Method for controlling the availability of a good

Abstract

The invention relates to a method for controlling the availability of a good, wherein at least one of the following input variables is ascertained: availability value of the good (12), date (14), weather data (16), week days (18), public holidays, vacation days, bed occupancy data and / or event data; wherein based on the input variables (12, 14, 16, 18) a probability distribution (10) of the quantity of required goods in a defined availability interval is forecast based on a trained model (22), and an output value (34) is determined based on the probability distribution (10); and wherein the availability of the good is controlled (36) based on the output value (34).

Description

[0001] Method for controlling the availability of goods The invention relates to a method for controlling the availability of goods according to patent claim 1. Furthermore, the invention relates to a computer program according to patent claim 10. The method for controlling the availability of goods described in this application and also the associated computer program generally relate to goods with an expiration date or best-before date. The remaining shelf life until the expiration date can be hours, days, or even weeks. In particular, the method relates to perishable goods such as food, fresh produce, and / or cut flowers. The goods can in particular be a produced food, such as a bakery product (rolls, bread, cakes), or generally fresh or perishable goods that are sold, for example, in supermarkets, hardware stores, or drugstores.The process is particularly applicable in the food trade, the food industry, the catering industry, and the out-of-home catering sector. 20 Especially with the goods mentioned above, controlling the availability of goods influences many aspects. For example, if too many goods are produced and offered than are currently in demand (oversupply), the surplus goods can spoil. This means that many resources, especially material resources, are wasted unnecessarily. On the other hand, offering too little goods is also disadvantageous. Both oversupply and too little supply lead to production and storage capacities not being properly utilized, and staff utilization is also suboptimal. As an example to explain the process, baked goods will be used below. 30If, for example, too many rolls are produced on one day or at a certain time and these are not sold, the produced rolls cannot be sold the next day or can only be sold poorly. Usually, surplus rolls are disposed of the following day, resulting in the loss of valuable raw materials produced with effort and energy. However, this example can also be applied to other goods, such as dairy products, fruit and vegetables, ready-to-eat meals, cut flowers, butchery products, etc. The underlying object of the present invention is therefore to provide a method for controlling the availability of goods and a computer program by means of which the use of energy and resources, such as personnel, time, money and, in particular, raw materials for the goods, can be reduced.10 The problem is solved with the features of the independent patent claims; further practical embodiments and advantages are described in conjunction with the dependent claims. The invention relates to a method for controlling the availability of a product. 15 As already described above, the product can in particular be a product with an expiration date, in particular a perishable product, which should accordingly be available in the right quantity at the right time. Thus, the product can in particular be food, fresh produce, and / or cut flowers. 20 According to the method, at least one of the following input variables is first determined: - Availability value of the product - Date, weather data, days of the week, public holidays, vacation days, bed occupancy data, and / or event data. 25The availability value can – as described below – be read from, among other things, an inventory management system and / or cash register system and / or determined based on recorded measured values. For example, 30 records which stocks are still in stock, for example from the difference between the goods produced the previous day and the goods sold. The availability value can also be measured. Such a measured value can, in particular, be a measured value from a sensor, e.g. a scale, an optical sensor, a fill level sensor and / or a pressure sensor, from which 35 the currently available supply of the goods can be read. In addition to the data relating purely to the goods, other input variables can be determined, including one or more dates. Based on the date, for example, the time of year can be determined.As described below, a correlation to a past date 5 can also be established. Weather data can be supplied as a further input variable. In particular, current weather data or weather data in a defined future time interval are used. Weather data up to 14 days in advance can be used. In particular, hourly weather data is used as input variables. Alternatively or additionally, weekdays, holidays, vacation days, bed occupancy data and / or event data serve as input variables. This data also has an impact on the demand for certain goods and accordingly influences the corresponding expected supply of goods. Returning to the example of bakery products, it is conceivable, for example,20 that more rolls should be available on Saturdays, Sundays and public holidays than on weekdays.Using one or more of the previously mentioned input variables, a probability distribution of the quantity of required goods in a defined availability interval is then predicted based on a trained model, and an output value is determined based on the probability distribution. The probability distribution indicates how likely it is that the quantity of the specific goods will be purchased in the certain previously defined availability interval. The one or more input variables are analyzed, in particular using AI, to determine the probability distribution. The availability interval can be freely selected for the respective application and can, for example, be one or more days or even just one or more hours. For example, the availability interval can cover the period of a sales shift. The selected output value is, in particular, the value, i.e.the quantity of goods with the greatest probability. In the example of bakery products, for example, a baseline value can be forecast based on the availability value (what is in stock), the date of the next day, and the weather forecast for the next day. In this example, the baseline value is the quantity of rolls that are most likely to be sold the next day. After the baseline value has been determined, the availability of goods is controlled based on the baseline value. In particular, an ordering process is controlled based on the baseline value. For example, for a bakery branch, the quantity of rolls that are likely to be sold according to the baseline value is ordered from the wholesale bakery. In particular, a production process is controlled based on the baseline value. If possible, only as many goods are produced or completed as are likely to be needed.If the availability interval is chosen to be relatively small, for example, and only covers a few hours, the exact quantity of goods expected to be required for this number of hours can be produced. 20 In the example of rolls, for example, a baking process can be started during the day whenever a larger quantity of rolls is expected to be in demand. The method then particularly also includes starting such a baking process. 25 Overall, the method according to the invention makes it possible to predict the availability of goods in such a way that as little surplus as possible is produced or ordered and, if possible, too few goods are offered. The input data used and the trained model enable an accurate data-based prediction. This can save energy and resources. 30 The individual input variables can, in particular, be downloaded automatically from one or more sources.In particular, the output value is transmitted to an interface, whereby the35 interface serves as a link to a device for controlling the availability of goods. In particular, the interface communicates with a merchandise management system, cash register system and / or with a production facility. In particular, it is provided that the output value is retrieved from the interface.5 In particular, the probability distribution is forecast using a learning algorithm which includes historical availability values ​​as training data. Historical availability values ​​are values ​​which lie in the past. Historical availability values ​​can be determined from a specific point in time in the past, starting from a specific day, from a10 specific time. In particular, the historical availability values ​​are determined on an hourly or daily basis, i.e. there is a value per hour or per day.However, other granularities are also conceivable. 15 In particular, the historical availability values ​​relate to ordered goods, sold goods, and / or the difference between ordered and sold goods. The historical availability values ​​are determined, in particular, from an inventory management system and / or cash register system that contains order and / or sales figures. Alternatively or additionally, 20 measured values ​​are used, e.g., values ​​from a scale, an optical sensor, a camera, a pressure sensor, and / or a fill level sensor, from which the available and removed goods, or the difference between these, can be derived. 25 In particular, the historical availability values ​​of a specific time interval and, in particular, corresponding data regarding dates, weather, days of the week, holidays, special days, events, and / or bed occupancy data are used.From this, an AI-based model is developed which is then used as the basis for the current forecast of the probability distribution. In order to determine the most accurate initial value possible, availability values ​​from a shorter period of time in a defined time interval are given a higher weighting than availability values ​​before this defined time interval. Such an autoregressive model can therefore quickly adapt to short-term changes in goods sales and is particularly accurate. In a practical embodiment of the method, the mean µ of the probability distribution is used as the initial value. For example, only as many rolls are ordered as the mean of the probability distribution resulted in. The output of such an initial value is designated as "None", so that most likely no surplus will be produced.10 It is also conceivable to choose a surplus value as the output value instead of the mean value µ. The surplus value can in particular be µ + σ. The output of such an output value is referred to as the "target". In this case, a quantity of goods is made available, whereby in the case of µ + σ, with a defined probability 15 a surplus of goods remains. The surplus value can be freely chosen and can also be µ + 1 / 2σ or µ + 2σ, depending on how much surplus is to be accepted. If a value is output as the output value that is greater than the mean value, 20 it could be rolls, for example. Here a surplus can be accepted because rolls can still be used, e.g. for breadcrumbs, dough or as animal feed.The initial value, and in particular whether it is the mean value or a surplus value, is determined based on a property of the goods. In particular, this property is the perishability of the goods or the possibility of reusing the goods for other purposes. In particular, the procedure is carried out at specified times. The times are adapted to the production process and the sales process of the respective goods. In particular, the procedure can be carried out daily, at intervals of several days, or even several times a day.35 In a practical embodiment of the method, the model on which the calculation of the probability distribution is based is recalculated if an actual deviation between the most recently determined output values ​​of a first time interval I and the previous output values ​​of a second time interval II, where time interval II lies further in the past than time interval I, exceeds a target deviation. For the retraining of the model 5, the values ​​in time interval I are then used in particular. This is intended to react to possible sudden changes in the demand for a product and to adapt the forecast to new trends as quickly as possible. In a further practical embodiment, the availability value and / or the historical availability values ​​are measured values ​​recorded by a sensor.In particular, the availability value and / or the historical availability values ​​can be recorded by a scale, an optical sensor, a camera, a pressure sensor and / or a fill level sensor. For example, a scale can be used to determine the number of goods still available in a display. Alternatively or additionally, a camera and subsequent image analysis can be used to determine how many or what volume of goods are currently still available. The same applies to the historical availability values; these can also be previously recorded measured values ​​from sensors. 20 As already described above, in step c), the availability of goods can be controlled by starting a production process. By determining the output value for a specific point in time, the production process can be started at that specific point in time.This makes it possible for fresh goods to be produced as shortly as possible before they are sold. In particular, it can also be used to optimize production processes, for example by scheduling production processes in such a way that there are as many synergy effects as possible. For example, several baking processes can be started one after the other, and the heat from the previous processes can be utilized in each case. One production step can be the better-timed baking of baked goods. In particular, a baking process can be started at a precise time, for example, when goods are likely to be needed. In step c), an oven is then controlled so that it heats up and the desired baking program is set. In particular, an output can be given to a person, so that the production of further goods is started and, if necessary, human intervention or action is required.For example, a person is asked to put rolls into the preheated oven or generally load a production facility. Alternatively, the loading of the oven or a production facility can also be automated using handling robots. The invention also relates to a computer program containing machine-readable instructions which, when executed on one or more computers, cause the computer(s) to carry out a method described above. Further practical embodiments and advantages are described below in conjunction with the figures. They show: Fig. 1 a block diagram for a method for controlling the availability of goods, Fig. 2 a first example of a probability distribution, and Fig. 3 a second example of a probability distribution. In Fig.Figure 1 shows a block diagram by means of which a method for controlling the availability of goods is to be visualized. To determine a probability distribution of goods required in the future, several input variables (12, 14, 16, 18) are fed to a calculation unit (20) on the left side. The input variables (12, 14, 16, 18) shown here are an availability value (12), the date (30), weather data (16), and weekdays (18). It is conceivable that other or further input variables are fed to the calculation unit (20), such as public holidays or bed occupancy data. In particular, the availability values ​​(12) can be measured values ​​recorded by a scale, an optical sensor, a pressure sensor, and / or a fill level sensor. 35 The input variables 12, 14, 16, 18, 20 are fed to the calculation unit 20. The calculation unit 20 is also based on a model 22.The model 22 was trained with historical availability data 24 and corresponding data such as data 26, weather data 28, and weekdays 30. 5 The calculation unit 20 then forecasts a probability distribution 10 from the input variables 12, 14, 16, 18 based on the model 22 (see also Fig. 2). The probability distribution 10 indicates the probability P with which a certain quantity N of a product will be purchased for the forecasted availability interval. 10 It can also be provided that a specification for a surplus value 32 is included. 15 Based on the probability distribution 10, an initial value N (symbolized by box 34) is determined, which is then used to control the availability of goods (symbolized by box 36). Fig. 2 and 3 show two examples of determined probability distributions20 10.These are, for example, probability distributions 10 that were forecast for the same product but for different locations. Looking at Figures 2 and 3 together, it can be seen that the probability distribution 10 in Figure 2 is narrower than the probability distribution 10 shown in Figure 3. If a "no value" is selected as the starting value, which corresponds to the mean value µ, this would correspond in the example shown to a number of 10 pieces 30 for both probability distributions 10. With the "no value," it is likely that no surplus will be produced. However, if a certain surplus can be accepted, a surplus value can also be selected as the starting value. For example, a "can value" (µ + σ) can be selected as the starting value.As can be seen, this would result in a smaller number of goods in the first distribution than in the wider distribution. The same applies to the other surplus values, "target" and "super target" (µ + 2σ). 5.

[0002] List of reference symbols 10 Probability distribution 5 12 Input variable (availability value) 14 Input variable (date) 16 Input variable (weather data) 18 Input variable (weekdays) 20 Calculation unit 10 22 Model 24 Training data (historical availability values) 26 Training data (date) 28 Training data (weather data) 30 Training data (weekdays) 15 32 Default surplus value 34 Determination of output value 36 Control availability 20

Claims

Patent claims 1. Method for controlling the availability of goods, a) wherein at least one of the following input variables is determined: 5 - availability value of the goods (12) - date (14), weather data (16), days of the week (18), holidays, vacation days, bed occupancy data and / or event data; b) wherein, based on the input variables (12, 14, 16, 18), a probability distribution (10) of the quantity of goods required in a defined availability interval is forecast based on a trained model (22), and an output value (34) is determined based on the probability distribution (10); c) and wherein the availability of goods is controlled (36) based on the output value (34).

2. Method according to the preceding claim, characterized in that the prediction of the probability distribution (10) is carried out using a self-learning algorithm that uses historical availability values (24) as training data. 3.Method according to the preceding claim, characterized in that, in a defined time interval, historical availability values from a shorter period of time are given a higher weighting than historical availability values before this defined time interval.

4. Method according to one of the preceding claims, characterized in that the mean value (µ) of the probability distribution (10) or a defined surplus value (32) is selected as the starting value (34).

5. Method according to one of the preceding claims, characterized in that the starting value (34) is selected based on a property of the product.

6. Method according to one of the preceding claims, characterized in that the method is carried out at specified times. 5 7. Method according to one of the preceding claims, characterized in that the model (22) on which the calculation of the probability distribution (10) is based is redetermined if an actual deviation between the most recently determined output values of a first time interval I and the previously determined output values of a second time interval II exceeds a target deviation.

8. Method according to one of the preceding claims, characterized in that the availability value (12) and / or the historical availability values (24) are measured values recorded by a sensor.

9. Method according to one of the preceding claims, characterized in that in step c), the availability of goods is controlled by starting a production process. 10.A computer program containing machine-readable instructions which, when executed on one or more computers, cause the computer(s) to carry out a method according to any one of claims 1 to 9.

Images