State diagnostic system, control method for state diagnostic system, and control program for state diagnostic system

Abstract

To provide a state diagnostic system capable of presenting the proposal content with high accuracy.SOLUTION: A state diagnostic system according to an example of the present disclosure includes: a proposal unit which generates first proposal information for correcting the state of a control system on the basis of state data indicating the state that has occurred in a control system including a control device; a determination unit which determines the similarity between the first proposal information generated by the proposal unit and second proposal information for correcting the state of the control system on the basis of relevant data related to the control system other than the state data; and an output unit which controls the output of the first and second proposal information on the basis of the similarity of the determination unit.SELECTED DRAWING: Figure 3

Description

[Technical field]

[0001] The present disclosure relates to a condition diagnostic system for determining the condition of a control system including a control device, a control method for the condition diagnostic system, and a control program for the condition diagnostic system. [Background technology]

[0002] 2. Description of the Related Art Conventionally, monitoring systems have been proposed that monitor the operating status of machines such as manufacturing equipment in real time and perform fault diagnosis.

[0003] In this regard, a system has been proposed that collects data on machines and, based on the collected data, presents suggestions for removing obstacles (see Patent Document 1).

[0004] On the other hand, there is a problem in that it is not possible to determine whether the proposed content is something that the user really needs, and there is a low probability that the proposal will be accepted by the user. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] JP 2018-5833 A Summary of the Invention [Problem to be solved by the invention]

[0006] The present disclosure is intended to solve the above-mentioned problems, and provides a condition diagnosis system capable of presenting highly accurate proposals, a control method for a condition diagnosis system, and a control program for a condition diagnosis system. [Means for solving the problem]

[0007] A condition diagnosis system according to an example of the present disclosure includes a proposal unit that generates first proposal information for correcting a condition of the control system based on condition data indicating a condition occurring in the control system including the control device, a determination unit that determines a similarity between the first proposal information generated by the proposal unit and second proposal information for correcting the condition of the control system based on associated data related to the control system other than the condition data, and an output unit that controls output of the first and second proposal information based on the similarity of the determination unit. With this configuration, it is possible to present highly accurate proposal content.

[0008] The output unit controls the output of the first and second proposal information based on a comparison between the similarity between the first and second proposal information and a first threshold. With this configuration, it is possible to present highly accurate proposal content because the output of the first and second proposal information is controlled based on a comparison between the similarity between the first threshold and the first threshold.

[0009] The output unit outputs the first proposal information when the similarity between the first and second proposal information is equal to or greater than a second threshold higher than the first threshold, and outputs the second proposal information when the similarity between the first and second proposal information is less than the second threshold higher than the first threshold. With this configuration, it is possible to present highly accurate proposal content because the output of the first and second proposal information is controlled based on a comparison between the similarity and the first and second thresholds.

[0010] The first and second proposed information include first and second text information, respectively, and the determination unit determines the similarity based on a first feature amount of a word included in the first text information and a second feature amount of a word included in the second text information. With this configuration, the similarity is determined using the feature amount of the words in the text information, so that a highly accurate determination is possible.

[0011] The determination unit includes a calculation unit that calculates a first feature amount of a word included in the first text information and a second feature amount of a word included in the second text information using a topic model, and a similarity determination unit that determines the similarity between the first feature amount calculated by the calculation unit and the second feature amount using a similarity function. With this configuration, the similarity is determined using the similarity function, so that highly accurate determination is possible.

[0012] The proposal unit includes an analysis unit that analyzes a status pattern of the status data, and a generation unit that generates, as first proposal information, one of a plurality of proposal files corresponding to the plurality of status patterns, according to the status pattern analyzed by the analysis unit. With this configuration, the status pattern is analyzed and the first proposal information is generated according to the analyzed status pattern, so that it is possible to generate highly accurate proposal information.

[0013] A control method for a condition diagnosis system according to an example of the present disclosure includes the steps of: generating first proposal information for correcting a condition of the control system based on condition data indicating a condition occurring in the control system including a control device; determining a similarity between the generated first proposal information and second proposal information for correcting the abnormality based on related data related to the control system other than the condition data; and outputting at least one of the first and second proposal information based on the similarity. With this configuration, it is possible to present proposal content with high accuracy.

[0014] A control program for a condition diagnosis system according to an example of the present disclosure causes a computer to execute the steps of: generating first proposal information for correcting a condition of a control system based on condition data indicating a condition occurring in the control system including a control device; determining a similarity between the generated first proposal information and second proposal information for correcting the abnormality based on related data related to the control system other than the condition data; and outputting at least one of the first and second proposal information based on the similarity. With this configuration, it is possible to present highly accurate proposal content. Effect of the Invention

[0015] The condition diagnosis system, the control method for a condition diagnosis system, and the control program for a condition diagnosis system disclosed herein are capable of presenting highly accurate proposals. [Brief description of the drawings]

[0016] [Figure 1] FIG. 2 is a diagram showing a specific example of a control system including a control device according to the first embodiment. [Diagram 2] 2 is a block diagram showing an example of a hardware configuration of a control device according to the present embodiment. FIG. [Diagram 3] 2 is a block diagram showing an example of a functional configuration of a control device according to the present embodiment; FIG. [Figure 4] FIG. 2 is a diagram illustrating functional blocks related to a state diagnosis of the control system 1 according to the embodiment. [Diagram 5] 1A to 1C are diagrams illustrating abnormality cause patterns and countermeasures in a control system 1 according to an embodiment. [Figure 6] 11 is a diagram illustrating an example of a proposed file FA according to an embodiment. FIG. [Figure 7] FIG. 11 is a flow diagram illustrating a process of a proposal unit 11 according to the embodiment. [Figure 8] FIG. 11 is a diagram illustrating second proposal information according to an embodiment. [Figure 9] 11 is a flow diagram illustrating the process of a determination unit 14 and an output unit 17 according to the embodiment. FIG. [Figure 10] 11 is a diagram for explaining generation of a word frequency table for each of a proposal file and a needs file. FIG. [Figure 11] FIG. 2 is a diagram for explaining a concept of generating a topic model according to an embodiment. [Figure 12] FIG. 11 is a flow diagram illustrating details of an output determination process according to the embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0017] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment of the present invention will be described in detail with reference to the drawings. In the drawings, the same or corresponding parts are designated by the same reference characters and the description thereof will not be repeated.

[0018] <System configuration> FIG. 1 is a diagram showing a specific example of a control system including a control device according to the first embodiment.

[0019] 1, the control system 1 includes a control device 100, an HMI (Human Machine Interface) 200, a production line 300, and a server 500. The control device 100, the HMI 200, and the server 500 are communicatively connected via an information network 6. The control device 100 and one or more devices included in the production line 300 are communicatively connected via a control network 4.

[0020] The control device 100 is typically a programmable logic controller (PLC), and controls one or more devices included in the production line 300.

[0021] The HMI 200 includes a function of presenting information to a user and a function of accepting operations from the user. In this embodiment, the HMI 200 provides the user with suggested information for correcting the state of the control system 1.

[0022] The production line 300 includes one or more devices for producing a product. The production line 300 illustrated in FIG. 1 produces painted metal plates 400. The production line 300 includes a paint preparation process 310, a painting process 320, a drying process 330, and an inspection process 340.

[0023] The equipment installed in the paint preparation process 310 includes a raw material feeder 311, an agitator 312, and a paint storage container 313. The raw material feeder 311 is a device that feeds paint raw materials (pigments, resins, additives, solvents, etc.) into a container. The agitator 312 agitates and mixes the raw materials in the container. The paint storage container 313 stores the paint at an appropriate temperature (paint storage temperature) to maintain the viscosity of the paint within a predetermined range. Explanatory variables related to the operation of the equipment installed in the paint preparation process 310 include the paint dilution rate, the agitation speed, and the paint storage temperature.

[0024] The equipment installed in the painting process 320 includes an applicator 321 and a belt conveyor 322. The applicator 321 uses compressed air to spray paint supplied from a paint storage vessel 313 onto a metal plate 400 being transported by the belt conveyor 322.

[0025] The devices installed in the drying process 330 include a dryer 331 and a belt conveyor 332. The dryer 331 heats the metal plate 400 being transported by the belt conveyor 332, thereby drying the paint on the metal plate 400.

[0026] Values ​​relating to the operation of the equipment installed in the paint preparation process 310, the painting process 320 and the drying process 330 are collected by the control device 100.

[0027] The inspection process 340 is a process for measuring the coating thickness of the metal plate 400. The coating thickness may be measured by an operator, or may be measured automatically using a coating thickness measuring device.

[0028] The server 500 provides the user with other suggested information for correcting the state of the control system 1.

[0029] <Control device hardware configuration> FIG. 2 is a block diagram showing an example of a hardware configuration of the control device according to the present embodiment.

[0030] Referring to FIG. 2, the control device 100 includes a processor 102 such as a CPU (Central Processing Unit) or an MPU (Micro-Processing Unit), a chipset 104, a main memory 106, a storage 110, a control system network controller 120, an information system network controller 122, a USB controller 124, and a memory card interface 126.

[0031] The processor 102 reads out various programs stored in the storage 110, deploys them in the main memory 106, and executes them to realize control calculations for controlling the controlled object. The chipset 104 controls data transmission between the processor 102 and each component.

[0032] The storage 110 stores a system program 112 for implementing basic processing, a user program 114 for implementing control calculations, and a status diagnosis program 116 for diagnosing the status of a control system including a control device.

[0033] The control network controller 120 controls data exchange with devices via the control network 4 .

[0034] The information network controller 122 controls data exchange with the HMI 100 and the like via the information network 6 .

[0035] The USB controller 124 controls the transfer of data to and from external devices (eg, support devices) via a USB connection.

[0036] The memory card interface 126 is configured to allow a memory card 128 to be attached / detached, and allows data to be written to the memory card 128 and various data (such as user programs) to be read from the memory card 128.

[0037] 2 shows an example of a configuration in which the processor 102 executes a program to provide necessary processing, but some or all of the provided processing may be implemented using a dedicated hardware circuit (e.g., ASIC or FPGA). Alternatively, the main part of the control device 100 may be realized using hardware that conforms to a general-purpose architecture (e.g., an industrial PC based on a general-purpose PC). In this case, virtualization technology may be used to run multiple OSs with different uses in parallel, and necessary applications may be executed on each OS.

[0038] <Control device functional configuration> FIG. 3 is a block diagram showing an example of a functional configuration of the control device according to the present embodiment.

[0039] With reference to FIG. 3, the control device 100 includes an IO processing unit 10, a proposal unit 11, a determination unit 14, and an output unit 17.

[0040] The IO processing unit 10 is realized by the processor 102 executing a user program 114 .

[0041] The proposing unit 11 , the determining unit 14 and the output unit 17 are realized by the processor 102 executing the state diagnosis program 116 .

[0042] The proposing unit 11 generates first proposal information for correcting the state of the control system 1 based on state data indicating a state occurring in the control system 1 including the control device 100.

[0043] The determination unit 14 determines the similarity between the first proposal information generated by the proposal unit 11 and second proposal information for correcting the state of the control system 1 based on associated data other than the state data related to the control system 1. In this example, the second proposal information is transmitted from the server 500.

[0044] The output unit 17 outputs at least one of the first and second pieces of proposed information based on the similarity determined by the determination unit .

[0045] The IO processing unit 10 executes collection processing and output processing. Collection processing is processing for collecting data from one or more devices included in the production line 300. Output processing is processing for outputting data obtained by processing to one or more devices included in the production line 300.

[0046] The data collected by the collection process includes status data related to the operation of one or more pieces of equipment included in the production line 300, such as data indicating measured values ​​such as paint dilution ratio, stirring speed, paint storage temperature, feed speed (painting process), air pressure, room temperature, discharge amount, spray distance, feed speed (drying process), and drying temperature. Furthermore, the data collected by the collection process includes data indicating measured values ​​indicating the quality of products produced by the production line 300. The data indicates the measured values ​​of variables and a work ID that identifies an individual product. The work ID is, for example, a serial number.

[0047] The IO processing unit 10 periodically collects the latest data from each process of the production line 300. A certain number of products are retained at each process and between processes of the production line 300. The data collected by the IO processing unit 10 is accumulated.

[0048] The proposing unit 11 includes an analyzing unit 12 and a generating unit 13 . The analysis unit 12 analyzes the status pattern of the status data of the production line 300 collected by the collection process.

[0049] The generating unit 13 generates, according to the state pattern analyzed by the analyzing unit 12, one proposed file out of the plurality of proposed files corresponding to the plurality of state patterns respectively, as first proposed information.

[0050] FIG. 4 is a diagram illustrating functional blocks related to state diagnosis of the control system 1 according to the embodiment.

[0051] Referring to FIG. 4, the server 500 includes a customer information data section 506 , a case data section 504 , and a customer needs estimation section 502 .

[0052] The customer information data section 506 is a database that stores information about customers. The information about customers may include, for example, any information about the customer, such as sales history of equipment, sales history of services, public IR information, sales call records, call center records, and information about web browsing history.

[0053] The case data section 504 is a database that stores information for proposing customer needs or solutions. The information for proposing customer needs or solutions may include information such as service examples, device introduction examples, and training examples.

[0054] The customer needs estimation unit 502 estimates the customer's needs based on information about the customer from the customer information data unit 506, utilizing information from the case data unit 504, and outputs proposal information for correcting the state of the control system 1 to the control device 100.

[0055] The control device 100 includes a proposal data unit 18, a proposal unit 11, a determination unit 14, and an output unit 17. The proposal data unit 18 is provided in the storage 110.

[0056] The proposal unit 11 outputs the proposal information stored in the proposal data unit 18 to the determination unit 14 . The determination unit 14 determines the similarity between the proposed information output from the proposing unit 11 (first proposed information) and the proposed information output from the customer needs estimation unit 502 (second proposed information).

[0057] The output unit 17 controls the output of the proposed information (first proposed information) output from the proposal unit 11 and the proposed information (second proposed information) output from the customer needs estimation unit 502 based on the similarity, which is the judgment result of the judgment unit 14.

[0058] <Explanation of the first proposal information> FIG. 5 is a diagram illustrating abnormality cause patterns and countermeasures in control system 1 according to the embodiment.

[0059] 5(A), status data is collected when an abnormality occurs in the production line 300 of the control system 1, and an abnormality factor pattern is identified according to the frequency of occurrence. In this example, status data P1 to P9 (hereinafter collectively referred to as status data P) obtained by a collection process in the production line 300 is acquired, and a frequently occurring abnormality factor pattern EA is identified.

[0060] Here, the values ​​of the status data P1 to P9 when an abnormality occurs are shown. Countermeasures are shown according to the abnormality pattern. Specifically, the implementation rate of changing the terminal insertion height setting is shown as 70%, the implementation rate of changing the core crimping device setting is shown as 20%, and the implementation rate of adjusting the iron piece crimping stroke is shown as 10%.

[0061] It is possible to identify abnormality factor patterns by analyzing previously collected status data.

[0062] Then, by using statistical information on the implementation ratio of each countermeasure taken against the abnormality factor pattern, it is possible to generate proposal information for the abnormality factor pattern.

[0063] For example, for abnormality pattern EA, it is highly likely that "changing the terminal insertion height settings" will be an effective countermeasure. Furthermore, it is highly likely that the next effective countermeasure will be "changing the core crimping device settings." Furthermore, it is highly likely that the next effective countermeasure will be "adjusting the core crimping stroke."

[0064] Through such analysis, a proposal file FA corresponding to the abnormality factor pattern EA is created in advance.

[0065] FIG. 6 is a diagram illustrating an example of a proposed file FA according to an embodiment. Referring to FIG. 6, a malfunction event and a countermeasure are described as a proposal file FA.

[0066] Specifically, the text information states, "Phenomenon: Real-time status diagnosis detected an abnormality, and there is a possibility that there is an abnormality caused by the iron core components in the iron core crimping process. The diameter of the iron core components may have slightly decreased due to fluctuations in lot switching (or manufacturer change). As a result, there is a tendency for the strength of the crimped joint to be insufficient compared to the standards. Solution: The crimped joint strength can be maintained by increasing the torque of the servo motor of the spin crimping device."

[0067] A proposed file FA is associated with the abnormality factor pattern FA and stored in the proposed data section 18.

[0068] 5(B), in the present example, similarly, status data at the time of an abnormality is collected, and an abnormality factor pattern is identified according to the frequency of the data. In the present example, a case is shown in which status data P1 to P9 obtained by a collection process in the production line 300 is acquired, and a frequently occurring abnormality factor pattern EB is identified.

[0069] Here, values ​​when abnormalities occur are shown for the status data P1 to P9. Countermeasures are shown for each abnormality pattern. Specifically, the implementation rate for changing the terminal bending angle setting is shown as 90%, and the implementation rate for changing the contact height setting is shown as 10%.

[0070] It is possible to identify abnormality factor patterns by analyzing previously collected status data.

[0071] Then, by using statistical information on the implementation ratio of each countermeasure taken against the abnormality factor pattern, it is possible to generate proposal information for the abnormality factor pattern.

[0072] For example, for the abnormality factor pattern FB, it is highly likely that "changing the terminal bending accuracy setting" will be an effective countermeasure. In addition, it is highly likely that "changing the contact height setting" will be an effective countermeasure after that.

[0073] Through such analysis, a proposal file FB corresponding to the abnormality factor pattern EB is created in advance.

[0074] Thereafter, various abnormality factor patterns are identified in a similar manner, and a proposal file corresponding to each abnormality factor pattern is created and stored in the proposal data section 18.

[0075] FIG. 7 is a flow diagram illustrating a process of proposing unit 11 according to the embodiment. 7, the proposal unit 11 acquires state data (step S2). Specifically, the proposal unit 11 acquires state data P and the like obtained by a collection process of the IO processing unit 10 in the production line 300.

[0076] Next, the analysis unit 12 of the proposal unit 11 analyzes the acquired state data P (step S4). As the analysis process, the distribution of the state data P is analyzed.

[0077] Next, the analysis unit 12 of the proposing unit 11 identifies an abnormality factor pattern if an abnormality is present (step S5). Specifically, for example, it is determined whether the distribution of the state data P is similar to a distribution such as an abnormality factor pattern EA, and if so, it is identified as the abnormality factor pattern EA. Alternatively, it is determined whether the distribution of the state data P is similar to a distribution such as an abnormality factor pattern EB, and if so, it is identified as the abnormality factor pattern EB. The same applies to other abnormality factor patterns.

[0078] Next, the generation unit 13 of the proposal unit 11 refers to the proposal data unit 18 according to the abnormality factor pattern identified by the analysis unit 12, and extracts a proposed file that conforms to the corresponding abnormality factor pattern (step S6). For example, when an abnormality factor pattern PA is identified, the generation unit 13 extracts a proposed file FA. When an abnormality factor pattern PB is identified, the generation unit 13 extracts a proposed file FB. The same applies to other abnormality factor patterns.

[0079] Next, the generation unit 13 of the proposal unit 11 generates the extracted proposal file as proposal information and outputs it to the judgment unit 14 (step S8). For example, when the proposal file FA is extracted, the file is output as proposal information. When the proposal file FB is extracted, the file is output as proposal information. The same applies to other cases.

[0080] Then, the process ends (END). <Explanation of the second proposal information> The second proposal information is output from the server 500.

[0081] FIG. 8 is a diagram illustrating the second proposal information according to the embodiment. Referring to FIG. 8, information for correcting the state of control system 1 is written as needs file NA.

[0082] Specifically, it is described that "The analysis results show that optimizing the maintenance cycle of equipment A is effective in improving energy productivity. We will propose an action plan for optimization." In addition, regarding the specific action plan, the following text information is described: "1. Preparation of maintenance history By preparing the maintenance history of equipment A and clearly understanding the maintenance work content and cycle, the maintenance implementation status can be accurately evaluated. 2. Evaluation of maintenance implementation status By evaluating the maintenance implementation status and considering the effectiveness and frequency of maintenance work. 3. Review of maintenance cycle By reviewing the maintenance cycle and changing it as necessary, the optimal maintenance cycle according to the condition of equipment A is set. 4. Implementation of maintenance plan By formulating and implementing the optimal maintenance plan, the operation rate of equipment A is improved. 5. Monitoring of maintenance cycle Even after setting the optimal maintenance cycle, it is necessary to periodically monitor and adjust the maintenance cycle according to the condition of equipment A."

[0083] The other needs files NB and NC are stored in the case data section 504 in a similar manner.

[0084] The needs file is not generated based on status data collected by the control device 100, but is proposed information for correcting the status of the control system based on relevant data related to the control system 1 other than the status data.

[0085] The customer needs estimation unit 502 of the server 500 estimates the customer's needs based on information about the customer from the customer information data unit 506, utilizing information from the case data unit 504, and outputs proposal information for correcting the state of the control system 1 to the control device 100.

[0086] For example, a needs file may be prepared for each customer, or an appropriate needs file for a customer may be selected from a plurality of needs files. A needs file may be generated based on information about the customer using artificial intelligence (generative AI) that uses machine learning. Alternatively, a salesperson or serviceman may analyze the customer's situation, and the analysis results may be compiled in text format as a needs file and stored in the case data section 504.

[0087] <Description of judgment process and output process> FIG. 9 is a flow diagram illustrating the processing of determination unit 14 and output unit 17 according to the embodiment.

[0088] 9, the determination unit 14 acquires a proposed file and a needs file (step S10). Specifically, the determination unit 14 acquires the proposed file generated by the proposal unit 11 and the needs file output from the server 500.

[0089] Next, the determination unit 14 generates a word frequency table for each of the acquired proposal file and needs file (step S12). In this example, a case where the word frequency table is generated using a TF-IDF (term frequency-inverse document frequency) score will be described as an example.

[0090] FIG. 10 is a diagram for explaining the generation of word frequency tables for each of the proposal file and the needs file.

[0091] 10(A) shows a case where the proposed file FA is decomposed into parts of speech, word matrix data is generated, and the TF-IDF score and occurrence frequency are calculated. In other words, the feature quantities of the words contained in the text information of the proposed file FA are calculated.

[0092] 10B shows a case where the needs file NA is decomposed into parts of speech, word matrix data is generated, and the TF-IDF score and occurrence frequency are calculated. In other words, the feature quantities of words included in the text information of the needs file NA are calculated.

[0093] Referring again to FIG. 9, the determination unit 14 generates a topic model (step S14). FIG. 11 is a diagram illustrating a concept of generating a topic model according to an embodiment.

[0094] 11(A) and (B), in this example, a case where topics are classified for the proposed file FA and the needs file NA using the LDA topic model will be described. The characters are visualized with their size adjusted according to the score value. This makes it easy to grasp the feature amount of the words.

[0095] In this document, as an example, a case is shown in which topics are classified into control device topics, methodology topics, and technique topics based on the feature quantities of the above words. However, this is not limited to this, and further classification into multiple topics is also possible.

[0096] 9 again, the determination unit 14 calculates the similarity using the finally classified topics (step S16). Specifically, the determination unit 14 calculates the topic similarity between the proposed file FA and the needs file NA. For example, the similarity is determined using a similarity function (COS function as an example). Note that the similarity may be determined using other functions other than the COS function.

[0097] Then, the output unit 17 executes an output determination process (step S18). Then, the process ends (END).

[0098] FIG. 12 is a flow diagram illustrating details of the output determination process according to the embodiment. 12, the output unit 17 determines whether the similarity calculated by the determination unit 14 is equal to or greater than a first threshold value (step S20). As an example, the first threshold value is set to "50." The first threshold value can be set appropriately.

[0099] In step S20, when the output unit 17 determines that the similarity calculated by the determination unit 14 is equal to or greater than the first threshold value (YES in step S20), the output unit 17 then determines whether the similarity is equal to or greater than a second threshold value (step S22). As an example, the second threshold value is set to "75." The second threshold value can be set appropriately.

[0100] In step S22, when the output unit 17 determines that the similarity calculated by the determination unit 14 is equal to or greater than the second threshold value (YES in step S22), the output unit 17 outputs the first proposed information (step S24). Specifically, the output unit 17 outputs the proposed file FA.

[0101] Then, the process ends (returns). On the other hand, in step S22, when the output unit 17 determines that the similarity calculated by the determination unit 14 is less than the second threshold value (NO in step S22), the output unit 17 outputs the second proposed information (step S26). Specifically, the needs file NA is output.

[0102] Then, the process ends (returns). On the other hand, in step S20, when the output unit 17 determines that the similarity calculated by the determination unit 14 is less than the first threshold value (NO in step S20), the process ends (returns).

[0103] In this embodiment, for example, if the similarity calculated by the determination unit 14 is equal to or greater than the first threshold value and less than the second threshold value, the needs file FA is output. Also, if the similarity calculated by the determination unit 14 is equal to or greater than the first threshold value and greater than the second threshold value, the proposed file FA is output.

[0104] On the other hand, since the types of information required vary depending on the user's preferences, the needs file NA and the proposal file FA may be output interchangeably.

[0105] In this example, a case has been described in which neither the first proposed information nor the second proposed information is output when the similarity calculated by the judgment unit 14 is less than the first threshold value, but this is not limited to this, and for example, either the first proposed information or the second proposed information may be output.

[0106] As described in the above embodiment, the method determines the similarity between the first and second proposed information and controls the output of the proposed information based on the determination result, making it possible to present proposal content with high accuracy.

[0107] In the above, we have described the case where the LDA topic model is used, but this is not limited to this. For example, topics may be classified using a Hierarchical Dirichlet Process (HDP), Probabilistic Latent Semantic Analysis (PLSA), or Correlated Topic Model (CTM).

[0108] The embodiments disclosed herein should be considered to be illustrative and not restrictive in all respects. The scope of the present disclosure is defined by the claims, not the above description, and is intended to include all modifications within the meaning and scope of the claims. [Explanation of symbols]

[0109] 1 control system, 4 control network, 6 information network, 10 IO processing section, 11 proposal section, 12 analysis section, 13 generation section, 14 judgment section, 17 output section, 18 proposal data section, 100 control device, 102 processor, 104 chip set, 106 main memory, 110 storage, 112 system program, 114 user program, 116 status diagnosis program, 120 control network controller, 122 information network controller, 124 controller, 126 memory card interface, 128 memory card, 300 production line, 500 server, 502 customer needs estimation section, 504 case data section, 506 customer information data section.

Claims

1. a suggestion unit that generates first suggestion information for correcting a state of a control system including a control device based on state data indicating a state occurring in the control system; a determination unit that determines a similarity between the first proposal information generated by the proposal unit and second proposal information for correcting a state of the control system based on associated data related to the control system other than the state data; an output unit that controls output of the first and second pieces of suggested information based on the similarity determined by the determination unit.

2. The condition diagnosis system according to claim 1 , wherein the output unit controls output of the first and second pieces of suggested information based on a comparison between a similarity between the first and second pieces of suggested information and a first threshold value.

3. The output unit is outputting the first proposed information when a similarity between the first and second proposed information is equal to or greater than a second threshold value that is higher than the first threshold value; 3 . The condition diagnosis system according to claim 2 , wherein when a similarity between the first and second pieces of suggested information is less than a second threshold value that is higher than the first threshold value, the second piece of suggested information is output.

4. the first and second suggestion information include first and second text information, respectively; The condition diagnosis system according to claim 1 , wherein the determination unit determines the similarity based on a first feature amount of a word included in the first text information and a second feature amount of a word included in the second text information.

5. The determination unit is a calculation unit that calculates a first feature amount of a word included in the first text information and a second feature amount of a word included in the second text information by using a topic model; 5. The condition diagnosis system according to claim 4, further comprising a similarity determining section that determines a similarity between the first feature amount calculated by the calculating section and a second feature amount by using a similarity function.

6. The suggestion unit, an analysis unit that analyzes a status pattern of the status data; The condition diagnosis system according to claim 1 , further comprising a generation unit that generates, as the first proposal information, one of a plurality of proposal files corresponding to a plurality of condition patterns respectively according to the condition patterns analyzed by the analysis unit.

7. generating first proposal information for correcting a state of a control system including a control device based on state data indicating a state occurring in the control system; determining a similarity between the generated first proposal information and second proposal information for correcting the abnormality based on related data related to the control system other than the status data; and outputting at least one of the first and second pieces of suggested information based on the degree of similarity.

8. On the computer, generating first proposal information for correcting a state of a control system including a control device based on state data indicating a state occurring in the control system; determining a similarity between the generated first proposal information and second proposal information for correcting the abnormality based on related data related to the control system other than the status data; and outputting at least one of the first and second pieces of suggested information based on the degree of similarity.

Images