CN114881578B - Overstocked material automatic inventory method based on multi-element collaborative traceability - Google Patents
Overstocked material automatic inventory method based on multi-element collaborative traceability Download PDFInfo
- Publication number
- CN114881578B CN114881578B CN202210790373.8A CN202210790373A CN114881578B CN 114881578 B CN114881578 B CN 114881578B CN 202210790373 A CN202210790373 A CN 202210790373A CN 114881578 B CN114881578 B CN 114881578B
- Authority
- CN
- China
- Prior art keywords
- materials
- warehouse
- goods
- traceability
- project
- 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; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/087—Inventory or stock management, e.g. order filling, procurement or balancing against orders
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/047—Probabilistic or stochastic networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Economics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Computational Linguistics (AREA)
- General Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- Tourism & Hospitality (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Biophysics (AREA)
- Evolutionary Biology (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Marketing (AREA)
- Quality & Reliability (AREA)
- Probability & Statistics with Applications (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
Abstract
The invention provides an automatic backlog material inventory method based on multi-element collaborative traceability, which comprises the following steps: obtaining application materials, and screening the application materials which fail to be matched as the materials to be recommended; according to the function of the materials to be recommended, searching whether materials with consistent functions exist in the warehouse, and if so, selecting the materials with the historical ex-warehouse frequency lower than a preset value as the materials for the warehouse; determining engineering related materials of the materials beneficial to the warehouse, and performing principal component analysis on the warehouse-out condition; determining a traceability factor, reasoning the backlog reason of the goods and materials in the interest bank, and marking the ex-bank limit level for the goods and materials in the interest bank by combining a reasoning result and a principal component analysis result; and selecting recommended inventory resources from the inventory resources according to the type quantity and the delivery limit level of the inventory resources. According to the invention, the goods and materials to be inventoried are further refined according to the traceability result, the delivery limit level of the goods and materials is facilitated, so that the matched goods and materials to be inventoried can be preferentially considered in the primary setting stage of the engineering project, and the utilization rate of the overstocked goods and materials is improved.
Description
Technical Field
The invention belongs to the field of material management, and particularly relates to an automatic backlog material inventory method based on multi-element collaborative traceability.
Background
When applying for materials in engineering projects, because the mastering conditions of project research personnel on inventory conditions are disjointed, research and development requirements are usually considered when the project research personnel can be initially set, overstocked materials which can also realize the same function in the inventory can be usually ignored, so that a purchasing department can only purchase new materials according to the material requirements provided by the project research personnel, and the waste and overstock of partial materials are caused.
In order to avoid the phenomenon, when a project research and development worker selects materials for an engineering project, the existing method generally selects materials meeting research and development requirements from inventory materials and recommends the materials to the project research and development worker to achieve the purpose of inventory and inventory, the inventory and inventory are performed only according to the inventory condition, the reason for overstock of the materials in a warehouse is ignored, the material inventory strategy is unreasonable, the problem that materials needed by other engineering projects are used by mistake is easily caused, and the implementation progress of other engineering projects is influenced.
Disclosure of Invention
The invention provides an automatic backlog material inventory method based on multi-element collaborative traceability, aiming at solving the problems of waste and backlog of materials, overcoming the neglect of the reason for backlog of materials in the existing inventory method aiming at the unreasonable material inventory strategy in the prior art, and comprising the following steps:
s100: acquiring application materials of a current project, matching the application materials in a warehouse, and screening the application materials failing in matching as materials to be recommended;
s200: retrieving whether materials with consistent functions exist in a warehouse or not according to the functions of the materials to be recommended in the current project, if not, generating material purchasing information, and if so, selecting the materials with historical ex-warehouse frequency lower than a preset value from the materials with consistent functions as materials for benefiting the warehouse;
s300: determining the engineering related materials of the interest library materials, and performing principal component analysis on the ex-warehouse conditions of the interest library materials and the engineering related materials;
s400: determining traceability factors of the goods and materials in the interest library and the related goods and materials of the engineering, reasoning overstock reasons of the goods and materials in the interest library according to the traceability factors through a pre-trained multivariate collaborative traceability reasoning model, and marking ex-warehouse limit levels for the goods and materials in the interest library by combining the reasoning results and the results of principal component analysis;
s500: and selecting the recommended inventory resources of the current item from the inventory resources according to the type quantity and the delivery limit level of the inventory resources.
Optionally, the matching of the application materials in the warehouse includes: and acquiring a material code of the applied material, and comparing the material code with an inventory list in the warehouse.
Optionally, the S300 includes:
acquiring a last ex-warehouse record of the goods and materials in the warehouse, and determining a historical project corresponding to the last ex-warehouse record;
taking all out-of-warehouse goods and materials provided by the warehouse for the historical project as project related goods and materials for the goods and materials which are beneficial to the warehouse, and acquiring historical out-of-warehouse records of the project related goods and materials;
and carrying out feature extraction on the historical ex-warehouse record of the engineering related materials and the last ex-warehouse record of the interest warehouse materials, and carrying out principal component analysis on the extracted features to obtain principal component variables.
Optionally, the S400 includes:
respectively obtaining the traceability factors of the materials and engineering related materials of the benefit bank, wherein the traceability factors comprise the latest ex-warehouse time, the material function type and the principal component variable;
inputting the traceability factors into a multivariate collaborative traceability reasoning model, and performing traceability reasoning on the goods and materials in the interest library to respectively obtain the backlog reasoning probability of the goods and materials in the interest library due to various engineering reasons, wherein the engineering reasons comprise engineering ending, engineering canceling, engineering pausing and engineering proceeding;
and adjusting the inference probability into a traceability coefficient according to the number of the principal component variables, determining the engineering reason corresponding to the highest traceability coefficient after adjustment as the backlog reason of the materials of the interest bank, and marking the materials of the interest bank as the ex-warehouse limit level corresponding to the backlog reason.
Optionally, the multivariate collaborative traceability inference model is a bayesian neural network trained for each engineering reason.
Optionally, the adjusting the inference probability according to the number of the principal component variables into a traceability coefficient includes:
determining an adjustment amount according to the number of the principal component variables, reducing the inference probability corresponding to the completion of the project and the cancellation of the project by the adjustment amount, and increasing the inference probability corresponding to the suspension of the project and the progress of the project by the adjustment amount;
and normalizing the adjusted inference probability to convert the inference probability into a traceability coefficient.
Optionally, in the engineering reasons, the corresponding ex-warehouse limit levels during engineering ending, engineering canceling, engineering suspending and engineering proceeding are sequentially increased.
Optionally, the meaning of the historical ex-warehouse frequency is the ex-warehouse frequency of the materials in the warehouse within a preset statistical time period.
Optionally, when only 1 kind of good bank materials is selected, the S500 includes:
and if the ex-warehouse limit level is the highest limit level, generating material purchasing information, and otherwise, selecting the recommended inventory material of the current project from the materials in the interest warehouse.
Optionally, when at least 2 kinds of materials for the interest library are selected, the S500 includes:
if the ex-warehouse limit levels of the goods and materials in the interest warehouse are the highest limit levels, generating goods and materials purchasing information;
otherwise, respectively generating inventory-selling priorities for various inventory-benefiting materials according to the sequence of the delivery limit levels, adjusting the inventory-selling priorities according to the historical delivery frequency of the inventory-benefiting materials when the inventory-benefiting materials with the same delivery limit levels exist, and selecting the recommended inventory-selling materials of the current project in the recommendation set according to the adjusted inventory-selling priorities.
The technical scheme provided by the invention has the beneficial effects that:
according to the invention, the alternative materials to be stocked are screened out on the basis of the traceability analysis based on the principal component analysis, the warehouse-out limit level of the materials to be stocked is further refined according to the traceability result, and then the flexible and reasonable overstocked material matching is carried out according to the research and development purpose of project research and development personnel, so that the matched materials to be stocked can be preferentially considered in the primary setting stage of the engineering project, the utilization rate of the overstocked materials is improved, and meanwhile, the automatic stockpiling of the overstocked materials can be carried out in time according to the research and development requirement of the engineering project, and the large amount of overstocked materials is avoided.
Drawings
In order to more clearly illustrate the technical solution of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on the drawings without creative efforts.
Fig. 1 is a schematic flow chart of an automatic backlog material inventory method based on multivariate collaborative traceability, according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The terms "first," "second," "third," "fourth," and the like in the description and in the claims, as well as in the drawings, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in other sequences than those illustrated or described herein.
It should be understood that, in various embodiments of the present invention, the sequence numbers of the processes do not mean the execution sequence, and the execution sequence of the processes should be determined by the functions and the internal logic of the processes, and should not constitute any limitation on the implementation process of the embodiments of the present invention.
It should be understood that in the present application, "comprising" and "having" and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It should be understood that, in the present invention, "a plurality" means two or more. "and/or" is merely an association describing an associated object, meaning that three relationships may exist, for example, and/or B, may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. "comprises A, B and C" and "comprises A, B, C" means that all three of A, B, C comprise, "comprises A, B or C" means that one of A, B, C comprises, "comprises A, B and/or C" means that any 1 or any 2 or 3 of A, B, C comprises.
It should be understood that in the present invention, "B corresponding to a", "a corresponds to B", or "B corresponds to a" means that B is associated with a, and B can be determined from a. Determining B from a does not mean determining B from a alone, but may be determined from a and/or other information. And the matching of A and B means that the similarity of A and B is greater than or equal to a preset threshold value.
As used herein, "if" may be interpreted as "at … …" or "when … …" or "in response to a determination" or "in response to a detection", depending on the context.
The technical solution of the present invention will be described in detail below with specific examples. These several specific embodiments may be combined with each other below, and details of the same or similar concepts or processes may not be repeated in some embodiments.
The embodiment is as follows:
as shown in fig. 1, this embodiment provides an automatic backlog material inventory method based on multi-element collaborative traceability, which includes:
s100: acquiring application materials of a current project, matching the application materials in a warehouse, and screening the application materials which fail to be matched as the materials to be recommended;
s200: retrieving whether materials with consistent functions exist in a warehouse or not according to the functions of the materials to be recommended in the current project, if not, generating material purchasing information, and if so, selecting the materials with historical ex-warehouse frequency lower than a preset value from the materials with consistent functions as materials for benefiting the warehouse;
s300: determining engineering related materials of the interest library materials, and performing principal component analysis on the ex-warehouse conditions of the interest library materials and the engineering related materials;
s400: determining traceability factors of the goods and materials related to the engineering, reasoning the overstock reason of the goods and materials of the interest library according to the traceability factors through a pre-trained multivariate collaborative traceability reasoning model, and marking the ex-warehouse limit level for the goods and materials of the interest library by combining a reasoning result and a result of principal component analysis;
s500: and selecting the recommended inventory resources of the current item from the inventory resources according to the type quantity and the delivery limit level of the inventory resources.
In order to maximize the utilization of the existing materials in the warehouse and reduce the material backlog and waste caused by unnecessary purchasing actions, the idle backlog in the warehouse is generally required to be stocked regularly. On the basis of the existing material inventory logic, a multi-element collaborative traceability mechanism is introduced, so that specific backlog reasons can be inferred and traced in the materials to be inventoried, and an inventory strategy which is more in line with the process condition of the engineering project is formulated. The automatic backlog material inventory checking method provided by the embodiment can timely check backlog materials according to project research and development requirements, avoids a large amount of backlogs of the materials, and improves the recommendation reasonableness for allocating inventory materials for designers who can develop and establish on the basis of backlog reason reasoning.
The matching of application materials in the warehouse comprises the following steps: and acquiring a material code of the applied material, and comparing the material code with an inventory list in the warehouse.
In this embodiment, the information carried by the material code includes the model and specification of the material. When research and development personnel can develop and can be initially set, a list of applied materials is provided for the warehouse management platform, the warehouse management platform searches the inventory information in the warehouse, and inventory materials with the same model and specification are preferentially determined. When the warehouse management platform does not retrieve the part of applicable materials which can be researched and initially set, matching fails, and then the good warehouse recommendation needs to be carried out according to the material condition in the warehouse.
In this embodiment, the research and development staff provides the inventory for applying for materials to the warehouse management platform, which includes not only the model and specification of the applied materials, but also material descriptions of the applied materials, where the description includes specific functions of the applied materials in the primarily-designed engineering project, and the warehouse management platform extracts keywords from the material descriptions, so as to retrieve whether materials with consistent functions exist in the warehouse according to the extracted keywords.
If the information does not exist, the fact that the materials in the current warehouse cannot meet the requirement of the primary establishment is indicated, and at the moment, the warehouse management platform generates material purchasing information to research personnel so as to prompt the research personnel that the materials are insufficient and the research personnel need to purchase additionally.
If the existing goods and materials exist, the goods and materials in the current warehouse can replace the originally applied goods and materials to meet the requirement of being capable of being researched and initially set, then the goods and materials with the historical ex-warehouse frequency lower than the preset value are selected from the goods and materials with the consistent functions to serve as goods and materials for the benefit of the warehouse, the goods and materials with the consistent functions are roughly screened through the historical ex-warehouse frequency, and the possibly overstocked warehouse is preliminarily selected.
The meaning of the historical ex-warehouse frequency is the ex-warehouse frequency of goods and materials in the warehouse within a preset statistical time period, and the preset statistical time period is manually set according to goods and materials inventory requirements.
In one embodiment, in order to solve the problem that the inventory strategy is unreasonable and other project schedules are affected simply by omitting the demands of other projects on inventory materials in the existing inventory method and inventory backlog materials are counted according to the inventory quantity, the specific backlog traceability of the library materials primarily screened in the step S200 is realized by executing the steps S300 and S400, and therefore the accuracy and the reasonableness of the recommendation of the inventory materials are improved. The S300 specifically includes:
acquiring a last ex-warehouse record of the goods and materials in the warehouse, and determining a historical project corresponding to the last ex-warehouse record;
taking all out-of-warehouse goods and materials provided by the warehouse for the historical project as project related goods and materials for the goods and materials which are beneficial to the warehouse, and acquiring historical out-of-warehouse records of the project related goods and materials;
and carrying out feature extraction on the historical ex-warehouse record of the engineering related materials and the last ex-warehouse record of the interest warehouse materials, and carrying out principal component analysis on the extracted features to obtain principal component variables.
The S400 specifically includes:
respectively obtaining the traceability factors of the materials and engineering related materials of the benefit bank, wherein the traceability factors comprise the latest ex-warehouse time, the material function type and the principal component variable;
inputting the traceability factors into a multivariate collaborative traceability reasoning model, and performing traceability reasoning on the materials in the interest library to respectively obtain the overstocked reasoning probability of the materials in the interest library due to various engineering reasons, wherein the engineering reasons comprise engineering ending, engineering canceling, engineering pause and engineering in-progress;
and adjusting the inference probability into a backlog coefficient according to the number of the principal component variables, determining an engineering reason corresponding to the highest backlog coefficient after adjustment as a backlog reason of the goods and materials in the interest warehouse, and marking the goods and materials in the interest warehouse as an ex-warehouse limit level corresponding to the backlog reason.
The principal component analysis is a statistical method, a group of variables possibly having correlation are converted into a group of linearly uncorrelated variables through orthogonal transformation, the group of converted variables is called principal component variables, the converted variables are usually used in a group of multidimensional data extraction process with specific certain correlation, original variables are converted into a plurality of linearly uncorrelated principal component variables through matrix rotation and other modes, and newly generated principal component variables contain most of information of the original variables, namely the characteristics of the extracted principal component variables can reflect the information of the original variables to the maximum extent, so that the purpose of reducing the dimension is achieved.
In this embodiment, the principal component analysis method is mainly used for providing an analysis basis for tracing the backlog situation of the goods and materials in the interest library, on one hand, the principal component analysis method is used for performing a conventional function of reducing the dimension of data for the multi-element collaborative tracing so as to reduce the reasoning difficulty, and on the other hand, the number of principal component variables analyzed by the principal components is used for analyzing the consistency degree of the ex-warehouse situation of the goods and materials in the interest library and other engineering related goods and materials. It can be known from the analysis principle of the principal component analysis method that the principal component variables are a group of independent variable arrays which retain the characteristics of the original data set, so that the number of the principal component variables can embody the correlation between the ex-warehouse conditions of the goods and the engineering related goods in the embodiment, and the more the principal component variables are, the stronger the independence of the ex-warehouse records of the goods and the engineering related goods is, that is, the more diverse the ex-warehouse conditions to a certain extent.
For example, let the last delivery record of the goods and materials in the warehouse be x 1 The historical ex-warehouse records of other engineering related materials are x respectively 2 、x 3 、…、x n And n represents the total number of types of goods and materials related to engineering. Now for the original variable X = { X = { [ X ] 1 ,x 2 ,…,x n Performing principal component analysis to obtain a principal component matrix Y = { Y = } 1 ,y 2 ,…,y n And calculating the variance contribution rate and the variance cumulative contribution rate of each variable in the principal component matrix, and selecting the first k variables with the variance cumulative contribution rate exceeding a certain proportion as principal component variables to represent all the characteristics of X. Therefore, when the k value is larger, the larger the number of the features in the original variable is, which means that the ex-warehouse conditions of the goods and other engineering related goods are more various. The method is characterized in that four backlog reasons of project ending, project canceling, project pause and project proceeding are traced, and for the conditions of project ending and project canceling, the goods and materials of interest banks and other related projects are not accumulated due to the historical projectThe warehouse is exported, so the k value of the warehouse is low, which means that the possibility of the warehouse material being non-limited material is high; for the conditions of suspension of the project and in-process of the project, if other project-related materials are frequently called for ex-warehouse due to the project progress, the ex-warehouse conditions of the project-related materials and the property materials for the benefit warehouse are inconsistent, and the k value is higher at the moment, which means that the possibility that the property materials for the benefit warehouse are limited material materials is higher at the moment. In addition, under the condition that a project is suspended or in progress, the situation that the historical project possibly applies for sufficient material reserves in the early stage and does not apply for supplementary materials exists, the project-related materials and the interest library materials are not delivered out of the historical project any more, the k value is low at the moment, but the reasonable inventory-activity logic is met at the moment, even if the inventory-related materials are delivered out of the historical project in the situation, the progress of the historical project is small, and therefore the inventory-related materials can be regarded as non-limited materials at the moment.
That is to say, in this embodiment, the number of principal component variables obtained by principal component analysis is used to adjust the ex-warehouse limit level, which has a real meaning that, although the ex-warehouse frequency of the materials in the warehouse is used, the related materials in other projects are still called out of the warehouse frequently due to the project progress, so as to avoid the under-consideration situation that the materials required by other projects are taken out by mistake only according to the material backlog degree in the conventional inventory management method.
In this embodiment, the term "engineering completion" means that a certain engineering is completed, and the materials for the library and the materials related to the engineering are not called for ex-warehouse by the engineering, so that the materials for the library can be provided as non-limiting materials for the engineering project that can be developed and set up initially due to the backlog. The project cancellation means that a project is called to stop in the implementation process, and the materials of the library and the related materials of the project are not called to be delivered out of the library any more at the moment, so the materials of the library can be provided to the project which can be researched and initially set as non-limiting materials under the backlog reason. The project suspension means that the progress of a certain project is suspended and stopped in the implementation process, and the goods and materials of the interest library and the related goods and materials of the project are also possible to be called out of the library due to the project when the subsequent project is recovered, so that the interest library is used as the limited goods and materials due to the backlog. In the process of engineering, as the name implies, a certain engineering is still in normal implementation, and at this time, the materials and the related materials of the engineering are still called out of the library according to the requirements of the engineering implementation, so that the library is used as the limited materials for the backlog reason.
Wherein, the adjusting the inference probability into the traceability coefficient according to the number of the principal component variables comprises:
determining an adjustment amount according to the number of the principal component variables, reducing the inference probability corresponding to the completion of the project and the cancellation of the project by the adjustment amount, and increasing the inference probability corresponding to the suspension of the project and the progress of the project by the adjustment amount;
and normalizing the adjusted inference probability to convert the inference probability into a traceability coefficient.
It should be noted that the adjustment amount may be a negative number in this embodiment, and the adjustment amount is usually set empirically, and the larger the number of principal component variables, the larger the adjustment amount.
For example, in one embodiment, the bayesian neural network respectively estimates 10%, 75%, 10% and 5% of the backlog probabilities of the library materials due to project completion, project cancellation, project suspension and project progress, assuming that the number k of principal component variables is 4, and determines that the corresponding adjustment amount is-4% when k =2, 14%, 79%, 6% and 1% after adjustment are obtained, and then performs normalization processing on 14%, 79%, 6% and 1% to convert the normalized values into traceability coefficients mapped to the interval of 0-1.
In another embodiment, the Bayesian neural network respectively estimates 10%, 75%, 10% and 5% of the backlog probabilities of the library materials due to project completion, project cancellation, project suspension and project progress, assuming that the number k of principal component variables is 7, and the corresponding adjustment amount is 20% when k =7, the adjustment amount is-10%, 55%, 30% and 25% after the adjustment, and then the-10%, 55%, 30% and 25% are normalized and converted into the traceability coefficient mapped to the 0-1 interval.
Therefore, when the adjustment quantity is positive, the adjustment of the inference probability has the physical meaning of reducing the inference probability corresponding to the completion of the project and the cancellation of the project and increasing the inference probability corresponding to the suspension of the project and the progress of the project; when the adjustment quantity is negative, the physical meaning of the adjustment of the inference probability is changed into raising the inference probability corresponding to the completion of the project and the cancellation of the project, and the inference probability corresponding to the suspension of the project and the progress of the project is reduced.
In the above process, by performing feature analysis on the ex-warehouse condition of the engineering related materials belonging to the same historical engineering, since the materials of an engineering design are of various types, in this embodiment, on one hand, the dimension reduction processing of the feature analysis is realized by a principal component analysis method, and on the other hand, whether the ex-warehouse conditions of the engineering related materials and the library materials are relatively synchronous can be reflected to a certain extent by the obtained number of principal component variables, if the number of the principal component variables is relatively large, it indicates that the synchronism of the ex-warehouse conditions of other engineering related materials and the library materials is not high, which is easily occurred in the suspension or in-progress stage of the historical engineering, for example, although the temporary ex-warehouse frequency of the library materials is relatively low, other related materials belonging to the same historical engineering are still in the frequency ex-warehouse, which can reflect that the historical engineering is in progress to a certain extent, or only a part related to the goods and materials of the interest library is suspended, so the goods and materials of the interest library can be taken out of the library along with the progress requirement of the historical project at any time, and the situation is not suitable for being recommended to the researched initial setting of the current project so as not to delay the progress of the historical project.
In this embodiment, among the engineering reasons, the corresponding ex-warehouse limit levels during engineering end, engineering cancellation, engineering pause and engineering progress are sequentially increased. Therefore, under the condition that a plurality of goods and materials for the good warehouse have the same ex-warehouse frequency, the goods and materials for the good warehouse which are backuped due to the completion of the project or the cancellation of the project are preferentially selected.
In this embodiment, the multivariate collaborative traceability inference model is a bayesian neural network trained for each engineering reason. The Bayesian neural network is trained by using a conventional training method through historical ex-warehouse data of various materials corresponding to various engineering reasons, and details are not repeated here.
In this embodiment, in order to fuse the backlog traceability result of the profit library materials, and thus initially recommend the optimal profit library materials for the research of the current project, the selection of the inventory materials is realized through S500, specifically:
when only 1 kind of good bank materials are selected, the S500 includes:
and if the ex-warehouse limit level is the highest limit level, generating material purchasing information, and otherwise, selecting the recommended inventory material of the current project from the materials in the interest warehouse.
As is apparent from the above description, the highest limit level corresponds to the backlog reason during the progress of the project, and therefore, even if so-called good-warehouse materials exist in the warehouse, it is not suitable for the current project at the initial setting stage because it belongs to another project in progress, so as not to delay the normal progress of the other project.
When at least 2 kinds of good library materials are selected, the step S500 includes:
if the ex-warehouse limit levels of the goods and materials in the interest warehouse are the highest limit levels, generating goods and materials purchasing information;
otherwise, respectively generating inventory-selling priorities for various inventory-benefiting materials according to the sequence of the delivery limit levels, adjusting the inventory-selling priorities according to the historical delivery frequency of the inventory-benefiting materials when the inventory-benefiting materials with the same delivery limit levels exist, and selecting the recommended inventory-selling materials of the current project in the recommendation set according to the adjusted inventory-selling priorities.
As can be seen from the above description, in this embodiment, the warehouse-benefit materials overstocked due to the completion of the project are preferentially selected for inventory, and when the warehouse-out restriction levels are the same, the warehouse-benefit materials with a lower warehouse-out frequency are selected for inventory, so as to improve the rationality of inventory.
The sequence numbers in the above embodiments are merely for description, and do not represent the sequence of the assembly or the use of the components.
The above description is only exemplary of the present invention and should not be taken as limiting the invention, as any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (7)
1. A backlog material automatic inventory method based on multi-element collaborative traceability is characterized by comprising the following steps:
s100: acquiring application materials of a current project, matching the application materials in a warehouse, and screening the application materials failing in matching as materials to be recommended;
s200: retrieving whether materials with consistent functions exist in the warehouse or not according to the functions of the materials to be recommended in the current project, if not, generating material purchasing information, and if so, selecting the materials with historical ex-warehouse frequency lower than a preset value from the materials with consistent functions as materials for benefiting the warehouse;
s300: determining engineering related materials of the interest library materials, and performing principal component analysis on the ex-warehouse conditions of the interest library materials and the engineering related materials;
s400: determining traceability factors of the goods and materials in the interest library and the related goods and materials of the engineering, reasoning overstock reasons of the goods and materials in the interest library according to the traceability factors through a pre-trained multivariate collaborative traceability reasoning model, and marking ex-warehouse limit levels for the goods and materials in the interest library by combining the reasoning results and the results of principal component analysis;
s500: selecting recommended inventory goods and materials of the current project from the inventory goods and materials according to the type quantity and the delivery limit level of the inventory goods and materials;
the S300 includes:
acquiring a last ex-warehouse record of the goods and materials in the warehouse, and determining a historical project corresponding to the last ex-warehouse record;
taking all out-of-warehouse goods and materials provided by the warehouse for the historical project as project related goods and materials for the goods and materials which are beneficial to the warehouse, and acquiring historical out-of-warehouse records of the project related goods and materials;
carrying out feature extraction on historical ex-warehouse records of engineering related materials and the last ex-warehouse record of the interest warehouse materials, and carrying out principal component analysis on the extracted features to obtain principal component variables;
the S400 includes:
respectively obtaining the traceability factors of the goods and materials of interest library and the related goods and materials of engineering, wherein the traceability factors comprise the latest time of leaving the library, the function type of the goods and materials and principal component variables;
inputting the traceability factors into a multivariate collaborative traceability reasoning model, and performing traceability reasoning on the goods and materials in the interest library to respectively obtain the backlog reasoning probability of the goods and materials in the interest library due to various engineering reasons, wherein the engineering reasons comprise engineering ending, engineering canceling, engineering pausing and engineering proceeding;
adjusting the inference probability into a traceability coefficient according to the number of the principal component variables, determining an engineering reason corresponding to the highest traceability coefficient after adjustment as a backlog reason of the materials of the interest bank, and marking the materials of the interest bank as an ex-warehouse limit level corresponding to the backlog reason;
the adjusting the inference probability into the traceability coefficient according to the number of the principal component variables comprises the following steps:
determining an adjustment amount according to the number of the principal component variables, reducing the inference probability corresponding to the completion of the project and the cancellation of the project by the adjustment amount, and increasing the inference probability corresponding to the suspension of the project and the progress of the project by the adjustment amount;
and normalizing the adjusted inference probability to convert the inference probability into a traceability coefficient.
2. The method for automatically checking backlog materials based on multi-element collaborative traceability as claimed in claim 1, wherein the matching of application materials in the warehouse comprises: the method comprises the steps of obtaining a material code applying for materials, comparing the material code with an inventory list in a warehouse, and enabling information carried by the material code to comprise the model and specification of the materials.
3. The method for automatically inventing backlog materials based on the multivariate collaborative traceability according to claim 1, wherein the multivariate collaborative traceability inference model is a Bayes neural network trained respectively for each engineering reason.
4. The method for automatically checking backlog materials based on multi-element collaborative traceability as claimed in claim 1, wherein the project reasons comprise project end, project cancel, project pause and corresponding ex-warehouse limit level during project progress are sequentially increased.
5. The method for automatically checking backlog materials based on multi-element collaborative traceability as claimed in claim 1, wherein the historical ex-warehouse frequency means the ex-warehouse frequency of materials in a warehouse within a preset statistical time period.
6. The method for automatically checking backlog materials based on multi-element collaborative traceability as claimed in claim 1, wherein when only 1 kind of materials for interest base is selected, said S500 comprises:
and if the ex-warehouse limit level is the highest limit level, generating material purchasing information, otherwise, selecting the goods and materials in the interest warehouse as the recommended inventory goods and materials of the current project.
7. The method for automatically checking backlog materials based on multi-element collaborative traceability as claimed in claim 1, wherein when at least 2 types of materials for interest base are selected, said S500 comprises:
if the ex-warehouse limit levels of the goods and materials in the interest warehouse are the highest limit levels, generating goods and materials purchasing information;
otherwise, respectively generating inventory-selling priorities for various inventory-benefiting materials according to the sequence of the delivery limit levels, adjusting the inventory-selling priorities according to the historical delivery frequency of the inventory-benefiting materials when the inventory-benefiting materials with the same delivery limit levels exist, and selecting the recommended inventory-selling materials of the current project in the recommendation set according to the adjusted inventory-selling priorities.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210790373.8A CN114881578B (en) | 2022-07-06 | 2022-07-06 | Overstocked material automatic inventory method based on multi-element collaborative traceability |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210790373.8A CN114881578B (en) | 2022-07-06 | 2022-07-06 | Overstocked material automatic inventory method based on multi-element collaborative traceability |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114881578A CN114881578A (en) | 2022-08-09 |
| CN114881578B true CN114881578B (en) | 2022-09-23 |
Family
ID=82683572
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210790373.8A Active CN114881578B (en) | 2022-07-06 | 2022-07-06 | Overstocked material automatic inventory method based on multi-element collaborative traceability |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114881578B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116805233B (en) * | 2023-08-25 | 2023-12-15 | 建信金融科技有限责任公司 | Asset inventory control method, device, equipment and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1731438A (en) * | 2005-08-17 | 2006-02-08 | 上海沪东集装箱码头有限公司 | Plant asset management system for container terminal |
| CN103455871A (en) * | 2013-07-31 | 2013-12-18 | 中国传媒大学 | Resource scheduling system and method |
| CN109492961A (en) * | 2018-09-12 | 2019-03-19 | 中国科学院电子学研究所 | A kind of goods and material handling method, system and computer readable storage medium |
| CN110310062A (en) * | 2019-06-11 | 2019-10-08 | 海南电网有限责任公司 | A kind of idle balance in the supply and demant of goods and materials benefit library system and sharp library method based on intelligent Matching |
| CN111260194A (en) * | 2020-01-09 | 2020-06-09 | 国网安徽省电力有限公司信息通信分公司 | Accurate material supply method and system based on block chain |
| CN112766850A (en) * | 2021-01-20 | 2021-05-07 | 浙江浙能电力股份有限公司 | Material combined storage management platform |
| CN112907381A (en) * | 2021-03-29 | 2021-06-04 | 中国建设银行股份有限公司 | Asset security system and method |
| CN114282884A (en) * | 2021-12-06 | 2022-04-05 | 国网浙江省电力有限公司 | Full-process control method for electric power materials |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108399500A (en) * | 2018-03-02 | 2018-08-14 | 江苏电力信息技术有限公司 | A kind of bipartite graph Optimum Matching method of complex condition balance in the supply and demant of goods and materials Li Ku |
| CN110874792A (en) * | 2019-11-15 | 2020-03-10 | 安徽海汇金融投资集团有限公司 | Method and system for checking and activating bad asset project |
| CN111260292A (en) * | 2020-01-17 | 2020-06-09 | 郑州地铁集团有限公司 | Method and system for balancing benefit bank of assets and materials |
| CA3202052A1 (en) * | 2020-12-15 | 2022-06-23 | Louis Rick Morris | Systems and methods for inventory control and optimization |
| CN112819298A (en) * | 2021-01-20 | 2021-05-18 | 浙江浙能电力股份有限公司 | Combined storage and resource multi-factory balance interest storage method and system |
-
2022
- 2022-07-06 CN CN202210790373.8A patent/CN114881578B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1731438A (en) * | 2005-08-17 | 2006-02-08 | 上海沪东集装箱码头有限公司 | Plant asset management system for container terminal |
| CN103455871A (en) * | 2013-07-31 | 2013-12-18 | 中国传媒大学 | Resource scheduling system and method |
| CN109492961A (en) * | 2018-09-12 | 2019-03-19 | 中国科学院电子学研究所 | A kind of goods and material handling method, system and computer readable storage medium |
| CN110310062A (en) * | 2019-06-11 | 2019-10-08 | 海南电网有限责任公司 | A kind of idle balance in the supply and demant of goods and materials benefit library system and sharp library method based on intelligent Matching |
| CN111260194A (en) * | 2020-01-09 | 2020-06-09 | 国网安徽省电力有限公司信息通信分公司 | Accurate material supply method and system based on block chain |
| CN112766850A (en) * | 2021-01-20 | 2021-05-07 | 浙江浙能电力股份有限公司 | Material combined storage management platform |
| CN112907381A (en) * | 2021-03-29 | 2021-06-04 | 中国建设银行股份有限公司 | Asset security system and method |
| CN114282884A (en) * | 2021-12-06 | 2022-04-05 | 国网浙江省电力有限公司 | Full-process control method for electric power materials |
Non-Patent Citations (6)
| Title |
|---|
| The application of RFID technology in the inventory management;Liu Jun"e;《IEEE XPlore》;20100823;全文 * |
| 仓储精益化管理模式下的电网库存规模长效管控机制研究;王金虎;《中国市场》;20170731(第21期);全文 * |
| 基于A-Workflow的电力仓储化资产盘活方法研究;张侃等;《粘接》;20210531(第5期);全文 * |
| 开展物资清仓利库 依法合规盘活资源;万宏伟等;《农电管理》;20120630(第6期);全文 * |
| 电力物资库存积压管理"五五"工作法;黄庆花等;《中国电力企业管理》;20181005(第28期);全文 * |
| 盘活资源压库利库 全面提升物资管理水平;哈尔滨铁路局齐齐哈尔机务段材料科QC小组;《铁路采购与物流》;20170725(第07期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114881578A (en) | 2022-08-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11120509B2 (en) | Predictive model segmentation platform | |
| Ghattas et al. | Improving business process decision making based on past experience | |
| US7212986B1 (en) | Method and apparatus for planning and monitoring multiple tasks based on user defined criteria and predictive ability | |
| CN109409532A (en) | Product development based on artificial intelligence and machine learning | |
| US7711670B2 (en) | Agent engine | |
| US9916584B2 (en) | Method and system for automatic assignment of sales opportunities to human agents | |
| US8121885B2 (en) | Plan solver | |
| CN110288193B (en) | Task monitoring processing method and device, computer equipment and storage medium | |
| CN114881578B (en) | Overstocked material automatic inventory method based on multi-element collaborative traceability | |
| CN111915410A (en) | Intelligent management and control system for high-dynamic production logistics process | |
| Martínez-Plumed et al. | CASP-DM: context aware standard process for data mining | |
| Voorberg et al. | Decisions for information or information for decisions? Optimizing information gathering in decision-intensive processes | |
| Jabbarova | Application of Z-number concept to supplier selection problem | |
| CN113362102B (en) | Client cable distribution method, system and storage medium | |
| Niedermann et al. | Deep business optimization: A platform for automated process optimization | |
| Chen et al. | A rough set approach to multiple criteria ABC analysis | |
| Debuse et al. | Building the KDD roadmap: A methodology for knowledge discovery | |
| Wang et al. | Multicriteria order acceptance decision support in over-demanded job shops: a neural network approach | |
| CN111144554A (en) | Intelligent response method, device, medium and equipment based on module decomposition | |
| EP2851851A1 (en) | A computer implemented tool and method for automating the forecasting process | |
| JP6980608B2 (en) | Examination support device, examination support method, and service provision method | |
| CN115689201A (en) | Multi-criterion intelligent decision optimization method and system for enterprise resource supply and demand allocation | |
| Khramov | Robotic and machine learning: how to help support to process customer tickets more effectively | |
| CN116187675A (en) | Task allocation method, device, equipment and storage medium | |
| Lo | An expert system for choosing demand forecasting techniques |
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 |