CN113344465B - Prediction system for pharmacy operation - Google Patents
Prediction system for pharmacy operation Download PDFInfo
- Publication number
- CN113344465B CN113344465B CN202110792097.4A CN202110792097A CN113344465B CN 113344465 B CN113344465 B CN 113344465B CN 202110792097 A CN202110792097 A CN 202110792097A CN 113344465 B CN113344465 B CN 113344465B
- Authority
- CN
- China
- Prior art keywords
- prediction
- module
- medicine
- historical
- statistics
- 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
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
- G06Q10/067—Enterprise or organisation modelling
-
- 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
- G06N3/045—Combinations of networks
-
- 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
Abstract
The invention relates to the technical field of medicine management, in particular to a prediction system for pharmacy management, which comprises the following components: the classifying module classifies the medicines in the pharmacy according to a classifying system to form a plurality of medicine classifications; the statistics module is used for providing historical data and counting the historical data according to different historical statistics time periods; the calculating module is respectively connected with the classifying module and the counting module and used for calculating a plurality of historical operation indexes of each type of medicine in the corresponding historical counting period; the processing module is connected with the calculation module, and combines the medicine classification, the history management index and the history statistics period of each medicine to form a three-dimensional data structure of the corresponding medicine; and the prediction module is connected with the processing module and predicts the operation condition of the medicine according to the three-dimensional data structure so as to generate a prediction result. The beneficial effects are that: the management condition of the medicine is predicted through the formed three-dimensional data structure, so that management decisions are made from higher dimensionalities, management actions are more accurately selected, and better operation of a pharmacy is ensured.
Description
Technical Field
The invention relates to the technical field of medicine management, in particular to a prediction system for pharmacy management.
Background
In order to facilitate pharmacy management, multidimensional data such as sales contribution rate of medicines, price of customers, gross interest rate, net interest rate, inventory turnover period and the like are generally required to be analyzed and carded, and meanwhile, management indexes of the pharmacy for a period of time in the future are also required to be predicted according to historical data, so that management means such as inventory adjustment, price updating and the like are adopted to ensure better operation of the pharmacy.
In the prior art, only sales are predicted, or sales are respectively predicted after medicines are classified, but in the prediction method, the sales price is regulated after the change trend of sales is predicted, if the sales price is reduced, high sales are generated, and the gross interest rate is reduced. At present, the method for predicting sales only considers the difference among medicines of each type, but ignores the internal relation among medicines of each type, so that the variation trend of the final predicted sales is inaccurate. Therefore, the above-mentioned distinguishing features are a difficult problem to be solved by those skilled in the art.
Disclosure of Invention
In view of the above problems in the prior art, a prediction system for pharmacy management is now provided.
The specific technical scheme is as follows:
the invention provides a prediction system for pharmacy operation, which comprises the following components:
the classifying module is used for classifying all medicines in the pharmacy according to a classifying system so as to form a plurality of medicine classifications;
a statistics module for providing a history data and carrying out statistics on the history data according to different history statistics time periods;
the calculating module is respectively connected with the classifying module and the counting module and is used for calculating a plurality of historical operation indexes of each type of medicine in the corresponding historical counting period;
the processing module is connected with the calculating module and is used for combining the medicine classification of each medicine, the historical operation index and the historical statistical time period to form a three-dimensional data structure corresponding to the medicine;
and the prediction module is connected with the processing module and used for predicting the operation condition of the medicine according to the three-dimensional data structure so as to generate a prediction result.
Preferably, the three-dimensional data structure is represented as coordinate values in an XYZ axis;
and the X axis in the XYZ axes is the medicine classification of the medicines, the Y axis is the history management index of the medicines, and the Z axis is the history statistical period.
Preferably, the method further comprises:
and the generation module is respectively connected with the processing module and the prediction module and is used for acquiring coordinate point data of the specific three-dimensional data structure on the XYZ axes so as to generate a history data image of the specific three-dimensional data structure.
Preferably, the prediction module includes:
the input unit is used for inputting a plurality of continuous historical data images into a convolutional cyclic neural network model formed by pre-training;
the code conversion unit is connected with the input unit and used for coding a plurality of continuous historical data images through a convolution network in the convolution cyclic neural network model so as to respectively generate one-dimensional feature vectors corresponding to each historical data image;
the prediction unit is connected with the coding unit and used for inputting each one-dimensional feature vector into a cyclic neural network in the convolutional cyclic neural network model to perform prediction so as to generate one-dimensional feature prediction vectors corresponding to all the one-dimensional feature vectors respectively;
and the reduction unit is connected with the prediction unit and used for reducing the one-dimensional characteristic prediction vector into a corresponding prediction image and outputting the corresponding prediction image as a prediction result.
Preferably, the reduction unit includes:
and the decoding subunit is used for decoding each one-dimensional characteristic prediction vector through a deconvolution network so as to restore the corresponding prediction image.
Preferably, the reduction unit includes:
and the mapping subunit is used for restoring the one-dimensional characteristic prediction vector into the prediction image in a mapping mode.
Preferably, a plurality of prediction periods are preset, and each prediction period corresponds to one historical statistical period;
the prediction system further comprises:
the selection module is connected with the statistics module and is used for providing users with the selection of the prediction time period;
the statistics module determines the historical statistics period on which the statistics of the historical data depends according to the prediction period output by the selection module.
Preferably, the plurality of the historical operating indexes include sales indexes, financial indexes, shop indexes, store indexes, inventory indexes, and order indexes.
Preferably, the sales index comprises a sold-out rate, a dynamic sales rate, and a sales contribution rate;
the financial indicators include gross and net interest rates;
the goods laying index comprises a new goods laying rate and a new goods ratio;
the store index comprises a person effect, a lawn effect, a guest unit price and a guest bill quantity;
the inventory index comprises turnover rate and inventory rate;
the order indicator includes a pin ratio and a stock ratio.
Preferably, the classification system comprises a motor system, a nervous system, an endocrine system, a circulatory system, a respiratory system, a digestive system, a urinary system, and a reproductive system.
The technical scheme has the following advantages or beneficial effects: the three-dimensional data structure corresponding to the medicines is formed through medicine classification, historical operation indexes and historical statistics time periods to predict the operation conditions of the medicines, so that operation decisions can be made from higher dimensionalities, operation actions can be accurately and directly selected, and better operation of a pharmacy is guaranteed.
Drawings
Embodiments of the present invention will now be described more fully with reference to the accompanying drawings. The drawings, however, are for illustration and description only and are not intended as a definition of the limits of the invention.
FIG. 1 is a functional block diagram of an embodiment of the present invention;
FIG. 2 is a block diagram of a prediction module of an embodiment of the present invention;
FIG. 3 is a block diagram of a restore module according to an embodiment of the invention;
FIG. 4 is a block diagram of another restore module according to an embodiment of the invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be noted that, without conflict, the embodiments of the present invention and features of the embodiments may be combined with each other.
The invention is further described below with reference to the drawings and specific examples, which are not intended to be limiting.
The invention provides a prediction system for pharmacy operation, which is shown in fig. 1 and comprises the following components:
a classification module 1 for classifying all medicines in the pharmacy according to a classification system to form a plurality of medicine classifications;
a statistics module 2, which provides a history data, and is used for counting the history data according to different history statistics time periods;
the calculating module 3 is respectively connected with the classifying module 1 and the counting module 2 and is used for calculating a plurality of historical operation indexes of each type of medicine in the corresponding historical counting period;
the processing module 4 is connected with the calculating module 3 and is used for combining the medicine classification, the historical operation indexes and the historical statistical time period of each type of medicine to form a three-dimensional data structure of the corresponding medicine;
and the prediction module 5 is connected with the processing module 4 and is used for predicting the operation condition of the medicine according to the three-dimensional data structure so as to generate a prediction result.
Specifically, each pharmacy first classifies all medicines in the pharmacy according to its own classification system, and in this embodiment, all medicines in the pharmacy are classified by using eight systems, i.e. a motor system, a nervous system, an endocrine system, a circulatory system, a respiratory system, a digestive system, a urinary system and a reproductive system, so that all medicines in the pharmacy are classified into multiple medicine classifications. In addition, it should be noted that, in this embodiment, the user-defined expansion of drug classification is supported, and the specific classification mode and the number of classifications are not limited, and the method of classifying all drugs by the eight-big system adopted in this embodiment is only used as a standardized suggestion.
Further, part of the historical data is counted according to different historical counting periods, so that the historical data corresponding to a plurality of historical operation indexes of each classified medicine in the corresponding historical counting period is calculated. In addition, before calculating the plurality of historical operation indexes, the plurality of historical operation indexes need to be combined in advance according to the attributes so as to combine the historical operation indexes with similar attributes together. In addition, it should be noted that, in this embodiment, the user-defined expansion of the historical operation indexes is supported, and the number and the defining manner of the historical operation indexes are not limited.
Further, the medicine classification, the historical operation indexes and the historical statistics time period of each type of medicine are combined to form a three-dimensional data structure of the corresponding medicine, and the operation condition of the medicine in the future historical statistics time period is predicted according to each type of medicine and the historical operation indexes corresponding to a certain historical statistics time period through the three-dimensional data structure, so that an operation decision can be made from a higher dimension, an operation action can be more accurately and directly selected, and better operation of a pharmacy is guaranteed.
In a preferred embodiment, the three-dimensional data structure is represented as coordinate values in an XYZ axis;
the X axis in the XYZ axis is the medicine classification of medicines, the Y axis is the history management index of medicines, and the Z axis is the history statistics period.
Specifically, in this embodiment, the drug classification, the historical management index, and the historical statistics period of the drug are combined into XYZ-axis three-dimensional coordinates, so that the drug classification and the historical management index of the drug corresponding to a certain historical statistics period can be easily known.
In a preferred embodiment, the method further comprises:
and a generation module 6, respectively connected to the processing module 4 and the prediction module 5, for acquiring coordinate point data of the specific three-dimensional data structure on the XYZ axes to generate a historical data image of the specific three-dimensional data structure.
Specifically, in this embodiment, according to the three-dimensional data structure formed by combining, from the perspective of any historical statistical period in the Z axis, the corresponding drug classification in the X axis and the historical operation index in the Y axis form a plurality of "snapshots" corresponding to a certain historical statistical period, where the "snapshots" are the above-mentioned historical data images, so that the operation status of each type of drug in a pharmacy in a certain historical statistical period can be clearly displayed.
In a preferred embodiment, as shown in fig. 2, the prediction module 5 comprises:
an input unit 50 for inputting a plurality of continuous historical data images into a convolutional neural network model formed by pre-training;
a code conversion unit 51 connected to the input unit 50 for encoding a plurality of consecutive historical data images through a convolutional network in the convolutional neural network model to generate one-dimensional feature vectors corresponding to each of the historical data images, respectively;
a prediction unit 52, connected to the encoding unit 51, for inputting each one-dimensional feature vector into a convolutional neural network in the convolutional neural network model for prediction, so as to generate one-dimensional feature prediction vectors corresponding to all the one-dimensional feature vectors respectively;
and a reduction unit 53 connected to the prediction unit 52 for reducing the one-dimensional feature prediction vector to a corresponding prediction image and outputting the result as a prediction result.
Specifically, first, according to the above-described manner of acquiring the history data images, a plurality of continuous history data images are acquired, in this embodiment, at least 20 continuous history data images are acquired, and these 20 continuous history data images are input into a convolutional recurrent neural network model trained in advance.
Further, a plurality of continuous historical data images are encoded through a convolution network to respectively generate one-dimensional feature vectors corresponding to each historical data image, and the one-dimensional feature vectors are further input into a cyclic neural network, so that each new feature vector, namely one-dimensional feature prediction vectors corresponding to all the one-dimensional feature vectors, can be obtained in a prediction mode.
And further, the one-dimensional characteristic predictive vector obtained in the step is restored to a predictive image corresponding to the historical data image, and further, future management conditions of the medicine are predicted according to the predictive image, so that management decisions can be made from a higher dimension, management actions can be more accurately and directly selected, and further, better operation of a pharmacy is guaranteed.
In a preferred embodiment, as shown in fig. 3, the reduction unit 53 includes:
a decoding subunit 530 is configured to decode each one-dimensional feature prediction vector through a deconvolution network to restore the one-dimensional feature prediction vector to a corresponding predicted image.
Specifically, the mode of restoring the historical data image into the predicted image may be that each one-dimensional feature prediction vector is decoded through a deconvolution network, so that each one-dimensional feature prediction vector is restored into a corresponding predicted image, and further, future management conditions of the medicine are predicted according to the predicted image.
In a preferred embodiment, as shown in fig. 4, the reduction unit 53 includes:
a mapping subunit 531, configured to restore the one-dimensional feature prediction vector into a predicted image by mapping.
Specifically, the method of restoring the historical data image into the predicted image may be a method of restoring each one-dimensional feature prediction vector into a corresponding predicted image by one-to-one mapping, and predicting future management status of the drug according to the predicted image.
In a preferred embodiment, a plurality of prediction periods are preset, and each prediction period corresponds to a historical statistics period;
the prediction system further comprises:
a selection module 7 connected with the statistics module 2 for providing the user with a selection prediction period;
the statistics module 2 determines a history statistics period on which the statistics of the history data depends, based on the prediction period output by the selection module 7.
Specifically, the plurality of prediction periods in this embodiment include a month statistics period, a week statistics period, and a day statistics period, and if the operation condition of the drug in the next month in the future needs to be predicted, the history statistics period corresponding to the prediction period to be adopted is the month statistics period, and generally suggests the history data of 5-20 months that are most recent in statistics history; if the operation condition of the next week in the future needs to be predicted for the medicine, the historical statistical period corresponding to the prediction period to be adopted is a week statistical period, and the latest 10-40 weeks of historical data in the statistics is generally recommended; if the operation condition of the drug in the next day is required to be predicted, the historical statistical period corresponding to the prediction period to be adopted is a daily statistical period, and the latest 30-60 days of historical data in the statistics is generally recommended.
In a preferred embodiment, the plurality of historical operating metrics includes sales metrics, financial metrics, shop metrics, store metrics, inventory metrics, and order metrics.
In a preferred embodiment, the sales index includes sold-out rate, dynamic sales rate, and sales contribution rate;
financial indicators include gross and net interest rates;
the goods laying index comprises a new goods laying rate and a new goods ratio;
store indexes comprise human efficiency, lawn efficiency, guest price and guest bill quantity;
inventory indicators include turnover rate and inventory rate;
the order indicator includes a pin ratio and a stock ratio.
Specifically, the sold-out rate = sales/orders in this example, which reflects the rate of sales of the drug over time; dynamic sales rate = number of stock with dynamic sales/number of stock prior to use for evaluating the index of sales of various kinds of goods in store; sales contribution rate = sales/total sales of a certain class of drugs, for providing reference data for operational decisions or order resolution etc.
In the present embodiment, the gross rate=gross/actual sales; net rate = net rate/actual sales.
New product spread = stock number of new products already in store/total stock number of new products; new item duty = new item stock/total stock.
Human efficiency = class incomes/business people for reflecting employee product knowledge and sales skills, and rationality of scheduling; plateau effect = class incomes/class business areas, which are used for analyzing the productivity of certain class of medicine areas so as to know the sales reality of the class of medicines, and are important indexes for measuring the marketing based on the class of medicines; guest price = business income/sales number for knowing that the customer's bearing capacity and the goods match the customer's capacity; the customer order quantity=sales number/sales number is used for knowing the sales collocation condition of goods and the consumption of customers, and discussing additional sales skills.
In a preferred embodiment, the classification system comprises the motor system, the nervous system, the endocrine system, the circulatory system, the respiratory system, the digestive system, the urinary system, the reproductive system.
The foregoing description is only illustrative of the preferred embodiments of the present invention and is not to be construed as limiting the scope of the invention, and it will be appreciated by those skilled in the art that equivalent substitutions and obvious variations may be made using the description and illustrations of the present invention, and are intended to be included within the scope of the present invention.
Claims (6)
1. A system for predicting pharmacy operation, comprising:
the classifying module is used for classifying all medicines in the pharmacy according to a classifying system so as to form a plurality of medicine classifications;
a statistics module for providing a history data and carrying out statistics on the history data according to different history statistics time periods;
the calculating module is respectively connected with the classifying module and the counting module and is used for calculating a plurality of historical operation indexes of each type of medicine in the corresponding historical counting period;
the processing module is connected with the calculating module and is used for combining the medicine classification of each medicine, the historical operation index and the historical statistical time period to form a three-dimensional data structure corresponding to the medicine;
the prediction module is connected with the processing module and used for predicting the operation condition of the medicine according to the three-dimensional data structure so as to generate a prediction result;
the three-dimensional data structure is represented as coordinate values in an XYZ axis;
the X axis in the XYZ axes is the medicine classification of the medicines, the Y axis is the history management index of the medicines, and the Z axis is the history statistical period;
further comprises:
the generation module is respectively connected with the processing module and the prediction module and is used for acquiring coordinate point data of the specific three-dimensional data structure on the XYZ axes so as to generate a history data image of the specific three-dimensional data structure;
the prediction module includes:
the input unit is used for inputting a plurality of continuous historical data images into a convolutional cyclic neural network model formed by pre-training;
the code conversion unit is connected with the input unit and used for coding a plurality of continuous historical data images through a convolution network in the convolution cyclic neural network model so as to respectively generate one-dimensional feature vectors corresponding to each historical data image;
the prediction unit is connected with the coding unit and used for inputting each one-dimensional feature vector into a cyclic neural network in the convolutional cyclic neural network model to perform prediction so as to generate one-dimensional feature prediction vectors corresponding to all the one-dimensional feature vectors respectively;
the reduction unit is connected with the prediction unit and used for reducing the one-dimensional characteristic prediction vector into a corresponding prediction image and outputting the corresponding prediction image as a prediction result;
the reduction unit includes:
and the decoding subunit is used for decoding each one-dimensional characteristic prediction vector through a deconvolution network so as to restore the corresponding prediction image.
2. The prediction system of claim 1, wherein the reduction unit comprises:
and the mapping subunit is used for restoring the one-dimensional characteristic prediction vector into the prediction image in a mapping mode.
3. The prediction system according to claim 1, wherein a plurality of prediction periods are preset, each of the prediction periods corresponding to one of the history statistical periods, respectively;
the prediction system further comprises:
the selection module is connected with the statistics module and is used for providing users with the selection of the prediction time period;
the statistics module determines the historical statistics period on which the statistics of the historical data depends according to the prediction period output by the selection module.
4. The predictive system of claim 1 wherein a plurality of said historical operating metrics include sales metrics, financial metrics, shop metrics, store metrics, inventory metrics, and order metrics.
5. The predictive system of claim 4 wherein the sales criteria include a sold-out rate, a dynamic sales rate, and a sales contribution rate;
the financial indicators include gross and net interest rates;
the goods laying index comprises a new goods laying rate and a new goods ratio;
the store index comprises a person effect, a lawn effect, a guest unit price and a guest bill quantity;
the inventory index comprises turnover rate and inventory rate;
the order indicator includes a pin ratio and a stock ratio.
6. The predictive system of claim 1, wherein the classification system comprises a motor system, a nervous system, an endocrine system, a circulatory system, a respiratory system, a digestive system, a urinary system, a reproductive system.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110792097.4A CN113344465B (en) | 2021-07-13 | 2021-07-13 | Prediction system for pharmacy operation |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110792097.4A CN113344465B (en) | 2021-07-13 | 2021-07-13 | Prediction system for pharmacy operation |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113344465A CN113344465A (en) | 2021-09-03 |
CN113344465B true CN113344465B (en) | 2023-09-15 |
Family
ID=77479624
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110792097.4A Active CN113344465B (en) | 2021-07-13 | 2021-07-13 | Prediction system for pharmacy operation |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113344465B (en) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2005216239A (en) * | 2004-02-02 | 2005-08-11 | Santo:Kk | Medicine procurement support system and its method |
CN109033275A (en) * | 2018-07-10 | 2018-12-18 | 武汉海云健康科技股份有限公司 | A kind of prediction technique of the drug regional demand based on association map and neural network |
WO2019144728A1 (en) * | 2018-01-29 | 2019-08-01 | 北京三快在线科技有限公司 | Data processing |
CN111091241A (en) * | 2019-12-11 | 2020-05-01 | 亿达信息技术有限公司 | BP neural network-based drug sales prediction and decision method and system |
CN111178624A (en) * | 2019-12-26 | 2020-05-19 | 浙江大学 | Method for predicting new product demand |
CA3059904A1 (en) * | 2019-10-24 | 2021-04-24 | Brian Keng | Method and system for generating aspects associated with a future event for a subject |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2002358402A (en) * | 2001-05-31 | 2002-12-13 | Dentsu Tec Inc | Method for sales predicting based upon customer value by three index axes |
US7801836B2 (en) * | 2006-09-27 | 2010-09-21 | Infosys Technologies Ltd. | Automated predictive data mining model selection using a genetic algorithm |
-
2021
- 2021-07-13 CN CN202110792097.4A patent/CN113344465B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2005216239A (en) * | 2004-02-02 | 2005-08-11 | Santo:Kk | Medicine procurement support system and its method |
WO2019144728A1 (en) * | 2018-01-29 | 2019-08-01 | 北京三快在线科技有限公司 | Data processing |
CN109033275A (en) * | 2018-07-10 | 2018-12-18 | 武汉海云健康科技股份有限公司 | A kind of prediction technique of the drug regional demand based on association map and neural network |
CA3059904A1 (en) * | 2019-10-24 | 2021-04-24 | Brian Keng | Method and system for generating aspects associated with a future event for a subject |
CN111091241A (en) * | 2019-12-11 | 2020-05-01 | 亿达信息技术有限公司 | BP neural network-based drug sales prediction and decision method and system |
CN111178624A (en) * | 2019-12-26 | 2020-05-19 | 浙江大学 | Method for predicting new product demand |
Non-Patent Citations (2)
Title |
---|
Medicine Expenditure Prediction via a Variance- Based Generative Adversarial Network;SHRUTI KAUSHIK 等;IEEE Access;110947-110958 * |
基于多指标与卷积神经网络的化工产品需求预测;吴学华;马晓华;娄海川;韩晓春;丁杰;侯卫锋;;自动化仪表;39(08);15-18+22 * |
Also Published As
Publication number | Publication date |
---|---|
CN113344465A (en) | 2021-09-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Mišić et al. | Data analytics in operations management: A review | |
US11922440B2 (en) | Demand forecasting using weighted mixed machine learning models | |
US10176494B2 (en) | System for individualized customer interaction | |
Vairaktarakis | Robust multi-item newsboy models with a budget constraint | |
US8650079B2 (en) | Promotion planning system | |
US10621203B2 (en) | Cross-category view of a dataset using an analytic platform | |
US20090006156A1 (en) | Associating a granting matrix with an analytic platform | |
US20090327037A1 (en) | System and Methods for Pricing Markdown with Model Refresh and Reoptimization | |
US20210125073A1 (en) | Method and system for individual demand forecasting | |
Yao et al. | Combining visual customer segmentation and response modeling | |
US7970640B2 (en) | Purchasing optimization system | |
CN112074849A (en) | Price optimization system | |
Kabasakal | Customer segmentation based on recency frequency monetary model: A case study in E-retailing | |
US7174304B1 (en) | System and method for estimating product distribution using a product specific universe | |
WO2021077226A1 (en) | Method and system for individual demand forecasting | |
US11182761B2 (en) | Information technology equipment replacement calculation systems and methods | |
US20230419184A1 (en) | Causal Inference Machine Learning with Statistical Background Subtraction | |
CN113344465B (en) | Prediction system for pharmacy operation | |
Wang et al. | A reliable location design of unmanned vending machines based on customer satisfaction | |
US20230244837A1 (en) | Attribute based modelling | |
WO2021065289A1 (en) | Store assistance system, store assistance method, and program | |
WO2021065290A1 (en) | Store supporting system, learning device, store supporting method, generation method of learned model, and program | |
JP2002123739A (en) | Device and method for processing information and recording medium | |
Perakis et al. | Ancillary services in targeted advertising: from prediction to prescription | |
Fridley | Improving online demand forecast using novel features in website data: a case study at Zara |
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 |