JPWO2023053681A5 - - Google Patents
Download PDFInfo
- Publication number
- JPWO2023053681A5 JPWO2023053681A5 JP2023550404A JP2023550404A JPWO2023053681A5 JP WO2023053681 A5 JPWO2023053681 A5 JP WO2023053681A5 JP 2023550404 A JP2023550404 A JP 2023550404A JP 2023550404 A JP2023550404 A JP 2023550404A JP WO2023053681 A5 JPWO2023053681 A5 JP WO2023053681A5
- Authority
- JP
- Japan
- Prior art keywords
- blood
- blood donation
- donation
- district
- locations
- 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
- 239000008280 blood Substances 0.000 claims 134
- 210000004369 blood Anatomy 0.000 claims 134
- 230000007704 transition Effects 0.000 claims 6
- 230000006870 function Effects 0.000 claims 4
- 238000010801 machine learning Methods 0.000 claims 4
- 238000006243 chemical reaction Methods 0.000 claims 2
- 230000002950 deficient Effects 0.000 claims 2
- 238000011156 evaluation Methods 0.000 claims 1
- 238000005457 optimization Methods 0.000 claims 1
Claims (9)
前記データ取得部により取得された、前記地区ごとの人口推移データ並びに前記地区ごとおよび前記血液種別ごとの献血量実績データに基づいて、前記地区ごとの献血量を前記血液種別ごとに予測する献血量予測部と、
を備える献血運用システム。 A data acquisition unit that acquires population transition data for each district that has been divided in advance, and blood donation volume data for each district and each blood type;
a blood donation volume prediction unit that predicts the blood donation volume for each district for each blood type based on the population transition data for each district and the blood donation volume record data for each district and each blood type acquired by the data acquisition unit;
A blood donation operation system equipped with the above.
過去の所定期間における前記地区ごとの人口推移データを説明変数とし、前記所定期間における前記地区ごとおよび血液種別ごとの献血量実績データを目的変数として、前記血液種別ごとに機械学習を行うことで、前記地区ごとの献血量を予測するための献血量予測モデルを前記血液種別ごとに生成し、
生成された前記血液種別ごとの献血量予測モデルに、予測対象期間における前記地区ごとの人口推移データを入力することで、前記予測対象期間における前記地区ごとの献血量を前記血液種別ごとに予測する、
請求項１に記載の献血運用システム。 The blood donation amount prediction unit includes:
Using population transition data for each of the districts in a specified period of time in the past as explanatory variables, and blood donation volume record data for each of the districts and blood type in the specified period as objective variables, machine learning is performed for each of the blood types to generate a blood donation volume prediction model for predicting the blood donation volume for each of the districts for each of the blood types;
The blood donation volume for each blood type is predicted for each of the districts during the prediction period by inputting population transition data for each of the districts during the prediction period into the blood donation volume prediction model for each of the blood types generated.
The blood donation management system according to claim 1.
をさらに備える請求項１に記載の献血運用システム。 a blood donation location determination unit that determines blood donation locations, including locations of blood donation vehicles over time, based on at least blood inventory information for each blood type regarding the amount of blood available in stock, blood order information for each blood type regarding the amount of blood ordered, location information regarding blood donation vehicle parking locations and fixed blood donation centers predetermined for each district, and blood donation volume prediction values for each district and each blood type obtained by prediction by the blood donation volume prediction unit;
The blood donation management system of claim 1 further comprising:
前記献血車の配置場所を含む献血場所を変数とし、前記血液種別ごとの前記血液在庫情報および前記血液種別ごとの前記血液注文情報に基づき得られる不足献血量と、前記地区ごとおよび前記血液種別ごとの献血量予測値に基づき得られる取得献血量と、に基づき得られる前記血液種別ごとの合計献血量を出力値とする評価関数において、前記血液種別ごとの合計献血量がマイナス値になることを避ける又は前記マイナス値の絶対値を最小化する最適化問題を、
前記地区ごとに予め定められた献血車駐車位置および固定的な献血所の位置に関する位置情報、並びに前記地区ごとおよび前記血液種別ごとの献血量予測値を制約条件として解くことで、前記時系列的な献血車の配置場所を含む献血場所を決定する、
請求項３に記載の献血運用システム。 The blood donation location determination unit:
In an evaluation function in which the blood donation locations including the locations of the blood donation vehicles are used as variables, and the total blood donation amount for each blood type obtained based on the shortage blood donation amount obtained based on the blood inventory information for each blood type and the blood order information for each blood type and the obtained blood donation amount obtained based on the predicted blood donation amount for each district and each blood type is used as an output value, an optimization problem is solved to prevent the total blood donation amount for each blood type from becoming a negative value or to minimize the absolute value of the negative value,
determining blood donation locations including the locations of blood donation vehicles in a time series by solving location information regarding the blood donation vehicle parking locations and fixed blood donation station locations that are predetermined for each district, and predicted blood donation amounts for each district and each blood type as constraint conditions;
A blood donation management system as claimed in claim 3.
前記献血場所決定部は、前記血液在庫情報から前記血液注文情報を減算して得られた不足血液量に前記換算係数を乗算することで、前記不足献血量を得る、
請求項４に記載の献血運用システム。 A conversion coefficient is previously calculated to convert the amount of blood shortage, which is a difference value obtained by subtracting the blood order information from the blood inventory information, into the amount of blood donation shortage.
The blood donation site determination unit obtains the deficient blood donation amount by multiplying the deficient blood amount obtained by subtracting the blood order information from the blood inventory information by the conversion coefficient.
A blood donation management system as claimed in claim 4.
過去の献血場所決定時における前記地区ごとに予め定められた献血車駐車位置および固定的な献血所の位置に関する位置情報、前記血液種別ごとの前記血液在庫情報、前記血液種別ごとの前記血液注文情報、および、前記地区ごとおよび前記血液種別ごとの献血量予測値を説明変数とし、当該献血場所決定時に決定された前記献血場所の情報を目的変数として、機械学習を行うことで、前記献血場所を決定するための献血場所決定モデルを生成し、生成された献血場所決定モデルに、対象日における前記地区ごとに予め定められた献血車駐車位置および固定的な献血所の位置に関する位置情報、前記血液種別ごとの前記血液在庫情報、前記血液種別ごとの前記血液注文情報、および、前記地区ごとおよび前記血液種別ごとの献血量予測値を入力することで、対象日における前記時系列的な献血車の配置場所を含む献血場所を決定する、
請求項３に記載の献血運用システム。 The blood donation location determination unit:
A blood donation location determination model for determining the blood donation location is generated by performing machine learning using location information on blood donation vehicle parking locations and fixed blood donation center locations predetermined for each district at the time of past blood donation location determination, the blood inventory information for each blood type, the blood order information for each blood type, and the predicted blood donation volume for each district and for each blood type as explanatory variables, and the information on the blood donation location determined at the time of blood donation location determination is used as a target variable, and a blood donation location including the time-series blood donation vehicle locations on the target day is determined by inputting location information on blood donation vehicle parking locations and fixed blood donation center locations predetermined for each district at the time of past blood donation location determination, the blood inventory information for each blood type, the blood order information for each blood type, and the predicted blood donation volume for each district and for each blood type on the target day into the generated blood donation location determination model.
A blood donation management system as claimed in claim 3.
前記献血量予測部は、前記地区ごとの献血量を前記性年代ごとおよび前記血液種別ごとに予測し、
前記献血場所決定部は、前記地区ごと、前記性年代ごとおよび前記血液種別ごとの献血量予測値を含む情報に基づいて、前記時系列的な献血車の配置場所を含む献血場所を決定する、
請求項３に記載の献血運用システム。 The data acquisition unit acquires population transition data by sex and age group and by district, and blood donation volume record data by sex and age group, by district, and by blood type,
The blood donation volume prediction unit predicts the blood donation volume for each of the regions for each of the sex and age groups and for each of the blood types,
The blood donation location determination unit determines blood donation locations including locations of blood donation vehicles in a time series based on information including predicted blood donation amounts for each district, each sex/age group, and each blood type.
A blood donation management system as claimed in claim 3 .
前記地区ごとの過去の人口推移データ実績値を説明変数とし、前記血液種別の前記地区ごとの献血量実績値を目的変数とする機械学習により生成され、
予測対象期間における前記地区ごとの人口推移データを入力値として、前記血液種別の前記地区ごとの献血量予測値を出力するよう、コンピュータを機能させるための学習済みモデル。 A trained model for causing a computer to function to output a predicted blood donation volume for each blood type in each district,
The data is generated by machine learning using the past population transition data actual value for each district as an explanatory variable and the blood donation amount actual value for each blood type for each district as a target variable,
A trained model for causing a computer to function in such a way that, using population trend data for each district during the prediction period as input values, it outputs a predicted blood donation volume for each blood type for each district.
地区ごとに予め定められた献血車駐車位置および固定的な献血所の位置に関する位置情報、血液種別ごとの血液在庫情報、前記血液種別ごとの血液注文情報、および、前記地区ごとおよび前記血液種別ごとの献血量実績値を説明変数とし、時系列的な献血車の配置場所を含む献血場所の実績情報を目的変数とする機械学習により生成され、
対象日における前記血液種別ごとおよび前記地区ごとの献血量予測値、前記地区ごとの献血車駐車位置および前記献血所の位置に関する位置情報、前記血液種別ごとの前記血液在庫情報、および、前記血液種別ごとの前記血液注文情報を入力値として、時系列的な献血車の配置場所を含む献血場所の情報を出力するよう、コンピュータを機能させるための学習済みモデル。 A trained model for causing a computer to determine blood donation locations, including locations of blood donation vehicles over time, comprising:
The blood donation vehicle parking locations and fixed blood donation center locations, which are predetermined for each district, blood inventory information for each blood type, blood order information for each blood type, and the actual blood donation volume for each district and each blood type are used as explanatory variables, and the blood donation center location information, including the time-series locations of blood donation vehicles, is used as the objective variable, and the blood donation center location information is generated by machine learning.
A trained model for causing a computer to function in such a way that, using as input values the predicted blood donation volume for each blood type and each district on a target day, location information regarding the parking locations of blood donation vehicles and the locations of blood donation centers for each district, the blood inventory information for each blood type, and the blood order information for each blood type, the computer outputs information on blood donation locations, including the locations of blood donation vehicles over time.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2021157918 | 2021-09-28 | ||
| PCT/JP2022/028190 WO2023053681A1 (en) | 2021-09-28 | 2022-07-20 | Blood donation management system and trained model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| JPWO2023053681A1 JPWO2023053681A1 (en) | 2023-04-06 |
| JPWO2023053681A5 true JPWO2023053681A5 (en) | 2024-04-18 |
Family
ID=85782280
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| JP2023550404A Pending JPWO2023053681A1 (en) | 2021-09-28 | 2022-07-20 |
Country Status (2)
| Country | Link |
|---|---|
| JP (1) | JPWO2023053681A1 (en) |
| WO (1) | WO2023053681A1 (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116895355B (en) * | 2023-09-11 | 2023-12-08 | 山东优杰生物科技有限公司 | Blood collection electronic information management system and method for blood collection vehicle |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2013068531A (en) * | 2011-09-22 | 2013-04-18 | Yazaki Energy System Corp | In-vehicle device and urgent invitation system |
| US11481395B2 (en) * | 2015-05-08 | 2022-10-25 | Fenwal, Inc. | Database query processing system for blood donation tracking system |
| JP2021015486A (en) * | 2019-07-12 | 2021-02-12 | いすゞ自動車株式会社 | Mobile blood sampling vehicle operation management system and mobile blood sampling vehicle operation management method |
-
2022
- 2022-07-20 JP JP2023550404A patent/JPWO2023053681A1/ja active Pending
- 2022-07-20 WO PCT/JP2022/028190 patent/WO2023053681A1/en active Application Filing
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109784806B (en) | Supply chain control method, system and storage medium | |
| US20230021252A1 (en) | Systems and methods for monitoring and enhancing utilization of batteries for electric vehicles | |
| CN102208132B (en) | Traffic predicting device, traffic predicting method | |
| JPWO2023053681A5 (en) | ||
| US20180192245A1 (en) | Extraction and Representation method of State Vector of Sensing Data of Internet of Things | |
| Hur et al. | A study on the man-hour prediction system for shipbuilding | |
| CN116167585A (en) | Data processing method, device, equipment and scheduling system applied to garbage collection | |
| CN109816157A (en) | Project plan optimization method, device, computer equipment and storage medium | |
| CN114942947A (en) | Follow-up visit data processing method and system based on intelligent medical treatment | |
| CN117875724A (en) | Purchasing risk management and control method and system based on cloud computing | |
| JPWO2023053684A5 (en) | ||
| CN113420975A (en) | System performance evaluation method and device | |
| CN111105050B (en) | Fan maintenance plan generation method, device, equipment and storage medium | |
| CN116484742A (en) | Vehicle dynamics modeling and vehicle state prediction method, system, equipment and medium | |
| JP6975073B2 (en) | Forecasting systems, forecasting methods, and programs | |
| JPH10228463A (en) | Demand prediction model evaluating method | |
| CN112926801B (en) | Load curve combined prediction method and device based on quantile regression | |
| CN116109339A (en) | Prediction method, prediction device and storage medium for accessory demand | |
| CN110858355A (en) | Project budget balance prediction method and device | |
| US11657446B2 (en) | Information processing apparatus for generating a vehicle operation plan in a plurality of different rental modes | |
| CN114463978A (en) | Data monitoring method based on rail transit information processing terminal | |
| CN113782192A (en) | Grouping model construction method based on causal inference and medical data processing method | |
| CN113859236A (en) | Car following control system, car, method, device, equipment and storage medium | |
| CN113011596A (en) | Method, device and system for automatically updating model and electronic equipment | |
| CN111462893A (en) | Chinese medical record auxiliary diagnosis method and system for providing diagnosis basis |