Processing system, processing method, and program

Abstract

This system provides a processing system that can perform startup self-diagnostic processes on appropriate hardware. [Solution] The processing system comprises a first processing unit and a second processing unit, wherein the first processing unit includes a transmission means for transmitting model information of the first processing unit as training data to the second processing unit during a self-diagnosis process at power-up, and the second processing unit includes a generation means for generating a device diagnostic checklist that narrows down the devices to be diagnosed based on the model information.

Description

[Technical Field]

[0001] The present disclosure relates to a processing system, a processing method, and a program. [Background Art]

[0002] Computers are used in various technical fields. Many computers execute a Power-On Self-Test at startup. Patent Document 1 discloses, as a related technique, a technology relating to an abnormality diagnosis apparatus that diagnoses an abnormality in a control system that controls equipment via data communication over a network. [Prior Art Documents] [Patent Documents]

[0003] [Patent Document 1] Japanese Unexamined Patent Application Publication No. 2019-213058 [Summary of the Invention] [Problem to be Solved by the Invention]

[0004] In the technical field related to Patent Document 1, there is a demand for a technology capable of executing self-diagnosis processing at startup on appropriate hardware.

[0005] One object of each aspect of the present disclosure is to provide a processing system, a processing method, and a program capable of solving the above problem. [Means for Solving the Problem]

[0006] According to one aspect of the present disclosure, the processing system comprises: A processing system comprising a first processing unit and a second processing unit, wherein the second processing unit includes a generation means that includes a trained AI model whose parameters are determined using training data, the input data being model information of the first processing unit and the output data being a device diagnostic checklist corresponding to the input data, and a generation means that generates a device diagnostic checklist narrowing down the devices to be diagnosed based on the trained AI model, and the first processing unit includes a first transmission means that transmits model information of the first processing unit to the second processing unit during a self-diagnosis process at power-up, and a check means that checks the devices indicated in the device diagnostic checklist generated by the generation means. .

[0007] According to another aspect of the present disclosure, the processing method comprises: A processing method to be executed by a processing system comprising a first processing unit and a second processing unit, wherein the second processing unit is a generation means including a trained AI model whose parameters are determined using training data that takes model information of the first processing unit as input data and a device diagnostic checklist corresponding to the input data as output data, generates a device diagnostic checklist that narrows down the devices to be diagnosed based on the trained AI model, and the first processing unit transmits the model information of the first processing unit to the second processing unit during a self-diagnosis process at power-up, and checks the devices indicated in the device diagnostic checklist generated by the second processing unit. .

[0008] According to another aspect of the present disclosure, the program is: A computer in a processing system comprising a first processing unit and a second processing unit is provided with a generation means that includes a trained AI model whose parameters are determined using training data in which model information of the first processing unit is input data and a device diagnostic checklist corresponding to the input data is output data. The means is to cause the computer to perform the following actions: generate a device diagnostic checklist that narrows down the devices to be diagnosed based on the trained AI model; transmit the model information of the first processing unit to the second processing unit during the self-diagnosis process when the first processing unit is powered on; generate a device diagnostic checklist that narrows down the devices to be diagnosed based on the model information; and check the devices shown in the generated device diagnostic checklist.. [Effects of the Invention]

[0009] According to each aspect of this disclosure, a startup self-diagnostic process can be performed on appropriate hardware. [Brief explanation of the drawing]

[0010] [Figure 1] This figure shows an example of the configuration of a processing system according to some embodiments of the present disclosure. [Figure 2] This figure shows a first example of the processing flow of a processing system according to some embodiments of the present disclosure. [Figure 3] This figure shows a second example of the processing flow of a processing system according to some embodiments of the present disclosure. [Figure 4] This figure shows an example of the configuration of a processing system according to some embodiments of the present disclosure. [Figure 5] This figure shows an example of the processing flow of a processing system according to some embodiments of the present disclosure. [Figure 6] This is a schematic block diagram showing the configuration of a computer according to at least one embodiment. [Modes for carrying out the invention]

[0011] The embodiments will be described in detail below with reference to the drawings. <Embodiment> A processing system 1 according to one embodiment of this disclosure will be described with reference to the drawings. The processing system 1 is a system that can perform a startup self-diagnostic process on appropriate hardware.

[0012] (Configuration of the processing system) A processing system 1 according to one embodiment of the present disclosure will be described with reference to the drawings. Figure 1 is a diagram showing an example of the configuration of a processing system 1 according to several embodiments of the present disclosure. As shown in Figure 1, the processing system 1 comprises a first processing unit 10 and a second processing unit 20.

[0013] As shown in FIG. 1, the first processing apparatus 10 includes a CPU 101. Examples of the first processing apparatus 10 include personal computers, servers, and the like. The CPU 101 executes various processes in the first processing apparatus 10.

[0014] As shown in FIG. 1, the second processing apparatus 20 includes a receiving unit 201, a storage 202, a generating unit 203, a UI (User Interface) module 204, an analysis module 205, a determination module 206, a conversion module 207, and a transmitting unit 208. Examples of the second processing apparatus 20 include cloud servers and the like.

[0015] The receiving unit 201 receives device diagnosis information from the first processing apparatus 10. The storage 202 stores the device diagnosis information.

[0016] The generating unit 203 reads the device diagnosis information and outputs (generates) a device diagnosis checklist. The generating unit 203 includes a trained AI model learned using training data (that is, a model for which parameters (weights) have been determined).

[0017] The UI module 204 displays the device diagnosis checklist on a web-based platform. The analysis module 205 analyzes a POST log and a system log.

[0018] The determination module 206 inputs the analysis result output by the analysis module 205 into an AI model (machine learning-based model) that operates based on unsupervised learning without training data. The determination module 206 determines, for the analysis result input to the AI model (machine learning-based model), the severity of the analyzed abnormality and the necessity for device diagnosis.

[0019] The conversion module 207 converts the device diagnostic checklist from an internal format into a format readable by NVRAM or CMOS. The transmission unit 208 transmits the format-converted device diagnostic checklist to the NVRAM or CMOS of the first processing apparatus 10.

[0020] Note that the processing performed by the processing system 1 according to an embodiment of the present disclosure is not limited to the above-described processing. For example, the processing system 1 may perform the processing described below.

[0021] (Processing Performed by the Processing System) Next, the processing performed by the processing system 1 will be described. FIG. 2 is a diagram showing a first example of a processing flow of the processing system 1 according to some embodiments of the present disclosure. FIG. 3 is a diagram showing a second example of a processing flow of the processing system 1 according to some embodiments of the present disclosure. The processing flow shown in FIG. 2 outlines the processing when the first processing apparatus 10 in the processing system 1 is powered on. The processing flow shown in FIG. 3 shows details of the processing when the first processing apparatus 10 in the processing system 1 is powered on.

[0022] (Outline of Processing at Power-On) First, with reference to FIG. 2, an outline of processing at power-on of the first processing apparatus 10 in the processing system 1 will be described.

[0023] A user performs an operation to turn on power to the first processing apparatus 10. A CPU 101 of the first processing apparatus 10 turns on the power of the first processing apparatus 10 in response to the user's operation (step S1). Then, the CPU 101 starts the BIOS (step S2). The CPU 101 executes POST (Power-On Self-Test) (step S3). The CPU 101 starts the boot loader (step S4). When the boot loader starts and an OS (Operating System) is selected, the CPU 101 starts the selected OS (step S5).

[0024] (Details of Processing at Power-On) Next, with reference to Figure 3, the details of the processing when the first processing unit 10 in the processing system 1 is powered on will be described. It should be assumed that the second processing unit 20 is already operational when the first processing unit 10 is powered on.

[0025] The CPU 101 executes the processes in steps S1 and S2. The CPU 101 also executes the process in step S3. The receiving unit 201 of the second processing unit 20 receives device diagnostic information from the first processing unit 10 only on the first occasion (step S21).

[0026] When the receiving unit 201 of the second processing unit 20 executes the process in step S21, the receiving unit 201 stores the received device diagnostic information in the storage 202 (step S22). The receiving unit 201 also outputs the device diagnostic information to the generation unit 203. The generation unit 203 reads the device diagnostic information output by the receiving unit 201 and outputs (generates) a device diagnostic checklist (step S23). The device diagnostic checklist is a list indicating the hardware to be targeted for self-diagnosis processing. The generation unit 203 includes a trained AI model that has been trained using training data (i.e., its parameters (weights) have been determined). The training data is data containing information on the necessity of device diagnosis for each model, consisting of multiple sets of input data and output data corresponding to that input data. The input data is model information. The output data is a device diagnostic checklist corresponding to that model information. Then, each of the multiple input data in the training data is input to the AI ​​model, and the parameters in the AI ​​model are determined using techniques such as backpropagation so that output data corresponding to the input data is output. Thus, an AI model whose parameters have been determined using training data is a trained AI model. Therefore, the generation unit 203 can generate a device diagnostic checklist suitable for the model information by inputting the model information as input data into the trained AI model. This device diagnostic checklist is a list that indicates the hardware to be targeted for the self-diagnostic processing at startup. As a result, the self-diagnostic processing at startup can be executed on the appropriate hardware.

[0027] Once the POST process is complete, the CPU 101 checks the hardware (various devices) indicated in the device diagnostic checklist generated by the generation unit 203 via the BIOS. The CPU 101 then sends device diagnostic information, which is the diagnostic information for the various devices (hardware) checked by the BIOS, to the second processing unit 20. After the POST process is complete, the devices are recognized correctly and have the latest device configuration information. Since the device diagnostic information in this state is considered to be the most accurate, the CPU 101 sends the most accurate device diagnostic information after the POST process is complete to the second processing unit 20.

[0028] The training data can be broadly divided into the following two categories. 1) Information on the device to be diagnosed Device information compatible with the model. 2) Criteria information for determining devices that require minimal diagnosis. Prioritization information for device diagnostics, determined based on the device's importance. The following categories will be used for classification. • Critical devices: Diagnostics required CPU, memory, storage devices, etc. • Main devices: Recommended for diagnosis Network interface, graphics card, etc. • Auxiliary devices: Optional for diagnosis

[0029] Here, we will explain in detail how to generate and use AI models. Generating and using an AI model involves the following steps: (1) collecting and preparing training data, (2) selecting and training a model, (3) providing input data, and (4) generating output data.

[0030] (1) Collection and preparation of training data We collect information regarding the diagnostic needs of devices in each device model. This data indicates which devices are essential for diagnosis. For example, if the hard disk and memory are considered particularly important for a certain device model A, that information is prepared as a training dataset.

[0031] (2) Model selection and training Choose a machine learning algorithm. The AI ​​model is trained using training data. At this stage, the AI ​​learns the diagnostic need patterns for each device model. For example, when using a decision tree algorithm, the model learns rules to determine which devices (hardware) should be prioritized for diagnosis based on the input diagnostic need information.

[0032] (3) Provision of input data When using a pre-trained AI model, the current device diagnostic information of that model is input. This is information about the devices that can be diagnosed at the moment. For example, a list is provided that currently only includes devices installed in device model B.

[0033] (4) Generation of output data The trained AI model selects only the necessary devices from the devices corresponding to the input data and creates a diagnostic list. The output data generates a diagnostic list for the appropriate device (hardware).

[0034] The content of the training data described above is determined according to the model information that indicates the model of the target first processing unit 10. In other words, the model of the target first processing unit 10 obtains a trained model using training data appropriate for that model. The generation unit 203 includes that trained model.

[0035] Next, the CPU 101 collects POST logs obtained according to the BIOS, and system logs such as SEL and syslog obtained from the OS (step S11). The CPU 101 sends the collected POST logs and system logs to the second processing unit 20.

[0036] The receiving unit 201 of the second processing unit 20 receives POST logs and system logs from the first processing unit 10 (step S24). The receiving unit 201 outputs the received POST logs and system logs to the analysis module 205 of the second processing unit 20. The analysis module 205 reads the POST logs and system logs output by the receiving unit 201. The analysis module 205 analyzes the read POST logs and system logs (step S25).

[0037] For example, the analysis module 205 includes an AI model that operates based on learning without supervised data. Here, the analysis module 205 takes information contained in POST logs and system logs as input to the AI ​​model and uses anomaly detection and classification algorithms to classify and analyze errors based on "target device," "error state," and "error content." The analysis module 205 outputs the analysis results to the judgment module 206.

[0038] The judgment module 206 inputs the analysis results output by the analysis module 205 into an AI model (machine learning-based model) that operates based on learning without supervised data. The judgment module 206 then determines the severity of the analyzed anomaly and the necessity of device diagnosis based on the analysis results input into the AI ​​model (machine learning-based model) (step S26).

[0039] For example, if the AI ​​model (machine learning-based model) outputs a minor error in the input analysis result, the judgment module 206 will determine to skip the diagnosis (i.e., the severity of the analyzed anomaly and the need for device diagnosis are low). Also, if the AI ​​model (machine learning-based model) detects a serious error in the input analysis result, the judgment module 206 will recommend a detailed hardware diagnosis (i.e., the severity of the analyzed anomaly and the need for device diagnosis are high). Note that the AI ​​model (machine learning-based model) included in the judgment module 206 is different from the AI ​​model included in the analysis module 205 mentioned above, which operates based on learning without supervised data.

[0040] Finally, the generation unit 203 reads these analysis results and judgment results as input. The generation unit 203 includes an AI model (unsupervised). Based on the analysis results of the latest POST logs and system logs and the judgment results of the need for diagnosis, the generation unit 203 updates (generates) the device diagnostic checklist periodically or in real time (step S27). This process eliminates unnecessary diagnoses, reduces the time required for POST, and prevents missing device abnormalities. As a result, the reliability of the processing system 1 can be ensured.

[0041] Next, the conversion module 207 of the second processing unit 20 reads the updated device diagnostic checklist. The conversion module 207 then converts the read device diagnostic checklist from its internal format to a format that can be read by NVRAM or CMOS (step S28). Alternatively, the UI module 204 of the second processing unit 20 may display the device diagnostic checklist on a web-based system, allowing the user to update it manually (step S29). Then, while the BIOS and OS of the first processing unit 10 are starting up, the transmission unit 208 of the second processing unit 20 transmits the converted device diagnostic checklist to the NVRAM or CMOS of the first processing unit 10 (step S30).

[0042] The CPU 101 of the first processing unit 10 receives a device diagnostic checklist from the second processing unit 20. The CPU 101 stores the received device diagnostic checklist in the NVRAM or CMOS of the first processing unit 10 (step S31). The CPU 101 turns off the power to the first processing unit 10 (step S32). When the first processing unit 10 is started up again, the CPU 101 performs a POST based on the device diagnostic checklist stored in the NVRAM or CMOS of the first processing unit 10, thereby reducing the time required for POST and suppressing the decrease in the error detection rate.

[0043] The generation unit 203 may have a data table that shows the correspondence between input data and output data, instead of a pre-trained AI model. The generation unit 203 then identifies the input data in the data table that matches the input data actually input to the generation unit 203. The generation unit 203 then identifies the output data corresponding to the identified input data in the data table. The generation unit 203 may then generate a device diagnostic checklist by outputting the identified output data (i.e., the device diagnostic checklist).

[0044] (advantage) The above describes a processing system 1 according to one embodiment of the present disclosure. The processing system 1 comprises a first processing unit 10 and a second processing unit 20. The first processing unit 10 includes a CPU 101 (an example of a transmission means) that transmits model information of the first processing unit 10 to the second processing unit 20 as training data during the self-diagnosis process at power-on. The second processing unit 20 includes a generation unit 203 (an example of a generation means) that generates a device diagnostic checklist narrowed down to the devices to be diagnosed based on the model information. This processing system 1 enables the execution of a self-diagnosis process at startup on appropriate hardware.

[0045] Next, a processing system 700 according to some embodiments of the present disclosure will be described. Figure 4 is a diagram showing an example of the configuration of a processing system 700 according to some embodiments of the present disclosure. As shown in Figure 4, the processing system 700 comprises a first processing unit 701 and a second processing unit 702.

[0046] The first processing unit 701 includes a transmission means 7011. During the self-diagnostic process when the first processing unit 701 is powered on, the transmission means 7011 transmits model information of the first processing unit 701 to the second processing unit 702 as training data.

[0047] The second processing unit 702 includes a generation means 7021. Based on the model information, the generation means 7021 generates a device diagnostic checklist that narrows down the devices to be diagnosed.

[0048] The processing system 700 can be implemented, for example, using the functions of the processing system 1 illustrated in Figure 1. The first processing unit 701 can be implemented, for example, using the functions of the first processing unit 10 illustrated in Figure 1. The second processing unit 702 can be implemented, for example, using the functions of the second processing unit 20 illustrated in Figure 1.

[0049] The transmission means 7011 can be implemented, for example, using the functions of the CPU 101 as illustrated in Figure 1. The generation means 7021 can be implemented, for example, using the functions of the generation unit 203 as illustrated in Figure 1.

[0050] Next, the processing performed by the processing system 700 according to some embodiments of the present disclosure will be described. Figure 5 is a diagram showing an example of the processing flow of the processing system 700 according to some embodiments of the present disclosure. Here, the processing of the processing system 700 will be described with reference to Figure 5.

[0051] In the first processing unit 701 of the processing system 700, the transmission means 7011 transmits model information of the first processing unit 701 to the second processing unit 702 as training data during the self-diagnosis process when the first processing unit 701 is powered on (step S101). In the second processing unit 702 of the processing system 700, the generation means 7021 generates a device diagnostic checklist that narrows down the devices to be diagnosed based on the model information (step S102).

[0052] The processing system 700 according to several embodiments of the present disclosure has been described above. This processing system 700 enables the execution of startup self-diagnostic processing on appropriate hardware.

[0053] In addition, the order of the processes in each embodiment of this disclosure may be changed, as long as appropriate processing is performed.

[0054] Although each embodiment of this disclosure has been described, the processing system 1, the first processing unit 10, the second processing unit 20, and other control devices described above may have a computer system inside. The processing steps described above are stored in the form of a program on a computer-readable recording medium, and the processing is performed when the computer reads and executes this program. A specific example of a computer is shown below.

[0055] Figure 6 is a schematic block diagram showing the configuration of a computer according to at least one embodiment. As shown in Figure 6, the computer 5 includes a CPU (Central Processing Unit) 6, main memory 7, storage 8, and interface 9.

[0056] For example, the processing system 1, the first processing unit 10, the second processing unit 20, and other control devices described above are each implemented in the computer 5. The operation of each processing unit described above is stored in storage 8 in the form of a program. The CPU 6 reads the program from storage 8, loads it into main memory 7, and executes the above processing according to the program. The CPU 6 also allocates memory areas in main memory 7 corresponding to each of the above-mentioned storage units according to the program.

[0057] Examples of storage 8 include HDDs (Hard Disk Drives), SSDs (Solid State Drives), magnetic disks, magneto-optical disks, CD-ROMs (Compact Disc Read Only Memory), DVD-ROMs (Digital Versatile Disc Read Only Memory), and semiconductor memory. Storage 8 may be an internal medium directly connected to the bus of computer 5, or an external medium connected to computer 5 via interface 9 or a communication line. Furthermore, if this program is distributed to computer 5 via a communication line, computer 5, upon receiving the program, may expand it into main memory 7 and execute the above processing. In at least one embodiment, storage 8 is a tangible storage medium that is not temporary.

[0058] Furthermore, the above program may implement some of the functions described above. Moreover, the above program may be a file that can implement the above functions in combination with a program already recorded in the computer system, a so-called differential file (differential program).

[0059] While several embodiments of this disclosure have been described, these embodiments are illustrative and do not limit the scope of the disclosure. These embodiments may be modified in various ways, without departing from the gist of the disclosure.

[0060] Furthermore, some or all of the above embodiments may also be described as follows, but are not limited to these.

[0061] (Note 1) A processing system comprising a first processing unit and a second processing unit, The first processing apparatus is A transmission means that transmits model information of the first processing unit as training data to the second processing unit during the self-diagnostic process when the power is turned on. Equipped with, The second processing apparatus is A generation means that generates a device diagnostic checklist with the target devices narrowed down based on the aforementioned model information. A processing system equipped with the following features.

[0062] (Note 2) The second processing apparatus is A device on the cloud, The processing system described in Appendix 1.

[0063] (Note 3) The second processing apparatus is Analysis means for analyzing abnormal conditions of a device, Equipped with, The first transmission means is, The abnormal state of the device detected during operation is transmitted to the second processing unit. The aforementioned analysis means is The abnormal state of the device transmitted by the first transmission means is analyzed, and the analysis results are reflected in the device diagnostic checklist as a precursor to the abnormality. The processing system described in Appendix 1 or Appendix 2.

[0064] (Note 4) A second transmission means transmits the device diagnostic checklist, which reflects the analysis results from the analysis means as precursors to the abnormality, to the first processing unit. The processing system described in Appendix 3, comprising:

[0065] (Note 5) The second transmission means is, The device diagnostic checklist generated by the generation means is transmitted to the first processing unit. The processing system described in Appendix 4, comprising:

[0066] (Note 6) A processing method performed by a processing system comprising a first processing unit and a second processing unit, The first processing apparatus, During the self-diagnostic process at power-on, the model information of the first processing unit is transmitted to the second processing unit as training data. The second processing apparatus, Based on the aforementioned model information, a device diagnostic checklist is generated that narrows down the devices to be diagnosed. A processing method that includes the following.

[0067] (Note 7) The second processing apparatus is A device on the cloud, The processing method described in Appendix 6.

[0068] (Note 8) The second processing apparatus, Analyze the abnormal state of the device, The first processing apparatus, The abnormal state of the device detected during operation is transmitted to the second processing unit. The second processing apparatus, The first processing unit analyzes the abnormal state of the device transmitted by the first processing unit and reflects the analysis results as a precursor to the abnormality in the device diagnostic checklist. The processing method described in Appendix 6 or Appendix 7, including the matter of.

[0069] (Note 9) The second processing apparatus, The device diagnostic checklist, which reflects the analysis results from the second processing unit as precursors to the abnormality, is transmitted to the first processing unit. The processing method described in Appendix 8, including the matter mentioned above.

[0070] (Note 10) The second processing apparatus, To transmit the generated device diagnostic checklist to the first processing unit, The processing method described in Appendix 8, including the method described in Appendix 8.

[0071] (Note 11) A computer in a processing system comprising a first processing unit and a second processing unit, In the self-diagnostic process when the power of the first processing unit is turned on, the model information of the first processing unit is transmitted to the second processing unit as training data, Based on the aforementioned model information, a device diagnostic checklist is generated that narrows down the devices to be diagnosed. A program that executes the command.

[0072] (Note 12) The second processing apparatus is A device on the cloud, The program described in Appendix 11.

[0073] (Note 13) The second processing apparatus, Analyze the abnormal state of the device, The first processing apparatus, The abnormal state of the device detected during operation is transmitted to the second processing unit. The second processing apparatus, The first processing unit analyzes the abnormal state of the device transmitted by the first processing unit and reflects the analysis results as a precursor to the abnormality in the device diagnostic checklist. A program described in Appendix 11 or Appendix 12 that causes the computer to perform the above action.

[0074] (Note 14) The second processing apparatus, The device diagnostic checklist, which reflects the analysis results from the second processing unit as precursors to the abnormality, is transmitted to the first processing unit. The program described in Appendix 13 that causes the computer to perform the above action.

[0075] (Note 15) The second processing apparatus, To transmit the generated device diagnostic checklist to the first processing unit, The program described in Appendix 14 that causes the aforementioned computer to execute. [Explanation of symbols]

[0076] 1,700 processing system 5. Computers 6, 101...CPU 7. Main Memory 8,202...Storage 9. Interface 10, 701 ···First Processing Unit 20,702...Second processing unit 201... Receiver 203...Generation section 204...UI Module 205...Analysis Module 206... Judgment Module 207...Conversion Module 208...Transmitter 7011...Transmission method 7021...Generation means

Claims

1. A processing system comprising a first processing unit and a second processing unit, The second processing apparatus is A generation means including a trained AI model whose parameters are determined using training data in which model information of the first processing device is input data and a device diagnostic checklist corresponding to the input data is output data, and a generation means that generates a device diagnostic checklist narrowed down to the devices to be diagnosed based on the trained AI model. Equipped with, The first processing apparatus is In the self-diagnostic process at power-on, a first transmission means transmits model information of the first processing unit to the second processing unit, A checking means for checking the devices shown in the device diagnostic checklist generated by the generation means, A processing system equipped with the following features.

2. The second processing apparatus is A device on the cloud, The processing system according to claim 1.

3. The second processing apparatus is Analysis means for analyzing abnormal conditions of a device, Equipped with, The first transmission means is, The abnormal state of the device detected during operation is transmitted to the second processing unit. The aforementioned analysis means is The abnormal state of the device transmitted by the first transmission means is analyzed, and the analysis results are reflected in the device diagnostic checklist as a precursor to the abnormality. The processing system according to claim 1 or claim 2.

4. A second transmission means transmits the device diagnostic checklist, which reflects the analysis results from the analysis means as precursors to the abnormality, to the first processing unit. The processing system according to claim 3, comprising:

5. The second transmission means is, The device diagnostic checklist generated by the generation means is transmitted to the first processing unit. The processing system according to claim 4.

6. A processing method performed by a processing system comprising a first processing unit and a second processing unit, The second processing apparatus, The generation means includes a trained AI model whose parameters are determined using training data, in which model information of the first processing unit is input data and a device diagnostic checklist corresponding to the input data is output data, and generates a device diagnostic checklist that narrows down the devices to be diagnosed based on the trained AI model. The first processing apparatus, During the self-diagnostic process at power-on, the model information of the first processing unit is transmitted to the second processing unit. The second processing unit checks the devices shown in the device diagnostic checklist generated by the second processing unit. A processing method that includes the following.

7. A computer in a processing system comprising a first processing unit and a second processing unit, The generation means includes a trained AI model whose parameters are determined using training data, which takes model information of the first processing device as input data and a device diagnostic checklist corresponding to the input data as output data, and generates a device diagnostic checklist that narrows down the devices to be diagnosed based on the trained AI model. In the self-diagnostic process when the power of the first processing unit is turned on, the model information of the first processing unit is transmitted to the second processing unit, Based on the aforementioned model information, a device diagnostic checklist is generated that narrows down the devices to be diagnosed. Check the devices listed in the generated device diagnostic checklist, A program that executes the command.

Images