Data processing apparatus, 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 apparatus, a program, and a data processing method.

Background Art

[0002] Patent Document 1 describes NFV (Network Functions Virtualization) and NSD (Network Service Descriptor). [Prior Art Document] [Patent Document] [Patent Document 1] Japanese Patent Application Laid-Open No. 2018-147429

Summary of the Invention

Means for Solving the Problems

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

[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. 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 an explanation of the configuration definition information in natural language, and document data related to the configuration definition information. The configuration definition information is NSD (Network Service Descriptor), and the configuration definition information related data may include at least one of set data including NSD and an explanation 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 one 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 corrected based on the network information displayed under the control of the display control unit, and the configuration definition information acquisition unit may input the corrected user intent into the configuration definition information model and acquire configuration definition information output from the configuration definition information model.

[0006] In any of the above data processing apparatuses, the storage unit may store a MANO model that takes configuration definition information and MANO output data as inputs and outputs modified configuration definition information, where the modified configuration definition information is generated by machine learning the configuration definition information, the MANO output data output from the MANO when the configuration definition information is input to the MANO, and the modified configuration definition information obtained by modifying the configuration definition information after the MANO output data is output, as learning data. When the output control unit inputs the configuration definition information to the MANO and the MANO outputs the MANO output data, the data processing apparatus may include a modified configuration definition information acquisition unit that 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 apparatus may include a MANO model generation unit that generates the MANO model by machine learning the configuration definition information, the MANO output data output from the MANO when the configuration definition information is input to the MANO, and the modified configuration definition information obtained by modifying the configuration definition information after the MANO output data is output, as learning data. 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 above data processing apparatuses, when the configuration definition information acquisition unit inputs the user intent to the configuration definition information model and the configuration definition information model outputs deficiency data information regarding deficiency data, the configuration definition information acquisition unit may inquire of the user about the deficiency data based on the deficiency data information.

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

[0009] According to an embodiment of the present invention, a data processing method executed by a computer is provided. The data processing method may include an intent acquisition step of acquiring a user intent including a natural language indicating requirements of a network, which is input by a user. The data processing method may include a configuration definition information acquisition step of inputting the user intent to a configuration definition information model that outputs configuration definition information when a natural language indicating requirements of a network, which is generated by updating a natural language processing model using configuration definition information-related data related to configuration definition information defining a configuration of the network, is input, and outputting configuration definition information obtained 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] Note that the above summary of the invention does not enumerate all the necessary features of the present invention. Also, sub-combinations of these feature groups may also be inventions.

Brief Description of the Drawings

[0011]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Mode for Carrying Out the Invention

[0012] Hereinafter, the present invention will be described through embodiments of the invention. However, the following embodiments do not limit the invention according to the claims. Also, not all combinations of features described in the embodiments are essential for the solution means of the invention.

[0013] Due to the popularity of SDN (Software-Defined Networking) and NFV, it has become possible to virtualize the resources of the mobile core network and represent them by an abstracted data model. Clear schemas have been defined by relevant standardization organizations for these abstracted virtual network data models (ETSI NFV ISG). As a result, it has become possible to automatically construct any network by constructing a network according to a reference architecture and inputting an accurate data model into an orchestrator (MANO).

[0014] However, in order to create a data model for building a network in such a way, expertise in mobile core / network / standard data models is required. Customer users are not only required to define requirements, but also required to bear the technical and human costs necessary for model creation. Even in the cases created by vendors or operators, since models tailored to requirements need to be considered on a customer-by-customer basis, high costs are required from the perspectives of technology, time, and human resources. Therefore, the number of users who can obtain sufficient benefits by using such a system is limited. In such a method, it is difficult to easily provide a network required by a wide range of users for the vertically integrated industries envisioned in the 5G era.

[0015] In contrast, in the data processing apparatus 100 according to the present embodiment, for example, as a method of expressing a user's intent, it is changed from an approach based on a strict data model to natural language processing (NLP: Natural Language Processing) established by recent AI technologies. In the data processing apparatus 100, for example, for an interactive natural language processing system typified by ChatGPT, after understanding the configuration of the network, the user's intent is input to generate a standardized abstract network data model. Although expertise is required to interpret the output data model, the output data model is input again to the interactive natural language processing system, and the system is fed back whether the model meets the user's intent by outputting an explanation in natural language. Then, by inputting the data model that has undergone this review to the orchestrator, a network required from the natural language-based intent can be constructed without expertise.

[0016] Here, an example will be given for explanation. The data processing apparatus 100 according to the present embodiment uses, for example, a dialogue system based on a large language model (LLM). In this system, the user 52 inputs the requirements of the network needed in natural language as the user intent. The system generates and outputs an NSD for realizing a network that meets 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 a network that meets the requirements, for the LLM trained on general content, as specialized knowledge for generating the NSD, the standard document of the NSD and the definition document of the description language are learned to optimize the model. Also, in order to generate an NSD from the requirements in natural language, model optimization is performed using the set of the requirements and description in natural language and the NSD as the training data. With these training data, the system learns the rules and relationships of the configuration and description method of the network described in natural language and the NSD that realizes it, and outputs the NSD with the configuration corresponding to the requirements for the input user intent in a form conforming to the definition. Conversely, by inputting the NSD, it is also possible to output an explanation of the content of the NSD (described network model) in natural language. In order to use the configuration pattern of the description format of the NSD and the natural language that explains it for learning, from the input NSD, the configuration of the network model described therein and the corresponding natural language description text are generated and output. In this way, an NSD can be output from the user intent in natural language, but it cannot be guaranteed that the NSD output in this way completely meets the user intent. Therefore, the output NSD is input again into the system, and a user review process is performed to output the natural language that explains the NSD. The user reviews whether the NSD meets his / her requirements from the description text. If not, the user intent in natural language is input again additionally, and the NSD is output again. Feedback by this user review is performed until the requirements are met.

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

[0018] The model for configuration definition information may be generated by updating a pre-trained natural language processing model using general learning data with 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 apparatus 100 may store the model for configuration definition information generated by itself. The data processing apparatus 100 may also acquire and store the model for configuration definition information generated by another apparatus.

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

[0020] The communication terminal 50 may be any terminal as long as it can communicate with the data processing apparatus 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 the user intent into the model for configuration definition information and obtains the configuration definition information output from the model for configuration definition information. The data processing device 100 inputs the obtained configuration definition information into the model for configuration definition information and obtains the network information output from the configuration definition information model. The data processing device 100 displays the obtained network information to the user 52. For example, the data processing device 100 causes the network information to be displayed on a display included 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, in natural language, the information of the network realized by the target configuration definition information, even a user 52 who cannot directly understand the configuration definition information can confirm whether the configuration definition information meets his / her requirements. When it is confirmed by browsing the network information that the configuration definition information meets his / her requirements, the configuration definition information may be input into the MANO. When it is confirmed that the configuration definition information does not meet his / her requirements, the user 52 generates a modified user intent obtained 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 obtains the modified user intent, inputs it into the model for configuration definition information, obtains the configuration definition information output from the model for configuration definition information, inputs the obtained configuration definition information into the model for configuration definition information, and obtains the network information output from the configuration definition information model. The data processing device 100 displays the obtained network information to the user 52. By repeating such processing, finally, configuration definition information that meets the requirements of the user 52 can be generated.

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

[0025] FIG. 2 is an explanatory diagram for explaining an NSD model 102, which is an example of a model for configuration definition information. 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 learned natural language processing model 20 using general learning data. The data processing device 100 may acquire the natural language processing model 20 generated by another device. The data processing device 100 may also generate the natural language processing model 20 by itself using general learning data.

[0027] The data processing apparatus 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 learning data for the correlation between NSD and natural language. The learning data for the correlation between NSD and natural language may include a set of descriptions of NSDs in natural language and NSDs. The NSD-related data 30 may include learning data for the NSD itself. The learning data for the NSD itself may include document data related to the NSD by ETSI (such as the standard document of the ETSI NSD). The learning data for the NSD itself may include document data related to the NSD by TOSCA (such as the official document regarding the TOSCA NSD).

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

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

[0030] When the user 52 can understand the NSD 180, the displayed NSD 180 is browsed. If there is no problem, it is input into the MANO. If there is a problem, the NSD 180 can be directly corrected, the user intent 54 can be corrected, or a new user intent 54 can be generated and input into the data processing apparatus 100.

[0031] The NSD model 102 may be configured to respond by asking the user 52 for insufficient information when generating an NSD for the input user intent if there is insufficient information.

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

[0033] The data processing device 100 that has obtained the user intent 54 inputs the user intent 54 into the NSD model 102. In this example, since the NSD model 102 lacks information, it outputs a response 104. The data processing device 100 causes the response 104 to be displayed to the user 52. In this example, the data processing device 100 causes the response 104 of "Do you have any requirements for communication speed?" to be displayed to the user 52.

[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 a user intent 56 of "I want to be able to maintain XX Mbps."

[0035] The data processing device 100 that has obtained the user intent 56 further inputs the user intent 56 into the NSD model 102. Since the NSD model 102 has no missing information, it outputs an NSD 180. The data processing device 100 causes the NSD 180 output from the NSD model 102 to be displayed to the user 52.

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

[0037] The data processing device 100 inputs the NSD180 into the NSD model 102 and acquires the network information 190 output from the NSD model 102. The data processing device 100 causes the acquired network information 190 to be displayed to the user 52. Thereby, the user 52 who cannot understand the NSD180 can be made to grasp what kind of network is realized by the NSD180.

[0038] The user 52 browses the displayed network information 190. If there is no problem, the user 52 inputs the NSD180 into the MANO. If there is a problem, the user 52 can input it into the data processing device 100 after modifying the user intent 54 or generating a new user intent 54.

[0039] FIG. 6 schematically shows an example of the processing flow by the data processing device 100. Here, an example of the flow from acquiring the user intent input by the user 52 to generating the NSD corresponding to the user intent and providing it to the MANO will be described.

[0040] In step 102 (steps may be described with S omitted), the data processing device 100 acquires the user intent. In S104, the data processing device 100 inputs the user intent acquired in S102 into the NSD model 102. In S106, the data processing device 100 acquires the NSD output by the NSD model 102.

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

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

[0043] Note that the data processing apparatus 100 may further have a function of correcting the NSD when the NSD provided to the MANO results in an error in the MANO.

[0044] FIG. 7 is an explanatory diagram for explaining the function of the data processing apparatus 100 to correct the NSD. The data processing apparatus 100 stores the MANO model 106 in advance. The MANO model 106 may be generated by machine learning using, as learning data, the NSD, the MANO output data output from the MANO 40 when the NSD is input to the MANO 40, and the corrected NSD which is the NSD corrected after the MANO output data is output, and is a model that takes the NSD and the MANO output data as inputs and outputs the corrected NSD.

[0045] The data processing apparatus 100 may store the MANO model 106 generated by itself. The data processing apparatus 100 may also obtain and store the MANO model 106 generated by another apparatus.

[0046] When generating the MANO model 106 by itself, the data processing apparatus 100 uses the learning data 32. The learning data 32 includes a set of the NSD, the MANO output data output from the MANO when the NSD is input to the MANO, and the corrected NSD which is the NSD corrected after the MANO output data is output. The MANO output data may include the response output by the MANO 40. The MANO output data may include the error message output by the MANO 40. The MANO output data may include the log output by the MANO 40.

[0047] When the data processing apparatus 100 inputs the NSD 180 to the MANO 40 and receives the MANO output data 42 from the MANO 40 due to a defect in the NSD 180, the NSD 180 and the MANO output data 42 are input to the MANO model 106, and a corrected version of the NSD 180 output from the MANO model 106 is obtained.

[0048] When the data processing apparatus 100 inputs the corrected version of the NSD 180 to the MANO 40 again and receives the MANO output data 42 from the MANO 40 due to a defect in the corrected version of the NSD 180, the corrected version of the NSD 180 and the MANO output data 42 are input to the MANO model 106, and a re-corrected version of the NSD output from the MANO model 106 is obtained and input to the MANO 40 again. The data processing apparatus 100 may repeat the process until the NSD 180 has no defects and the NSD 180 is accepted by the MANO 40.

[0049] FIG. 8 schematically shows an example of the functional configuration of the data processing apparatus 100. The data processing apparatus 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 corrected configuration definition information acquisition unit 126, and a MANO model generation unit 128. Note that it is not always essential for the data processing apparatus 100 to include 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 the configuration definition information model. As an example, the storage unit 110 stores the NSD model 102 in advance. For example, the storage unit 110 stores the MANO model 106 in advance.

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

[0052] For example, the data collection unit 112 acquires general learning data from the outside and stores it in the storage unit 110. For example, the data collection unit 112 acquires configuration definition information-related data from the outside and stores it in the storage unit 110. As an example, the data collection unit 112 acquires NSD-related data from the outside and stores it in the storage unit 110. For example, the data collection 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 collection 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 configuration definition information model generation unit 114 generates a configuration definition information model. As an example, the configuration definition information model generation unit 114 generates an NSD model 102. The configuration definition information model generation unit 114 stores the generated configuration definition information model in the storage unit 110. As an example, the configuration definition information model generation unit 114 stores the generated NSD model 102 in the storage unit 110. The configuration definition information model generation unit 114 may generate a configuration definition information model 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 configuration definition information model generation unit 114 may generate an NSD model 102 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 configuration definition information model generation unit 114 generates a configuration definition information model by performing model optimization using the configuration definition information related data on the natural language processing model 20. As an example, the configuration definition information model generation unit 114 generates an NSD model 102 by performing model optimization using the NSD related data on the natural language processing model 20. Examples of model optimization methods include, but are not limited to, Fine-tuning and Embeddings, and any method may be used.

[0054] The network desired by user 52 varies depending on differences such as vendor, carrier, purpose, performance, etc. The model generation unit 114 for configuration definition information may generate a model for configuration definition information by updating the natural language processing model 20 using configuration definition information-related data corresponding to these differences. The model generation unit 114 for configuration definition information uses, for example, configuration definition information-related data including a set of configuration definition information corresponding to a specific vendor and an explanatory text of the configuration definition information in natural language. As an example, the model generation unit 114 for configuration definition information uses, for example, NSD-related data including a set of NSD corresponding to a specific vendor and an explanatory text of the NSD in natural language. The model generation unit 114 for configuration definition information uses, for example, configuration definition information-related data including a set of configuration definition information corresponding to a specific carrier and an explanatory text of the configuration definition information in natural language. As an example, the model generation unit 114 for configuration definition information uses, for example, NSD-related data including a set of NSD corresponding to a specific carrier and an explanatory text of the NSD in natural language. Thereby, it is possible to generate a model for configuration definition information that can output configuration definition information that better matches the network desired by user 52.

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

[0056] The configuration definition information acquisition unit 118 inputs the user intent acquired by the intent acquisition unit 116 into the configuration definition information model stored in the storage unit 110, and acquires the configuration definition information output from the configuration definition information model. As an example, the configuration definition information acquisition unit 118 inputs the user intent acquired by the intent acquisition unit 116 into the NSD model 102 stored in the storage unit 110, and acquires the NSD output from the NSD model 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] When the configuration definition information acquisition unit 118 inputs the user intent into the configuration definition information model and deficiency data information regarding deficiency data is output from the configuration definition information model, the configuration definition information acquisition unit 118 may inquire the user 52 about the deficiency data based on the deficiency data information. As an example, when the configuration definition information acquisition unit 118 inputs the user intent into the NSD model 102 and deficiency data information regarding deficiency data is output from the NSD model 102, the configuration definition information acquisition unit 118 may inquire the user 52 about the deficiency data based on the deficiency data information. When, as a result of the inquiry, the configuration definition information acquisition unit 118 acquires the deficiency data input by the user 52, the configuration definition information acquisition unit 118 may further input the deficiency data into the configuration definition information model. As an example, when, as a result of the inquiry, the configuration definition information acquisition unit 118 acquires the deficiency data input by the user 52, the configuration definition information acquisition unit 118 may further input the deficiency data into the NSD model 102. When further deficiency data information is output from the configuration definition information model, the configuration definition information acquisition unit 118 may inquire the user 52, and when no deficiency data information is output and configuration definition information is output, the configuration definition information acquisition unit 118 may acquire the configuration definition information. As an example, when further deficiency data information is output from the NSD model 102, the configuration definition information acquisition unit 118 may inquire the user 52, and when no deficiency data information is output and NSD is output, 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 configuration definition information model stored in the storage unit 110, and acquires the network information output from the configuration definition information model. As an example, the network information acquisition unit 120 inputs the NSD acquired by the configuration definition information acquisition unit 118 into the NSD model 102 stored in the storage unit 110, and acquires the network information output from the NSD model 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 the 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 to the MANO. As an example, the output control unit 122 controls to output the NSD acquired by the configuration definition information acquisition unit 118 to the MANO.

[0060] The display control unit 124 controls to display 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 apparatus 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 control to display the configuration definition information acquired by the configuration definition information acquisition unit 118. As an example, the display control unit 124 may control to display the NSD acquired by the configuration definition information acquisition unit 118. The display control unit 124 may control to display the network information acquired by the network information acquisition unit 120.

[0062] The intent acquisition unit 116 may acquire the 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 into the configuration definition information model and acquire the configuration definition information output from the configuration definition information model. As an example, the configuration definition information acquisition unit 118 may input the modified user intent acquired by the intent acquisition unit 116 into the NSD model 102 and acquire the NSD output from the NSD model 102.

[0063] The intent acquisition unit 116 may acquire the 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 into the configuration definition information model and acquire the configuration definition information output from the configuration definition information model. As an example, the configuration definition information acquisition unit 118 may input the user intent acquired by the intent acquisition unit 116 into the NSD model 102 and acquire the NSD output from the NSD model 102.

[0064] When the output control unit 122 inputs the configuration definition information to the MANO and the MANO output data is output from the MANO, the modified configuration definition information acquisition unit 126 inputs the configuration definition information and the MANO output data to the MANO model 106 and acquires the modified configuration definition information output from the MANO model 106. As an example, when the output control unit 122 inputs the NSD to the MANO and the MANO output data is output from the MANO, the modified configuration definition information acquisition unit 126 inputs the NSD and the MANO output data to the MANO model 106 and acquires 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 performing machine learning using, as learning data, 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 which is the configuration definition information modified after the MANO output data is output. As an example, the MANO model generation unit 128 may generate the MANO model 106 by performing machine learning using, as learning data, 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 which is the NSD modified after the MANO output data is output.

[0066] FIG. 9 schematically shows an example of the hardware configuration of a computer 1200 that functions as the data processing apparatus 100. Programs installed in the computer 1200 cause the computer 1200 to function as one or more "units" of the apparatus according to the present embodiment, or cause the computer 1200 to execute operations associated with the apparatus according to the present embodiment or the one or more "units", and / or cause the computer 1200 to execute the process according to the present embodiment or stages of the process. Such programs may be executed by the CPU 1212 to cause the computer 1200 to execute certain 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 graphic controller 1216, which are interconnected 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, or the like. The storage device 1224 may be a hard disk drive, a solid state drive, or the like. The computer 1200 also includes legacy input / output units 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 programs 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 in a frame buffer or the like provided in the RAM 1214 or within 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 a program or data from a DVD-ROM or the like and provides it 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] ROM 1230 stores therein a boot program or the like executed by computer 1200 upon activation and / or a program dependent on the hardware of computer 1200. Input / output chip 1240 may also be connected to input / output controller 1220 via various input / output units such as a USB port, a parallel port, a serial port, a keyboard port, a mouse port, etc.

[0071] The program is provided by a computer-readable storage medium such as a DVD-ROM or an IC card. The program is read from the computer-readable storage medium, installed in storage device 1224, RAM 1214, or ROM 1230, which is also an example of a computer-readable storage medium, and executed by CPU 1212. The information processing described in these programs is read by computer 1200, resulting in cooperation between the programs and the various types of hardware resources described above. The apparatus or method may be configured by realizing the operation or processing of information according to the use of computer 1200.

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

[0073] Further, the CPU 1212 may cause all or a necessary part 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 may execute various types of processing on the data on the RAM 1214. Next, the CPU 1212 may 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 may 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 branch, unconditional branch, information search / replacement, etc. described throughout this disclosure and specified by the instruction sequence of the program, and write back the result to the RAM 1214. Further, the CPU 1212 may search for information in files, databases, etc. within 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 searches for an entry that matches the condition where the attribute value of the first attribute is specified among the plurality of entries, reads the attribute value of the second attribute stored in the entry, and thereby may obtain the attribute value of the second attribute associated with the first attribute that satisfies a predetermined condition.

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

[0076] In the flowchart and block diagram in this embodiment, the blocks may represent the stages of the process in which the operation is executed or the "parts" of the apparatus having the role of executing the operation. Specific stages and "parts" may be implemented by a dedicated circuit, a programmable circuit supplied together with computer-readable instructions stored on a computer-readable storage medium, and / or a processor supplied together with computer-readable instructions stored on a computer-readable storage medium. The dedicated circuit may include digital and / or analog hardware circuits and may include an integrated circuit (IC) and / or discrete circuits. The programmable circuit may include, for example, a reconfigurable hardware circuit including logical products, logical sums, exclusive logical sums, negative logical products, negative logical sums, and other logical operations, flip-flops, registers, and memory elements, such as a field programmable gate array (FPGA) and a programmable logic array (PLA).

[0077] The computer-readable storage medium may include any tangible device capable of storing instructions executable by an appropriate device. As a result, the computer-readable storage medium having the instructions stored therein will comprise a product including instructions that can be executed to create means for performing the operations specified in the flowchart or block diagram. Examples of the computer-readable storage medium may include electronic storage media, magnetic storage media, optical storage media, electromagnetic storage media, semiconductor storage media, and the like. More specific examples of the computer-readable storage medium may include floppy (registered trademark) disks, diskettes, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), electrically erasable programmable read-only memory (EEPROM), static random access memory (SRAM), compact disk read-only memory (CD-ROM), digital versatile disk (DVD), Blu-ray (registered trademark) disk, memory stick, integrated circuit card, and the like.

[0078] Computer-readable instructions may include any combination of one or more programming languages, including source code or object code written in assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, status setting data, or object-oriented programming languages such as Smalltalk®, JAVA®, C++, and conventional procedural programming languages such as the "C" programming language or similar programming languages.

[0079] The computer-readable instructions may be provided locally or via a wide area network (WAN) such as a local area network (LAN), the Internet, etc., to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, or a programmable circuit, for the processor of the general-purpose computer, the special-purpose computer, or other programmable data processing device, or the programmable circuit to execute the operations specified in the flowchart or block diagram by generating means for executing the computer-readable instructions. Examples of processors include computer processors, processing units, microprocessors, digital signal processors, controllers, microcontrollers, etc.

[0080] As described above, the present invention has been described using embodiments, but the technical scope of the present invention is not limited to the scope described in the above embodiments. It is obvious to those skilled in the art that various changes or improvements can be made to the above embodiments. It is clear from the description of the claims that forms with such changes or improvements can also be included in the technical scope of the present invention.

[0081] In the claims, the specification, and the drawings, the execution order of each process such as operations, procedures, steps, and stages in the apparatus, system, program, and method shown is not explicitly indicated as "earlier" or "preceding" etc. in particular, and it should be noted that it can be realized in any order unless the output of the previous process is used in the subsequent process. Regarding the operation flows in the claims, the specification, and the drawings, even if explanations are made using "first," "next," etc. for convenience, it does not mean that it is essential to implement in this order.

Description of Reference Numerals

[0082] 10 Network, 20 Natural Language Processing Model, 30 NSD-related Data, 32 Training Data, 40 MANO, 42 MANO Output Data, 50 Communication Terminal, 52 User, 54 User Intent, 56 User Intent, 100 Data Processing Device, 102 Model for NSD, 104 Response, 106 Model for MANO, 110 Storage Unit, 112 Data Collection Unit, 114 Model Generation Unit for Configuration Definition Information, 116 Intent Acquisition Unit, 118 Configuration Definition Information Acquisition Unit, 120 Network Information Acquisition Unit, 122 Output Control Unit, 124 Display Control Unit, 126 Revised Configuration Definition Information Acquisition Unit, 128 Model Generation Unit for MANO, 180 NSD, 190 Network Information, 1200 Computer, 1210 Host Controller, 1212 CPU, 1214 RAM, 1216 Graphics 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 that outputs configuration definition information when natural language indicating requirements of a network, which is generated by updating a natural language processing model using configuration definition information-related data related to configuration definition information defining a network configuration, is input, and outputs network information indicating in natural language information of the network realized by the configuration definition information when the configuration definition information is input; An intent acquisition unit that acquires a user intent including natural language indicating requirements of a network input by a user; 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; An output control unit that controls to output the configuration definition information acquired by the configuration definition information acquisition unit; Comprising; 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; A display control unit that controls to display the network information acquired by the network information acquisition unit; Further comprising; The intent acquisition unit acquires the user intent corrected based on the network information displayed under the control of the display control unit; The configuration definition information acquisition unit inputs the corrected user intent into the configuration definition information model and acquires the configuration definition information output from the configuration definition information model; A data processing device.

2. 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; Comprising; The storage unit stores the configuration definition information model generated by the configuration definition information model generation unit. The data processing device according to claim 1.

3. The configuration definition information-related data includes at least one of set data including configuration definition information and an explanation of the configuration definition information in natural language, and document data related to the configuration definition information. The data processing device according to claim 2.

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

5. A data processing apparatus, A storage unit that stores a configuration definition information model that outputs configuration definition information when natural language indicating network requirements, which is generated by updating a natural language processing model using configuration definition information related data related to configuration definition information defining the configuration of a network, is input, and outputs network information indicating in natural language information of a network realized by the configuration definition information when the configuration definition information is input; An intent acquisition unit that acquires a user intent including natural language indicating network requirements input by a user; 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; An output control unit that controls to output the configuration definition information acquired by the configuration definition information acquisition unit and includes: The storage unit stores a MANO model that takes as input the configuration definition information and the MANO output data and outputs the modified configuration definition information, which is 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 the modified configuration definition information that is the modified configuration definition information after the MANO output data is output; The data processing apparatus, 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 further includes. A data processing apparatus.

6. A MANO model generation unit that generates a model for MANO by performing machine learning on configuration definition information, MANO output data output from the MANO when the configuration definition information is input to the MANO, and modified configuration definition information that is the configuration definition information modified after the MANO output data is output, as learning data The data processing device according to claim 5, comprising the above

7. The data processing device according to claim 6, wherein the MANO output data includes at least any one of a response, an error message, and a log output by the MANO

8. A program for causing a computer to function as the data processing device according to any one of claims 1 to 7

9. A data processing method executed by a computer, comprising: An intent acquisition step of acquiring a user intent including a natural language indicating requirements of a network, which is input by a user A configuration definition information acquisition step of inputting the user intent to a configuration definition information model that outputs configuration definition information when a natural language indicating requirements of a network, which is generated by updating a natural language processing model using configuration definition information-related data related to configuration definition information defining the configuration of the network, is input, and acquiring the configuration definition information output 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 Comprising A network information acquisition step of inputting the configuration definition information acquired in the configuration definition information acquisition step to the configuration definition information model and acquiring network information output from the configuration definition information model A display control step of controlling to display the network information acquired in the network information acquisition step Further comprising A modified intent acquisition step of acquiring a modified user intent based on the network information displayed under the control in the display control step A configuration definition information acquisition step of inputting the modified user intent acquired in the modified intent acquisition step to the configuration definition information model and acquiring the configuration definition information output from the configuration definition information model Further comprising Data processing method.

10. A data processing method executed by a computer, an intent acquisition step of acquiring a user intent including a natural language indicating requirements of a network, which is input by a user; a configuration definition information acquisition step of inputting the user intent into a configuration definition information model that outputs configuration definition information when a natural language indicating requirements of a network, which is generated by updating a natural language processing model using configuration definition information-related data related to configuration definition information defining the configuration of the network, is input, and outputs network information indicating, in natural language, the network information realized by the configuration definition information when the configuration definition information is input, and acquiring the configuration definition information output from the configuration definition information model; inputting the configuration definition information acquired in the configuration definition information acquisition step into MANO (Management and Orchestration), and when MANO output data is output from the MANO, inputting the configuration definition information and the MANO output data into a MANO model that takes, as input, the configuration definition information, the MANO output data output from the MANO when the configuration definition information is input into the MANO, and the modified configuration definition information that is the configuration definition information modified after the MANO output data is output, and outputs the modified configuration definition information, and learning, as learning data, the configuration definition information and the MANO output data, and acquiring the modified configuration definition information output from the MANO model; A data processing method comprising the above steps.

Images