CN116934051A - Method and device for predicting demand scheduling - Google Patents
Method and device for predicting demand scheduling Download PDFInfo
- Publication number
- CN116934051A CN116934051A CN202311015909.XA CN202311015909A CN116934051A CN 116934051 A CN116934051 A CN 116934051A CN 202311015909 A CN202311015909 A CN 202311015909A CN 116934051 A CN116934051 A CN 116934051A
- Authority
- CN
- China
- Prior art keywords
- demand
- information
- time point
- scheduling
- items
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 66
- 238000004519 manufacturing process Methods 0.000 claims description 222
- 238000012549 training Methods 0.000 claims description 75
- 238000010801 machine learning Methods 0.000 claims description 28
- 238000004590 computer program Methods 0.000 claims description 27
- 230000006870 function Effects 0.000 claims description 25
- 238000012360 testing method Methods 0.000 claims description 20
- 230000008569 process Effects 0.000 claims description 9
- 238000010276 construction Methods 0.000 claims description 2
- 238000011161 development Methods 0.000 abstract description 14
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 11
- 238000012827 research and development Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 4
- 238000012546 transfer Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000011981 development test Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06N20/00—Machine learning
-
- 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
- G06Q10/105—Human resources
-
- 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
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- General Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Operations Research (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Game Theory and Decision Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Educational Administration (AREA)
- Medical Informatics (AREA)
- Development Economics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method and a device for predicting demand scheduling, and relates to the technical field of artificial intelligence, wherein the method comprises the following steps: acquiring initial parameter information and service demand information; extracting business target information and business budget information in business demand information, inquiring a designated database according to the business target information and the business budget information, and determining a solution of the business demand information; according to the solution of the service demand information, splitting the service demand information into a plurality of demand items to be scheduled, and determining the scheduling attribute of each demand item, wherein each demand item corresponds to a service function; the scheduling result of the plurality of demand items to be scheduled is output, the demand scheduling can be effectively performed by cooperating with each business system resource, the flexibility and the rationality of the demand scheduling are improved, the development efficiency is improved, and the user satisfaction is improved.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a demand scheduling prediction method and device.
Background
This section is intended to provide a background or context to the embodiments of the invention that are recited in the claims. The description herein is not admitted to be prior art by inclusion in this section.
In the development process of software products, a great deal of service demands exist, and in order to realize the demands of service targets, multiple systems are required to perform collaborative development test. Resource limitation exists in research and development teams of different services, when service demands of different research and development teams are continuously issued and iteration demands of various systems are continuously created, a collaborative scheduling mechanism for realizing disclosure transparency is required to be established, production expectations of different service demands are synchronously managed, and user satisfaction is improved.
The existing demand scheduling prediction method manages and classifies demands, provides demands under the influence of team research personnel and different factors, adopts FPA and other methods to predict development workload, and performs demand scheduling through forward prediction and reverse prediction. However, the consideration range of the existing demand scheduling prediction method only comprises a single system or a simple cooperative situation, and the solution is missing when resource limitation is carried out on different systems simultaneously, so that the flexibility is lacking; in addition, the human demand scheduling is greatly influenced by subjective factors, the scheduling scheme is easy to unreasonable, the human scheduling efficiency is low, the development progress is influenced, and the user demands cannot be met.
Disclosure of Invention
The embodiment of the invention provides a demand scheduling prediction method, which is used for effectively carrying out demand scheduling by cooperating with various business system resources, and is beneficial to improving the flexibility and rationality of the demand scheduling, further improving the development efficiency and improving the user satisfaction, and the method comprises the following steps:
initial parameter information and service demand information are acquired, wherein the initial parameter information comprises preset information: the method comprises the steps of delivering a time point, service system resource information of the delivering time point and human resource information of the delivering time point;
extracting business target information and business budget information in business demand information, inquiring a designated database according to the business target information and the business budget information, and determining a solution of the business demand information; the appointed database stores solutions corresponding to different business target information and business budget information, and the solutions represent business functions to be developed which meet business requirement information;
according to the solution of the service demand information, splitting the service demand information into a plurality of demand items to be scheduled, and determining the scheduling attribute of each demand item, wherein each demand item corresponds to a service function;
inputting a plurality of to-be-scheduled demand items, scheduling attribute and initial parameter information of each demand item into a scheduling prediction model, and outputting scheduling results of the plurality of to-be-scheduled demand items, wherein the scheduling prediction model is obtained by training a machine learning model according to historical demand items, the scheduling attribute of the historical demand items, historical initial parameter information and actual corresponding scheduling results.
The embodiment of the invention also provides a device for predicting the demand schedule, which is used for effectively carrying out the demand schedule by cooperating with the resources of each business system, is beneficial to improving the flexibility and the rationality of the demand schedule, further improving the development efficiency and improving the satisfaction of users, and comprises the following steps:
the information acquisition module is used for acquiring initial parameter information and service demand information, wherein the initial parameter information comprises preset: the method comprises the steps of delivering a time point, service system resource information of the delivering time point and human resource information of the delivering time point;
the solution determining module is used for extracting service target information and service budget information in the service demand information, inquiring a designated database according to the service target information and the service budget information, and determining a solution of the service demand information; the appointed database stores solutions corresponding to different business target information and business budget information, and the solutions represent business functions to be developed which meet business requirement information;
the system comprises a demand item splitting module, a service function management module and a service function management module, wherein the demand item splitting module is used for splitting service demand information into a plurality of demand items to be scheduled according to a solution of the service demand information, and determining a scheduling attribute of each demand item, wherein each demand item corresponds to one service function;
The scheduling prediction module is used for inputting a plurality of to-be-scheduled demand items, the scheduling attribute of each demand item and initial parameter information into the scheduling prediction model, and outputting the scheduling results of the plurality of to-be-scheduled demand items, wherein the scheduling prediction model is obtained by training the machine learning model according to the historical demand items, the scheduling attribute of the historical demand items, the historical initial parameter information and the actual corresponding scheduling results.
The embodiment of the invention also provides computer equipment, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor realizes the prediction method of the demand schedule when executing the computer program.
The embodiment of the invention also provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program realizes the prediction method of the demand scheduling when being executed by a processor.
The embodiment of the invention also provides a computer program product, which comprises a computer program, wherein the computer program is executed by a processor to realize the prediction method of the demand scheduling.
In the embodiment of the invention, initial parameter information and service demand information are acquired, wherein the initial parameter information comprises preset: the method comprises the steps of delivering a time point, service system resource information of the delivering time point and human resource information of the delivering time point; extracting business target information and business budget information in business demand information, inquiring a designated database according to the business target information and the business budget information, and determining a solution of the business demand information; the appointed database stores solutions corresponding to different business target information and business budget information, and the solutions represent business functions to be developed which meet business requirement information; according to the solution of the service demand information, splitting the service demand information into a plurality of demand items to be scheduled, and determining the scheduling attribute of each demand item, wherein each demand item corresponds to a service function, and the scheduling attribute comprises a conventional demand, an emergency demand and a rigid demand; inputting a plurality of to-be-scheduled demand items, scheduling attribute and initial parameter information of each demand item into a scheduling prediction model, and outputting scheduling results of the plurality of to-be-scheduled demand items, wherein the scheduling prediction model is obtained by training a machine learning model according to historical demand items, the scheduling attribute of the historical demand items, historical initial parameter information and actual corresponding scheduling results.
Compared with the situation that resource limitation is carried out on different systems at the same time in the prior art, only the service demands of a single system are manually scheduled, the method integrates the service system resource information and the human resource information of different production time points, trains a machine learning model by establishing a priority label to obtain a scheduling prediction model, and utilizes the scheduling prediction model to predict the scheduling result of the service demands, so that demand scheduling can be effectively carried out in cooperation with each service system resource, the flexibility and the rationality of demand scheduling are improved, the development efficiency is improved, and the user satisfaction is improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. In the drawings:
FIG. 1 is a process flow diagram of a method for predicting demand schedules according to an embodiment of the invention;
FIG. 2 is a flow chart of a method of training and testing a scheduling prediction model according to an embodiment of the present application;
FIG. 3 is a flowchart of a method for creating a priority label for a demand item with a scheduling attribute of a regular demand according to an embodiment of the present application;
FIG. 4 is a flowchart of a method for creating a priority label for a demand item whose scheduling attribute is an urgent demand according to an embodiment of the present application;
FIG. 5 is a flowchart of a method for creating a priority label for a demand item with a rigid demand attribute according to an embodiment of the present application;
FIG. 6 is a schematic diagram illustrating a device for predicting demand intervals according to an embodiment of the present application
Fig. 7 is a schematic diagram of a computer device according to an embodiment of the application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the embodiments of the present application will be described in further detail with reference to the accompanying drawings. The exemplary embodiments of the present application and their descriptions herein are for the purpose of explaining the present application, but are not to be construed as limiting the application.
First, the technical terms in the application are explained:
demand scheduling: refers to the process of determining the development and production time point for the technical requirements issued to the development of each system.
Scheduling attributes: in the present application, the scheduling attribute refers to an attribute of a requirement item obtained after splitting, and may specifically include a conventional requirement, an urgent requirement and a rigidity requirement. Wherein, the conventional demand refers to a general demand without fixed or urgent production time requirements; rigidity requirements refer to the requirement that production must be put into operation according to a certain fixed time, which is absolutely accurate and cannot be changed, according to related policies or regulations; an urgent need refers to a need to put into production before the latest time of production acceptable to the business sector, i.e. the production must be completed within a certain time limit.
FIG. 1 is a process flow diagram of a method for predicting demand schedules according to an embodiment of the invention. As shown in fig. 1, the method for predicting demand schedule in the embodiment of the present invention may include:
step 101, obtaining initial parameter information and service demand information, wherein the initial parameter information comprises preset: the method comprises the steps of delivering a time point, service system resource information of the delivering time point and human resource information of the delivering time point;
step 102, extracting business target information and business budget information in business demand information, inquiring a designated database according to the business target information and the business budget information, and determining a solution of the business demand information; the appointed database stores solutions corresponding to different business target information and business budget information, and the solutions represent business functions to be developed which meet business requirement information;
step 103, splitting the business demand information into a plurality of demand items to be scheduled according to the solution of the business demand information, and determining a scheduling attribute of each demand item, wherein each demand item corresponds to a business function, and the scheduling attribute comprises a conventional demand, an emergency demand and a rigidity demand;
step 104, inputting a plurality of to-be-scheduled demand items, scheduling attribute and initial parameter information of each demand item into a scheduling prediction model, and outputting scheduling results of the plurality of to-be-scheduled demand items, wherein the scheduling prediction model is obtained by training a machine learning model according to historical demand items, the scheduling attribute of the historical demand items, historical initial parameter information and actual corresponding scheduling results.
The following describes specific implementation steps of the method for predicting demand schedule in the embodiment of the present invention:
first, initial parameter information and service requirement information can be acquired, wherein the initial parameter information comprises preset parameters: the method comprises the steps of a production time point, business system resource information of the production time point and human resource information of the production time point.
In one embodiment, the service system resource information includes each point in time of production: service system type information, service system quantity information, and service system throughput information; the human resource information comprises the following information of each production time point: developer grouping information and service system allocation information of each group.
In an embodiment, a production time point in a future period (for example, 1 year) can be preset by a production administrator, so as to facilitate unified production and online of software products; each point in time of production may be pre-determined by the technician: setting service system type information, service system quantity information, service system throughput information, research and development personnel grouping information, service system allocation information of each grouping and the like, namely, simultaneously maintaining research and development resources in two aspects of service system and personnel allocation, so that under the condition of limited research and development resources, service demands are continuously issued, and under the condition that iteration demands of each service system are continuously established, preconditions are provided for resource integration of the collaborative service systems; the service demand information can be obtained by the research staff of different service research and development teams according to the actual conditions of the service.
In addition, in the implementation, the required seal time, namely the latest required seal time from the conventional production time point and the shutdown production time point, can be set by a schedule manager and can be used as a reference condition for the subsequent schedule of the required items, wherein the seal time refers to the time when the software product is determined to be not changed any more.
After the initial parameter information and the service demand information are acquired, service target information and service budget information in the service demand information can be extracted, a designated database is inquired according to the service target information and the service budget information, and a solution of the service demand information is determined; the appointed database stores solutions corresponding to different business target information and business budget information, and the solutions represent business functions to be developed which meet business requirement information.
It should be noted that, because different customers want to realize different service targets, the service targets may include service scale, service quality, service implementation function, etc., for example, the customers need to realize the transfer service, the service targets may only realize a single transfer function, or may also realize a multifunctional payment platform (payment device) such as transfer, voice, chat, etc., corresponding budgets for realizing different service targets are different, and generally, the more complex the service targets are, the higher the budgets are.
Similarly, different software development companies can provide different solutions, and each software development company can pre-establish corresponding relations between different business target information and business budget information and solutions according to self development capabilities, such as development level, number of development personnel and the like, and store the corresponding relations in a designated database. In the specific implementation, a new solution can be provided according to the actual situation, and the corresponding relation in the appointed database can be reset. Through the steps, the method can meet the requirements of clients according to the development capability in adaptability and flexibility, and improve the user experience.
Next, according to the solution according to the service requirement information, the service requirement information is split into a plurality of requirement items to be scheduled, and a scheduling attribute of each requirement item is determined, wherein each requirement item corresponds to a service function.
In specific implementation, other scheduling attributes of each demand item, such as the definition (1-5 from low to high) of the demand item, the priority information (1-5 from low to high) of the demand item, and the like, can be determined according to the analysis result of the service demand information.
And then, inputting the plurality of to-be-scheduled demand items, the scheduling attribute of each demand item and the initial parameter information into a scheduling prediction model, and outputting the scheduling result of the plurality of to-be-scheduled demand items, wherein the scheduling prediction model is obtained by training a machine learning model according to the historical demand items, the scheduling attribute of the historical demand items, the historical initial parameter information and the actual corresponding scheduling result.
FIG. 2 is a flow chart of a method of training and testing a scheduling prediction model according to an embodiment of the present invention. As shown in fig. 2, in one embodiment, the training and testing process of the scheduling prediction model may include:
step 201, taking a history demand item, a scheduling attribute of the history demand item, history initial parameter information and an actual corresponding scheduling result as sample data, and constructing a training set and a testing set;
step 202, training a machine learning model by using a training set to obtain the scheduling prediction model;
and 203, testing the scheduling prediction model by using a test set.
In one embodiment, training the machine learning model with a training set to obtain the scheduling prediction model may include:
establishing a priority label for the training set; and training the machine learning model by using the training set of the established priority label to obtain the scheduling prediction model.
It should be noted that, the demand items with different schedule attributes have different schedule conditions, and the priority label can be established or adjusted according to the schedule conditions corresponding to the demand items with different schedule attributes.
For example, if the scheduling attribute of the demand item is an urgent demand, the demand item has a time limit condition for production, the latest production time of the demand item needs to be determined, and production of the corresponding demand item must be completed before the latest production time; if the scheduling attribute of the demand item is a rigid demand, the demand item has a rigid time condition for production, the accurate production time of the demand item needs to be determined, and production of the corresponding demand item needs to be completed at the accurate production time. When the demand items are scheduled, the latest production time or the accurate production time of the two demand items needs to be considered, so that the priority label is established or adjusted according to the scheduling conditions corresponding to the demand items with different scheduling attributes, the training quality of the scheduling prediction model can be improved, and the reasonability and the accuracy of the scheduling prediction result are improved.
FIG. 3 is a flowchart of a method for creating a priority label for a demand item with a scheduling attribute of a regular demand according to an embodiment of the present invention. As shown in fig. 3, in one embodiment, establishing a priority label for a training set includes:
step 301, for a demand item with a scheduling attribute being a conventional demand, establishing priority labels for a plurality of demand items according to a split time sequence of the demand items;
step 302, determining a reference production time point of each demand item from idle production time points according to priority labels of a plurality of demand items;
step 303, when the service system resource information and the human resource information with the reference time point of production are insufficient to support the corresponding demand item to complete production, re-determining the reference time point of production of the demand item from the idle time point of production after the reference time point of production according to the sequence from front to back until the service system resource information and the human resource information of the re-determined reference time point of production are sufficient to support the corresponding demand item to complete production;
and 304, adjusting priority labels of the plurality of requirement items according to the sequence of the redetermined reference production time points.
FIG. 4 is a flowchart of a method for creating a priority label for a demand item whose scheduling attribute is an urgent demand according to an embodiment of the present invention. As shown in fig. 4, in one embodiment, establishing a priority label for a training set includes:
Step 401, for a demand item with a scheduling attribute being an urgent demand, establishing priority labels for a plurality of demand items according to a time limit demand sequence of the demand item;
step 402, determining a reference production time point of each demand item from idle production time points according to priority labels and time limit conditions of a plurality of demand items;
step 403, searching each production time point located before the reference production time point when the service system resource information and the human resource information with the reference production time point are insufficient to support the corresponding demand items to finish production;
step 404, acquiring priority labels of the scheduled demand items of each production time point, and sequentially judging whether the service system resource information and the human resource information of each production time point are enough to support the demand items with the scheduling attribute as urgent demands to finish production according to the sequence from low priority labels to high priority labels;
step 405, when judging that there are service system resource information and human resource information of a time point of production, and enough to support that a demand item with a scheduling attribute of urgent demand is produced, replacing a priority label of the demand item with the scheduling attribute of urgent demand to the time point of production, and re-determining the time point of production as a reference time point of production of the demand item with the scheduling attribute of urgent demand;
Step 406, adjusting priority labels of the plurality of requirement items according to the determined sequence of the reference production time points.
FIG. 5 is a flowchart of a method for creating a priority label for a demand item whose scheduling attribute is a rigid demand in an embodiment of the present invention. As shown in fig. 5, in one embodiment, establishing a priority label for a training set includes:
step 501, for a demand item with a rigid scheduling attribute, establishing priority labels for a plurality of demand items according to the rigid time demand sequence of the demand item;
step 502, determining a reference production time point of each demand item from idle production time points according to priority labels and rigid time conditions of a plurality of demand items;
step 503, searching a production time point located before a reference production time point when the business system resource information and the human resource information with the reference production time point are insufficient to support the corresponding demand items to finish production;
step 504, acquiring priority labels of the scheduled demand items of each production time point, and sequentially judging whether the service system resource information and the human resource information of each production time point are enough to support the demand items with the scheduling attribute being the rigid demand to finish production according to the sequence from low priority labels to high priority labels;
Step 505, when judging that the service system resource information and the human resource information of the time point of production are sufficient to support the completion of production of the demand item with the scheduling attribute being the rigid demand, replacing the priority label of the demand item with the scheduling attribute being the rigid demand to the time point of production, and re-determining the time point of production as the reference time point of production of the demand item with the scheduling attribute being the rigid demand;
step 506, adjusting priority labels of the plurality of requirement items according to the determined sequence of the reference production time points.
In specific implementation, the method for determining the reference production time point is different for the requirement items with different scheduling attributes.
(1) For a demand item with a scheduling attribute of a conventional demand, firstly, judging whether the demand item is a demand related to shutdown, if so, selecting a shutdown production time point to produce, and if not, selecting the conventional production time point to produce. The conventional demand item production requires that all the collaborative systems produce production at the same production time point, so that the closest production time point after the demand item selection closing plate is subjected to daily distance begins to try to determine the reference production time point.
(2) For a demand item with a scheduling attribute of urgent demand, for example, a production time point with a latest business acceptable date closest to the latest business acceptable date and a demand splitting time longer than a demand packaging time, a reference production time point can be determined by referring to a demand item scheduling method with a scheduling attribute of conventional demand. If the reference production time point determined by the scheduling is before the latest production time corresponding to the emergency demand item, the reference production time point is determined to be completed, and if the reference production time point determined by the scheduling is after the latest production time corresponding to the emergency demand item, the production time point closest to the latest production time corresponding to the emergency demand item is determined to be the reference production time point.
(3) For the demand items with rigid demand as the scheduling attribute, the scheduling personnel can determine the reference production time point of the rigid demand items according to the split time sequence of the demand items. If the accurate production time corresponding to the rigid demand item is consistent with the conventional or shutdown production time point, determining the production time point as a reference production time point; if the accurate production time corresponding to the rigid demand item is inconsistent with the normal or shutdown production time point, the rigid production time point is established, and the production time point is determined to be the reference production time point.
In specific implementation, the corresponding priority label can be set or adjusted with reference to other characteristics of each requirement item. For example, the definition of each demand item, the number of cooperative systems of each demand item, and the like can be referred to for comprehensive judgment, and the priority label of each demand item is established.
After the replacement is completed, the replaced demand items also need to be re-staged, and all workload is recalculated.
In one embodiment, training the machine learning model with a training set to obtain the scheduling prediction model may include: and training the machine learning model by using a training set by adopting an XGBoost algorithm to obtain the scheduling prediction model.
It should be noted that, in the embodiment of the present invention, any regression-type algorithm may be used, and the training set is used to train the machine learning model, including but not limited to: linear regression algorithms, XGBoost algorithms, GBDT algorithms, and the like.
The embodiment of the invention also provides a device for predicting the demand schedule, which is described in the following embodiment. Because the principle of the device for solving the problem is similar to that of the prediction method of the demand schedule, the implementation of the device can refer to the implementation of the prediction method of the demand schedule, and the repetition is omitted.
FIG. 6 is a schematic diagram of a device for predicting demand intervals according to an embodiment of the present invention. As shown in fig. 6, the device for predicting a demand schedule in the embodiment of the present invention may specifically include:
the information obtaining module 601 is configured to obtain initial parameter information and service requirement information, where the initial parameter information includes preset: the method comprises the steps of delivering a time point, service system resource information of the delivering time point and human resource information of the delivering time point;
the business requirement information analysis module 602 is configured to analyze the business requirement information to obtain an analysis result of the business requirement information;
the demand item splitting module 603 is configured to split the service demand information into a plurality of demand items to be scheduled according to an analysis result of the service demand information, and determine a scheduling attribute of each demand item, where each demand item corresponds to a service function;
The scheduling prediction module 604 is configured to input a plurality of to-be-scheduled demand items, a scheduling attribute of each demand item, and initial parameter information into a scheduling prediction model, and output a scheduling result of the plurality of to-be-scheduled demand items, where the scheduling prediction model is obtained by training a machine learning model according to a historical demand item, the scheduling attribute of the historical demand item, the historical initial parameter information, and an actual corresponding scheduling result.
In one embodiment, the service system resource information includes each point in time of production: business system quantity information and business system throughput information; the human resource information comprises the following information of each production time point: developer grouping information and service system allocation information of each group.
In one embodiment, the training and testing process of the scheduling prediction model includes:
the construction module is used for taking the historical demand items, the scheduling attribute of the historical demand items, the historical initial parameter information and the actual corresponding scheduling results as sample data to construct a training set and a testing set;
the model training module is used for training the machine learning model by utilizing a training set to obtain the scheduling prediction model;
and the model test module is used for testing the scheduling prediction model by using a test set.
In one embodiment, the model training module is specifically configured to:
establishing a priority label for the training set;
and training the machine learning model by using the training set of the established priority label to obtain the scheduling prediction model.
In one embodiment, the model training module is specifically configured to:
for a demand item with a scheduling attribute of conventional demand, establishing priority labels for a plurality of demand items according to the splitting time sequence of the demand item;
determining a reference production time point of each demand item from idle production time points according to priority labels of a plurality of demand items;
when the business system resource information and the human resource information with the reference production time point are insufficient to support the corresponding demand items to finish production, the reference production time point of the demand items is redetermined from the production time point which is positioned behind the reference production time point and is idle according to the sequence from front to back until the business system resource information and the human resource information of the redetermined reference production time point are sufficient to support the corresponding demand items to finish production;
and adjusting the priority labels of the plurality of requirement items according to the determined sequence of the reference production time points.
In one embodiment, the model training module is specifically configured to:
for a demand item with a scheduling attribute of urgent demand, establishing priority labels for a plurality of demand items according to the time limit demand sequence of the demand item;
determining a reference production time point of each demand item from idle production time points according to priority labels and time limiting conditions of a plurality of demand items;
searching each production time point positioned before the reference production time point when the business system resource information and the human resource information with the reference production time point are insufficient to support the corresponding demand items to finish production;
acquiring priority labels of scheduled demand items of each production time point, and sequentially judging whether the service system resource information and the human resource information of each production time point are enough to support the demand items with scheduling attributes as urgent demands to finish production according to the sequence of the priority labels from low to high;
when judging that the business system resource information and the human resource information of the time point of production are sufficient to support that the demand items with the scheduling attribute of the urgent demand finish production, replacing the priority label of the demand items with the scheduling attribute of the urgent demand to the time point of production, and re-determining the time point of production as the reference time point of production of the demand items with the scheduling attribute of the urgent demand;
And adjusting the priority labels of the plurality of requirement items according to the determined sequence of the reference production time points.
In one embodiment, the model training module is specifically configured to:
for a demand item with a scheduling attribute of rigid demand, establishing priority labels for a plurality of demand items according to the rigid time demand sequence of the demand item;
determining a reference production time point of each demand item from idle production time points according to priority labels and rigid time conditions of a plurality of demand items;
searching a production time point positioned before the reference production time point when the business system resource information and the human resource information with the reference production time point are insufficient to support the corresponding demand items to finish production;
acquiring priority labels of scheduled demand items of each production time point, and sequentially judging whether the service system resource information and the human resource information of each production time point are enough to support the demand items with the scheduling attribute being the rigid demand to finish production according to the sequence from low priority labels to high priority labels;
when judging that the business system resource information and the human resource information of the time point of production are sufficient to support the completion of production of the demand items with the arrangement attribute of the rigid demand, replacing the priority label of the demand items with the arrangement attribute of the rigid demand to the time point of production, and re-determining the time point of production as the reference time point of production of the demand items with the arrangement attribute of the rigid demand;
And adjusting the priority labels of the plurality of requirement items according to the determined sequence of the reference production time points.
In one embodiment, the model training module is specifically configured to:
and training the machine learning model by using a training set by adopting an XGBoost algorithm to obtain the scheduling prediction model.
Based on the foregoing inventive concept, as shown in fig. 7, the present invention further proposes a computer device 700, including a memory 710, a processor 720, and a computer program 730 stored in the memory 710 and executable on the processor 720, where the processor 720 implements the foregoing method for predicting demand scheduling when executing the computer program 730.
The embodiment of the invention also provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program realizes the prediction method of the demand scheduling when being executed by a processor.
The embodiment of the invention also provides a computer program product, which comprises a computer program, wherein the computer program is executed by a processor to realize the prediction method of the demand scheduling.
In summary, in the embodiment of the present invention, initial parameter information and service requirement information are obtained, where the initial parameter information includes preset parameters: the method comprises the steps of delivering a time point, service system resource information of the delivering time point and human resource information of the delivering time point;
Extracting business target information and business budget information in business demand information, inquiring a designated database according to the business target information and the business budget information, and determining a solution of the business demand information; the appointed database stores solutions corresponding to different business target information and business budget information, and the solutions represent business functions to be developed which meet business requirement information; according to the solution of the service demand information, splitting the service demand information into a plurality of demand items to be scheduled, and determining the scheduling attribute of each demand item, wherein each demand item corresponds to a service function, and the scheduling attribute comprises a conventional demand, an emergency demand and a rigid demand; inputting a plurality of to-be-scheduled demand items, scheduling attribute and initial parameter information of each demand item into a scheduling prediction model, and outputting scheduling results of the plurality of to-be-scheduled demand items, wherein the scheduling prediction model is obtained by training a machine learning model according to historical demand items, the scheduling attribute of the historical demand items, historical initial parameter information and actual corresponding scheduling results.
Compared with the situation that resource limitation is carried out on different systems at the same time in the prior art, only the service demands of a single system are manually scheduled, the method integrates the service system resource information and the human resource information of different production time points, trains a machine learning model by establishing a priority label to obtain a scheduling prediction model, and utilizes the scheduling prediction model to predict the scheduling result of the service demands, so that demand scheduling can be effectively carried out in cooperation with each service system resource, the flexibility and the rationality of demand scheduling are improved, the development efficiency is improved, and the user satisfaction is improved.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The foregoing description of the embodiments has been provided for the purpose of illustrating the general principles of the invention, and is not meant to limit the scope of the invention, but to limit the invention to the particular embodiments, and any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (19)
1. A method for predicting demand scheduling, comprising:
initial parameter information and service demand information are acquired, wherein the initial parameter information comprises preset information: the method comprises the steps of delivering a time point, service system resource information of the delivering time point and human resource information of the delivering time point;
extracting business target information and business budget information in business demand information, inquiring a designated database according to the business target information and the business budget information, and determining a solution of the business demand information; the appointed database stores solutions corresponding to different business target information and business budget information, and the solutions represent business functions to be developed which meet business requirement information;
according to the solution of the service demand information, splitting the service demand information into a plurality of demand items to be scheduled, and determining the scheduling attribute of each demand item, wherein each demand item corresponds to a service function, and the scheduling attribute comprises a conventional demand, an emergency demand and a rigid demand;
inputting a plurality of to-be-scheduled demand items, scheduling attribute and initial parameter information of each demand item into a scheduling prediction model, and outputting scheduling results of the plurality of to-be-scheduled demand items, wherein the scheduling prediction model is obtained by training a machine learning model according to historical demand items, the scheduling attribute of the historical demand items, historical initial parameter information and actual corresponding scheduling results.
2. The method of claim 1, wherein the business system resource information comprises for each point in time of commissioning: service system type information, service system quantity information, and service system throughput information;
the human resource information comprises the following information of each production time point: developer grouping information and service system allocation information of each group.
3. The method of claim 1, wherein the training and testing process of the scheduling prediction model comprises:
taking the historical demand items, the scheduling attributes of the historical demand items, the historical initial parameter information and the actual corresponding scheduling results as sample data to construct a training set and a testing set;
training a machine learning model by using a training set to obtain the scheduling prediction model;
and testing the scheduling prediction model by using a test set.
4. The method of claim 3, wherein training a machine learning model with a training set to obtain the scheduling prediction model comprises:
establishing a priority label for the training set;
and training the machine learning model by using the training set of the established priority label to obtain the scheduling prediction model.
5. The method of claim 4, wherein establishing a priority label for a training set comprises:
for a demand item with a scheduling attribute of conventional demand, establishing priority labels for a plurality of demand items according to the splitting time sequence of the demand item;
determining a reference production time point of each demand item from idle production time points according to priority labels of a plurality of demand items;
when the business system resource information and the human resource information with the reference production time point are insufficient to support the corresponding demand items to finish production, the reference production time point of the demand items is redetermined from the production time point which is positioned behind the reference production time point and is idle according to the sequence from front to back until the business system resource information and the human resource information of the redetermined reference production time point are sufficient to support the corresponding demand items to finish production;
and adjusting the priority labels of the plurality of requirement items according to the determined sequence of the reference production time points.
6. The method of claim 4, wherein establishing a priority label for a training set comprises:
for a demand item with a scheduling attribute of urgent demand, establishing priority labels for a plurality of demand items according to the time limit demand sequence of the demand item;
Determining a reference production time point of each demand item from idle production time points according to priority labels and time limiting conditions of a plurality of demand items;
searching each production time point positioned before the reference production time point when the business system resource information and the human resource information with the reference production time point are insufficient to support the corresponding demand items to finish production;
acquiring priority labels of scheduled demand items of each production time point, and sequentially judging whether the service system resource information and the human resource information of each production time point are enough to support the demand items with scheduling attributes as urgent demands to finish production according to the sequence of the priority labels from low to high;
when judging that the business system resource information and the human resource information of the time point of production are sufficient to support that the demand items with the scheduling attribute of the urgent demand finish production, replacing the priority label of the demand items with the scheduling attribute of the urgent demand to the time point of production, and re-determining the time point of production as the reference time point of production of the demand items with the scheduling attribute of the urgent demand;
and adjusting the priority labels of the plurality of requirement items according to the determined sequence of the reference production time points.
7. The method of claim 4, wherein establishing a priority label for a training set comprises:
for a demand item with a scheduling attribute of rigid demand, establishing priority labels for a plurality of demand items according to the rigid time demand sequence of the demand item;
determining a reference production time point of each demand item from idle production time points according to priority labels and rigid time conditions of a plurality of demand items;
searching a production time point positioned before the reference production time point when the business system resource information and the human resource information with the reference production time point are insufficient to support the corresponding demand items to finish production;
acquiring priority labels of scheduled demand items of each production time point, and sequentially judging whether the service system resource information and the human resource information of each production time point are enough to support the demand items with the scheduling attribute being the rigid demand to finish production according to the sequence from low priority labels to high priority labels;
when judging that the business system resource information and the human resource information of the time point of production are sufficient to support the completion of production of the demand items with the arrangement attribute of the rigid demand, replacing the priority label of the demand items with the arrangement attribute of the rigid demand to the time point of production, and re-determining the time point of production as the reference time point of production of the demand items with the arrangement attribute of the rigid demand;
And adjusting the priority labels of the plurality of requirement items according to the determined sequence of the reference production time points.
8. The method of claim 3, wherein training a machine learning model with a training set to obtain the scheduling prediction model comprises:
and training the machine learning model by using a training set by adopting an XGBoost algorithm to obtain the scheduling prediction model.
9. A demand schedule prediction apparatus, comprising:
the information acquisition module is used for acquiring initial parameter information and service demand information, wherein the initial parameter information comprises preset: the method comprises the steps of delivering a time point, service system resource information of the delivering time point and human resource information of the delivering time point;
the solution determining module is used for extracting service target information and service budget information in the service demand information, inquiring a designated database according to the service target information and the service budget information, and determining a solution of the service demand information; the appointed database stores solutions corresponding to different business target information and business budget information, and the solutions represent business functions to be developed which meet business requirement information;
The system comprises a demand item splitting module, a demand item scheduling module and a demand item scheduling module, wherein the demand item splitting module is used for splitting service demand information into a plurality of demand items to be scheduled according to a solution of the service demand information, and determining a scheduling attribute of each demand item, wherein each demand item corresponds to a service function, and the scheduling attribute comprises a conventional demand, an emergency demand and a rigid demand;
the scheduling prediction module is used for inputting a plurality of to-be-scheduled demand items, the scheduling attribute of each demand item and initial parameter information into the scheduling prediction model, and outputting the scheduling results of the plurality of to-be-scheduled demand items, wherein the scheduling prediction model is obtained by training the machine learning model according to the historical demand items, the scheduling attribute of the historical demand items, the historical initial parameter information and the actual corresponding scheduling results.
10. The apparatus of claim 9, wherein the business system resource information comprises for each point in time of commissioning: service system type information, service system quantity information, and service system throughput information;
the human resource information comprises the following information of each production time point: developer grouping information and service system allocation information of each group.
11. The apparatus of claim 9, wherein the training and testing process of the scheduling prediction model comprises:
The construction module is used for taking the historical demand items, the scheduling attribute of the historical demand items, the historical initial parameter information and the actual corresponding scheduling results as sample data to construct a training set and a testing set;
the model training module is used for training the machine learning model by utilizing a training set to obtain the scheduling prediction model;
and the model test module is used for testing the scheduling prediction model by using a test set.
12. The apparatus of claim 11, wherein the model training module is specifically configured to:
establishing a priority label for the training set;
and training the machine learning model by using the training set of the established priority label to obtain the scheduling prediction model.
13. The apparatus of claim 12, wherein the model training module is specifically configured to:
for a demand item with a scheduling attribute of conventional demand, establishing priority labels for a plurality of demand items according to the splitting time sequence of the demand item;
determining a reference production time point of each demand item from idle production time points according to priority labels of a plurality of demand items;
when the business system resource information and the human resource information with the reference production time point are insufficient to support the corresponding demand items to finish production, the reference production time point of the demand items is redetermined from the production time point which is positioned behind the reference production time point and is idle according to the sequence from front to back until the business system resource information and the human resource information of the redetermined reference production time point are sufficient to support the corresponding demand items to finish production;
And adjusting the priority labels of the plurality of requirement items according to the determined sequence of the reference production time points.
14. The apparatus of claim 12, wherein the model training module is specifically configured to:
for a demand item with a scheduling attribute of urgent demand, establishing priority labels for a plurality of demand items according to the time limit demand sequence of the demand item;
determining a reference production time point of each demand item from idle production time points according to priority labels and time limiting conditions of a plurality of demand items;
searching each production time point positioned before the reference production time point when the business system resource information and the human resource information with the reference production time point are insufficient to support the corresponding demand items to finish production;
acquiring priority labels of scheduled demand items of each production time point, and sequentially judging whether the service system resource information and the human resource information of each production time point are enough to support the demand items with scheduling attributes as urgent demands to finish production according to the sequence of the priority labels from low to high;
when judging that the business system resource information and the human resource information of the time point of production are sufficient to support that the demand items with the scheduling attribute of the urgent demand finish production, replacing the priority label of the demand items with the scheduling attribute of the urgent demand to the time point of production, and re-determining the time point of production as the reference time point of production of the demand items with the scheduling attribute of the urgent demand;
And adjusting the priority labels of the plurality of requirement items according to the determined sequence of the reference production time points.
15. The apparatus of claim 12, wherein the model training module is specifically configured to:
for a demand item with a scheduling attribute of rigid demand, establishing priority labels for a plurality of demand items according to the rigid time demand sequence of the demand item;
determining a reference production time point of each demand item from idle production time points according to priority labels and rigid time conditions of a plurality of demand items;
searching a production time point positioned before the reference production time point when the business system resource information and the human resource information with the reference production time point are insufficient to support the corresponding demand items to finish production;
acquiring priority labels of scheduled demand items of each production time point, and sequentially judging whether the service system resource information and the human resource information of each production time point are enough to support the demand items with the scheduling attribute being the rigid demand to finish production according to the sequence from low priority labels to high priority labels;
when judging that the business system resource information and the human resource information of the time point of production are sufficient to support the completion of production of the demand items with the arrangement attribute of the rigid demand, replacing the priority label of the demand items with the arrangement attribute of the rigid demand to the time point of production, and re-determining the time point of production as the reference time point of production of the demand items with the arrangement attribute of the rigid demand;
And adjusting the priority labels of the plurality of requirement items according to the determined sequence of the reference production time points.
16. The apparatus of claim 11, wherein the model training module is specifically configured to:
and training the machine learning model by using a training set by adopting an XGBoost algorithm to obtain the scheduling prediction model.
17. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method of any of claims 1 to 8 when executing the computer program.
18. A computer readable storage medium, characterized in that the computer readable storage medium stores a computer program which, when executed by a processor, implements the method of any of claims 1 to 8.
19. A computer program product, characterized in that the computer program product comprises a computer program which, when executed by a processor, implements the method of any of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311015909.XA CN116934051A (en) | 2023-08-11 | 2023-08-11 | Method and device for predicting demand scheduling |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311015909.XA CN116934051A (en) | 2023-08-11 | 2023-08-11 | Method and device for predicting demand scheduling |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116934051A true CN116934051A (en) | 2023-10-24 |
Family
ID=88394113
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311015909.XA Pending CN116934051A (en) | 2023-08-11 | 2023-08-11 | Method and device for predicting demand scheduling |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116934051A (en) |
-
2023
- 2023-08-11 CN CN202311015909.XA patent/CN116934051A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Kerzel | Enterprise AI Canvas Integrating artificial intelligence into business | |
| US20220027744A1 (en) | Resource data modeling, forecasting and simulation | |
| EP3188096A1 (en) | Data analysis for predictive scheduling optimization for product production | |
| Aslam et al. | A quantitative framework for task allocation in distributed agile software development | |
| US20160086121A1 (en) | Providing Gamification Analytics in an Enterprise Environment | |
| Freitas et al. | Process simulation support in BPM tools: The case of BPMN | |
| Elzamly et al. | Modelling and evaluating software project risks with quantitative analysis techniques in planning software development | |
| Nafianto et al. | Development of Flexible Production Scheduling by Applying Gantt Charts in Manufacturing Module Open Source ERP (Case Study CV. XYZ) | |
| Al-Azawi et al. | Towards agent-based agile approach for game development methodology | |
| CN116091185A (en) | Customer loss early warning method and device | |
| García-Magariño et al. | A repository of method fragments for agent-oriented development of learning-based edge computing systems | |
| Pereira et al. | Towards a characterization of BPM tools' simulation support: the case of BPMN process models | |
| CN113592439A (en) | Software project flow management system and method | |
| CN117196530A (en) | Digital intelligent scheduling method and system for software project set and human resource pool | |
| CN116934051A (en) | Method and device for predicting demand scheduling | |
| CN116523244A (en) | Testing manpower risk early warning method based on outsourcing resources | |
| Zhen et al. | A structured modelling approach to simulating dynamic behaviours in complex organisations | |
| Zebro et al. | Process Mining in Project Management for Smart Cities | |
| Aiello | Workflow performance evaluation. | |
| Zagajsek et al. | Requirements management process model for software development based on legacy system functionalities | |
| US20220327562A1 (en) | Methods and systems for applying survival analysis models to produce temporal measures of sales productivity | |
| Biller et al. | A Practitioner’s Guide to Digital Twin Development | |
| US11093359B2 (en) | System and method for automated desktop analytics triggers | |
| WO2024065776A1 (en) | Method for data processing, apparatus for data processing, electronic device, and storage medium | |
| KR101273374B1 (en) | System and Method for executing simulation workflow based on plug-in |
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 |