Information processing system, orthodontic appliance, information processing method and program

Abstract

We provide information processing systems and the like that can efficiently optimize deformation processing processes. [Solution] According to one aspect of the present invention, an information processing system is provided, comprising a processor, the processor being configured to perform the following steps by reading a program, the acquisition step of acquiring object information including at least a first shape of the object to be deformed before processing, the prediction step of setting deformation processing conditions for the object based on the object information and first reference information, and further predicting a second shape of the object after deformation processing based on the object information, deformation processing conditions and second reference information, the first reference information including a correlation between the object information and the deformation processing conditions, and the second reference information including a correlation between the object information and the deformation processing conditions and the second shape.

Description

Technical Field

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

Background Art

[0002] The following document discloses a method of determining the indentation amount and indentation position using a straightening value or the like in the straightening of a member by indentation.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Although the above method can efficiently perform straightening (deformation processing), there is still room for further improvement regarding the optimization of the deformation processing process.

[0005] In view of the above circumstances, the present invention aims to provide an information processing system and the like that can efficiently optimize a deformation processing process.

Means for Solving the Problems

[0006] According to one aspect of the present invention, an information processing system is provided, comprising a processor, the processor configured to perform the following steps by reading a program: in the acquisition step, object information is acquired, which includes at least a first shape of the object to be deformed before processing; in the prediction step, deformation processing conditions for the object are set based on the object information and first reference information; and further, a second shape of the object after deformation processing is predicted based on the object information, deformation processing conditions and second reference information, wherein the first reference information includes a correlation between the object information and the deformation processing conditions, and the second reference information includes a correlation between the object information and the deformation processing conditions and the second shape.

[0007] In this configuration, the second shape of the object after deformation can be predicted based on the first shape of the object before deformation. By using this prediction result, the deformation process can be efficiently optimized. [Brief explanation of the drawing]

[0008] [Figure 1] This is a diagram showing the configuration of Information Processing System 1. [Figure 2] This is a block diagram showing the hardware configuration of the information processing device 2. [Figure 3] This is a block diagram showing the hardware configuration of user terminal 3. [Figure 4] This block diagram shows the functions implemented by the information processing device 2 (processor 23) and the functions implemented by the user terminal 3 (processor 33). [Figure 5] This is a schematic diagram showing the configuration of an orthodontic device 100 used to correct the shape of an object. [Figure 6] This figure shows an example of a deformation processing table. [Figure 7] This flowchart shows an example of the optimization process for the deformation processing table performed by the information processing device 2 (processor 23). [Figure 8] This flowchart shows an example of the processing flow for deformation machining simulation. [Figure 9] This is an activity diagram showing the flow of information processing (output processing of the deformation processing table) performed by information processing system 1. [Modes for carrying out the invention]

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

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

[0011] Furthermore, in various information processing according to one embodiment, an input and an output corresponding to the input can be realized. Here, as long as an output is obtained as a result of the input, the form of the information referenced in such information processing (hereinafter referred to as reference information) is not limited. The reference information may be, for example, rule-based information such as a database, a lookup table, or a predetermined function (including a decision formula such as a regression equation constructed by a statistical method), or a trained model that has been pre-trained to learn the correlation between input and output, or a generative AI such as a large-scale language model or visual language model that can output a desired result by inputting a prompt.

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

[0013] Furthermore, a circuit in a broad sense is a circuit realized by combining at least a suitable combination of circuits, circuits, processors, and memory. The processor may be a general-purpose processor or a dedicated circuit. In other words, it includes application-specific integrated circuits (ASICs), programmable logic devices (for example, simple programmable logic devices (SPLDs), complex programmable logic devices (CPLDs), and field programmable gate arrays (FPGAs)), etc.

[0014] 1. Hardware Configuration This section describes the hardware configuration.

[0015] <Information Processing System 1> Figure 1 is a diagram showing the configuration of information processing system 1. Information processing system 1 primarily optimizes the deformation processing process.

[0016] The information processing system 1 comprises an information processing device 2 and a plurality of user terminals 3. The information processing device 2 and the user terminals 3 are configured to communicate with each other via a telecommunications line.

[0017] In an embodiment of the information processing system 1, the information processing system 1 is composed of one or more devices or components. For example, if the information processing system 1 consists solely of the information processing device 2, the information processing system 1 can be the information processing device 2. Hereinafter, these components will be described.

[0018] <Information Processing Device 2> FIG. 2 is a block diagram showing the hardware configuration of the information processing device 2. The information processing device 2 includes a communication bus 20, a communication unit 21, a storage unit 22, and a processor 23. The communication unit 21, the storage unit 22, and the processor 23 are electrically connected to each other inside the information processing device 2 via the communication bus 20.

[0019] <Communication Unit 21> The communication unit 21 preferably uses wired communication means such as USB, IEEE1394, Thunderbolt (registered trademark), wired LAN network communication, etc., but may also include wireless LAN network communication, mobile communication such as LTE / 5G, BLUETOOTH (registered trademark) communication, and the like as needed. That is, it is more preferable to implement it as a set of these plurality of communication means. That is, the information processing device 2 may communicate various kinds of information from the outside via the communication unit 21 and a network.

[0020] <Storage Unit 22> The storage unit 22 stores various types of information defined by the above 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 device 2 executed by the processor 23, or as a memory such as a Random Access Memory (RAM) that temporarily stores necessary information (arguments, arrays, etc.) related to program operations. The storage unit 22 stores various programs, variables, and the like related to the information processing device 2 that are executed by the processor 23.

[0021] <Processor 23> The processor 23 performs processing and control of the overall operation related to the information processing device 2. The processor 23 is, for example, a Central Processing Unit (CPU). The processor 23 realizes various functions related to the information processing device 2 by reading predetermined programs stored in the memory unit 22. That is, information processing by software stored in the memory unit 22 can be concretely realized by the processor 23, which is an example of hardware, and executed as each functional unit included in the processor 23. These will be described in more detail in the next section. Note that the processor 23 is not limited to being a single unit; the information processing device 2 may have multiple processors 23 for each function. Furthermore, the information processing device 2 may have a configuration that combines these.

[0022] The information processing device 2 may be on-premise or in a cloud-based configuration. In the case of a cloud-based information processing device 2, for example, the above-mentioned functions and processing may be provided in the form of SaaS (Software as a Service) or cloud computing.

[0023] <User Terminal 3> Figure 3 is a block diagram showing the hardware configuration of the user terminal 3. As shown in Figure 3, the user terminal 3 comprises a communication bus 30, a communication unit 31, a storage unit 32, a processor 33, an output unit 34, and an input unit 35. The communication unit 31, storage unit 32, processor 33, output unit 34, and input unit 35 are electrically connected within the user terminal 3 via the communication bus 30. The descriptions of the communication unit 31, storage unit 32, and processor 33 are the same as the descriptions of each part in the information processing device 2 and are therefore omitted.

[0024] <Output section 34> The output unit 34 displays a graphical user interface (GUI) screen that can be operated by the user. The output unit 34 may be included in the casing of the user terminal 3 or it may be an external component. Specifically, the output unit 34 can be implemented as a display device such as a CRT display, liquid crystal display, organic EL display, or plasma display. It is preferable that these display devices be used according to the type of user terminal 3.

[0025] <Input section 35> The input unit 35 receives operation input from the user. The operation input is transmitted to the processor 33 via the communication bus 30 as a command signal. The processor 33 can perform predetermined controls or calculations based on the transmitted command signal as needed. The input unit 35 may be included in the casing of the user terminal 3 or it may be external. For example, the input unit 35 may be implemented as a touch panel in conjunction with the output unit 34. When the input unit 35 is implemented as a touch panel, the user can input tap operations, swipe operations, etc. to the input unit 35. Instead of a touch panel, the input unit 35 can be a switch button, mouse, trackpad, QWERTY keyboard, etc.

[0026] 2. Functional Configuration This section describes the functional configuration of this embodiment. Information processing by software stored in the memory unit 22 is specifically realized by the processor 23, which is an example of hardware, and can be executed as each functional unit included in the processor 23.

[0027] Figure 4 is a block diagram showing the functions implemented by the information processing device 2 (processor 23) and the functions implemented by the user terminal 3 (processor 33).

[0028] As shown in Figure 4A, the information processing device 2 (processor 23) includes an acquisition unit 231, a deformation processing table preparation unit 232, a prediction unit 233, a deformation processing table optimization unit 234, and an artificial intelligence unit 240. As shown in Figure 4B, the user terminal 3 (processor 33) includes a display unit 331 and an operation acquisition unit 332.

[0029] <Acquisition part 231> The acquisition unit 231 is configured to acquire object information that includes at least the first shape of the object to be deformed before processing. The "object" is an article that undergoes plastic deformation due to the application of external force. This makes it possible to predict the second shape for objects that cannot be re-deformed, thereby reducing processing losses for the object.

[0030] "Deformation processing" is a process that changes the shape of an object by applying, for example, compressive or tensile force to it. Examples of deformation processing include straightening, pressing, forging, and extrusion (injection) of an object.

[0031] The object may be an intermediate product or a finished product. The material of the object is not particularly limited, but is typically metal. The shape of the object is also not particularly limited. Specific examples of objects include shafts and bearings.

[0032] "Object information" includes, for example, if the object is a shaft, shape information such as outer diameter, inner diameter, wall thickness, and tolerance (deviation from the reference value) for each part along the axial direction. Object information may also include the material of the object, processing history (e.g., processing conditions such as hardening, forging, cutting, etc., lot number indicating the processing date, etc.).

[0033] Figure 5 is a schematic diagram showing the configuration of a straightening device 100 for straightening an object. The straightening device 100 comprises a straightening machine 110 and an information processing system 1. The straightening machine 110 is configured to straighten the object based on information (optimized deformation processing table) based on the second shape of the object (shape after deformation processing) predicted by the prediction unit 233, which will be described later.

[0034] The straightening machine 110 has a mechanism that deforms a part of an object by applying a predetermined straightening force (pressing force, tensile force, etc.) of a predetermined magnitude to that part. The straightening machine 110 in Figure 5 straightens the outer shape of the object O, which is a rod-shaped shaft member, by pressing it radially. The straightening machine 110 presses a predetermined position on the object O with a specified pressing force and / or amount of pressing.

[0035] The acquisition unit 231 may acquire machine information relating to the characteristics of a machine used for deformation processing (e.g., a straightening machine 110) in deformation processing. "Machine information" is information that represents, for example, the processing conditions of the straightening machine 110 (e.g., the support form of the object O, the drive method of the processing unit 111, etc.), the correlation between the deformation processing target value (straightening target value) set for the straightening machine 110 and the drive result of the straightening machine 110 (straightening result). Examples of this correlation include the relationship between the set pressing force and the amount of pressing into the object by said pressing force (amount of straightening of the object), and the relationship between the set pressing amount and the pressing force applied to the object according to said pressing amount (current consumption of the motor that drives the processing unit 111, etc.). Furthermore, the machine information may include a program, algorithm, etc. that converts the straightening target value (input value such as pressing amount) into parameters such as the current supplied to the motor, etc. In addition, the machine information may be information that can simulate the behavior of the machine, created based on the specifications of the machine.

[0036] The acquisition unit 231 acquires object information and processing machine information by receiving input of object information and processing machine information from, for example, the user terminal 3. Object information is obtained, for example, by measurement using a measuring device. Processing machine information is obtained, for example, from a processing machine that performs straightening on the object (for example, a straightening machine 110). Alternatively, the acquisition unit 231 may directly acquire processing machine information from the straightening machine 110, etc., via the communication unit 21.

[0037] Furthermore, the acquisition unit 231 may accept input or selection of initial values ​​(deformation processing tables to be optimized) of candidate tables prepared by the deformation processing table preparation unit 232, which will be described later, from the user terminal 3.

[0038] <Deformation processing table preparation section 232> The deformation processing table preparation unit 232 is configured to prepare multiple candidate tables that will be candidates for the deformation processing table to be optimized by the deformation processing table optimization unit 234, which will be described later.

[0039] The deformation processing table defines the deformation force corresponding to the combination of deformation processing position and deformation processing amount in the object information. Figure 6 shows an example of a deformation processing table. The deformation processing table in Figure 6 is a table that describes the deformation force (a numerical value representing the magnitude of the straightening force or compressive force) linked to the combination of deformation processing position (axial straightening position [SP1~SP6]) and deformation processing amount (range of straightening amount [PA1~PA4]) in the object O, which is a shaft member. Note that the deformation processing position may include the "entire object".

[0040] Here, the "deformation processing position" may include not only the position where the processing unit 111 performs the pressing (coordinates of the point of application) but also the position of the support seat 112 that supports the object (coordinates of the fulcrum). Furthermore, the deformation processing position may include information combining multiple processing positions and their priority order. In addition, the "deformation processing amount" is the difference between the current shape of the object and the target shape, or the target deformation amount relative to the current shape of the object.

[0041] The deformation position and amount of deformation of the object are determined by the measurement results of the object's shape (first shape before processing). For example, if the measurement results of the object's shape indicate that it is necessary to correct the object at a straightening position SP2 with a straightening amount PA2 (indentation amount) (indentation in the radial direction), then a straightening force corresponding to "25" is input to the straightening machine 110 by referring to the deformation processing table in Figure 6.

[0042] A deformation processing table is prepared for each type of object (shape, material, etc.). The deformation processing tables are registered, for example, in a database for deformation processing tables stored in the storage unit 22.

[0043] The candidate table is the information that the deformation processing table optimization unit 234, described later, determines whether or not to output as a deformation processing table. In other words, from among the multiple candidate tables prepared by the deformation processing table preparation unit 232, the deformation processing table optimization unit 234 selects one candidate table as a deformation processing table and registers it in a database, for example.

[0044] The deformation processing table preparation unit 232 generates multiple candidate tables to be used as search targets for the search algorithm used by the deformation processing table optimization unit 234, which will be described later, to search for deformation processing tables. Multiple candidate tables are generated, for example, by using an existing deformation processing table (deformation processing table of a similar object or similar processing machine) as the initial value and randomly changing the individual table elements from the initial value. Examples of search algorithms that can be used include linear search algorithms, binary search algorithms, depth-first search algorithms, breadth-first search algorithms, hash search algorithms, heuristic search algorithms, binary tree search, etc.

[0045] The deformation processing table preparation unit 232 prepares several new candidate tables for the prediction unit 233 to refer to if, in the deformation processing table optimization unit 234, there is no candidate table among the multiple candidate tables for which the number of iterations of second shape prediction by the prediction unit 233 (described later) is less than or equal to a predetermined value. This reduces the number of second shape predictions for each candidate table by the prediction unit 233, thereby reducing the computational load on the information processing system 1. Note that "the number of prediction iterations is less than or equal to a predetermined value" is the condition for ending the search for deformation processing tables. The "predetermined value" here is set appropriately depending on the characteristics of the object, the characteristics of the processing machine, etc.

[0046] The deformation processing table preparation unit 232, for example, generates multiple candidate tables for initial search and provides them to the prediction unit 233 for reference. If no table exists where the number of prediction iterations until the conditions are met is less than or equal to a predetermined value (i.e., the deformation processing table optimization unit 234 is unable to find a deformation processing table that satisfies the conditions), it generates multiple new candidate tables according to the search algorithm and provides them to the prediction unit 233 for reference. Alternatively, the deformation processing table preparation unit 232 may generate a population of candidate tables to be searched, extract a group of candidate tables from this population to be provided to the prediction unit 233 for reference, and if no table exists where the number of prediction iterations is less than or equal to a predetermined value, it may extract another group of candidate tables from this population and provide them to the prediction unit 233 for reference.

[0047] <Prediction section 233> The prediction unit 233 is configured to predict the amount of deformation caused by deformation processing of the object. Specifically, first, the prediction unit 233 sets the deformation processing conditions for the object based on the object information acquired by the acquisition unit 231 and the first reference information.

[0048] "Deformation processing conditions" are parameters (such as the magnitude of the force, the direction of the force, the duration for which the force is applied, the amount of deformation, and the position of deformation) that are input (set) into the processing machine used for deformation processing. Typically, these are multiple parameters whose relationships are defined by a deformation processing table (for example, a combination of deformation processing position and indentation force).

[0049] The first reference information is information that includes the correlation between object information and deformation processing conditions, and is stored, for example, in the memory unit 22. The first reference information is an estimator constructed to take object information as input and output deformation processing conditions. The first reference information may include, for example, calculation formulas, functions, tables, simple algorithms, etc. that show the correlation between object information and deformation processing conditions. The correlation included in the first reference information can be constructed, for example, by statistically analyzing measured data that records object information (shape, etc.) of an actual object and the deformation processing conditions used in the deformation processing of that object.

[0050] In detail, the first reference information includes a deformation machining table and auxiliary reference information for referencing the deformation machining table. This makes it possible to improve machining accuracy and efficiency in conventional machining methods using a deformation machining table.

[0051] The auxiliary reference information included in the first reference information includes the correlation between object information (e.g., the outline of the object) and the deformation processing location and deformation amount on the object. The auxiliary reference information is an estimator constructed to take object information as input and output the deformation processing location and deformation amount. The auxiliary reference information may also include, for example, calculation formulas, functions, tables, simple algorithms, etc., that show the correlation between object information and the deformation processing location and deformation amount. Furthermore, the auxiliary reference information may also include processing machine information (e.g., the control program of the processing machine, etc.) acquired by the acquisition unit 231.

[0052] The auxiliary reference information may include a machine learning model that takes object information as input and outputs deformation processing position and deformation processing amount. The machining condition determination model is included in the artificial intelligence unit 240. The machining condition determination model is trained using training object information (measured data) and combinations of deformation processing position and deformation processing amount corresponding to the object information as training data. The parameters of the machining condition determination model calculated and tuned through such training constitute the correlation of the auxiliary reference information.

[0053] Specifically, the prediction unit 233 first determines the deformation position and deformation amount on the object based on object information (shape of the object before deformation) and auxiliary reference information. Next, the prediction unit 233 determines the deformation force by applying the determined deformation position and deformation amount to the deformation table. As a result, the deformation position, deformation amount, and deformation force are set as deformation conditions for predicting the second shape of the object (shape after deformation).

[0054] The prediction unit 233 refers to one of several candidate tables prepared by the deformation processing table preparation unit 232 as the deformation processing table. In other words, the prediction unit 233 sets one deformation processing condition for each of the multiple candidate tables. For example, for one object, the prediction unit 233 sets a first deformation processing condition corresponding to the first candidate table, a second deformation processing condition corresponding to the second candidate table, and so on.

[0055] After setting the deformation processing conditions, the prediction unit 233 predicts the second shape of the object after deformation processing based on the object information, the deformation processing conditions, and the second reference information. The "second shape" may be an absolute shape indicating the dimensions of the object, or it may be a relative shape indicating the deviation (runout) from the target shape of the object or the amount of deformation from the first shape.

[0056] The second reference information includes information that shows the correlation between object information and deformation processing conditions and the second shape, and is stored, for example, in the memory unit 22. The second reference information is an estimator constructed to take object information and deformation processing conditions as input and output the second shape. The second reference information may include, for example, calculation formulas, functions, tables, simple algorithms, etc. that show the correlation between object information and deformation processing conditions and the second shape. The correlation included in the second reference information can be constructed, for example, by statistically analyzing measured data that records the object information and deformation processing conditions of an actual object and the second shape (processing result) of that object.

[0057] The second reference information may include a shape prediction model that has been trained to output a second shape by taking object information and deformation processing conditions as input. The shape prediction model is included in the artificial intelligence unit 240. The shape prediction model is trained using combinations of object information and deformation processing conditions (measured data) for training and the shape of the object after deformation processing corresponding to the object information and deformation processing conditions (measured data) as training data. The parameters of the shape prediction model calculated and tuned through such training constitute the correlation of the second reference information.

[0058] The measured data used as explanatory variables (input information) in the machine learning of the shape prediction model includes object information such as the total number of straightening operations performed on the object to date, the number of straightening operations at each deformation processing location, the current runout, the initial runout before straightening, and the deformation amount obtained by subtracting the initial runout from the current runout. The measured data used as explanatory variables also includes deformation processing conditions such as the indentation force and the indentation position (absolute position or relative position from a specific position). The measured data used as the objective variable (output information) includes, for example, the change in runout due to straightening.

[0059] The prediction unit 233 references each of the multiple deformation processing conditions set based on each of the multiple candidate tables. In other words, the prediction unit 233 uses the deformation processing conditions corresponding to each of the multiple candidate tables to determine one second shape (predicted shape) corresponding to each of the multiple candidate tables. For example, for a single object, the prediction unit 233 generates a first predicted shape corresponding to the first candidate table, a second predicted shape corresponding to the second candidate table, and so on.

[0060] After predicting the second shape, the prediction unit 233 repeatedly resets the deformation processing conditions based on the object to be modified information including the second shape and the first reference information, and predicts the second shape based on the object to be modified information, the reset deformation processing conditions, and the second reference information, until the predicted second shape satisfies predetermined conditions.

[0061] "Prescribed conditions" include, for example, that the shape of the object does not exceed the set tolerance, and that the shape of the object is within the range of the target dimensions for deformation processing. Furthermore, the modified object information is, for example, information obtained by replacing the first shape included in the object information with a predicted second shape.

[0062] Specifically, if the second shape of the object obtained in the first prediction satisfies predetermined conditions (for example, if the second shape is within tolerance), the prediction unit 233 terminates the prediction of the second shape (virtual deformation processing of the object), records the number of predictions for the second shape as 1, and links it to the candidate table referenced during the prediction (when setting the deformation processing conditions).

[0063] On the other hand, if the second shape of the object obtained in the first prediction does not satisfy the predetermined conditions (for example, if the second shape exceeds the tolerance), the prediction unit 233 resets the deformation processing conditions by applying the corrected object information, in which the first shape included in the object information has been replaced with the second shape, to the first reference information (candidate table and auxiliary reference information). Subsequently, the prediction unit 233 re-predicts the second shape using the reset deformation processing conditions. In other words, the prediction unit 233 re-acquires the second shape by performing virtual deformation processing again on the second shape obtained by virtual deformation processing. If the second shape re-predicted in this way satisfies the predetermined conditions, the prediction unit 233 records the number of predictions for the second shape as 2, linked to the candidate table referenced during the prediction.

[0064] If the re-predicted second shape does not meet the predetermined conditions even when using the deformation processing conditions reset based on the information of the object to be modified, the prediction unit 233 repeatedly resets the deformation processing conditions based on the latest second shape and re-predicts the second shape (virtual deformation processing). If a second shape that meets the predetermined conditions is obtained before reaching the predetermined upper limit of repetitions, the prediction unit 233 records the number of prediction repetitions to date as the prediction count and links it to the candidate table referenced during the prediction. On the other hand, if a second shape that meets the predetermined conditions cannot be obtained even after reaching the predetermined upper limit of repetitions, the prediction unit 233 records information indicating that the candidate table referenced during the prediction is not a target for search (it is not a deformation processing table that allows for appropriate deformation processing).

[0065] The prediction unit 233 repeatedly sets deformation processing conditions and predicts the second shape for each of the multiple candidate tables. In other words, the prediction unit 233 determines the number of predictions (virtual number of corrections) for each of the multiple candidate tables. Note that the setting of deformation processing conditions and the prediction of the second shape for each candidate table may be performed in parallel (i.e., processing for multiple candidate tables may be performed simultaneously) or in series (i.e., processing for one candidate table may be completed before processing for the next candidate table is performed).

[0066] Furthermore, the prediction unit 233 may combine multiple object information for each of the multiple candidate tables and measure the number of predictions for each combination of one candidate table and one object information (repeating the setting of deformation processing conditions and prediction of the second shape). In other words, the prediction unit 233 may obtain the number of predictions for each combination of the nth candidate table and the mth object information (the first shape of the mth object) (n>2, m>2). The multiple object information used by the prediction unit 233 here is, for example, the object information for each of the multiple objects that can be deformed by a single processing machine (workpieces included in the group of workpieces to be processed).

[0067] Furthermore, the prediction unit 233 may predict the second shape using the processing score of the object. In other words, the prediction unit 233 may predict the second shape of the object after deformation processing based on the object information, deformation processing conditions, processing score, and second reference information. In this case, the second reference information includes the correlation between the object information, deformation processing conditions, processing score, and the second shape.

[0068] The "processing score" is a numerical value that indicates the degree to which the mechanical properties of an object change due to deformation processing. The processing score is higher for objects whose physical properties are more easily changed. "Physical properties" are parameters that indicate the mechanical characteristics of an object that change due to deformation processing, and are observed during or after deformation processing. For example, if the physical property is the amount of plastic deformation, an object with a higher processing score can be judged as being more easily plastically deformed (or was easily plastically deformed before deformation processing).

[0069] The prediction unit 233 calculates a processing score based, for example, on the deformation processing conditions set by the prediction unit 233, the physical properties of the object during or after deformation processing, and the third reference information. The "physical properties of the object during or after deformation processing" are predicted by the prediction unit 233 using, for example, physical property prediction information included in the first reference information. The physical property prediction information is information that includes the correlation between object information and the physical properties of the object during or after deformation processing, and is a simulator constructed based on processing machine information, measured data, etc.

[0070] The third reference information includes information that contains the correlation between deformation processing conditions, material properties, and processing scores, and is stored, for example, in the memory unit 22. The third reference information is an estimator constructed to output a processing score, taking deformation processing conditions and material properties as input. The third reference information may include, for example, calculation formulas, functions, tables, simple algorithms, etc., that show the correlation between combination data of deformation processing conditions and material properties and the processing score. The correlations included in the third reference information can be constructed, for example, by statistically analyzing measured data that records the deformation processing conditions used in the actual deformation processing and the material properties observed in the actual deformation processing.

[0071] The third reference information may include a score calculation model that has been trained to output a processing score using deformation processing conditions and material properties as input. The score calculation model is included in the artificial intelligence unit 240. The score calculation model is trained using combinations of deformation processing conditions and material properties for training (measured data) and processing scores corresponding to those combinations as training data. The parameters of the score calculation model calculated and tuned through such training constitute the correlation of the third reference information.

[0072] <Deformation processing table optimization unit 234> The deformation processing table optimization unit 234 is configured to optimize the deformation processing table based on the number of times the prediction unit 233 predicts the second shape until the second shape satisfies predetermined conditions (prediction count). This makes it possible to optimize the deformation processing table in accordance with the actual deformation processing in objects and / or deformation processing where there is an upper limit on the number of processing cycles.

[0073] The deformation processing table optimization unit 234 optimizes the deformation processing table using, for example, a candidate table with a small number of prediction iterations. For example, the deformation processing table optimization unit 234 outputs the optimized deformation processing table from among multiple candidate tables, the one in which the number of prediction iterations for the second shape is less than or equal to a predetermined value or the minimum number. This makes it possible to search for deformation processing tables using a known search algorithm, thereby reducing the computational load on the information processing system 1.

[0074] If the number of iterations of predictions for multiple object information (first shapes of multiple objects) is recorded for each candidate table, the deformation processing table optimization unit 234 will, for example, select the one with the smallest average number of iterations of predictions for multiple object information as the optimized deformation processing table.

[0075] The deformation processing table output by the deformation processing table optimization unit 234 is referenced in the processing machine (e.g., straightening machine 110) when determining the deformation processing conditions (e.g., pressing force) of the object. Alternatively, the deformation processing table output by the deformation processing table optimization unit 234 may be used in the processing machine after adjustments have been made based on the actual processing results.

[0076] <Artificial Intelligence Department 240> The artificial intelligence unit 240 is configured to receive input from each functional unit and return the instructed output. The artificial intelligence used by the information processing device 2 in each functional unit may be common to all units, or it may be prepared individually for each functional unit.

[0077] Specific algorithms used in machine learning for artificial intelligence include nearest neighbors, naive Bayes, decision trees, support vector machines, deep learning using neural networks, and regression models.

[0078] The artificial intelligence unit 240 has a trained model constructed using a learning method such as supervised learning, unsupervised learning, or self-supervised learning. In supervised learning, machine learning is performed using training data. Training data consists of pairs of input data and output data (correct answer data) for training. The trained model included in the artificial intelligence unit 240 can undergo additional training as transfer learning or fine-tuning using new data acquired from the user terminal 3, etc.

[0079] <Display section 331> The display unit 331 of the user terminal 3 is configured to display the image indicated by the data transmitted from the information processing device 2 on the output unit 34.

[0080] <Operation acquisition unit 332> The operation acquisition unit 332 of the user terminal 3 is configured to accept operations from the user of the user terminal 3 via the input unit 35.

[0081] 3. Information Processing Methods This section describes the information processing method of the information processing device 2. In this information processing method, the functions of each part of the information processing device 2 are executed as separate steps.

[0082] This information processing method comprises an acquisition step, a deformation processing table preparation step, a prediction step, and a deformation processing table optimization step. In the acquisition step, object information is acquired, which includes at least the first shape of the object to be deformed before processing. In the deformation processing table preparation step, multiple candidate tables that will serve as candidates for the deformation processing table are prepared. In the prediction step, deformation processing conditions for the object are set based on the object information and first reference information including the deformation processing table, and further, the second shape of the object after deformation processing is predicted based on the object information, deformation processing conditions, and second reference information. In the deformation processing table optimization step, the deformation processing table is optimized based on the number of iterations of predicting the second shape until the second shape satisfies predetermined conditions.

[0083] Figure 7 is a flowchart showing an example of the process flow for optimizing the deformation processing table performed by the information processing device 2 (processor 23). In this process, first, the information processing device 2 prepares multiple candidate tables (step S110). Next, the information processing device 2 sets one of the multiple objects to which the deformation processing table is applied as the processing target (step S120). Subsequently, the information processing device 2 performs a deformation processing simulation to predict the second shape of the processing target object using the candidate tables (step S130).

[0084] Figure 8 is a flowchart showing an example of the processing flow for deformation machining simulation. Deformation machining simulation is performed for each of the prepared candidate tables. In deformation machining simulation, first, the information processing device 2 sets one candidate table to be simulated from among the prepared candidate tables (step S131). Next, the information processing device 2 acquires the object information of the object to be processed, the candidate table, the machining score, etc. (step S132).

[0085] Next, the information processing device 2 sets deformation processing conditions based on the object information, candidate table, etc. (step S133). After setting the deformation processing conditions, the information processing device 2 predicts the second shape of the object after deformation processing based on the object information, deformation processing conditions, processing score, etc. (step S134). In other words, the information processing device 2 simulates the processing of the object on a digital twin. After predicting the second shape, the information processing device 2 determines whether the second shape satisfies the prediction termination conditions. Specifically, the information processing device 2 determines whether the second shape is within tolerance (i.e., whether it satisfies predetermined conditions) and whether the number of predictions for the second shape is greater than or equal to the upper limit (step S135).

[0086] If the second shape is within tolerance or the number of predictions for the second shape exceeds the upper limit (S135: YES), the information processing device 2 terminates the deformation machining simulation for one candidate table and then determines whether predictions for the second shape (calculation of the number of predictions) have been performed for all candidate tables (step S136). If predictions have been performed for all candidate tables (S136: YES), the information processing device 2 terminates the deformation machining simulation. On the other hand, if there are candidate tables for which predictions have not been performed (S136: NO), the information processing device 2 repeats the process from setting the unpredicted candidate tables as simulation targets (S131) ​​to determining the prediction termination conditions (S135) for each candidate table.

[0087] On the other hand, in the prediction termination condition determination (S135), if the second shape exceeds the tolerance and the number of predictions for the second shape is less than the upper limit (S135: NO), the information processing device 2 makes a new prediction for the second shape after deformation processing based on the current second shape. In other words, the information processing device 2 repeats the setting of deformation processing conditions (S133) and the prediction of the second shape (S134) until the prediction termination condition is met.

[0088] As shown in Figure 7, after the deformation processing simulation is performed (i.e., after calculating the number of predictions for the second shape for each of the multiple candidate tables), the information processing device 2 terminates the deformation processing simulation for one object and determines whether or not predictions (calculation of the number of predictions) for the second shape for each of the candidate tables have been performed for all objects (step S140). If predictions have been performed for all objects (S140: YES), the information processing device 2 calculates the average number of predictions for each candidate table (the sum of the number of predictions for each of the multiple objects divided by the number of objects) (step S150). On the other hand, if there are objects for which predictions have not been performed (S140: NO), the information processing device 2 repeats the process of setting the unpredicted objects as processing targets (S120) and performing the deformation processing simulation (S130) for each object.

[0089] After calculating the average number of predictions, the information processing device 2 determines whether the average number of predictions for each candidate table satisfies the search termination condition (step S160). Specifically, the information processing device 2 determines whether there is a candidate table among the multiple candidate tables whose average number of predictions is less than or equal to a predetermined value. If the search termination condition is met (S160: YES), the information processing device 2 outputs the candidate table with the smallest average number of predictions as the deformation processing table (step S170). On the other hand, if the search termination condition is not met (S160: NO), the information processing device 2 repeats the process starting from preparing a new candidate table (a candidate table for which the number of predictions has not been calculated) (S110). In this way, a deformation processing table optimized for multiple objects is searched from multiple candidate tables.

[0090] Figure 9 is an activity diagram showing the flow of information processing (output processing of the deformation processing table) performed by the information processing system 1. Below, the information processing will be explained according to each activity in this activity diagram.

[0091] The output process for the deformation processing table begins when the user inputs necessary information, such as object information, at the user terminal 3 (Activity A110). The information processing device 2 (processor 23) acquires the object information and other data entered at the user terminal 3 (Activity A120). Subsequently, the information processing device 2 optimizes the deformation processing table based on the acquired object information and other data, according to the deformation processing table optimization process described above (Activity A130). Furthermore, the information processing device 2 outputs the optimized deformation processing table to the user terminal 3 (Activity A140). As a result, the deformation processing table is displayed or saved at the user terminal 3 (Activity A150).

[0092] 4. Effect The operation of this embodiment can be summarized as follows: Based on the first shape of the object before deformation, the second shape of the object after deformation can be predicted. By using this prediction result, the deformation process can be efficiently optimized.

[0093] Although embodiments of the present invention have been described above, the present invention is not limited thereto and can be modified as appropriate without departing from the technical spirit of the invention.

[0094] 5. Others In the above embodiment, the information processing device 2 performed various storage and control functions, but instead of the information processing device 2, multiple external devices may be used. That is, various information and programs may be stored in a distributed manner across multiple external devices using blockchain technology or the like.

[0095] The embodiments of this model are not limited to the information processing system 1, but may also be an information processing method or a program. The information processing method comprises each step of the information processing system 1. The program causes a computer to execute each step of the information processing system 1.

[0096] At least one of the devices included in the information processing system 1 may be located outside the country in which the functions of the information processing system 1 are performed.

[0097] The information processing system 1 may consist only of the information processing device 2. In other words, the information processing system 1 does not necessarily have to include a user terminal 3.

[0098] The information processing system 1 may be integrated with the orthodontic machine 110. For example, the information processing system 1 may be housed in the casing of the orthodontic machine 110.

[0099] The information processing system 1 does not necessarily have to include a deformation processing table preparation unit 232 and a deformation processing table optimization unit 234. In other words, the information processing system 1 does not necessarily have to optimize the deformation processing process using a deformation processing table. For example, the information processing system 1 may be configured to output a predicted second shape, and the user may refer to this to adjust the deformation processing conditions of the object.

[0100] The product may be provided in any of the following embodiments.

[0101] (1) An information processing system comprising a processor, wherein the processor is configured to perform the following steps by reading a program, the acquisition step of acquiring object information which includes at least a first shape of an object to be deformed before processing; the prediction step of setting deformation processing conditions for the object based on the object information and first reference information, and further predicting a second shape of the object after deformation based on the object information, the deformation processing conditions and second reference information, wherein the first reference information includes a correlation between the object information and the deformation processing conditions, and the second reference information includes a correlation between the object information and the deformation processing conditions and the second shape.

[0102] (2) The information processing system described in (1) above, wherein the first reference information includes a deformation processing table that defines a deformation processing force corresponding to a combination of deformation processing position and deformation processing amount in the object information.

[0103] (3) An information processing system as described in (2) above, wherein the processor is configured to further perform a deformation processing table optimization step, wherein in the prediction step, after predicting the second shape, the deformation processing conditions are repeatedly reset based on the object to be modified information including the second shape and the first reference information, and the second shape is predicted based on the object to be modified information, the reset deformation processing conditions, and the second reference information until the second shape satisfies predetermined conditions, and in the deformation processing table optimization step, the deformation processing table is optimized based on the number of times the prediction of the second shape is repeated until the second shape satisfies predetermined conditions.

[0104] (4) An information processing system as described in (3) above, wherein the processor is configured to further perform the following steps: in the deformation processing table preparation step, a plurality of candidate tables to be candidates for the deformation processing table are prepared; in the prediction step, each of the plurality of candidate tables is referenced as the deformation processing table; and in the deformation processing table optimization step, the system outputs the optimized deformation processing table from among the plurality of candidate tables in which the number of iterations of the prediction of the second shape is less than or equal to a predetermined value or the minimum number of iterations.

[0105] (5) An information processing system as described in (4) above, wherein in the deformation processing table preparation step, if in the deformation processing table optimization step there is no candidate table among the plurality of candidates in which the number of iterations of predicting the second shape is less than or equal to the predetermined value, an information processing system prepares a new plurality of candidate tables to be referenced in the prediction step.

[0106] (6) An information processing system according to any one of (1) to (5) above, wherein the object is an article that undergoes plastic deformation by the deformation process.

[0107] (7) An orthodontic device comprising an information processing system described in any one of (1) to (6) above, and an orthodontic machine configured to correct the object based on information based on the second shape predicted in the prediction step.

[0108] (8) An information processing method comprising each step performed by the information processing system described in any one of (1) to (6) above.

[0109] (9) A program that causes a computer to perform each step of the information processing system described in any one of (1) to (6) above. Of course, this is not always the case.

[0110] Finally, while various embodiments relating to this disclosure have been described, these are presented as examples only 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 and spirit of the invention, as well as in the claims and their equivalents. [Explanation of Symbols]

[0111] 1: Information Processing System 2: Information Processing Device 20: Communications bus 21: Communications Department 22: Storage section 23: Processor 231: Acquisition Department 232: Preparation section for deformation processing table 233: Prediction Department 234: Deformation Processing Table Optimization Unit 240: Artificial Intelligence Department 3: User terminal 30: Communications bus 31: Communications Department 32: Storage section 33: Processor 331: Display section 332: Operation acquisition section 34: Output section 35: Input section 100: Orthodontic device 110: Straightening machine 111: Processing department 112: catch seat

Claims

1. An information processing system, Equipped with a processor, The aforementioned processor is configured to perform the following steps by reading a program: In the acquisition step, object information is acquired that includes at least the first shape of the object to be deformed before processing. An information processing system that, in the prediction step, sets deformation processing conditions for the object based on the object information and first reference information, and further predicts the second shape of the object after deformation processing based on the object information, the deformation processing conditions and second reference information, wherein the first reference information includes the correlation between the object information and the deformation processing conditions, and the second reference information includes the correlation between the object information and the deformation processing conditions and the second shape.

2. In the information processing system described in claim 1, The first reference information includes a deformation processing table that defines the deformation force corresponding to the combination of deformation processing position and deformation processing amount in the object information, and is part of an information processing system.

3. In the information processing system described in claim 2, The processor is configured to further perform a deformation machining table optimization step, In the prediction step, after predicting the second shape, the deformation processing conditions based on the object to be modified information including the second shape and the first reference information, and the prediction of the second shape based on the object to be modified information, the reset deformation processing conditions, and the second reference information are repeated until the second shape satisfies predetermined conditions. An information processing system that optimizes the deformation processing table in the deformation processing table optimization step based on the number of times the prediction of the second shape is repeated until the second shape satisfies the predetermined conditions.

4. In the information processing system described in claim 3, The aforementioned processor is configured to perform the following steps: In the step of preparing the deformation processing table, several candidate tables that can be used as candidates for the deformation processing table are prepared, In the prediction step, the deformation processing table is determined by referring to each of the multiple candidate tables, In the deformation processing table optimization step, the information processing system outputs, among the plurality of candidate tables, the one in which the number of iterations of the prediction of the second shape is less than or equal to a predetermined value or the minimum number of iterations, as the optimized deformation processing table.

5. In the information processing system described in claim 4, An information processing system that, in the deformation processing table preparation step, if in the deformation processing table optimization step there is no candidate table among the plurality of candidate tables in which the number of iterations of the prediction of the second shape is less than or equal to the predetermined value, prepares a new plurality of candidate tables to be referenced in the prediction step.

6. In the information processing system described in claim 1, The object is an article that undergoes plastic deformation by the deformation process, and is an information processing system.

7. It is an orthodontic appliance, The information processing system described in claim 1, A straightening machine configured to straighten the object based on information derived from the second shape predicted in the prediction step, An orthodontic appliance equipped with the following features.

8. Information processing method, An information processing method comprising each step performed by the information processing system according to any one of claims 1 to 6.

9. It is a program, A program for causing a computer to perform each step of the information processing system described in any one of claims 1 to 6.

Images