Configuration assistance method, learning completed model generation method, recording medium, configuration assistance system, and work system

Abstract

An object of the present disclosure is to give a proposal of an improved arrangement of components. A configuration assistance method according to the present disclosure includes an acquisition step and a proposal step. A component mounting system (100) is a system that generates a product (P3) by mounting a plurality of components (P1) supplied to a plurality of supply portions (3) to an object (P2). The acquisition step is a step of acquiring mounting data (D1) related to the plurality of components (P1) included in the product (P3). The proposal step is a step of proposing, using a learned model, an arrangement of the plurality of components (P1) for the plurality of supply portions (3) based on the mounting data (D1) so that a mounting time required for generation of the product (P3) in the component mounting system (100) is shortened. The learned model is a model generated in correspondence with a feature of at least one supply portion (3) among the plurality of supply portions (3).

Description

TECHNICAL FIELD

[0001] The present disclosure generally relates to a configuration assistance method, a learning-finished model generation method, a program, a configuration assistance system, and a work system. More specifically, it relates to a configuration assistance method, a learning-finished model generation method, a program, a configuration assistance system, and a work system that assist in deciding a configuration of a plurality of components in a plurality of supply sections for a component mounting system that mounts a plurality of components supplied to the plurality of supply sections to an object. BACKGROUND

[0002] Patent Document 1 describes an operation analysis device for monitoring in a component mounting line so that a line mounting tempo or an operation rate of the line does not decrease, and maintaining a high production efficiency of the line as a whole by analyzing a factor of the decrease and removing it.

[0003] In this operation analysis device, in a component mounting machine that has the largest mounting tempo performance value in a component mounting line, i.e., a bottleneck component mounting machine, in order to eliminate a reason why the mounting tempo performance value of the bottleneck component mounting machine, i.e., a line mounting tempo, does not reach a target value, an arrangement of a component supply device or an optimization of a component mounting order is made so that a tempo loss is reduced. Thereby, for example, if the reason is an imbalance of the mounting tempo performance values of each component mounting machine, by making a correction of the distribution of components to each mounting machine, the tempo loss is reduced, and it is possible to maintain the line mounting tempo at the target value.

[0004] PRIOR ART DOCUMENTS

[0005] PATENT DOCUMENT

[0006] Patent Document 1: JP Laid-open Patent Publication No. 2002-111298 SUMMARY

[0007] However, in Patent Document 1, even if the correction of the distribution of components to each mounting machine is made, it is not explicitly disclosed how the components are distributed to each mounting machine, and improvement is sought with respect to the configuration (including the distribution) of the components.

[0008] The present disclosure is made in view of the above-described circumstances, and aims to provide a configuration assistance method, a learning-finished model generation method, a program, a configuration assistance system, and a work system that can give a proposal of a configuration of components that has been improved.

[0009] A configuration assistance method according to an embodiment of the present disclosure is a method of assisting a decision of a configuration of a plurality of components in a plurality of supply sections of a component mounting system, and includes an acquisition step and a proposal step. The component mounting system is a system that generates a product by mounting the plurality of components supplied to the plurality of supply sections to an object. The acquisition step is a step of acquiring mounting data related to the plurality of components included in the product. The proposal step is a step of proposing, using a learned model, a configuration of the plurality of components in the plurality of supply sections based on the mounting data so that mounting time required for generation of the product in the component mounting system is shortened. The learned model is a model generated in correspondence with a feature of at least one supply section among the plurality of supply sections.

[0010] A learned model generation method according to an embodiment of the present disclosure generates a learned model used in the configuration assistance method in correspondence with a feature of at least one supply section among the plurality of supply sections.

[0011] A program according to an embodiment of the present disclosure is a program for causing one or more processors to execute the configuration assistance method or the learned model generation method.

[0012] A configuration assistance system according to an embodiment of the present disclosure is a system that assists a decision of a configuration of a plurality of components in a plurality of supply sections of a component mounting system, and includes an acquisition section and a proposal section. The component mounting system is a system that generates a product by mounting the plurality of components supplied to the plurality of supply sections to an object. The acquisition section acquires mounting data related to the plurality of components included in the product. The proposal section proposes, using a learned model, a configuration of the plurality of components in the plurality of supply sections based on the mounting data so that mounting time required for generation of the product in the component mounting system is shortened. The learned model is a model generated in correspondence with a feature of at least one supply section among the plurality of supply sections.

[0013] A work system according to an embodiment of the present disclosure includes the configuration assistance system and the component mounting system. The component mounting system generates the product using the configuration of the plurality of components proposed in the configuration assistance system. BRIEF DESCRIPTION OF DRAWINGS

[0014] Figure 1 is a schematic diagram showing an appearance of a component mounting system that uses the configuration assistance method according to Embodiment 1.

[0015] Figure 2 is a conceptual diagram showing a configuration of components in a supply section of the component mounting system of the above-described configuration assistance method.

[0016] Figure 3 is a block diagram showing an outline of a job system including the configuration assistance system according to Embodiment 1.

[0017] Figure 4 A of Figure 4 B is a conceptual diagram showing a proposal of a configuration of a plurality of components in the supply section of the configuration assistance method.

[0018] Figure 5 is a flowchart showing an example of the configuration assistance method.

[0019] Figure 6 is an explanatory diagram showing a proposal of an allocation of components in a multi-stage manner of the configuration assistance method.

[0020] Figure 7 is an explanatory diagram showing a proposal of a reconfiguration of the configuration assistance method. DETAILED DESCRIPTION

[0021] (Embodiment 1)

[0022] The configuration assistance method, program, configuration assistance system 20 (refer to Figures 1-7 ), and job system 200 (refer to Figure 3 ) according to the present embodiment will be described below with reference to Figure 3 .

[0023] (1) Outline

[0024] The configuration assistance method according to the present embodiment is a configuration assistance method that assists a configuration of a plurality of components P1 in a plurality of supply sections 3 with respect to a component mounting system 100, as shown in Figure 1 . The component mounting system 100 has a plurality of supply sections 3 for supplying components P1 used in the component mounting system 100, and generates a product P3 by mounting the plurality of components P1 supplied to the plurality of supply sections 3 to an object P2.

[0025] That is, the component mounting system 100 has at least one mounting machine (mounting device) 10 for mounting the components P1 to the object P2, as shown in Figure 1 . The mounting machine 10 has a capturing section 41 (refer to Figure 1 ) for capturing the components P1. The capturing section 41 is configured by a suction nozzle, for example, and captures (holds) the components P1 in a releasable (i.e., a state in which the capturing is released) state. The mounting machine 10 captures the components P1 supplied from the supply sections 3 with the capturing section 41, moves the capturing section 41 in a state in which the components P1 are captured, and releases the components P1 on the object P2, thereby mounting the components P1 on a mounting surface of the object P2.

[0026] In this embodiment, as an example, the component mounting system 100 mounts multiple units ( Figure 1 In the example, for example, four installation machines 10 are connected to form an installation production line. In other words, the component installation system 100 has multiple installation machines 10 connected to each other to form an installation production line. In such a component installation system 100 (installation production line), for example, multiple installation machines 10 sequentially install components P1 on one object P2 to ultimately generate a product P3 with multiple components P1 installed.

[0027] Each of the multiple installation machines 10 has at least one supply unit 3, which installs the component P1 supplied to it. That is, each installation machine 10 installs one or more components P1 supplied to it by its own supply unit 3 onto the object P2. Figure 1 In the example, each of the multiple installation machines 10 has multiple (here, two) supply units 3. In this embodiment, since the component installation system 100 has multiple installation machines 10, it is assumed that each of the multiple installation machines 10 has one supply unit 3, and as a whole, the component installation system 100 also has multiple supply units 3.

[0028] The component installation system 100 is used, for example, in facilities such as factories, research institutes, office buildings, and educational facilities, in the manufacturing of various products such as electronic equipment, automobiles, clothing, food, pharmaceuticals, and handicrafts.

[0029] In such a component installation system 100, there are many configuration patterns for the multiple components P1 located in the multiple supply units 3 of the multiple installation machines 10. That is, for multiple components P1, since it is possible to select which supply unit 3 of the multiple installation machines 10 to which each component P1 is assigned, if the number of components P1 becomes, for example, hundreds, the configuration patterns of the multiple components P1 in the multiple supply units 3 become numerous. Moreover, due to the configuration of the multiple components P1 in the multiple supply units 3, the installation time required to generate the product P3 in the component installation system 100 varies greatly. For example, the installation time varies greatly depending on how the multiple components P1 are distributed to the multiple installation machines 10. Thus, the configuration of the multiple components P1 in the multiple supply units 3 is an important factor affecting the installation time of the component installation system 100, and because there are many configuration patterns, finding a suitable configuration is very difficult.

[0030] Therefore, the configuration assistance method according to this embodiment assists in determining the configuration of multiple components P1 in multiple supply units 3 of the component mounting system 100 as described above. According to this configuration assistance method, a more suitable configuration can be found more easily (in a shorter time), for example, the configuration of multiple components P1 in multiple supply units 3 can be determined without the help of a skilled person.

[0031] That is, the configuration assistance method according to this embodiment is a method for proposing the configuration of multiple components P1 in multiple supply units 3 for a component mounting system 100. The component mounting system 100 generates a product P3 by mounting the multiple components P1 supplied to the multiple supply units 3 onto an object P2. Here, the configuration assistance method according to this embodiment can further employ the following three functions to provide an improved configuration proposal for the components P1.

[0032] The first function utilizes the learned model M1 (reference). Figure 3 The configuration proposal is as follows. To achieve the first function, the configuration helper method has an acquisition step and a proposal step. The acquisition step is to acquire the installation data D1 (refer to...). Figure 3 The installation data D1 is data related to the multiple components P1 contained in the product P3. The proposal step uses the learned model M1 based on the installation data D1 to propose a configuration for the multiple components P1 of the multiple supply units 3 to shorten the installation time. The learned model M1 is a model generated by establishing a correspondence with the characteristics of at least one of the multiple supply units 3. The installation time is the time required to generate the product P3 in the component installation system 100.

[0033] Thus, in the first function, the configuration assistance method uses the learned model M1 in the proposal step to propose configurations for multiple components P1 of multiple supply units 3. That is, in the proposal step, instead of proposing a uniquely determined configuration, a suitable configuration is more easily found by using techniques such as a "determination method" for configurations performed by a skilled person, for example, by implementing the learned model M1. In particular, since the learned model M1 is a model generated by establishing a correspondence with the characteristics of at least one of the multiple supply units 3, the configurations of multiple components P1 can be proposed, for example, taking into account the performance or specifications of the installation machine 10. Therefore, in this configuration assistance method, a proposal for an improved configuration of component P1 can be given.

[0034] The second function is the allocation of component P1 in a multi-level manner. To implement this second function, the configuration assistance method has a primary proposal step and a secondary proposal step. The primary proposal step proposes to multiple primary groups G11, G12 (see reference). Figure 6 The steps for configuring multiple components P1. The secondary proposal step is to propose, after the primary proposal step, that multiple primary groups G11 and G12 be classified into multiple secondary groups G21 to G24 (see reference). Figure 6 The steps for configuring multiple components P1 for multiple secondary groups G21 to G24 in the case of ). Each of the multiple secondary groups G21 to G24 includes at least one supply unit 3 among multiple supply units 3.

[0035] Here, the one-proposal step and the two-proposal step in the second function include the proposal step in the first function. In other words, the proposal step includes the one-proposal step and the two-proposal step.

[0036] As such, in the second function, the proposal of the arrangement of the plurality of components P1 is divided into the one-proposal step of arranging the components P1 in a plurality of one groups G11, G12 and the two-proposal step of arranging the components P1 in a plurality of two groups G21 to G24 in more detail. In summary, since the arrangement of the plurality of components P1 is not achieved by one-stage processing but by multi-stage processing set hierarchically, in each stage, the options for deriving a suitable arrangement of the plurality of components P1 can be suppressed to be less. As a result, the processing for proposing the arrangement of the plurality of components P1 in each stage can be simplified. Therefore, in the arrangement assistance method, a proposal of an improved arrangement of the components P1 can be given.

[0037] The third function is re-arrangement. To achieve the third function, the arrangement assistance method has a proposal step, a determination step, and a re-arrangement step. The proposal step is a step of proposing an arrangement of a plurality of components P1 for a plurality of supply sections 3. The determination step is a step of determining a certain supply section 3 among the plurality of supply sections 3 as a target supply section. The supply section 3 determined as the target supply section is a supply section 3 that satisfies a determination condition with respect to a time required for generation of the product P3 in the component mounting system 100 in a case where the arrangement of the plurality of components P1 proposed in the proposal step is adopted. The re-arrangement step is a step of proposing an arrangement of the plurality of components P1 for the target supply section and a reference supply section. The reference supply section is constituted by at least one supply section 3 among the plurality of supply sections 3 other than the target supply section.

[0038] As such, in the third function, even in a case where the arrangement of the plurality of components P1 proposed in the proposal step is not optimal, a new arrangement of the plurality of components P1 can be proposed in the re-arrangement step. Also, the supply section 3 that becomes the target of re-arrangement in the re-arrangement step is the target supply section that satisfies the determination condition with respect to the time required for generation of the product P3 in the component mounting system 100 in a case where the arrangement proposed in the proposal step is adopted among the plurality of supply sections 3. That is, in the re-arrangement step, re-proposal can be made with respect to the arrangement of the supply section 3 that satisfies a certain condition with respect to the time required for generation of the product P3 in the component mounting system 100 among the arrangement proposed in the proposal step. Therefore, in the arrangement assistance method, a proposal of an improved arrangement of the components P1 can be given.

[0039] Further, as an example, the configuration assistance method according to the present embodiment is executed in the configuration assistance system 20. In other words, the configuration assistance system 20 is a manner for embodying the above-described configuration assistance method. That is, the configuration assistance system 20 assists the decision of the configuration of the plurality of components P1 in the plurality of supply portions 3 with respect to the component mounting system 100. The component mounting system 100 is a system that generates a product P3 by mounting the plurality of components P1 supplied to the plurality of supply portions 3 to an object P2 as described above, and is an assembly line as an example in the present embodiment.

[0040] Here, the configuration assistance system 20 has a computer system having one or more processors and one or more memories as a main structure. In other words, the configuration assistance method according to the present embodiment is used on a computer system (configuration assistance system 20). That is, the configuration assistance method can also be embodied by a program. The program according to the present embodiment is a program for causing one or more processors to execute the configuration assistance method according to the present embodiment.

[0041] Further, the work system 200 according to the present embodiment is provided with the configuration assistance system 20 and the component mounting system 100. The component mounting system 100 is a system that uses and generates a product P3 under the configuration of the plurality of components P1 proposed in the configuration assistance system 20.

[0042] (2) Details

[0043] Details of the configuration assistance method, the program, the configuration assistance system 20, and the work system 200 according to the present embodiment will be described below.

[0044] (2.1) Premise

[0045] In the present embodiment, a case where the component mounting system 100 is used in the manufacturing of electronic devices in a factory is described. A general electronic device has various circuit blocks such as a power supply circuit and a control circuit, for example. At the time of manufacturing these circuit blocks, these processes are performed in the order of a solder application process, a mounting process, and a soldering process as an example. In the solder application process, paste solder is applied (or printed) to a substrate (including a printed wiring board). In the mounting process, a component P1 (including an electronic component) is mounted (mounted) to the substrate. In the soldering process, for example, by heating the substrate in a state where the component P1 is mounted in a reflow soldering furnace, the paste solder is melted to perform soldering.

[0046] The component mounting system 100 performs a job of mounting a plurality of components P1 (electronic components) to a substrate as the object P2 in a mounting process. Thus, in the component mounting system 100, a product P3 composed of the substrate (the object P2) to which the plurality of components P1 are mounted is generated. In other words, the product P3 includes the object P2 (here, the substrate) and the plurality of components P1 mounted to the object P2.

[0047] In the present embodiment, as an example, a case where the component mounting system 100 is used in mounting of components (the components P1) based on a surface mounting technology (SMT: Surface Mount Technology) is described. That is, the components as the components P1 are surface mount devices (SMDs) and are mounted by being mounted to surfaces (mounting surfaces) of substrates as the object P2. However, the example is not restrictive and the component mounting system 100 can be used in mounting of components (the components P1) based on an insertion mounting technology (IMT: Insertion Mount Technology). In this case, the components as the components P1 are insertion mount devices having lead terminals and are mounted to surfaces (mounting surfaces) of substrates as the object P2 by being inserted into the lead terminals into holes of the substrates as the object P2.

[0048] Further, the "supply part" in the present disclosure is a site (position) in the component mounting system 100 for supplying the components P1 used in the component mounting system 100. The component mounting system 100 has a plurality of supply parts 3 and performs a mounting job using the components P1 supplied to each of the supply parts 3. For example, the supply part 3 is configured to be able to equip a tape feeder for supplying the components P1. The tape feeder is able to supply the plurality of components P1 from the supply part 3 to the component mounting system 100 by mounting a reel of a tape on which the plurality of components P1 are housed. Such a supply part 3 includes a plurality of slots into which the tape feeders are mounted and supplies the plurality of components P1 to the component mounting system 100 (the mounting machine 10) by mounting the plurality of tape feeders to the plurality of slots. In the present embodiment, as an example, it is assumed that the supply part 3 is a "table" composed of a collection of the plurality of slots. The "table" described here is an imaginary table and does not accompany a physical entity.

[0049] Hereinafter, as an example, three axes of an X-axis, a Y-axis, and a Z-axis orthogonal to each other are set, an axis parallel to a surface of the substrate as the object P2 is set as the "X-axis" and the "Y-axis", and an axis parallel to a thickness direction of the substrate is set as the "Z-axis". In particular, the "X-axis" is an axis in a direction in which a plurality of mounting machines 10 in the component mounting system 100 are arranged. Further, a side of the capturing section 41 as viewed from the substrate as the object P2 is defined as a positive direction of the Z-axis (also referred to as "upward"). Furthermore, a state as viewed from the positive direction of the Z-axis (upward) is also referred to as "plan view observation" hereinafter. The X-axis, the Y-axis, and the Z-axis are all imaginary axes, and arrows of "X", "Y", and "Z" in the drawing are merely indicated for illustration and do not accompany a physical entity. Furthermore, these directions are not intended to limit directions at the time of use of the component mounting system 100.

[0050] Further, the proposal of the "arrangement" of the components P1 according to the present disclosure includes proposals of various items related to the arrangement of the plurality of components P1 in the plurality of supply sections 3, and for example, both of a proposal of the allocation of the components P1 and a proposal of the arrangement of the components P1. The allocation of the plurality of components P1 means that the plurality of components P1 is divided into a plurality of parts, and one or more components P1 after the division is assigned to any of the plurality of supply sections 3 (the stocker in the present embodiment). That is, in the allocation, in a case where one supply section 3 is assigned with a plurality of components P1, the order of the plurality of components P1 is not specified. On the other hand, the proposal of the arrangement of the plurality of components P1 means that the plurality of components P1 is divided into a plurality of parts, one or more components P1 after the division is assigned to any of the plurality of supply sections 3 (the stocker in the present embodiment), and the order (arrangement) in each supply section 3 is specified. Thus, in a case where the supply section 3 is the "stocker" constituted by a collection of a plurality of slots as in the present embodiment, as the arrangement of the components P1, which one of the components P1 corresponds to which slot of the plurality of slots included in one supply section 3 (the stocker) is specified. That is, in the proposal of the arrangement, in a case where one supply section 3 is assigned with a plurality of components P1, the order of the plurality of components P1 is specified.

[0051] In the present embodiment, as an example, it is assumed that the proposal of the "arrangement" of the components P1 performed by the arrangement assistance method or the arrangement assistance system 20 is only the allocation of the components P1 among the proposal of the allocation of the components P1 and the proposal of the arrangement of the components P1. That is, in the arrangement assistance method or the arrangement assistance system 20 according to the present embodiment, the plurality of components P1 is divided into a plurality of parts, one or more components P1 after the division is assigned to any of the plurality of supply sections 3, and the order of the one or more components P1 after the division is not specified.

[0052] Further, the "proposal" of the configuration of the component P1 according to the present disclosure includes both a manner of outputting the result of deriving the configuration of the component P1 to a person or an external system and a manner of actually determining the configuration of the component P1 in the plurality of supply units 3 according to the result of deriving the configuration of the component P1. According to the former manner, only a proposal (suggestion) of the configuration of the component P1 is accepted in the person or the external system that receives the result of deriving the configuration of the component P1 from the configuration assistance method or the configuration assistance system 20, and it is determined whether to adopt the result of derivation. According to the latter manner, the result of deriving the configuration of the component P1 is directly adopted from the configuration assistance method or the configuration assistance system 20 to the component mounting system 100 without passing through the determination of the person or the external system.

[0053] Further, the "feature" of the supply unit 3 according to the present disclosure includes, for example, a feature related to the mounting machine 10 in which the supply unit 3 is provided. The feature related to the mounting machine 10 includes, for example, the type, performance, characteristics, or specifications of the mounting machine 10 such as the speed (maximum mounting speed), the number of the capture units 41 (the number of the nozzles), the number of the supply units 3, the type of the capture units 41, the number of the slots, the number of the mounting heads 4, and the type of the machine. The "number of the capture units 41" refers to the maximum number of the capture units 41 that can be equipped in one mounting head 4. The "type of the capture units 41" includes, for example, a suction nozzle that sucks the component P1 and a mechanical chuck that pinches (squeezes) the component P1. The "number of the slots" refers to the number of the slots in one supply unit 3 (or one mounting machine 10), in other words, the maximum number of the tape feeders that can be equipped in one supply unit 3 (or one mounting machine 10).

[0054] Further, the "speed" of the mounting machine 10 according to the present disclosure refers to the maximum mounting speed in the mounting machine 10, that is, the maximum value of the speed involved in the mounting of the component P1 in the mounting machine 10. That is, the mounting machine 10 operates so as to capture the component P1 with the capture unit 41, move the capture unit 41 in a state where the component P1 is captured, and mount the component P1 on the object P2. Therefore, for example, the speed (the maximum mounting speed) of the mounting machine 10 differs depending on the speed of capturing and releasing (that is, releasing the capture) of the component P1 in the capture unit 41 and the moving speed of the capture unit 41. In the present embodiment, with respect to the speed, for example, the speed is classified into a plurality of speed domains such as a multifunction machine (low-speed machine), a medium-speed machine, and a high-speed machine, and if the difference in the speed is small, the speed is regarded as the same speed domain.

[0055] Further, the "determination condition" according to the present disclosure is a specific condition set with respect to the time required for the generation of the product P3 in the component mounting system 100. As an example, the time (mounting time) required for the generation of the product P3 in the component mounting system 100 can become the determination condition in that the time is the longest or the shortest among the plurality of supply units 3.

[0056] (2.2) Configuration of component mounting system

[0057] Next, the configuration of the component mounting system 100 using the configuration assistance method according to the present embodiment will be described with reference to Figure 1 and Figure 2

[0058] The component mounting system 100 according to the present embodiment has, as described above, a plurality of (here, four) mounting machines 10 that constitute a mounting line. The plurality of mounting machines 10 are arranged in a row along the X axis. In distinguishing the plurality of mounting machines 10, the plurality of mounting machines 10 are each referred to as a first mounting machine 11, a second mounting machine 12, a third mounting machine 13, and a fourth mounting machine 14 in that order from the negative side of the X axis as shown in Figure 1

[0059] In the component mounting system 100 according to the present embodiment, the first mounting machine 11 is at the head of the row, and the object P2 moves through the plurality of mounting machines 10 in the order of the second mounting machine 12, the third mounting machine 13, and then the fourth mounting machine 14 that is at the end of the row. That is, the object P2 moves in the positive direction of the X axis while sequentially passing through the plurality of mounting machines 10. The component mounting system 100 installs a plurality of components PI to the object P2 with each of the mounting machines 10 during the passage of the object P2 through the plurality of mounting machines 10. Thus, the component mounting system 100 imports a substrate that is the object P2 from the first mounting machine 11 side, performs mounting of a plurality of components PI (electronic components) to the object P2 with the plurality of mounting machines 10, and on this basis, discharges a product P3 from the fourth mounting machine 14 side.

[0060] Accordingly, the component mounting system 100 can finally produce the product P3 on which a plurality of components PI are mounted by sequentially mounting the components PI with the plurality of mounting machines 10. The "mounting time" according to the present disclosure is the time required for production of the product P3 in the component mounting system 100, and is, for example, the time from the time when one object P2 is imported into the component mounting system 100 until the time when the product P3 is discharged from the component mounting system 100. That is, the time from the time point when the object P2, that is, one substrate is imported into the first mounting machine 11 until the time point when a plurality of components PI are mounted to the substrate (object P2) and the product P3 is discharged from the fourth mounting machine 14 becomes the "mounting time".

[0061] In the present embodiment, the basic configuration of each of the plurality of mounting machines 10 is common. Therefore, the configuration will be described below only for the first mounting machine 11 unless otherwise specified, but the same configuration is basically employed for the other mounting machines (the second mounting machine 12, the third mounting machine 13, and the fourth mounting machine 14) as well.

[0062] ​​The mounting machine 10 (first mounting machine 11) has at least one supply part 3 (tape feeder) and at least one mounting head 4. In the present embodiment, the mounting machine 10 has two supply parts 3. The two supply parts 3 are located at both ends in the Y-axis direction of the mounting machine 10. In addition, the mounting machine 10 has two mounting heads 4. The two mounting heads 4 are arranged to the both sides in the Y-axis direction from the center line in the Y-axis direction of the mounting machine 10 so as to correspond to the two supply parts 3 one-to-one, respectively.

[0063] That is, the mounting machine 10 has a substantially symmetrical configuration with respect to the Y-axis direction, and the mounting head 4 and the supply part 3 are arranged on both sides of the center line in the Y-axis direction, respectively. Therefore, the mounting machine 10 mounts the components P1 supplied to the two supply parts 3 by the two mounting heads 4 by individually driving the two mounting heads 4 with respect to the object P2 introduced between the two supply parts 3.

[0064] As such, in the present embodiment, although there are two mounting heads 4 in one mounting machine 10, since the supply parts 3 (tape feeders) are also provided with two, one mounting head 4 corresponds to one supply part 3. That is, in each supply part 3, there is only one corresponding mounting head 4, and the "number of mounting heads 4" included in the characteristics of the supply part 3 becomes "1".

[0065] The mounting head 4 has one or more capturing parts 41. In the present embodiment, the mounting head 4 in the first mounting machine 11 has a plurality of (for example, 16) capturing parts 41 (refer to FIG. 2). Figure 1 The mounting head 4 moves the capturing part 41 so as to approach the object P2 (substrate) in a state where the capturing part 41 has captured the component P1 (component), and mounts the component P1 to the mounting surface T21 of the object P2.

[0066] The component P1 captured by the capturing part 41 of the mounting head 4 is supplied to the supply part 3. In the present embodiment, as described above, the supply part 3 is a "tape feeder" constituted by a collection of a plurality of slots in which the tape feeders can be mounted. Therefore, in the supply part 3, a plurality of tape feeders can be mounted up to the number of slots. The mounting head 4 captures the component P1 (component) from the tape feeder with the capturing part 41 mounted to the supply part 3.

[0067] In addition, the mounting machine 10 can have a driving device, a conveying device, a control device, a communication part, and the like in addition to the above-described structure. However, the driving device, the conveying device, the control device, the communication part, and the like are not necessarily structures of the mounting machine 10. In Figure 1 and Figure 2 In the present embodiment, the mounting machine 10 has a structure in which the supply part 3 and the mounting head 4 are arranged on both sides of the center line in the Y-axis direction, and the mounting head 4 and the supply part 3 are arranged on both sides of the center line in the Y-axis direction, respectively. Therefore, the mounting machine 10 mounts the components P1 supplied to the two supply parts 3 by the two mounting heads 4 by individually driving the two mounting heads 4 with respect to the object P2 introduced between the two supply parts 3.

[0068] The driving device is a device that moves the mounting head 4. In the present embodiment, the driving device moves the mounting head 4 in the X-Y plane. The "X-Y plane" referred to here is a plane that includes the X axis and the Y axis, and is a plane that is orthogonal to the Z axis. In other words, the driving device moves the mounting head 4 in the X axis direction and the Y axis direction.

[0069] The conveying device is a device that conveys the substrate that is the object P2. The conveying device is realized by, for example, a belt conveyor or the like. The conveying device conveys the object P2 (substrate) along the X axis. The conveying device conveys the object P2 at least in the mounting space below the mounting head 4, that is, opposite the capturing portion 41 in the Z axis direction. Also, the conveying device stops the object P2 in the mounting space until the mounting of the component P1 (component) to the object P2 (substrate) by the mounting head 4 is completed.

[0070] The control device controls each portion of the component mounting system 100. The control device has a microcontroller having one or more processors and one or more memories as a main structure. That is, the functions of the control device are realized by the processor of the microcontroller executing a program recorded in the memory of the microcontroller. The program can be recorded in the memory in advance, can be provided via an electric communication line such as the Internet, or can be recorded in a non-temporary recording medium such as a memory card and provided.

[0071] The communication portion is configured to communicate with the superior system directly or indirectly via a network or a relay or the like. Thus, the mounting machine 10 can transmit and receive data with the superior system.

[0072] The mounting machine 10 configured as described above is used in a state in which the tape feeder equipped with the reel that houses a tape on which a plurality of components P1 are mounted is mounted in each of the plurality of slots in the supply portion 3. Thus, the components P1 taken out from the tape by the tape feeder are sequentially supplied to each of the plurality of slots in the supply portion 3 in this state. In this state, the mounting machine 10 performs, as a basic operation, capturing of the components P1 supplied to the supply portion 3 by the tape feeder by the capturing portion 41 of the mounting head 4 and mounting (arrangement) to a target position on the object P2. The mounting machine 10 repeatedly performs such a basic operation.

[0073] Here, if the mounting head 4 has a plurality of (as an example, 16) capturing portions 41, the mounting machine 10 can mount a plurality of components P1 by one basic operation. That is, the mounting machine 10 can mount a plurality of components P1 collectively because it can collectively capture a plurality of components P1 by a plurality of capturing portions 41 of the mounting head 4 in one basic operation. Furthermore, the mounting machine 10 having a plurality of (as an example, two) mounting heads 4 can simultaneously mount a plurality of components P1 by individually driving the plurality of mounting heads 4 with the plurality of mounting heads 4.

[0074] Further, in the present embodiment, the plurality of mounting machines 10 included in the component mounting system 100 have different characteristics as described below. Here, the first mounting machine 11 and the second mounting machine 12 have the same characteristics, and the third mounting machine 13 and the fourth mounting machine 14 each have different characteristics from the first mounting machine 11 (or the second mounting machine 12).

[0075] That is, as the mounting machines 10, since there are many kinds, performance, characteristics, or specifications of individuals, in the plurality of mounting machines 10 constituting the component mounting system 100, there are cases where the characteristics are also different from each other. Specifically, depending on the mounting machines 10, there are cases where, for example, the speed (the maximum mounting speed), the number of the capturing portions 41 (the number of the nozzles), the number of the supply portions 3, the kind of the capturing portions 41, the number of the slots, the number of the mounting heads 4, and the model, and the like are different.

[0076] In the present embodiment, as the different characteristics among the plurality of mounting machines 10 (here, four), there are the speed, the number of the capturing portions 41, the kind of the capturing portions 41, and the model, and the like. As an example, regarding the "speed", the first mounting machine 11 and the second mounting machine 12 are "high-speed machines", in contrast to which the third mounting machine 13 is a "medium-speed machine", and the fourth mounting machine 14 is a "multi-function machine". Regarding the "number of the capturing portions 41", the first mounting machine 11 and the second mounting machine 12 are "16", in contrast to which the third mounting machine 13 is "8", and the fourth mounting machine 14 is "3".

[0077] On the other hand, as the characteristics common among the plurality of mounting machines 10 (here, four), there are the number of the supply portions 3, the number of the slots, and the number of the mounting heads 4, and the like. As an example, regarding the "number of the supply portions 3", as described above, each of the mounting machines 10 is "2". Similarly, as an example, regarding the "number of the mounting heads 4", as described above, each of the mounting machines 10 is "2". Further, regarding the "number of the slots", it is assumed that each of the mounting machines 10 is "60".

[0078] Here, since the "number of the capturing portions 41" represents the number of the capturing portions 41 in one mounting head 4, if seen in units of the mounting machines 10 each having two mounting heads 4, there are twice as many capturing portions 41 as described above. For example, the number of the capturing portions 41 in the first mounting machine 11 as a whole is "32". Similarly, since the "number of the slots" represents the number of the slots in one supply portion 3, if seen in units of the mounting machines 10 each having two supply portions 3, there are twice as many slots as described above. For example, the number of the slots in the first mounting machine 11 as a whole is "120". Further, the characteristics of the mounting machines 10 as described above are sometimes different even if the models of the mounting machines 10 are the same, for example, in a case where the detailed specifications of the mounting machines 10 are different, or in a case where the performance is reduced due to aging deterioration, or the like.

[0079] As described above, in this embodiment, since the component mounting system 100 has four mounting machines 10, and each mounting machine 10 has two supply units 3, there are a total of eight supply units 3 in the component mounting system 100 as a whole. These eight supply units 3 are distinguished as follows: Figure 2 As shown, they are referred to as the first supply unit 31, the second supply unit 32, the third supply unit 33, the fourth supply unit 34, the fifth supply unit 35, the sixth supply unit 36, the seventh supply unit 37, and the eighth supply unit 38. The first supply unit 31 and the second supply unit 32 are located in the first mounting machine 11, the third supply unit 33 and the fourth supply unit 34 are located in the second mounting machine 12, the fifth supply unit 35 and the sixth supply unit 36 ​​are located in the third mounting machine 13, and the seventh supply unit 37 and the eighth supply unit 38 are located in the fourth mounting machine 14.

[0080] (2.3) Configuration of the auxiliary system

[0081] Next, refer to Figure 3 The structure of the configuration assistance system 20 involved in this embodiment will be explained.

[0082] As described above, the configuration assistance system 20 is a system that assists in determining the configuration of multiple components P1 in the multiple supply units 3 of the component mounting system 100. In this embodiment, as described above, the component mounting system 100 as a whole has eight supply units 3, namely the first supply unit 31 to the eighth supply unit 38. Therefore, the configuration assistance system 20 according to this embodiment is used to determine the configuration of the multiple components P1 in these eight supply units 3.

[0083] Configuration assistance system 20, etc. Figure 3 As shown, the configuration assistance system 20 includes an acquisition unit 21, a proposal unit 22, a determination unit 23, a reconfiguration unit 24, an output unit 25, a simulation unit 26, and a model storage unit 27. In this embodiment, the configuration assistance system 20, as described above, uses a computer system with one or more processors and one or more memories as its main structure. The functions of at least the acquisition unit 21, proposal unit 22, determination unit 23, reconfiguration unit 24, output unit 25, and simulation unit 26 in the configuration assistance system 20 are implemented by executing programs on one or more processors.

[0084] The acquisition unit 21 acquires installation data Dl. The installation data Dl is data related to the plurality of components Pl included in the product P3. That is, the installation data Dl is data related to all of the plurality of components Pl installed in the component mounting system 100. As an example, in a case where "200" components Pl are installed in the component mounting system 100, the installation data Dl contains data related to each of these "200" components Pl. The installation data Dl contains at least data for distinguishing the plurality of components Pl, for example, as to the quality, product number, specification, manufacturer, size, terminal number, terminal arrangement, and circuit constant of each of the plurality of components Pl.

[0085] The proposal unit 22 proposes the arrangement of the plurality of components Pl for the plurality of supply units 3. In the present embodiment, the proposal unit 22 uses the learned model Ml to propose the arrangement of the plurality of components Pl for the plurality of supply units 3 based on the installation data Dl so that the installation time is shortened. The learned model Ml is a model generated in correspondence with the characteristics of at least one of the plurality of supply units 3. The installation time is the time required for the generation of the product P3 in the component mounting system 100. Details of the learned model Ml are described in the section "(3.2) Learned Model".

[0086] Here, in the arrangement assistance system 20 (arrangement assistance method) related to the present embodiment, the allocation (proposal of arrangement) of the components Pl in a multi-stage manner is employed. Therefore, in the present embodiment, the proposal unit 22 contains a plurality of processing blocks so as to be able to cope with the allocation in a multi-stage manner. Specifically, the proposal unit 22 contains a primary proposal unit 221, a secondary proposal unit 222, and a tertiary proposal unit 223.

[0087] The primary proposal unit 221 proposes the arrangement of the plurality of components Pl for the plurality of primary groups Gl l, Gl2. The secondary proposal unit 222 proposes the arrangement of the plurality of components Pl for the plurality of secondary groups G21 to G24 in a case where the plurality of primary groups Gl l, Gl2 are each classified into the plurality of secondary groups G21 to G24. The plurality of secondary groups G21 to G24 each contain at least one of the plurality of supply units 3. The tertiary proposal unit 223 proposes the arrangement of the plurality of components Pl for the plurality of tertiary groups G31 to G38 in a case where the plurality of secondary groups G21 to G24 are each classified into the plurality of tertiary groups G31 to G38 (see Figure 6 ). The plurality of tertiary groups G31 to G38 each contain at least one of the plurality of supply units 3. Details of the multi-stage manner are described in the section "(3.3) Multi-stage Manner".

[0088] The determination section 23 determines a certain supply section 3 among the plurality of supply sections 3 as the target supply section in the case where the configuration of the plurality of components P1 proposed in the proposal section 22 is adopted. Here, the supply section 3 determined as the target supply section is the supply section 3 for which the time required for the generation of the product P3 in the component mounting system 100 satisfies the determination condition. That is, the determination section 23 determines the supply section 3 for which the time required for the generation of the product P3 in the component mounting system 100 satisfies the determination condition as the "target supply section". The determination of the target supply section is described in detail in the section of "(3.4) Reconfiguration".

[0089] The reconfiguration section 24 proposes the configuration of the plurality of components P1 for the target supply section and the reference supply section. Here, the reference supply section is constituted by at least one supply section 3 among the plurality of supply sections 3 other than the target supply section. Therefore, in the determination section 23, the supply section 3 serving as the "target supply section" and the supply section 3 serving as the "reference supply section" are substantially extracted from the plurality of supply sections 3. That is, the determination section 23 determines at least one of the supply sections 3 among the plurality of supply sections 3 for which the time required for the generation of the product P3 in the component mounting system 100 does not satisfy the determination condition as the "target supply section".

[0090] Then, the reconfiguration section 24 performs the reconfiguration of the plurality of components P1 with the target supply section and the reference supply section extracted (determined) among the plurality of supply sections 3 as the targets. That is, the reconfiguration section 24 proposes a new configuration instead of the configuration (allocation) of the plurality of components P1 for the target supply section and the reference supply section proposed once in the proposal section 22. In the present embodiment, the reconfiguration section 24 re-proposes the configuration of the plurality of components P1 after resetting the configuration of the plurality of components P1 for the target supply section and the reference supply section. The reconfiguration is described in detail in the section of "(3.4) Reconfiguration".

[0091] The output section 25 outputs the configuration data D2 generated in at least one of the proposal section 22 and the reconfiguration section 24. The "configuration data" in the present disclosure is data representing the configuration of the plurality of components P1 for the plurality of supply sections 3 proposed in at least one of the proposal section 22 and the reconfiguration section 24. That is, the configuration data D2 is data representing the allocation of the plurality of components P1 mounted in the component mounting system 100 to any supply section 3. As an example, in the case where "200" components P1 are mounted in the component mounting system 100, the mounting data D1 includes data for each of the "200" components P1 indicating which of the plurality of (here, eight) supply sections 3 the component P1 is determined to be allocated to.

[0092] As a manner of output of the arrangement data D2 in the output section 25, there are, for example, output to the simulation section 26, transmission to the component mounting system 100 or other systems, display, sound output, recording (writing) to a non-temporary recording medium, and printing (printing out), and the like. In the present embodiment, as an example, the output section 25 directly or indirectly outputs the arrangement data D2 to the simulation section 26. Further, in the present embodiment, as an example, the output section 25 directly or indirectly outputs (transmits) the arrangement data D2 to the component mounting system 100. Thereby, in the component mounting system 100, mounting of the plurality of components PI using the arrangement of the plurality of components PI specified in the arrangement data D2 can be performed. Further, for example, according to a manner of display or sound output, the output section 25 can output the arrangement data D2 to a person such as an operator.

[0093] The simulation section 26 simulates the action of mounting the plurality of components PI in the component mounting system 100. Here, the simulation section 26 simulates the action of the component mounting system 100 in a case where the arrangement of the plurality of components PI proposed in at least one of the proposal section 22 and the rearrangement section 24 is used. In the present embodiment, the simulation section 26 acquires the arrangement data D2 from the output section 25, and performs simulation based on the arrangement data D2. At this time, the simulation section 26 performs simulation using device data or the like that characterizes the structure of the component mounting system 100 in addition to the arrangement data D2. The "device data" mentioned here includes the features of the supply section 3, that is, features related to the mounting machine 10 provided with the supply section 3, and the like.

[0094] The simulation section 26 at least acquires the "mounting time" required for the production of the product P3 in the component mounting system 100. In the present embodiment, in particular, the simulation section 26 acquires the mounting time for each of the plurality of supply sections 3 included in the component mounting system 100. That is, the simulation section 26 acquires the mounting time required for mounting of the components PI for each of the plurality of supply sections 3 included in the component mounting system 100 as a simulation result. The simulation result in the simulation section 26 is output in an arbitrary manner, for example, from the output section 25. In the present embodiment, the simulation result in the simulation section 26 is at least output to the determination section 23, and used in the determination of the target supply section in the determination section 23.

[0095] The model storage section 27 stores the learned model Ml. The learned model Ml stored in the model storage section 27 is used at least in the proposal of the arrangement of the components P1 in the proposal section 22. In the present embodiment, the learned model Ml stored in the model storage section 27 is used not only in the proposal of the arrangement of the components P1 in the proposal section 22 but also in the proposal of the arrangement of the components P1 in the re-arrangement section 24. Details are described in the column of "(3.2) Learned Model". The learned model Ml is generated in the pre-learning. Further, the learned model Ml is a model generated in correspondence with the characteristics of at least one of the plurality of supply sections 3 in the component mounting system 100. Here, since the component mounting system 100 includes a plurality of supply sections 3 having mutually different characteristics, there are a plurality of kinds of the learned model Ml. Therefore, the model storage section 27 is configured to be able to store a plurality of (kinds of) learned models Ml.

[0096] Further, in addition to the above-described configuration, the arrangement assistance system 20 can further include a communication section and a user interface, and the like. However, the communication section and the user interface, and the like are not necessarily included in the arrangement assistance system 20. In Figure 3 In the present embodiment, as the configuration of the arrangement assistance system 20, the illustration of the structures other than the acquisition section 21, the proposal section 22, the determination section 23, the re-arrangement section 24, the output section 25, the simulation section 26, and the model storage section 27 is appropriately omitted.

[0097] The communication section is configured to communicate directly or indirectly via a network or a relay, and the like, with the component mounting system 100 and / or a superior system. Thereby, the arrangement assistance system 20 can transmit and receive data between the component mounting system 100 and / or the superior system.

[0098] The user interface includes, for example, a touch panel display, and performs acceptance of the operation of the user and presentation (display) of information to the user. The user interface is not limited to the touch panel display, and can include, for example, a keyboard, a pointing device, a mechanical switch, a gesture sensor, and the like. Further, the user interface can have a sound input / output section instead of or in addition to the touch panel display.

[0099] Further, the arrangement assistance system 20 according to the present embodiment, as described above, constitutes the work system 200 together with the component mounting system 100. That is, the work system 200 according to the present embodiment, as described above, includes the arrangement assistance system 20 and the component mounting system 100. The component mounting system 100 is a system that uses the arrangement of the plurality of components P1 proposed in the arrangement assistance system 20 and generates the product P3. Figure 3 The arrangement assistance system 20 and the component mounting system 100. The component mounting system 100 is a system that uses the arrangement of the plurality of components P1 proposed in the arrangement assistance system 20 and generates the product P3.

[0100] (3) Arrangement assistance method

[0101] The configuration assistance method according to the present embodiment will be described in more detail below. In the present embodiment, the configuration assistance method employs the three functions of the proposal of the configuration using the learned model Ml, the allocation of the components P1 in the multi-stage manner, and the reconfiguration as described above. Therefore, the configuration assistance method according to the present embodiment will be described below in four parts of the basic manner, the proposal of the configuration using the learned model Ml, the allocation of the components P1 in the multi-stage manner, and the reconfiguration.

[0102] Further, the following will be described as an example assuming a case where 240 components P1 are allocated to the following eight supply portions 3. That is, in the present embodiment, the component mounting system 100 is provided with the first mounting machine 11, the second mounting machine 12, the third mounting machine 13, and the fourth mounting machine 14, a total of four mounting machines 10, as described above. Further, since each of the four mounting machines 10 has two supply portions 3, there are a total of eight supply portions 3 as the allocation destinations of the plurality of components P1 (here, 240 components) in the component mounting system 100 as a whole.

[0103] Here, it is assumed that both the first mounting machine 11 and the second mounting machine 12 have the feature that the number of the capturing portions 41 is "16". Therefore, the first supply portion 31 and the second supply portion 32 provided in the first mounting machine 11, and the third supply portion 33 and the fourth supply portion 34 provided in the second mounting machine 12 each have the feature that the number of the capturing portions 41 is "16". On the other hand, it is assumed that the third mounting machine 13 has the feature that the number of the capturing portions 41 is "8". Therefore, the fifth supply portion 35 and the sixth supply portion 36 provided in the third mounting machine 13 each have the feature that the number of the capturing portions 41 is "8". Further, it is assumed that the fourth mounting machine 14 has the feature that the number of the capturing portions 41 is "3". Therefore, the seventh supply portion 37 and the eighth supply portion 38 provided in the fourth mounting machine 14 each have the feature that the number of the capturing portions 41 is "3".

[0104] However, these conditions are only for illustrating one specific example of the configuration assistance method, and are not intended to limit the range of application of the configuration assistance method.

[0105] (3.1) Basic Manner

[0106] First, the basic manner of the configuration assistance method according to the present embodiment will be described with reference to A of FIG. 10, B of FIG. 11, and C of FIG. 12. Figure 4 A of FIG. 10 and B of FIG. 11 are conceptual diagrams showing the proposal of the configuration of the plurality of components P1 in the plurality of supply portions 3 based on the configuration assistance method. Figure 4 C of FIG. 12 is a conceptual diagram showing the proposal of the configuration of the plurality of components P1 in the plurality of supply portions 3 based on the configuration assistance method. Figure 5 A of FIG. 10 and B of FIG. 11 are conceptual diagrams showing the proposal of the configuration of the plurality of components P1 in the plurality of supply portions 3 based on the configuration assistance method. Figure 4 A of FIG. 10 and B of FIG. 11 are conceptual diagrams showing the proposal of the configuration of the plurality of components P1 in the plurality of supply portions 3 based on the configuration assistance method. Figure 4 A of FIG. 10 and B of FIG. 11 are conceptual diagrams showing the proposal of the configuration of the plurality of components P1 in the plurality of supply portions 3 based on the configuration assistance method.

[0107] As in this embodiment, in a component mounting system 100 having multiple (here, eight) supply units 3, there are many configuration patterns for the multiple components P1 in the multiple supply units 3. Particularly in this embodiment, as described above, since the number of slots in each supply unit 3 is "60", the component mounting system 100 as a whole has 480 (=60×8) slots. Therefore, the component mounting system 100 can mount a maximum of 480 components P1. If the actual number of mounted components P1 becomes several hundred, the configuration patterns of the multiple components P1 in the multiple supply units 3 become enormous. Moreover, depending on the configuration of the multiple components P1 in the multiple supply units 3, the installation time required to generate the product P3 in the component mounting system 100 varies significantly.

[0108] That is, even if the component mounting system 100 has the same structure, if the configurations of the multiple components P1 in the multiple supply units 3 are different, the mounting machine 10 used to install each component P1 will vary, and the installation time required for each component P1 will vary significantly. Therefore, even if the installation time required to generate one product P3 is shortened, it is very difficult to find a suitable configuration pattern for the multiple components P1 from a large number of patterns. Therefore, the configuration assistance method according to this embodiment can find a suitable configuration more easily (in a shorter time) by assisting in the operation of determining the configuration of the multiple components P1 in the multiple supply units 3 in the component mounting system 100.

[0109] Here, in the configuration assistance method according to this embodiment, as described above, the proposal for the "configuration" of component P1 is only the allocation of component P1 among the proposals for the distribution and arrangement of component P1. That is, in this embodiment, multiple components P1 are divided into multiple parts, and one or more of the divided components P1 are assigned to any one of the multiple supply units 3, without specifying the order of the one or more divided components P1.

[0110] That is, the configuration assistance method involved in this embodiment is as follows: Figure 4 A and Figure 4 As shown in Figure B, the basic method involves distributing multiple unconfigured components P1 to two or more supply units 3. Figure 4 A and Figure 4 In B, the unconfigured space Sp0, marked "unconfigured," is a hypothetical space that symbolically represents the state of not being allocated to any supply unit 3, i.e., the unconfigured state. That is, in Figure 4 In A, component P1, which exists in the unallocated space Sp0, is in a state where it is not assigned to either supply unit 3. On the other hand, in Figure 4 A and Figure 4In B of FIG. 10, the space labeled as "supply part" is an imaginary space that schematically represents a state in which the parts P1 are assigned to any of the supply parts 3, i.e., a state of completion of arrangement. That is, in B of FIG. 10, the parts P1 existing in the space labeled with reference numeral "31" are in a state of having been assigned to the first supply part 31. Similarly, in B of FIG. 11, the parts P1 existing in the space labeled with reference numeral "32" are in a state of having been assigned to the second supply part 32. Figure 4 In B of FIG. 10, the parts P1 existing in the space labeled with reference numeral "31" are in a state of having been assigned to the first supply part 31. Similarly, in B of FIG. 11, the parts P1 existing in the space labeled with reference numeral "32" are in a state of having been assigned to the second supply part 32. Figure 4 In B of FIG. 10, the parts P1 existing in the space labeled with reference numeral "31" are in a state of having been assigned to the first supply part 31. Similarly, in B of FIG. 11, the parts P1 existing in the space labeled with reference numeral "32" are in a state of having been assigned to the second supply part 32.

[0111] The arrangement assistance method according to the present embodiment is such that, as shown in A of FIG. 12, all of the plurality of parts P1 to be mounted in the component mounting system 100 are set to an unarranged state as an initial state. That is, in the arrangement assistance method, first, by setting all of the plurality of parts P1 to a state of not being assigned to any of the supply parts 3, as shown in A of FIG. 12, an initial state is achieved in which all of the plurality of parts P1 exist in the unarranged space SpO. Figure 4 In B of FIG. 10, the parts P1 existing in the space labeled with reference numeral "31" are in a state of having been assigned to the first supply part 31. Similarly, in B of FIG. 11, the parts P1 existing in the space labeled with reference numeral "32" are in a state of having been assigned to the second supply part 32. Figure 4 In B of FIG. 10, the parts P1 existing in the space labeled with reference numeral "31" are in a state of having been assigned to the first supply part 31. Similarly, in B of FIG. 11, the parts P1 existing in the space labeled with reference numeral "32" are in a state of having been assigned to the second supply part 32.

[0112] Then, according to the arrangement assistance method, the processing based on the basic mode is completed in a state in which all of the plurality of parts P1 to be mounted in the component mounting system 100 are assigned to any of the supply parts 3, i.e., in a state in which there are no parts P1 existing in the unarranged space SpO. Figure 4 In B of FIG. 10, the parts P1 existing in the space labeled with reference numeral "31" are in a state of having been assigned to the first supply part 31. Similarly, in B of FIG. 11, the parts P1 existing in the space labeled with reference numeral "32" are in a state of having been assigned to the second supply part 32.

[0113] Specifically, for example, the allocation of multiple components P1 is performed by establishing a one-to-one correspondence between the component identification information used to identify multiple components P1 and the supply department identification information used to identify multiple supply departments 3. As an example, for a component P1 that is not allocated to any supply department 3, the supply department identification information is not established in correspondence with the component identification information, or the supply department identification information corresponding to the component identification information is null. Furthermore, for a component P1 allocated to the first supply department 31, the supply department identification information of the first supply department 31 is established in correspondence with the component identification information. Then, based on the completion of the correspondence between the component identification information and the supply department identification information for all multiple components P1, a state is achieved where all multiple components P1 are allocated to any supply department 3. The data representing the correspondence between the component identification information and the supply department identification information in the state where all multiple components P1 are allocated becomes configuration data D2. That is, configuration data D2 becomes data representing the allocation to any supply department 3 through the correspondence between the complete representation of multiple components P1 and the supply department identification information.

[0114] In the configuration assistance method according to this embodiment, a learned model M1 is used in the proposal of the configuration of component P1 in such a basic manner. That is, in the basic manner of the configuration assistance method, the learned model M1 is used to propose the configuration of multiple components P1 for multiple supply units 3. The learned model M1 is a model generated by establishing a correspondence with the features of at least one of the multiple supply units 3. In the configuration assistance method according to this embodiment, the learned model M1 is used to propose the configuration of multiple components P1 for multiple supply units 3, so that the installation time required for the generation of the product P3 in the component installation system 100 is shortened. Details are explained in the column "(3.2) Learned Model", and the learned model M1 is generated by reinforcement learning.

[0115] Furthermore, the configuration assistance method involved in this embodiment is as follows: Figure 5 As shown, the system is broadly divided into a processing section S100 for temporary configuration and a processing section S200 for reconfiguration. Furthermore, in both the processing section S100 for temporary configuration and the processing section S200 for reconfiguration, the configuration assistance method proposes the allocation of multiple components P1 in the basic manner described above. That is, in this embodiment, in both the processing section S100 for temporary configuration and the processing section S200 for reconfiguration, the learned model M1 is used.

[0116] That is, in the processing section S100 for temporary configuration, the plurality of components P1 are temporarily allocated to the plurality of supply sections 3. Among them, in a case where at least a part of the components P1 are allocated to an inappropriate supply section 3, there is a possibility that a bad situation such as a lengthening of mounting time in the component mounting system 100 is caused. Therefore, in the processing section S200 for reconfiguration, by re-allocating the plurality of components P1 which are temporarily allocated, a more appropriate configuration (allocation) is proposed.

[0117] Further, in the processing section S100 for temporary configuration, when the plurality of components P1 are allocated to the plurality of supply sections 3, if the number of supply sections 3 increases, the search space for reinforcement learning of the learned model M1 becomes large, and the generation of the learned model M1 becomes difficult. Therefore, the configuration assistance method according to the present embodiment adopts a multi-stage manner of allocation of components P1 in the processing section S100 for temporary configuration. That is, according to the multi-stage manner of allocation of components P1, in each stage, for example, even if the plurality of components P1 are allocated to 2 groups, the plurality of components P1 can be finally allocated to 4 or more groups. As a result, in the allocation in each stage, it is possible to narrow the search space for reinforcement learning of the learned model M1 while using the learned model M1.

[0118] As described above, according to the configuration assistance method according to the present embodiment, for example, without the help of a skilled person or the like, it is possible to determine the configuration of the plurality of components P1 in the plurality of supply sections 3, and it is possible to give a proposal of an improved configuration of components P1.

[0119] Further, Figure 5 The flowchart shown is only an example, and the order of processing can be appropriately changed, and processing can be appropriately added or deleted.

[0120] (3.2) Learned Model

[0121] Next, the proposal of the configuration of the plurality of components P1 using the learned model M1 among the configuration assistance method according to the present embodiment will be described in more detail with reference to Figure 5 and Figure 6

[0122] The configuration assistance method has a step of acquiring and a step of proposing. The step of acquiring is a step of acquiring mounting data D1, and corresponds to Figure 5 ​The process S101 of the flowchart shown. The acquisition step is performed by the acquisition section 21 of the configuration assistance system 20. The installation data D1 is data related to the plurality of components P1 contained in the product P3. The proposal step is a step of proposing a configuration of the plurality of components P1 for the plurality of supply sections 3 so as to shorten the installation time, using the learned model M1, from the installation data D1. The proposal step is performed by the proposal section 22 of the configuration assistance system 20. In the present embodiment, since the allocation of the components P1 in the multi-stage manner is adopted, in the Figure 5 In the flowchart shown, the processes S102 to S10m of the allocation of the "1st stage" to the "Nth stage" correspond to the proposal step.

[0123] In the present embodiment, the generation (pre-learning) of the learned model M1 is performed in the configuration assistance system 20. Further, as described above, the reinforcement learning is used in the generation of the learned model M1. That is, the configuration assistance system 20 utilizes the proposal section 22 as a learner of the reinforcement learning, for example. The "reinforcement learning" of the present disclosure is one approach of a machine learning technique, which is a framework of automatically obtaining a rule from data.

[0124] In the machine learning technique, as an approach widely used differently from the "reinforcement learning", there is "teacher learning". The "teacher learning" is an approach of learning based on data in which a numerical value to be a learning target is clearly defined. Therefore, in the "teacher learning", a large amount of data (learning data) in which a clear target is specified is required at the time of learning. However, in the technical field of the component installation system 100, as for the configuration of the plurality of components P1 in the plurality of supply sections 3, the numerical value to be a target is not clear, and furthermore, it is difficult to collect a large amount of learning data for learning.

[0125] On the contrary, the "reinforcement learning" is an approach of performing an "action" in a certain "environment", observing a "state" changed as a result of the "action", and giving a high "reward" to an "action" that can obtain a good result. Moreover, in the "reinforcement learning", a selection method of learning an optimal "action" that maximizes the "reward" through this series of "actions" is learned. Therefore, in the "reinforcement learning", it is not necessary to prepare learning data in which a clear target is specified as in the "teacher learning", and it is possible to generate a learned model M1 of a selection method of learning an optimal "action". That is, even in a case where the solution space is too large and the actual correct answer is not clear, the "reinforcement learning" can learn the "action" while evaluating the "action" from a series of rewards observed by repeating trial and error with respect to the "environment" given.

[0126] Therefore, reinforcement learning is particularly effective in generating a learning completed model Ml in a situation where a correct answer is not clear and optimization of a large combination is required, such as in the proposal of a configuration of a plurality of components P1 in a plurality of supply sections 3, like the learning completed model Ml.

[0127] In more detail, in reinforcement learning, an installation time is calculated for a case where a certain configuration is adopted for a plurality of components P1, and how close this installation time is to an ideal installation time (an installation time on the specifications of the installation machine 10) is set as a "reward". In the present embodiment, as an example, the installation time at this time is calculated in the simulation section 26. In reinforcement learning, the larger the search space, the more the number of times of trial and error is repeated in order to obtain a good "reward", and the more time-consuming the search for an optimal solution. Therefore, in the configuration assistance method according to the present embodiment, in order to reduce the size of the search space in reinforcement learning, the allocation of components P1 in a multi-stage manner is employed, and details regarding the multi-stage manner are described in the column of "(3.3) Multi-stage manner".

[0128] In addition, in the component mounting system 100, the characteristics of the installation machine 10 and the number of installation machines, and the types and the number of components P1 to be mounted, and the like differ, for example, depending on the specifications of the product P3. Among these, if the reinforcement learning is performed every time to generate a learning completed model Ml in coordination with the product P3, it can take time from the time when the specifications of the product P3 are decided until the time when the learning completed model Ml is generated. Therefore, in the present embodiment, the learning completed model Ml is generated by "pre-learning" in which learning is performed before the specifications of the product P3 are decided. Thus, in the configuration assistance method according to the present embodiment, if the specifications of the product P3 are decided, the learning completed model Ml generated in the pre-learning can be used to immediately start the proposal of a configuration of components P1.

[0129] In addition, in the present embodiment, the learner (for example, the proposal section 22) creates configuration data D2 in the algorithm of reinforcement learning, and outputs the created configuration data D2 from the output section 25 to the simulation section 26. Thus, the simulation section 26 performs simulation based on the configuration data D2, and calculates an "installation time". The learner (for example, the proposal section 22) converts the installation time thus calculated into a ratio with respect to an ideal installation time, and performs reinforcement learning using the calculated ratio as a "reward". Then, reinforcement learning is performed by repeating the above series of processes many times in order to obtain a better "reward". In the present embodiment, as an example, in order to perform reinforcement learning, deep reinforcement learning (DQN: Deep Q-Network) that adds the performance of feature extraction of deep learning, or the like is used.

[0130] Further, in the present embodiment, the learned model Ml is a model generated in correspondence with the characteristics of at least one of the plurality of supply parts 3 in the component mounting system 100. That is, the characteristics of the supply parts 3 are reflected in the learned model Ml, and the learned model Ml is generated for each of the characteristics of the supply parts 3. Therefore, if the component mounting system 100 includes a plurality of supply parts 3 having mutually different characteristics, a plurality of types of learned models Ml are generated.

[0131] In particular, in the present embodiment, the learned model Ml is made to correspond to the characteristics of the supply parts 3 that are destinations of allocation (assignment) of the component P1 by using a proposal of a configuration of the component P1 that utilizes the learned model Ml. Therefore, for example as shown in Figure 6 the learned model Ml is made to correspond to the characteristics of the supply parts 3 that are destinations of allocation (assignment) of the component P1 by using a proposal of a configuration of the component P1 that utilizes the learned model Ml. Therefore, for example as shown in Figure 6 In the column of "(3.3) Multi-stage method", it is explained how the learned models Ml 1 to Ml 7 are used. In the present disclosure, in the case where these plurality of learned models Ml 1 to Ml 7 are not particularly distinguished, each of the plurality of learned models Ml 1 to Ml 7 is simply referred to as "learned model Ml".

[0132] Here, for example, in the case where the two supply parts 3 that are destinations of allocation have the same characteristics (let's call them "first characteristics"), the learned model Ml is generated in correspondence with the first characteristics. That is, the learned model Ml includes a model generated in correspondence with the characteristics (first characteristics) of one of the plurality of supply parts 3. As an example, in the case where the two supply parts 3 that are destinations of allocation both have characteristics in which the number of the capturing parts 41 is "16", the learned model Ml for allocating the component P1 reflects the characteristics in which the number of the capturing parts 41 is "16".

[0133] On the other hand, for example, in the case where the two supply parts 3 that are destinations of allocation have mutually different characteristics (let's call them "first characteristics" and "second characteristics"), the learned model Ml is generated in correspondence with both the first characteristics and the second characteristics. That is, the learned model Ml includes a model generated in correspondence with the characteristics of two or more of the plurality of supply parts 3. As an example, in the case where the two supply parts 3 that are destinations of allocation respectively have characteristics in which the number of the capturing parts 41 is "16" or "8", the learned model Ml for allocating the component P1 reflects the two characteristics in which the number of the capturing parts 41 is "16" and "8".

[0134] Further, in a case where the features of the plurality of supply parts 3 are classified into one or more feature groups, the learned model Ml includes a model generated in correspondence with one or more feature groups. For example, with respect to the speed of the mounting machine 10 (the maximum mounting speed), for example, by being classified into a plurality of speed domains such as a multifunction machine (low speed machine), a medium speed machine, and a high speed machine, if the difference in speed is small, all are set to "high speed machine" or the like, and can be regarded as the same speed domain. That is, if the feature of the supply part 3 is the "speed" of the mounting machine 10, the "speed domain" of the multifunction machine (low speed machine), the medium speed machine, and the high speed machine becomes a feature group including a plurality of features (speeds). In this way, in a case where a feature group including a plurality of features different from each other is set, the learned model Ml also includes a model generated in correspondence with a feature group, not in correspondence with each feature. Since the feature group is constituted by a collection of a plurality of features, the learned model Ml generated in correspondence with a feature group also corresponds to a learned model Ml generated in correspondence with the feature of at least one supply part 3.

[0135] Further, the configuration assistance method according to the present embodiment also has an update step of updating the learned model Ml. That is, the learned model Ml generated by machine learning (reinforcement learning in the present embodiment) is not fixed, and can be appropriately updated by the update step. Specifically, the learner (for example, the proposal part 22) periodically or irregularly updates the learned model Ml stored in the model storage part 27. The update of the learned model Ml can be achieved, for example, by transfer learning that utilizes past learned knowledge in current learning, or by replacement with a new learned model Ml. If the update of the learned model Ml is possible, a suitable learned model Ml corresponding to the requirements of the user can also be generated at the stage of use of the configuration assistance method (the configuration assistance system 20).

[0136] Further, in the present embodiment, the learned model Ml includes a model generated in correspondence with information related to the product P3 generated by the component mounting system 100. The information related to the product P3 includes, for example, the technical field to which the product P3 belongs, the batch number of the product P3, or the price range of the product P3, and the like. The component mounting system 100 is used, for example, in the generation of the product P3 in various technical fields such as the technical field of electronic equipment or the technical field of automobiles. Therefore, according to matters inherent to each technical field (industry), even if the same product P3, the optimal configuration of the component P1 differs. Therefore, in the present embodiment, the learned model Ml is also generated in correspondence with the information related to the product P3, and is also made to reflect not only the features of at least one supply part 3, but also matters inherent to the product P3.

[0137] Further, in the arrangement assistance method according to the present embodiment, in the arrangement of the plurality of components P1 with respect to the plurality of supply parts 3, a restriction condition that restricts arrangement of a specific component P1 with respect to a specific supply part 3 is attached. That is, depending on the supply part 3, there are cases where arrangement of a specific component P1 cannot be performed due to a restriction on the specifications of the mounting machine 10 or a restriction on the size of the component P1, or the like. In order to cope with such cases, the restriction condition can be attached. By attaching the restriction condition, with respect to the specific component P1 for which arrangement to the specific supply part 3 is restricted in the restriction condition, the specific supply part 3 is excluded from the allocation target. As an example, with respect to a supply part where a tape feeder cannot be mounted and only a tray can be provided, arrangement of a component P1 that is supplied by a tape feeder can be restricted in the restriction condition.

[0138] Further, in the present embodiment, the determination of the arrangement of the specific component P1 with respect to the specific supply part 3 according to the restriction condition is performed separately from the proposal of the arrangement of the plurality of components P1 with respect to the plurality of supply parts 3 using the learned model M1. That is, the restriction of the arrangement of the component P1 according to the restriction condition is performed, for example, before or after the proposal of the arrangement of the component P1 using the learned model M1. As an example, if the restriction of the arrangement of the component P1 according to the restriction condition is performed before the proposal of the arrangement of the component P1 using the learned model M1, the number of options for deriving a suitable arrangement of the plurality of components P1 can be reduced.

[0139] As described above, in the arrangement assistance method according to the present embodiment, in the arrangement of the plurality of components P1, the arrangement of the plurality of components P1 with respect to the plurality of supply parts 3 is proposed from the mounting data D1 using the learned model M1 so that the mounting time is shortened (proposal step). Therefore, in the proposal step, instead of the arrangement being uniquely determined by the proposal, a suitable arrangement can be more simply found out by, for example, a skill of implementing the "determination method" of the arrangement by a skilled person using the learned model M1.

[0140] (3.3) Multi-stage method

[0141] Next, the multi-stage method of the arrangement of the components P1 in the arrangement assistance method according to the present embodiment will be described in more detail with reference to Figure 5 and Figure 6

[0142] The arrangement assistance method has a primary proposal step and a secondary proposal step. The primary proposal step is a step of proposing arrangement (allocation) of a plurality of components P1 with respect to a plurality of primary groups G11, G12, and corresponds to Figure 5 ​The processing S102 of the flowchart shown. The first proposal step is executed by the first proposal section 221 of the proposal section 22 in the configuration assistance system 20. The second proposal step is a step of proposing the arrangement of the plurality of components P1 for the plurality of second groups G21 to G24 after the first proposal step, and corresponds to Figure 5 The processing S103 of the flowchart shown. The second proposal step is executed by the second proposal section 222 of the proposal section 22 in the configuration assistance system 20. That is, after the first proposal step, the second proposal step is executed to propose the arrangement of the plurality of components P1 for the plurality of second groups G21 to G24. Figure 5 In the flowchart shown, the processing S102 to S10m corresponding to the allocation of the "1st stage" to the "Nth stage" of the proposal step includes the first proposal step and the second proposal step.

[0143] In this embodiment, the configuration assistance method also has a third proposal step. The third proposal step is a step of proposing the arrangement of the plurality of components P1 for the plurality of third groups G31 to G38 in the case where the plurality of second groups G21 to G24 are each classified into the plurality of third groups G31 to G38 after the second proposal step. The plurality of third groups G31 to G38 each include at least one supply section 3 among the plurality of supply sections 3. In summary, according to the third proposal step, the plurality of second groups G21 to G24 are each classified into the plurality of third groups G31 to G38 which are more finely divided, and the arrangement of the plurality of components P1 for the plurality of third groups G31 to G38 is proposed.

[0144] That is, in this embodiment, as shown in Figure 5 As shown, the arrangement of the plurality of components P1 is not achieved in a 2-stage process, but in a process of N stages (here, N is a natural number of "3" or more) set hierarchically. Therefore, after the allocation of the 2nd stage (S103) as the second proposal step is performed, more finely divided allocation can be achieved by performing allocation of the 3rd stage or later. In particular, in this embodiment, since it is assumed that the plurality of components P1 are allocated to 2 groups at each stage, and finally to 8 supply sections 3, the allocation is performed in 3 stages. Therefore, the third proposal step corresponds to the final stage in the proposal step, that is, Figure 5 The processing S10m (here, m is "4") of the flowchart shown. The third proposal step is executed by the third proposal section 223 of the proposal section 22 in the configuration assistance system 20.

[0145] Figure 6is a diagram showing an example of a schematic representation of the allocation of components P1 in a multi-stage manner. In the present embodiment, the proposal of the arrangement of the plurality of components P1 is divided into at least a primary proposal step of arranging the components P1 in a plurality of primary groups G11, G12 and a secondary proposal step of arranging the components P1 in a plurality of secondary groups G21 to G24 in more detail. Thus, since the arrangement of the plurality of components P1 is achieved not by a 1-stage process but by a multi-stage process set hierarchically, the options for deriving a suitable arrangement of the plurality of components P1 can be reduced in each stage.

[0146] In Figure 6 , the plurality of primary groups G11, G12 corresponds to the groups after classification in the case where the unarranged space Sp0 in which the plurality of components P1 in the unarranged state in which none of the supply portions 3 is allocated is classified into 2 or more groups. The plurality of primary groups G11, G12 each includes at least one supply portion 3 among the plurality of supply portions 3.

[0147] Specifically, as Figure 6 indicated, the primary group G11 (labeled as "Group 1" in the figure) includes the 1st supply portion 31, the 2nd supply portion 32, the 3rd supply portion 33, and the 4th supply portion 34. The primary group G12 (labeled as "Group 2" in the figure) includes the 5th supply portion 35, the 6th supply portion 36, the 7th supply portion 37, and the 8th supply portion 38.

[0148] In the primary proposal step, the plurality of components P1 in the unarranged state present in the unarranged space Sp0 is allocated to the plurality of primary groups G11, G12. Thus, the plurality of (here, 240) components P1 is allocated to any of the plurality of primary groups G11, G12.

[0149] Further, in Figure 6 , the plurality of secondary groups G21 to G24 corresponds to the groups after classification in the case where each of the plurality of primary groups G11, G12 is further classified into 2 or more groups. Here, a case is assumed in which each of the 2 primary groups G11, G12 is further classified into 2 secondary groups and a total of 4 secondary groups G21 to G24 are generated. The plurality of secondary groups G21 to G24 each includes at least one supply portion 3 among the plurality of supply portions 3.

[0150] Specifically, as Figure 6As shown, the secondary group G21 (labeled as "Group 1_1" in the figure) and the secondary group G22 (labeled as "Group 1_2" in the figure) are subordinates of the primary group G11. In other words, the primary group G11 is classified into 2 secondary groups G21, G22. The secondary group G23 (labeled as "Group 2_1" in the figure) and the secondary group G24 (labeled as "Group 2_2" in the figure) are subordinates of the primary group G12. In other words, the primary group G12 is classified into 2 secondary groups G23, G24. Also, the secondary group G21 includes the 1st supply part 31 and the 2nd supply part 32, and the secondary group G22 includes the 3rd supply part 33 and the 4th supply part 34. The secondary group G23 includes the 5th supply part 35 and the 6th supply part 36, and the secondary group G24 includes the 7th supply part 37 and the 8th supply part 38.

[0151] The secondary proposal step allocates the plurality of components P1 included in the primary group G11 to the plurality of secondary groups G21, G22, and allocates the plurality of components P1 included in the primary group G12 to the plurality of secondary groups G23, G24. Thereby, the plurality of (here, 240) components P1 are allocated to any one of the plurality of secondary groups G21 to G24.

[0152] Further, in Figure 6 , the plurality of tertiary groups G31 to G38 correspond to the classified groups in the case where each of the plurality of secondary groups G21 to G24 is further classified into 2 or more groups. Here, a case where each of the 4 secondary groups G21 to G24 is further classified into 2 tertiary groups and a total of 8 tertiary groups G31 to G38 are generated is assumed. Each of the plurality of tertiary groups G31 to G38 respectively includes at least one supply part 3 among the plurality of supply parts 3.

[0153] Specifically, as shown in Figure 6 , the tertiary group G31 and the tertiary group G32 are subordinates of the secondary group G21, and the tertiary group G33 and the tertiary group G34 are subordinates of the secondary group G22. In other words, the secondary group G21 is classified into 2 tertiary groups G31, G32, and the secondary group G22 is classified into 2 tertiary groups G33, G34. The tertiary group G35 and the tertiary group G36 are subordinates of the secondary group G23, and the tertiary group G37 and the tertiary group G38 are subordinates of the secondary group G24. In other words, the secondary group G23 is classified into 2 tertiary groups G35, G36, and the secondary group G24 is classified into 2 tertiary groups G37, G38. Also, in Figure 6In the example, since multiple cubic groups G31 to G38 become the final level of the multi-level method, each of the multiple cubic groups G31 to G38 contains one supply unit 3. That is, in this embodiment, since the final allocation to the component P1 of the eight supply units 3 is envisioned, the multiple (here, eight) cubic groups G31 to G38 that become the final level correspond one-to-one with the first to eighth supply units 31 to 38.

[0154] In the three proposal steps, multiple components P1 contained in secondary group G21 are allocated to multiple tertiary groups G31 and G32, and multiple components P1 contained in secondary group G22 are allocated to multiple tertiary groups G33 and G34. Furthermore, in the three proposal steps, multiple components P1 contained in secondary group G23 are allocated to multiple tertiary groups G35 and G36, and multiple components P1 contained in secondary group G24 are allocated to multiple tertiary groups G37 and G38. Thus, multiple (here, 240) components P1 are allocated to any one of the multiple tertiary groups G31 to G38, namely, the first to eighth supply units 31 to 38.

[0155] Here, in the configuration assistance method involved in this embodiment, such as Figure 6 As shown, the learned model M1 is used during the allocation at each stage. That is, the learned model M1 is used to propose the configuration of multiple components P1 in at least one of the first proposal step and the second proposal step. The learned model M1, as also explained in the column “(3.2) Learned Model”, is a model generated by establishing a correspondence with the characteristics of at least one of the multiple supply units 3. In this embodiment, the learned model M1 is used in all of the first proposal step, the second proposal step, and the third proposal step.

[0156] Specifically, in the primary proposal step of assigning multiple components P1 to multiple primary groups G11 and G12, the learned model M11 is used to propose the configuration of multiple components P1 in the multiple primary groups G11 and G12 based on the installation data D1, thereby shortening the installation time. In the secondary proposal step of assigning multiple components P1 to multiple secondary groups G21 to G24, the learned models M12 and M13 are used to propose the configuration of multiple components P1 in the multiple secondary groups G21 to G24 based on the installation data D1, thereby shortening the installation time. In the tertiary proposal step of assigning multiple components P1 to multiple tertiary groups G31 to G38, the learned models M14 to M17 are used to propose the configuration of multiple components P1 in the multiple tertiary groups G31 to G38 based on the installation data D1, thereby reducing the installation time.

[0157] Here, as from Figure 6As is also clear, the learning completed model Ml used differs depending on which of the first proposal step, the second proposal step, and the third proposal step the stage is. That is, in the present embodiment, as described above, the various learning completed models Ml 1 to Ml 7 are used depending on the allocation destination of the component P 1. For example, the learning completed model Ml 1 used in the first proposal step and the learning completed models Ml 2, Ml 3 used in the second proposal step are different. As a result, in the present embodiment, the algorithm used to propose the arrangement of the plurality of components P 1 differs between the first proposal step and the second proposal step. Here, by the "algorithm differs", in the present embodiment, it means that the learning completed model Ml used differs. Furthermore, in the present embodiment, in the allocation at each stage, the various learning completed models Ml 1 to Ml 7 are used depending on the allocation destination of the component P 1. For example, in the second proposal step, the learning completed model Ml 2 is used in the allocation of the plurality of components P 1 contained in the first group G 11 to the plurality of second groups G 21, G 22. In contrast to this, in the second proposal step, the learning completed model Ml 3 is used in the allocation of the plurality of components P 1 contained in the second group G 12 to the plurality of second groups G 23, G 24. Similarly, in the third proposal step, the learning completed model Ml 4 is used in the allocation of the plurality of components P 1 contained in the second group G 21 to the plurality of third groups G 31, G 32. In contrast to this, in the third proposal step, the learning completed model Ml 7 is used in the allocation of the plurality of components P 1 contained in the second group G 24 to the plurality of third groups G 37, G 38.

[0158] Furthermore, in the present embodiment, in the allocation at each stage, the various learning completed models Ml 1 to Ml 7 are used depending on the allocation destination of the component P 1. For example, in the second proposal step, the learning completed model Ml 2 is used in the allocation of the plurality of components P 1 contained in the first group G 11 to the plurality of second groups G 21, G 22. In contrast to this, in the second proposal step, the learning completed model Ml 3 is used in the allocation of the plurality of components P 1 contained in the second group G 12 to the plurality of second groups G 23, G 24. Similarly, in the third proposal step, the learning completed model Ml 4 is used in the allocation of the plurality of components P 1 contained in the second group G 21 to the plurality of third groups G 31, G 32. In contrast to this, in the third proposal step, the learning completed model Ml 7 is used in the allocation of the plurality of components P 1 contained in the second group G 24 to the plurality of third groups G 37, G 38.

[0159] As a result, in the arrangement assistance method related to the present embodiment, as shown in FIG. 7, the 7 learning completed models Ml 1 to Ml 7 are used. Figure 6

[0160] Specifically, the learning completed model Ml 1 used in the first proposal step is a model for allocating the plurality of components P 1 to be allocated to the first to eighth supply portions 31 to 38 to the two first groups G 11, G 12. Regarding the learning completed model Ml 1, the first to fourth supply portions 31 to 34 in which the number of the capturing portions 41 included in the allocation destination is "16", the fifth and sixth supply portions 35, 36 in which the number of the capturing portions 41 is "8", and the seventh and eighth supply portions 37, 38 in which the number of the capturing portions 41 is "3". Therefore, the learning completed model Ml 1 is a model generated so as to reflect the three features that the number of the capturing portions 41 is "16", "8", and "3", and to correspond to these three features.

[0161] ​The learning completed model M12 used in the secondary proposal step is a model for allocating the plurality of components P1 that should be allocated to the 1st to 4th supply sections 31 to 34 to the 2 secondary groups G21, G22. With regard to the learning completed model M12, the 1st to 4th supply sections 31 to 34 in which the number of the capturing sections 41 is "16" are included in the allocation destination. Therefore, the learning completed model M12 is a model generated so as to reflect one characteristic that the number of the capturing sections 41 is "16" and to correspond to this characteristic.

[0162] On the other hand, the learning completed model M13 used in the secondary proposal step is a model for allocating the plurality of components P1 that should be allocated to the 5th to 8th supply sections 35 to 38 to the 2 secondary groups G23, G24. With regard to the learning completed model M13, the 5th and 6th supply sections 35, 36 in which the number of the capturing sections 41 is "8" and the 7th and 8th supply sections 37, 38 in which the number of the capturing sections 41 is "3" are included in the allocation destination. Therefore, the learning completed model M13 is a model generated so as to reflect two characteristics that the number of the capturing sections 41 is "8" and "3" and to correspond to these two characteristics.

[0163] The learning completed model M14 used in the tertiary proposal step is a model for allocating the plurality of components P1 that should be allocated to the 1st and 2nd supply sections 31, 32 to the 2 tertiary groups G31, G32. With regard to the learning completed model M14, the 1st and 2nd supply sections 31, 32 in which the number of the capturing sections 41 is "16" are included in the allocation destination. Therefore, the learning completed model M14 is a model generated so as to reflect one characteristic that the number of the capturing sections 41 is "16" and to correspond to this characteristic.

[0164] The learning completed model M15 used in the tertiary proposal step is a model for allocating the plurality of components P1 that should be allocated to the 3rd and 4th supply sections 33, 34 to the 2 tertiary groups G33, G34. With regard to the learning completed model M15, the 3rd and 4th supply sections 33, 34 in which the number of the capturing sections 41 is "16" are included in the allocation destination. Therefore, the learning completed model M15 is a model generated so as to reflect one characteristic that the number of the capturing sections 41 is "16" and to correspond to this characteristic.

[0165] The learning completed model M16 used in the tertiary proposal step is a model for allocating the plurality of components P1 that should be allocated to the 5th and 6th supply sections 35, 36 to the 2 tertiary groups G35, G36. With regard to the learning completed model M16, the 5th and 6th supply sections 35, 36 in which the number of capture sections 41 is "8" are included in the allocation destination. Therefore, the learning completed model M16 is a model generated so as to reflect 1 characteristic that the number of capture sections 41 is "8" and correspond to the characteristic that the number of capture sections 41 is "8".

[0166] The learning completed model M17 used in the tertiary proposal step is a model for allocating the plurality of components P1 that should be allocated to the 7th and 8th supply sections 37, 38 to the 2 tertiary groups G37, G38. With regard to the learning completed model M17, the 7th and 8th supply sections 37, 38 in which the number of capture sections 41 is "3" are included in the allocation destination. Therefore, the learning completed model M17 is a model generated so as to reflect 1 characteristic that the number of capture sections 41 is "3" and correspond to the characteristic that the number of capture sections 41 is "3".

[0167] Further, with regard to the plurality of (here, 7) learning completed models M11 to M17 described above, reinforcement learning is performed individually to generate. That is, reinforcement learning is performed in advance for each stage of the plurality of stages (here, 3 stages) set hierarchically to generate the learning completed models M11 to M17 described above. By causing the plurality of learning completed models M11 to M17 generated thus to cooperate, the multi-stage manner architecture shown above is constructed. Figure 6

[0168] ​As explained above, in the configuration assistance method according to the present embodiment, the configuration of the plurality of components P1 is not achieved by one stage of processing, but is achieved by a plurality of stages (three stages in this case) of processing set hierarchically. Thereby, compared with a multiple selection method in which the plurality of components P1 is allocated by one stage of processing, it is possible to suppress the options for deriving a suitable configuration of the plurality of components P1 in each stage to be fewer. As a result, it is possible to narrow the search space for reinforcement learning of the learned model M1. For example, in a case where 240 components are allocated to the above-mentioned eight supply sections 3, if it is a one-stage multiple selection method, the search space is assumed to be "10240". In contrast, if it is a three-stage multiple selection method, even under the same conditions, the search space involved in the first proposal step becomes "1080", the search space involved in the second proposal step becomes "1072", and the search space involved in the third proposal step becomes "1036". As a result, the search space for allocating 240 components to the above-mentioned eight supply sections 3 becomes "1080 + 1072 + 1036", which is significantly narrower than "10240" of the multiple selection method, and it is possible to reduce the size of the search space to a size at which actual learning can be performed.

[0169] Further, the above-mentioned explanation is only one example of the configuration assistance method according to the present embodiment, and for example, the configuration of the plurality of components P1 can not be achieved by three stages of processing, but can be achieved by two stages or four stages or more of processing. In a case where the allocation is divided into two stages, the third proposal step is omitted, and the second groups G21 to G24 are each established in one-to-one correspondence with the plurality of supply sections 3. On the other hand, in a case where the allocation is divided into four stages, further subgroups of the third groups G31 to G38 to which the plurality of components P1 is allocated in the third proposal step are generated as fourth groups. In a case where the allocation is divided into five stages, further subgroups of the fourth groups are generated as fifth groups.

[0170] (3.4) Reconfiguration

[0171] Next, the reconfiguration among the configuration assistance methods according to the present embodiment will be explained in more detail with reference to Figure 5 and Figure 7

[0172] The configuration assistance method has a proposal step, a determination step, and a reconfiguration step. The proposal step is a step of proposing a configuration of the plurality of components P1 with respect to the plurality of supply sections 3, and corresponds to the processing S102 to S10m of the flowchart shown in Figure 5 . The proposal step is executed by the proposal section 22 of the configuration assistance system 20. The determination step is a step of determining a certain supply section 3 among the plurality of supply sections 3 as a target supply section, and corresponds to the processing S11 of the flowchart shown in Figure 5 ​The processing S201 of the flowchart shown. The determining step is executed by the determining section 23 of the configuration assistance system 20. The supply section 3 determined as the object supply section is a supply section 3 that satisfies the determination condition with respect to the mounting time in the case where the configuration of the plurality of components P1 proposed in the proposing step is adopted. The reconfiguring step is a step of proposing the configuration of a plurality of components P1 to the object supply section and the reference supply section, and corresponds to Figure 5 The processing S202 to S204 of the flowchart shown. The reconfiguring step is executed by the reconfiguring section 24 of the configuration assistance system 20. The reference supply section is constituted by at least one supply section 3 other than the object supply section among the plurality of supply sections 3.

[0173] In the present embodiment, the components P1 configured in the object supply section are taken as objects, and the additional allocation (S203) is repeatedly executed for a specified number of times in the reconfiguring step (S202 to S204). The "additional allocation" mentioned here is a process of reconfiguring (allocating) a part of the components P1 to the plurality of supply sections 3 on the basis of the configuration (allocation) of the plurality of components P1 proposed in the temporary configuration (S100) with respect to the plurality of supply sections 3. Therefore, the "specified number of times" in which the additional allocation is repeatedly executed is a number of times determined in correspondence with the number of components P1 that become objects of the additional allocation and the like.

[0174] That is, in the processing portion S100 for the temporary configuration, when the plurality of components P1 are allocated to the plurality of supply sections 3, in the case where an inappropriate configuration (allocation) is made with respect to at least a part of the components P1, there is a possibility that the desired result cannot be obtained as it is. For example, in the case where a certain component P1 is allocated to an inappropriate supply section 3 in the temporary configuration (S100), the mounting of the component P1 takes time, and a bad situation in which the mounting time of the entire component mounting system 100 becomes long occurs. Therefore, in the configuration assistance method according to the present embodiment, instead of determining the configuration of the components P1 in the proposing step, the proposal of the configuration in the proposing step is taken as the "temporary configuration", and the change (correction) of the configuration of the plurality of components P1 can be made through the reconfiguring step thereafter.

[0175] Further, the supply section 3 that becomes the object of the reconfiguration in the reconfiguring step is the supply section 3 that satisfies the determination condition with respect to the mounting time, that is, the component P1 configured in the object supply section. Furthermore, the supply section 3 that becomes the object of the reconfiguration in the reconfiguring step includes not only the object supply section that satisfies the determination condition but also the component P1 configured in the reference supply section that is a supply section 3 different from the object supply section. Therefore, the plurality of components P1 configured in the respective different supply sections 3 (the object supply section and the reference supply section) in the temporary configuration can be disturbed. Therefore, even in the case where a certain component P1 is allocated to an inappropriate supply section 3 in the temporary configuration, the bad situation in which the mounting time becomes long and the like can be eliminated by the reconfiguration of the component P1 in the reconfiguring step.

[0176] Further, in the configuration assistance method according to the present embodiment, as shown in Figure 5 the installation time of the components P1 is sought. In the present embodiment, the "improvement of the installation time" means that the installation time of the entire component mounting system 100 is shortened. That is, the configuration assistance method determines whether the installation time is improved after the reconfiguration step (S202 to S204) as shown in Figure 5 the installation time of the components P1 is sought. In the present embodiment, the "improvement of the installation time" means that the installation time of the entire component mounting system 100 is shortened. That is, the configuration assistance method determines whether the installation time is improved after the reconfiguration step (S202 to S204) as shown in

[0177] In the configuration assistance method, if the installation time is not improved (S205: No), the configuration of the components P1 changed in the reconfiguration step is returned to the state before the reconfiguration step, that is, the "original component configuration" (S206). On the other hand, if the installation time is improved (S205: Yes), the process S206 is skipped. That is, by performing the reconfiguration, if the installation time is not improved, the state before the reconfiguration is returned, and only in the case where the installation time is improved (shortened), the configuration of the components P1 obtained in the reconfiguration is adopted.

[0178] Thereafter, the configuration assistance method determines whether there is a movement of the components P1 from the state before the reconfiguration step (S207). If there is any movement of the components P1 in the reconfiguration step (S207: Yes), the process S201 is repeated. On the other hand, if none of the components P1 is moved in the reconfiguration step (S207: No), the process section S200 for reconfiguration is ended. That is, as long as the configuration of the components P1 can be changed (modified) in the reconfiguration step, there is any movement of the components P1 in the reconfiguration step (S207: Yes), and therefore the determination step (S201) and the reconfiguration step (S202 to S204) are repeatedly executed. In other words, until the change (modification) mode of the configuration of the components P1 in which the installation time is improved is exhausted in the reconfiguration step, the determination step (S201) and the reconfiguration step (S202 to S204) are repeatedly executed.

[0179] Figure 7 is a diagram schematically showing a pattern of reconfiguration. In Figure 7In the present embodiment, the configuration (allocation) of the plurality of components P1 in the temporary configuration proposal for the plurality of supply sections 3 is conceptually represented, and the reconfiguration of the plurality of components P1 allocated to the 4th supply section 34 and the 6th supply section 36 among the 1st to 8th supply sections 31 to 38 is represented. In this example, the case where the 4th supply section 34 is the "target supply section" and the 6th supply section 36 is the "reference supply section" is represented as an example.

[0180] In this example, in the present embodiment, as an example, the supply section 3 in which the mounting time becomes a bottleneck is selected as the target supply section. That is, as a result of the component mounting system 100 sequentially mounting the plurality of components P1 allocated to the plurality of supply sections 3, the supply section 3 in which the mounting of the components P1 takes the longest time among the plurality of supply sections 3 becomes a bottleneck with respect to the mounting time. That is, in the present embodiment, the determination condition includes that the time (mounting time) required for the generation of the product P3 in the component mounting system 100 is the longest among the plurality of supply sections 3. In the present embodiment, the determination condition includes that the time (mounting time) required for the mounting of the components P1 allocated to the target supply section is the longest among the plurality of supply sections 3. Figure 7 In the example of the temporary configuration proposal, since the time required for the mounting of the components P1 allocated to the 4th supply section 34 among the plurality of supply sections 3 is the longest, the 4th supply section 34 is extracted as the target supply section.

[0181] In this way, in the determination step, the supply section 3 in which the mounting time satisfies the determination condition among the plurality of supply sections 3 is determined as the target supply section. Therefore, in the present embodiment, the configuration data D2 created in the temporary configuration is output from the output section 25 to the simulation section 26. Thus, the simulation section 26 performs simulation based on the configuration data D2, and calculates the "mounting time". The determination section 23 extracts the supply section 3 (target supply section) in which the determination condition is satisfied based on the mounting time thus calculated.

[0182] On the other hand, the reference supply section is constituted by any supply section 3 among the plurality of supply sections 3 other than the target supply section (here, the 4th supply section 34). In the present embodiment, it is assumed that any one supply section 3 among the plurality of supply sections 3 other than the target supply section (here, the 4th supply section 34) is sequentially selected as the reference supply section. In the present embodiment, the determination condition includes that the time (mounting time) required for the mounting of the components P1 allocated to the reference supply section is shorter than the time (mounting time) required for the mounting of the components P1 allocated to the target supply section. Figure 7 In the example of the temporary configuration proposal, the reconfiguration of the case where the 6th supply section 36 among the plurality of supply sections 3 is selected as the reference supply section is represented. For example, if the reconfiguration shown in FIG. 6 is completed, next, the 7th supply section 37 among the plurality of supply sections 3 is selected as the reference supply section, and the reconfiguration is performed. Figure 7 In the example of the temporary configuration proposal, the reconfiguration of the case where the 6th supply section 36 among the plurality of supply sections 3 is selected as the reference supply section is represented. For example, if the reconfiguration shown in FIG. 6 is completed, next, the 7th supply section 37 among the plurality of supply sections 3 is selected as the reference supply section, and the reconfiguration is performed.

[0183] Further, in the reconfiguration step, as shown in FIG. 7, the reconfiguration of the case where the 6th supply section 36 among the plurality of supply sections 3 is selected as the reference supply section is performed. Figure 7As shown, after temporarily moving the plurality of components P1 disposed in the target supply section (the 4th supply section 34) and the reference supply section (the 6th supply section 36) to the non-disposition space SpO, the plurality of components P1 are newly allocated to the target supply section and the reference supply section. That is, the plurality of components P1 disposed in the target supply section and the reference supply section in the temporary disposition are, after once returning to a state in which neither of the supply sections 3 is allocated, i.e., a non-disposition state, newly allocated to the target supply section and the reference supply section. That is, in the re-disposition step, for the target supply section and the reference supply section, after resetting the disposition of the plurality of components P1, the disposition of the plurality of components P1 is newly proposed.

[0184] Further, in the disposition assistance method according to the present embodiment, as shown in Figure 7 As shown, the disposition (allocation) of the plurality of components P1 in the re-disposition also uses the learned model M1. In the present embodiment, the learned model M1 is used to propose the disposition of the plurality of components P1 at least one of the proposal step and the re-disposition step. The learned model M1, as also explained in the column of "(3.2) Learned Model", is a model generated in correspondence with the characteristics of at least one of the plurality of supply sections 3. In particular, in the present embodiment, the learned model M1 is used in both the proposal step and the re-disposition step.

[0185] Here, in the present embodiment, as described above, depending on the allocation destination of the components P1, various learned models M1 are used. Therefore, in the re-disposition in which the 4th supply section 34 as the target supply section and the 6th supply section 36 as the reference supply section are used as the allocation destination, a learned model M18 different from the learned models M11 to M17 used in the temporary disposition (the proposal step) is used. As a result, in the present embodiment, the algorithm for proposing the disposition of the plurality of components P1 is different between the proposal step and the re-disposition step.

[0186] Specifically, the learned model M18 used in the re-disposition step is a model for allocating the plurality of components P1 to be allocated to two supply sections 3 to the 4th supply section 34 and the 6th supply section 36. Regarding the learned model M18, the 4th supply section 34 in which the number of capture sections 41 is "16" and the 6th supply section 36 in which the number of capture sections 41 is "8" are included in the allocation destination. Therefore, the learned model M18 is a model generated in correspondence with the two characteristics that the number of capture sections 41 is "16" and "8" in order to reflect the two characteristics.

[0187] Further, in the reconfiguration step, as well as in the proposal step, the proposal is made for the arrangement of the plurality of components P1 of the plurality of supply sections 3 so as to shorten the mounting time. That is, in the reconfiguration step, the proposal is made for the arrangement of the plurality of components P1 of the target supply section and the reference supply section so as to shorten the mounting time required for the production of the product P3 in the component mounting system 100.

[0188] Further, in the reconfiguration step in the present embodiment, as well as in the proposal step, when the arrangement of the plurality of components P1 of the plurality of supply sections 3 is proposed, a constraint condition that specifies whether or not the arrangement of a specific component P1 with respect to a specific supply section 3 is possible is attached. As described in the column of "(3.2) Learned Model", by attaching the constraint condition, with respect to the specific component P1 that is specified in the constraint condition as not being able to be arranged with respect to the specific supply section 3, the specific supply section 3 is excluded from the target of the reconfiguration (allocation).

[0189] In the arrangement assistance method according to the present embodiment, as described above, the determination step (S201) and the reconfiguration step (S202 to S204) are repeatedly executed until the change pattern of the arrangement of the components P1 in which the mounting time is improved in the reconfiguration step is exhausted. Therefore, if the result of the reconfiguration of the supply section 3 (target supply section) with respect to which the determination condition is satisfied (becomes a bottleneck) with respect to the mounting time is that the other supply section 3 satisfies the determination condition, the other supply section 3 is taken as the target supply section, and the reconfiguration step is repeatedly performed. On the other hand, if the result of the reconfiguration of the supply section 3 with respect to which the determination condition is satisfied (becomes a bottleneck) with respect to the mounting time is that the same supply section 3 satisfies the determination condition without change, it is considered that the change pattern of the arrangement of the components P1 is exhausted, and the processing section S200 for the reconfiguration is ended.

[0190] As described above, the arrangement assistance method according to the present embodiment has the reconfiguration step (S202 to S204) in addition to the acquisition step (S101) and the proposal step (S102 to S10m). The reconfiguration step is a step in which the proposal is made for the arrangement of the plurality of components P1 of the plurality of supply sections 3 after the proposal step. In particular in the present embodiment, the learned model M1 generated in the reinforcement learning is also used in the reconfiguration step, and it is possible to further propose the arrangement of the components P1 so as to more shorten the mounting time than the arrangement proposed in the proposal step.

[0191] Further, since the arrangement assistance method according to the present embodiment adopts the multi-stage manner in the proposal step, the reconfiguration step becomes a step in which the arrangement of the plurality of components P1 is proposed after the secondary proposal step. Also in the reconfiguration step, at least with respect to the supply section 3 in which the time required for the production of the product P3 in the component mounting system is the longest among the plurality of supply sections 3, the arrangement of the plurality of components P1 is proposed.

[0192] (4) Modified example

[0193] Embodiment 1 is only one of various embodiments of the present disclosure. Embodiment 1 can be variously changed in design and the like as long as it can achieve the purpose of the present disclosure. In addition, the drawings referred to in the present disclosure are all schematic drawings, and the size of each of the constituent elements in the drawings and the thickness ratio of each of the constituent elements do not necessarily reflect the actual size ratio. In addition, the same function as the configuration assistance method according to Embodiment 1 can be embodied by the configuration assistance system 20, a (computer) program, or a non-transitory recording medium that records the program, and the like. The program according to Embodiment 1 is a program for causing one or more processors to execute the configuration assistance method according to Embodiment 1.

[0194] Modified examples of Embodiment 1 are listed below. The modified examples described below can be appropriately combined and used.

[0195] The configuration assistance system 20 in the present disclosure includes a computer system. The computer system has a processor and a memory as main structures. The functions as the configuration assistance system 20 in the present disclosure are realized by the processor executing a program recorded in the memory of the computer system. The program can be recorded in advance in the memory of the computer system, can be provided via an electric communication line, or can be recorded in a non-transitory recording medium such as a memory card, an optical disc, a hard disk drive, or the like that is readable by the computer system. The processor of the computer system is constituted by one or more electronic circuits including a semiconductor integrated circuit (IC) or a large-scale integrated circuit (LSI). The integrated circuit such as the IC or the LSI is called differently depending on the degree of integration, and includes an integrated circuit called a system LSI, a VLSI (Very Large Scale Integration), or a ULSI (Ultra Large Scale Integration). Furthermore, a FPGA (Field-Programmable Gate Array) that is programmed after the manufacture of the LSI, or a logic device that can reconfigure the connection relationship within the LSI or the circuit division within the LSI can also be used as the processor. The plurality of electronic circuits can be integrated in one chip, or can be dispersed in a plurality of chips. The plurality of chips can be integrated in one device, or can be dispersed in a plurality of devices. The computer system includes a microcontroller having one or more processors and one or more memories. Therefore, the microcontroller is also constituted by one or more electronic circuits including a semiconductor integrated circuit or a large-scale integrated circuit.

[0196] Moreover, it is not a necessary structure of the configuration assistance system 20 that the plurality of functions in the configuration assistance system 20 are gathered in one housing. The structural elements of the configuration assistance system 20 can also be provided dispersedly in a plurality of housings. Furthermore, at least a part of the functions of the configuration assistance system 20 can also be implemented by a cloud (cloud computing) or the like.

[0197] As a function that can be implemented dispersedly in two or more systems such as a cloud (or server) and a cloud edge (edge), there are, for example, the following functions.

[0198] As a first function, there is a generation function of the learned model Ml. That is, the generation of the learned model Ml can be performed in one system, and the configuration assistance method (proposal step or the like) that utilizes the learned model Ml can be performed in another system. As an example, the generation of the learned model Ml can be performed in a cloud (or server), and the configuration assistance method (proposal step or the like) that utilizes the learned model Ml can be performed in a cloud edge. In this case, in one system such as a cloud, a generation method of a learned model that is generated by causing the learned model used in the configuration assistance method to correspond to the features of at least one of the plurality of supply parts 3 is concretized.

[0199] As the second function, there is a function of allocation of the component P1 in a multi-stage manner. That is, it is possible to perform a proposal step in one system, and a step after a secondary proposal step (including a tertiary proposal step, etc.) in other systems. As an example, the primary proposal step can be performed in the cloud (or server), and the step after the secondary proposal step (including the tertiary proposal step, etc.) can be performed in the fog. In this case, the configuration assistance system 20 is embodied in the system such as the fog, and only performs the step after the secondary proposal step (including the tertiary proposal step, etc.). In summary, the configuration assistance system 20 assists in the decision of the configuration of the plurality of components P1 in the plurality of supply sections 3 with respect to the component mounting system 100. The component mounting system 100 generates a product P3 by mounting the plurality of components P1 supplied to the plurality of supply sections 3 to the object P2. The configuration assistance system 20 does not have the primary proposal section 221, but has the secondary proposal section 222. The secondary proposal section 222 proposes the configuration of the plurality of components P1 with respect to the plurality of secondary groups G21 to G24 in the case where the plurality of primary groups G11, G12 are each classified into the plurality of secondary groups G21 to G24. The plurality of secondary groups G21 to G24 each include at least one supply section 3 among the plurality of supply sections 3. The secondary proposal section 222 receives the proposal of the configuration of the plurality of components P1 with respect to the plurality of primary groups G11, G12, and proposes the configuration of the plurality of components P1 with respect to the plurality of secondary groups G21 to G24. Here, the proposal of the configuration of the plurality of components P1 with respect to the plurality of primary groups G11, G12 is performed by other systems (cloud or server, etc.) having the primary proposal section 221, which are different from the configuration assistance system 20. That is, the configuration assistance system 20 receives the proposal of the configuration of the plurality of components P1 with respect to the plurality of primary groups G11, G12 from other systems, and proposes the configuration of the plurality of components P1 with respect to the plurality of secondary groups G21 to G24.

[0200] As the third function, there is a reconfiguration function. That is, the proposal step can be performed in one system, the determination step and the reconfiguration step can be performed in other system. As an example, the proposal step can be performed in the cloud edge, the determination step and the reconfiguration step can be performed in the cloud (or server). In this case, the configuration assistance method is embodied in the system such as the cloud (or server), and only includes the determination step and the reconfiguration step. In summary, the configuration assistance method is a method of assisting the decision of the configuration of the plurality of components P1 in the plurality of supply portions 3 of the component mounting system 100. The component mounting system 100 generates a product P3 by mounting the plurality of components P1 supplied to the plurality of supply portions 3 to the object P2. The configuration assistance method does not have the proposal step, but has the determination step and the reconfiguration step. The determination step is a step of accepting the proposal of the configuration of the plurality of components for the plurality of supply portions, and determining the supply portion 3 that satisfies the determination condition among the plurality of supply portions 3 as the object supply portion in the case where the configuration of the plurality of components P1 proposed is adopted. The determination condition is a condition on the time required for the generation of the product P3 in the component mounting system 100. The reconfiguration step is a step of proposing the configuration of the plurality of components P1 to the object supply portion and the reference supply portion constituted by at least one supply portion 3 other than the object supply portion among the plurality of supply portions 3.

[0201] Conversely, in Embodiment 1, at least a part of the functions of the configuration assistance system 20 or the work system 200 dispersed in the plurality of devices can be gathered in one housing. For example, a part of the functions dispersed in the component mounting system 100 and the configuration assistance system 20 can also be gathered in the component mounting system 100.

[0202] Further, the use of the component mounting system 100 is not limited to the manufacturing of electronic devices in a factory. For example, in the case where the component mounting system 100 is used in the mounting of mechanical components to a glass plate, the component mounting system 100 performs the work of mounting the mechanical components as the components P1 to the glass plate as the object P2.

[0203] Further, the number of the capturing portions 41 provided in the mounting head 4 and the like is not limited to the number described in Embodiment 1. For example, the capturing portions 41 can be 17 or more. Of course, the mounting head 4 can also be provided with only one capturing portion 41. The mounting head 4 can be a rotary head.

[0204] Further, at least one of the plurality of mounting machines 10 can be provided with only one supply portion 3, or three or more supply portions 3. Likewise, at least one of the plurality of mounting machines 10 can be provided with only one mounting head 4, or three or more mounting heads 4.

[0205] Further, in Embodiment 1, the reference supply part is constituted by an arbitrary supply part 3 other than the target supply part among the plurality of supply parts 3, but is not limited to this example. For example, the supply part 3 richest in installation time with respect to the installation time can be set as the reference supply part. That is, as a result of the component mounting system 100 sequentially installing the plurality of components P1 arranged in the plurality of supply parts 3, the supply part 3 among the plurality of supply parts 3 in which the time taken for installation of the components P1 is the shortest is richest in installation time. That is, the reference supply part includes the supply part 3 in which the time required for generation of the product P3 in the component mounting system 100 is the shortest among the plurality of supply parts 3. According to this structure, in rearrangement, the plurality of components P1 can be shuffled between the target supply part in which the installation time becomes a bottleneck and the reference supply part richest in installation time. As a result, it is easy to seek improvement in installation time by rearrangement.

[0206] Further, the determination condition for determining the target supply part can be a condition related to installation time, and is not limited to the installation time being the longest (the supply part 3 becoming a bottleneck) among the plurality of supply parts 3. For example, the determination condition can be that the time required for generation of the product P3 in the component mounting system 100 (installation time) is the Mth (M is an integer of 2 or more) longest among the plurality of supply parts 3. Conversely, the determination condition can be that the time required for generation of the product P3 in the component mounting system 100 (installation time) is the shortest among the plurality of supply parts 3, and the like. In this way, according to the determination condition, for example, it is possible to reduce the deviation in the time required for generation of the product P3 in the component mounting system 100 among the plurality of supply parts 3. In this case, for example, it is possible to ease the concentration of burden on a particular mounting machine 10.

[0207] Further, the target supply part is not limited to one supply part 3, and can be two or more supply parts 3. Similarly, the reference supply part is not limited to one supply part 3, and can be two or more supply parts 3.

[0208] Further, the structure in which the tape feeder is installed in the supply part 3 is not limited, and for example, a tray on which a plurality of components P1 are loaded can be provided. Furthermore, as a whole of the component mounting system 100, for example, a supply part 3 in which the tape feeder is installed and a supply part 3 in which the tray is provided can be mixed.

[0209] Further, the proposal of the "arrangement" of the components P1 by the arrangement assistance method can be up to the proposal of the arrangement of the components P1. In this case, in the arrangement assistance method, the plurality of components P1 is divided into a plurality of parts, one or more components P1 after the division are allocated to any of the plurality of supply parts 3, and the order (arrangement) into each supply part 3 is specified. As a result, in the case where a plurality of components P1 are allocated to one supply part 3, the order to the plurality of components P1 is specified.

[0210] Further, the pre-learning of the learned model M1 is not limited to the configuration assistance system 20, and can be performed in other systems. In this case, the configuration assistance system 20 uses the learned model M1 generated in the other systems to perform the proposal of the configuration of the component P1 in the proposal section 22 and the reconfiguration section 24.

[0211] Further, in both the proposal step and the reconfiguration step, it is not necessary to perform the proposal of the configuration of the component P1 using the learned model M1. For example, the proposal of the configuration of the component P1 using the learned model M1 can be performed only in the proposal step among the proposal step and the reconfiguration step, or the proposal of the configuration of the component P1 using the learned model M1 can be performed only in the reconfiguration step. Further, the learned model M1 can not be used in either of the proposal step and the reconfiguration step. That is, as for the function of the multi-stage manner of the allocation and the reconfiguration of the component P1, the same function as that of Embodiment 1 can be achieved even if the learned model M1 is not used.

[0212] Further, in Embodiment 1, it is not necessary to perform the proposal of the configuration of the component P1 using the learned model M1 in all of the primary proposal step, the secondary proposal step, and the tertiary proposal step. For example, the proposal of the configuration of the component P1 using the learned model M1 can be performed only in any one or two steps among the primary proposal step, the secondary proposal step, and the tertiary proposal step.

[0213] Further, the means for generating the learned model M1 is not limited to reinforcement learning, and can be, for example, "teacher learning" or the like.

[0214] Further, the configuration assistance method according to Embodiment 1 is not limited to a manner in which all the processes are performed by one or more processors, and at least a part of the processes can be performed by a person. For example, as for the process of setting the constraint condition or the like, a person can perform the process using a user interface or the like.

[0215] Further, the means for calculating the installation time used in the generation of the learned model M1 or the like is not limited to the simulation in the simulation section 26. For example, instead of the simulation, a classifier or the like generated by deep learning using a multi-layer neural network can be used to calculate the installation time.

[0216] (Embodiment 2)

[0217] The configuration assistance method according to the present embodiment is different from the configuration assistance method according to Embodiment 1 in the process section S200 for reconfiguration. Figure 5 Reference) from the configuration assistance method according to Embodiment 1. Hereinafter, the same structures as those of Embodiment 1 are denoted by common reference numerals, and the explanation is appropriately omitted.

[0218] That is, in Embodiment 1, in the reconfiguration step, when the reconfiguration of the component P1 is performed, on the basis of the determination step in which it is determined that the supply part 3 (the target supply part) satisfying the determination condition, the component P1 disposed in the target supply part is set as the target of the reconfiguration. Also, if the result of the reconfiguration of the supply part 3 (the target supply part) satisfying the determination condition is that the same supply part 3 satisfies the determination condition unchanged, it is regarded that the change mode of the disposition of the component P1 is exhausted, and the processing part S200 for the reconfiguration is ended.

[0219] On the contrary, in the present embodiment, even if the result of the reconfiguration of the supply part 3 satisfying the determination condition with respect to the mounting time is that the same supply part 3 satisfies the determination condition unchanged, the processing part S200 for the reconfiguration is continued. That is, in the disposition assistance method related to the present embodiment, even if the change mode of the disposition of the component P1 with the supply part 3 satisfying the determination condition as the target supply part is exhausted, the reconfiguration step is repeated with other supply parts 3 as the target supply part. Specifically, after the change mode of the disposition of the component P1 with the supply part 3 satisfying the determination condition as the target supply part is exhausted, any of the plurality of supply parts 3 is sequentially selected as the target supply part regardless of whether the determination condition is satisfied or not.

[0220] As a result, according to the disposition assistance method related to the present embodiment, it is possible to reconfigure all of the plurality of supply parts 3 as the target, and even compared with Embodiment 1, a more suitable disposition can be found.

[0221] As a modification of Embodiment 2, the disposition assistance method can not originally have the determination step of determining the supply part 3 satisfying the determination condition as the target supply part. In this case, the disposition assistance method, in the reconfiguration, sequentially selects any of the plurality of supply parts 3 as the target supply part regardless of whether the determination condition is satisfied or not.

[0222] The structure explained in Embodiment 2 (including the modification) can be suitably combined with the structure explained in Embodiment 1 (including the modification) and used.

[0223] (Summary)

[0224] As explained above, the configuration assistance method according to the first aspect is a method of assisting a decision of a configuration of a plurality of components (P1) in a plurality of supply portions (3) for a component mounting system (100), having a step of acquiring and a step of proposing. The component mounting system (100) is a system of generating a product (P3) by mounting a plurality of components (P1) supplied to the plurality of supply portions (3) to an object (P2). The step of acquiring is a step of acquiring mounting data (D1) related to the plurality of components (P1) included in the product (P3). The step of proposing is a step of proposing a configuration of the plurality of components (P1) for the plurality of supply portions (3) from the mounting data (D1) using a learned model (M1) so that a mounting time required for generation of the product (P3) in the component mounting system (100) is shortened. The learned model (M1) is a model generated in correspondence with a feature of at least one supply portion (3) among the plurality of supply portions (3).

[0225] According to this aspect, in the step of proposing, instead of proposing a configuration decided uniquely, a suitable configuration can be found more easily, for example, by implementing a "decision method" technique of a skilled person using the learned model (M1). In particular, since the learned model (M1) is a model generated in correspondence with a feature of at least one supply portion (3) among the plurality of supply portions (3), a configuration of the plurality of components (P1) is proposed, for example, taking into account the performance or specifications of the mounting machine (10) and the like. Thus, in this configuration assistance method, a proposal of an improved configuration of the components (P1) can be given.

[0226] In the configuration assistance method according to the second aspect, on the basis of the first aspect, the learned model (M1) includes a model generated in correspondence with a feature of two or more supply portions (3) among the plurality of supply portions (3).

[0227] According to this aspect, even if the plurality of components (P1) is assigned to two or more supply portions (3) in the step of proposing, a suitable configuration can be proposed easily using the learned model (M1) suitable for the two or more supply portions (3) to which the plurality of components (P1) is assigned.

[0228] In the configuration assistance method according to the third aspect, on the basis of the first or second aspect, in a case where the features of the plurality of supply portions (3) are classified into one or more feature groups, the learned model (M1) includes a model generated in correspondence with the one or more feature groups.

[0229] According to this aspect, even if there are supply portions (3) having various features, a suitable configuration can be proposed easily using the learned model (M1) suitable for the supply portions (3) by setting the same features to one feature group.

[0230] In the configuration assistance method according to the fourth aspect, the learning completed model (Ml) is generated using reinforcement learning on the basis of any one of the first to third aspects.

[0231] According to this aspect, the generation of the learning completed model (Ml) in a situation where the correct answer is not clear and optimization for a large combination is required becomes easy.

[0232] The configuration assistance method according to the fifth aspect further includes a step of updating the learning completed model (Ml) on the basis of any one of the first to fourth aspects.

[0233] According to this aspect, a suitable learning completed model (Ml) corresponding to the user's requirements can be generated at the stage of using the configuration assistance method.

[0234] In the configuration assistance method according to the sixth aspect, the learning completed model (Ml) includes a model generated in correspondence with information related to a product (P3) generated by the component mounting system (100) on the basis of any one of the first to fifth aspects.

[0235] According to this aspect, since the learning completed model (Ml) that reflects not only the characteristics of the supply section (3) but also matters inherent to the product (P3) is used, it is easy to propose a suitable configuration.

[0236] In the configuration assistance method according to the seventh aspect, the proposal step includes a primary proposal step and a secondary proposal step on the basis of any one of the first to sixth aspects. The primary proposal step is a step of proposing a configuration of the plurality of components (Pl) with respect to the plurality of primary groups (Gl l, Gl2). The secondary proposal step is a step of proposing a configuration of the plurality of components (Pl) with respect to the plurality of secondary groups (G21 to G24) in the case where the plurality of primary groups (Gl l, Gl2) are each classified into the plurality of secondary groups (G21 to G24) after the primary proposal step. The plurality of secondary groups (G21 to G24) each include at least one supply section (3) among the plurality of supply sections (3).

[0237] According to this mode, the proposal of the configuration of the plurality of components (P1) is divided into a primary proposal step of configuring the components (P1) to a plurality of primary groups (G11, G12) and a secondary proposal step of configuring the components (P1) to a plurality of secondary groups (G21 to G24) that are more detailed. In total, since the configuration of the plurality of components (P1) is not realized by a stage-by-stage process but by a multi-stage process that is set hierarchically, the options for deriving a suitable configuration of the plurality of components (P1) can be suppressed to be fewer at each stage. As a result, the process for proposing the configuration of the plurality of components (P1) in each stage can be simplified. Therefore, in this configuration assistance method, an improved proposal of the configuration of the components (P1) can be given.

[0238] In the configuration assistance method according to the 8th mode, on the basis of the 7th mode, the learned model (M1) is different in the primary proposal step and the secondary proposal step.

[0239] According to this mode, the configuration of the plurality of components (P1) can be proposed using a suitable learned model (M1) in each of the primary proposal step and the secondary proposal step.

[0240] In the configuration assistance method according to the 9th mode, on the basis of the 7th or 8th mode, the configuration of the plurality of components (P1) is proposed using a learned model (M1) in at least one of the primary proposal step and the secondary proposal step.

[0241] According to this mode, instead of proposing a configuration that is uniquely determined, a suitable configuration can be found more easily, for example, by using the skill of the "determination method" of the configuration that is performed by an expert using a learned model (M1).

[0242] In the configuration assistance method according to the 10th mode, on the basis of any one of the 7th to 9th modes, there is further a tertiary proposal step. The tertiary proposal step is a step of proposing the configuration of the plurality of components (P1) with respect to a plurality of tertiary groups (G31 to G38) that classify the plurality of secondary groups (G21 to G24) each into a plurality of tertiary groups (G31 to G38) after the secondary proposal step. The plurality of tertiary groups (G31 to G38) each include at least one of the plurality of supply portions (3).

[0243] According to this mode, the proposal of the configuration of the plurality of components (P1) is realized by dividing into the primary proposal step and the secondary proposal step and further dividing into a tertiary proposal step of configuring the components (P1) to a plurality of tertiary groups (G31 to G38) that are more detailed. As a result, the process for proposing the configuration of the plurality of components (P1) in each stage can be further simplified.

[0244] The configuration assistance method according to the 11th aspect further includes a reconfiguration step of proposing a configuration of the plurality of components (P1) for the plurality of supply units (3) after the proposal step.

[0245] According to this aspect, even if the configuration of the plurality of components (P1) proposed in the proposal step is not optimal, a new configuration of the plurality of components (P1) can be proposed in the reconfiguration step.

[0246] In the wiring assistance method according to the 12th aspect, at least a supply unit (3) in which a time required for generation of the product (P3) in the component mounting system (100) is the longest among the plurality of supply units (3) is proposed a configuration of the plurality of components (P1) in the reconfiguration step on the basis of the 11th aspect.

[0247] According to this aspect, a component (P1) configured in a supply unit (3) in which a time required for generation of the product (P3) in the component mounting system (100) becomes a bottleneck can be taken as a target, and a new configuration of the plurality of components (P1) can be proposed in the reconfiguration step.

[0248] In the configuration assistance method according to the 13th aspect, a constraint condition in which a configuration of a specific component (P1) for a specific supply unit (3) is specified as being possible or impossible is attached to the configuration of the plurality of components (P1) for the plurality of supply units (3) on the basis of any one of the first to 12th aspects.

[0249] According to this aspect, as for a specific component (P1) specified in the constraint condition as being impossible to configure in a specific supply unit (3), the specific supply unit (3) can be excluded from the target of allocation, and it is easy to simplify the proposal of the configuration.

[0250] In the configuration assistance method according to the 14th aspect, a determination of the possibility of a configuration of a specific component (P1) for a specific supply unit (3) according to the constraint condition is performed separately from the proposal of a configuration of the plurality of components (P1) for the plurality of supply units (3) using the learned model (M1) on the basis of the 13th aspect.

[0251] According to this aspect, the number of options for deriving a suitable configuration of the plurality of components (P1) can be reduced.

[0252] The learned model generation method according to the 15th aspect generates a learned model used in any one of the configuration assistance methods according to the first to 14th aspects in correspondence with a feature of at least one supply unit (3) among the plurality of supply units (3).

[0253] According to this aspect, an improved proposal of a configuration of the components (P1) can be made.

[0254] The program according to the 16th aspect is a program for causing one or more processors to execute the configuration assistance method according to any one of the first to 14th aspects or the generation method of a learned model according to the 15th aspect.

[0255] According to this aspect, it is possible to give a proposal for the configuration of components (P1) that has been improved.

[0256] The configuration assistance system (20) according to the 17th aspect is a system that assists in the decision of the configuration of a plurality of components (P1) in a plurality of supply sections (3) for a component mounting system (100), and includes an acquisition section (21) and a proposal section (22). The component mounting system (100) is a system that generates a product (P3) by mounting a plurality of components (P1) supplied to a plurality of supply sections (3) to an object (P2). The acquisition section (21) acquires mounting data (D1) related to a plurality of components (P1) included in the product (P3). The proposal section (22) proposes the configuration of a plurality of components (P1) for a plurality of supply sections (3) from the mounting data (D1) using a learned model (M1) so that the mounting time required for the generation of the product (P3) in the component mounting system (100) is shortened. The learned model (M1) is a model that corresponds to the characteristics of at least one supply section (3) among the plurality of supply sections (3).

[0257] According to this aspect, it is possible to give a proposal for the configuration of components (P1) that has been improved.

[0258] In the configuration assistance system (20) according to the 18th aspect, on the basis of the 17th aspect, the proposal section (22) includes a primary proposal section (221) and a secondary proposal section (222). The primary proposal section (221) proposes the configuration of a plurality of components (P1) for a plurality of primary groups (G11, G12). The secondary proposal section (222) proposes the configuration of a plurality of components (P1) for a plurality of secondary groups (G21 to G24) in the case where the plurality of primary groups (G11, G12) are each classified into the plurality of secondary groups (G21 to G24). The plurality of secondary groups (G21 to G24) each include at least one supply section (3) among the plurality of supply sections (3).

[0259] According to this aspect, it is possible to give a proposal for the configuration of components (P1) that has been improved.

[0260] In the configuration assistance system (20) according to the 19th aspect, the proposal unit (22) includes a secondary proposal unit (222) in addition to the 17th aspect. The secondary proposal unit (222) proposes a configuration of the plurality of components (P1) with respect to a plurality of secondary groups (G21 to G24) in a case where the plurality of primary groups (G11, G12) are each classified into the plurality of secondary groups (G21 to G24). The plurality of secondary groups (G21 to G24) each include at least one supply unit (3) among the plurality of supply units (3). The secondary proposal unit (222) accepts a proposal of a configuration of the plurality of components (P1) with respect to the plurality of primary groups (G11, G12) and proposes a configuration of the plurality of components (P1) with respect to the plurality of secondary groups (G21 to G24).

[0261] According to this aspect, a proposal of an improved configuration of the components (P1) can be made.

[0262] The work system (200) according to the 20th aspect includes the configuration assistance system (20) according to any one of the 17th to 19th aspects and the component mounting system (100). The component mounting system (100) is used in a configuration of the plurality of components (P1) proposed by the configuration assistance system (20) to generate a product (P3).

[0263] According to this aspect, a proposal of an improved configuration of the components (P1) can be made.

[0264] The present application is not limited to the above-described aspects, and the various aspects (including modifications) of the configuration assistance method according to Embodiment 1 and Embodiment 2 can be embodied by the configuration assistance system (20), the work system (200), a program, and a non-transitory recording medium that records the program.

[0265] As for the structures according to the 2nd to 14th aspects, structures that are not essential to the configuration assistance method can be appropriately omitted.

[0266] As for the structures according to the 17th or 18th aspect, structures that are not essential to the configuration assistance system (20) can be appropriately omitted.

[0267] Explanation of Reference Numerals

[0268] 3 supply unit

[0269] 20 configuration assistance system

[0270] 21 acquisition unit

[0271] 22 proposal unit

[0272] 100 component mounting system

[0273] 200 work system

[0274] 221 primary proposal section

[0275] 222 secondary proposal section

[0276] D1 installation data

[0277] M1 learned model

[0278] G11, G12 primary group

[0279] G21 to G24 secondary group

[0280] G31 to G38 tertiary group

[0281] P1 part

[0282] P2 object

[0283] P3 product

Claims

1. A configuration assistance method of assisting decision of configuration of a plurality of components in a plurality of supply sections for a component mounting system that generates a product by mounting the plurality of components supplied to the plurality of supply sections to an object, the configuration assistance method having: an acquisition step of acquiring mounting data related to the plurality of components included in the product; and a proposal step of proposing configuration of the plurality of components for the plurality of supply sections based on the mounting data using a learned model generated in correspondence with features of at least one supply section among the plurality of supply sections so that mounting time required for generation of the product in the component mounting system is shortened, the features including a maximum mounting speed of a mounting machine provided with the at least one supply section, a number of catchers, a number of supply sections, a kind of catchers, a number of slots, a number of mounting heads, and a machine type.

2. The configuration assistance method according to claim 1, wherein the learned model includes a model generated in correspondence with features of two or more supply sections among the plurality of supply sections.

3. The configuration assistance method according to claim 1 or 2, wherein in a case where the features of the plurality of supply sections are classified into one or more feature groups, the learned model includes a model generated in correspondence with the one or more feature groups.

4. The configuration assistance method according to claim 1 or 2, wherein the learned model is generated using reinforcement learning.

5. The configuration assistance method according to claim 1 or 2, wherein the configuration assistance method further has: an update step of updating the learned model.

6. The configuration assistance method according to claim 1 or 2, wherein the learned model includes a model generated in correspondence with information related to the product generated by the component mounting system.

7. The configuration assistance method according to claim 1 or 2, wherein the proposal step includes: a primary proposal step of proposing configuration of the plurality of components for a plurality of primary groups; and a secondary proposal step of, after the primary proposal step, proposing configuration of the plurality of components for a plurality of secondary groups in a case where the plurality of primary groups are each classified into the plurality of secondary groups including at least one supply section among the plurality of supply sections.

8. The configuration assistance method according to claim 7, wherein in the primary proposal step and the secondary proposal step, the learned model is different.

9. The configuration assistance method according to claim 7, wherein in at least one of the primary proposal step and the secondary proposal step, the learned model is used to propose configuration of the plurality of components.

10. The configuration assistance method according to claim 7, wherein the configuration assistance method further has: a tertiary proposal step of, after the secondary proposal step, proposing configuration of the plurality of components for a plurality of tertiary groups in a case where the plurality of secondary groups are each classified into the plurality of tertiary groups including at least one supply section among the plurality of supply sections.

11. The configuration assistance method according to claim 1 or 2, wherein the configuration assistance method further has: a reconfiguration step, after the proposal step, of proposing a configuration of the plurality of components for the plurality of supply sections.

12. The configuration assistance method according to claim 11, wherein in the reconfiguration step, at least a supply section in which a time required for generation of the product in the component mounting system is longest among the plurality of supply sections, a configuration of the plurality of components is proposed.

13. The configuration assistance method according to claim 1 or 2, wherein when proposing a configuration of the plurality of components for the plurality of supply sections, a constraint condition of specifying whether or not a configuration of a specific component for a specific supply section is possible is attached.

14. The configuration assistance method according to claim 13, wherein a judgment of whether or not the configuration of the specific component for the specific supply section according to the constraint condition is performed separately from the proposal of the configuration of the plurality of components for the plurality of supply sections using the learned model.

15. A learned model generation method of generating a learned model used in the configuration assistance method according to any one of claims 1 to 14 in correspondence with a feature of at least one supply section among the plurality of supply sections.

16. A non-transitory recording medium readable by a computer, recording a program for causing one or more processors to execute the configuration assistance method according to any one of claims 1 to 14 or the learned model generation method according to claim 15.

17. A configuration assistance system of assisting a decision of a configuration of a plurality of components in a plurality of supply sections for a component mounting system of generating a product by mounting the plurality of components supplied from the plurality of supply sections to an object, the configuration assistance system has: an acquisition section of acquiring mounting data related to the plurality of components included in the product; and a proposal section of proposing a configuration of the plurality of components for the plurality of supply sections based on the mounting data using a learned model in correspondence with a feature of at least one supply section among the plurality of supply sections so as to shorten a mounting time required for generation of the product in the component mounting system, the feature includes a maximum mounting speed of a mounting machine provided with the at least one supply section, a number of capturing sections, a number of supply sections, a kind of capturing section, a number of slots, a number of mounting heads, and a machine type.

18. The configuration assistance system according to claim 17, wherein the proposal section includes: a primary proposal section of proposing a configuration of the plurality of components for a plurality of primary groups; and a secondary proposal section of proposing a configuration of the plurality of components for a plurality of secondary groups in a case where the plurality of primary groups are each classified into the plurality of secondary groups including at least one supply section among the plurality of supply sections.

19. The configuration assistance system according to claim 17, wherein the proposal section includes: A secondary proposal unit that accepts a proposal of a configuration of the plurality of components for the plurality of primary groups, the proposal classifying each of the plurality of primary groups into a plurality of secondary groups that each contain at least one of the plurality of supply units, and proposing a configuration of the plurality of components for the plurality of secondary groups.

20. A work system comprising: the configuration assistance system according to any one of claims 17 to 19; and the component mounting system that is used under the configuration of the plurality of components proposed in the configuration assistance system, and generates the product.

Images