MODEL ANALYSIS APPARATUS, MODEL ANALYSIS METHOD, AND PROGRAM

Abstract

A model analysis device according to the present disclosure is provided with: a target information acquisition means that acquires equipment configuration information including hardware configuration information and software configuration information, which consists of firmware configuration information and protocol processing software configuration information, about a verification target; a model information acquisition means that acquires configuration information from which a trained model used to verify the verification target has been generated; a suitability evaluation means that evaluates the suitability of the verification target for the trained model on the basis of the acquired configuration information about the verification target and the trained model; and an output means that outputs the evaluation result.

Description

[Technical field]

[0001] The present disclosure relates to a model analysis device, a model analysis method, and a recording medium. [Background technology]

[0002] There is a demand to use trained models provided by third parties or trained models created in the past in the latest environment to verify the security of specific network devices. When verifying operation using these trained models, it is required that our environment is similar to the environment in which the trained models were created.

[0003] For example, Patent Document 1 discloses a server device capable of selecting and supplying an optimal trained model for various devices with different environments, conditions, etc. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2020-161167 A Summary of the Invention [Problem to be solved by the invention]

[0005] However, the invention described in the above-mentioned Patent Document 1 merely selects a model that is compatible between different devices based on the data used to generate the trained model. In operational verification of network devices, it is necessary to select a model taking into consideration software information that configures the device. However, there are various combinations of software used in devices, and selecting a compatible model is time-consuming.

[0006] One example of the objectives of the present disclosure is to provide a model analysis device that can easily search for a suitable trained model in operational verification of network equipment. [Means for solving the problem]

[0007] A model analysis apparatus in one aspect of the present disclosure comprises a target information acquisition means for acquiring equipment configuration information including hardware configuration information of a verification target and software configuration information consisting of firmware configuration information and protocol processing software configuration information, a model information acquisition means for acquiring equipment configuration information in an environment in which a trained model used to verify the verification target was generated, a compatibility evaluation means for evaluating the compatibility of the verification target with the trained model based on the acquired equipment configuration information of the verification target and the trained model, and an output means for outputting the evaluated results.

[0008] A model analysis apparatus in one aspect of the present disclosure includes a target information acquisition means for acquiring device configuration information including hardware configuration information of a verification target and software configuration information consisting of firmware configuration information and protocol processing software configuration information, a model search means for searching for a trained model suitable for verification of the verification target based on the acquired device configuration information, and an output means for outputting the searched trained model.

[0009] A model analysis method in one aspect of the present disclosure acquires equipment configuration information including hardware configuration information of a verification target and software configuration information consisting of firmware configuration information and protocol processing software configuration information, acquires equipment configuration information in an environment in which a trained model used to verify the verification target was generated, evaluates the compatibility of the verification target with the trained model based on the acquired equipment configuration information of the verification target and the trained model, and outputs the evaluated results.

[0010] Another model analysis method in one aspect of the present disclosure acquires device configuration information including hardware configuration information of a verification target and software configuration information consisting of firmware configuration information and protocol processing software configuration information, searches for a trained model suitable for verification of the verification target based on the acquired device configuration information, and outputs the searched trained model.

[0011] A recording medium in one aspect of the present disclosure stores a program that causes a computer to acquire equipment configuration information including hardware configuration information of a verification target and software configuration information consisting of firmware configuration information and protocol processing software configuration information, acquire equipment configuration information in an environment in which a trained model used to verify the verification target was generated, evaluate the suitability of the verification target with respect to the trained model based on the acquired equipment configuration information of the verification target and the trained model, and output the evaluated results.

[0012] Another recording medium in one aspect of the present disclosure acquires device configuration information including hardware configuration information of a verification target and software configuration information consisting of firmware configuration information and protocol processing software configuration information, searches for a trained model suitable for verification of the verification target based on the acquired device configuration information, and outputs the searched trained model. Effect of the Invention

[0013] One example of an effect of the present disclosure is that it can provide a model analysis device that can easily search for a suitable trained model when verifying the operation of network equipment. [Brief description of the drawings]

[0014] [Figure 1] FIG. 1 is a block diagram showing the configuration of a model analysis device according to the first embodiment. [Diagram 2] FIG. 2 is a diagram showing a hardware configuration in which the model analysis apparatus according to the first embodiment is realized by a computer apparatus and its peripheral devices. [Diagram 3] FIG. 3 is a table showing an example of storage of device configuration information in the first embodiment. [Figure 4] FIG. 4 is a flowchart showing the operation of the model analysis in the first embodiment. [Diagram 5] FIG. 5 is a block diagram showing a configuration of a model analysis device in a modified example of the first embodiment. [Figure 6]FIG. 6 is a block diagram showing a configuration of a model analysis apparatus according to the second embodiment. [Figure 7] FIG. 7 shows an example of a display screen of a matching model search tool in the second embodiment. [Figure 8] FIG. 8 shows another example of a display screen of the matching model search tool in the second embodiment. [Figure 9] FIG. 9 is a flowchart showing the operation of the model analysis in the second embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0015] Next, an embodiment will be described in detail with reference to the drawings.

[0016] [First embodiment] FIG. 1 is a block diagram showing a configuration of a model analysis device 100 in the first embodiment. The model analysis device 100 in the first embodiment is a device for verifying whether a trained model generated in the past in its own environment and a trained model generated in the environment of another operator are compatible with the configuration of its own network equipment when a trained model is shared among a plurality of operators. Referring to FIG. 1, the model analysis device 100 includes a target information acquisition unit 101, a model information acquisition unit 102, a compatibility evaluation unit 103, and an output unit 104. The model analysis device 100, which is an essential component of this embodiment, will be described in detail below.

[0017] 2 is a diagram illustrating an example of a hardware configuration in which the model analysis device 100 in the first embodiment of the present disclosure is realized by a computer device 500 including a processor. As illustrated in FIG. 2, the model analysis device 100 includes a central processing unit (CPU) 501, memories such as a read only memory (ROM) 502 and a random access memory (RAM) 503, a storage device 505 such as a hard disk for storing a program 504, a communication interface (I / F) 508 for network connection, and an input / output interface 511 for inputting and outputting data. In the first embodiment, the configuration information acquired by the target information acquisition unit 101 and the model information acquisition unit 102 is input to the model analysis device 100 via the input / output interface 511, for example.

[0018] CPU 501 operates an operating system to control the entire model analysis device 100 according to the first embodiment of the present invention. CPU 501 also reads programs and data from a recording medium 506 mounted in, for example, a drive device 507 into a memory. CPU 501 also functions as object information acquisition unit 101, model information acquisition unit 102, compatibility evaluation unit 103, output unit 104, or parts of these in the first embodiment, and executes processes or commands in the flowchart shown in Fig. 4, which will be described later, based on the programs.

[0019] The recording medium 506 is, for example, an optical disk, a flexible disk, a magneto-optical disk, an external hard disk, or a semiconductor memory. A recording medium that is a part of the storage device is a non-volatile storage device, and the program is recorded therein. The program may also be downloaded from an external computer (not shown) that is connected to a communication network.

[0020] The input device 509 is realized by, for example, a mouse, a keyboard, built-in key buttons, etc., and is used for input operations. The input device 509 is not limited to a mouse, a keyboard, or built-in key buttons, and may be, for example, a touch panel. The output device 510 is realized by, for example, a display, and is used to check the output.

[0021] As described above, the first embodiment shown in FIG. 1 is realized by the computer hardware shown in FIG. 2. However, the means for realizing each part of the model analysis device 100 in FIG. 1 is not limited to the configuration described above. The model analysis device 100 may be realized by one physically combined device, or may be realized by two or more physically separated devices connected by wire or wirelessly. For example, the input device 509 and the output device 510 may be connected to the computer device 500 via a network. The model analysis device 100 in the first embodiment shown in FIG. 1 may also be configured by cloud computing or the like.

[0022] 1, the target information acquisition unit 101 is a means for acquiring configuration information of a device including hardware configuration information of a verification target and software configuration information consisting of firmware configuration information and protocol processing software configuration information. Verification in this embodiment refers to verifying whether there are any abnormalities in the operation, security, etc. of the hardware and software (firmware and protocol processing software) of the network device. The verification target also includes a configuration consisting of multiple network devices.

[0023] The hardware configuration is, for example, chip configuration information that controls the operation of the device. The chip configuration information includes the architecture, manufacturer name, model number, etc. of the chip. The firmware information is information about the software for operating the hardware, and includes, for example, the firmware name and version number. The protocol information includes information about the protocol name and protocol processing software (routing software). The protocol name, for example, refers to the protocol name of layer 3, which is the "network layer" in the third layer of the OSI (Open Systems Interconnection) reference model. Specific examples of protocol names include BGP (Border Gateway Protocol), OSPF (Open Shortest Path First), and STP (Spanning Tree Protocol). For example, if the protocol is BGP, the protocol processing software is "GoBGP" or "FRR", and if the protocol is OSPF, the protocol processing software is "FRR" or "Quagga".

[0024] Fig. 3 is a table showing an example of storage of device configuration information in this embodiment. As shown in Fig. 3, for example, in configuration A, the chip name model number "ABC1111chip" is stored as hardware configuration information. In addition, the firmware name FSP (Intel Firmware Support Package) and its version "v0.9" are stored as firmware configuration information. The protocol name "STP", its protocol processing software "FRR", and its version "v6.1" are stored as protocol configuration information.

[0025] The target information acquisition unit 101 acquires configuration information of the device to be verified, for example, when a user performs an operation for verification as a trigger. The target information acquisition unit 101 may search for this information stored in the storage device 505. For example, identifier information of the verification target and configuration information of the device to be verified are stored in a linked state in the storage device 505. In this case, the target information acquisition unit 101 can acquire configuration information linked to the ID stored in the storage device 505 by accepting input of identifier information such as an ID given to the verification target by the user. Note that the configuration information may be stored in another configuration (for example, a configuration information storage means) instead of the storage device 505. The target information acquisition unit 101 outputs the acquired configuration information of the verification target to the conformity evaluation unit 103.

[0026] The model information acquisition unit 102 is a means for acquiring configuration information of a device in an environment in which a trained model used for verifying a verification target is generated. The trained model is a model generated by machine learning in order to output a verification result based on, for example, verification data in the past when the same or similar configuration is in a normal state and an abnormal state in each business operator. The trained model includes, but is not limited to, a decision tree model, a linear regression model, a logistic regression model, a neural network model, and the like. The model information acquisition unit 102 acquires configuration information of a device of a trained model used for verifying a verification target, for example, by receiving an input from an input device 509 by a user. In addition, when the configuration information of a device of a trained model is stored in the storage device 505, the model information acquisition unit 102 may acquire the configuration information from the storage device 505. Note that the configuration information of the device referred to here is configuration information that can be compared with the configuration information acquired by the target information acquisition unit 101. In other words, it is the configuration information of a device including hardware configuration information and software configuration information consisting of firmware configuration information and protocol processing software configuration information. The model information acquisition unit 102 outputs the configuration information of the acquired trained model to the compatibility evaluation unit 103.

[0027] The compatibility evaluation unit 103 is a means for evaluating the compatibility of the validation target with the trained model based on the acquired configuration information of the devices of the validation target and the trained model. When the configuration information is input from the target information acquisition unit 101 and the model information acquisition unit 102, the compatibility evaluation unit 103 evaluates the compatibility of the validation target with the trained model. Specifically, the compatibility evaluation unit 103 compares each piece of configuration information with another and evaluates the presence or absence of compatibility based on the similarity of the configuration information.

[0028] For example, if the similarity of the configuration information is within a predetermined range, the compatibility evaluation unit 103 evaluates that there is compatibility. On the other hand, if the similarity of the configuration information is not within the predetermined range, the compatibility evaluation unit 103 evaluates that there is no compatibility.

[0029] The predetermined range in the hardware configuration information is, for example, when chip names are compared as hardware configuration information, both are from the same series by the same manufacturer. In this case, the compatibility evaluation unit 103 determines the similarity of the hardware configuration information by taking into account OEM (Original Equipment Manufacturing) supply information. Specifically, the compatibility evaluation unit 103 determines that the hardware configuration information is the same even if the chip name and manufacturer name are different if the manufacturer and product information match due to OEM supply. The predetermined range in the software information is, for example, when the firmware name and protocol name match and the difference in the software version is only a minor version. However, this range is not limited to this range as long as the software operation can be considered to be substantially equivalent. In addition, the compatibility evaluation unit 103 determines the similarity of the software configuration information by taking into account software compatibility information. For example, the compatibility evaluation unit 103 considers that "FRR2.0" and "Quagga1.1" are compatible, and determines the similarity of these software information as being the same. The compatibility evaluation unit 103 thus determines the degree of similarity and outputs the compatibility to the output unit 104 .

[0030] The output unit 104 is a means for outputting the result of the evaluation by the compatibility evaluation unit 103. The output unit 104 outputs the compatibility evaluation result to an output device 510 or the like. The compatibility evaluation is an evaluation of whether or not the trained model to be applied is compatible under its own configuration environment.

[0031] The operation of model analysis device 100 configured as above will be described with reference to the flowchart of FIG.

[0032] 4 is a flowchart showing an outline of the operation of the model analysis device 100 in the first embodiment. Note that the processing according to this flowchart may be executed based on program control by the above-mentioned processor.

[0033] As shown in FIG. 4, first, the target information acquisition unit 101 acquires configuration information of the equipment in the verification target (step S101). Next, the model information acquisition unit 102 acquires configuration information of the equipment in the environment in which the trained model used to verify the verification target was generated (step S102). Next, the compatibility evaluation unit 103 evaluates the compatibility of the verification target with the trained model based on the acquired configuration information of the equipment of the verification target and the trained model (step S103). Finally, the output unit 104 outputs the result of the compatibility evaluated by the compatibility evaluation unit 103 (step S104). With this, the model analysis device 100 ends the operation of the model analysis.

[0034] In the model analysis device 100 according to the first embodiment, the compatibility evaluation unit 103 evaluates the compatibility of the verification target with the trained model based on device configuration information including hardware configuration information of the obtained verification target and trained model, and software configuration information including firmware configuration information and protocol processing software configuration information. This makes it possible to easily search for a compatible model even in an operating environment including multiple software programs.

[0035] [Modification of the first embodiment] Next, a modified example of the first embodiment of the present disclosure will be described in detail with reference to the drawings. FIG. 5 is a block diagram showing the configuration of a model analysis device 110 in a modified example of the first embodiment. The model analysis device 110 in the modified example of the first embodiment includes a target information acquisition unit 111, a model information acquisition unit 112, a compatibility calculation unit 113, a compatibility evaluation unit 114, and an output unit 115. That is, the modified example of the first embodiment is significantly different in that it includes a compatibility calculation unit 113 in addition to the configuration of the first embodiment. The modified example of the first embodiment also differs from the first embodiment in that it uses network configuration information as configuration information in addition to hardware configuration information and software configuration information.

[0036] The target information acquisition unit 111 acquires network configuration information in addition to hardware configuration information and software configuration information of the verification target. Network configuration information is information that indicates the connection relationship between hardware. In this specification, the network configuration information is expressed as "A⇔B⇔C⇔D." This indicates that device A and device B are directly connected, device B and device C are directly connected, and device C and device D are directly connected. The method by which the target information acquisition unit 111 acquires network configuration information is the same as the method by which the target information acquisition unit 101 acquires hardware information and software information.

[0037] In the first embodiment, the model information acquisition unit 112 acquires network configuration information in addition to hardware configuration information and software information from which a trained model used to verify a verification target has been generated. Note that the method by which the model information acquisition unit 112 acquires network configuration information is similar to the method by which the model information acquisition unit 112 acquires hardware information and software information.

[0038] The compatibility calculation unit 113 calculates compatibility indicating the degree of compatibility based on the similarity between the hardware configuration, software information, and network configuration information of the validation target and the trained model acquired by the target information acquisition unit 111 and the model information acquisition unit 112. The compatibility calculation unit 113 sets a coefficient indicating the similarity for each configuration, setting the coefficient value to "1.0" in the case of a perfect match and decreasing the value of the coefficient depending on the degree of difference.

[0039] Specifically, the compatibility calculation unit 113 sets the coefficient to "1.0" if the hardware configuration is of the same manufacturer and model number. If the hardware configuration is of the same series by the same manufacturer, the coefficient is set to "0.8." If the software configuration is the same software and the same version, the compatibility calculation unit 113 sets the coefficient to "1.0." If the software is the same but the versions are different, the coefficient is changed according to the difference in the versions. For example, if the difference is in the minor version name, the coefficient is set to "0.9," and if the difference is in the major version name, the coefficient is set to "0.5."

[0040] The compatibility calculation unit 113 also calculates the compatibility of the network configuration information based on the similarity. The similarity of the network configuration information indicates the similarity of the connection relationship of the devices among the devices that configure the network. For example, when the network configuration of the network itself is "A⇔B⇔C⇔D", if the network connection configuration of "A⇔B⇔C" is the same (for example, "D⇔A⇔B⇔C"), the compatibility calculation unit 113 sets the coefficient to "0.8". As another example, when the network configuration of the network itself is "A⇔B⇔C⇔D", if only the network connection configuration of "A⇔B" is the same (for example, "A⇔B⇔D⇔C", "C⇔A⇔B⇔D", "D⇔A⇔B⇔C", "A⇔B⇔C⇔D", or "A⇔B⇔D⇔C"), the compatibility calculation unit 113 sets the coefficient to "0.5".

[0041] As described above, the compatibility calculation unit 113 calculates the coefficients for the hardware configuration, the software configuration, and the network configuration, and then calculates the compatibility by calculating the average of the calculated coefficients. Note that the compatibility calculation unit 113 may calculate the compatibility by further using the network configuration information only when the hardware configuration and the software configuration are completely identical. However, the method of calculating the compatibility by the compatibility calculation unit 113 is not limited to this as long as it is a method that can calculate the similarity of each configuration.

[0042] The compatibility evaluation unit 114 evaluates the compatibility of the trained model to be verified based on the compatibility calculated by the compatibility calculation unit 113. If the calculated compatibility is equal to or greater than a threshold, the compatibility evaluation unit 114 determines that there is compatibility. On the other hand, if the calculated compatibility is smaller than the threshold, the compatibility evaluation unit 114 determines that there is no compatibility. The threshold is determined in advance and is stored in, for example, the storage device 505.

[0043] The output unit 115 outputs the result of the evaluation by the compatibility evaluation unit 114. The evaluation of compatibility by the output unit 115 is an evaluation of whether or not the trained model to be adapted is adapted under its own configuration environment. The output unit 115 may output the result of the compatibility calculated by the compatibility calculation unit 113.

[0044] In the model analysis device 110 in the modified example of the first embodiment, the compatibility evaluation unit 114 evaluates the compatibility of the trained model to be verified based on the compatibility calculated by the compatibility calculation unit 113. As a result, the compatibility evaluation unit 114 determines that there is compatibility even if the hardware configuration information is different, for example, if the software configuration information is the same and the compatibility is equal to or greater than a threshold. Therefore, it is possible to evaluate whether the trained model is compatible as a result of comprehensively judging the configuration information of the device.

[0045] [Second embodiment] Next, a second embodiment of the present disclosure will be described in detail with reference to the drawings. Hereinafter, the description of the present embodiment will be omitted for the content that overlaps with the above description, so long as the description of the present embodiment is not unclear. In the second embodiment, the model analysis device 120 is a device for searching which model is suitable for its own equipment configuration when sharing a trained model among multiple businesses. Each component in each embodiment of the present disclosure can be realized by a computer device based on program control or firmware, as well as by hardware, as in the computer device shown in FIG. 2.

[0046] Fig. 6 is a block diagram showing a configuration of a model analysis device 120 according to a second embodiment of the present disclosure. The model analysis device 120 according to the second embodiment will be described with reference to Fig. 6, focusing on differences from the model analysis device 100 according to the first embodiment. The model analysis device 120 according to the second embodiment includes a target information acquisition unit 121, a model search unit 122, an output unit 123, and a result receiving unit 124.

[0047] The target information acquisition unit 121 in this embodiment can acquire configuration information of the verification target linked to the identifier information by inputting identifier information such as an ID assigned to the device to be verified. In this embodiment, the configuration information is device configuration information including hardware configuration information and software configuration information consisting of firmware configuration information and protocol processing software configuration information. The target information acquisition unit 121 outputs the acquired device configuration information to the model search unit 122.

[0048] The model search unit 122 searches for a suitable trained model based on the configuration information of the device to be verified. When the configuration information of the verification target is input from the target information acquisition unit 121, a trained model previously generated by each business operator with the same or similar configuration is searched for. Here, "similar" refers to a case where the similarity described in the first embodiment is within a predetermined range. The trained model is a trained model generated by machine learning for outputting a verification result based on verification data in normal and abnormal cases at each business operator.

[0049] The output unit 123 is a means for displaying and outputting the trained model searched for by the model search unit 122 on the output device 510 or the like. The output unit 123 may output, as metadata, supplementary information such as the purpose of the model, the format of data used in the validation data (time, tx_pkt_cnt, rx_pkt_cnt), and usage method, or URL information indicating the storage location of the trained model.

[0050] Here, a description will be given of the execution of the process from the acquisition of configuration information by the target information acquisition unit 121 to the output of the search results of model candidates by the output unit 123 in this embodiment. Fig. 7 is an example of a display screen of a compatible model search tool. As shown in Fig. 7, when an ID given to a device to be verified is input to the input unit A for search, the configuration information linked to the ID and information on a trained model compatible with that configuration information are displayed.

[0051] Fig. 8 is another example of the display screen of a compatible model search tool. As shown in Fig. 8, when an ID assigned to a verification target is entered into input section A for a search, information on trained model candidates that are compatible with the configuration of the verification target is displayed. In the example of Fig. 8, the information on trained model candidates is output in order of compatibility between the model name and the verification target (i.e., the higher the compatibility value).

[0052] The result receiving unit 124 is a means for receiving the compatibility result of the trained model to the verification target. The result receiving unit 124 receives the compatibility result by operation from the input device 509. The result receiving unit 124 receives the result based on a criterion such as higher, equal, or lower than the compatibility value output by the compatible model search tool, and stores the result in the storage device 505. When searching for a compatible model thereafter, the model search unit 122 searches by referring to the stored result.

[0053] The operation of model analysis device 120 configured as above will be described with reference to the flowchart of FIG.

[0054] 9 is a flowchart showing an outline of the operation of the model analysis device 120 in the second embodiment. Note that the processing according to this flowchart may be executed based on program control by the above-mentioned processor.

[0055] As shown in FIG. 9, first, the target information acquisition unit 111 acquires configuration information of the device to be verified (step S201). Next, the model search unit 122 searches for a suitable trained model based on the configuration of the device to be verified (step S202). Next, the output unit 203 outputs information on the trained model searched by the model search unit 122 (step S203). Finally, the result receiving unit 124 receives an input of the result of actually matching the trained model (step S204). Note that the result received by the result receiving unit 124 is used when the model search unit 122 searches for a trained model when the flow is repeated again. With the above, the model analysis device 100 ends the operation of the model analysis.

[0056] In the model analysis device 120 according to the second embodiment of the present disclosure, the model search unit 122 searches for a suitable trained model based on configuration information of the device, including hardware configuration information, firmware configuration information, and protocol processing software configuration information, of the verification target. This makes it possible to obtain information on a suitable trained model by simply inputting the configuration information of the device.

[0057] Although the present invention has been described above with reference to the embodiments, the present invention is not limited to the above-mentioned embodiments. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present invention within the scope of the present invention.

[0058] For example, although a plurality of operations are described in order in the form of a flowchart, the order of description does not limit the order in which the plurality of operations are performed. Therefore, when implementing each embodiment, the order of the plurality of operations can be changed within a range that does not interfere with the content. In addition, in this embodiment, a suitable trained model is searched for based on the configuration information of the device including the hardware configuration information of the verification target, firmware configuration information, and protocol processing software configuration information, but this is not limited to this. The model search unit 122 may search for a suitable model based on network configuration information and verification contents in addition to the configuration information of the device including, for example, the hardware configuration information of the verification target and software configuration information consisting of firmware configuration information and protocol processing software configuration information.

[0059] A part or all of the above-described embodiments can be described as, but is not limited to, the following supplementary notes.

[0060] (Appendix 1) a target information acquiring means for acquiring configuration information of a device including hardware configuration information of a verification target and software configuration information consisting of firmware configuration information and protocol processing software configuration information; A model information acquisition means for acquiring configuration information of the device in an environment in which a trained model used for verifying the verification target is generated; A conformity evaluation means for evaluating the conformity of the validation target with respect to the trained model based on the acquired configuration information of the validation target and the trained model; and an output means for outputting the evaluated result.

[0061] (Appendix 2) The configuration information of the device in the environment in which the validation target and the trained model were generated includes configuration information of a plurality of devices, the target information acquiring means and the model information acquiring means further acquire, as the configuration information, network configuration information including connection information between the plurality of devices; 2. The model analysis apparatus of claim 1.

[0062] (Appendix 3) 3. The model analysis apparatus according to claim 1, wherein the hardware configuration information of the verification target and the hardware configuration information from which the trained model was generated include chip configuration information that controls the operation of the device.

[0063] (Appendix 4) The method further includes a degree of conformance calculation means for calculating a degree of conformance indicating a degree of conformance based on the acquired configuration information of the verification target and the trained model, 4. The model analysis apparatus according to any one of claims 1 to 3, wherein the compatibility evaluation means evaluates the compatibility based on the calculated degree of compatibility.

[0064] (Appendix 5) The verification target further includes a configuration information storage means for storing the identifier information of the verification target and the configuration information of the verification target in a linked manner, 5. The model analysis apparatus according to any one of claims 1 to 4, wherein the target information acquisition means acquires the configuration information stored in the configuration information storage means based on the identifier information of the verification target.

[0065] (Appendix 6) a target information acquiring means for acquiring configuration information of a device including hardware configuration information of a verification target and software configuration information consisting of firmware configuration information and protocol processing software configuration information; A model search means for searching for a trained model suitable for verification of the verification target based on the acquired configuration information of the device; and an output means for outputting the searched trained model.

[0066] (Appendix 7) the configuration information of the device to be verified includes configuration information of a plurality of devices, The target information acquisition means further acquires network configuration information including connection information between the plurality of devices as the configuration information. 7. The model analysis apparatus of claim 6.

[0067] (Appendix 8) 8. The model analysis apparatus according to claim 6, wherein the hardware configuration information of the verification target includes chip configuration information that controls the operation of the device.

[0068] (Appendix 9) The method further includes a result receiving means for receiving a result of adapting the trained model to a verification target, The model analysis device according to any one of Addendums 6 to 8, wherein the model search means further uses the matching result to search for the matching trained model.

[0069] (Appendix 10) a configuration information storage means for storing the identifier information of the verification target and the configuration information of the verification target in a linked manner; The model analysis apparatus according to any one of claims 6 to 9, wherein the target information acquisition means acquires the configuration information stored in the configuration information storage means based on the identifier information of the verification target.

[0070] (Appendix 11) The model analysis device according to claim 6 or 7, wherein the trained model is a model that receives the configuration information as input and outputs the matching trained model candidate.

[0071] (Appendix 12) Acquire device configuration information including hardware configuration information of a verification target and software configuration information consisting of firmware configuration information and protocol processing software configuration information; Acquire configuration information of the device in an environment in which a trained model conforming to the validation target was generated; Evaluating the conformity of the validation target with respect to the trained model based on the acquired configuration information of the device of the validation target and the trained model; The model analysis method outputs the evaluated results.

[0072] (Appendix 13) Acquire device configuration information including hardware configuration information of a verification target and software configuration information consisting of firmware configuration information and protocol processing software configuration information; Searching for a trained model suitable for verification of the verification target based on the acquired configuration information of the device; A model analysis method that outputs the searched trained model.

[0073] (Appendix 14) Acquire device configuration information including hardware configuration information of a verification target and software configuration information consisting of firmware configuration information and protocol processing software configuration information; Acquire configuration information of the device in an environment in which a trained model conforming to the validation target was generated; Evaluating the conformity of the validation target with respect to the trained model based on the acquired configuration information of the device of the validation target and the trained model; A recording medium storing a program for causing a computer to execute the following: outputting the evaluated result.

[0074] (Appendix 15) Acquire device configuration information including hardware configuration information of a verification target and software configuration information consisting of firmware configuration information and protocol processing software configuration information; Searching for a trained model suitable for verification of the verification target based on the acquired configuration information of the device; A recording medium storing a program for causing a computer to execute the steps of: outputting the searched trained model. [Explanation of symbols]

[0075] 100, 110, 120 Model Analytical Equipment 101, 111, 121 Target information acquisition section 102, 112 Model information acquisition unit 113 Conformity calculation unit 103, 114 Conformity Assessment Department 104, 115, 123 Output section 122 Model Search Department 124 Results Reception Department

Claims

1. a target information acquiring means for acquiring configuration information of a device including hardware configuration information of a verification target and software configuration information consisting of firmware configuration information and protocol processing software configuration information; A model information acquisition means for acquiring configuration information of the device in an environment in which a trained model used for verifying the verification target is generated; A conformity evaluation means for evaluating conformity of the verification target with respect to the trained model based on the acquired configuration information of the verification target and the trained model; and an output means for outputting the evaluated result, The compatibility evaluation means evaluates the compatibility based on the similarity between configuration information of the verification target and configuration information of the environment in which the trained model was generated.

2. The configuration information of the device in the environment in which the validation target and the trained model are generated includes configuration information of a plurality of devices, the target information acquiring means and the model information acquiring means further acquire, as the configuration information, network configuration information including connection information between the plurality of devices; The model analysis apparatus of claim 1 .

3. 3. The model analysis device according to claim 1, wherein the hardware configuration information of the verification target and the hardware configuration information from which the trained model was generated include chip configuration information that controls operation of the device.

4. The method further includes: calculating a degree of conformance indicating a degree of conformance based on the acquired configuration information of the verification target and the trained model; 4. The model analysis device according to claim 1, wherein the compatibility evaluation means evaluates the compatibility based on the calculated degree of compatibility.

5. The verification target further includes a configuration information storage means for storing the identifier information of the verification target and the configuration information of the verification target in a linked manner, The model analysis apparatus according to any one of claims 1 to 4, wherein the target information acquisition means acquires the configuration information stored in the configuration information storage means based on the identifier information of the verification target.

6. a target information acquiring means for acquiring configuration information of a device including hardware configuration information of a verification target and software configuration information consisting of firmware configuration information and protocol processing software configuration information; A model search means for searching for a trained model suitable for verification of the verification target based on the acquired configuration information of the device; and an output means for outputting the retrieved trained model; The model search means searches for the trained model whose similarity to the configuration information of the device is within a predetermined range.

7. the configuration information of the device to be verified includes configuration information of a plurality of devices, The target information acquisition means further acquires network configuration information including connection information between the plurality of devices as the configuration information. The model analysis apparatus according to claim 6.

8. 8. The model analysis apparatus according to claim 6, wherein the hardware configuration information of the verification target includes chip configuration information that controls an operation of the device.

9. The method further includes a result receiving means for receiving a result of adapting the trained model to a verification target, The model analysis device according to any one of claims 6 to 8, wherein the model search means further uses the matching result to search for the matching trained model.

10. a configuration information storage means for storing the identifier information of the verification target and the configuration information of the verification target in a linked manner; The model analysis apparatus according to any one of claims 6 to 9, wherein the target information acquisition means acquires the configuration information stored in the configuration information storage means based on the identifier information of the verification target.

11. The model analysis device according to claim 6 or 7, wherein the trained model is a model that receives the configuration information as input and outputs the matching trained model candidate.

12. A computer comprising: Acquire device configuration information including hardware configuration information of a verification target and software configuration information consisting of firmware configuration information and protocol processing software configuration information; Acquire the configuration information in an environment in which a trained model conforming to the validation target was generated; Evaluating the conformity of the validation target with respect to the trained model based on the acquired configuration information of the validation target and the trained model; Outputting the evaluated result; A model analysis method in which, in the evaluation, the compatibility is evaluated based on a similarity between configuration information of a verification target and configuration information of an environment in which the trained model was generated.

13. A computer comprising: Acquire device configuration information including hardware configuration information of a verification target and software configuration information consisting of firmware configuration information and protocol processing software configuration information; Searching for a trained model suitable for verification of the verification target based on the acquired configuration information; Outputting the retrieved trained model; A model analysis method, in which the search searches for the trained model whose similarity to the configuration information of the device is within a predetermined range.

14. Acquire device configuration information including hardware configuration information of a verification target and software configuration information consisting of firmware configuration information and protocol processing software configuration information; Acquire the configuration information in an environment in which a trained model conforming to the validation target was generated; Evaluating the conformity of the validation target with respect to the trained model based on the acquired configuration information of the validation target and the trained model; Outputting the evaluated result; A program that causes a computer to execute the following in the evaluation: evaluating the compatibility based on a similarity between configuration information of a verification target and configuration information of an environment in which the trained model was generated.

15. Acquire device configuration information including hardware configuration information of a verification target and software configuration information consisting of firmware configuration information and protocol processing software configuration information; Searching for a trained model suitable for verification of the verification target based on the acquired configuration information; Outputting the retrieved trained model; A program for causing a computer to execute the following: in the search, searching for the trained model whose similarity to the configuration information of the device is within a predetermined range.

Images