Data processing device, program, and data processing method

Abstract

To provide a program causing a computer to function as a data processing device.SOLUTION: A data processing device comprises: a storage unit which outputs configuration definition information generated by updating a natural language processing model using data related to configuration definition information related to configuration definition information for defining a network configuration when a natural language indicative of network requirements is input, and stores a configuration definition information model, which outputs network information indicative of information of the network achieved by the configuration definition information when the configuration definition information is input; an intent acquisition unit which acquires a user intent including the natural language input by a user and indicative of the network requirements; a configuration definition information acquisition unit which acquires configuration definition information output by the configuration definition information model by inputting the user intent into the configuration definition information model; and an output control unit which outputs the configuration definition information acquired by the configuration definition information acquisition unit.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a data processing device, a program, and a data processing method. [Background technology]

[0002] Patent Document 1 describes NFV (Network Functions Virtualization) and NSD (Network Service Descriptor). [Prior art document] [Patent documents] [Patent Document 1] JP 2018-147429 A Summary of the Invention [Means for solving the problem]

[0003] According to an embodiment of the present invention, a data processing device is provided. The data processing device may include a storage unit that stores a configuration definition information model, which is a learning model that outputs configuration definition information when a natural language indicating a network requirement is input, and is generated by updating a natural language processing model using configuration definition information-related data related to configuration definition information that defines a network configuration, and outputs network information in natural language indicating information on a network realized by the configuration definition information when the configuration definition information is input. The data processing device may include an intent acquisition unit that acquires a user intent input by a user, the user intent including a natural language indicating a network requirement. The data processing device may include a configuration definition information acquisition unit that inputs the user intent into the configuration definition information model and acquires the configuration definition information output from the configuration definition information model. The data processing device may include an output control unit that controls the configuration definition information acquired by the configuration definition information acquisition unit to output the configuration definition information acquired.

[0004] The data processing device may include a configuration definition information model generation unit that generates the configuration definition information model by updating the natural language processing model using the configuration definition information related data, and the storage unit may store the configuration definition information model generated by the configuration definition information model generation unit. The configuration definition information related data may include at least one of set data including configuration definition information and a description of the configuration definition information in natural language, and document data related to the configuration definition information. The configuration definition information is an NSD (Network Service Descriptor), and the configuration definition information related data may include at least one of set data including an NSD and a description of the NSD in natural language, document data related to the NSD by ETSI (European Telecommunications Standards Institute), and document data related to the NSD by TOSCA (Topology and Orchestration Specification for Cloud Applications).

[0005] Any of the data processing devices may include a network information acquisition unit that inputs the configuration definition information acquired by the configuration definition information acquisition unit into the configuration definition information model and acquires network information output from the configuration definition information model, and a display control unit that controls to display the network information acquired by the network information acquisition unit. The intent acquisition unit may acquire the user intent modified based on the network information displayed under control of the display control unit, and the configuration definition information acquisition unit may input the modified user intent into the configuration definition information model and acquire the configuration definition information output from the configuration definition information model.

[0006] In any of the data processing devices, the storage unit may store a MANO model that uses configuration definition information and MANO output data as input and outputs modified configuration definition information, the MANO model being generated by machine learning using as learning data the configuration definition information, the MANO output data output from the MANO when the configuration definition information is input to the MANO, and modified configuration definition information, which is the configuration definition information modified after the MANO output data is output. The data processing device may include a modified configuration definition information acquisition unit that, when the output control unit inputs the configuration definition information to the MANO and the MANO output data is output from the MANO, inputs the configuration definition information and the MANO output data to the MANO model and acquires the modified configuration definition information output from the MANO model. The data processing device may include a MANO model generation unit that generates the MANO model by machine learning using as learning data the configuration definition information, the MANO output data output from the MANO when the configuration definition information is input to the MANO, and modified configuration definition information, which is the configuration definition information modified after the MANO output data is output. The MANO output data may include at least one of a response, an error message, and a log output by the MANO.

[0007] In any of the data processing devices, the configuration definition information acquisition unit may input the user intent into the configuration definition information model, and when missing data information regarding missing data is output from the configuration definition information model, inquire of the user about the missing data based on the missing data information.

[0008] According to one embodiment of the present invention, there is provided a program for causing a computer to function as the data processing device.

[0009] According to one embodiment of the present invention, there is provided a data processing method executed by a computer. The data processing method may include an intent acquisition step of acquiring a user intent input by a user, the user intent including a natural language indicating a network requirement. The data processing method may include a configuration definition information acquisition step of inputting the user intent into a configuration definition information model generated by updating a natural language processing model using configuration definition information related data related to configuration definition information that defines a network configuration, the configuration definition information model being configured to output configuration definition information when a natural language indicating a network requirement is input, and output network information indicating in natural language information of a network realized by the configuration definition information when configuration definition information is input, and acquiring configuration definition information output from the configuration definition information model. The data processing method may include an output control step of controlling to output the configuration definition information acquired in the configuration definition information acquisition step.

[0010] The above summary of the invention does not list all of the necessary features of the present invention. Also, subcombinations of these features may also be inventions. [Brief description of the drawings]

[0011] [Figure 1] An example of a data processing device 100 is shown diagrammatically. [Diagram 2] FIG. 2 is an explanatory diagram for explaining an NSD model 102. [Diagram 3] 1 is an explanatory diagram for explaining input / output to / from the NSD model 102. FIG. [Figure 4] 1 is an explanatory diagram for explaining input / output to / from the NSD model 102. FIG. [Diagram 5] 1 is an explanatory diagram for explaining input / output to / from the NSD model 102. FIG. [Figure 6] 1 illustrates an example of a processing flow by the data processing device 100. [Figure 7]FIG. 2 is an explanatory diagram illustrating a function of the data processing device 100 to modify an NSD. [Figure 8] 1 illustrates an example of a functional configuration of a data processing device 100. [Figure 9] An example of a hardware configuration of a computer 1200 functioning as the data processing device 100 is shown in schematic form. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0012] The present invention will be described below through embodiments of the invention, but the following embodiments do not limit the scope of the invention according to the claims. Furthermore, not all of the combinations of features described in the embodiments are necessarily essential to the solution of the invention.

[0013] The popularity of SDN (Software-Defined Networking) and NFV has made it possible to virtualize mobile core network resources and represent them using abstracted data models. These abstracted virtualized network data models have clear schemas defined by relevant standardization organizations (ETSI NFV ISG). As a result, by constructing a network according to a reference architecture and inputting the appropriate data model into the orchestrator (MANO), it is now possible to automatically construct any network.

[0014] However, to create a data model for building a network in this way, specialized knowledge on mobile core / network / standard data models is required, and customer users are not only required to define requirements, but also to incur the technical and human costs required for model creation. Even in cases where a vendor or operator creates the model, it requires high costs in terms of technology, time, and human resources, as it is necessary to consider a model tailored to the requirements of each customer. Therefore, the number of users who can obtain sufficient benefits from using such a system is limited. With this method, it is difficult to easily provide a network that meets the needs of a wide range of users for the vertically integrated industries envisioned in the 5G era.

[0015] On the other hand, in the data processing device 100 according to the present embodiment, for example, the method of expressing the user's intent is changed from an approach based on a strict data model to natural language processing (NLP) established by recent AI technology. In the data processing device 100, for example, an interactive natural language processing system, such as ChatGPT, is made to understand the configuration of the network, and then the user's intent is input to generate a standardized abstract network data model. Expert knowledge is required to interpret the output data model, but this output data model is input again to the interactive natural language processing system, and an explanation in natural language is output, providing feedback on whether the model satisfies the user's intent. Then, by inputting the data model that has been reviewed into an orchestrator, a required network can be constructed from the intent in natural language without expert knowledge.

[0016] Here, an example will be described. The data processing device 100 according to the present embodiment uses, for example, an interactive system based on large-scale language models (LLMs). In this system, the user 52 inputs the requirements of the network required in natural language as a user intent. The system generates and outputs an NSD for realizing the network that satisfies the requirements. The NSD may be an example of configuration definition information that defines the configuration of the network. In order to generate an NSD for realizing the network that satisfies the requirements, the LLM that has learned about general-purpose contents is made to learn standard documents for NSD and definition documents of description languages ​​as specialized knowledge for generating the NSD, and model optimization is performed. In addition, in order to generate an NSD from requirements in natural language, model optimization is performed using a set of requirements / explanations and NSDs in natural language as training data. Using these learning data, the system learns the rules and relationships of the network described in natural language and the configuration / description method of the NSD that realizes it, and outputs an NSD with a configuration according to the requirements in response to the input user intent in a format that conforms to the definition. Conversely, by inputting an NSD, an explanation of the contents of the NSD (the described network model) in natural language can also be output. In order to use the configuration patterns of the NSD description format and the natural language that explains it for learning, the system generates and outputs the configuration of the network model described in the input NSD and the corresponding natural language description. In this way, it is possible to output an NSD from a natural language user intent, but it cannot be guaranteed that the output NSD will completely satisfy the user intent. Therefore, a user review process is performed in which the output NSD is input again into the system and a natural language description of the NSD is output. The user reviews whether the NSD meets their requirements from the description. If not, the system inputs an additional natural language user intent again and outputs the NSD again. This user review feedback is continued until the requirements are met.

[0017] 1 shows an example of a data processing device 100. The data processing device 100 stores a model for configuration definition information in advance. The model for configuration definition information outputs configuration definition information when a natural language indicating network requirements is input. When configuration definition information is input, the model for configuration definition information outputs network information indicating, in natural language, information on a network realized by the configuration definition information.

[0018] The model for configuration definition information may be generated by updating a natural language processing model trained using general learning data, using configuration definition information-related data related to the configuration definition information. The general learning data may include a large amount of text data that is generally publicly available. The data processing device 100 may store the model for configuration definition information that it has generated. The data processing device 100 may also acquire and store a model for configuration definition information generated by another device.

[0019] The data processing device 100 acquires a user intent including a natural language indicating a network requirement input by a user 52. The user 52 may be a user who uses a service provided by the data processing device 100. The data processing device 100 receives the user intent, for example, from a communication terminal 50 used by the user 52 via the network 10. The data processing device 100 may accept a direct input of the user intent by the user 52 to the data processing device 100.

[0020] The communication terminal 50 may be any terminal that can communicate with the data processing device 100 via the network 10. For example, the communication terminal 50 may be a PC (Personal Computer), a smartphone, a tablet terminal, or the like.

[0021] The network 10 may include the Internet. The network 10 may include the cloud. The network 10 may include a mobile communication network. The network 10 may include a LAN (Local Area Network).

[0022] The data processing device 100 inputs a user intent into a configuration definition information model and acquires configuration definition information output from the configuration definition information model. The data processing device 100 inputs the acquired configuration definition information into the configuration definition information model and acquires network information output from the configuration definition information model. The data processing device 100 displays the acquired network information to the user 52. For example, the data processing device 100 displays the network information on a display provided in the data processing device 100. For example, the data processing device 100 transmits the network information to the communication terminal 50 via the network 10.

[0023] The user 52 browses the network information. Since the network information indicates information on the network realized by the target configuration definition information in natural language, even the user 52 who cannot directly understand the configuration definition information can confirm whether the configuration definition information satisfies his / her requirements. If the user 52 browses the network information and confirms that the configuration definition information satisfies his / her requirements, the configuration definition information may be input to MANO. If the user 52 confirms that the configuration definition information does not satisfy his / her requirements, the user 52 generates a modified user intent by modifying the input user intent. The modified user intent may be generated by modifying the input user intent, or may be newly generated as a modified version of the input user intent. The data processing device 100 acquires the modified user intent, inputs it into the configuration definition information model, acquires the configuration definition information output from the configuration definition information model, inputs the acquired configuration definition information into the configuration definition information model, and acquires the network information output from the configuration definition information model. The data processing device 100 displays the acquired network information to the user 52. By repeating such processing, it is finally possible to generate configuration definition information that satisfies the requirements of the user 52.

[0024] As described above, an example of the configuration definition information is NSD, but is not limited thereto. For example, another example of the configuration definition information is a template by a cloud service provider. Specific examples include a CloudFormation template of AWS (Amazon Web Services) and an ARM template of Azure. When building a system on the cloud, configuration information is generally written in these templates and deployed. They are known as an example of IaaS (Infrastructure as a Service). Another example of the configuration definition information is a k8s manifest file. Since mobile core applications are often implemented in containers, configuration information may be defined by a manifest file of k8s, which is a container orchestration system. In this embodiment, a case where the configuration definition information is NSD will be mainly described as an example.

[0025] 2 is an explanatory diagram for explaining the NSD model 102, which is an example of a configuration definition information model. As described above, the data processing device 100 may generate the NSD model 102 by itself.

[0026] The data processing device 100 first prepares a natural language processing model 20 that has been trained using general training data. The data processing device 100 may obtain a natural language processing model 20 generated by another device. The data processing device 100 may generate the natural language processing model 20 by itself using the general training data.

[0027] The data processing device 100 may generate the NSD model 102 by updating the natural language processing model 20 using the NSD-related data 30. The NSD-related data 30 may include training data for the correlation between the NSD and natural language. The training data for the correlation between the NSD and natural language may include a natural language description of the NSD and a set of NSDs. The NSD-related data 30 may include training data for the NSD itself. The training data for the NSD itself may include document data related to the NSD by ETSI (such as ETSI's standard document for NSD). The training data for the NSD itself may include document data related to the NSD by TOSCA (such as TOSCA's official document for NSD).

[0028] 3 is an explanatory diagram for explaining input and output to the NSD model 102. In the example shown in FIG. 3, a user 52 inputs a user intent 54 saying, "I want to create a 5G mobile core that can maintain a communication speed of XX Mbps. Create an NSD for that purpose."

[0029] The data processing device 100, which has acquired the user intent 54, inputs the user intent 54 to the NSD model 102, and acquires the NSD 180 output from the NSD model 102. The data processing device 100 causes the acquired NSD 180 to be displayed to the user 52.

[0030] If the user 52 can understand the NSD 180, he or she can view the displayed NSD 180 and, if there are no problems, input it into MANO; if there are problems, the user 52 can directly modify the NSD 180, modify the user intent 54, or generate a new user intent 54 and input it into the data processing device 100.

[0031] The NSD model 102 may be configured to respond by inquiring of the user 52 about the missing information when generating an NSD for an input user intent, if the information is missing.

[0032] Fig. 4 is an explanatory diagram for explaining input and output to the NSD model 102. In the example shown in Fig. 4, a user 52 first inputs a user intent 54 saying "I want to create a 5G mobile core. Create an NSD for that. If there is any missing information, please ask me."

[0033] The data processing device 100, which has acquired the user intent 54, inputs the user intent 54 to the model for NSD 102. In this example, the model for NSD 102 outputs a response 104 because information is insufficient. The data processing device 100 displays the response 104 to the user 52. In this example, the data processing device 100 displays the response 104 to the user 52, asking "Are there any communication speed requirements?"

[0034] The user 52 who has viewed the response 104 inputs a user intent 56 according to the content of the response 104. In this example, the user 52 inputs the user intent 56 of "I want to be able to maintain XX Mbps."

[0035] The data processing device 100, which has acquired the user intent 56, further inputs the user intent 56 to the model for NSD 102. Since there is no missing information, the model for NSD 102 outputs an NSD 180. The data processing device 100 displays the NSD 180 output from the model for NSD 102 to the user 52.

[0036] 5 is an explanatory diagram for explaining input and output to the NSD model 102. Here, a case will be described in which an NSD 180 generated by inputting a user intent 54 to the NSD model 102 is input to the NSD model 102.

[0037] The data processing device 100 inputs the NSD 180 into the model 102 for NSD, and acquires the network information 190 output from the model 102 for NSD. The data processing device 100 displays the acquired network information 190 to the user 52. This allows the user 52, who cannot understand the NSD 180, to understand what kind of network is realized by the NSD 180.

[0038] The user 52 can view the displayed network information 190 and, if there are no problems, input the NSD 180 into MANO, or, if there are problems, modify the user intent 54 or generate a new user intent 54 and input it into the data processing device 100.

[0039] 6 is a schematic diagram showing an example of a process flow by the data processing device 100. Here, an example of a process flow from acquiring a user intent input by the user 52 to generating an NSD corresponding to the user intent and providing it to MANO will be described.

[0040] In step (sometimes abbreviated to S) 102, the data processing device 100 acquires a user intent. In S104, the data processing device 100 inputs the user intent acquired in S102 to the model 102 for NSD. In S106, the data processing device 100 acquires the NSD output by the model 102 for NSD.

[0041] In S108, the data processing device 100 inputs the NSD acquired in S106 to the NSD model 102. In S110, the data processing device 100 acquires the network information output by the NSD model 102 and displays it to the user 52. The user 52 views the displayed network information, and corrects the user intent 54 if there is a problem.

[0042] If the user intent 54 has been modified (YES in S112), the process returns to S102, and the user intent 54 modified by the user 52 is obtained. If the user intent 54 has not been modified (NO in S112), the process proceeds to S114. In S114, the data processing device 100 provides the NSD corresponding to the unmodified network information to MANO. Through the above process, it is possible to generate an NSD 180 that satisfies the requirements of the user 52.

[0043] The data processing device 100 may further include a function of correcting the NSD when the NSD provided to the MANO causes an error in the MANO.

[0044] 7 is an explanatory diagram for explaining the function of the data processing device 100 to correct the NSD. The data processing device 100 pre-stores the MANO model 106. The MANO model 106 is generated by machine learning using the NSD, the MANO output data output from MANO40 when the NSD is input to MANO40, and the corrected NSD, which is the NSD corrected after the MANO output data is output, as learning data, and may be a model that uses the NSD and the MANO output data as inputs and the corrected NSD as output.

[0045] The data processing device 100 may store the MANO model 106 that it has generated. The data processing device 100 may also acquire and store the MANO model 106 that has been generated by another device.

[0046] When generating the MANO model 106 by itself, the data processing device 100 uses the learning data 32. The learning data 32 includes a set of an NSD, MANO output data output from MANO when the NSD is input to MANO, and a corrected NSD which is an NSD corrected after the MANO output data is output. The MANO output data may include a response output by MANO40. The MANO output data may include an error message output by MANO40. The MANO output data may include a log output by MANO40.

[0047] When the data processing device 100 receives MANO output data 42 from MANO 40 due to a defect in NSD 180 when NSD 180 is input to MANO 40, the data processing device 100 inputs NSD 180 and the MANO output data 42 into the MANO model 106 to obtain a corrected NSD 180 output from the MANO model 106.

[0048] The data processing device 100 inputs the corrected NSD 180 again to MANO 40, and when the data processing device 100 receives the MANO output data 42 from MANO 40 due to a defect in the corrected NSD 180, it inputs the corrected NSD 180 and the MANO output data 42 to the MANO model 106, obtains the re-corrected NSD output from the MANO model 106, and inputs it again to MANO 40. The data processing device 100 may repeat this process until the defect in the NSD 180 is eliminated and the NSD 180 is accepted by MANO 40.

[0049] 8 is a schematic diagram showing an example of a functional configuration of the data processing device 100. The data processing device 100 includes a storage unit 110, a data collection unit 112, a configuration definition information model generation unit 114, an intent acquisition unit 116, a configuration definition information acquisition unit 118, a network information acquisition unit 120, an output control unit 122, a display control unit 124, a modified configuration definition information acquisition unit 126, and a MANO model generation unit 128. Note that it is not essential that the data processing device 100 includes all of these.

[0050] The storage unit 110 stores various data. For example, the storage unit 110 stores the natural language processing model 20 in advance. For example, the storage unit 110 stores a model for configuration definition information. As an example, the storage unit 110 stores the model 102 for NSD in advance. For example, the storage unit 110 stores the model 106 for MANO in advance.

[0051] The data collection unit 112 collects various data. The data collection unit 112 stores the collected data in the storage unit 110. For example, the data collection unit 112 acquires a natural language processing model 20 from outside and stores it in the storage unit 110. For example, the data collection unit 112 acquires a configuration definition information model from outside and stores it in the storage unit 110. As an example, the data collection unit 112 acquires an NSD model 102 from outside and stores it in the storage unit 110. For example, the data collection unit 112 acquires a MANO model 106 from outside and stores it in the storage unit 110.

[0052] For example, the data collecting unit 112 acquires general learning data from the outside and stores it in the storage unit 110. For example, the data collecting unit 112 acquires configuration definition information related data from the outside and stores it in the storage unit 110. As an example, the data collecting unit 112 acquires NSD related data from the outside and stores it in the storage unit 110. For example, the data collecting unit 112 acquires peripheral data including a set of configuration definition information, MANO output data, and modified configuration definition information from the outside and stores it in the storage unit 110. As an example, the data collecting unit 112 acquires learning data including a set of NSD, MANO output data, and modified NSD from the outside and stores it in the storage unit 110.

[0053] The model generation unit 114 for configuration definition information generates a model for configuration definition information. As an example, the model generation unit 114 for configuration definition information generates the model 102 for NSD. The model generation unit 114 for configuration definition information stores the generated model for configuration definition information in the storage unit 110. As an example, the model generation unit 114 for configuration definition information stores the generated model 102 for NSD in the storage unit 110. The model generation unit 114 for configuration definition information may generate the model for configuration definition information by updating the natural language processing model 20 stored in the storage unit 110 using the configuration definition information related data stored in the storage unit 110. As an example, the model generation unit 114 for configuration definition information may generate the model for NSD by updating the natural language processing model 20 stored in the storage unit 110 using the NSD related data stored in the storage unit 110. For example, the model generation unit for configuration definition information 114 generates a model for configuration definition information by executing model optimization using configuration definition information related data for the natural language processing model 20. As an example, the model generation unit for configuration definition information 114 generates a model for NSD 102 by executing model optimization using NSD related data for the natural language processing model 20. Examples of model optimization techniques include Fine-tuning and Embeddings, but are not limited to these, and any technique may be used.

[0054] The network desired by the user 52 differs depending on the difference in vendor, carrier, purpose, performance, etc. The configuration definition information model generation unit 114 may generate the configuration definition information model by updating the natural language processing model 20 using configuration definition information related data according to these differences. The configuration definition information model generation unit 114 uses configuration definition information related data including, for example, a set of configuration definition information and a description of the configuration definition information in natural language corresponding to a specific vendor. As an example, the configuration definition information model generation unit 114 uses NSD related data including, for example, a set of NSD and a description of the NSD in natural language corresponding to a specific vendor. The configuration definition information model generation unit 114 uses configuration definition information related data including, for example, a set of configuration definition information and a description of the configuration definition information in natural language corresponding to a specific carrier. As an example, the configuration definition information model generation unit 114 uses NSD related data including, for example, a set of NSD and a description of the NSD in natural language corresponding to a specific carrier. This makes it possible to generate a configuration definition information model capable of outputting configuration definition information that more closely matches the network desired by the user 52.

[0055] The intent acquisition unit 116 acquires a user intent input by the user 52. The intent acquisition unit 116 may receive the user intent input by the user 52 to the communication terminal 50 from the communication terminal 50. The intent acquisition unit 116 may acquire a user intent directly input by the user 52 to the data processing device 100.

[0056] The configuration definition information acquisition unit 118 inputs the user intent acquired by the intent acquisition unit 116 into the model for configuration definition information stored in the storage unit 110, and acquires the configuration definition information output from the model for configuration definition information. As an example, the configuration definition information acquisition unit 118 inputs the user intent acquired by the intent acquisition unit 116 into the model for NSD 102 stored in the storage unit 110, and acquires the NSD output from the model for NSD 102. The configuration definition information acquisition unit 118 stores the acquired configuration definition information in the storage unit 110. As an example, the configuration definition information acquisition unit 118 stores the acquired NSD in the storage unit 110.

[0057] The configuration definition information acquisition unit 118 may input a user intent to the configuration definition information model, and when missing data information regarding the missing data is output from the configuration definition information model, inquire of the user 52 about the missing data based on the missing data information. As an example, the configuration definition information acquisition unit 118 may input a user intent to the NSD model 102, and when missing data information regarding the missing data is output from the NSD model 102, inquire of the user 52 about the missing data based on the missing data information. The configuration definition information acquisition unit 118 may acquire the missing data input by the user 52 as a result of the inquiry, and further input the missing data into the configuration definition information model. As an example, the configuration definition information acquisition unit 118 may acquire the missing data input by the user 52 as a result of the inquiry, and further input the missing data into the NSD model 102. When further missing data information is output from the model for configuration definition information, the configuration definition information acquisition unit 118 may inquire of the user 52, and when configuration definition information is output without outputting missing data information, the configuration definition information acquisition unit 118 may acquire the configuration definition information. As an example, when further missing data information is output from the model 102 for NSD, the configuration definition information acquisition unit 118 may inquire of the user 52, and when an NSD is output without outputting missing data information, the configuration definition information acquisition unit 118 may acquire the NSD.

[0058] The network information acquisition unit 120 inputs the configuration definition information acquired by the configuration definition information acquisition unit 118 into the model for configuration definition information stored in the storage unit 110, and acquires the network information output from the model for configuration definition information. As an example, the network information acquisition unit 120 inputs the NSD acquired by the configuration definition information acquisition unit 118 into the model for NSD 102 stored in the storage unit 110, and acquires the network information output from the model for NSD 102. The network information acquisition unit 120 stores the acquired network information in the storage unit 110.

[0059] The output control unit 122 controls to output data stored in the storage unit 110. The output control unit 122 may control to output the configuration definition information acquired by the configuration definition information acquisition unit 118. As an example, the output control unit 122 may control to output the NSD acquired by the configuration definition information acquisition unit 118. For example, the output control unit 122 controls to output the configuration definition information acquired by the configuration definition information acquisition unit 118 toward MANO. As an example, the output control unit 122 controls to output the NSD acquired by the configuration definition information acquisition unit 118 toward MANO.

[0060] The display control unit 124 controls the display of the data stored in the storage unit 110. For example, the display control unit 124 causes the data stored in the storage unit 110 to be displayed on a display included in the data processing device 100. For example, the display control unit 124 transmits the data stored in the storage unit 110 to the communication terminal 50 via the network 10 and causes the communication terminal 50 to display the data.

[0061] The display control unit 124 may perform control so as to display the configuration definition information acquired by the configuration definition information acquisition unit 118. As an example, the display control unit 124 may perform control so as to display the NSD acquired by the configuration definition information acquisition unit 118. The display control unit 124 may perform control so as to display the network information acquired by the network information acquisition unit 120.

[0062] The intent acquisition unit 116 may acquire a user intent modified by the user 52 or the like based on the network information displayed under the control of the display control unit 124. The configuration definition information acquisition unit 118 may input the modified user intent acquired by the intent acquisition unit 116 to a model for configuration definition information, and acquire the configuration definition information output from the model for configuration definition information. As an example, the configuration definition information acquisition unit 118 may input the modified user intent acquired by the intent acquisition unit 116 to the model for NSD 102, and acquire the NSD output from the model for NSD 102.

[0063] The intent acquisition unit 116 may acquire a user intent generated by the user 52 after the network information is displayed under the control of the display control unit 124. The configuration definition information acquisition unit 118 may input the user intent acquired by the intent acquisition unit 116 to a model for configuration definition information, and acquire the configuration definition information output from the model for configuration definition information. As an example, the configuration definition information acquisition unit 118 may input the user intent acquired by the intent acquisition unit 116 to the model for NSD 102, and acquire the NSD output from the model for NSD 102.

[0064] When the output control unit 122 inputs configuration definition information to MANO and MANO output data is output from MANO, the modified configuration definition information acquisition unit 126 inputs the configuration definition information and the MANO output data to the MANO model 106 to acquire the modified configuration definition information output from the MANO model 106. As an example, when the output control unit 122 inputs NSD to MANO and MANO output data is output from MANO, the modified configuration definition information acquisition unit 126 inputs the NSD and the MANO output data to the MANO model 106 to acquire the modified NSD output from the MANO model 106.

[0065] The MANO model generation unit 128 generates the MANO model 106. The MANO model generation unit 128 stores the generated MANO model 106 in the storage unit 110. The MANO model generation unit 128 may generate the MANO model 106 by machine learning the configuration definition information stored in the storage unit 110, the MANO output data output from MANO when the configuration definition information is input to MANO, and the modified configuration definition information that is the configuration definition information modified after the MANO output data is output, as learning data. As an example, the MANO model generation unit 128 may generate the MANO model 106 by machine learning the NSD stored in the storage unit 110, the MANO output data output from MANO when the NSD is input to MANO, and the modified NSD that is the NSD modified after the MANO output data is output, as learning data.

[0066] 9 is a schematic diagram showing an example of a hardware configuration of a computer 1200 functioning as the data processing device 100. A program installed on the computer 1200 can cause the computer 1200 to function as one or more "parts" of the device according to the present embodiment, or cause the computer 1200 to execute operations or one or more "parts" associated with the device according to the present embodiment, and / or cause the computer 1200 to execute a process or steps of the process according to the present embodiment. Such a program can be executed by the CPU 1212 to cause the computer 1200 to execute specific operations associated with some or all of the blocks of the flowcharts and block diagrams described herein.

[0067] The computer 1200 according to this embodiment includes a CPU 1212, a RAM 1214, and a graphics controller 1216, which are connected to each other by a host controller 1210. The computer 1200 also includes input / output units such as a communication interface 1222, a storage device 1224, a DVD drive, and an IC card drive, which are connected to the host controller 1210 via an input / output controller 1220. The DVD drive may be a DVD-ROM drive, a DVD-RAM drive, etc. The storage device 1224 may be a hard disk drive, a solid state drive, etc. The computer 1200 also includes a legacy input / output unit such as a ROM 1230 and a keyboard, which are connected to the input / output controller 1220 via an input / output chip 1240.

[0068] The CPU 1212 operates according to a program stored in the ROM 1230 and the RAM 1214, thereby controlling each unit. The graphic controller 1216 acquires image data generated by the CPU 1212 into a frame buffer or the like provided in the RAM 1214 or into itself, and causes the image data to be displayed on the display device 1218.

[0069] The communication interface 1222 communicates with other electronic devices via a network. The storage device 1224 stores programs and data used by the CPU 1212 in the computer 1200. The DVD drive reads programs or data from a DVD-ROM or the like and provides them to the storage device 1224. The IC card drive reads programs and data from an IC card and / or writes programs and data to an IC card.

[0070] The ROM 1230 stores therein a boot program or the like that is executed by the computer 1200 upon activation, and / or a program that depends on the hardware of the computer 1200. The input / output chip 1240 may also connect various input / output units to the input / output controller 1220 via a USB port, a parallel port, a serial port, a keyboard port, a mouse port, and the like.

[0071] The programs are provided by a computer-readable storage medium such as a DVD-ROM or an IC card. The programs are read from the computer-readable storage medium, installed in the storage device 1224, the RAM 1214, or the ROM 1230, which are also examples of computer-readable storage media, and executed by the CPU 1212. Information processing described in these programs is read by the computer 1200, and brings about cooperation between the programs and the various types of hardware resources described above. An apparatus or method may be constructed by implementing operations or processing of information according to the use of the computer 1200.

[0072] For example, when communication is performed between the computer 1200 and an external device, the CPU 1212 may execute a communication program loaded in the RAM 1214 and instruct the communication interface 1222 to perform communication processing based on the processing described in the communication program. Under the control of the CPU 1212, the communication interface 1222 reads transmission data stored in a transmission buffer area provided in the RAM 1214, the storage device 1224, a DVD-ROM, or a recording medium such as an IC card, and transmits the read transmission data to the network, or writes reception data received from the network to a reception buffer area or the like provided on the recording medium.

[0073] Furthermore, the CPU 1212 may cause all or a necessary portion of a file or database stored in an external recording medium such as the storage device 1224, a DVD drive (DVD-ROM), an IC card, etc. to be read into the RAM 1214, and perform various types of processing on the data on the RAM 1214. The CPU 1212 may then write back the processed data to the external recording medium.

[0074] Various types of information, such as various types of programs, data, tables, and databases, may be stored in the recording medium and undergo information processing. The CPU 1212 may perform various types of processing on the data read from the RAM 1214, including various types of operations, information processing, conditional judgment, conditional branching, unconditional branching, information search / replacement, etc., as described throughout this disclosure and specified by the instruction sequence of the program, and write back the results to the RAM 1214. The CPU 1212 may also search for information in a file, database, etc. in the recording medium. For example, when a plurality of entries each having an attribute value of a first attribute associated with an attribute value of a second attribute are stored in the recording medium, the CPU 1212 may search for an entry whose attribute value of the first attribute matches a specified condition from among the plurality of entries, read the attribute value of the second attribute stored in the entry, and thereby obtain the attribute value of the second attribute associated with the first attribute that satisfies a predetermined condition.

[0075] The above-described programs or software modules may be stored in a computer-readable storage medium on the computer 1200 or in the vicinity of the computer 1200. In addition, a recording medium such as a hard disk or a RAM provided in a server system connected to a dedicated communication network or the Internet can be used as a computer-readable storage medium, thereby providing the programs to the computer 1200 via the network.

[0076] The blocks in the flowcharts and block diagrams in the present embodiment may represent stages of a process in which an operation is performed or "parts" of an apparatus responsible for performing the operation. Particular stages and "parts" may be implemented by dedicated circuitry, programmable circuitry provided with computer-readable instructions stored on a computer-readable storage medium, and / or a processor provided with computer-readable instructions stored on a computer-readable storage medium. The dedicated circuitry may include digital and / or analog hardware circuits, and may include integrated circuits (ICs) and / or discrete circuits. The programmable circuitry may include reconfigurable hardware circuits, such as, for example, field programmable gate arrays (FPGAs), programmable logic arrays (PLAs), and the like, including AND, OR, XOR, NAND, NOR, and other logical operations, flip-flops, registers, and memory elements.

[0077] A computer-readable storage medium may include any tangible device capable of storing instructions that are executed by a suitable device, such that a computer-readable storage medium having instructions stored thereon comprises an article of manufacture that includes instructions that can be executed to create means for performing the operations specified in the flowcharts or block diagrams. Examples of computer-readable storage media may include electronic storage media, magnetic storage media, optical storage media, electromagnetic storage media, semiconductor storage media, and the like. More specific examples of computer-readable storage media may include floppy disks, diskettes, hard disks, random access memories (RAMs), read-only memories (ROMs), erasable programmable read-only memories (EPROMs or flash memories), electrically erasable programmable read-only memories (EEPROMs), static random access memories (SRAMs), compact disk read-only memories (CD-ROMs), digital versatile disks (DVDs), Blu-ray disks, memory sticks, integrated circuit cards, and the like.

[0078] The computer readable instructions may include either assembler instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk®, JAVA®, C++, etc., and conventional procedural programming languages ​​such as the “C” programming language or similar programming languages.

[0079] Computer readable instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, or to a programmable circuit, either locally or over a local area network (LAN), a wide area network (WAN), such as the Internet, etc., to cause the processor of the general purpose computer, special purpose computer, or other programmable data processing apparatus, or to a programmable circuit, to execute the computer readable instructions to generate means for performing the operations specified in the flowcharts or block diagrams. Examples of processors include computer processors, processing units, microprocessors, digital signal processors, controllers, microcontrollers, etc.

[0080] Although the present invention has been described above using the embodiments, the technical scope of the present invention is not limited to the scope described in the above embodiments. It is clear to those skilled in the art that various modifications and improvements can be made to the above embodiments. It is clear from the description of the claims that such modifications and improvements can also be included in the technical scope of the present invention.

[0081] It should be noted that the order of execution of each process, such as operations, procedures, steps, and stages, in the devices, systems, programs, and methods shown in the claims, specifications, and drawings is not specifically stated as "before" or "prior to," and that the process may be performed in any order unless the output of a previous process is used in a later process. Even if the operational flow in the claims, specifications, and drawings is described using "first," "next," etc. for convenience, it does not mean that the process must be performed in this order. [Explanation of symbols]

[0082] 10 network, 20 natural language processing model, 30 NSD-related data, 32 learning data, 40 MANO, 42 MANO output data, 50 communication terminal, 52 user, 54 user intent, 56 user intent, 100 data processing device, 102 NSD model, 104 response, 106 MANO model, 110 memory unit, 112 data collection unit, 114 configuration definition information model generation unit, 116 intent acquisition unit, 118 configuration definition information acquisition unit, 120 network information acquisition unit, 122 output control unit, 124 display control unit, 126 modified configuration definition information acquisition unit, 128 MANO model generation unit, 180 NSD, 190 network information, 1200 computer, 1210 host controller, 1212 CPU, 1214 RAM, 1216 graphic controller, 1218 display device, 1220 input / output controller, 1222 Communication interface, 1224 storage device, 1230 ROM, 1240 input / output chip

Claims

1. a storage unit that stores a configuration definition information model generated by updating a natural language processing model using configuration definition information related data related to configuration definition information that defines a network configuration, the configuration definition information model outputs configuration definition information when natural language indicating network requirements is input, and outputs network information indicating in natural language information about a network realized by the configuration definition information when configuration definition information is input; an intent acquisition unit that acquires a user intent including a natural language that indicates a network requirement input by a user; a configuration definition information acquisition unit that inputs the user intent into the configuration definition information model and acquires configuration definition information output from the configuration definition information model; an output control unit that controls the configuration definition information acquisition unit to output the acquired configuration definition information; A data processing device comprising:

2. a configuration definition information model generating unit that generates the configuration definition information model by updating the natural language processing model using the configuration definition information related data; Equipped with The data processing apparatus according to claim 1 , wherein the storage unit stores the configuration definition information model generated by the configuration definition information model generation unit.

3. 3. The data processing apparatus according to claim 2, wherein the configuration definition information related data includes at least one of set data including the configuration definition information and a description of the configuration definition information in natural language, and document data related to the configuration definition information.

4. The configuration definition information is a Network Service Descriptor (NSD), 4. The data processing device according to claim 3, wherein the configuration definition information related data includes at least one of set data including an NSD and a description of the NSD in natural language, document data related to the NSD according to ETSI (European Telecommunications Standards Institute), and document data related to the NSD according to TOSCA (Topology and Orchestration Specification for Cloud Applications).

5. a network information acquiring unit that inputs the configuration definition information acquired by the configuration definition information acquiring unit into the configuration definition information model and acquires network information output from the configuration definition information model; a display control unit that controls the network information acquisition unit to display the network information acquired by the network information acquisition unit; A data processing apparatus according to claim 1 , comprising:

6. The intent acquisition unit acquires the user intent modified based on the network information displayed under the control of the display control unit, The data processing apparatus according to claim 5 , wherein the configuration definition information acquisition unit inputs the corrected user intent to the configuration definition information model, and acquires the configuration definition information output from the configuration definition information model.

7. The storage unit stores a MANO model that receives configuration definition information and MANO output data as input and outputs modified configuration definition information, the model being generated by machine learning using configuration definition information, MANO output data output from MANO when the configuration definition information is input to the MANO, and modified configuration definition information, which is the configuration definition information modified after the MANO output data is output, as learning data; The data processing device includes: a modified configuration definition information acquisition unit that, when the output control unit inputs the configuration definition information to MANO and the MANO output data is output from the MANO, inputs the configuration definition information and the MANO output data to the MANO model and acquires modified configuration definition information output from the MANO model; A data processing apparatus according to claim 1 , comprising:

8. A MANO model generation unit that generates the MANO model by performing machine learning using, as learning data, configuration definition information, MANO output data output from MANO when the configuration definition information is input to MANO, and modified configuration definition information, which is the configuration definition information modified after the MANO output data is output. The data processing apparatus according to claim 7 , comprising:

9. The data processing device according to claim 8 , wherein the MANO output data includes at least one of a response, an error message, and a log output by the MANO.

10. 5. A data processing device according to claim 1, wherein the configuration definition information acquisition unit inputs the user intent into the configuration definition information model, and when missing data information regarding missing data is output from the configuration definition information model, queries the user about the missing data based on the missing data information.

11. A program for causing a computer to function as the data processing device according to any one of claims 1 to 4.

12. 1. A computer-implemented data processing method, comprising: an intent acquisition stage for acquiring a user intent input by a user, the user intent including a natural language indicating a requirement for the network; a configuration definition information acquisition step of inputting the user intent into a configuration definition information model generated by updating a natural language processing model using configuration definition information related data related to configuration definition information that defines a network configuration, the configuration definition information model outputting configuration definition information when natural language indicating network requirements is inputted, and outputting network information in natural language indicating information on a network realized by the configuration definition information when configuration definition information is inputted, and acquiring the configuration definition information outputted from the configuration definition information model; an output control step of controlling to output the configuration definition information acquired in the configuration definition information acquisition step; A data processing method comprising:

Images