15 | 菜鸟智能物流控股有限公司 | Method and device for distributing logistics orders and computer system |
-
2022
- 2022-01-26 CN CN202210090708.5A patent/CN114169944B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102184507A (en) * | 2011-05-16 | 2011-09-14 | 苏州两江科技有限公司 | Warehouse replenishing method |
| CN110782064A (en) * | 2019-09-10 | 2020-02-11 | 浙江工业大学 | Visualization method and system integrating vehicle scheduling optimization and task allocation |
| CN112700177A (en) * | 2019-10-22 | 2021-04-23 | 北京京东振世信息技术有限公司 | Warehouse selection method and device for transporting transportation center and storage medium |
| CN111401619A (en) * | 2020-03-10 | 2020-07-10 | 杭州网易再顾科技有限公司 | Purchase order processing method and device, electronic equipment and storage medium |
| CN112613701A (en) * | 2020-12-02 | 2021-04-06 | 红云红河烟草(集团)有限责任公司 | Finished cigarette logistics scheduling method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114169944A (en) | 2022-03-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Shi et al. | Analytics for cross‐border e‐commerce: inventory risk management of an online fashion retailer | |
| Herer et al. | The multilocation transshipment problem | |
| Ouhimmou et al. | Design of robust distribution network under demand uncertainty: A case study in the pulp and paper | |
| CN114118888B (en) | Method and device for order delivery | |
| CN109447355A (en) | Dispatching optimization method, device, medium and the calculating equipment of articles from the storeroom | |
| CN113792951B (en) | Logistics distribution method and device, storage medium and electronic equipment | |
| CN110135878B (en) | Method and device for determining sales price | |
| Taleizadeh et al. | Optimising multi-product multi-chance-constraint inventory control system with stochastic period lengths and total discount under fuzzy purchasing price and holding costs | |
| Li et al. | A multi-phase algorithm for a joint lot-sizing and pricing problem with stochastic demands | |
| CN117557190A (en) | Method, apparatus, device and computer readable medium for restocking warehouse | |
| CN113779241B (en) | Information acquisition method and device, computer readable storage medium, and electronic device | |
| CN114169944B (en) | User demand determination method and device, storage medium and electronic equipment | |
| CN113011672A (en) | Logistics timeliness prediction method and device, electronic equipment and storage medium | |
| CN117993536A (en) | Inventory planning system and method for short-term commodities | |
| CN113222493A (en) | Supply chain inventory management method and device and electronic equipment | |
| Chen et al. | Deep learning models for forecasting electricity demand in green low-carbon supply chains | |
| Tong et al. | A customer-oriented method to support multi-task green scheduling with diverse time-of-use prices in Cloud Manufacturing | |
| CN117273318B (en) | Material alignment sleeve analysis method and device | |
| CN110858337B (en) | Method and device for generating configuration information | |
| JP4993097B2 (en) | Company policy decision support device, company policy decision support method and program | |
| CN110490682B (en) | Method and device for analyzing commodity attributes | |
| CN113538080A (en) | Task list splitting method and device | |
| CN113888230B (en) | Electronic coupon issuance method and device, readable storage medium and electronic device | |
| CN113762695B (en) | A method and device for allocating task orders | |
| Liu et al. | A genetic algorithm heuristic approach to general outsourcing capacitated production planning problems |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |