Symbolization method

Abstract

To provide an encoding method capable of generating images capable of learning and inferring correlations between multiple signals.SOLUTION: The encoding method is an encoding method that is executed by a computer to encode the output of multiple output devices. The encoding method includes: an acquisition step of acquiring collected data group output from multiple output units; a verification step of generating a verified data group that is validated data of each period and each output device based on the collected data group; and an image generation step of creating an encoded image in which the verified data of two or more output devices included in multiple output devices are encoded based on the verified data group.SELECTED DRAWING: Figure 2

Description

Technical Field

[0001] The present invention relates to an encoding method.

Background Art

[0002] Various sensors have been used in manufacturing equipment for the automation of manufacturing and control. In recent years, various sensors are also used in various places other than manufacturing equipment, such as offices and ordinary households. Measurement values obtained by sensors are used not only for control but also for condition monitoring and anomaly detection. Patent Document 1 discloses a pattern detection system from time-series data.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the invention described in Patent Document 1, only one signal can be a processing target.

Means for Solving the Problems

[0005] An encoding method according to a first aspect of the present invention is an encoding method for encoding outputs of a plurality of output devices, which is executed by a computer, and includes an acquisition step of acquiring a collection data group that is an output of the plurality of output devices, a verification step of generating a verified data group that is verified data for each time zone and for each of the output devices based on the collection data group, and an image generation step of creating an encoded image obtained by encoding the verified data of two or more of the output devices included in the plurality of output devices based on the verified data group. Furthermore, in the image generation step, the encoded image is divided into multiple regions, and for each region, the verified data corresponding to the output of the processing target output device, which is one of the output devices, is encoded as brightness, grayscale, or color. A second aspect of the present invention is an encoding method performed by a computer for encoding the outputs of a plurality of output devices, comprising: an acquisition step of acquiring a group of collected data which are the outputs of the plurality of output devices; a verification step of generating a group of verified data which are verified data for each time period and for each output device based on the group of collected data; and an image generation step of creating an encoded image which encodes the verified data of two or more of the output devices included in the plurality of output devices based on the group of verified data, wherein the encoded image comprises a plurality of layers, and further comprises a drawing determination step of determining a combination of the output devices to be drawn on the same layer based on the correlation of the outputs of the plurality of output devices. A third aspect of the present invention is an encoding method performed by a computer for encoding the outputs of a plurality of output devices, comprising: an acquisition step of acquiring a group of collected data which are the outputs of the plurality of output devices; a verification step of generating a group of verified data which are verified data for each time period and for each output device based on the group of collected data; and an image generation step of creating an encoded image which encodes the verified data of two or more of the output devices included in the plurality of output devices based on the group of verified data, further comprising a drawing determination step of determining the type of encoded image based on the requirements specification, wherein the image generation step generates the encoded image of the type determined in the drawing determination step.

Advantages of the Invention

[0006] According to the present invention, it is possible to generate images that can learn and infer correlations between multiple signals. [Brief explanation of the drawing]

[0007] [Figure 1] Diagram illustrating usage scenarios for the computing device. [Figure 2] Functional configuration diagram of the computing unit [Figure 3] Hardware configuration diagram of the computing unit [Figure 4] A diagram showing an example of a device list. [Figure 5] A diagram showing an example of collected data. [Figure 6] A diagram showing an example of pre-processed data. [Figure 7] A diagram showing an example of verified data. [Figure 8] A diagram showing an example of image parameters. [Figure 9] A diagram showing an example of requirements specifications. [Figure 10] A diagram showing an example of a graph image. [Figure 11] A diagram showing an example of a pixel image. [Figure 12] Flowchart showing the processing of the drawing decision unit [Figure 13] Flowchart showing the processing of the image generation unit [Figure 14] Figure showing variations in the graph image in Modification Example 1. [Figure 15] Figure showing another variation of the graph image in Modification Example 1. [Figure 16] Figure showing another variation of the pixel image in Modification 2. [Modes for carrying out the invention]

[0008] —First Embodiment— Hereinafter, a first embodiment of the encoding method will be described with reference to FIGS. 1 to 13. FIG. 1 is a diagram showing a usage scenario of the arithmetic unit 1 according to the present invention. The arithmetic unit 1 generates a graph image 48 and a pixel image 49 using a number of output values output by a plurality of output devices 9. The graph image 48 and the pixel image 49 are input to the learning model 1000 and used for learning and inference.

[0009] Various known configurations can be adopted for the learning model 1000. The type of model adopted by the learning model 1000 is not particularly limited, and any of supervised learning, unsupervised learning, and reinforcement learning may be used. The learning model 1000 may be executed by the arithmetic unit 1 or may be executed by a device different from the arithmetic unit 1. The learning model 1000 may be executed by different devices in the learning phase and the inference phase, or the arithmetic unit 1 that generates the graph image 48 and the pixel image 49 may be physically different devices in the learning phase and the inference phase.

[0010] The output device 9 is a sensor or various electronically controlled devices. The output value is the sensing data of the sensor, the calculation result of the electronically controlled device, and the value set for the electronically controlled device from the outside. Specific examples of the output value include the temperature measured by the temperature sensor, the number of proximity detections per unit time measured by the proximity sensor, the speed measured by the speed sensor, the illuminance set by the lighting having an automatic dimming function, the valve opening calculated by the positioner that controls the control valve, and the like. Further, the output value may be the set temperature of the air conditioning equipment set by the user, the speed of the belt conveyor set by the user, and the like.

[0011] The relationship between the output device 9 and the output of the learning model 1000 is as follows. In the first example, the output device 9 is a sensor or an electronic control device installed in a certain room. The arithmetic unit 1 installed in that room generates a graph image 48 and inputs it to the learning model 1000 operating on the cloud server. The learning model 1000 infers the state of the room based on the graph image 48, for example, normal, flooding, fire, etc. In the second example, the output device 9 is an acceleration sensor and a gyroscope built into a smartphone. The arithmetic unit 1 is the same smartphone, generates a pixel image 49 and inputs it to the learning model 1000, and infers the actions of the person holding the smartphone, for example, during running, walking, moving on an escalator, etc.

[0012] Hereinafter, the generation of the graph image 48 and the pixel image 49 by the arithmetic unit 1 in the configuration shown in FIG. 1 will be described in detail. The method for generating the graph image 48 and the pixel image 49 by the arithmetic unit 1 is constant regardless of the operation phase of the learning model 1000. Hereinafter, the arithmetic unit 1 will be described as being able to create both the graph image 48 and the pixel image 49, but the arithmetic unit 1 only needs to be able to create at least one of the graph image 48 and the pixel image 49.

[0013] FIG. 2 is a functional configuration diagram of the arithmetic unit 1. The arithmetic unit 1 includes an acquisition unit 11, a preprocessing unit 12, a verification unit 13, an image generation unit 14, and a drawing determination unit 15. However, in FIG. 2, data stored in the storage device 4 included in the arithmetic unit 1 is also described for convenience of explanation. In the storage device 4, a device list 41, a collection data group 42, a preprocessed data group 43, a verified data group 44, image parameters 45, requirement specifications 46, a graph image 48, and a pixel image 49 are stored.

[0014] The acquisition unit 11 acquires output values ​​from multiple output devices 9 and stores them in the storage device 4 as a collection data group 42. Communication between the acquisition unit 11 and each output device 9 may be wired or wireless. The acquisition unit 11 may also communicate directly with the output devices 9 or indirectly via a repeater or network. Furthermore, instead of communicating directly with the output devices 9, the acquisition unit 11 may acquire output values ​​offline via a storage medium.

[0015] The preprocessing unit 12 processes the collected data group 42 to generate the preprocessed data group 43. The preprocessing unit 12 arranges all the data included in the collected data group 42 in chronological order and fills in the blanks using the interpolation method described in the device list 41. The preprocessing unit 12 also converts the non-numeric data included in the collected data group 42 into numerical values ​​using a predetermined method. For example, the preprocessing unit 12 replaces ON values ​​with "1" and OFF values ​​with "0".

[0016] The verification unit 13 processes the pre-processed data group 43 to generate the verified data group 44. The verification unit 13 generates verified data by integrating data and supplementing missing data so that the sensing data is at predetermined time intervals. In other words, the verification unit 13 generates verified data for each output device 9 that represents the output value for each time period. In this embodiment, an example is described where this time period is 1 minute, but it may be shorter than 1 minute, such as 1 second or 0.5 seconds, or longer than 1 minute, such as 30 minutes, 1 hour, or 1 day.

[0017] The image generation unit 14 generates a graph image 48 and a pixel image 49. The drawing determination unit 15 determines the drawing type and layer number in the device list 41. In other words, the drawing determination unit 15 determines the drawing type and layer number for each output value and writes them to the device list 41. However, the drawing determination unit 15 is not an essential component of the arithmetic unit 1, and the arithmetic unit 1 does not need to include the drawing determination unit 15 if the device list 41 is completed in advance or if the operator rewrites the device list 41.

[0018] The device list 41 contains data related to the output values ​​output by the output device 9. The data included in the device list 41 is pre-created, except for the drawing type and layer number. The collected data group 42 is a collection of sensing information acquired by the acquisition unit 11 from the output device 9. This sensing information is time-stamped. The time-stamp may be added by each output device 9 or by the acquisition unit 11. Figure 2 only conceptually shows the collected data group 42, and in reality it may consist of multiple files.

[0019] The preprocessed data group 43 is a collection of data generated by the preprocessing unit 12 using the collected data group 42. The verified data group 44 is a collection of data generated by the verification unit 13 using the preprocessed data group 43. The image parameters 45 are a set of parameters created in advance and are referenced by the image generation unit 14 when generating the graph image 48 and the pixel image 49. The requirements specification 46 is a requirement for the image generated by the arithmetic unit 1 and is created in advance. The graph image 48 is an image obtained by removing the axis and tick values ​​from a graph created using the verified data that constitutes the verified data group 44. The pixel image 49 is an image that represents each of the verified data included in the verified data group 44 as brightness, grayscale, or color. Specific examples of the graph image 48 and the pixel image 49 will be described later.

[0020] Figure 3 is a hardware configuration diagram of the arithmetic unit 1. The arithmetic unit 1 comprises a central arithmetic unit (CPU) 81, a read-only memory device (ROM) 82, a read / write memory device (RAM) 83, a user interface (input / output device) 84, a communication device 85, and a memory device 4. The CPU 81 performs the various calculations mentioned above by loading the program stored in the ROM 82 into the RAM 83 and executing it.

[0021] The arithmetic unit 1 may be implemented using a rewritable logic circuit such as an FPGA (Field Programmable Gate Array) or an application-specific integrated circuit such as an ASIC (Application Specific Integrated Circuit) instead of the combination of CPU 81, ROM 82, and RAM 83. Alternatively, the arithmetic unit 1 may be implemented using a different configuration, such as a combination of CPU 81, ROM 82, RAM 83 and an FPGA, instead of the combination of CPU 81, ROM 82, and RAM 83.

[0022] The input / output device 84 is a keyboard, mouse, liquid crystal display, etc. The arithmetic unit 1 receives input from the user using the input / output device 84. The user can input and modify the device list 41 and image parameters 45 using the input / output device 84. The communication device 85 is a communication module that enables communication with other devices, and may be a separate piece of hardware such as a network interface card, or it may be implemented as a function of the SoC or CPU. The communication device 85 may implement either wireless or wired communication. The storage device 4 is a non-volatile storage device, such as a hard disk drive.

[0023] Figure 4 shows an example of a device list 41. The device list 41 contains information about all output values ​​included in the output device 9. In the example shown in Figure 4, the output type, minimum value, maximum value, storage method, and plotting type are shown for the output values ​​of the four output devices 9, D001 to D004. The output type is a distinction between whether the sensing data is numerical, i.e., a continuous value, or a discrete value. In the example shown in Figure 4, the number of values ​​is also indicated in the case of discrete values. In the example shown in Figure 4, a plotting type is specified for each output device 9, but a common plotting type may be specified for all output devices 9.

[0024] The minimum and maximum values ​​are listed only when the output type is a continuous value, and the minimum and maximum values ​​for continuous values ​​are defined. The interpolation method represents the interpolation method performed by the preprocessor 12. The drawing type is information on whether to draw on the graph image 48 or the pixel image 49, and on which layer. Of the information listed in the device list 41, only this drawing type is set by the drawing determination unit 15.

[0025] Figure 5 shows an example of the collected data set 42. In the example shown in Figure 5, the output values ​​of four output devices 9, D001 to D004, are shown, and a hash (#) is used for columns where no value exists. In Figure 5, for the sake of explanation, all data is combined into a single table and sorted by the timestamp value. The values ​​in Figures 6 and 7 described below are based on the values ​​shown in Figure 5.

[0026] Figure 6 shows an example of the pre-processed data set 43. In Figure 6, asterisks are used to indicate columns with values ​​that differ from those in the collected data set 42 shown in Figure 5. The changes in Figure 6 from Figure 5 are as follows: Firstly, the "ON" value for the second device D002 has been replaced with "1", and the "OFF" value has been replaced with "0". Secondly, values ​​have been set in the five columns where no values ​​existed through interpolation. As will be explained in more detail later, the interpolation process is performed by the pre-processing unit 12 based on the interpolation method values ​​described in the device list 41.

[0027] Figure 7 shows an example of the validated data set 44. The change from Figure 6 to Figure 7 is that the data for "10:24:30" has been removed to ensure a consistent time interval. As a result, representative values ​​of the output of output device 9 for each one-minute time period are listed in Figure 7 as validated data. Although the figure shows an example of removing data, data may also be added to maintain a consistent time interval. Known interpolation techniques, such as linear interpolation from preceding and succeeding data, may be used to add data.

[0028] Figure 8 shows an example of image parameters 45. Image parameters 45 are referenced by the image generation unit 14 when generating graph images 48 and pixel images 49. Image parameters 45 are broadly divided into two types: those for graph images and those for pixel images. The image parameters 45 for graph images consist of three parts: the number of horizontal pixels, the number of vertical pixels, and the time corresponding to the entire width. The "number of horizontal pixels" and "number of vertical pixels" are the horizontal and vertical sizes of the graph image 48 to be generated. The "time corresponding to the entire width" is the length of the period represented by the entire width of the graph image 48, and can also be said to be the length of the period contained in one generated graph image 48. Based on the example shown in Figure 8, the generated graph image 48 has 1440 pixels horizontally and 1000 pixels vertically, and stores 24 hours, or one day's worth of data.

[0029] Figure 9 shows an example of requirement specification 46. Requirement specification 46 is referenced by the drawing determination unit 15. Requirement specification 46 concerns the requirements for the image generated by the arithmetic unit 1, and includes whether or not visibility is required and whether or not simplicity is required. In the example shown in Figure 9, "YES" is indicated to indicate that visibility is required for the image generated by the arithmetic unit 1, and "YES" is indicated to indicate that simplicity is required for the image generated by the arithmetic unit 1.

[0030] The image parameters 45 for pixel images consist of four parameters: the number of horizontal pixels, the time corresponding to the entire width, the duration of one data point in one image, and the pixel size of one data point. "Number of horizontal pixels" has the same meaning as for graph images. "Time corresponding to the entire width" is the length of the period represented by the entire width of the pixel image 49. "Duration of one data point in one image" is the length of the period to be contained in one generated pixel image 49. In the example shown in Figure 8, "Time corresponding to the entire width" is "24 hours," or 1 day, and "Duration of one data point in one image" is "7 days," so there are 7 columns of one type of sensing data in one pixel image 49. "Pixel size of one data point" is the number of horizontal and vertical pixels of one sensing data point in the pixel image 49.

[0031] Figure 10 shows an example of a graph image 48. In the example shown in Figure 10, the graph image 48 is obtained by plotting the output values ​​of five output devices 9, for example, the first device D001 to the fifth device D005, for a given day as a line graph. However, to be precise, the graph image 48 is created using verified data that has undergone processing by the preprocessing unit 12 and the verification unit 13, rather than the raw values ​​output by the output devices 9 included in the collected data group 42. The graph image 48 extends in mutually orthogonal X and Y directions. The graph image 48 shown in Figure 10 is an image obtained by plotting verified data that constitutes the verified data group 44, with time taken in the horizontal axis (X direction) and output values ​​in the vertical axis (Y direction). Specifically, the left end of the horizontal axis is the value at 0:00 and the right end is the value at 23:59. However, the time axis of the graph image 48 does not have to be one day; it could be one hour, several days, one year, etc. Furthermore, the time at the left end of the horizontal axis is not limited to the above; it may be any time depending on the characteristics and use of the data.

[0032] In the plot of the first device, the lower end of the vertical axis represents the minimum output value of the first device, and the upper end of the vertical axis represents the maximum output value of the first device. In the plot of the second device, the lower end of the vertical axis represents the minimum output value of the second device, and the upper end of the vertical axis represents the maximum output value of the second device. The plots of the third to fifth devices are similar. However, the minimum output value of the first device is not the minimum value of the first device used to generate a specific graph image 48, but the minimum output value of the first device throughout the entire period. In this embodiment, the minimum value of the first device listed in the device list 41 is used. Similarly, the maximum value of the first device is the maximum value of the first device listed in the device list 41. The minimum and maximum values ​​of the second to fifth devices are also similar. In Figure 10, the line type is changed for each device for plotting purposes, but the differences between devices may be expressed by using different colors.

[0033] Figure 11 shows an example of a pixel image 49. The pixel image 49 shown in Figure 11 shows the output values ​​for one week from a total of 10 output devices 9, from the first device D001 to the tenth device D010. The pixel image 49 shown in Figure 11 is 1440 pixels wide and 70 pixels high. Each pixel in this pixel image 49 represents one of the output values ​​for each minute. Since one day has 1440 minutes, one horizontal line represents the output value for one day for each output device 9. In Figure 11, the output values ​​for one week, or 7 days, are shown for each output device 9, so 7 pixels are used vertically for each output device 9.

[0034] The enlarged view of pixel image 49 shown below Figure 11 represents an area of ​​5 pixels horizontally and 15 pixels vertically. In Figure 11, the output value is represented by the type of hatching for each pixel. The leftmost column represents the output value from 0:00 to 0:01, and the second column from the left represents the output value from 0:01 to 0:02. The top row shows the output value for the first day of the first device, and the second row shows the output value for the second day of the first device. In other words, the data is plotted at 1-minute intervals horizontally and at 1-day intervals vertically. In Figure 11, the plot values ​​are represented by the type of hatching for plotting purposes, but the plot values ​​could also be represented by color.

[0035] Figure 12 is a flowchart showing the processing of the drawing determination unit 15. The drawing determination unit 15 performs the following processing if the drawing type and layer number fields in the device list 41 are blank. The processing of the drawing determination unit 15 is performed before the generation of the graph image 48 and pixel image 49 by the image generation unit 14. The drawing determination unit 15 first refers to the requirements specification 46 and determines whether visibility is required. If the drawing determination unit 15 determines that visibility is required, in other words, that the visibility value in the requirements specification 46 is "YES", it affirms this step and proceeds to step S304, and if it determines that visibility is not required, it proceeds to step S302.

[0036] In step S302, the drawing determination unit 15 determines the relationship between the total number of output values ​​listed in the device list 41 and the threshold values ​​of "20" and "50". If the drawing determination unit 15 determines that the total number of output values ​​is less than 20, it proceeds to step S304; if it determines that the total number of output values ​​is 20 or more but less than 50, it proceeds to step S303; and if it determines that the total number of output values ​​is 50 or more, it proceeds to step S305. In this embodiment, the drawing determination unit 15 makes the above determination using the number of devices "20" and "50" as threshold values, but it is not necessarily limited to these numbers, and any value may be set. In step S303, the drawing determination unit 15 refers to the requirements specification 46 and determines whether simplicity is required. If the drawing determination unit 15 determines that simplicity is required, in other words, that the value of simplicity in the requirements specification 46 is "YES", it affirms this step and proceeds to step S305; if it determines that simplicity is not required, it proceeds to step S304.

[0037] In step S304, the drawing determination unit 15 determines that the image to be generated is a graph image 48 and proceeds to step S311. In step S305, the drawing determination unit 15 determines that the image to be generated is a pixel image 49 and proceeds to step S311. In step S311, the drawing determination unit 15 uses the vast number of output values ​​obtained so far to calculate a correlation coefficient that shows the correlation between the output values. Pearson's product-moment correlation coefficient or Spearman's rank correlation coefficient can be used as this correlation coefficient, and other correlation coefficients may also be used.

[0038] In the following step S312, the drawing determination unit 15 groups output values ​​that are strongly related to each other based on the correlation coefficient values ​​calculated in step S311. However, there is a limit to the number of output values ​​that can be included in one group. For example, the upper limit is about 5 to 10 for graph images 48 and about 20 for pixel images 49. The drawing determination unit 15 then assigns a sequential number starting from "1" to each of these groups. There is no hierarchy among the group numbers, and these group numbers are used as the layer numbers.

[0039] In the following step S313, the drawing determination unit 15 records the image type and group number determined in step S304 or step S305 in the device list 41 and terminates the process shown in Figure 12. The drawing determination unit 15 records the image type in the drawing type column of the device list 41 and the group number in the layer number column. Hereafter, steps S301 to S305 in Figure 12 will also be referred to as the drawing determination step, and steps S311 to S312 will also be referred to as the drawing determination step.

[0040] Figure 13 is a flowchart showing the processing of the image generation unit 14. First, in step S321, the image generation unit 14 selects an undrawn layer to be processed. An undrawn layer is a layer that has not yet been selected as a processing target from all the drawing type and layer number combinations listed in the device list 41. For example, in the example of the device list 41 shown in Figure 4, there are three: graph image 48 layer number 1, graph image 48 layer number 2, and pixel image 49 layer number 1. When step S321 is executed for the first time, the image generation unit 14 selects one of these three as the processing target layer and proceeds to step S322.

[0041] In the following step S322, the image generation unit 14 reads all verified data belonging to the processing target layer from the verified data group 44 and proceeds to step S323. In the following step S323, the image generation unit 14 determines the type of processing target layer, that is, whether it is a graph image 48 or a pixel image 49. If the image generation unit 14 determines that the processing target layer is a graph image 48 layer, it proceeds to step S324; if it determines that the processing target layer is a pixel image 49 layer, it proceeds to step S326.

[0042] In step S324, the image generation unit 14 reads the minimum and maximum values ​​for each data read in step S322 from the device list 41. These minimum and maximum values ​​correspond to the lower and upper ends of the graph drawing area, as shown in Figure 10. In the following step S325, the image generation unit 14 draws a graph of the data read in step S322 according to the image parameters 45 and the minimum and maximum values ​​read in step S324. This graph becomes the image of the specified layer of the graph image 48. Next, the image generation unit 14 proceeds to step S328.

[0043] In step S326, the image generation unit 14 reads the minimum and maximum values ​​for each data read in step S322 from the device list 41 and determines the correspondence between the output value and color. For example, if the minimum value of a certain output value is "0" and the maximum value is "100", the image generation unit 14 divides "0xffffff" by "100" to determine the weight of the output value "1", and uses the top two digits of the hexadecimal representation as the values ​​for R, G, and B respectively. In the following step S327, the image generation unit 14 draws on the specified layer of the pixel image 49 based on the values ​​read in step S322, the correspondence between the values ​​and colors determined in step S326, and the values ​​of the image parameters 45, and proceeds to step S328.

[0044] In step S328, which is executed when the processing in step S325 or step S327 is completed, the image generation unit 14 determines whether drawing has been completed for all combinations of drawing types and layer numbers listed in the device list 41. If the image generation unit 14 determines that all drawing has been completed, it terminates the process shown in Figure 13; if it determines that there are layers that have not been drawn, it returns to step S321.

[0045] According to the first embodiment described above, the following effects and advantages can be obtained. (1) The computing unit 1, which is a computer, encodes the outputs of multiple output devices 9 using the following encoding method, i.e., it converts them into images. The encoding method executed by the computing unit 1 includes an acquisition step, executed by the acquisition unit 11, which acquires a group of collected data 42, which are the outputs of multiple output devices 9; a verification step, executed by the verification unit 13, which generates a group of verified data 44, which are verified data for each time period and for each output device 9, based on the group of collected data 42; and an image generation step, executed by the image generation unit 14, which creates encoded images, i.e., graph images 48 and pixel images 49, by encoding the verified data of two or more output devices 9 included in the multiple output devices 9, based on the group of verified data 44. As a result, it is possible to generate images that can learn and infer correlations between multiple signals.

[0046] (2) Graph image 48 is a two-dimensional image with extent in the X and Y directions. In the image generation step, validated data from different time periods are placed at different positions in the X direction, and validated data with different values ​​are placed at different positions in the Y direction. Therefore, the correlation between multiple signals can be represented as a two-dimensional graph and used for training machine learning models and for inference using machine learning models.

[0047] (3) In the image generation step, verified data originating from the same output device 9 are further connected by lines in chronological order and represented as a line graph.

[0048] (4) In the image generation step, the pixel image 49 is divided into multiple regions, and verified data corresponding to the output of the processing target output device, which is one output device 9, is encoded as brightness, grayscale, or color for each region. Therefore, the correlation between multiple signals can be represented as the pixel image 49.

[0049] (5) The pixel image 49 is a two-dimensional image that extends in a second direction orthogonal to the X and Y directions. The image generation unit 14 targets the output devices to be processed for each region and arranges verified data corresponding to each minute of time in the X direction, and verified data corresponding to each day of time in the Y direction. As a result, the arithmetic unit 1 can generate a pixel image 49 by arranging the outputs of each output device 9 for each rectangular region.

[0050] (6) The drawing determination unit 15 executes a drawing determination step (S311 to S312 in Figure 12) that determines the combination of output devices 9 to be drawn on the same layer based on the correlation of the outputs of the multiple output devices 9. As a result, outputs of output devices 9 with strong correlations can be placed on the same layer.

[0051] (7) The drawing determination unit 15 executes a drawing determination step (S301 to S305 in Figure 12) that determines the type of encoded image based on the requirements specification 46. In the image generation step executed by the image generation unit 14, an encoded image of the type described in the drawing type column of the device list 41, i.e., a graph image 48 or a pixel image 49, is generated.

[0052] (Variation 1) The operator may register different forms of the graph image 48, such as "Graph 2" or "Graph 3," in the drawing type in the device list 41. In this case, the image generation unit 14 generates a graph image 48 in a form different from that of the first embodiment.

[0053] Figure 14 shows a second graph image 48-2, which is another variation of graph image 48. The example shown in Figure 14 is of a different type of graph than the example shown in Figure 10. That is, Figure 14 is a scatter plot in which only markers are plotted and there are no lines connecting the markers. In Figure 14, the type of plot is changed for each output device 9 for the sake of plotting, but the differences between the output devices 9 could also be represented by using different colors.

[0054] Figure 15 shows a third graph image, 48-3, which is yet another variation of graph image 48. However, Figure 15 also includes graph image 48, which plots the same data, for comparison. Furthermore, to clarify the difference in representation, Figure 15 only shows the output of one output device 9. In the third graph image 48-3, a specific value included in the output value is not plotted, but is substituted with another value immediately preceding it. The third graph image 48-3 is effective for output values ​​that change from one value to another, passing through zero, such as the current used in motor control.

[0055] (Modification 2) The operator may register different forms of the pixel image 49, such as "Pixel 2" or "Pixel 3," in the drawing type in the device list 41. In this case, the image generation unit 14 generates a pixel image 49 that is different from that of the first embodiment.

[0056] Figure 16 shows another variation of the pixel image 49. The upper part of Figure 16 shows the pixel image 49 in the first embodiment, the middle part of Figure 16 shows the second form, the second pixel image 49-2, and the lower part of Figure 16 shows the third form, the third pixel image 49-3. The pixel image 49 is divided into regions only in the vertical direction as shown, and only the output values ​​of the same output device 9 are arranged in the horizontal direction as shown.

[0057] In contrast, the second pixel image 49-2 is divided into two parts not only in the vertical direction but also in the horizontal direction. The third pixel image 49-3 is divided into three parts not only in the vertical direction but also in the horizontal direction. Furthermore, although the divided regions are represented as rectangles here, they may be divided into regions of shapes other than rectangles. In this way, the pixel image 49 can be divided into any shape, and it is sufficient that the shape remains the same throughout the training and inference phases of the learning model 1000.

[0058] (Variation 3) In the embodiment described above, it was assumed that the graph image 48 and the pixel image 49 had multiple layers. However, the graph image 48 and the pixel image 49 may be image files that do not have a layer structure, such as JPG or BMP. In this case, the graph image 48 and the pixel image 49 will be multiple files.

[0059] In the embodiments and modifications described above, the configuration of the functional blocks is merely an example. Several functional configurations shown as separate functional blocks may be integrated, or a configuration represented in one functional block diagram may be divided into two or more functions. Furthermore, some of the functions of one functional block may be provided by other functional blocks.

[0060] In the embodiments and modifications described above, the program is stored in the ROM 82, but the program may also be stored in the storage device 4. Furthermore, the arithmetic unit 1 may be equipped with an input / output interface (not shown), and the program may be read from another device via the input / output interface and a medium available to the arithmetic unit 1 when needed. Here, the medium refers to, for example, a storage medium detachable from the input / output interface, or a communication medium, i.e., a wired, wireless, or optical network, or a carrier wave or digital signal propagating through such a network. Also, some or all of the functions realized by the program may be realized by hardware circuits or an FPGA.

[0061] The embodiments and modifications described above may be combined in any way. Although various embodiments and modifications have been described above, the present invention is not limited to these. Other embodiments that can be conceivable within the scope of the technical idea of ​​the present invention are also included within the scope of the present invention. [Explanation of Symbols]

[0062] 1: Arithmetic device 9: Output device 11: Acquisition part 12: Pre-processing 13: Verification Department 14: Image generation unit 15:Drawing judgment section 41: Device List 42: Collected Data Set 43: Preprocessed data set 44: Verified Data Sets 45: Image parameters 46: Requirements Specification 48: Graph image 49: Pixel image

Claims

1. A coding method performed by a computer for encoding the outputs of multiple output devices, An acquisition step of acquiring a group of collected data which is the output of the plurality of output devices, A verification step that generates a set of verified data, which consists of verified data for each time period and for each output device, based on the aforementioned collected data set. The image generation step includes creating an encoded image by encoding the verified data of two or more output devices included in the plurality of output devices, based on the verified data set, In the image generation step, An encoding method comprising dividing the encoded image into multiple regions and encoding the verified data corresponding to the output of a processing target output device, which is one output device, as brightness, grayscale, or color for each region.

2. In the encoding method described in claim 1, The encoded image is a two-dimensional image having extent in a first direction and a second direction orthogonal to the first direction. In the image generation step, An encoding method in which, for each of the aforementioned regions, the verified data corresponding to the output of the first time interval is arranged in the first direction, and the verified data corresponding to the output of a second time interval, which is a longer time interval than the first time interval, is arranged in the second direction, with respect to the output device to be processed.

3. A coding method performed by a computer for encoding the outputs of multiple output devices, An acquisition step of acquiring a group of collected data which is the output of the plurality of output devices, A verification step that generates a set of verified data, which consists of verified data for each time period and for each output device, based on the aforementioned collected data set. The image generation step includes creating an encoded image by encoding the verified data of two or more output devices included in the plurality of output devices, based on the verified data set, The encoded image includes multiple layers, An encoding method further comprising a drawing determination step of determining a combination of output devices to draw on the same layer based on the correlation of the outputs of the plurality of output devices.

4. A coding method performed by a computer for encoding the outputs of multiple output devices, An acquisition step of acquiring a group of collected data which is the output of the plurality of output devices, A verification step that generates a set of verified data, which consists of verified data for each time period and for each output device, based on the aforementioned collected data set. The image generation step includes creating an encoded image by encoding the verified data of two or more output devices included in the plurality of output devices, based on the verified data set, The method further includes a drawing determination step that determines the type of encoded image based on the requirements specification, The image generation step involves an encoding method that generates the encoded image of the type determined in the drawing determination step.

Images