Method for generating universal learned model

Abstract

To provide a system and a method for generating a universal learned model capable of appropriately controlling a group of operating devices having the same configuration.SOLUTION: A method for generating a universal learned model includes: an initial learning step S10 of subjecting a predetermined machine learning model to learning based on predetermined initial data to generate an initial learned model; an installation step S20 of incorporating the initial learned model that controls a predetermined operating device into a plurality of operating devices; an additional learning step S30 of individually performing additional learning based on respective operation data obtained by operating the respective operating devices; an integration processing step S40 of performing integration processing on an obtained plurality of individual learned models and transmitting them to an integration processing server; and an integration step S50 of obtaining the universal learned model.SELECTED DRAWING: Figure 4

Description

[Technical field]

[0001] The present invention relates to control of an operating device using machine learning technology, and more particularly to control of an operating device using a machine learning device having a tree structure. [Background technology]

[0002] In recent years, the field of machine learning has attracted a lot of attention due to the existence of large amounts of data, dramatic improvements in computer computing capabilities, advances in algorithms, etc. In this context, a new machine learning framework with a tree structure has attracted attention (Patent Document 1).

[0003] FIG. 18 is an explanatory diagram showing the basic structure of a learning tree related to a new machine learning framework. FIG. 18(a) shows the structure of a learning tree in the learning method, and FIG. 18(b) shows an image of a state space corresponding to the structure. As is clear from the figure, the learning tree structure is configured by arranging each node corresponding to each hierarchically divided state space in a tree shape or a lattice shape from the top node (start node or root node) to the bottom node (terminal node or leaf node). Note that the figure shows an example in which N, d, and n are 2 in an N-layer, d-dimensional, n-partition learning tree, and the numbers 1 to 4 assigned to the four terminal nodes in the first layer of the learning tree shown in FIG. 18(a) correspond to the four state spaces shown in FIG. 18(b), respectively.

[0004] When performing a learning process using the learning tree, input data is sequentially associated with each divided state space, and the data is accumulated in each state space. At this time, when new data is input to a state space where no data existed until then, new nodes are generated sequentially. On the other hand, the predicted output is calculated by calculating a transition vector from each data contained in the state space corresponding to the node corresponding to the new input data, and taking the arithmetic mean of the transition vectors. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] JP 2016-173686 A Summary of the Invention [Problem to be solved by the invention]

[0006] In recent years, there have been attempts to apply machine learning techniques to various operating devices, such as robot arms in factories. For example, it is common to incorporate a trained model that has undergone pre-training into a group of operating devices having the same configuration.

[0007] However, even if operating devices have the same configuration, each operating device has variations in mechanical or electrical characteristics due to individual differences, changes over time, etc., and as a result, there is a risk that the pre-trained model will not be able to properly control all operating devices.

[0008] The present invention has been made against the above-mentioned technical background, and its purpose is to provide a system, method, etc. for generating a general-purpose trained model that can accommodate the individual characteristics of an operating device.

[0009] Further objects and advantages of the present invention will become readily apparent to those skilled in the art by referring to the following description of the specification. [Means for solving the problem]

[0010] The above-mentioned technical problems can be solved by a method and a system having the following configuration.

[0011] The method for generating a general-purpose trained model according to the present disclosure includes an initial learning step of generating an initial trained model by training a specified machine learning model based on specified initial data, and an integration step of incorporating the initial trained model that controls a specified operating device into a plurality of the operating devices, and integrating a plurality of individual trained models obtained by performing additional learning on the basis of individual operation data obtained by operating each of the operating devices to obtain a general-purpose trained model.

[0012] According to such a configuration, after common learning is performed as initial learning, additional learning is performed according to each individual operating device, and the results are integrated, so that a general-purpose trained model that can also handle the individual characteristics of a specific operating device can be generated. In addition, since a certain level of accuracy can be ensured due to the initial learning, a general-purpose trained model can be generated while continuing to use the operating device.

[0013] The generation of the initial trained model may be performed in a predetermined initial training server connected to a network, and the incorporation of the initial trained model into the operating device may be performed by downloading it from the initial training server to each of the operating devices via the network.

[0014] In addition, the initial trained model may be incorporated into the operating device by mounting the initial trained model on an integrated circuit and incorporating the integrated circuit into each of the operating devices.

[0015] The method for generating a generic trained model may further include a re-incorporation step of incorporating the generic trained model into each of the operating devices.

[0016] The machine learning model may be a learning model having a tree structure constructed by hierarchically arranging a plurality of nodes, each of which corresponds to a hierarchically divided state space.

[0017] The integrated circuit may be provided with a communication unit for communicating with a predetermined integrated processing server, the individual trained model may be transmitted from each of the operating devices to the integrated processing server via each of the communication units, and the integrated processing may be executed in the integrated processing server.

[0018] The initial data may be data generated based on a test of the operating device or a simulation of the operating device.

[0019] The integration step may further include a selective integration step of selectively integrating the individual trained models based on associated information corresponding to each of the individual trained models.

[0020] The present disclosure can also be conceived as a method as described below. That is, the method according to the present disclosure includes an initial learning step of performing learning on a predetermined machine learning model based on predetermined initial data to generate an initial trained model, an incorporating step of incorporating the initial trained model that controls a predetermined operating device into a plurality of the operating devices, an additional learning step of performing additional learning on each of the operating devices based on individual operation data obtained by operating each of the operating devices to generate a plurality of individual trained models, and an integration step of integrating the individual trained models to obtain a general-purpose trained model.

[0021] Furthermore, the present disclosure can also be conceived as a system. That is, the system according to the present disclosure includes an initial learning unit that performs learning on a predetermined machine learning model based on predetermined initial data to generate an initial trained model, and an integration unit that incorporates the initial trained model that controls a predetermined operating device into a plurality of the operating devices, and integrates a plurality of individual trained models obtained by performing additional learning on the basis of individual operation data obtained by operating each of the operating devices to obtain a general-purpose trained model. Effect of the Invention

[0022] According to the present disclosure, it is possible to generate a general-purpose trained model that can also accommodate the individual characteristics of an operating device. [Brief description of the drawings]

[0023] [Figure 1] FIG. 1 is an explanatory diagram regarding the overall configuration of the system. [Diagram 2] FIG. 2 is an explanatory diagram of the configuration of the information processing device. [Diagram 3] FIG. 3 is an explanatory diagram regarding the configuration of the operating device. [Figure 4] Figure 4 is a general flowchart for generating a general-purpose trained model. [Diagram 5] FIG. 5 is a general flowchart of the learning process. [Figure 6] FIG. 6 is a flowchart relating to the error calculation process. [Figure 7] FIG. 7 is a flow chart regarding the operation of the operating device. [Figure 8] FIG. 8 is a flowchart relating to the prediction process. [Figure 9] FIG. 9 is a flowchart relating to the integration process. [Figure 10] FIG. 10 is a detailed flowchart of the integration process. [Figure 11] FIG. 11 is a conceptual diagram (part 1) of the integration process. [Figure 12] FIG. 12 is a conceptual diagram (part 2) of the integration process. [Figure 13] FIG. 13 is a diagram showing the overall configuration of the system (second embodiment). [Figure 14] FIG. 14 is a general flowchart relating to generation of a general-purpose trained model (second embodiment). [Figure 15] FIG. 15 is a flowchart illustrating the process of selecting trained models to be integrated. [Figure 16] FIG. 16 is a conceptual diagram of the integration process based on the accompanying information. [Figure 17]FIG. 17 is a conceptual diagram of a multi-stage integration process performed using accompanying information. [Figure 18] FIG. 18 is an explanatory diagram of the basic structure of a learning tree. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0024] Hereinafter, an embodiment of the present invention will be described in detail with reference to the accompanying drawings.

[0025] <1. First embodiment> A first embodiment of the present disclosure will be described with reference to FIGS.

[0026] <1.1 Device configuration> The device configuration of a general-purpose trained model generation system 5 according to this embodiment will be described with reference to FIGS. 1 to 3.

[0027] 1 is an explanatory diagram of the overall configuration of a general-purpose trained model generation system 5 according to this embodiment. As is clear from the figure, the general-purpose trained model generation system 5 includes an information processing device 1 that performs information processing such as a learning process described below, an integration processing server 2 that integrates trained models, and a plurality of operating devices 3 such as a robot arm, and each device 1 to 3 is connected to each other via the Internet. As described below, a predetermined trained model that has been trained in the information processing device 1 is mounted on the integrated circuit 4, and the integrated circuit after mounting the trained model is mounted on each operating device 3.

[0028] FIG. 2 is an explanatory diagram of a schematic configuration of the information processing device 1. As is clear from the figure, the information processing device 1 has a display unit 11 including a display, an audio output unit 12 that outputs audio through a speaker, an input unit 13 that accepts input from a keyboard, a mouse, etc., a control unit 14 consisting of a CPU, etc., a storage unit 15 consisting of memories such as ROM, RAM, flash memory, and a hard disk that store operating programs and predetermined data, and a communication unit 1 for communicating with external devices, which are connected to each other via a system bus. The control unit 14 reads out programs and predetermined data from the storage unit 15 and performs predetermined information processing including machine learning. The hardware configuration of the integrated processing server 2 is also approximately the same as that of the information processing device 1, so a description of the configuration will be omitted here.

[0029] 3 is an explanatory diagram of the configuration of the integrated circuit 4 mounted inside the operating device 3. As is clear from the figure, the integrated circuit 4 is composed of a control unit 41 consisting of an MPU or the like, a storage unit 42 consisting of a ROM, a RAM, or the like, a communication unit 43 consisting of a communication unit or the like for communicating with an external device such as the integrated processing server 2, an output unit 44 connected to the operating circuit or the like of the operating device 3 and providing a control output, and an I / O unit 45 for inputting and outputting with the external device, which are electrically connected to each other via a system bus or the like. That is, the control unit 41 can control a predetermined operating device 3 using a trained model read from the storage unit 42.

[0030] <1.2 Operation> Next, the operation of the general-purpose trained model generation system 5 according to this embodiment will be described with reference to FIGS.

[0031] <1.2.1 Initial learning steps> 4 is a general flowchart relating to a method for generating a general-purpose trained model. As is clear from the figure, when the process starts, the information processing device 1 performs a training process for a model having a tree structure (S10).

[0032] FIG. 5 is a detailed flowchart of the learning process (S10). As is clear from the figure, when the process starts, first, initial data is read and input to the learning model is performed (S101). Here, the initial data consists of input data and corresponding teacher data, and the teacher data is a group of actual data obtained by actually operating the operating device 3 or a group of data obtained by simulation using a physical simulator or the like. For example, if the operating device 3 is a robot arm, the teacher data may be a command value of the output torque, actual joint angle data obtained by an angle sensor, a hand position photographed by a camera, etc., depending on the control mode. When the input process to the learning model is completed, next, a state space to which the input data should belong and a node corresponding to the state space are specified, and thus a plurality of nodes, that is, one path from the root node to the terminal node is specified (S102). At this time, if a node that has never been active in the past exists on the path, a new node is generated at that position. After that, for each node on the path, an error corresponding to the prediction error of each node is calculated (S103). Then, all the data and parameters for each node are saved as a file (S104), and the process ends. Note that the parameters here are, for example, information about the range of values ​​to be learned (learning space), i.e., the maximum and minimum values ​​of the input and output data, the network structure (number of layers, number of dimensions, number of divisions), etc.

[0033] FIG. 6 is a flowchart showing details of the error calculation process (S103). When the process starts, first, the root node is set as the node of interest (S1031). Next, for the node of interest, an error update process is performed by the formula Et+1=(1-α)Et+α|O-O'| (S1032). Here, Et+1 represents the error after the update, Et represents the error before the update, and α represents the forgetting factor (0<α<1). As is clear from the formula, the error Et+1 after the update is calculated by weighting and adding the error Et before the update and the absolute value of the difference between the predicted output O based on the input data and the predicted output O' based on the data included in the node of interest using the forgetting factor α. In other words, the smaller the difference between the predicted output O based on the input data and the predicted output O' based on the past data included in the node of interest, the smaller Et+1 becomes, so that the smaller the error Et+1 is, the better the prediction accuracy is. The updated error Et+1 is associated with the node of interest and stored as the error E in the storage unit 15 (S1033).

[0034] Then, a process is performed to determine whether the node of interest is the lowest layer node (S1034), and if it is not the lowest layer node, a process is performed to change the node of interest to a node one level lower (S1035). This series of processes, the process of changing the node of interest to a node one level lower on the path (S1035), the process of updating the error (S1032), and the process of saving (S1033), are repeated until the node of interest is reached (S1034NO). On the other hand, if the node of interest has reached the lowest layer node (terminal node) (S1034YES), the process ends. That is, according to this series of processes, an error E corresponding to the prediction accuracy is generated for each of all nodes on the path.

[0035] The method of calculating the error E is not limited to the above. Therefore, for example, an error obtained by referring to a node on a route lower than the node of interest may be used.

[0036] <1.2.2 Mounting step> Returning to Fig. 4, when the learning process is completed, a process is performed in which a trained model corresponding to the learning result is mounted on an integrated circuit (IC) 4, and then a process is performed in which the integrated circuit 4 is mounted on each operating device 3 (S20). Specifically, the tree structure model trained based on the above-mentioned initial data is read by the control unit 41 and stored in the storage unit 42 in an executable manner. The trained model is further configured in a manner that allows additional learning, and is configured so that when new data is obtained in each operating device 3, further additional learning can be performed based on the data.

[0037] <1.2.3 Additional learning steps> After the installation process in the operation device 3 is completed, the operation device 3 is actually controlled using the installed trained model, and additional learning process is performed based on the actual operation data obtained by the operation (S30).

[0038] 7 is a detailed flowchart regarding the operation (S30) of the operating device 3. As is clear from the figure, when the process starts, the operation of the operating device 3 is controlled by a prediction process using a trained model (S301).

[0039] FIG. 8 is a flowchart showing the details of the prediction process (S301). As is clear from the figure, when the process starts, first, new data related to the operating device 3 is obtained, and the data is used as input data (S3011). Next, based on the input data, a state space (node) to which the data should belong is identified, and a path consisting of a series of multiple nodes is identified (S3012). When the path is identified, a node on the path with the smallest error E is identified (S3013), and a predicted output is generated based on the arithmetic mean (composite vector of the transition vectors) of the transition vectors of each data corresponding to the node with the smallest error E (S3014). This predicted output is transmitted as a command value to the operating circuit of the operating device 3 via the output unit 44, and the operating device 3 operates in response to this. That is, a predicted output is generated based on the node with the smallest error on the path, and thus a predicted output can be generated based on a node expected to have relatively good prediction accuracy.

[0040] In this embodiment, the predicted output is generated based on data corresponding to the node with the minimum error on the path, but the present invention is not limited to such processing. Therefore, for example, a configuration may be adopted in which the predicted output is always generated based on data corresponding to the terminal node.

[0041] Returning to Fig. 7, when the prediction process is completed, the actual operation data of the operation device 3 is stored (S302). A series of processes including this prediction process (S301) and the storage process of the operation data (S302) are repeated until a predetermined operation end condition is met (S303 NO). When the predetermined operation end condition is met (S303), the series of operations ends, and an additional learning process is performed using the stored operation data as teacher data (S304). This additional learning process is substantially the same as the process (S101 to S104) shown in Fig. 2, so a description thereof will be omitted here. After that, the process ends.

[0042] In order to explain the operation in FIG. 7 more specifically, a task of shifting the joint angle of a one-joint robot arm, whose joint angle is 0 degrees according to a predetermined standard in the initial state, to a state of 30 degrees will be explained as an example. First, when the process starts and the initial angle (0 degrees) and the target angle (30 degrees) are given to a learned model that has learned the relationship between them and the command value of the output torque, a prediction process of the command value of the output torque is performed, and the operation of the robot arm is controlled according to the predicted output (S301). After the operation control, a sensor provided in the robot arm detects angle data as actual operation data (S302). Thereafter, when the task ends with the actual driving of the robot arm, the operation ends (S303 YES), and additional learning process is performed using the actual angle value obtained from the sensor (S304). As described above, the robot arm performs additional learning for each actual operation to improve accuracy. Note that, here, the configuration is such that the output torque is predicted using the initial angle and the target angle as inputs, but the present disclosure is not limited to such a learning configuration. Therefore, it goes without saying that other combinations of input / output configurations may be adopted.

[0043] <1.2.4 Integration process steps> 4, when the individual additional learning process (S30) in each operating device 3 is completed, a process is performed in which data on the additionally trained model, i.e., data on nodes and parameters, is transmitted from each operating device 3 to the integrated processing server 2 via the network (S40). Upon receiving the data, the integrated processing server 2 performs a process of integrating the additionally trained models (S50).

[0044] FIG. 9 is a detailed flowchart of the integration process (S50). When the process starts, the parameter files generated when generating the trained models are read for the two different trained models (S501). It is determined whether the learning intervals match or approximately match based on the parameter files (S502). If they do not match (S502NO), an error message is output to the user via a display (not shown) to inform that integration cannot be performed (S505), and it is then determined whether integration processing between all the trained trees has been completed (S506). On the other hand, if the learning spaces match or approximately match, a data file related to the nodes of the two trained models is read (S503). After that, after integration processing of the trained trees related to the two different trained models described later is performed (S504), it is determined whether integration processing between all the trained trees has been completed (S506). If it is determined that integration processing between all the trained trees has not been completed (S506NO), integration processing is performed with a different combination of trained trees (S506NO). On the other hand, when it is determined that the integration process between all the learning trees is completed (S506 YES), the process ends. Note that here, the approximate agreement of the learning space means, for example, that the maximum and minimum values ​​of the data included in one trained model are included within a range with a certain margin (for example, about 10%) of the maximum and minimum values ​​of the data included in the other trained model.

[0045] 10 is a detailed flowchart of the integration process (S504). When the process starts, the first node position is set as the focus position (S5041). Next, a process is performed to determine whether a node exists in both learning trees at the focus position (S5042). If a node exists in both learning trees at the focus position (S5042 YES), an integration process is performed for the two nodes (S5043).

[0046] Here, the aspect of the node integration process according to this embodiment will be described. FIG. 12 is a conceptual diagram of the node integration process (S5043). FIG. 12(a) is a first integration example in which two colored nodes on the upper left and right are integrated into one colored node on the lower side. In the figure, E represents the above-mentioned error, and C represents the number of data included so far. The error E of the upper left node is α (>0), the number of data C is k (an integer equal to or greater than 0), and the error E of the upper right node is β (>0), and the number of data C is m (an integer equal to or greater than 0). When integrating these nodes, the data associated with each node is integrated so as to be associated with one node. In addition, the error E after integration is calculated by weighting and adding the above-mentioned errors α and β using the numbers of data k and m. Furthermore, the number of data C after integration is calculated by adding up the numbers of data k and m.

[0047] According to such a configuration, integration between nodes is performed by performing weighted addition according to the number of data included, so that learning-related parameters can be integrated according to the reliability based on the number of data.

[0048] FIG. 12(b) is a second integration example in which two colored nodes on the upper left and right are integrated into one colored node on the lower side. The error E of the upper left node is α (>0), the number of data C is n (an integer equal to or greater than 0), and the error E of the upper right node is ∞, and the number of data C is 1. Here, the error E is ∞, which is a value given for convenience because the number of data associated with the node is still one and the error is not defined. When integrating these nodes, the data associated with each node is integrated so that it is associated with one node. In addition, the error E after integration is calculated as α based on the above-mentioned errors α and ∞. Furthermore, the number of data C after integration is calculated as n+1 by adding the number of data n and 1.

[0049] In this embodiment, in performing the node integration process, each data associated with each node, the error E, and the number of data C are the integration targets, but the integration targets are not limited to these parameters. Therefore, when integrating nodes, it goes without saying that other parameters associated with the nodes may be the integration targets.

[0050] 10, when the node integration process (S5043) is completed, the integrated node is stored in the storage unit (S5044). Then, a process is performed to determine whether all node positions have been processed (S5045).

[0051] On the other hand, if a node does not exist in either learning tree at the focus position (S5042 NO), then a process of determining whether or not a node exists in either learning tree is performed (S5047). If a node does not exist in either learning tree (S5047 NO), no further process is performed, and a process of determining whether or not all node positions have been processed is performed (S5047 NO). If a node exists at the focus position of either learning tree (S5047 YES), the nodes below the focus node in the data of the existing learning tree are copied and saved as integrated data (S5048). Then a process of determining whether or not all node positions have been processed is performed (S5045).

[0052] With this configuration, when a certain node exists in only one of the trained models, the nodes below that node also exist in only that trained model, making it possible to perform efficient integration processing.

[0053] When all node positions have been processed (S5045 YES), the process ends. On the other hand, when all node positions have not yet been processed (S5045 NO), a process is performed to change and set the focus position to a predetermined next node position (S5046), and node integration process (S5043) or one of the nodes is duplicated (S5048) again. At this time, the focus position is set (depth-first search) from the higher node position. This is because when a node exists in only one learning tree (S5047 YES), the nodes below the focus node are duplicated (S5048), so it is more efficient to perform a search from the higher node position.

[0054] Fig. 11 is a conceptual diagram of merging learning trees. As is clear from the figure, when the first learning tree in the upper left and the second learning tree in the upper right are merged, as shown in the lower part of the figure, the black nodes are merged, while the nodes of the first learning tree or the second learning tree are duplicated for the white nodes.

[0055] According to such a configuration, since learning models based on a tree structure are integrated, the integration process is easier than with neural networks and the like.

[0056] In addition, with this configuration, each individual trained model can be aggregated and integrated from a large number of operating devices 3 that have performed additional learning into the integrated processing server 2, making it possible to generate a trained model that can be used universally for that type of operating device.

[0057] <1.2.5 Download Step> Returning to FIG. 4, when the integration process of the trained model in the integration process server 2 (S50) is completed, a process is performed to download the integrated model (general-purpose trained model) from the integration process server 2 to each operation device 3 via a network (S60). Specifically, after a predetermined period of time has elapsed, the owner of the operation device 3 or the like downloads the integrated model to an information processing device such as a personal computer (not shown), and transfers the integrated model from the information processing device to each operation device 3 via the I / O unit 45 to store it in each storage unit 42 of the operation device 3. Then, the process ends.

[0058] According to such a configuration, it is possible to control the operating device 3 with higher accuracy by using the integrated model that has learned the characteristics of various operating devices 3. In addition, the owner of the operating device 3 can select whether to use the already installed learned model or the integrated model.

[0059] In this embodiment, the owner of the operating device 3 or the like downloads the integrated model to an information processing device such as a personal computer (not shown), but the present disclosure is not limited to such a configuration. Therefore, for example, the owner of the operating device 3 or the like may issue a download command to the operating device 3, which causes the operating device 3 to download the latest integrated model via the communication unit 43.

[0060] <2. Second embodiment> Next, a second embodiment of the present invention will be described with reference to Fig. 13 to Fig. 16. In this embodiment, various types of associated information are used when performing integration processing between trained models.

[0061] 13 is an overall configuration diagram of a general-purpose trained model generation system 100 according to this embodiment. As is clear from the figure, the general-purpose trained model generation system 100 is configured by connecting a first information processing device 101, a second information processing device 102, and an information processing terminal 103 via a network such as the Internet. Each device exchanges information with each other via communication.

[0062] As described later, the first information processing device 101 is mainly responsible for learning processing, and performs initial learning and integration processing of learned models. The second information processing device 102 functions as an application server, and is responsible for, for example, providing a predetermined application program to the information processing terminal 103 and performing predetermined server-side processing, and also communicates information with the first information processing device 101 and the information processing terminal 3. The information processing terminal 103 is an information processing device such as a smartphone or a tablet computer, and can download a predetermined application program from the second information processing terminal 102. The information processing terminal 103 cooperates with the second information processing device 102 to provide a predetermined application to a user. The information processing terminal 103 is connected to a wearable terminal 104 that can be paired with the information processing terminal 103 by a standard such as Bluetooth (registered trademark). The wearable terminal 104 is equipped with various sensors that sense blood pressure, heart rate, body temperature, number of steps, etc., and the acquired sensor information is transmitted to the information processing terminal 3. Note that the device configuration of each device is approximately the same as the configuration shown in FIG. 2, so a description thereof will be omitted here.

[0063] While various examples of the contents of the application program are conceivable, in this embodiment, the application program is an application program that predicts the risk of a certain disease of the user of the wearable terminal 104 using various sensor information acquired from the wearable terminal 104 as input. The information acquired from the sensors includes vital sign information such as blood pressure, heart rate, and body temperature, and activity amount information such as the number of steps.

[0064] FIG. 14 is a general flowchart of a process for generating a general-purpose trained model according to this embodiment.

[0065] When the process starts, in the first information processing device 101, initial learning is performed using a learning model having a tree structure similar to that of the first embodiment (S81). The details of the learning process are substantially the same as those in Figs. 5 and 6, and therefore a detailed description thereof will be omitted.

[0066] However, the learning process in this embodiment is performed by performing supervised learning using vital information such as blood pressure, heart rate, and body temperature, and activity amount information such as the number of steps, as input, and actual disease information of various users (various numerical values, diagnosis results, evaluations of health conditions, etc.) as teacher data. That is, through the learning process, a trained model can be obtained that outputs disease information such as a predicted disease risk for the user based on the vital information and activity amount information.

[0067] The trained model generated in the first information processing device 101 is downloaded to each information processing terminal 103 via application software executed on the information processing terminal 103 (S82). Note that the trained model may be downloaded to each information processing terminal 103 in response to a command from the information processing terminal 102 functioning as an application server.

[0068] At this time, the information processing terminal 103 receives input of associated information about the user through the application program and stores it in an internal storage unit. The associated information is, for example, information about age, sex, or area of ​​residence.

[0069] Thereafter, additional learning is performed individually in each information processing terminal 103 (S83). Details of the additional learning process are substantially the same as those shown in Figs. 7 and 8, and therefore detailed description thereof will be omitted. However, in the additional learning process in this embodiment, actual illness information of each user inputted via application software is used as actual operation data. Furthermore, the end of operation (S303) is determined, for example, by the passage of a predetermined period of time.

[0070] When a predetermined period has elapsed, the trained model that has been additionally trained and associated information regarding the user who transmits the trained model are transmitted to the first information processing device 101 (S84).

[0071] When the first information processing device 101 receives the trained model that has undergone additional training and the associated information, the first information processing device 101 performs a process of integrating the trained models based on the associated information (S85).

[0072] The details of the integration process are substantially the same as those shown in Fig. 9 to Fig. 12, and therefore a detailed description thereof will be omitted. However, in the integration process of this embodiment, a process of selecting trained models to be integrated is performed prior to the integration process shown in Fig. 9.

[0073] FIG. 15 is a flowchart related to the selection process of trained models to be integrated. As is clear from the figure, when the process starts, the first information processing device 101 selects trained models to be integrated according to a predetermined selection criterion and the received associated information (S851). Here, the predetermined selection criterion is a selection criterion that is stored in advance in the first information processing device 101 or set by another device or terminal, and the content thereof may be, for example, information on the area where the user lives. That is, the first information processing device 101 performs a process of selecting only trained models related to users who live in the same area, for example.

[0074] Thereafter, the selected trained models are appropriately integrated to obtain multiple general-purpose trained models (S852). That is, each general-purpose trained model is an integration of trained models related to users residing in the same area. Note that the integration process is substantially the same as that shown in FIG. 9, and therefore will not be described.

[0075] FIG. 16 is a conceptual diagram of the integration process (S85) based on the associated information. In the figure, a plurality of trained models having a tree structure are arranged in two tiers, an upper tier and a lower tier. The lower tier (first tier) is a plurality of trained models 110-1 to 110-N (N is a natural number of 2 or more) that have been individually additionally trained in each information processing terminal 103. The upper tier (second tier) is a plurality of trained models 120-1 to 120-M (M is a natural number of 2 or more) having a tree structure that are generated by integrating the trained models 110-1 to 110-N in the lower tier. As is clear from the figure, for example, when the predetermined selection criterion is the area of ​​residence, a plurality of trained models having a tree structure shown in the upper tier (second tier) are generated by integrating the plurality of trained models in the lower tier obtained from users living in the same area.

[0076] Returning to FIG. 14, when the integration process (S85) is completed, a process of storing each integrated trained model is performed, and the process ends (S86). Each stored trained model may be configured to be downloadable to each information processing terminal 103 thereafter. Each stored trained model may also be transmitted to a second information processing device. At this time, a corresponding trained model may be configured to be downloadable according to the associated information. For example, a predictive model (trained model) suitable for people living in the same area as oneself may be downloaded.

[0077] According to this configuration, additional trained models are integrated based on a predetermined selection criterion and associated information, so that a general-purpose trained model can be generated by integrating trained models having common associated information. This makes it possible to generate a trained model suitable for a specific purpose or user.

[0078] <3. Modifications> In the first embodiment, a trained model after additional training is transmitted from the operation device 3, but the present disclosure is not limited to such a configuration. Therefore, for example, the operation data may be transmitted from the operation device 3 to the integration processing server 2, and the integration processing server 2 may learn the operation data, thereby realizing the integration.

[0079] In the above-described embodiment, although there is no particular limitation on the timing of transmission of the trained model after additional learning, the timing of the transmission may be after a certain amount of additional learning has progressed, or may be sequential.

[0080] In the above embodiment, information is aggregated in the integrated processing server 2 on the network, but it may also be aggregated in, for example, a PLC (Programmable Logic Controller) connected to the network.

[0081] In the first embodiment, a robot arm is exemplified as the operating device 3, but the present invention is not limited to such an operating device. Therefore, the present invention can be applied to various operating devices, such as sensor devices, mobile phones, automobiles, drones, AI speakers, ships, marine floats, tunnel excavation shields, construction machinery, railways, EVs, air conditioners, compressors, factory machines, household robots, nuclear fusion control, PLCs, communication gateways, smart houses, wearable terminals, home appliances, various meters (electricity, water, gas, etc.), game machines, etc. Note that the operation in this disclosure is not limited to only the mechanical operation of the device, but also includes, for example, electrical or electromagnetic operation in the device.

[0082] In the first embodiment, a trained model that has been trained in advance is mounted on the integrated circuit 4, and the integrated circuit 4 is incorporated into the operating device 3, and then additional training is performed individually, but the present disclosure is not limited to such a configuration. Therefore, for example, after performing pre-training on the information processing device 1 to generate a trained model, the trained model may be downloaded directly or indirectly to each operating device 3, and additional training may be performed in each operating device 3 based on the downloaded trained model.

[0083] In the first embodiment, the information processing device 1 and the integrated processing server 2 are shown as separate components, but they may be integrated. In addition, some functions may be independent, or distributed processing may be performed.

[0084] The integrated circuit 4 in the first embodiment may be configured with an FPGA (Field-Programmable Gate Array) or the like.

[0085] In the second embodiment, as shown in Fig. 16, the integration process based on the associated information is performed in two stages. However, the present invention is not limited to such a configuration. Therefore, for example, the integration may be performed in multiple stages, each of which is stored, and an appropriate integrated trained model may be provided in response to a request from the information processing terminal 103 or the like.

[0086] FIG. 17 is a conceptual diagram of a multi-stage integration process performed using associated information. The bottom layer shows a first layer 130 consisting of trained models 130-1 to 130-N obtained by additional learning in an individual information processing terminal 103. The middle layer shows a second layer 140 consisting of trained models 140-1 to 140-M obtained by integrating trained models in the layer immediately below. The top layer shows a K-th layer 150 consisting of trained models 150-1 to 150-L obtained by integrating trained models in the layer immediately below. As shown in the figure, a multi-stage integration process may be performed based on associated information. For example, in the second layer, trained models in the first layer may be integrated based on regional information, and in the third layer, integration may be performed based on regional information from a broader perspective. In addition, in other layers, integration may be performed in stages based on gender, age information, and the like.

[0087] According to such a configuration, an appropriate integrated trained model can be provided to the information processing terminal 103 or the second information processing device 102 as needed.

[0088] In the above embodiment, a learning model using a tree structure is used as the learning model, but the present invention is not limited to such a method, and therefore, other learning models that can be integrated can be used. [Industrial Applicability]

[0089] It can be used in industries that manufacture systems for generating general-purpose trained models. [Explanation of symbols]

[0090] 1. Information processing device 2. Integrated Processing Server 3 Operating device 4. Integrated Circuits 5. General-purpose trained model generation system 100 General-purpose trained model generation system 101 First information processing device 102 Second information processing device 103 Information processing terminal 104 Wearable Devices

Claims

1. An initial learning step of learning a predetermined machine learning model based on predetermined initial data to generate an initial trained model; A method for generating a general-purpose trained model, comprising: an integration step of incorporating the initial trained model that controls a specific operating device into a plurality of the operating devices, and integrating a plurality of individual trained models obtained by performing additional learning on the basis of individual operation data obtained by operating each of the operating devices to obtain a general-purpose trained model.

2. The generation of the initial trained model is performed in a predetermined initial training server connected to a network, The method for generating a general-purpose trained model as described in claim 1, wherein the initial trained model is incorporated into the operating device by downloading it from the initial training server to each operating device via the network.

3. The method for generating a general-purpose trained model as described in claim 1, wherein the incorporation of the initial trained model into the operating device is performed by mounting the initial trained model on an integrated circuit and incorporating the integrated circuit into each of the operating devices.

4. The method for generating a general-purpose trained model further includes: The method for generating a generic trained model as described in claim 1 , further comprising a re-incorporation step of incorporating the generic trained model into each of the operating devices.

5. The method for generating a general-purpose trained model as described in claim 1, wherein the machine learning model is a learning model having a tree structure constructed by hierarchically arranging a plurality of nodes, each of which corresponds to a hierarchically divided state space.

6. the integrated circuit includes a communication unit for communicating with a predetermined integrated processing server; The individual trained model is transmitted from each of the operating devices to the integrated processing server via each of the communication units; The method for generating a general-purpose trained model according to claim 1 , wherein the integration process is executed in the integration process server.

7. The method for generating a general-purpose trained model according to claim 1 , wherein the initial data is data generated based on a test of the operating device or a simulation of the operating device.

8. The integration step further comprises: The method for generating a general-purpose trained model according to claim 1, further comprising a selective integration step of selectively integrating the individual trained models based on associated information corresponding to each of the individual trained models.

9. An initial learning step of learning a predetermined machine learning model based on predetermined initial data to generate an initial trained model; an incorporation step of incorporating the initially trained model that controls a predetermined operating device into a plurality of the operating devices; an additional learning step of performing additional learning on the basis of individual operation data obtained by operating each of the operation devices to generate a plurality of individual trained models; An integration step of integrating each of the individual trained models to obtain a general-purpose trained model; A re-integration step of re-integrating the generic trained model into each of the operating devices; A method for generating a general-purpose trained model comprising:

10. An initial learning unit that learns a predetermined machine learning model based on predetermined initial data to generate an initial trained model; A system for generating a general-purpose trained model comprising: an integration unit that incorporates the initial trained model that controls a specific operating device into multiple operating devices, and integrates multiple individual trained models obtained by performing additional learning on individual operation data obtained by operating each of the operating devices to obtain a general-purpose trained model.

Images