JP2022099377A - Measure proposing device, measure proposing system and measure proposing substrate - Google Patents

Abstract

To provide a measure proposing device and a measure proposing substrate capable of improving the precision of a measure proposed on a process flow.SOLUTION: A measure proposing device 1 is for a measure proposed in multiple process flows in a product developing process. The measure proposing device includes: a communicating unit that is connected to an independent-business communication network 4; an obtaining unit that obtains, through the independent-business communication network 4, to-be-evaluated object information containing event data relating to an event, and process-flow information representing a process flow at which the event data occurs; a reference database that stores, on the basis of a relevancy between plural pieces of data contained in past to-be-evaluated object information obtained in advance and plural pieces of data contained in reference information associated with the past to-be-evaluated object information, a similarity having a similarity level associated with the relevancy; a relation information searching unit which refers to the reference database on the basis of the to-be-evaluated information obtained by the obtaining unit, selects the optimal reference information associated with a solution calculated on the basis of the similarity, and generates relation information on the basis of the optimal reference information; and an outputting unit that outputs the relation information generated by the relation information searching unit to the own process flow and to the process flows relating thereto on the basis of the process-flow information.SELECTED DRAWING: Figure 1

Description

The present invention relates to a measure proposal device, a measure proposal system, and a measure proposal board that propose measures in a plurality of processes in a product development process.

Conventionally, for example, the method for estimating an abnormal process in Patent Document 1 has been proposed as a method for accurately estimating an abnormal process that causes a quality abnormality in a product.

The abnormal process estimation method disclosed in Patent Document 1 has a collection process of having a plurality of sensors and collecting sensor data of the sensors in a production line composed of a plurality of processes, and normal quality while the production line is in a normal state. A generation process that generates a plurality of correlation models between the sensors corresponding to each process by executing machine learning based on the elapsed time between the processes based on the sensor data of the minute, and the sensor data at the time of arbitrary evaluation and the processing. Evaluate the degree of deviation from the normal state in each process based on the output value of the correlation model obtained by inputting the evaluation amount for each process, which takes into account the elapsed time between processes to the sensor data, into the corresponding correlation model. It has an evaluation process to be performed and a determination process for determining an abnormal process that causes a product quality abnormality from among the processes based on the degree of deviation.

Japanese Unexamined Patent Publication No. 2019-49940

Here, when evaluating an event such as a defect that occurs in a plurality of processes in a product development process, at present, an event that occurs in a specific process is evaluated using a communication band allocated by a telecommunications carrier. .. For this reason, if there are multiple other related processes, it takes time to find and respond to the root cause of the problem that occurred, and there is a concern that appropriate and appropriate measures cannot be taken promptly. In this regard, in the disclosed technique of Patent Document 1, a sensor installed on a manufacturing line is connected via a communication network, and a correlation model is used in the manufacturing process to determine an abnormal process that causes a product quality abnormality. If there are multiple other related steps, the evaluation of the root cause of the event that has occurred is delayed, and appropriate and appropriate countermeasures cannot be taken promptly. Under these circumstances, it is desired to improve the accuracy of measures proposed in multiple processes in the product development process, and to improve the quality assurance and manufacturing efficiency of the entire development and manufacturing process or the own process (or the entire company). ..

Therefore, the present invention has been devised in view of the above-mentioned problems, and the purpose of the present invention is to improve the accuracy of the measures proposed in a plurality of processes in the product development process, and to improve the accuracy of the entire development / manufacturing process or the entire development / manufacturing process. The purpose is to provide a measure proposal device, a measure proposal system, and a measure proposal board for improving the quality assurance and manufacturing efficiency of the own process.

The measure proposal device according to the first invention is a measure proposal device that proposes measures in a plurality of processes in the product development process, and includes a communication unit connected to a self-employed communication network installed in the target area of the product development process. An acquisition unit that acquires evaluation target information including event data related to an event that occurred in the process and process information indicating the process in which the event data was generated via the self-employed communication network connected by the communication unit. Based on the relationship between the plurality of data included in the past evaluation target information acquired in advance and the plurality of data included in the reference information associated with the past evaluation target information. Based on the reference database in which the similarity associated with is stored and the evaluation target information acquired by the acquisition unit, the reference database is referred to, and the optimum said to be associated with the solution calculated based on the similarity. A related information search unit that selects reference information and generates related information based on the optimum reference information, and the related information generated by the related information search unit are related to the own process based on the process information. It is characterized by having an output unit for outputting to a process.

The measure proposing device according to the second invention is characterized in that, in the first invention, the reference information stored in the reference database includes the measure information of the event generated in the product development process.

The measure proposing device according to the third invention is characterized in that, in the first invention or the second invention, the related information generated by the related information retrieval unit includes the measure information in the process.

In any one of the first invention to the third invention, the measure proposal device according to the fourth invention includes the product information, parts information, design information, defect information, priority information, and the evaluation target information related to the event generated in the process. And include product development information having information on at least one of the applicable information.

In any of the first to fourth inventions, the measure proposing device according to the fifth invention uses the similarity between the relationship between the past evaluation target information and the reference information as learning data. It is characterized by being constructed by the machine learning that was done.

When the measure proposing device according to the sixth invention newly acquires the relationship between the past evaluation target information and the reference information in any one of the first invention to the fifth invention, the said relationship is obtained. It is characterized by further including an update unit that reflects the similarity.

The measure proposal system according to the seventh invention is a measure proposal system that proposes measures in a plurality of processes in the product development process, and is a communication means connected to a self-employed communication network installed in the target area of the product development process. Acquisition means for acquiring evaluation target information including event data related to an event occurring in the process and process information indicating the process in which the event data is generated via the self-employed communication network connected by the communication means. Based on the relationship between the plurality of data included in the past evaluation target information acquired in advance and the plurality of data included in the reference information associated with the past evaluation target information. The reference database is referred to based on the database in which the similarity associated with the data is stored and the evaluation target information acquired by the acquisition means, and the optimum reference associated with the solution calculated based on the similarity. A related information search means that selects information and generates related information based on the optimum reference information, and the related information generated by the related information search means are used in the own process and related steps based on the process information. It is characterized in that it is provided with an output means for outputting to.

The measure proposal platform according to the eighth invention is a measure proposal board that proposes measures in a plurality of processes in the product development process, and includes a communication unit connected to a self-employed communication network installed in the target area of the product development process. Acquisition means for acquiring evaluation target information including event data related to an event occurring in the process and process information indicating the process in which the event data is generated via the self-employed communication network connected by the communication unit. Based on the relationship between the plurality of data included in the past evaluation target information acquired in advance and the plurality of data included in the reference information associated with the past evaluation target information. The reference database is referred to based on the database in which the similarity associated with the data is stored and the evaluation target information acquired by the acquisition means, and the optimum reference associated with the solution calculated based on the similarity. A related information search means that selects information and generates related information based on the optimum reference information, and the related information generated by the related information search means are used in the own process and related steps based on the process information. It is characterized in that it is provided with an output means for outputting to.

According to the first to sixth inventions, the communication unit is connected to the self-employed communication network installed in the target area of the product development process, and the acquisition unit generates event data and event data related to the event that occurred in the process. The evaluation target information including the process information indicating the completed process is acquired. Therefore, it is possible to quickly acquire various events that occur in a plurality of processes in the product development process. This makes it possible to improve the accuracy of the measures proposed in the process, and improve the quality assurance and manufacturing efficiency of the entire development and manufacturing process or the own process.

Further, according to the first to sixth inventions, the related information retrieval unit refers to the reference database and generates related information for the evaluation target information. Therefore, it is possible to generate related information based on the result of evaluating the events that have occurred in the past. As a result, it is possible to improve the accuracy of the measures proposed for the problems that have occurred, and to improve the quality assurance and manufacturing efficiency of the entire development and manufacturing process or its own process.

In particular, according to the second invention, the reference information includes the measure information. Therefore, it is possible to realize an evaluation based on the characteristics of the cause of the defect that differs for each event that occurs in the product development process. This makes it possible to further improve the accuracy of the measures proposed in the process, and improve the quality assurance and manufacturing efficiency of the entire development and manufacturing process or the own process.

In particular, according to the third invention, the related information includes the measure information. Therefore, it is possible to realize the evaluation based on the own process in consideration of the related information or the countermeasures in the related process. This makes it possible to further improve the accuracy of the measures proposed in the process, and improve the quality assurance and manufacturing efficiency of the entire development and manufacturing process or the own process.

In particular, according to the fourth invention, the evaluation target information includes product development information. Therefore, it is possible to realize the evaluation based on the product information, the parts information, the design information, the defect information, the priority information, the application information, etc. regarding the event generated in the process. This makes it possible to further improve the accuracy of the measures proposed in the process, and improve the quality assurance and manufacturing efficiency of the entire development and manufacturing process or the own process.

In particular, according to the fifth invention, the similarity is constructed by machine learning using the relationship between the past evaluation target information and the similarity with the reference information as learning data. Therefore, even when evaluating unknown evaluation target information different from past evaluation target information, quantitative evaluation can be performed. This makes it possible to further improve the accuracy of the proposed measures and improve the quality assurance and manufacturing efficiency of the entire development and manufacturing process or its own process.

In particular, according to the sixth invention, when the update unit newly acquires the relationship between the past evaluation target information and the reference information, the update unit reflects the relationship in the similarity. Therefore, the similarity can be easily updated, the evaluation accuracy can be continuously improved, and the quality assurance and manufacturing efficiency of the entire development and manufacturing process or the own process can be improved.

Further, according to the seventh invention, the communication means is connected to the self-employed communication network installed in the target area of the product development process, and the acquisition means is the event data related to the event generated in the process and the process in which the event data is generated. The evaluation target information including the process information indicating the above is acquired. Therefore, it is possible to quickly acquire various events that occur in a plurality of processes in the product development process. This makes it possible to improve the accuracy of the measures proposed in the process, and improve the quality assurance and manufacturing efficiency of the entire development and manufacturing process or the own process.

Further, according to the eighth invention, the measure proposal board is a communication means connected to the self-employed communication network installed in the target area of the product development process, event data related to the event generated in the process, and the process in which the event data is generated. It is provided with the acquisition means for acquiring the evaluation target information including the process information indicating. Therefore, it is possible to quickly acquire various events that occur in a plurality of processes in the product development process. This makes it possible to improve the accuracy of the measures proposed in the process, and improve the quality assurance and manufacturing efficiency of the entire development and manufacturing process or the own process.

FIG. 1 is a schematic diagram showing an example of a product process process of the measure proposal system in the present embodiment. FIG. 2 is a schematic diagram showing an example of the measure proposal system in the present embodiment. FIG. 3 is a schematic diagram showing an example of the operation of the measure proposal system in the present embodiment. FIG. 4A is a schematic diagram showing an example of the configuration of the measure proposal system in the present embodiment, and FIG. 4B is a schematic diagram showing an example of the function of the measure proposal system in the present embodiment. FIG. 5 is a schematic diagram showing an example of the design stage of the measure proposal system in the present embodiment. FIG. 6 is a flowchart showing an example of the operation of the measure proposal system in the present embodiment.

Hereinafter, an example of the measure proposal device, the measure proposal system, and the measure proposal platform in the embodiment to which the present invention is applied will be described with reference to the drawings.

(Implementation 1: Measure Proposal System 100)
With reference to FIG. 1, an example of the product process process of the measure proposal system 100 and the measure proposal device 1 in the present embodiment will be described.

As shown in FIG. 1, for example, the measure proposal system 100 in the present embodiment is targeted for a product process in an IT system environment in, for example, a manufacturing industry. The measure proposal system 100 targets, for example, all processes A01 (for example, basic design, development / design / evaluation, production preparation, production, shipping, sales / service, etc.) related to the product development process. Equipment A10 indicates requirements and equipment in each process of process A01. The equipment A11 is, for example, AI / machine learning that functions for the equipment A10, and by using them, the quality of measures in each process is guaranteed.

Further, the equipment A12 is, for example, a PLM (Product Lifecycle Management) platform, and data such as a design drawing and a bill of materials of the company's products (“E-BOM: design bill of materials”, “P-BOM: process bill of materials”, “ It will be shared in the entire process from the planning stage to disposal and recycling via "M-BOM: Manufacturing Bill of Materials" and "S-BOM: Maintenance Bill of Materials"). Further, the equipment A12 includes, for example, a control system such as SCADA (Supervisory Control and Data Acquisition), HMI (Human Machine Interface), and DCS (distributed control system). The equipment A13 is, for example, a DB or a cloud, and the equipment A12 performs cooperation using, for example, these equipments.

In addition, the measure proposal system 100 is an optimal measure for solving, improving, quality assurance, or improving manufacturing efficiency of problems A20 to A23 in, for example, processes A01 and facilities A10 to A13 as problems when implementing robot control. I will provide a.

Problem A20 shows, for example, globalization in a company and the number of factories. Problem A21 shows, for example, problems in traceability and digital thread in step A01. Problem A22 presents, for example, the problem of knowledge of CAD (computer-aided design) in equipment A10 and difficulty in automating robot programming. Problem A23 shows, for example, cooperation by PLM / MES (Manufacturing Execution System) / ERP (Enterprise Resource Planning) for simulation, execution, and recording of a robot.

The measure proposal system 100 in the present embodiment uses AI / machine learning and a product development platform for each process of a plurality of processes, for example, to complete the measure in each own process in process A01. (Completion of own process) is possible. This makes it possible for the measure proposal system 100 to improve the quality assurance and manufacturing efficiency of the entire development and manufacturing process or its own process (or the entire company).

The measure proposal system 100 in this embodiment has a measure proposal device 1 as shown in FIG. 2, for example. The measure proposal device 1 is connected to, for example, a device that executes a plurality of processes 3a, 3b, 3c, etc. in the product development process 3, and is also connected to another terminal or a server 5 via, for example, a self-employed communication network 4. May be good.

The measure proposal device 1 is provided with, for example, a self-employed communication network 4 which is a communication infrastructure unique to a manufacturing company. The self-employed communication network 4 is a communication network (Local 5G communication) different from the band allocated by the telecommunications carrier, for example, to the manufacturing company, and is a communication network installed on the premises as a communication infrastructure unique to the manufacturing company. .. The measure proposal system 100 is connected to the product development process 3 in the manufacturing factory via the self-employed communication network 4. The measure proposal system 100 causes a device or the like provided in each process to execute a plurality of processes of the product development process 3 via the self-employed communication network 4. The measure proposal device 1 connects to the database 2 via the self-employed communication network 4.

The plurality of processes are, for example, various devices for executing a product development process 3 in a certain manufacturing development, for example, a process 3a for selling / servicing a product, a process 3b for planning a product, a process 3c for designing a product, and the like. It consists of equipment such as measuring instruments, processing robots, and sensors. In the product development process 3, for example, as other processes, in addition to the equipment that executes processes 3a to 3c, for example, a production process for producing a product, a process for producing a product, a marketing concept and a design process, and sales / Various devices that execute processes such as service CRM (Customer Relationship Management) may be included. It is constructed so as to be connected to the self-employed communication network 4 via a device that performs a plurality of processes, and to cooperate with a device that executes a plurality of processes of the product development process 3 in the site or area of a manufacturing company, for example.

The database 2 is connected to the measure proposal device 1 via the self-employed communication network 4. Various information and data are stored in the database 2 via, for example, the measure proposal device 1 and the respective devices such as steps 3a to 3c. The database 2 includes, for example, various databases in the manufacturing company, such as a planning information database, a design information database, a development information database, a parts information database, an after-sales support information database, a purchasing information database, a market evaluation database, a defect information database, and the like. Is included at least. The database 2 contains, for example, various information and data acquired through devices that execute a plurality of processes 3a to 3c, each process in the product development process, proposed measures, products, parts, and various documents and designs. Figures, related information, etc. are stored in association with each other.

The measure proposal system 100 evaluates an event that has occurred in the product development process 3, for example, via each device that executes a plurality of processes 3a to 3c in the product development process 3. In the measure proposal system 100, for example, in the product development process 3, each device that executes steps 3a to 3c via the self-employed communication network 4 connected by the self-employed communication network 4 installed in the target area of the product development process. In addition to evaluating events that occurred in the own process, it can also be used, for example, to evaluate events that occurred in other related processes.

As shown in FIG. 3, for example, the measure proposal system 100 has a defect occurrence corresponding to each process input via a device that executes a plurality of processes 3a, 3b, 3c, etc. in the product development process 3. After acquiring the event, refer to the reference database described later and generate the related information for the evaluation target information. The measure proposal device 1 outputs the display content 1a of the generated proposed measure to the display unit 109 or the like.

The display content 1a shows, for example, the result of evaluating each event that occurred in a plurality of processes 3a, 3b, 3c, etc. in the product development process 3. The measure proposal device 1 displays, for example, as the display content 1a of the proposed measure, information as shown in the display content 1b, the display content 1c, and the display content 1d regarding the related information and the proposed measure.

The measure proposal device 1 shows related information of an event occurring in each process such as "normal" or "defect (process 3b: defect)", and also shows "part b1 and backlash" as shown in the display content 1b, for example. "Parts b1, 80%, image (part b1)" as shown in the display content 1c, and "Process 3b: Countermeasure [list], stay" as shown in the display content 1d, for example. Measures to be completed within process 3b such as shape change [design data] [drawing], related process [process 3a] [process 3c], etc. When there are a plurality of countermeasures, the list, for example, "related steps [step 3a] [step 3c]" is displayed as a step related to the own process (step 3b).

The measure proposal device 1 collects important information such as the cause of the event that occurred in the own process "process 3b", the priority level of the parts related to the countermeasure, the related market defect, and the prohibited items, and does not have a teacher. Information such as learning results, the probability that a defect factor has occurred, the establishment of effective countermeasure parts, and the like may be shown.

As the measure proposal device 1, for example, an electronic device such as a personal computer (PC) is used, and for example, an electronic device such as a smartphone, a tablet terminal, a wearable terminal, an IoT (Internet of Things) device, a Raspberry Pi (registered trademark), etc. A single board computer may be used, and an input device (not shown) such as a microphone or a camera may be built in. For example, when an HMD (Head Mounted Display) with a built-in input device is used as the measure proposal device 1, the evaluator or the like visually recognizes the event that occurred in the process through the display to relate the event that occurred in the process. Be able to recognize information and proposed measures. Therefore, the difficulty level of the quality evaluation work of the measures proposed in the process can be reduced, and the evaluation work time can be shortened.

The measure proposal device 1 displays, for example, display content 1a based on the acquired event data and display content 1a (display content 1b, display content 1c, display content 1d, etc.) of the measure proposed in the process in which the event data is generated. Displayed in unit 109.

For example, when one event data is related to an event occurring in a plurality of other processes, the measure proposal device 1 can separately generate related information to the event occurring in the other process, and the display unit 109 can display the information. Can display related information and proposed measures for the events that occurred in each process. It should be noted that, for example, when generating related information for an event occurring in one process or a proposed measure, it may be based on a plurality of event data.

The evaluation target information includes event data and process information, and may include, for example, measure information. The evaluation target information may include a plurality of event data, and may include, for example, an event that occurred in one step and event data that occurred in another related step. In this case, it is possible to generate related information based on the event data of the event that occurred in a plurality of steps, and it is possible to improve the evaluation accuracy. The evaluation target information may be represented in a bird's-eye view, for example, in a text format, a numerical format such as a text format or a matrix, or, for example, a list or a countermeasure map in which countermeasures and failure cases are associated with each other.

The process information indicates countermeasures for the event of the process in which the event data is generated. The process information includes, for example, a plurality of processes 3a, 3b, 3c, etc. in the product development process 3, and also includes various newly added process information reports and the like. By including the process information in the evaluation target information, it is possible to realize highly accurate evaluation based on the characteristics of each process. Further, by carrying out the evaluation based on the system of each measure, the similarity between the processes can be incorporated into the evaluation target, and the evaluation variation between the processes can be suppressed. As for the process information, in addition to the own process, for example, related processes before and after and other processes may be displayed on the display unit 109 or the like in the same manner as the related information.

The process information is directly input to the measure proposal device 1 by an evaluator or the like so as to be linked to the event data acquired by the measure proposal device 1, for example, and a plurality of process information is stored in the measure proposal device 1 in advance. It may be selected by the measure proposal device 1 based on the event data. When the measure proposal device 1 selects the process information, for example, a learning model stored in the measure proposal device 1 in advance may be used so that the process information can be selected for the acquired event data. In this case, the learning model is generated by known machine learning using event data and process information prepared in advance as learning data.

The process information has information on at least one of the date and time when the event occurred, the place of occurrence, the responder, and the schedule for taking measures against the event generated in the process as event data. The process information may include information on countermeasures in a pre-process, a post-process, and other related processes, for example, depending on the priority of countermeasures in which an event occurs.

The evaluation information may be directly input to the measure proposal device 1 by the evaluator or the like so as to be linked to the event data acquired by the measure proposal device 1, or may be transmitted from, for example, another terminal or the like.

(Measures proposal device 1)
Next, an example of the measure proposal device 1 in the present embodiment will be described with reference to FIG. FIG. 4A is a schematic diagram showing an example of the configuration of the measure proposal device 1 in the present embodiment, and FIG. 4B is a schematic diagram showing an example of the function of the measure proposal device 1 in the present embodiment. be.

As shown in FIG. 4A, for example, the measure proposal device 1 stores a housing 10, a CPU (Central Processing Unit) 101, a ROM (Read Only Memory) 102, a RAM (Random Access Memory) 103, and the storage. A unit 104 and I / F 105 to 107 are provided. Each configuration 101 to 107 is connected by an internal bus 110.

The CPU 101 controls the entire measure proposal device 1. The ROM 102 stores the operation code of the CPU 101. The RAM 103 is a work area used when the CPU 101 operates. The storage unit 104 stores various information such as evaluation target information and a reference database. As the storage unit 104, for example, in addition to an HDD (Hard Disk Drive), a data storage device such as an SSD (Solid State Drive) or a floppy disk is used. For example, the measure proposal device 1 may have a GPU (Graphics Processing Unit) (not shown). Having a GPU enables higher-speed arithmetic processing than usual.

The I / F 105 is an interface for transmitting and receiving various information with devices that execute a plurality of processes 3a, 3b, 3c, etc. in the product development process 3, and is installed in, for example, a target area of the product development process. It may be an interface for transmitting and receiving various information with other devices, a server 5, and the like via the self-employed communication network 4. The I / F 106 is an interface for transmitting / receiving information to / from the input unit 108. For example, a keyboard is used as the input unit 108, and an evaluator or the like who uses the measure proposal device 1 inputs various information or a control command of the measure proposal device 1 via the input unit 108. The I / F 107 is an interface for transmitting and receiving various information to and from the display unit 109. The display unit 109 outputs various information such as related information stored in the storage unit 104, or the processing status of the measure proposal device 1. A display is used as the display unit 109, and a touch panel type may be used, for example.

<Reference database>
In the reference database stored in the storage unit 104, between a plurality of data included in the past evaluation target information acquired in advance and a plurality of data included in the reference information associated with the past evaluation target information. Based on the relationship (for example, the number of occurrences, the occurrence time, the occurrence area, etc.), the learning model having the similarity having the similarity associated with the relationship is stored. In the reference database, for example, the similarity associated with the past evaluation target information and the reference information, or the similarity associated with the relationship based on the relationship with a plurality of data contained in the reference information associated with the past evaluation target information. May be remembered. The similarity is constructed by machine learning using a plurality of learning data, for example, using past evaluation target information and reference information as a set of learning data.

In this case, for example, similarity indicates the degree of connection between many-to-many information (a plurality of data included in past evaluation target information, a pair, and a plurality of data included in reference information). Similarities are updated from time to time during machine learning. That is, similarity indicates, for example, a function optimized based on past event data and reference information. Therefore, related information to the evaluation target information is generated using the similarity constructed based on all the results of evaluating the events that have occurred in the process in the past. Thereby, even when the event generated in the process has a configuration state in which it is combined with other parts or the like, the optimum related information can be generated.

In addition, the reference database can quantitatively generate optimal related information even when the evaluation target information is the same as or similar to the past evaluation target information or when it is dissimilar. By increasing the generalization ability when performing machine learning, it is possible to improve the evaluation accuracy for unknown evaluation target information, and improve the quality assurance and manufacturing efficiency in the entire development and manufacturing process or in the own process.

The similarity may have, for example, a plurality of similarities indicating the degree of connection between the plurality of data included in the past evaluation target information and the plurality of data included in the reference information.

The past evaluation target information indicates the same type of information as the evaluation target information described above. The past evaluation target information includes, for example, a plurality of evaluation target information acquired when evaluating an event that occurred in a process in the past.

The reference information is linked to the past evaluation target information and shows information about the event that occurred in the process. The reference information indicates the evaluation based on the status, state, or influence of the event that occurred in the process (for example, "normal", "defect", "non-defective product collection", etc.), and also measures information on the cause of the event that occurred in the process. May include. The specific contents included in the reference information can be arbitrarily set.

The measure information includes, for example, the work name of a specific event factor such as change, replacement, repair, etc. (for example, "process 3b: countermeasure [list]", "change of stay shape [design data] [drawing]"), and related process. Information (for example, "related steps [step 3a] [step 3c]") is shown. The various event factors extend to at least a portion or other related process of the event that occurred in the process.

Here, using FIG. 5, for example, an example of correspondence between a quality assurance stage in the target department A30 (quality assurance department) and a plurality of stages A001 of each process A01 in the design stage of the department A31 (design department). To explain. FIG. 5 shows an example of correspondence between the quality assurance stage and the design stage of the measure proposal system in this embodiment.

As shown in FIG. 5, the measure providing system 100 acquires, for example, information on the collection of non-defective products and information on market defects from the department A30 (quality control department) at the sales / service stage. The measure providing system 100 predicts the life of a preset product near the life of the product, and measures the countermeasure (for example, even if the product has a short life, if there is no problem as an individual component constituting the product, the part is provided. Decide what to reuse after cleaning / inspection, etc.). At the stage of market defect, the department 30 analyzes the defect of the product, investigates the cause, and takes countermeasures (for example, which part of the product the market defect occurred in, whether there is a related part, or whether to change the design). Etc.). For example, the department A30 inputs various events, countermeasures, failure cases, etc. into the countermeasure map A301 shared in advance based on each determined countermeasure for each component constituting the product (countermeasure A300). ).

In the countermeasure map A301, for example, "1" is input as information indicating the contact point of the parts related to the countermeasure, the priority level of the response (3 levels, etc.) is input, and further, important countermeasures for the related market defects are input to each part. You may add it every time. The countermeasure map A301 is shared among the departments. For various types of information, for example, market site search results (such as the latest defect occurrence status and countermeasure information) may be input. The priority level input to the countermeasure map A301 is, for example, a product module, a part, a name, or, for example, a case level (for example, level 1: large damage, level 2: during damage, level 3: normal countermeasure, etc.) in the design process. It is input in association with.

The measure providing system 100 refers to various reference databases in the department A31 (design department), for example, via the measure map A301 in which the measures are input in the department A30, and examines the search results under design and various measures. (Countermeasure A302). For example, referring to the countermeasure map A301, discrimination is made based on "1" given as information indicating the contact points related to the countermeasure and the related parts (for example, matching between the parts and the countermeasure), and the priority of the countermeasure to be implemented for each part. You may decide such as. Department A31 (design department) implements each measure.

The measure providing system 100 shows, for example, a measure in which the measure of the module or the component constituting the product, which is input via "1" in the measure map A301, is given the highest priority. For example, the measure providing system 100 shows measures for a module to which "1" is not input in the measure map A301 but to which "1" is given, or other parts related to the parts. In the measure providing system 100, for example, "1" is not input to the measure map A301, but the relationship of "1" in the measure map (for example, the number of occurrences of various events, the state and tendency, the occurrence time, the occurrence area). The similarity may be determined based on the above. For the similarity, for example, machine learning using the similarity between the relationship between the past evaluation target information and the reference information associated with the relationship as learning data may be used. The measure providing system 100 selects, for example, the optimum reference information associated with the solution calculated based on the similarity, generates related information based on the optimum reference information, and generates the generated related information based on the process information. Output to own process and related processes.

For example, in determining similarity, the measure providing system 100 is between a plurality of data included in the past evaluation target information acquired in advance and a plurality of data included in the reference information associated with the past evaluation target information. Based on the relationship in, the reference database in which the similarity having the similarity associated with the relationship is stored may be referred to and the countermeasure may be shown. The measure providing system 100 refers to the reference database based on the acquired evaluation target information, selects the optimum reference information associated with the solution calculated based on the similarity, and generates related information based on the optimum reference information. do.

The measure providing system 100 uses the measure map A301 shared by each department, for example, in the search for parts correspondence at each stage by the department A31 (design department), "phase: design" and "keyword: fuel injector" at the time of search. When such information is input, the related information can be displayed on the designer terminal (not shown) as the related information A303. Further, the measure providing system 100 may associate, for example, the component attribute of the E-BOM (design bill of materials) with the measure displayed in the measure map A301, and display it as the related information A304 as a measure list. The measure providing system 100 receives specific measures against defects in the displayed measure list, for example, from the design department A31, and various received information may be added to the measure map A301 for each product or part. good.

Further, the measure providing system 100 outputs related information and countermeasure information related to the work in each process to a dedicated processing terminal in each process such as CAD-related equipment in the design process via the PLM platform, for example. You may do so. In the measure providing system 100, for example, in the design department A31, for example, the design department, the design department information indicating that the person is a designer, the product being designed or the parts constituting the product are designed part information, and the status indicating the progress of the design work. Based on the information, etc., various information input from the related department using the countermeasure map A301, the reference database, etc. are referred to, the related information based on the optimum reference information is generated, and the generated related information is used as the processing terminal. It may be output. The countermeasure map A301 is shared among various departments in multiple processes in the factory, for example, on the PLM platform, and information that identifies each department, each person in charge, each work, a manufacturing base (production base), a manufacturing date and time, and a process. Appropriate related information and countermeasure information may be output in real time based on the information.

The measure providing system 100 is, for example, on the design screen of the CAD terminal of the design department A31 (for example, related information A303, etc.), related information as information to be taken measures in design, and information linked to the measures (for example, related information A304, etc.). ) May be superimposed and displayed. As a result, for example, information related to events that occur outside the design process can be reflected in the design, quality improvement of events that occur in the design process, etc., quality assurance of the entire development and manufacturing process, or manufacturing efficiency of the own process. Can be improved.

As a result, the design department A31 can confirm the list items while looking at the design screen (related information A303), and various measures can be reflected in the design. If the design department 31A finds a countermeasure that is not output in the list of the countermeasure map A301, the design department 31A may additionally input the countermeasure.

In the measure providing system 100, the measure A305 determined by the design department A31 may be updated to the measure map A301 after being confirmed by the quality assurance department A30. This makes it possible to horizontally develop, for example, designing other vehicle models, product development at other production bases, and future product development.

Note that the similarity may indicate, for example, various relationships (number of occurrences of events, occurrence time, future prediction, occurrence area, etc.) between past evaluation target information and reference information, and the degree of connection. In this case, the similarity may be determined based on various relationships. By using similarity based on various relationships, a plurality of data included in the reference information is used for each of the plurality of data (“data A” to “data C”) included in the past evaluation target information. The degree of relationship (“reference A” to “reference C”) can be associated and stored. Therefore, for example, through similarity, it is possible to link a plurality of data included in the reference information to one data included in the past evaluation target information, and it is possible to generate multifaceted related information. be able to.

For example, the similarity is associated with a plurality of data included in the past evaluation target information and a plurality of data included in the reference information. For a plurality of data, for example, a contact relationship (for example, flag "1") is attached to a component related to a countermeasure between the respective data. It has a plurality of similarities associated with the connection status, type, etc. of the relationship (flag "1"). The similarity is shown in three or more steps, such as percentage, ten steps, or five steps, and is shown, for example, by the characteristics of the line (eg, thickness, etc.). For example, the "data A" included in the past evaluation target information indicates a similarity AA "85%" with the "reference A" included in the reference information, and the "reference B" included in the reference information. The similarity AB "55%" between them is shown. That is, the "similarity" indicates the degree of connection between each data, and for example, the higher the degree of similarity, the stronger the connection of each data. When constructing the similarity by the above-mentioned machine learning, the similarity may be set to have three or more levels of similarity.

The past evaluation target information may be stored in a reference database by dividing, for example, past event data and past process information. In this case, the similarity having the similarity associated with the relationship is stored based on the relationship between the combination of the past event data and the past process information and the plurality of data included in the reference information. The similarity is calculated. In addition to the above, the past evaluation target information may be stored in the reference database by dividing the past measure information.

The past evaluation target information may include, for example, synthetic data and similarity. Synthetic data is indicated by three or more levels of similarity with past event data or past process information. The composite data may be stored in the reference database in the form of a numerical value, a matrix, a histogram, or the like, or may be stored in the form of, for example, an image or a character string.

FIG. 4B is a schematic diagram showing an example of the function of the measure proposal device 1. The measure proposal device 1 includes a communication unit 11, an acquisition unit 12, a related information retrieval unit 13, an output unit 14, and a storage unit 15, and may have, for example, an update unit 16. Each function shown in FIG. 4B is realized by the CPU 101 executing a program stored in the storage unit 104 or the like with the RAM 103 as a work area, and may be controlled by, for example, artificial intelligence.

<Communication unit 11>
The communication unit 11 connects to the self-employed communication network 4 installed in the target area of the product development process and performs various communications. The communication unit 11 is connected to the self-employed communication network 4, and is a communication network (Local 5G communication) different from the band allocated by the communication carrier, for example, to the manufacturing company as its own communication infrastructure on the premises. Communication is performed via the installed self-employed communication network 4. The communication unit 11 may be further connected to a communication network such as the general Internet to perform various communications.

<Acquisition unit 12>
The acquisition unit 12 acquires evaluation target information including event data and process information. The acquisition unit 12 acquires various event data from a device or the like that executes a plurality of steps 3a, 3b, 3c, etc. in the product development process 3, and also obtains, for example, a plurality of steps 3a from other connected devices. Acquire event data related to process 3b, process 3c, and the like.

The acquisition of related event data is acquired by referring to the database based on, for example, the part number associated with the event that has occurred. In addition to acquiring the process information input in advance from the evaluator or the like, the acquisition unit 12 may acquire the process data corresponding to the event data and the related information related to the process from, for example, another device or the like.

When the acquisition unit 12 acquires, for example, the measure information, the acquisition unit 12 acquires it as evaluation target information together with the event data. The frequency and cycle for the acquisition unit 12 to acquire the evaluation target information is arbitrary.

The acquisition unit 12 receives various information transmitted to the measure proposal device 1. The acquisition unit 12 may receive various information such as variety information and harvest information transmitted from an external terminal such as another terminal via, for example, the self-employed communication network 4 and the I / F 105.

The acquisition unit 12 may refer to the learning model stored in the storage unit 104, for example, select the process information corresponding to the event data, and acquire it as the evaluation target information.

<Related Information Retrieval Unit 13>
The related information retrieval unit 13 refers to the reference database and generates related information for the evaluation target information. For example, the related information search unit 13 uses the evaluation target information as input data, selects the optimum reference information associated with the solution calculated based on the similarity, and generates the related information based on the optimum reference information.

When the related information retrieval unit 13 refers to a reference database, for example, it selects data that is the same as or similar to the data included in the evaluation target information (for example, "data A": the first data). As the first data, data that partially or completely matches the evaluation target information is selected, and for example, similar data is selected. When the evaluation target information is represented by a numerical value such as a matrix, the numerical range included in the selected first data may be set in advance.

The related information retrieval unit 13 selects the reference information associated with the selected first data and the similarity between the selected first data and the reference information (first similarity), and selects the selected reference information and the first. Generate relevant information based on similarity. The first similarity degree may be selected from the similarity constructed in advance, or may be calculated by the related information retrieval unit 13.

For example, the related information retrieval unit 13 is based on the data "reference A" included in the reference information associated with the first data "data A" and the relationship between the "data A" and the "reference A". 1 Select the similarity (similarity AA) "85%". The reference information and the first similarity may include a plurality of data. In this case, in addition to the above-mentioned "reference A" and "85%", the reference information "reference B" associated with the first data "data A" and the second between "data A" and "reference B". 1 Similarity (similarity AB) "55%" may be selected to generate relevant information based on "Reference A" and "85%", as well as "Reference B" and "23%".

The related information may include evaluation target information. The related information may indicate the factor (occurrence factor) of the event that occurred in the process represented by the probability by using, for example, the reference information and the similarity.

The related information retrieval unit 13 uses format data such as an output format stored in advance in the storage unit 104 or the like to allow the evaluator or the like to understand the above-selected reference information and the first similarity degree (for example). Generates related information indicating (character string). For example, a known technique may be used for setting the format when generating related information.

The related information retrieval unit 13 determines the content of the related information based on, for example, the selected first similarity degree. For example, the related information retrieval unit 13 generates related information based on the reference information associated with the first similarity of "50%" or more, and associates the reference information associated with the first similarity of less than "50%". It may be set not to be reflected in the information. As for the determination criteria based on the first similarity degree, for example, an evaluator or the like may set a threshold value or the like in advance, and the threshold range or the like can be arbitrarily set. Further, the related information retrieval unit 13 may determine the content of the related information based on, for example, the result of calculating two or more first similarity degrees or the comparison of two or more first similarity degrees.

<Output unit 14>
The output unit 14 outputs related information. The output unit 14 transmits related information to the display unit 109 via the I / F 107, and also transmits related information to another terminal or the like via, for example, the I / F 105. The output unit 14 outputs, for example, data for displaying an image that reproduces the surface state of the event that occurred in the process shown in FIG. 4 to the display unit 109 or the like.

<Memory unit 15>
The storage unit 15 retrieves various information such as a reference database stored in the storage unit 104 as needed. The storage unit 15 stores various information acquired or generated by the respective configurations 11, 13 to 16 in the storage unit 104.

<Display unit 109>
The display unit 109 displays related information. As shown in FIG. 3, for example, the display unit 109 displays the display content 1a and the display content 1b to the display content 1d as the content of the related information of the event generated in the process. The display content 1a shows related information including an event generated in the process based on the event data acquired by the acquisition unit 12 and a plurality of display contents. Related information includes links in each area of display contents 1b to 1d or in the area (for example, a rectangular frame of display contents 1b to display contents 1d, or links (for example, [ list ], [ design data ], [ drawing ], []. It is displayed for the event that occurred in the process to be evaluated via [ Step 3a ] and [ Step 3c ]). Thereby, for example, even when the event that occurred in a plurality of steps is evaluated at once, each of them is displayed. Information related to events that have occurred in the process and measures to be proposed can be displayed. In addition, the display unit 109 may display related information using only a list or a character string, for example. In the above display method, the related information may be displayed. , Known techniques can be used.

<Update part 16>
The update unit 16 updates, for example, the reference database. When the update unit 16 newly acquires the relationship between the past evaluation target information and the reference information, the update unit 16 reflects the relationship in the similarity. For example, when the evaluator or the like determines the accuracy of the related information or the content of the proposed measure based on the related information generated by the related information search unit 13, and the measure proposal device 1 acquires the determination result, the update unit 16 performs. , Update the similarity contained in the reference database based on the judgment result.

<Product development process 3>
The product development process 3 includes a plurality of steps. The product development process 3 is, for example, various devices for executing a product development process 3 in a certain product development, for example, a process 3a for selling / servicing a product, a process 3b for planning a product, a process 3c for designing a product, and the like. , Performed by equipment such as measuring instruments, processing robots, and sensors. The product development process 3 is executed by various devices that execute, for example, the production process for producing the product, the process for producing the product, the marketing concept and design process, and the sales / service CRM process shown in FIG. May be done. The product development process 3 is connected to the self-employed communication network 4 via a device that performs a plurality of processes, and cooperates with a device that executes a plurality of processes of the product development process 3 in, for example, the site or area of a manufacturing company. May be good.

<Self-employed communication network 4>
The self-employed communication network 4 is constructed as a communication network (Local 5G communication) different from the band allocated by the communication carrier, for example, to a manufacturing company. The self-employed communication network 4 connects a plurality of processes by the measure proposal system 100, for example, as a product development process 3 in a manufacturing factory.

<Server 5>
For example, the server 5 stores the above-mentioned various information. For example, various information sent via the self-employed communication network 4 is stored in the server 5. For example, the server 5 stores the same information as the storage unit 104, and may send and receive various information to and from one or more measure proposal devices 1 via the self-employed communication network 4. That is, the measure proposal device 1 may use the server 5 instead of the storage unit 104.

<Other equipment>
As another device (not shown), for example, a device embodied in an electronic device is used as in the measure proposal device 1. The other terminal indicates, for example, a central control device capable of communicating with a plurality of measure proposal devices 1. Other terminals can be connected to, for example, a plurality of measure proposal devices 1, and can acquire related information generated by each measure proposal device 1. This makes it possible to analyze information related to events that have occurred in multiple processes, for example, to improve the quality of events that have occurred in the process, and to improve the quality assurance and manufacturing efficiency of the entire development and manufacturing process or its own process. Is possible.

(Example of operation of measure proposal system 100)
Next, an example of the operation of the measure proposal system 100 in this embodiment will be described. FIG. 6 is a flowchart showing an example of the operation of the measure proposal system 100 in the present embodiment.

<Communication means S110>
The communication unit 11 connects to the self-employed communication network 4 installed in the target area of the product development process 3 (communication means S110). The communication unit 11 is connected via, for example, a self-employed communication network 4 based on a communication processing request from each device that executes a plurality of processes 3a, 3b, 3c, etc. in the product development process 3. The proposal device 1, the database 2, or the server 5 and the data related to the events occurring in the respective processes 3a to 3c, the related information in the measure proposal device 1, and the like are transmitted and received between the respective processes.

<Acquisition means S120>
The acquisition unit 12 acquires evaluation target information including an event generated in the process and process data (acquisition means S120). The acquisition unit 12 acquires, for example, event data and process data received from the equipment of each process as evaluation target information. For example, the acquisition unit 12 has "There is a market defect of stay parts (part number XX): XX cases" as a sales process in the sales zone, and "Change of stay shape (part number XX)" in the development process of the development zone: XX. Acquire the events that occurred in each process such as "○ cases" and "Change of stay design (part number XX): XX cases" in the design process of the design area. The acquisition unit 12 stores the evaluation target information in the storage unit 104, for example, via the storage unit 15.

The acquisition unit 12 acquires evaluation target information including, for example, measure information. The measure information is input to the measure proposal device 1 by an evaluator or the like so as to be linked to the event data in advance, and the acquisition unit 12 selects each information suitable for the event data based on the event data, for example. You may. In this case, the acquisition unit 12 selects each information suitable for the event information from the plurality of measure information stored in the storage unit 104 in advance.

For example, when the events generated in the plurality of steps 3a to 3c are acquired, the acquisition unit 12 acquires the plurality of event data generated by the devices of the plurality of processes as one evaluation target information. The acquisition unit 12 may acquire the evaluation target information every time the event data is generated, or may receive, for example, the event data generated in an arbitrary period at once and acquire the evaluation target information.

<Related information retrieval means S130>
Next, the reference database is referred to to generate related information for the evaluation target information (related information retrieval means S130). The related information retrieval unit 13 acquires the evaluation target information acquired by the acquisition unit 12, and acquires, for example, the reference database stored in the storage unit 104. For example, the related information search unit 13 uses the evaluation target information as input data, and selects the optimum reference information linked to the solution calculated based on the similarity linked to the relationship based on the relationship shown by the function or the like. And generate relevant information based on the optimal reference information. At this time, for example, the related information search unit 13 may select a plurality of reference information for one evaluation target information.

The related information search unit 13 may generate one related information for one evaluation target information, or may generate one related information for a plurality of evaluation target information, for example. The related information retrieval unit 13 generates related information by using format data such as an output format stored in the storage unit 104, for example. The related information retrieval unit 13 stores the related information in the storage unit 104, for example, via the storage unit 15.

<Output means S140>
Next, the related information is output (output means S140). The related information may include various measure information proposed in association with the related information. The output unit 14 outputs related information to the display unit 109 and the like. The output unit 14 may output to another terminal or the server 5 via, for example, the self-employed communication network 4.

The output unit 14 designates, for example, a display content 1a showing an event that occurred in a process based on event data and a proposed measure, and an event that occurred in the process to be evaluated among the display contents 1a, and becomes an evaluation target. Information for displaying the information related to the event generated in the process on the display unit 109 is output to the display unit 109. As a result, the display unit 109 displays related information including the display content 1a and the related display content 1b to 1c, and the proposed measures.

<Update means S150>
In addition, for example, when the relationship between the past evaluation target information and the reference information is newly acquired, the relationship may be reflected in the similarity (update means S150). For example, when the measure proposal device 1 acquires a determination result in which the evaluator or the like determines the accuracy of the related information based on the related information generated by the related information search unit 13, the update unit 16 stores the determination result in the reference database. Update the memorized similarity. In addition to the similarity, the updating unit 16 may update the relationship, for example.

As a result, the operation of the measure proposal system 100 in the present embodiment is completed. The timing when the update means S150 is implemented is arbitrary.

According to the present embodiment, the related information retrieval unit 13 refers to the reference database and generates related information for the evaluation target information. Reference information includes process information. Therefore, it is possible to generate related information based on the result of evaluating the events that have occurred in the process in the past. As a result, it is possible to improve the accuracy of the measures proposed in the process, and to improve the quality assurance and manufacturing efficiency of the entire development and manufacturing process or the own process. In addition to the related information, the related information retrieval unit 13 may output (propose), for example, a measure for a problem to each display unit 109 or the like in real time by a device, a system, or another device in each process. ..

Further, according to the present embodiment, the evaluation target information includes process information. Therefore, it is possible to realize an evaluation based on the characteristics of event factors that differ for each process. This makes it possible to further improve the accuracy of the measures proposed in the process, and improve the quality assurance and manufacturing efficiency of the entire development and manufacturing process or the own process.

Further, according to the present embodiment, the evaluation target information includes the measure information. Therefore, it is possible to realize the proposal of the measures generated in different processes depending on the conditions of the measures. This makes it possible to further improve the accuracy of evaluating events that have occurred in a plurality of steps. In addition, since related information associated with the countermeasure conditions can be obtained, it is possible to identify the conditions that cause the event to occur and to grasp the work associated with the change of the countermeasure conditions. This makes it possible to improve the measures proposed in the process.

Further, according to the present embodiment, the display unit 109 displays information on measures for the own process, the previous process, the subsequent process, and the other processes related to the event generated in the process to be evaluated. Therefore, even when different events occur in a plurality of related processes, the related information can be easily known as one event data. As a result, it is possible to confirm the priority of sorting the events and countermeasures that occurred in the process based on the related information, and it is possible to implement the countermeasures efficiently and reliably.

Further, according to the present embodiment, the similarity is constructed by machine learning using the past evaluation target information and the reference information as learning data. Therefore, even when evaluating unknown evaluation target information different from past evaluation target information, quantitative evaluation can be performed. This makes it possible to further improve the evaluation accuracy and improve the quality assurance and manufacturing efficiency of the entire development and manufacturing process or the own process.

Further, according to the present embodiment, when the update unit 16 newly acquires the relationship between the past evaluation target information and the reference information, the update unit 16 reflects the relationship in the similarity. Therefore, the similarity can be easily updated, the evaluation accuracy can be continuously improved, and the quality assurance and manufacturing efficiency of the entire development and manufacturing process or the own process can be improved.

Further, according to the present embodiment, the communication means for performing the communication means S110, the acquisition means for performing the acquisition means S120, the related information retrieval means for performing the related information retrieval means S130, and the output means for performing the output means S140 are used as a measure proposal board. May be provided. As a result, it can be mounted on various devices in a factory, for example. Therefore, it is possible to improve the accuracy of the measures proposed in the process, and to improve the quality assurance and manufacturing efficiency of the entire development and manufacturing process or the own process.

Although embodiments of the present invention have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These novel embodiments can be implemented in various other embodiments, and various omissions, replacements, and changes can be made without departing from the gist of the invention. These embodiments and modifications thereof are included in the scope and gist of the invention, and are also included in the scope of the invention described in the claims and the equivalent scope thereof.

1: Measure proposal device 1a: Display content 1b: Display content 1c: Display content 1d: Display content 2: Database 3: Product development process 3a: Process 3b: Process 3c: Process 4: Self-employed communication network 5: Server 10: Housing 11: Communication unit 12: Acquisition unit 13: Related information search unit 14: Output unit 15: Storage unit 16: Update unit 100: Measure proposal system 101: CPU
102: ROM
103: RAM
104: Storage unit 105: I / F
106: I / F
107: I / F
108: Input unit 109: Display unit 110: Internal bus A01: Process A001: Stage A10: Equipment A11: Equipment A12: Equipment A13: Equipment A20: Issue A21: Issue A22: Issue A23: Issue A30: Department A31: Department A300: Countermeasure A301: Countermeasure map A302: Countermeasure A303: Related information A304: Related information A305: Measure b1: Parts S110: Communication means S120: Acquisition means S130: Related information search means S140: Output means S150: Update means

Claims (8)

It is a measure proposal device that proposes measures in multiple processes in the product development process.
A communication unit connected to a self-employed communication network installed in the target area of the product development process,
An acquisition unit that acquires evaluation target information including event data related to an event that occurred in the process and process information indicating the process in which the event data was generated via the self-employed communication network connected by the communication unit. When,
Based on the relationship between a plurality of data included in the past evaluation target information acquired in advance and a plurality of data included in the reference information associated with the past evaluation target information, the relationship is linked to the relationship. A reference database that stores similarities with similarities,
Based on the evaluation target information acquired by the acquisition unit, the reference database is referred to, the optimum reference information associated with the solution calculated based on the similarity is selected, and the optimum reference information is used. A related information search unit that generates related information, and
A measure proposal device including an output unit that outputs the related information generated by the related information search unit to the own process and a related process based on the process information. The measure proposal device according to claim 1, wherein the reference information stored in the reference database includes measure information of the event generated in the product development process. The measure proposal device according to claim 1 or 2, wherein the related information generated by the related information search unit includes the measure information in the process. The evaluation target information includes product development information having information on at least one of product information, component information, design information, defect information, priority information, and application information related to an event occurring in the process. The measure proposal device according to any one of items 1 to 3. The similarity is any one of claims 1 to 4, characterized in that the similarity is constructed by machine learning using the relationship between the past evaluation target information and the reference information as learning data. Described measure proposal device. Claims 1 to 5, wherein when a relationship between the past evaluation target information and the reference information is newly acquired, an update unit that reflects the relationship in the similarity is further provided. The measure proposal device described in any one of the items. It is a measure proposal system that proposes measures in multiple processes in the product development process.
A communication unit connected to a self-employed communication network installed in the target area of the product development process,
An acquisition means for acquiring evaluation target information including event data related to an event that occurred in the process and process information indicating the process in which the event data was generated via the self-employed communication network connected by the communication unit. When,
Based on the relationship between a plurality of data included in the past evaluation target information acquired in advance and a plurality of data included in the reference information associated with the past evaluation target information, the relationship is linked to the relationship. A database that stores similarities with similarities,
Based on the evaluation target information acquired by the acquisition means, the reference database is referred to, the optimum reference information associated with the solution calculated based on the similarity is selected, and the optimum reference information is used. Related information retrieval means to generate related information,
An output means for outputting the related information generated by the related information retrieval means to the own process and related processes based on the process information.
A measure proposal system characterized by being equipped with. It is a measure proposal board that proposes measures in multiple processes in the product development process.
Communication means to connect to the self-employed communication network installed in the target area of the product development process,
Acquisition means for acquiring evaluation target information including event data related to an event occurring in the process and process information indicating the process in which the event data is generated via the self-employed communication network connected by the communication means. When,
Based on the relationship between a plurality of data included in the past evaluation target information acquired in advance and a plurality of data included in the reference information associated with the past evaluation target information, the relationship is linked to the relationship. A database that stores similarities with similarities,
Based on the evaluation target information acquired by the acquisition means, the reference database is referred to, the optimum reference information associated with the solution calculated based on the similarity is selected, and the optimum reference information is used. Related information search means to generate related information,
An output means for outputting the related information generated by the related information search means to the own process and the related process based on the process information.
A measure proposal board characterized by being equipped with.

Images