Information processing device, information processing method, and information processing program

Abstract

An information processing device 10: acquires reference values relating to the operation of a system requested by a user; generates source code from the acquired reference values using a trained generation model that outputs source code for software that controls the system in response to input of operation information relating to the operation of the system; compiles the generated source code; generates software; evaluates whether or not the control state for the system using the generated software satisfies a reference value; and if the control state satisfies the reference value, provides the generated software to the user.

Description

Information processing device, information processing method, and information processing program

[0001] The present invention relates to an information processing device, an information processing method, and an information processing program.

[0002] In the past, software development in communication systems was carried out by developers, and the operation of the developed software was carried out by operators. However, as communication systems have become more complex, the importance of "DevOps," which closely coordinates software development and operation to improve productivity, has increased.

[0003] Japanese Patent Application Laid-Open No. 2023-183447

[0004] However, there is room for improvement in software development and operation. For example, in communication systems, software development and operation are carried out by different people, which can result in a long lead time from software development to operation. Furthermore, problems such as human error are likely to occur.

[0005] The present invention has been made in view of the above, and aims to provide an information processing device, an information processing method, and an information processing program that can shorten the process from software development to operation.

[0006] An information processing device according to one embodiment of the present invention includes an acquisition unit that acquires a reference value related to the operation of a system requested by a user, a code unit that generates source code from the acquired reference value using a trained generation model that outputs source code for software that controls the system in response to input operational information related to the operation of the system, a compilation unit that compiles the generated source code and generates the software, and an evaluation unit that evaluates whether the control status for the system using the generated software satisfies the reference value, and if the control status satisfies the reference value, provides the generated software to the user.

[0007] An information processing method according to one aspect of the present invention is an information processing method executed by an information processing device, and includes: an acquisition step of acquiring a reference value related to the operation of a system requested by a user; a coding step of generating source code from the reference value using a trained generative model that outputs source code for software that controls the system in response to input operational information related to the operation of the system; a compilation step of compiling the generated source code to generate the software; and an evaluation step of evaluating whether the control status for the system using the generated software satisfies the reference value, and if the control status satisfies the reference value, providing the generated software to the user.

[0008] An information processing program according to one aspect of the present invention causes a computer to execute the following steps: an acquisition step for acquiring a reference value related to the operation of a system requested by a user; a coding step for generating source code from the reference value using a trained generative model that outputs source code for software that controls the system in response to input operational information related to the operation of the system; a compilation step for compiling the generated source code to generate the software; and an evaluation step for evaluating whether the control status of the system using the generated software satisfies the reference value, and if the control status satisfies the reference value, providing the generated software to the user.

[0009] FIG. 1 is a diagram illustrating an overview of an information processing system according to an embodiment. FIG. 2 is a block diagram illustrating an example configuration of an information processing device of the information processing system according to an embodiment. FIG. 3 is a diagram illustrating an example of a training data storage unit of the information processing device according to an embodiment. FIG. 4 is a diagram illustrating an example of a code information storage unit of the information processing device according to an embodiment. FIG. 5 is a diagram illustrating an example of a software storage unit of the information processing device according to an embodiment. FIG. 6 is a diagram illustrating an example of a generative model storage unit of the information processing device according to an embodiment. FIG. 7 is a diagram illustrating a specific example 1 of an information processing system according to an embodiment. FIG. 8 is a diagram illustrating a specific example 2 of an information processing system according to an embodiment. FIG. 9 is a diagram illustrating a specific example 3 of an information processing system according to an embodiment. FIG. 10 is a flowchart illustrating an example of a processing flow of the information processing system according to an embodiment. FIG. 11 is a hardware configuration diagram illustrating an example of a computer that realizes the functions of the information processing device according to an embodiment.

[0010] Hereinafter, each embodiment of the present invention will be described with reference to the drawings, but the present invention is not limited to the following each embodiment. In addition, in the description of the drawings, the same parts are given the same reference numerals, and duplicated explanations are omitted, and explanations of members having similar functions and similar processes are also omitted.

[0011] 1. Introduction An overview of an information processing system 100 according to an embodiment will be described with reference to Fig. 1. Fig. 1 is a diagram showing an overview of the information processing system 100 according to an embodiment. In Fig. 1, the information processing system 100 is configured with an information processing device 10 and an operator O.

[0012] The information processing device 10 is a device that receives input from an operator O and executes various information processes, and is a RAN (Radio Access Network) Intelligent Controller (RIC), a server, etc. The RIC is an information processing device that estimates various types of information based on the RAN and predetermined computational resources such as AI (Artificial Intelligence).

[0013] First, the information processing device 10 trains the generation model M (step S1). For example, the information processing device 10 trains the generation model M by inputting training data based on operation information of the communication system to the generation model M. Here, the generation model M is a machine learning model that outputs source code of software that controls the communication system in response to input operation information. The operation information is information related to the operation of the communication system collected from base stations of the communication system, such as KPIs (Key Performance Indicators) that are evaluation indicators of the communication system (e.g., abnormal disconnection rate, handover success rate), alarm information related to abnormal alarms, etc. of the communication system (e.g., hardware alarms, software alarms, KPI alarms), traffic information related to the communication data volume of the communication system (e.g., communication data volume of each wireless terminal), etc.

[0014] Second, the operator O instructs the information processing device 10 to place a service order (step S2). For example, the operator O inputs reference values ​​such as KPIs and criteria of the communication system requested by the operator O as the service order.

[0015] Third, the information processing device 10 generates source code using the generation model M (step S3). For example, the information processing device 10 inputs a service order obtained from an operator O into the generation model M and obtains the source code of the RAN software output by the generation model M. At this time, the information processing device 10 generates source code of the RAN software for realizing each process such as downlink and uplink in the communication system, for example.

[0016] Fourth, the information processing device 10 generates software using a compiler (step S4). For example, the information processing device 10 compiles the source code of the RAN software output by the generative model M to generate the RAN software.

[0017] Fifth, the information processing device 10 evaluates the software using the digital twin (step S5). For example, the information processing device 10 executes the generated RAN software in a communication system in the virtual space of the digital twin, acquires operational information of the communication system in the virtual space, and compares it with the service order to evaluate the software.

[0018] Sixth, the information processing device 10 feeds back the evaluation results (step S6). For example, if the evaluation results satisfy the service order, the information processing device 10 releases the generated RAN software. On the other hand, if the evaluation results do not satisfy the service order, the information processing device 10 retrains the generative model M using training data based on operational information of the communication system in the virtual space. At this time, the information processing device 10 repeatedly executes the processes of steps S3 to S5 described above until it can generate RAN software whose evaluation results satisfy the service order.

[0019] By executing the processes of steps S1 to S6 described above, the information processing system 100 can shorten the lead time from RAN software development to operation and complete the process from development to operation in a short period of time. Furthermore, the information processing system 100 can reduce obstacles such as human error that occur in the process from RAN software development to operation. In other words, by utilizing the generative model M, the information processing system 100 can automate the realization of "DevOps," which closely links RAN software development and operation.

[0020] 2. Configuration and processing of information processing device 10 The configuration and processing of the information processing device 10 will be described using Fig. 2. Fig. 2 is a block diagram showing an example configuration of the information processing device 10 of the information processing system 100 according to the embodiment. The information processing device 10 is configured from an input unit 11, an output unit 12, a communication unit 13, a storage unit 14, and a control unit 15.

[0021] (Input Unit 11) The input unit 11 controls input of various information to the information processing device 10. For example, the input unit 11 is realized by a mouse, a keyboard, etc., and accepts input of various information to the information processing device 10.

[0022] (Output Unit 12) The output unit 12 controls the output of various information from the information processing device 10. For example, the output unit 12 is realized by a display or the like, and displays various information stored in the information processing device 10.

[0023] (Communication Unit 13) The communication unit 13 controls data communication with other devices. For example, the communication unit 13 performs data communication with each communication device via a router or the like. The communication unit 13 can also perform data communication with a terminal (not shown).

[0024] (Storage Unit 14) The storage unit 14 is realized by, for example, a semiconductor memory element such as a random access memory (RAM) or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 14 has a training data storage unit 14a, a code information storage unit 14b, a software storage unit 14c, and a generative model storage unit 14d. The storage unit 14 stores various information referenced when the control unit 15 operates and various information acquired when the control unit 15 operates.

[0025] (Training Data Storage Unit 14a) The training data storage unit 14a stores training data. Here, an example of information stored in the training data storage unit 14a will be described with reference to FIG. 3. FIG. 3 is a diagram showing an example of the training data storage unit 14a of the information processing device 10 according to the embodiment. In the example of FIG. 3, the training data storage unit 14a has an item such as "Training Data."

[0026] The "training data" is training data used by the training unit 15e (described later), and is, for example, operational information relating to the operation of the communication system collected from base stations of the communication system, and a data set of source code for RAN software that controls the communication system. The operational information is, for example, KPIs that are evaluation indicators of the communication system, alarm information relating to abnormal alarms of the communication system, traffic information relating to the amount of communication data in the communication system, and the like.

[0027] FIG. 3 shows an example in which training data including "training data #1," "training data #2," "training data #3," . . . are stored in the training data storage unit 14a.

[0028] (Code information storage unit 14b) The code information storage unit 14b stores code information including source code and the like. An example of information stored in the code information storage unit 14b will now be described with reference to FIG. 4. FIG. 4 is a diagram illustrating an example of the code information storage unit 14b of the information processing device 10 according to the embodiment. In the example of FIG. 4, the code information storage unit 14b has an item such as "code information."

[0029] The "code information" is source code generated by the code unit 15b (described later), such as the source code of the RAN software. The "code information" is also information referenced by the compile unit 15c (described later), such as a program including an algorithm used to compile the source code of the RAN software, or a programming language such as C or Python.

[0030] FIG. 4 shows an example in which code information such as "code information #1," "code information #2," "code information #3," . . . is stored in the code information storage unit 14b.

[0031] (Software storage unit 14c) The software storage unit 14c stores software generated by the compilation unit 15c, which will be described later. An example of information stored in the software storage unit 14c will now be described with reference to FIG. 5. FIG. 5 is a diagram showing an example of the software storage unit 14c of the information processing device 10 according to the embodiment. In the example of FIG. 5, the software storage unit 14c has an item such as "Software."

[0032] The "software" is software generated by the compilation unit 15c (described later), for example, RAN software.

[0033] FIG. 5 shows an example in which software items "Software #1," "Software #2," "Software #3," . . . are stored in the software storage unit 14c.

[0034] (Generative model storage unit 14d) The generative model storage unit 14d stores the generative model M. Here, an example of information stored in the generative model storage unit 14d will be described with reference to FIG. 6. FIG. 6 is a diagram illustrating an example of the generative model storage unit 14d of the information processing device 10 according to the embodiment. In the example of FIG. 6, the generative model storage unit 14d has an item such as "generative model."

[0035] A "generative model" is model data of a machine learning model that is trained by the training unit 15e described later and used by the code unit 15b described later, and is data that includes, for example, execution data for executing the algorithm of the generative model M, model parameters which are setting values, hyperparameters, etc.

[0036] FIG. 6 shows an example in which a plurality of trained generative models M, such as "generative model #1," "generative model #2," . . . , are stored in the generative model storage unit 14d.

[0037] (Control Unit 15) The control unit 15 is realized by, for example, a CPU (Central Processing Unit) or an MPU (Micro Processing Unit) executing various programs (corresponding to an example of an information processing program) stored in a storage device inside the information processing device 10 using RAM as a work area. The control unit 15 is also realized by, for example, an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

[0038] As shown in Fig. 2, the control unit 15 has an acquisition unit 15a, a code unit 15b, a compilation unit 15c, an evaluation unit 15d, and a training unit 15e, and realizes or executes the functions and actions of the information processing described below. Note that the internal configuration of the control unit 15 is not limited to the configuration shown in Fig. 2, and may be other configurations as long as they perform the information processing described below. Furthermore, the connection relationships between the processing units of the control unit 15 are not limited to the connection relationships shown in Fig. 2, and may be other connection relationships.

[0039] (Acquisition unit 15a) The acquisition unit 15a acquires reference values ​​related to the operation of a system requested by a user. Here, the system is, for example, a communication system. For example, the acquisition unit 15a acquires, as a service order, reference values ​​related to the operation of the communication system requested by an operator O who is an administrator of the communication system. The acquisition unit 15a also acquires, as a service order, KPIs and criteria as reference values ​​related to the operation of the communication system requested by the operator O of the communication system. The acquisition unit 15a can also store the acquired service order in the memory unit 14.

[0040] (Code Unit 15b) The code unit 15b generates software source code from the acquired reference values ​​using a trained generation model M that outputs source code for software that controls a communication system in response to input operation information related to the system's operation. Here, the software is, for example, RAN software. For example, the code unit 15b generates source code for the RAN software from the acquired reference values ​​using a trained generation model M that outputs source code for RAN software that controls a communication system in response to input operation information related to the communication system's operation. The operation information includes at least one of KPIs, alarm information, and traffic information collected from base stations of the communication system. The KPIs are, for example, indicators such as an abnormal disconnection rate and a handover success rate in the communication system. The alarm information is, for example, information related to abnormal values ​​of hardware or software in the communication system or abnormal values ​​of KPIs. The traffic information is, for example, the amount of communication data per terminal user of a wireless terminal in the communication system. The code unit 15b stores the generated software source code in the code information storage unit 14b.

[0041] (Compiler 15c) The compiler 15c compiles the source code of the generated software to generate the software. For example, the compiler 15c compiles the source code of the generated RAN software using an automatic compiler to generate the RAN software. The compiler 15c also generates, as the RAN software, software that executes, for example, processes related to the downlink in the communication system and processes related to the uplink in the communication system. The compiler 15c stores the generated software in the software storage unit 14c.

[0042] (Evaluation unit 15d) Evaluation unit 15d evaluates whether the control status for a system using the generated software satisfies a reference value, and if the control status satisfies the reference value, provides the generated software to a user. For example, evaluation unit 15d evaluates whether the communication control status for a communication system using the generated RAN software satisfies a reference value required by operator O, and if the control status satisfies the reference value, provides the generated RAN software to operator O.

[0043] Furthermore, the evaluation unit 15d executes the generated software in a system constructed in the virtual space of the digital twin and evaluates whether the control status satisfies a reference value. For example, the evaluation unit 15d executes the generated RAN software in a communication system constructed in the virtual space of the digital twin and evaluates whether the communication control status satisfies a reference value. The evaluation unit 15d refers to the software stored in the software storage unit 14c.

[0044] (Training Unit 15e) The training unit 15e trains the generative model M. For example, the training unit 15e trains the generative model M using training data. At this time, the training unit 15e trains the generative model M using, as training data, operational information of the communication system collected from base stations of the communication system and a data set of source code of RAN software that controls the communication system. Note that the training unit 15e refers to the training data stored in the training data storage unit 14a.

[0045] Furthermore, if the control status does not satisfy a reference value, the training unit 15e retrains the generative model M. For example, if the communication control status of RAN software executed in a communication system constructed in the virtual space of the digital twin does not satisfy a reference value, the training unit 15e retrains the generative model M using training data. At this time, the training unit 15e can also create training data based on operation information collected from the communication system constructed in the virtual space of the digital twin, and retrain the generative model M using the created training data.

[0046] 7 to 9, specific examples of the information processing system 100 according to the embodiment will be described. In the following, specific examples 1 to 3 of the information processing system 100 according to the embodiment will be described.

[0047] (Specific Example 1) Specific example 1 of the information processing system 100 according to the embodiment will be described with reference to Fig. 7. Fig. 7 is a diagram showing specific example 1 of the information processing system 100 according to the embodiment. Below, as specific example 1, an example of processing of the entire information processing system 100 will be described.

[0048] As shown in Figure 7 (1), an operator O trains by inputting the analysis results of operational information such as "KPI / ALM (alarm information)" and "traffic information" as training data into the "GenAI engine" of the information processing device 10, i.e., the generative model M.

[0049] As shown in Figure 7 (2), operator O develops "firmware / setting information" as software by inputting "SO (service order)", which is the standard value requested by operator O, into the "GenAI engine" of information processing device 10, i.e., the trained generative model M.

[0050] As shown in FIG. 7(3), the information processing device 10 generates source code from "SO", which is the reference value requested by the operator O, via the "GenAI engine", i.e., the trained generative model M.

[0051] As shown in FIG. 7(4), the information processing device 10 generates software from a "source code pool" including the generated source code and an "algorithm library" via an "automatic compiler."

[0052] As shown in FIG. 7 (5), the information processing device 10 evaluates the generated software through an "automated evaluation system" using a digital twin, and then releases the software.

[0053] As described above, the information processing system 100 according to the embodiment can automate the realization of "DevOps," which closely links the development and operation of RAN software, by utilizing generative AI.

[0054] (Specific Example 2) Specific Example 2 of the information processing system 100 according to the embodiment will be described with reference to Fig. 8. Fig. 8 is a diagram showing Specific Example 2 of the information processing system 100 according to the embodiment. Below, as Specific Example 2, processing example 1 of the information processing device 10 of the information processing system 100 will be described.

[0055] As shown in FIG. 8(1), the information processing device 10 acquires a "service order" including KPIs and criteria from an operator O. The information processing device 10 also inputs the acquired "service order" into a "GenAI engine," i.e., a trained generative model M.

[0056] As shown in Figure 8 (2), when generating source code and software, the information processing device 10 shares data with ``RAN software code'' including the source code of the RAN software, ``algorithm library'' including programs that execute algorithms, and ``language DB (database)'' including programming languages ​​such as C language and Python.

[0057] As shown in Fig. 8 (3), the information processing device 10 generates source code from the "service order" acquired from the operator O via the "GenAI engine." The information processing device 10 also inputs the generated source code into the "automatic compiler."

[0058] 8(4), the information processing device 10 generates software from the generated source code via an "automatic compiler." The information processing device 10 also inputs the generated software into an "automatic evaluation system."

[0059] As shown in Figure 8 (5), the information processing device 10 evaluates the generated software through an "automated evaluation system" using a digital twin, and if the evaluation results meet the standard values, releases the software.

[0060] As shown in Figure 8 (6), the information processing device 10 evaluates the generated software through an ``automatic evaluation system'' using a digital twin, and if the evaluation result does not meet the standard value, it feeds back the evaluation result.

[0061] As described above, the information processing system 100 according to the embodiment can automate the realization of "DevOps," which closely links the development and operation of RAN software, by combining code generation with an automatic compiler and an automatic evaluation system, rather than simply generating code using generative AI.

[0062] Specific Example 3 Specific Example 3 of the information processing system 100 according to the embodiment will be described with reference to Fig. 9. Fig. 9 is a diagram showing Specific Example 3 of the information processing system 100 according to the embodiment. Below, as Specific Example 3, processing example 2 of the information processing device 10 of the information processing system 100 will be described.

[0063] As shown in FIG. 9(1), the information processing device 10 acquires a "service order" including KPIs and criteria from an operator O. The information processing device 10 also inputs the acquired "service order" into a "GenAI engine," i.e., a trained generative model M.

[0064] As shown in Figure 9 (2), when generating source code and software, the information processing device 10 shares data with "RAN software code" including the source code of the RAN software, an "algorithm library" including programs that execute algorithms, and a "language DB (database)" including programming languages ​​such as C language and Python.

[0065] As shown in Fig. 9 (3), the information processing device 10 generates source code from the "service order" acquired from the operator O via the "GenAI engine." The information processing device 10 also inputs the generated source code into the "automatic compiler."

[0066] 9(4), the information processing device 10 generates software from the generated source code via an "automatic compiler." The information processing device 10 also inputs the generated software into an "automatic evaluation system."

[0067] As shown in Figure 9 (5), the information processing device 10 evaluates the generated software through an "automated evaluation system" using a digital twin, and if the evaluation results meet the standard values, releases the software.

[0068] As shown in Figure 9 (6), the information processing device 10 evaluates the generated software through an "automatic evaluation system" using a digital twin, and if the evaluation result does not meet the standard value, it feeds back the evaluation result.

[0069] As shown in FIG. 9(7), when the information processing device 10 evaluates the generated software, it compares the evaluation result with the SO criteria, which are reference values.

[0070] As shown in FIG. 9(8), the information processing device 10 outputs a release notification if the evaluation result satisfies the SO criteria.

[0071] As shown in FIG. 9(9), if the evaluation result does not satisfy the SO criteria, the information processing device 10 changes the source code, changes the parameters of the generative model M, and so on.

[0072] As described above, the information processing system 100 according to the embodiment can automate the realization of "DevOps," which closely links the development and operation of RAN software, by looping and releasing processing until software that satisfies the service order is generated.

[0073] 4. Processing Flow of Information Processing System 100 The processing flow of the information processing system 100 according to the embodiment will be described with reference to FIG. 10. FIG. 10 is a flowchart showing an example of the processing flow of the information processing system 100 according to the embodiment. Note that the processing of steps S101 to S106 below may be executed in a different order. Furthermore, some of the processing of steps S101 to S106 below may be omitted.

[0074] (Generation Model Training Process) First, the information processing device 10 executes a generation model training process (step S101). For example, the information processing device 10 trains the generation model M by inputting training data based on operation information (e.g., KPIs, alarm information, traffic information) collected from base stations of the communication system to the generation model M.

[0075] (Service Order Instruction Process) Second, the operator O executes the service order instruction process (step S102). For example, the operator O inputs reference values ​​such as KPIs and criteria of the communication system requested by the operator O as a service order.

[0076] (Source Code Generation Process) Third, the information processing device 10 executes a source code generation process (step S103). For example, the information processing device 10 inputs a service order acquired from an operator O into a generation model M, and acquires the source code of the RAN software output by the generation model M.

[0077] (Software Generation Process) Fourth, the information processing device 10 executes software generation process (step S104). For example, the information processing device 10 compiles the source code of the RAN software output by the generative model M using an automatic compiler to generate the RAN software.

[0078] (Software Evaluation Process) Fifth, the information processing device 10 executes software evaluation process (step S105). For example, the generated RAN software is executed in a communication system in the virtual space of the digital twin, operation information of the communication system in the virtual space is acquired, and the software is evaluated by comparing it with the service order.

[0079] (Evaluation Result Feedback Processing) Sixth, the information processing device 10 executes evaluation result feedback processing (step S106). For example, if the evaluation result satisfies the service order, the information processing device 10 releases the generated RAN software and terminates the processing. On the other hand, if the evaluation result does not satisfy the service order, the information processing device 10 retrains the generation model M using training data based on operation information of the communication system in the virtual space, and repeatedly executes the processing of the above steps S103 to S105 until RAN software whose evaluation result satisfies the service order can be generated.

[0080] 5. Effects of the embodiment The effects of the embodiment will be described below. Effects 1 to 5 corresponding to each process according to the embodiment will be described below.

[0081] (Effect 1) First, in the processing according to the above-described embodiment, the information processing device 10 acquires a reference value related to the operation of the system requested by the operator O, and uses a trained generation model M that outputs source code for software that controls the system in response to input operation information related to the system operation to generate source code from the acquired reference value, compiles the generated source code, generates software, evaluates whether the control status of the system using the generated software satisfies the reference value, and if the control status satisfies the reference value, provides the generated software to the operator O. Therefore, in this processing, by utilizing the generation model M, it is possible to shorten the process from software development to operation.

[0082] (Effect 2) Secondly, in the process according to the embodiment described above, if the control situation does not satisfy the reference value, the information processing device 10 retrains the generative model M. Therefore, in this process, by utilizing the generative model M that has received feedback from the evaluation results, it is possible to shorten the process from software development to operation.

[0083] (Effect 3) Third, in the processing according to the embodiment described above, the information processing device 10 executes the generated software in a system constructed in the virtual space of the digital twin and evaluates whether the control status satisfies a reference value. Therefore, in this processing, there is no need to evaluate the generated software in a real environment, and the process from software development to operation can be shortened.

[0084] (Effect 4) Fourth, in the process according to the above-described embodiment, the system is a communication system, and the operational information includes at least one of KPIs, alarm information, and traffic information collected from base stations of the communication system. Therefore, in this process, by utilizing the generative model M, it is possible to shorten the process from software development to operation in the communication system.

[0085] (Effect 5) Fifth, in the process according to the above-described embodiment, the software is RAN software. Therefore, in this process, by utilizing the generative model M, it is possible to shorten the process from development to operation of RAN software in a communication system.

[0086] 6. Hardware Configuration The information processing device 10 according to the embodiment described above is realized, for example, by a computer 1000 configured as shown in FIG. 11. The following description will be given using the information processing device 10 as an example. FIG. 11 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device 10 according to the embodiment. The computer 1000 has a CPU 1100, a RAM 1200, a ROM 1300, a HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

[0087] The CPU 1100 operates and controls each unit based on programs stored in the ROM 1300 or the HDD 1400. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 starts up, programs that depend on the hardware of the computer 1000, and the like.

[0088] The HDD 1400 stores programs executed by the CPU 1100, data used by such programs, etc. The communication interface 1500 receives data from other devices via a predetermined communication network and sends it to the CPU 1100, and transmits data generated by the CPU 1100 to other devices via the predetermined communication network.

[0089] The CPU 1100 controls output devices such as a display and a printer, and input devices such as a keyboard and a mouse, via the input / output interface 1600. The CPU 1100 acquires data from the input devices via the input / output interface 1600. The CPU 1100 also outputs generated data to the output devices via the input / output interface 1600.

[0090] Media interface 1700 reads a program or data stored in recording medium 1800 and provides it to CPU 1100 via RAM 1200. CPU 1100 loads the program or data from recording medium 1800 onto RAM 1200 via media interface 1700 and executes the loaded program. Recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or a PD (Phase Change Rewritable Disc), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

[0091] For example, when the computer 1000 functions as the information processing device 10 according to the embodiment, the CPU 1100 of the computer 1000 executes programs loaded onto the RAM 1200 to realize the functions of the control unit 15. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, the CPU 1100 may obtain these programs from another device via a predetermined communication network.

[0092] [7. Other] Of the processes described in each of the above embodiments, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically using known methods. In addition, the information including the processing procedures, specific names, various data, and parameters shown in the above documents and drawings can be changed as desired unless otherwise specified. For example, the various information shown in each drawing is not limited to the information shown in the drawings.

[0093] Furthermore, the components of each device shown in the figure are conceptual functional components and do not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of them can be functionally or physically distributed and integrated in any unit depending on various loads, usage conditions, etc.

[0094] Furthermore, the above-described embodiments can be combined as appropriate within the scope of not causing any contradiction in the processing content.

[0095] Although some of the embodiments of the present application have been described in detail above with reference to the drawings, these are merely examples, and the present invention can be implemented in other forms that include the embodiments described in the Disclosure of the Invention section and that have undergone various modifications and improvements based on the knowledge of those skilled in the art.

[0096] Furthermore, the above-mentioned "section, module, unit" can be read as "means" or "circuit," etc. For example, a receiving section can be read as receiving means or receiving circuit.

[0097] REFERENCE SIGNS LIST 10 Information processing device 11 Input unit 12 Output unit 13 Communication unit 14 Storage unit 14a Training data storage unit 14b Code information storage unit 14c Software storage unit 14d Generative model storage unit 15 Control unit 15a Acquisition unit 15b Code unit 15c Compilation unit 15d Evaluation unit 15e Training unit 100 Information processing system

Claims

1. An information processing device comprising: an acquisition unit that acquires reference values ​​related to the operation of a system requested by a user; a code unit that generates source code from the acquired reference values ​​using a trained generative model that outputs source code for software that controls the system in response to input operational information related to the operation of the system; a compilation unit that compiles the generated source code to generate the software; and an evaluation unit that evaluates whether the control status of the system using the generated software satisfies the reference values, and if the control status satisfies the reference values, provides the generated software to the user.

2. The information processing device according to claim 1, further comprising: a training unit that retrains the generative model when the control situation does not satisfy the reference value.

3. The information processing device according to claim 1, wherein the evaluation unit executes the generated software in the system constructed in the virtual space of the digital twin and evaluates whether the control status satisfies the reference value.

4. An information processing device according to any one of claims 1 to 3, wherein the system is a communication system, and the operational information includes at least one of KPI (Key Performance Indicator), alarm information, and traffic information collected from base stations of the communication system.

5. The information processing device according to any one of claims 1 to 3, wherein the software is RAN (Radio Access Network) software.

6. An information processing method executed by an information processing device, comprising: an acquisition step of acquiring reference values ​​related to the operation of a system requested by a user; a coding step of generating source code from the reference values ​​using a trained generative model that outputs source code for software that controls the system in response to input operational information related to the operation of the system; a compilation step of compiling the generated source code to generate the software; and an evaluation step of evaluating whether the control status of the system using the generated software satisfies the reference values, and if the control status satisfies the reference values, providing the generated software to the user.

7. An information processing program that causes a computer to execute the following steps: an acquisition procedure that acquires reference values ​​related to the operation of a system requested by a user; a coding procedure that generates source code from the reference values ​​using a trained generative model that outputs source code for software that controls the system in response to input operational information related to the operation of the system; a compilation procedure that compiles the generated source code to generate the software; and an evaluation procedure that evaluates whether the control status of the system using the generated software satisfies the reference values, and if the control status satisfies the reference values, provides the generated software to the user.

Images