Data processing device, method, and program

Abstract

A data processing device according to one embodiment of the present invention comprises: an input unit that receives, from a user who uses a service, an input relating to the situation at the time of use of the service; a calculation unit that calculates a requirement relating to provision of the service to the user on the basis of a result of the input to the input unit and information stored in a storage device that stores information indicating the relationship between the situation at the time of use of the service and the requirement relating to the provision of the service to the user; and a generation unit that generates a question prompting the user to provide an additional input relating to the situation at the time of use of the service when the requirement calculated by the calculation unit is not appropriate.

Description

Data processing apparatus, method, and program

[0001] Embodiments of the present invention relate to a data processing apparatus, method, and program.

[0002] As a perspective of information and communication technology, the form of communication service provision in the 6G / IOWN (registered trademark) era is expected to shift from the conventional monthly communication service to a form that provides, at any time, a communication service of optimal quality for the application service used by the user according to the timing or environment in which the user, who is the service user, wants to use the service.

[0003] In an environment as described above, it is assumed that the usage demands of service users will also be diverse, and it is necessary to correctly grasp various requirements such as communication quality indicators or indicator values that satisfy these demands, and to input the configurations necessary for controlling each resource device.

[0004] On the other hand, users are not familiar with the necessary communication quality items and resource control systems. Therefore, through hearings from users, etc., studies are being conducted to extract the requirements related to the above communication quality from the demands containing many non-technical terms expressed by users, and to provide services optimized for the demands of users.

[0005] For example, in quality requirement extraction techniques such as those disclosed in Patent Document 1, Non-Patent Document 1, Non-Patent Document 2, or Non-Patent Document 3, requirements composed of communication quality indicators are extracted through interaction with users, etc.

[0006] International Publication No. 2023 / 157304

[0007] Hiroaki Kikushima, Nobukazu Fukuda, Chao Wu, Shingo Horiuchi, Kenichi Tayama, "Quantitative Intent Derivation Method Based on User Service Utilization Requirements," Proceedings of the IEICE 2022 National Convention, B-14-8, Mar. 2022. Chao Wu, Nobukazu Fukuda, Hiroaki Kikushima, Shingo Horiuchi, Kenichi Tayama, "A Method for Extracting Appropriate Services from User Intent," IEICE 2023 Society Conference, 2023 / 9 / 5. Dimitrios Michael Manias, Ali Chouman, and Abdallah Shami, "Towards Intent-Based Network Management: Large Language Models for Intent Extraction in 5G Core Networks," 2024 20th International Conference on the Design of Reliable Communication Networks (DRCN), May 2024.

[0008] On the other hand, if the content of the user's request is insufficient, for example, if the words included in the request are ambiguous, or if the request contains abstract words, then the requirements extracted from the request will be insufficient as requirements for providing an appropriate service, and an appropriate service cannot be provided to the user.

[0009] This invention was made in view of the above circumstances, and its purpose is to provide a data processing device, method, and program that can obtain requirements for appropriate service provision based on user requests.

[0010] A data processing device according to one aspect of the present invention includes: an input unit that receives input from a user of the service regarding the circumstances of the service usage; a calculation unit that calculates requirements for the provision of the service to the user based on the results of the input from the input unit and information stored in a storage device that stores information indicating the relationship between the circumstances of the service usage and the requirements for the provision of the service to the user; and a generation unit that generates a question requesting additional input from the user regarding the circumstances of the service usage when the requirements calculated by the calculation unit are inappropriate.

[0011] A data processing method according to one aspect of the present invention is a method performed by a data processing device, comprising: an input unit of the data processing device receiving input from a user of the service regarding the circumstances of the service use; a calculation unit of the data processing device calculating requirements for the provision of the service to the user based on the results of the input from the input unit and information stored in a storage device that stores information indicating the relationship between the circumstances of the service use and the requirements for the provision of the service to the user; and a generation unit of the data processing device generating a question requesting additional input from the user regarding the circumstances of the service use when the requirements calculated by the calculation unit are inappropriate.

[0012] According to the present invention, it is possible to obtain requirements for providing appropriate services based on user requests.

[0013] Figure 1 is a diagram showing an example of application of a data processing device according to one embodiment of the present invention. Figure 2 is a diagram illustrating an example of the processing procedure by the data processing device according to one embodiment of the present invention. Figure 3 is a diagram illustrating an example of question generation according to the content of the user's response. Figure 4 is a diagram illustrating an example of extracting mentioned words and generating a question sentence according to the content of the user's response. Figure 5 is a diagram showing an example of each item related to the user's request. Figure 6 is a diagram showing an example of each item related to the user's request. Figure 7 is a diagram showing an example of each item related to the user's request. Figure 8 is a diagram showing an example of each item related to the user's request. Figure 9 is a diagram illustrating an example of question generation according to the content of the response to a question to the user. Figure 10 is a block diagram showing an example of the hardware configuration of a data processing device according to one embodiment of the present invention.

[0014] Embodiments relating to this invention will be described below. Figure 1 is a diagram showing an example of application of a data processing device according to one embodiment of the present invention. As shown in Figure 1, the data processing device 100 according to one embodiment of the present invention comprises a user I / F (interface) 10, a service usage status input unit 20, a quantification requirement calculation unit 30, a data management unit 40, a requirement extraction degree calculation unit 50, a question generation unit 60, and a service requirement output unit 70.

[0015] The quantification requirement calculation unit 30 includes a service category identification unit 31, a service category-specific requirement indicator identification unit 32, an indicator-specific acquisition range identification unit 33, and a service requirement calculation unit 34.

[0016] The user interface 10 receives input operations or voice input from the user and displays notifications from the question generation unit 60 on a display device (not shown). The service usage status input unit 20 receives input of usage requirements, which are the service usage status related to the service used by the user, based on operations received by the user interface 10.

[0017] The data management unit 40 is equipped with a storage device, which contains a service-to-service-category DB (database) 41 and a service-category-specific request index DB 42, both of which are used to calculate quantitative intents.

[0018] Each part of the Quantification Requirements Calculation Unit 30 uses the input results from the Service Usage Status Input Unit 20 and the respective DBs in the Data Management Unit 40 to calculate quality requirements for the service being used as quantitative Intents, which are quantitative Intents corresponding to the input content from the Service Usage Status Input Unit 20.

[0019] The data management unit 40 stores data models in the service-to-service-category DB 41 and ontologs in the service-category-specific requirement indicator DB 42. The data models include a service-category data definition model.

[0020] The service category data definition model defines data that the service usage status input unit 20 can accept as input through user operations, such as the names of services that the user can select on the input screen for the name of the service they wish to use, such as web conferencing, VOD (Video On Demand), or remote control.

[0021] Furthermore, this service category data definition model defines the name of the service mentioned above, and the category to which the service with that name belongs (hereinafter sometimes referred to as the service category), for example, the category to which the above-mentioned web conferencing belongs, "video and audio two-way distribution service."

[0022] The above ontology includes an ontology for service category-specific requirement metrics. This ontology for service category-specific requirement metrics defines the types of quantitative intent quality metrics related to the service types defined in the service category data definition model described above, such as quality metrics (communication quality metrics) (QoE (Quality of Experience)), stability metrics (jitter), stability metrics (packet loss), and delay metrics (RTT (Round-Trip Time)).

[0023] The ontology described above outputs requirements for service provision based on the input service usage status, and is constructed so that these output service provision requirements approach the correct information.

[0024] The service category identification unit 31 of the quantification requirement calculation unit 30 identifies the service category to which the name of the service used belongs by inputting the name of the service used into a service category data definition model stored in the service-to-service category DB 41 in the data management unit 40.

[0025] The service category-specific requirement indicator identification unit 32 of the quantitative requirement calculation unit 30 reads the ontology of service category-specific requirement indicators stored in the service category-specific requirement indicator DB 42 in the data management unit 40, and uses this ontology to identify the quality indicators required for the services provided to the user in the service category identified by the service category identification unit 31.

[0026] Here, the following (a) to (d) are identified as quality indicators for the specified service category "video and audio two-way distribution service": (a) Quality indicator (QoE) (b) Stability indicator (jitter) (c) Stability indicator (packet loss) (d) Latency indicator (RTT) The indicator-specific acquisition range identification unit 33 of the quantification requirement calculation unit 30 reads the ontology of service category-specific requirement indicators stored in the service category-specific requirement indicator DB 42 in the data management unit 40, and uses this ontology to identify the indicator-specific acquisition range, which is the setting range of the value of the quality indicator identified by the service category-specific requirement indicator identification unit 32.

[0027] The available range for each metric may include the identified service category, the category's identifier (ID), the number of metrics, the metric name, the identifier for that metric name, the required value range, and a vector v. This vector represents the relationship between the magnitude of the identified quality metric value and the quality level.

[0028] For example, if the vector relating to a certain quality indicator is "1", it means that the higher the value of that quality indicator, the better the quality. Conversely, if the vector is "-1", it means that the higher the value of that quality indicator, the worse the quality.

[0029] The Quantification Requirements Calculation Unit 30's Service Requirements Calculation Unit 34 calculates the Service Requirements, which are quality indicator values ​​for the service being used, using the obtainable range for each indicator identified by the Indicator-Specific Obtainable Range Identification Unit 33.

[0030] For example, the following (a) to (d) are calculated as service requirements for use: (a) Quality Index (QoE): 4.0 or higher (b) Stability Index (Jitter): 10 [ms] or less (c) Stability Index (Packet Loss): 0.5 [%] or less (d) Relay Time (RTT): 300 [ms] or less In other words, in this embodiment, each unit (indicated by the symbol a in Figure 1), consisting of the service usage status input unit 20, the quantification requirement calculation unit 30, and the data management unit 40, has functions such as calculating quality requirements for the service being used based on user input of the service usage status. This calculation is described in, for example, Patent Document 1.

[0031] Furthermore, in this embodiment, each unit (reference numeral b in Figure 1), consisting of the requirements extraction degree calculation unit 50, the question generation unit 60, and the service requirements output unit 70, has the function of prompting the user to provide additional input when the user's input of service usage requirements is inappropriate, thereby ensuring that the quality requirements for the service used, calculated by the quantitative requirements calculation unit 30, are appropriate as quality requirements related to the provision of services to the user. Details of these functions will be described below.

[0032] The requirements extraction degree calculation unit 50 calculates a requirements extraction degree that indicates whether the quality requirements for the service used, calculated by the quantitative requirements calculation unit 30, are appropriate as quality requirements for providing services to users, for example, whether all necessary requirements have been calculated without omission, or whether the values ​​of the requirements are appropriate. Based on this requirements extraction degree, the unit determines whether the quality requirements for the service used, calculated by the quantitative requirements calculation unit 30, are appropriate as quality requirements for providing services to users.

[0033] When the requirement extraction degree calculation unit 50 determines that the quality requirements for the service used, calculated by the quantitative requirement calculation unit 30, are not appropriate as quality requirements for providing services to the user, that is, when the question generation unit 60 determines that it is necessary to generate a question requesting additional input from the user, the question generation unit 60 determines that the usage requirements, which are the service usage status related to the service used by the user and entered through the operation received by the user I / F 10, are insufficient, and generates a question requesting additional input from the user to make the entered usage requirements sufficient.

[0034] The question generation unit 60 includes a mentioned word extraction unit 61, a question method DB 62, and a question sentence generation unit 63. When it is determined that question generation processing is necessary as described above, the mentioned word extraction unit 61 extracts descriptions from the input, which are sentences or words included in the usage requirements that represent the service usage status related to the service used by the user, that should be mentioned to the user as insufficient, such as ambiguous words, abstract words, or parts that are insufficient as a response, such as descriptions where the reason is unclear.

[0035] The question method DB 62 stores information indicating how to ask questions to the user, based on the extraction results by the mentioned word extraction unit 61. The question method includes, for example, an overview of the question method and an example of a question sentence. The question sentence generation unit 63 obtains information indicating how to ask questions to the user from the question method DB 62, based on the extraction results by the mentioned word extraction unit 61, and uses this obtained question method information to generate a question sentence to the user that is sufficient for the input usage requirements, and notifies the user of this question sentence by displaying a message on the user I / F 10 or the like.

[0036] When the requirement extraction degree calculation unit 50 determines that the quality requirements for the service used, calculated by the quantitative requirement calculation unit 30, are appropriate as quality requirements for providing services to the user, the service requirement output unit 70 determines that the usage requirements, which are the service usage status related to the services used by the user and input through the operation received by the user I / F 10, are sufficient, and outputs these quality requirements as quality requirements for the services to be provided to the user.

[0037] In this embodiment, when user input is insufficient, the question generation unit 60 generates a question for the user. Upon receiving this question, the user inputs a response through operations on the user interface 10. This response ensures that the usage requirements, which represent the service usage status related to the service used by the user, are sufficient. As a result, the quality requirements for the service used, calculated by the quantitative requirement calculation unit 30, become appropriate as quality requirements for service provision to the user. This enables the provision of optimal services to the user.

[0038] Figure 2 is a diagram illustrating an example of the processing procedure by a data processing device according to one embodiment of the present invention. Figure 3 is a diagram illustrating an example of question generation in response to user responses. Next, an example of question generation by the question generation unit 60 will be described. In the example shown in Figure 3, first, the question generation unit 60 generates and notifies the user of question content "1", which is the first question from the telecommunications carrier providing communication services to the user regarding the service usage requirements requested by the user. The user inputs the service usage requirements they request, related to question content "1", as question response "1" using the user interface 10. Next, after this input, the user is notified of question content "2", which is the next question to the user regarding usage requirements, unrelated to the content of question response "1". The user inputs the service usage requirements they request, related to question content "2", as question response "2" using the user interface 10.

[0039] In this embodiment, with respect to the above-mentioned question content "1", a question response "1" is input by user operation to the user I / F 10, and upon this input, the service usage status input unit 20 receives the input of usage requirements, which are the service usage status related to the service used by the user (S10). After processing in the quantitative requirement calculation unit 30, the service requirement calculation unit 34 of the quantitative requirement calculation unit 30 calculates the service requirement for use, which is a quality index value for the service used (S20).

[0040] Then, the requirements extraction degree calculation unit 50 calculates a requirements extraction degree that indicates the degree to which the requirements for the service used calculated in S20 are appropriate as quality requirements for providing services to users, and determines whether this requirements extraction degree is above a threshold (S30).

[0041] If the requirement extraction rate is below the threshold (No. in S30), the mention word extraction unit 61 of the question generation unit 60 extracts ambiguous words, abstract words, or parts that are insufficient as an answer from the answer content "1", which is the content of the question answer "1" described above, as emphasis to be mentioned (S40).

[0042] The word extraction unit 61 obtains a question method from the question method DB 62 that corresponds to the response content "1" and is based on psychology or UX (User Experience) design (S50). Examples of question methods include questions aimed at clarifying the reasons related to the response content "1," that is, prompting the user to input additional specific explanatory text to supplement parts of the explanation that are insufficient, or questions aimed at prompting the user to input ambiguous or abstract words included in the response content "1" into relatively clear words.

[0043] Then, the question generation unit 63 combines the results of the word extraction unit 61, which extracts the accents to be mentioned, and the results of the question method acquisition to generate a question for the user regarding the response content "1" (S60).

[0044] The answer to this question text is input by the user's operation on the user I / F 10, so that an appropriate answer to the question content "1" can be obtained (reference sign a in FIG. 3). The same can be done for the question answer "2" for the above-mentioned question content "2". Also, when the requirement extraction degree calculated according to the above answer is still less than the threshold value, the generation of the question text is repeatedly performed until the requirement extraction degree becomes equal to or higher than the threshold value. As a result, the content of the usage requirements of the service desired by the user becomes appropriate, and the quantification requirement calculation unit 30 can calculate appropriate quality requirements for the used service.

[0045] Also, when the requirement extraction degree calculated by the requirement extraction degree calculation unit 50 is equal to or higher than the threshold value (Yes in S30), the service requirement output unit 70 determines that the quality requirement for the used service based on the user's answer is appropriate as the quality requirement related to the service provision to the user, and the usage requirement input as the user's answer is sufficient. Then, this quality requirement is determined as the quality requirement related to the service provided to the user and output (S70).

[0046] FIG. 4 is a diagram for explaining an example of extraction of reference words and generation of question text according to the response content from the user. In FIG. 4, an example of a prompt for realizing the processing by each part (reference sign a in FIG. 4) including the reference word extraction unit 61 and the question method DB 62 of the question generation unit 60, and an example of a question text generated using the LLM (Large Language Models) by the question text generation unit 63 (reference sign b in FIG. 4) of the question generation unit 60 are shown. Also, not limited to this example, question generation using a method such as fine-tuning may be performed.

[0047] In the example shown in FIG. 4, the reference word extraction unit 61 of the question generation unit 60 extracts words to be noted from the response content of the user, and uses Few-shot for the extraction result shown by reference sign c in FIG. 4 to extract several ambiguous words, abstract words, or insufficient parts included in the response content.

[0048] In the prompt shown in FIG. 4, the question methods "1" and "2", which include the outline of the question method and examples of question sentences as described above and are stored in the question method DB 62, are described, and the response content by the user is reflected. The question generation unit 60 inputs the prompt shown in FIG. 4 to the LLM, and causes the LLM to output a question sentence for the response content from the user.

[0049] FIGS. 5 to 8 are diagrams showing an example of each item related to the user's request. Here, an example of the specification of the service usage requirements, which are questions to the user related to the requirements of the service and requests input by the user based on the responses from the user, will be described. In the example shown in FIG. 5, the items of the service usage requirements include (1) the attributes of the participants in the service, (2) the name of the service to be used, (3) the priority with respect to other attributes related to the processing delay, (4) information related to the processing speed, (5) information related to the processing delay, (6) information related to the communication bandwidth, (7) information related to the stability of the processing, and (8) the communication connection method, and these items are managed, for example, in the internal memory of the question sentence generation unit 63.

[0050] Then, when the user responds with "I want to use it in a game tournament" by voice input using, for example, the user I / F 10 to the first question to the user "For what purpose do you use it?", and as a result of this response, it is determined that the processing by the question generation unit 60 is necessary as described above, the question sentence generation unit 63 of the question generation unit 60 is based on the question method "Force the verbalization to clarify ambiguous words (e.g., What specifically does ~ mean?)" stored in the question method DB 62, generates a question sentence for the user "You want to hold a game tournament. Could you please tell me specifically?", and sends it to the user I / F 10.

[0051] When a user responds to this question via User I / F 10 with "I want to hold an online FPS (First-Person Shooter) game gathering. There will be 5 players and about 30 people cheering at the venue," the following changes are made to each item of the service usage requirements shown in Figure 5, as shown in Figure 6: the first line of the service usage requirements reflects the participant attribute "players," the service used "FPS game," and the number of people related to communication bandwidth, "5 people." The second line of the service usage requirements reflects the participant attribute "venue guests" and the number of people related to communication bandwidth, "30 people."

[0052] If the most recent response determines that further processing by the question generation unit 60 is necessary, the question text generation unit 63 of the question generation unit 60 generates a question for the user, "What do you value most in a game tournament?", based on the question method "Asking for one's own opinion (e.g., What did you think?)" stored in the question method DB 62, and sends it to the user I / F 10.

[0053] When the user responds to this question via User I / F 10 with "I guess it's that the movement doesn't stutter during competitive games. If it stutters during competitive games, it would be an uncomfortable situation for everyone in the venue," then, for each item of the service usage requirements shown in Figure 6, the information related to communication delay, "FPS games" and "no stuttering in games," as well as the information related to stability, "no stuttering," are reflected in the first line of the service usage requirements, as shown in Figure 7.

[0054] If the most recent response determines that further processing by the question generation unit 60 is necessary, the question text generation unit 63 of the question generation unit 60 generates a question for the user, "Have you experienced similar jerky movements in the past?", based on the question method "Think about other things that are similar to the thing or event you want to think about (e.g., Has something similar happened in the past?)" stored in the question method DB 62, and sends it to the user I / F 10.

[0055] When a user responds to this question via I / F10 with "It gets laggy when there are a lot of people watching at the venue, which is a problem since the main users are those playing the game. I want it to be smooth all the time," then, for each item of the service usage requirements shown in Figure 7, the number of people related to the communication bandwidth, "1," is reflected in the first line of the service usage requirements, as shown in Figure 8, and the number of people related to the communication bandwidth, "2," is reflected in the second line of the service usage requirements.

[0056] Figure 9 illustrates an example of question generation based on the content of the user's response to a question. In this embodiment, as shown in Figure 9, when the user's response to the initial question, "What will you use it for?", is insufficient for extracting quality requirements, the generation of questions to the user is repeated until the user's response is sufficient for extracting quality requirements. As a result, when the user's response becomes sufficient for extracting quality requirements, the insufficient quality requirements can be articulated.

[0057] Figure 10 is a block diagram showing an example of the hardware configuration of a data processing device according to one embodiment of the present invention. In the example shown in Figure 10, the data processing device 100 according to the above embodiment is composed of, for example, a server computer or a personal computer, and has a hardware processor 111A such as a CPU (Central Processing Unit). A program memory 111B, a data memory 112, an input / output interface 113, and a communication interface 114 are connected to this hardware processor 111A via a bus 115.

[0058] The communication interface 114 includes, for example, one or more wireless communication interface units, enabling the transmission and reception of information with the communication network. As the wireless interface, for example, an interface employing a low-power wireless data communication standard such as a wireless LAN (Local Area Network) is used.

[0059] The input / output interface 113 is connected to an input device 200 and an output device 300, which are attached to the data processing device 100 and used by users or the like.

[0060] The input / output interface 113 can capture operation data entered by a user or the like through an input device 200 such as a keyboard, touch panel, or touchpad, and output the output data to an output device 300, including a display device using liquid crystal or organic EL (electroluminescence), for display. The input device 200 and output device 300 may be devices built into the data processing device 100, or they may be input and output devices of other information terminals that can communicate with the data processing device 100 via a network.

[0061] The program memory 111B is a non-temporary tangible storage medium in which a non-volatile memory that can be written to and read at any time, such as an HDD (Hard Disk Drive) or SSD (Solid State Drive), is used in combination with another non-volatile memory such as ROM (Read Only Memory), and can store programs necessary for executing various control processes, etc., according to one embodiment.

[0062] The data memory 112 is a tangible storage medium that, for example, uses a combination of the above-mentioned non-volatile memory and volatile memory such as RAM (Random Access Memory), and can be used to store various data or information acquired and created during the process of various operations.

[0063] A data processing device 100 according to one embodiment of the present invention may be configured as a data processing device having the parts shown in Figure 1 as the software processing function unit.

[0064] The storage devices used as work memories by each part of the data processing device 100, or on which each DB shown in Figure 1 is provided, may be configured using the data memory 112 shown in Figure 10. However, the storage areas configured in these storage devices are not essential to the data processing device 100, and may be areas provided in external storage media such as USB (Universal Serial Bus) memory, or in storage devices such as database servers located in the cloud.

[0065] Each of the processing functions in the above-described section can be implemented by having the hardware processor 111A read and execute a program stored in the program memory 111B. Some or all of these processing functions may be implemented in various other forms, including application-specific integrated circuits (ASICs) or field-programmable gate arrays (FPGAs).

[0066] Furthermore, the methods described in each embodiment can be stored as programs (software means) that can be executed by a computer on recording media such as magnetic disks (floppy disks, hard disks, etc.), optical disks (CD-ROMs, DVDs, MOs, etc.), and semiconductor memories (ROMs, RAMs, flash memories, etc.), and can also be transmitted and distributed via communication media. The programs stored on the media also include configuration programs that configure the computer to run software means (including not only the execution program but also tables or data structures). The computer implementing this device reads the program recorded on the recording media and, if necessary, constructs the software means using the configuration program, and executes the above-described processes by controlling the operation of this software means. Note that the recording media referred to in this specification are not limited to those for distribution, but also include storage media such as magnetic disks or semiconductor memories provided inside the computer or in devices connected via a network.

[0067] It should be noted that the present invention is not limited to the embodiments described above, and can be modified in various ways during implementation without departing from its essence. Furthermore, each embodiment may be combined as appropriate, and in that case, the combined effects can be obtained. Moreover, the above embodiments include various inventions, and various inventions can be extracted by selecting combinations from the multiple constituent elements disclosed. For example, if the problem can be solved and effects obtained even if some constituent elements are deleted from all the constituent elements shown in the embodiment, then the configuration with these deleted constituent elements can be extracted as an invention.

[0068] 100...Data Processing Unit 10...User Interface 20...Service Usage Status Input Unit 30...Quantification Requirements Calculation Unit 31...Service Category Identification Unit 32...Service Category-Specific Requirements Indicator Identification Unit 33...Indicator-Specific Acquisition Range Identification Unit 34...Service Requirements Calculation Unit 40...Data Management Unit 41...Service-to-Service Category DB 42...Service Category-Specific Requirements Indicator DB 50...Requirement Extraction Degree Calculation Unit 60...Question Generation Unit 61...Mentioned Word Extraction Unit 62...Question Method DB 63...Question Text Generation Unit 70...Service Requirements Output Unit

Claims

1. A data processing device comprising: an input unit that receives input from a user of the service regarding the circumstances of the service usage; a calculation unit that calculates requirements for the provision of the service to the user based on the results of the input from the input unit and information stored in a storage device that stores information indicating the relationship between the circumstances of the service usage and the requirements for the provision of the service to the user; and a generation unit that generates a question requesting additional input from the user regarding the circumstances of the service usage when the requirements calculated by the calculation unit are inappropriate.

2. The data processing apparatus according to claim 1, wherein the generation unit generates a question to the user requesting additional input, which extracts words included in the results of the input by the input unit and prompts the user to make the extracted words into relatively clear words, when the requirements calculated by the calculation unit are not appropriate.

3. The data processing apparatus according to claim 1, wherein the generation unit generates a question requesting additional input from the user, prompting the user to add an explanatory text regarding the circumstances of using the service when the requirements calculated by the calculation unit are not appropriate.

4. The data processing apparatus according to claim 1, wherein the generation unit generates an initial question prompting the user to input information regarding the circumstances of using the service prior to the initial input by the input unit, and the input unit receives input regarding the circumstances of using the service as a response to the initial question.

5. A data processing method performed by a data processing device, comprising: an input unit of the data processing device receiving input from a user of the service regarding the circumstances of the service use; a calculation unit of the data processing device calculating requirements for the provision of the service to the user based on the results of the input from the input unit and information stored in a storage device that stores information indicating the relationship between the circumstances of the service use and the requirements for the provision of the service to the user; and a generation unit of the data processing device generating a question requesting additional input from the user regarding the circumstances of the service use when the requirements calculated by the calculation unit are inappropriate.

6. A data processing program that causes a processor to function as each part of the data processing apparatus according to any one of claims 1 to 4.

Images