Information Processing System, Information Processing Method, and Program

Abstract

Provided are an information processing system, a method, and a program capable of overall optimization of a manufacturing line. 【Solution means】In an information processing system in which an information processing device and a plurality of user terminals are communicably connected through a communication line, a control unit 11 of the information processing device 10 includes a pre-process model that simulates a pre-process for generating an intermediate product from raw materials, and a post-process model that simulates a post-process for generating a final product from the intermediate product. A model acquisition unit 112 that acquires the model, a condition acquisition unit 113 that acquires process conditions in each of the pre-process model and the post-process model, and by inputting the process conditions into at least a connection model in which the pre-process model and the post-process model are connected, at least one of the characteristic value of the intermediate product, the characteristic value of the final product, the state value of the device used in the pre-process, and the state value of the device used in the post-process is obtained as an inference value. It includes an inference unit 114.

Description

[Technical Field]

[0001] The present invention relates to an information processing system, an information processing method, and a program. [Background technology]

[0002] Patent Document 1 discloses a system for optimizing production plans and logistics plans by using a plurality of manufacturing processes as an optimization unit. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2024-58363 Summary of the Invention [Problem to be solved by the invention]

[0004] The above system can be optimized using production cost as an objective function, but the cost of each manufacturing process is fixed and unrelated to other processes, so there is room for improvement in optimizing the entire manufacturing line.

[0005] In view of the above circumstances, the present invention provides an information processing system and the like that enables the overall optimization of a manufacturing line. [Means for solving the problem]

[0006] According to one aspect of the present invention, there is provided an information processing system including a processor configured to execute the following steps by reading a program. In a model acquisition step, a pre-process model simulating a pre-process for generating an intermediate product from raw materials and a post-process model simulating a post-process for generating a final product from the intermediate product are acquired. In a condition acquisition step, process conditions in each of the pre-process model and the post-process model are acquired. In an inference step, by inputting the process conditions into a connected model in which at least the pre-process model and the post-process model are connected, at least one of a characteristic value of the intermediate product, a characteristic value of the final product, a state value of a device used in the pre-process, and a state value of a device used in the post-process is acquired as an inference value.

[0007] According to such an aspect, by referring to the inference value obtained from the connected model and adjusting the process conditions in the pre-process and / or the post-process, the entire manufacturing line can be optimized.

Brief Description of Drawings

[0008]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Embodiments for Carrying Out the Invention

[0009] Hereinafter, embodiments of the present invention will be described with reference to the drawings. Various features shown in the embodiments described below can be combined with each other.

[0010] Incidentally, the program for realizing the software appearing in one embodiment may be provided as a non-transitory computer-readable medium that can be read by a computer, may be provided so as to be downloadable from an external server, or may be provided such that the program is launched on an external computer and its function is realized on a client terminal (so-called cloud computing).

[0011] Also, in various information processes according to one embodiment, an input and an output corresponding to the input can be realized. Here, if an output is obtained as a result of the input, the form of the information (hereinafter referred to as reference information) referred to in such information processing is not limited. The reference information may be, for example, rule-based information such as a database, a lookup table, a predetermined function (including a judgment formula such as a regression formula constructed by a statistical method), a learned model in which the correlation between the input and the output has been learned in advance, or a large language model capable of outputting a desired result by inputting a prompt.

[0012] Also, in one embodiment, the "unit" may include, for example, hardware resources implemented by a circuit in a broad sense and information processing of software that can be specifically realized by these hardware resources. Also, in one embodiment, various information is handled, and these information are represented, for example, by physical values of signal values representing voltage and current, the high and low of signal values as a set of binary bits composed of 0 or 1, or quantum superposition (so-called quantum bits), and communication and calculation can be executed on a circuit in a broad sense.

[0013] Furthermore, a circuit in a broad sense is a circuit realized by appropriately combining at least a circuit, circuitry, a processor, a memory, etc. The processor may be a general-purpose processor or a dedicated circuit. That is, it includes application specific integrated circuits (ASICs), programmable logic devices (e.g., simple programmable logic devices (SPLDs), complex programmable logic devices (CPLDs), and field programmable gate arrays (FPGAs)).

[0014] 1. Hardware Configuration In this section, the hardware configuration will be described.

[0015] <Information Processing System 1> FIG. 1 is a configuration diagram showing the information processing system 1. The information processing system 1 includes a communication line 2, an information processing device 10, and a plurality of user terminals 20. The information processing device 10 and the user terminals 20 are configured to be communicable through the communication line 2. The connection between the information processing device 10 and the user terminals 20 may be wired or wireless.

[0016] In one embodiment of the information processing system 1, the information processing system 1 is composed of one or more devices or components. Hereinafter, these components will be described.

[0017] <Information Processing Device 10> Figure 2 is a block diagram showing the hardware configuration of the information processing apparatus 10. As shown in Figure 2, the information processing apparatus 10 includes a control unit 11, a storage unit 12, a communication unit 13, and a communication bus 14. The control unit 11, the storage unit 12, and the communication unit 13 are electrically connected to each other inside the information processing apparatus 10 via the communication bus 14.

[0018] <Control Unit 11> The control unit 11 performs processing and control of the overall operations related to the information processing apparatus 10. The control unit 11 is, for example, a Central Processing Unit (CPU). The control unit 11 realizes various functions related to the information processing apparatus 10 by reading a predetermined program stored in the storage unit 12. That is, the information processing by software stored in the storage unit 12 is specifically realized by the control unit 11, which is an example of hardware, and can be executed as each functional unit included in the control unit 11. These will be described in more detail in the next section. Note that the control unit 11 is not limited to being single, and the information processing apparatus 10 may have a plurality of control units 11 for each function. Further, the information processing apparatus 10 may have a configuration combining these.

[0019] <Storage Unit 12> The storage unit 12 stores various information defined by the foregoing description. This can be implemented, for example, as a storage device such as a Solid State Drive (SSD) that stores various programs and the like related to the information processing apparatus 10 executed by the control unit 11, or as a memory such as a Random Access Memory (RAM) that stores temporarily necessary information (arguments, arrays, etc.) related to the calculation of a program. The storage unit 12 stores various programs, variables, etc. related to the information processing apparatus 10 executed by the control unit 11.

[0020] <Communication Unit 13> The communication unit 13 preferably uses wired communication means such as USB, IEEE 1394, Thunderbolt (registered trademark), and wired LAN network communication. However, it may also include wireless LAN network communication, mobile communication such as LTE / 5G, and BLUETOOTH (registered trademark) communication as required. That is, it is more preferably implemented as a set of these multiple communication means. That is, the information processing apparatus 10 may communicate various information from the outside via the communication unit 13 and the network.

[0021] The information processing apparatus 10 may be in an on-premises form or a cloud form. As the information processing apparatus 10 in the cloud form, for example, it may provide the above-described functions and processes in the form of SaaS (Software as a Service) or cloud computing.

[0022] <User terminal 20> The user terminal 20 is an information processing terminal used by a user who uses the manufacturing line optimization service provided by the information processing apparatus 10. FIG. 3 is a block diagram showing the hardware configuration of the user terminal 20. As shown in FIG. 3, the user terminal 20 includes a control unit 21, a storage unit 22, a communication unit 23, an input unit 24, an output unit 25, and a communication bus 26. The control unit 21, the storage unit 22, the communication unit 23, the input unit 24, and the output unit 25 are electrically connected inside the user terminal 20 via the communication bus 26. The descriptions of the control unit 21, the storage unit 22, and the communication unit 23 are omitted because they are the same as the descriptions of the respective units in the information processing apparatus 10.

[0023] <Input unit 24> The input unit 24 receives action inputs made by the user. The action inputs are transferred as command signals to the control unit 21 via the communication bus 26. The control unit 21 can execute predetermined control and calculations as necessary based on the transferred command signals. The input unit 24 may be included in the housing of the user terminal 20 or may be externally attached. For example, the input unit 24 may be integrated with the output unit 25 and implemented as a touch panel. When the input unit 24 is implemented as a touch panel, the user can input tap actions, swipe actions, etc. to the input unit 24. As the input unit 24, instead of a touch panel, a switch button, a mouse, a track pad, a QWERTY keyboard, etc. can be adopted.

[0024] <Output unit 25> The output unit 25 displays a screen of a graphical user interface (GUI) that the user can act on. The output unit 25 may be included in the housing of the user terminal 20 or may be externally attached. Specifically, the output unit 25 can be implemented as a display device such as a CRT display, a liquid crystal display, an organic EL display, a plasma display, etc. These display devices are preferably implemented selectively according to the type of the user terminal 20.

[0025] 2. Functional configuration In this section, the functional configuration of this embodiment will be described. The information processing by software stored in the storage unit 12 is specifically realized by the control unit 11 which is an example of hardware, and thus can be executed as each functional unit included in the control unit 11 (the processor included in the information processing system 1).

[0026] FIG. 4 is a block diagram showing the functions realized by the information processing apparatus 10 (control unit 11) and the user terminal 20 (control unit 21).

[0027] As shown in FIG. 4A, the information processing apparatus 10 (control unit 11) includes a model registration unit 111, a model acquisition unit 112, a condition acquisition unit 113, an inference unit 114, a target acquisition unit 115, a condition adjustment unit 116, and an artificial intelligence unit 120. As shown in FIG. 4B, the user terminal 20 (control unit 21) includes a display unit 211 and an operation acquisition unit 212.

[0028] <Model registration unit 111> The model registration unit 111 is configured to accept the registration of a production process model that simulates the process of generating a product. Specifically, the model registration unit 111 accepts the upload of a production process model from the user terminal 20, the input of the storage location of the production process model on the network from the user terminal 20, etc., and registers the model in, for example, the model database stored in the storage unit 12.

[0029] The "process of generating a product" means a production process in which raw materials are received and the target product is obtained through processes such as chemical reactions and mechanical processing of the raw materials using equipment. Specifically, the "process of generating a product" includes a synthesis process of multiple raw materials, a dispersion process of raw materials, a mixing (kneading) process of multiple raw materials, a separation process of specific components from raw materials, a modification process of raw materials, a forming (casting) process of raw materials, a cutting process of raw materials, a coating process of raw materials, a dyeing process of raw materials, a surface processing (polishing, plating, thin film formation) process of raw materials, an attachment process of other parts to raw materials, an attachment process of raw materials to other parts, a packaging process of raw materials, etc. Note that multiple types of raw materials may be input into one production process. Also, multiple types of products may be obtained from one production process.

[0030] The "production process model that simulates the process" is a numerical model that defines the correlation between input parameters representing the characteristics of raw materials and process conditions (device setting conditions) and output parameters representing the characteristics of the product and the state of the device used in the process.

[0031] The characteristics of the raw materials, which are input parameters, include, for example, the material of the raw materials (composition ratio, purity, quality), temperature distribution, stress distribution, volume, density, shape, etc. The process conditions, which are input parameters, include, for example, temperature, pressure, magnetic field, voltage (current), processing time, processing sequence, etc. when performing processes such as chemical reactions and mechanical processing.

[0032] More specific process conditions include, for example, temperature sequence, partial pressure sequence, switching timing of gas species, output value sequence of heating power supply, rotation sequence of each axis of the processing device, feed rate sequence of each axis, processing pressure sequence, device shape, material input amount, type of consumable member and physical property values before process execution, cumulative usage times of consumable members before process execution, cumulative usage times of the device before process execution, cumulative usage times of the device after the latest maintenance, installation environment of the device (temperature, humidity, etc.), processing position with respect to the raw materials, etc.

[0033] The characteristics of the product, which are output parameters, include, for example, temperature distribution, stress distribution, defect density distribution, shape (surface shape), material composition ratio, etc. The state of the device, which is an output parameter, includes temperature distribution (heat generation distribution) inside the device, pressure distribution (gas partial pressure distribution, gas flow velocity distribution), magnetic field distribution, type of consumable member and physical property values after process execution, cumulative usage times of consumable members after process execution, cumulative usage times of the device after process execution, cumulative usage times of the device after the latest maintenance, installation environment of the device (temperature, humidity, etc.), degree of device deterioration, degree of deterioration of consumable members, degree of device contamination, time series data (sensor values) such as temperature, gas flow rate, current, etc. inside the device, electricity consumption, production speed, CO2 emission amount, production cost, production variation, estimated maintenance time of the device, replacement time of consumable members, etc.

[0034] The production process model is an estimator constructed to be able to output output parameters with input parameters as inputs. The production process model may be, for example, a table, a function, a simple algorithm, etc. that shows the correlation between input parameters and output parameters. The correlation included in the production process model can be constructed, for example, by statistically analyzing the measured data in the production process that the production process model mimics.

[0035] The production process model may be a learning model trained to output output parameters using input parameters as input. In this case, the production process model is trained using a combination of input parameters for learning and output parameters corresponding to the input parameters as teacher data. The parameters of the learning model calculated, tuned, etc. by such learning constitute the correlation of the production process model.

[0036] The production process model may be a physical simulator (physical calculation engine). In this case, the production process model uses the input parameters as initial conditions and outputs, as output parameters, the results of performing physical calculations of the processes included in the production process on the raw materials.

[0037] The model registration unit 111 may register model information regarding the production process model together with the production process model. The model information is input from the user terminal 20. The model information includes, for example, the dimensions (the number of elements of the parameters) of the input parameters and output parameters respectively, element information about the individual elements of the input parameters and output parameters, meta information of the production process model, usage range information, and the like.

[0038] The element information includes, for example, the name of the element, the numerical range (maximum value and minimum value), the variation of the numerical value, the unit, the significant digits, a flag indicating whether adjustment is possible (whether it is a fixed value), non-disclosure information indicating whether it can be disclosed to other users, and the like.

[0039] Elements included in the non-disclosure information with information (flag) indicating "not publicly available" become non-public elements, and the specific numerical values of the non-public elements are not disclosed to other users who use the production process model (that is, users other than the user who registered the production process model). Also, when the non-public element is an input parameter, the non-disclosure information includes information specifying, for example, either of the following adjustment methods (1) and (2) for adjusting the numerical value of the non-public element. (1) The numerical value of the non-public element is fixed and adjustment is not possible (the numerical value is not displayed to other users) (2) The numerical values of the non-disclosed elements can be selected from the pre-prepared candidates (the numerical values listed in the list). However, the candidates are displayed with labels such as "A", "B", "C", etc., and the numerical values are not displayed to other users.

[0040] The meta information includes information related to the construction of the production process model (learning curve, teacher data, hyperparameters, etc. ), the equations used by the production process model, boundary conditions, approximation conditions, assumption conditions, definitions of physical property values, etc.

[0041] The usage range information includes information of other users who permit the use of the production process model as part of the connection model of the inference unit 114 described later. The production process model registered by a certain user is permitted to be selected as an element of the manufacturing line (connection model) for optimization only for other users set as available users in the usage range information.

[0042] The model registration unit 111 may receive the registration of the first production process model that simulates the process of generating a product from the first user, and may also receive the registration of the second production process model that simulates the process of generating a product from the second user. The second production process model is a model that simulates a production process different from the first production process model. For example, it is a model that simulates the subsequent process of the production process simulated by the first production process model. For example, in the manufacturing line of a certain product, the second user is a company responsible for the downstream process with respect to the first user.

[0043] The model registration unit 111 may receive an update from the user for the already registered production process model. Specifically, the model acquisition unit 112 receives the input of the updated production process model from the user, and replaces the production process model registered in the model database with the updated production process model.

[0044] In addition, the model registration unit 111 registers the configuration information of the connection model in the model database as information indicating a manufacturing line in which a plurality of production process models are connected. The connection model is a model that simulates a manufacturing line including a plurality of production processes. The registration of the configuration information of the connection model is performed, for example, by the user selecting, on the user terminal 20, a plurality of production process models constituting the manufacturing line to be optimized in the order of the processes.

[0045] The model registration unit 111 receives, from the user terminal 20, information (model name, ID, etc.) for specifying a plurality of selected production process models and information indicating the order of the processes, and registers them in the model database as the configuration information of the connection model. The production process models that can be selected by the user as elements of the connection model are production process models that are set to be selectable (that is, set as available users) among the production process models registered by other users in addition to the production process models registered by the user himself / herself.

[0046] When a production process model is updated, the model registration unit 111 may notify the user who registered the connection model in which the production process model is incorporated that the production process model has been updated. For example, the model registration unit 111 may transmit information (model name, update date and time, update content, etc.) of the updated production process model to the user terminal 20 of the user who registered the connection model in which the updated production process model is incorporated.

[0047] <Model acquisition unit 112> The model acquisition unit 112 is configured to acquire, from among the production process models registered by the model registration unit 111 (that is, registered in the model database), a model to be used for the inference of a specified manufacturing line (that is, a model included in the connection model).

[0048] Specifically, the model acquisition unit 112 acquires a pre-process model that simulates a pre-process for generating an intermediate product from raw materials and a post-process model that simulates a post-process for generating a final product from the intermediate product. The raw materials input into the pre-process model may already have gone through some production process (i.e., a product generated in another production process). The final product generated by the post-process model may be input into yet another production process (i.e., the raw material for another production process). That is, the "final product" simply means the product obtained from the post-process included in the "linked model", and does not mean the final product of the entire manufacturing line including the post-process.

[0049] The intermediate product generated by the pre-process corresponds to the raw material for the post-process. Therefore, in the inference unit 114 described later, a part of the output parameters of the pre-process model (typically, a part of the characteristics of the product) is used as a part of the input parameters of the post-process model (typically, the characteristics of the raw material).

[0050] The model acquisition unit 112 may acquire the production process model registered by the model registration unit 111 as the pre-process model or the post-process model. Thereby, optimization of the manufacturing line can be performed using the production process model prepared by the user. Note that the model acquisition unit 112 may acquire a production process model other than the production process model registered by the user (for example, a production process model registered by the provider of the service provided by the information processing system 1) as the pre-process model or the post-process model.

[0051] Also, the model acquisition unit 112 may acquire the first production process model registered by the first user as the pre-process model and acquire the second production process model registered by the second user as the post-process model. Thereby, optimization can be performed for a manufacturing line including production processes with different execution entities (i.e., production processes executed by a plurality of users respectively).

[0052] The manufacturing line handled by the information processing system 1 may include three or more production processes. For example, the subsequent process may include an intermediate process that generates a secondary intermediate product from the intermediate product and a final process that generates the final product from the secondary intermediate product. In this case, the model acquisition unit 112 may acquire a previous process model, an intermediate process model that simulates the intermediate process, and a final process model that simulates the final process. The intermediate process model and the final process model may be production process models registered by the same user, or may be production process models registered by different users. The model acquisition unit 112 may acquire a production process model other than the production process model registered by the user (the production process model registered by the service provider) as the intermediate process model or the final process model.

[0053] <Condition acquisition unit 113> The condition acquisition unit 113 is configured to acquire the process conditions in each of the previous process model and the subsequent process model, which are the conditions for the inference unit 114 to perform inference. Specifically, the condition acquisition unit 113 receives the input or selection of each element included in the process conditions of each production process model at the user terminal 20. The condition acquisition unit 113 may receive the input of the characteristics of the raw materials in addition to the process conditions for the previous process model.

[0054] Also, when the subsequent process includes the intermediate process and the final process models, the condition acquisition unit 113 acquires the process conditions in each of the previous process model, the intermediate process model, and the final process model.

[0055] Instead of the process conditions input or selected at the user terminal 20, the condition acquisition unit 113 may acquire the process conditions adjusted by the condition adjustment unit 116 described later.

[0056] <Inference unit 114> The inference unit 114 is configured to infer the values of output parameters in a connection model in which a plurality of process models are connected. Specifically, the inference unit 114 inputs process conditions into a connection model in which at least a previous process model and a subsequent process model are connected, thereby obtaining at least one of the characteristic values of the intermediate product, the characteristic values of the final product, the state values of the devices used in the previous process, and the state values of the devices used in the subsequent process as an inference value.

[0057] Also, when the subsequent process includes an intermediate process and a final process model, the inference unit 114 inputs process conditions into a connection model in which the previous process model, the intermediate process model, and the final process model are connected, thereby obtaining at least one of the characteristic values of the intermediate product, the characteristic values of the secondary intermediate product, the characteristic values of the final product, the state values of the devices used in the previous process, the state values of the devices used in the intermediate process, and the state values of the devices used in the final process as an inference value. Thereby, inference values regarding each process can also be obtained for a manufacturing line including three or more production processes.

[0058] More specifically, the inference unit 114 inputs the characteristic values of the raw material into the production process model at the head of the connection model (that is, the previous process model), and inputs the respective process conditions acquired by the condition acquisition unit 113 into each production process model (the previous process model and the subsequent process model) constituting the connection model, thereby causing each production process to output an inference value (the characteristic value of the product and / or the state value of the device).

[0059] Note that the number of elements and the types of elements of the process conditions differ for each production process. Also, the number of elements and the types of elements of the characteristic values of the product to be generated and the state values of the devices also differ for each production process.

[0060] The inference unit 114 may obtain, as inference values, the characteristic values of the final product, the state values of the apparatuses used in the previous process, and the state values of the apparatuses used in the subsequent process by inputting the process conditions into the connection model. Thereby, it is possible to estimate the quality of the product obtained from the production line simulated by the connection model, and based on the state values of the apparatuses in each process, it is possible to estimate indices for optimization such as the energy efficiency and consumption cost of the production line.

[0061] The inference unit 114 may obtain the characteristic values of the intermediate product and the state values of the apparatuses used in the previous process by inputting the characteristic values of the raw material and the process conditions into the previous process model, and obtain the characteristic values of the final product and the state values of the apparatuses used in the subsequent process by inputting the characteristic values of the intermediate product and the process conditions into the subsequent process model. Thereby, while reliably passing on the execution result (information on the intermediate product) of the previous process model to the subsequent process model, it is possible to infer the state of the apparatuses in each process.

[0062] The inference unit 114 may input only some of the plurality of elements included in the characteristic values of the intermediate product into the subsequent process model. That is, the inference unit 114 does not necessarily have to use all the elements of the characteristic values of the intermediate product as input parameters of the subsequent process model. The elements defined as input parameters in the model information of the subsequent process model are input into the subsequent process model.

[0063] Note that the inference unit 114 does not necessarily have to obtain all of the characteristic values of the intermediate product, the characteristic values of the final product, the state values of the apparatuses used in the previous process, and the state values of the apparatuses used in the subsequent process. For example, the inference unit 114 may obtain only the characteristic values of the final product, or may obtain only the state values of the apparatuses used in the previous process and the state values of the apparatuses used in the subsequent process.

[0064] The inference unit 114 records the inference value (such as the characteristic value of the final product) obtained from the connection model in the model database, for example, by associating it with the connection model for which the inference was performed. Further, the inference unit 114 causes the user terminal 20 to display the inference value. Thereby, the user can confirm each inference value on the user terminal 20.

[0065] FIG. 5 is a diagram schematically showing information input / output in a connection model in which a pre-process model and a post-process model are connected. As shown in FIG. 5, in the pre-process model PM1, a characteristic value CV1 indicating the characteristics of the raw material and a process condition PC1 in the pre-process are input as input parameters. In response to the input of these input parameters, the pre-process model PM1 outputs a characteristic value CV2 indicating the characteristics of the intermediate product and a state value SV1 indicating the state of the apparatus used in the pre-process during or after the execution of the pre-process.

[0066] In the post-process model PM2 connected to the pre-process model PM1, a characteristic value CV2 indicating the characteristics of the intermediate product and a process condition PC2 in the post-process are input as input parameters. In response to the input of these input parameters, the post-process model PM2 outputs a characteristic value CV3 indicating the characteristics of the final product and a state value SV2 indicating the state of the apparatus used in the post-process during or after the execution of the post-process.

[0067] <Target acquisition unit 115> The target acquisition unit 115 is configured to acquire a target value regarding the inference value acquired by the inference unit 114. For example, the target acquisition unit 115 accepts input, selection, etc. of the target value on the user terminal 20, associates the accepted target value with the connection model that optimizes the process conditions, and registers it in the model database.

[0068] The target value is an objective function when optimizing the process conditions input to the connection model, and is a numerical value indicating the inference value itself, or the upper or lower limit (target range) of an evaluation index derived from the inference value. Examples of evaluation indices include productivity indices such as manufacturing time, decarbonization indices such as CO2 emissions, energy-saving indices such as power consumption and fuel consumption, cost indices such as manufacturing cost and consumption efficiency of raw materials or fuels, defect rate indices such as product yield, and product quality indices such as stability of product performance.

[0069] The productivity index, decarbonization index, energy-saving index, and cost index are calculated, for example, using the state values of the devices in each production process and the first reference information. The first reference information is information including the correlation between the state values of the devices in each production process and each index. The first reference information includes, for example, calculation formulas, functions, tables, learning models of the artificial intelligence unit 120, simulators, and the like.

[0070] The defect rate index and product quality index are calculated, for example, using the characteristic values of the products in each production process and the second reference information. The second reference information is information including the correlation between the characteristic values of the products in each production process and each index. The second reference information includes, for example, calculation formulas, functions, tables, learning models of the artificial intelligence unit 120, simulators, and the like.

[0071] Each evaluation index may be calculated using both the state values of the devices in each production process and the characteristic values of the products, and the third reference information. The third reference information is information including the correlation between the state values of the devices in each production process and the characteristic values of the products, and each index. The third reference information includes, for example, calculation formulas, functions, tables, learning models of the artificial intelligence unit 120, simulators, and the like.

[0072] The user creates and inputs, for example, at the user terminal 20, an index to be used as the target for optimizing the production line, or selects an index from among the pre-prepared options. The user may set a plurality of indices for one production line. Also, the user inputs, at the user terminal 20, the target value for each index.

[0073] The target acquisition unit 115 may acquire search conditions for optimal process conditions in addition to the target value. The search conditions are input by the user on the user terminal 20. The search conditions include, for example, among the elements included in the process conditions of each process, the elements to be optimized (search for optimal values), the adjustment range of the elements to be optimized (for example, the upper and lower limits of the search), the conditions set for the fourth reference information described later (for example, the type of algorithm), the search time, and the like.

[0074] When the concatenation model for which the user optimizes the process conditions includes a production process model registered by another user, for the elements that are not non-disclosure elements among the process conditions of the production process model, the user can set search conditions in the same manner as the process conditions of the production process model registered by the user himself / herself. On the other hand, among the process conditions of the production process model registered by another user, for the non-disclosure elements, any of the following treatments is performed according to the designation of another user. (1) When the numerical value of the non-disclosure element is fixed, the numerical value of the non-disclosure element is not searched (not optimized). (2) When the numerical value of the non-disclosure element can be selected from the candidates prepared in advance (the numerical values listed in the list), the search (optimization) within the candidates is performed.

[0075] <Condition adjustment unit 116> The condition adjustment unit 116 is configured to adjust the process conditions in the concatenation model based on the inference value acquired by the inference unit 114, the target value acquired by the target acquisition unit 115, and the fourth reference information. According to such a configuration, based on the target value set by the user, the process conditions of the manufacturing line using the concatenation model can be optimized.

[0076] The fourth reference information includes the correlation between the inferred value and the target value and the process conditions. The fourth reference information is stored, for example, in the storage unit 12. The fourth reference information is an estimator constructed to be able to output the process conditions adjusted to achieve the target value with the inferred value and the target value as inputs. The fourth reference information may include, for example, calculation formulas, functions, tables, simple algorithms, etc. that indicate the correlation between the combined data of the inferred value and the target value and the process conditions. The correlation included in the fourth reference information can be constructed, for example, by statistically analyzing the data recording the process conditions used in the actual production process and the measured values such as the characteristic values of the product observed in the actual production process and the state values of the apparatus.

[0077] Also, the fourth reference information may be a search algorithm for searching for the optimum value of each element included in the process conditions. When using such a search algorithm, the condition adjustment unit 116 adjusts the current process conditions in the direction in which it is estimated that the inferred value approaches the target value along the search algorithm, and uses the adjusted process conditions (specifically, causes the condition acquisition unit 113 to acquire the adjusted process conditions) to update the inferred value in the inference unit 114. Further, the condition adjustment unit 116 repeats the adjustment of the process conditions and the update of the inferred value using the updated inferred value. The adjustment of the process conditions is repeated until the search end condition is satisfied. The search end condition is, for example, that the difference between the inferred value and the target value reaches less than the threshold value, or that the search time set as the search condition has elapsed. The parameters (branch conditions, determination conditions, etc.) constituting the search algorithm constitute the correlation of the fourth reference information.

[0078] Further, the fourth reference information may include a condition adjustment model that is pre-machine learned so as to be able to take an inference value and a target value as inputs and output process conditions for achieving the target value. In this case, the condition adjustment unit 116 inputs the inference value and the target value into the condition adjustment model included in the artificial intelligence unit 120, and causes the condition adjustment model to output process conditions. The condition adjustment model is constructed, for example, by machine learning using, as teacher data, records associating process conditions used in the production process in the past with measured values such as characteristic values of products observed in the production process and state values of devices. In the condition adjustment model, parameters calculated, tuned, etc. by learning constitute the correlation of the fourth reference information.

[0079] The condition adjustment unit 116 does not necessarily have to adjust all elements of the process conditions. For example, the condition adjustment unit 116 may fix the process conditions of some production processes and adjust only the process conditions of other production processes. Also, in each production process, some elements of the process conditions may be fixed and only other elements may be adjusted. The range of the process conditions or elements to be adjusted is set, for example, as search conditions.

[0080] The condition adjustment unit 116 records the adjusted process conditions (optimized process conditions) in the model database, for example, by associating them with the concatenated model for which optimization has been performed. Also, the condition adjustment unit 116 causes the optimized process conditions and the inference value and / or target value when the optimized process conditions are used to be displayed on the user terminal 20. Thereby, the user can confirm the optimized process conditions and the inference value and / or target value after optimization on the user terminal 20.

[0081] Further, the condition adjustment unit 116 may calculate the contribution rate of each element included in the process conditions to the inference value and / or target value and cause it to be displayed on the user terminal 20. Examples of such contribution rates include the contribution rate of the decarbonization index of the temperature sequence in the previous process to the reduction. The contribution rate is calculated or estimated, for example, based on data (correlation between each element of the process conditions and the inference value and / or target value) obtained during the search for the optimized process conditions.

[0082] <Artificial intelligence unit 120> The artificial intelligence unit 120 is configured to receive an input from each functional unit and return an instructed output. Note that the artificial intelligence used by the information processing apparatus 10 in each functional unit may be common or may be individually prepared for each functional unit.

[0083] The artificial intelligence unit 120 may include a learning model such as a language model such as a Transformer or a Recurrent Neural Network (RNN) including a generative AI.

[0084] The language model is an example of a learning model by a machine learning algorithm. Specific algorithms for machine learning include the nearest neighbor method, the naive Bayes method, decision trees, support vector machines, and deep learning (deep learning) using neural networks. The artificial intelligence unit 120 can appropriately apply the above algorithms.

[0085] The artificial intelligence unit 120 may have a trained model constructed by a learning method such as supervised learning, unsupervised learning, or self-supervised learning. In supervised learning, machine learning is performed using teacher data (learning data). The teacher data is composed of a pair of input data for learning and output data (correct data). Also, the language model may be not only trained for a specific task but also a general-purpose model that can be generally used for a wide range of tasks. The learning model included in the artificial intelligence unit 120 can perform additional learning as transfer learning or fine-tuning.

[0086] <Display unit 211> The display unit 211 of the user terminal 20 is configured to cause the output unit 25 to display the screen indicated by the screen data transmitted from the information processing apparatus 10.

[0087] <Operation acquisition unit 212> The operation acquisition unit 212 of the user terminal 20 is configured to receive operations by the user of the user terminal 20.

[0088] 3. Information Processing Method In this section, the information processing method of the information processing apparatus 10 will be described. In this information processing method, each part of the information processing apparatus 10 is executed by a computer as each step.

[0089] Specifically, this information processing method includes a model registration step, a model acquisition step, a condition acquisition step, an inference step, a target acquisition step, and a condition adjustment step. In the model registration step, registration of a model that simulates the process of generating a product is received. In the model acquisition step, a pre-process model that simulates the pre-process of generating an intermediate product from raw materials and a post-process model that simulates the post-process of generating a final product from the intermediate product are acquired. In the condition acquisition step, the process conditions in each of the pre-process model and the post-process model are acquired. In the inference step, by inputting the process conditions into at least a connected model in which the pre-process model and the post-process model are connected, at least one of the characteristic value of the intermediate product, the characteristic value of the final product, the state value of the apparatus used in the pre-process, and the state value of the apparatus used in the post-process is acquired as an inference value. In the target acquisition step, a target value regarding the inference value is acquired. In the condition adjustment step, the process conditions are adjusted based on the inference value, the target value, and the reference information.

[0090] FIG. 6 is an activity diagram showing an example of the flow of information processing (process condition adjustment processing) executed by the information processing system 1. Hereinafter, the information processing will be described along each activity of this activity diagram.

[0091] The process condition adjustment processing starts from the provision of the production process model by the user. The user provides the production process model to the information processing apparatus 10 by uploading etc. at the user terminal 20 (activity A110). The information processing apparatus 10 registers the production process model provided from the user terminal 20 (activity A120).

[0092] After registering the production process model, the user creates a connection model (activity A130) by designating at least the previous process model and the subsequent process model on the user terminal 20. The information processing apparatus 10 acquires the previous process model and the subsequent process model designated on the user terminal 20 from among the registered production process models (activity A140).

[0093] After creating the connection model, the user inputs initial process conditions and target values on the user terminal 20 (activity A150). The information processing apparatus 10 acquires the process conditions and target values input on the user terminal 20 (activity A160). Subsequently, the information processing apparatus 10 inputs the acquired process conditions into the connection model and acquires inference values (such as the characteristics of the final product) (activity A170).

[0094] After acquiring the inference values, the information processing apparatus 10 determines whether or not the end condition for process condition adjustment is satisfied (activity A180). If the end condition is not satisfied (for example, if the inference values have not reached the target values), the information processing apparatus 10 adjusts the process conditions according to a predetermined algorithm or the like (activity A190). After adjusting the process conditions, the information processing apparatus 10 re-executes the acquisition of the inference values in activity A170. On the other hand, if the end condition is satisfied, the information processing apparatus 10 outputs the final process conditions and inference values to the user terminal 20 (activity A200). As a result, the final process conditions and inference values are displayed on the user terminal 20 (activity A210).

[0095] 4. Operation Summarizing the operation of the present embodiment, it is as follows. That is, by referring to the inference values obtained from the connection model and adjusting the process conditions in the previous process and / or the subsequent process, the entire manufacturing line can be optimized.

[0096] As described above, embodiments of the present invention have been explained. However, the present invention is not limited to this, and can be appropriately changed without departing from the technical idea of the invention.

[0097] 5. Others In the above embodiment, the information processing apparatus 10 performed various storage and control operations. However, instead of the information processing apparatus 10, a plurality of external devices may be used. That is, various information and programs may be distributed and stored in a plurality of external devices using blockchain technology or the like.

[0098] The aspect of this embodiment is not limited to the information processing system 1, and may be an information processing method or a program. The information processing method includes each step executed by the information processing system 1. The program causes a computer to execute each step of the information processing system 1.

[0099] At least one of the devices included in the information processing system 1 may be installed outside the country where the functions of the information processing system 1 are exhibited.

[0100] The information processing system 1 may be composed only of the information processing apparatus 10. That is, the information processing system 1 does not necessarily have to include the user terminal 20.

[0101] The information processing system 1 does not necessarily have to include the condition adjustment unit 116. For example, the information processing system 1 may be one in which the user manually searches for the optimal process conditions for obtaining a predetermined inference value (target value).

[0102] It may also be provided in each of the aspects described below.

[0103] (1) An information processing system, comprising a processor configured to execute the following steps by reading a program. In a model acquisition step, a pre-process model simulating a pre-process for generating an intermediate product from raw materials and a post-process model simulating a post-process for generating a final product from the intermediate product are acquired. In a condition acquisition step, process conditions in each of the pre-process model and the post-process model are acquired. In an inference step, at least one of a characteristic value of the intermediate product, a characteristic value of the final product, a state value of a device used in the pre-process, and a state value of a device used in the post-process is acquired as an inference value by inputting the process conditions into a connected model in which at least the pre-process model and the post-process model are connected.

[0104] (2) In the information processing system according to (1) above, in the inference step, by inputting the process conditions into the connected model, a characteristic value of the final product, a state value of a device used in the pre-process, and a state value of a device used in the post-process are acquired as the inference value.

[0105] (3) In the information processing system according to (2) above, in the inference step, by inputting a characteristic value of the raw materials and the process conditions into the pre-process model, a characteristic value of the intermediate product and a state value of a device used in the pre-process are acquired. By inputting a characteristic value of the intermediate product and the process conditions into the post-process model, a characteristic value of the final product and a state value of a device used in the post-process are acquired.

[0106] (4) In the information processing system according to any one of (1) to (3) above, the post-process includes an intermediate process of generating a secondary intermediate product from the intermediate product and a final process of generating the final product from the secondary intermediate product. In the model acquisition step, the pre-process model, an intermediate process model simulating the intermediate process, and a final process model simulating the final process are acquired. In the condition acquisition step, the process conditions in each of the pre-process model, the intermediate process model, and the final process model are acquired. In the inference step, by inputting the process conditions into the connected model in which the pre-process model, the intermediate process model, and the final process model are connected, at least one of the characteristic value of the intermediate product, the characteristic value of the secondary intermediate product, the characteristic value of the final product, the state value of the device used in the pre-process, the state value of the device used in the intermediate process, and the state value of the device used in the final process is acquired as the inference value. Information processing system.

[0107] (5) In the information processing system according to any one of (1) to (4) above, the processor is configured to further execute the following steps. In the target acquisition step, a target value regarding the inference value is acquired. In the condition adjustment step, the process conditions are adjusted based on the inference value, the target value, and reference information. The reference information includes the correlation between the inference value and the target value and the process conditions. Information processing system.

[0108] (6) In the information processing system according to any one of (1) to (5) above, the processor is configured to further execute the following steps. In the model registration step, registration of a model simulating a process of generating a product is received. In the model acquisition step, the model is acquired as the pre-process model or the post-process model. Information processing system.

[0109] (7) In the information processing system according to (6) above, in the model registration step, registration of a first model simulating a process of generating a product from a first user is received, and registration of a second model simulating a process of generating a product from a second user is received. In the model acquisition step, the first model is acquired as the previous process model, and the second model is acquired as the subsequent process model. Information processing system.

[0110] (8) An information processing method comprising each step executed by the information processing system according to any one of (1) to (7) above. Information processing method.

[0111] (9) A program for causing a computer to execute each step of the information processing system according to any one of (1) to (7) above. Program. Of course, this is not all.

Description of Signs

[0112] 1: Information processing system 2: Communication line 10: Information processing device 11: Control unit 12: Storage unit 13: Communication unit 14: Communication bus 20: User terminal 21: Control unit 22: Storage unit 23: Communication unit 24: Input unit 25: Output unit 26: Communication bus 111: Model registration unit 112: Model acquisition unit 113: Condition acquisition unit 114: Inference unit 115: Target acquisition unit 116: Condition adjustment unit 120: Artificial intelligence unit 211: Display unit 212: Operation acquisition unit CV1: Characteristic value CV2: Characteristic value CV3: Characteristic value PC1: Process condition PC2: Process condition PM1: Previous process model PM2: Next process model SV1: State value SV2: State value

Claims

1. An information processing system, comprising a processor configured to execute the following steps by reading a program, In a model acquisition step, an upstream process model simulating an upstream process for generating an intermediate product from raw materials and a downstream process model simulating a downstream process for generating a final product from the intermediate product are acquired, In a condition acquisition step, characteristic values of the raw materials and process conditions in each of the upstream process model and the downstream process model are acquired, In an inference step, by inputting the characteristic values of the raw materials and the process conditions into a connected model in which at least the upstream process model and the downstream process model are connected, at least one of the characteristic values of the intermediate product, the characteristic values of the final product, the state values of the equipment used in the upstream process, and the state values of the equipment used in the downstream process is acquired as an inference value. An information processing system.

2. In the information processing system according to Claim 1, In the inference step, by inputting the characteristic values of the raw materials and the process conditions into the connected model, the characteristic values of the final product, the state values of the equipment used in the upstream process, and the state values of the equipment used in the downstream process are acquired as the inference values. An information processing system.

3. In the information processing system according to Claim 2, In the inference step, the characteristic values of the intermediate product and the state values of the equipment used in the upstream process are acquired by inputting the characteristic values of the raw materials and the process conditions into the upstream process model, and the characteristic values of the final product and the state values of the equipment used in the downstream process are acquired by inputting the characteristic values of the intermediate product and the process conditions into the downstream process model. An information processing system.

4. In the information processing system according to Claim 1, The downstream process includes an intermediate process for generating a secondary intermediate product from the intermediate product and a final process for generating the final product from the secondary intermediate product, In the model acquisition step, the upstream process model, an intermediate process model simulating the intermediate process, and a final process model simulating the final process are acquired, In the condition acquisition step, the process conditions in each of the upstream process model, the intermediate process model, and the final process model are acquired, In the inference step, by inputting the characteristic values of the raw material and the process conditions into the connection model in which the previous process model, the intermediate process model, and the final process model are connected, at least one of the characteristic values of the intermediate product, the characteristic values of the secondary intermediate product, the characteristic values of the final product, the state values of the devices used in the previous process, the state values of the devices used in the intermediate process, and the state values of the devices used in the final process is obtained as the inference value. An information processing system.

5. In the information processing system according to claim 1, the processor is configured to further execute the following steps, In the target acquisition step, a target value regarding the inference value is acquired, In the condition adjustment step, the process conditions are adjusted based on the inference value, the target value, and reference information, The reference information includes the correlation between the inference value and the target value, and the process conditions. An information processing system.

6. In the information processing system according to claim 1, the processor is configured to further execute the following steps, In the model registration step, registration of a model simulating the process of generating a product is received, In the model acquisition step, the model is acquired as the previous process model or the subsequent process model. An information processing system.

7. In the information processing system according to claim 6, In the model registration step, registration of a first model simulating the process of generating a product from a first user is received, and registration of a second model simulating the process of generating a product from a second user is received, In the model acquisition step, the first model is acquired as the previous process model, and the second model is acquired as the subsequent process model. An information processing system.

8. An information processing method, wherein an information processing device executes each step of the information processing system according to any one of claims 1 to 7. An information processing method.

9. A program, for causing a computer to execute each step of the information processing system according to any one of claims 1 to 7. A program.

Images