Methods, systems, and programs

Abstract

To accurately predict the molding results of paste-like foods using a molding machine. [Solution] The method of the present disclosure includes obtaining a plurality of characteristic values, which include a first characteristic value indicating the flow properties of the paste material constituting the paste-like food formed by a molding machine, a second characteristic value indicating the mechanical properties of the paste material, a third characteristic value indicating the molding conditions when the paste-like food is formed by the molding machine, and a fourth characteristic value based on one or more combinations of the first characteristic value, the second characteristic value, and the third characteristic value; and outputting an index corresponding to the obtained plurality of characteristic values, using a model that has been pre-designed to output an index indicating the stability of the paste-like food formed by the molding machine, which includes a first index indicating the stability of the extrusion of the paste material from the molding machine when the paste-like food is formed, and a second index indicating the stability of the shape of the paste-like food formed by the molding machine, in response to the input of a plurality of characteristic values.

Description

Technical Field

[0001] The present disclosure relates to a method, a system, and a program.

Background Art

[0002] In recent years, technologies for food processing using molding machines such as 3D food printers have been advancing. In such technologies, for example, a fluid paste-like or dough-like food raw material (hereinafter referred to as a paste material) is pressed and extruded from a molding machine, and the extruded paste material is three-dimensionally laminated to form a food having a desired shape or structure (hereinafter referred to as a paste-like food).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Patent Document 2

Patent Document 3

Patent Document 4

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the above-described technology, the molding result of the paste-like food by the molding machine can vary depending on various characteristics related to molding, such as the physical properties of the paste material and the performance of the molding machine. However, in order to reduce actual trial and error and perform food processing efficiently, it is desirable to be able to appropriately predict the molding result of the paste-like food in advance.

[0005] Therefore, one of the problems that this disclosure aims to solve is to provide a method, system, and program that can appropriately predict in advance the molding results of paste-like food products by a molding machine. [Means for solving the problem]

[0006] An example of the method presented herein is a method performed by at least one computer, which includes: acquiring a plurality of characteristic values ​​including a first characteristic value indicating the flow properties of a paste material constituting a paste-like food product formed by a molding machine; a second characteristic value indicating the mechanical properties of the paste material; a third characteristic value indicating the molding conditions when the paste-like food product is formed by the molding machine; and a fourth characteristic value based on one or more combinations of the first, second, and third characteristic values; and outputting an index corresponding to the acquired plurality of characteristic values, using a model pre-designed to output an index indicating the stability of the paste-like food product formed by the molding machine, the index including a first index indicating the stability of the extrusion of the paste material from the molding machine when the paste-like food product is formed; and a second index indicating the stability of the shape of the paste-like food product formed by the molding machine, in response to input of a plurality of characteristic values.

[0007] Another example of a system provided by this disclosure is an acquisition unit that acquires a plurality of characteristic values, including a first characteristic value indicating the flow properties of a paste material constituting a paste-like food product formed by a molding machine, a second characteristic value indicating the mechanical properties of the paste material, a third characteristic value indicating the molding conditions when the paste-like food product is formed by the molding machine, and a fourth characteristic value based on one or more combinations of the first, second, and third characteristic values; and an output unit that outputs an index corresponding to the acquired plurality of characteristic values, using a model pre-designed to output an index indicating the stability of the paste-like food product formed by the molding machine, the index including a first index indicating the stability of the extrusion of the paste material from the molding machine when the paste-like food product is formed, and a second index indicating the stability of the shape of the paste-like food product formed by the molding machine, in response to the input of a plurality of characteristic values.

[0008] Furthermore, another example of the present disclosure is a program for causing at least one computer to perform the following: acquire a plurality of characteristic values, including a first characteristic value indicating the flow properties of the paste material constituting a paste-like food product formed by a molding machine; a second characteristic value indicating the mechanical properties of the paste material; a third characteristic value indicating the molding conditions when the paste-like food product is formed by the molding machine; and a fourth characteristic value based on one or more combinations of the first, second, and third characteristic values; and output an index corresponding to the acquired plurality of characteristic values, using a model pre-designed to output an index indicating the stability of the paste-like food product formed by the molding machine, the index including a first index indicating the stability of the extrusion of the paste material from the molding machine when the paste-like food product is formed; and a second index indicating the stability of the shape of the paste-like food product formed by the molding machine, in response to the input of a plurality of characteristic values. [Brief explanation of the drawing]

[0009] [Figure 1] Figure 1 is an illustrative and schematic diagram showing an overview of food processing to which the technology according to the embodiment is applied. [Figure 2] Figure 2 is an illustrative and schematic block diagram showing the functional configuration of the system according to the embodiment. [Figure 3] Figure 3 is an illustrative and schematic diagram showing a learning model according to an embodiment. [Figure 4] Figure 4 is an illustrative and schematic flowchart showing an example of the flow of the characteristic value acquisition process according to the embodiment. [Figure 5] Figure 5 is an illustrative and schematic flowchart showing an example of the flow of the molding result prediction process according to the embodiment. [Figure 6] Figure 6 is an illustrative and schematic diagram showing the results of an experiment that confirmed the effectiveness of the technology according to the embodiment. [Figure 7]Figure 7 is an illustrative and schematic block diagram showing an example of the hardware configuration of an information processing device that constitutes the system according to the embodiment. [Modes for carrying out the invention]

[0010] The embodiments of the methods, systems, and programs relating to this disclosure will be described below with reference to the drawings. The configurations of the embodiments described below, and the operations and effects resulting from such configurations, are merely examples and are not limited to the contents described below.

[0011] Furthermore, ordinal numbers such as "1st" and "2nd" are used as needed below, but these ordinal numbers are used for the convenience of identification and do not indicate any particular priority.

[0012] Figure 1 is an illustrative and schematic diagram showing an overview of food processing to which the technology according to the embodiment is applied.

[0013] The technology described in this embodiment can be applied, for example, to the field of food processing using a molding machine 100 called a 3D food printer, as shown in Figure 1. In the example shown in Figure 1, a fluid paste material 110 is extruded under pressure from a nozzle 101 of the molding machine 100, and the extruded paste material 110 is stacked three-dimensionally to form a paste-like food product 111 of a desired shape or structure.

[0014] In such technology, the molding results of the paste-like food 111 by the molding machine 100 can vary depending on various molding characteristics, such as the physical properties of the paste material 110 and the performance of the molding machine 100. However, in order to reduce actual trial and error and process food efficiently, it would be desirable to be able to appropriately predict the molding results of the paste-like food 111 in advance.

[0015] Therefore, the embodiment realizes appropriately predicting in advance the molding result of the paste-like food 111 by the molding machine 100 through the configuration and processing described below.

[0016] FIG. 2 is an exemplary and schematic block diagram showing a functional configuration of the system 200 according to the embodiment.

[0017] As shown in FIG. 2, the system 200 according to the embodiment includes an acquisition unit 210 and an output unit 220.

[0018] The acquisition unit 210 is configured to acquire characteristic values indicating various characteristics related to the molding of the paste-like food 111 by the molding machine 100. More specifically, in the embodiment, the acquisition unit 210 includes a first characteristic value indicating the flow characteristics of the paste material 110 constituting the paste-like food 111, a second characteristic value indicating the mechanical characteristics of the paste material 110, a third characteristic value indicating the molding conditions when the paste-like food 111 is molded by the molding machine 100, and a fourth characteristic value based on one or more combinations of the first to third characteristic values, and is configured to acquire a plurality of characteristic values including these.

[0019] Note that, in the embodiment, the first characteristic value may include values exemplified below. · A value indicating the shear stress at an arbitrary shear rate of the paste material 110 · A value indicating the apparent viscosity at an arbitrary shear rate of the paste material 110 · A value indicating the yield stress of the paste material 110 · A value indicating the consistency index of the paste material 110 · A value indicating the flow index of the paste material 110 · A value indicating the storage modulus at an arbitrary strain rate of the paste material 110 · A value indicating the storage modulus at an arbitrary shear stress of the paste material 110 · A value indicating the storage modulus at an arbitrary frequency of the paste material 110 · A value indicating the loss modulus at an arbitrary strain rate of the paste material 110 • A value indicating the loss modulus of elasticity of the paste material 110 at any shear stress. • A value indicating the loss modulus of the paste material 110 at any given frequency. • A value representing the loss tangent of the paste material 110 at any strain rate. • A value representing the loss tangent of the paste material 110 at any shear stress. • A value indicating the loss-elastic tangent of paste material 110 at any frequency.

[0020] Furthermore, in the embodiment, the second characteristic value may include the values ​​exemplified below. • Value indicating the hardness of paste material 110 • Value indicating the adhesion of paste material 110 • Value indicating the adhesion strength of paste material 110 • Value indicating the cohesiveness of paste material 110 • Value indicating the Young's modulus of paste material 110 • Value indicating the elasticity of paste material 110 • Value indicating the chewability of paste material 110 • Value indicating the gumming properties of paste material 110 • A value indicating the stress at any strain rate or distance of the paste material 110.

[0021] Furthermore, in the embodiment, the third characteristic value may include the values ​​exemplified below. • Typical flow rate of the molding machine 100 when molding paste-like food 111 using the molding machine 100 • Representative length of the molding machine 100 when molding paste-like food 111 using the molding machine 100 Observation time of the molding machine 100 during the molding of paste-like food 111 by the molding machine 100.

[0022] Furthermore, in the embodiment, the fourth characteristic value may include the values ​​exemplified below. • Reynolds number as the ratio of inertial force to viscous force of paste material 110 during molding of paste-like food 111 by molding machine 100 ·Froude number as the ratio of the inertial force of the paste material 110 to gravity during molding of paste-like food 111 according to 100 Galilean number as the ratio of gravity to the viscosity of paste material 110 during molding of paste-like food 111 by molding machine 100. The Bingham number is the ratio of the yield stress to the viscous stress of the paste material 110 during the molding of the paste-like food 111 by the molding machine 100. Deborah's number is the ratio of the relaxation time to the observation time of the paste material 110 during the molding of the paste-like food 111 by the molding machine 100. • The Weisenberg number is the ratio of the viscosity to the elastic force of the paste material 110 during the molding of the paste-like food 111 by the molding machine 100.

[0023] The calculation methods for the various values ​​exemplified above are easily understood by those skilled in the art, therefore, further detailed explanations are omitted here.

[0024] The output unit 220 is configured to output an index indicating the stability of the paste-like food product 111 formed by the molding machine 100, based on a plurality of characteristic values ​​acquired by the acquisition unit 210. More specifically, the output unit 220 is configured to output an index corresponding to the plurality of characteristic values ​​acquired by the acquisition unit 210, using a learning model 221 that has been pre-trained by machine learning to output the index in response to the input of the plurality of characteristic values ​​exemplified above.

[0025] In the following, we will mainly describe a configuration in which an indicator is output using a pre-trained learning model 221 obtained by machine learning, but this configuration is merely one example. The technology disclosed herein may also include a configuration in which an inference model is pre-designed to output in response to inputs of multiple characteristic values ​​using simple linear regression analysis or various other analytical methods, without using machine learning, and an indicator is output using this inference model.

[0026] Figure 3 is an illustrative and schematic diagram showing a learning model 221 according to an embodiment.

[0027] As shown in Figure 3, the learning model 221 according to the embodiment is configured to output two indicators in response to the input of first to fourth characteristic values ​​as multiple characteristic values ​​acquired by the acquisition unit 210: a first indicator indicating the stability of the extrusion of the paste material 110 from the molding machine 100 when the paste-like food 111 is formed, and a second indicator indicating the stability of the shape of the paste-like food 111 formed by the molding machine 100. Thus, according to the technology of the embodiment, it is possible to appropriately predict and evaluate in advance the molding result of the paste-like food 111 by the molding machine 100 using these two different indicators. In the embodiment, the output format of the indicator may be a simple ○ (suitable) / × (unsuitable) format indicating whether or not a predetermined standard has been reached, or it may be a format in which the standard is set in three or more stages. In addition, in the embodiment, when outputting the indicator, a policy for adjusting the mixing ratio of the paste material 110 to improve the evaluation by the indicator may also be output.

[0028] Here, the learning model 221 according to the embodiment may be configured to accept all of the various values ​​exemplified above as first to fourth characteristic values ​​as input, or it may be configured to accept only values ​​that have been selectively determined by a predetermined feature selection algorithm during training of the learning model 221 as potentially contributing to improving the accuracy of the indicator output from the learning model 221, rather than all of the various values ​​exemplified above as input. As the feature selection algorithm, a generally well-known algorithm such as RFE (Recursive Feature Elimination) can be used. In addition, as the algorithm used to train the learning model 221 in the embodiment, a generally well-known algorithm such as logistic regression (LG), simple Bayes (NB), support vector machine (SVM), random forest (RF), and Light GBM (LGBM) can be used.

[0029] Based on the configuration described above, the system 200 according to the embodiment executes processing in the flow shown in Figures 4 and 5 below.

[0030] Figure 4 is an illustrative and schematic flowchart showing an example of the flow of characteristic value acquisition processing according to the embodiment. The series of processes shown in Figure 4 are executed by the acquisition unit 210 of the system 200 according to the embodiment.

[0031] As shown in Figure 4, the acquisition unit 210 in this embodiment first acquires information regarding the physical properties of the paste material 110 and the performance of the molding machine 100 in S410. The physical properties of the paste material 110 are acquired, for example, by analyzing the paste material 110 with an analytical device (physical property measuring instrument). Then, in S420, the acquisition unit 210 calculates first to fourth characteristic values, including the various values ​​exemplified above, based on the information acquired in S410. Then, in S430, the acquisition unit 210 databases the first to fourth characteristic values ​​calculated in S420. The process then ends.

[0032] Figure 5 is an illustrative and schematic flowchart showing an example of the flow of the molding result prediction process according to the embodiment. The series of processes shown in Figure 5 are executed by the output unit 220 of the system 200 according to the embodiment.

[0033] As shown in Figure 5, the output unit 220 in this embodiment first acquires the first to fourth characteristic values ​​that were databased in S420 (see Figure 4) in S510. Then, in S520, the output unit 220 uses the feature selection algorithm described above to extract characteristic values ​​from all of the first to fourth characteristic values ​​acquired in S510 that may contribute to improving the accuracy of the indicator output from the learning model 221.

[0034] Then, in S530, the output unit 220 inputs the characteristic values ​​extracted in S520 into the learning model 221. Then, in S540, the output unit 220 outputs the first and second indicators output from the learning model 221 in response to the characteristic values ​​input in S530. Then, the process ends.

[0035] As described above, the system 200 according to the embodiment includes an acquisition unit 210 and an output unit 220. The acquisition unit 210 acquires a plurality of characteristic values, including a first characteristic value indicating the flow characteristics of the paste material 110 constituting the paste-like food 111 formed by the molding machine 100, a second characteristic value indicating the mechanical properties of the paste material 110, a third characteristic value indicating the molding conditions when the paste-like food 111 is formed by the molding machine 100, and a fourth characteristic value based on one or more combinations of the first characteristic value, the second characteristic value, and the third characteristic value. The output unit 220 outputs an index corresponding to the multiple characteristic values ​​acquired by the acquisition unit 210, using a learning model 221 as an example of a model pre-designed to output an index indicating the stability of the paste-like food 111 formed by the molding machine 100, which includes a first index indicating the stability of the extrusion of the paste material 110 from the molding machine 100 when the paste-like food 111 is formed, and a second index indicating the stability of the shape of the paste-like food 111 formed by the molding machine 100, in response to the input of multiple characteristic values.

[0036] With the above configuration, the molding results of the paste-like food 111 by the molding machine 100 can be appropriately predicted in advance based on the correlation between the first to fourth characteristic values, which show the physical properties of the paste material 110 and the performance of the molding machine 100 from multiple perspectives, and the first and second indicators, which show the stability of the paste-like food 111 molded by the molding machine 100 from multiple perspectives.

[0037] In particular, the technology described in this embodiment aims to improve prediction accuracy by not only considering the first to third characteristic values ​​individually, but also by further considering a fourth characteristic value based on one or more combinations of these first to third characteristic values. Below, we will briefly explain the results of a comparative experiment comparing cases where the fourth characteristic value is not considered and cases where it is considered.

[0038] Figure 6 is an illustrative and schematic diagram showing the results of an experiment that confirmed the effectiveness of the technology according to the embodiment.

[0039] Table 600, shown in Figure 6, shows the results of an experiment that confirmed the accuracy (correct response rate) of the output of a learning model trained without including the fourth characteristic value in the training data and a learning model trained with the fourth characteristic value included. In the example shown in Figure 6, the correct response rates of a learning model trained using logistic regression (LG), a learning model trained using simple Bayes (NB), a learning model trained using support vector machines (SVM), a learning model trained using random forest (RF), and a learning model trained using Light GBM (LGBM) are summarized in a table. As shown in Figure 6, in this experiment, the learning model trained with the fourth characteristic value included in the training data obtained a higher correct response rate than the learning model trained without including the fourth characteristic value in the training data. Therefore, it was confirmed that considering the fourth characteristic value can be expected to improve the accuracy of predicting the molding result of the paste-like food 111 by the molding machine 100.

[0040] In the embodiments described above, an example is given of applying the technology of this disclosure to a molding machine 100 (see Figure 1) called a 3D food printer, which maintains its shape by extruding paste material 110 from a nozzle 101 and stacking it three-dimensionally. However, the technology of this disclosure can be applied to molding machines other than 3D food printers, as long as they are molding machines usable in the food industry that can pressurize and extrude a fluid paste material from a flow path such as a nozzle and maintain the shape of the extruded paste material. Examples of molding machines other than 3D food printers include, for example, a food extruder, which extrudes paste material linearly from a nozzle and maintains a linear shape, and a rolling mill, which extrudes paste material into a sheet shape while pressurizing it with rollers and maintains a sheet shape.

[0041] Finally, the hardware configuration of the system 200 according to the above-described embodiment will be explained. The system 200 according to the embodiment is implemented by an information processing device 700 having a hardware configuration equivalent to that of a general-purpose computer, as shown in Figure 7 below.

[0042] Figure 7 is an exemplary and schematic block diagram showing the hardware configuration of the information processing device 700 that constitutes the system 200 according to the embodiment.

[0043] As shown in Figure 7, the information processing device 700 includes a processor 710, memory 720, storage 730, input / output interface (I / F) 740, and communication interface (I / F) 750. These hardware components are connected to the bus 760.

[0044] The processor 710 is configured, for example, as a CPU (Central Processing Unit) and comprehensively controls the operation of each part of the information processing device 700.

[0045] The memory 720 includes, for example, ROM (Read Only Memory) and RAM (Random Access Memory), and provides volatile or non-volatile storage for various types of data, such as programs executed by the processor 710, and a workspace for the processor 710 to execute programs.

[0046] Storage 730 includes, for example, an HDD (Hard Disk Drive) or SSD (Solid State Drive) and stores various types of data non-volatilely.

[0047] The input / output interface 740 controls the input of data from an input device, such as a mouse or keyboard, to the information processing device 700, and the output of data from the information processing device 700 to an output device, such as a display or speaker.

[0048] The communication interface 750 enables the information processing device 700 to communicate with other devices.

[0049] The functional configuration of the system 200 according to this embodiment (see Figure 2) is realized as a group of functional modules through the cooperation of hardware and software, as a result of the processor 710 executing a program pre-stored in the memory 720 or storage 730. However, in this embodiment, some or all of the group of functional modules shown in Figure 2 may be realized solely by hardware, such as specially designed circuits. Furthermore, in this embodiment, the group of functional modules shown in Figure 2 may be realized by a single information processing device 700, or they may be distributed and realized across multiple information processing devices 700.

[0050] The program described above does not necessarily need to be pre-stored in memory 720 or storage 730. For example, the program described above may be provided as a computer program product recorded in an installable or executable format on a computer-readable medium such as various magnetic disks like flexible disks (FDs) or various optical disks like DVDs (Digital Versatile Disks).

[0051] Furthermore, the aforementioned program may be provided or distributed via a network such as the Internet. In other words, the aforementioned program may be provided in a form where it is stored on a computer connected to a network such as the Internet and available for download via the network.

[0052] While embodiments of this disclosure have been described above, these embodiments are presented as examples and are not intended to limit the scope of the invention. These novel embodiments can be implemented in a variety of other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their variations are included in the scope or spirit of the invention, as well as in the claims of the invention and its equivalents. [Explanation of Symbols]

[0053] 100 molding machine 110 Paste ingredients 111 Paste-like foods 200 Systems 210 Acquisition Department 220 Output section

Claims

1. A method that is performed by at least one computer, Obtaining a plurality of characteristic values, including a first characteristic value indicating the flow properties of the paste material constituting the paste-like food formed by the molding machine, a second characteristic value indicating the mechanical properties of the paste material, a third characteristic value indicating the molding conditions when the paste-like food is formed by the molding machine, and a fourth characteristic value based on one or more combinations of the first characteristic value, the second characteristic value, and the third characteristic value, An index indicating the stability of the paste-like food formed by the molding machine, comprising a first index indicating the stability of the extrusion of the paste material from the molding machine when the paste-like food is formed, and a second index indicating the stability of the shape of the paste-like food formed by the molding machine, is output using a model pre-designed to output an index corresponding to the acquired multiple characteristic values ​​in response to the input of the multiple characteristic values. Methods that include...

2. The model includes a learning model that has been pre-trained by machine learning to output the indicator in response to the input of the plurality of characteristic values. The method according to claim 1.

3. The aforementioned multiple characteristic values ​​are characteristic values ​​that have been selectively determined by a predetermined feature selection algorithm during the training of the learning model, as they may contribute to improving the accuracy of the output of the indicator from the learning model. The method according to claim 2.

4. The first characteristic value is, A value representing the shear stress of the paste material at any shear rate, The value representing the apparent viscosity of the paste material at any shear rate, The value indicating the yield stress of the paste material, The value indicating the consistency index of the paste material, The value indicating the flow index of the paste material, The value representing the storage modulus of the paste material at any given strain rate, The value representing the storage modulus of the paste material at any shear stress, The value representing the storage modulus of the paste material at any frequency, The value representing the loss modulus of elasticity at any strain rate of the paste material, The value representing the loss modulus of elasticity at any shear stress of the paste material, The value representing the loss modulus of elasticity of the paste material at any frequency, The value representing the loss loss tangent at any strain rate of the paste material, The value representing the loss loss tangent at any shear stress of the paste material, The value representing the loss-elastic tangent of the paste material at any frequency, The method according to claim 1, including the method described in claim 1.

5. The second characteristic value is, The value indicating the hardness of the paste material, The value indicating the adhesion of the paste material, The value indicating the adhesion force of the paste material, The value indicating the cohesiveness of the paste material, The value representing the Young's modulus of the aforementioned paste material, The value indicating the elasticity of the paste material, The value indicating the chewability of the paste material, The value indicating the gumming properties of the paste material, A value indicating the stress at any strain rate or distance of the paste material, The method according to claim 1, including the method described in claim 1.

6. The third characteristic value is, The representative flow rate of the molding machine when molding the paste-like food by the molding machine, The representative length of the molding machine when molding the paste-like food by the molding machine, The observation time of the molding machine during the molding of the paste-like food by the molding machine, The method according to claim 1, including the method described in claim 1.

7. The aforementioned fourth characteristic value is, The Reynolds number, which is the ratio of the inertial force to the viscous force of the paste material during molding of the paste-like food by the molding machine, The Froude number, which is the ratio of the inertial force to gravity of the paste material during molding of the paste-like food by the molding machine, The Galilean number, which is the ratio of gravity to the viscous force of the paste material during molding of the paste-like food by the molding machine, The Bingham number, which is the ratio of the yield stress to the viscous stress of the paste material during molding of the paste-like food by the molding machine, The Deborah number, which is the ratio of the relaxation time and observation time of the paste material during the molding of the paste-like food by the molding machine, The Weisenberg number, which is the ratio of the viscous force to the elastic force of the paste material during molding of the paste-like food by the molding machine, The method according to claim 1, including the method described in claim 1.

8. An acquisition unit that acquires a plurality of characteristic values, including a first characteristic value indicating the flow properties of the paste material constituting the paste-like food formed by the molding machine, a second characteristic value indicating the mechanical properties of the paste material, a third characteristic value indicating the molding conditions when the paste-like food is formed by the molding machine, and a fourth characteristic value based on one or more combinations of the first characteristic value, the second characteristic value, and the third characteristic value. An output unit outputs an index corresponding to the acquired multiple characteristic values, using a model pre-designed to output an index indicating the stability of the paste-like food formed by the molding machine, the index including a first index indicating the stability of the extrusion of the paste material from the molding machine when the paste-like food is formed, and a second index indicating the stability of the shape of the paste-like food formed by the molding machine, in response to the input of the multiple characteristic values. A system that includes this.

9. On at least one computer, Obtaining a plurality of characteristic values, including a first characteristic value indicating the flow properties of the paste material constituting the paste-like food formed by the molding machine, a second characteristic value indicating the mechanical properties of the paste material, a third characteristic value indicating the molding conditions when the paste-like food is formed by the molding machine, and a fourth characteristic value based on one or more combinations of the first characteristic value, the second characteristic value, and the third characteristic value, An index indicating the stability of the paste-like food formed by the molding machine, comprising a first index indicating the stability of the extrusion of the paste material from the molding machine when the paste-like food is formed, and a second index indicating the stability of the shape of the paste-like food formed by the molding machine, is output using a model pre-designed to output an index corresponding to the acquired multiple characteristic values ​​in response to the input of the multiple characteristic values. A program to execute [something].

Images