Information processing apparatus, information processing method, and information processing program

Abstract

To support processing related to information provision.SOLUTION: An information processing apparatus according to the present application includes a generation unit, a replacement unit, and an output unit. The generation unit is configured to generate an explanatory text explaining a weather overview using a trained model that has been trained to generate the explanatory text including a blank area defined as an insertion location of information of a plurality of constituent elements constituting the weather information from weather information indicating a content of the weather. The replacement unit replaces the blank area with information of the component by using information extracted from the weather information according to a rule base generated in advance. The output unit outputs the commentary text in which the blank area is replaced with information corresponding to each element related to the weather.SELECTED DRAWING: Figure 6

Description

[Technical Field]

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

[0002] Conventionally, information providing technologies that provide various information to users have been known. As an example of such information providing technologies, a technology has been proposed that, when a question written in natural language is received, outputs an answer to the question by natural language processing (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2005-332271 Summary of the Invention [Problem to be solved by the invention]

[0004] However, conventional techniques have room for improvement in supporting processes related to information provision.

[0005] The present application has been made in view of the above, and aims to support processing related to information provision. [Means for solving the problem]

[0006] The information processing device according to the present application includes a generation unit, a replacement unit, and an output unit. The generation unit generates commentary text that explains the general state of the weather using a trained model that has been trained to generate commentary text including blank areas defined as insertion points for information of multiple components that make up the weather information from weather information that indicates the details of the weather. The replacement unit replaces the blank areas with information of the components using information extracted from the weather information according to a rule base that is generated in advance. The output unit outputs the commentary text in which the blank areas have been replaced with information of the components. [Effects of the Invention]

[0007] According to one aspect of the embodiment, processing related to information provision can be supported. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram illustrating an example of information processing according to the embodiment. [Figure 2] FIG. 2 is a diagram illustrating an example of a learning method according to the embodiment. [Figure 3] FIG. 3 is a diagram illustrating an example of an explanatory sentence generated by the trained model according to the embodiment. [Figure 4] FIG. 4 is a diagram for explaining an example of a process for replacing a blank area included in an explanatory text with information on components that make up weather information according to the embodiment. [Figure 5] FIG. 5 is a diagram illustrating an example of the system configuration of the information processing system according to the embodiment. [Figure 6] FIG. 6 is a diagram illustrating an example of the configuration of an information processing device according to the embodiment. [Figure 7] FIG. 7 is a diagram showing an outline of a replacement dictionary stored in a replacement dictionary storage unit according to the embodiment. [Figure 8] FIG. 8 is a flowchart illustrating an example of a procedure of information processing executed by the information processing device according to the embodiment. [Figure 9]FIG. 9 is a hardware configuration diagram illustrating an example of a computer that realizes the functions of the information processing device according to the embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, modes for implementing an information processing device, an information processing method, and an information processing program according to the present application (hereinafter referred to as "embodiments") will be described in detail with reference to the drawings. Note that the information processing device, the information processing method, and the information processing program according to the present application are not limited to these embodiments. Furthermore, the respective embodiments can be appropriately combined within the scope of not causing any contradiction in the processing content. Furthermore, the same components in the following embodiments will be assigned the same reference numerals, and redundant explanations will be omitted.

[0010] [Embodiment] [1. An example of information processing] An example of information processing according to the embodiment will be described below with reference to the drawings: Fig. 1 is a diagram for explaining an example of information processing according to the embodiment.

[0011] The information processing according to the embodiment is realized by an information processing system SYS (see, for example, FIG. 5) including the terminal device 10 shown in FIG. 1 and the information processing device 100 shown in FIG. 1. The terminal device 10 and the information processing device 100 are each connected to a network N (see, for example, FIG. 5) by wire or wirelessly. The terminal device 10 and the information processing device 100 can communicate with other devices through the network N.

[0012] 1 transmits weather information indicating the details of the weather to the information processing device 100 in response to an operation by a user U (step S11). For example, the weather information is information used to generate an explanatory text that explains the general state of the weather, and corresponds to information on weather forecasts for every predetermined time period (for example, every hour) or information on weekly weather forecasts.

[0013] When the information processing device 100 receives weather information from the terminal device 10, it generates an explanatory text explaining the general weather conditions from the received weather information using a trained model that has been trained to generate explanatory text including blank areas defined as insertion points for information of multiple components that make up the weather information (step S12).

[0014] The information processing device 100 also replaces blank areas with information about the constituent elements corresponding to the blank areas using information extracted from the weather information according to a rule base generated in advance (step S13).The information processing device 100 also outputs explanatory text in which the blank areas have been replaced with the information about the constituent elements, and transmits the explanatory text to the terminal device 10 (step S14).

[0015] Conventionally, when a natural language processing model is used to generate explanatory text that explains the general weather conditions from weather information, values ​​such as temperature and precipitation, particularly numerical values ​​such as the difference from the previous day, may not be properly reflected. Therefore, this application describes an example in which, when an explanatory text that explains the general weather conditions is generated from weather information, values ​​such as temperature and precipitation, particularly numerical values ​​indicating the difference from the previous day, are properly reflected, thereby supporting the process of providing weather information.

[0016] Note that the information processing according to the embodiment is not particularly limited to the case shown in Fig. 1. The terminal device 10 may transmit only location information to the information processing device 100. In this case, the information processing device 100 acquires weather information corresponding to the location information received from the terminal device 10 from another system, and generates an explanatory text that explains the general state of the weather using the acquired weather information. Then, the information processing device 100 transmits the generated explanatory text to the terminal device 10 together with the weather information.

[0017] An example of a learning method for generating a trained model used for information processing by the information processing device 100 according to the embodiment will be described below with reference to Fig. 2. Fig. 2 is a diagram for explaining an example of the learning method according to the embodiment. In the following description, when there is no need to particularly distinguish between the learning data according to the embodiment, the data will be collectively referred to as "learning data SD."

[0018] As learning samples used in machine learning to generate a trained model, multiple pieces of training data SD, such as training data SD1, training data SD2, and training data SD3 shown in Fig. 2, are prepared in advance. The contents of the training data SD will be specifically explained below using the training data SD1. The training data SD1 is configured by associating weather forecast information SD1-1 with weather overview information SD1-2.

[0019] As shown in Fig. 2, weather forecast information SD1-1 includes, for example, hourly weather information such as sunny, rainy, or cloudy, and hourly weather-related numerical information such as temperature, precipitation, humidity, and wind speed. Note that Fig. 2 is an example of weather forecast information SD1-1, and is not limited to hourly weather information, and may also be weekly weather forecast information.

[0020] Furthermore, the weather overview information SD1-2 is information that serves as a sample sentence explaining the weather overview. As shown in FIG. 2, the weather overview information SD1-2 is text information that includes blank areas with different labels for each weather-related element, such as temperature, precipitation, humidity, and wind speed, in a topic extracted as a weather overview from the weather forecast information SD1-1. An example of a label according to the embodiment is described below. For example, [MASK:A] represents a label corresponding to the maximum temperature, [MASK:B] represents a label corresponding to the difference between the maximum temperature and the previous day, [MASK:C] represents a label corresponding to the minimum temperature, [MASK:D] represents a label corresponding to the difference between the minimum temperature and the previous day, [MASK:E] represents a label corresponding to the probability of morning precipitation, and [MASK:F] represents a label corresponding to the probability of afternoon precipitation. Note that the blank areas do not necessarily have to be blank, and may simply specify the insertion location of each weather-related element.

[0021] The information processing device 100 uses learning data SD1, which associates weather forecast information SD1-1 with weather overview information SD1-2, to learn a model that inputs weather information and generates explanatory text through machine learning. The information processing device 100 also similarly learns models for other learning data SD, such as learning data SD2 and learning data SD3. In this way, the information processing device 100 creates a trained model M-2 that inputs weather information and generates explanatory text. For example, a natural language processing model such as BERT (Bidirectional Encoder Representations from Transformers) can be used as the learning model M-1.

[0022] An example of an explanatory sentence generated using the trained model shown in Fig. 2 will be described below with reference to Fig. 3. Fig. 3 is a diagram illustrating an example of an explanatory sentence generated by the trained model according to the embodiment.

[0023] When the information processing device 100 receives weather information TD to be processed from the terminal device 10, it inputs the received weather information TD into the trained model M-2 and obtains explanatory text TX that explains the general weather conditions output from the trained model M-2. As shown in Fig. 3, the explanatory text TX is output in a state where it includes blank areas in the topic explaining the general weather conditions, with different labels assigned to each weather-related element, such as temperature, precipitation, humidity, and wind speed.

[0024] An example of a process for replacing blank areas included in the commentary text TX shown in Fig. 3 with information about the components that make up the weather information will be described below with reference to Fig. 4. Fig. 4 is a diagram for explaining an example of a process for replacing blank areas included in the commentary text TX according to the embodiment with information about the components that make up the weather information.

[0025] 4, the information processing device 100 has a substitution dictionary storage unit 122. In the substitution dictionary (an example of a "rule base") stored in the substitution dictionary storage unit 122, information on labels to be added to blank areas included in the commentary text TX is associated in advance with information indicating components that correspond to the corresponding labels among the components that make up the weather information.

[0026] The information processing device 100 obtains, from the weather information TD according to the substitution dictionary, information corresponding to the component corresponding to the corresponding label among the components constituting the weather information TD, and uses the obtained information to replace blank areas contained in the commentary text TX with information about the component corresponding to the blank area. The information about the components constituting the weather information TD includes values ​​indicating the difference between the previous day and values ​​corresponding to temperature, precipitation, humidity, wind speed, etc. Note that the information about the components constituting the weather information TD may include information other than temperature, precipitation, humidity, and wind speed. For example, it may include information about various indices provided by other systems that provide weather information. The various indices may include year-round indices such as a laundry index and an ultraviolet index, as well as seasonal indices such as a discomfort index and a water pipe freezing index.

[0027] For example, in the case shown in Figure 4, [MASK:A] is replaced with a number indicating the maximum temperature, [MASK:B] is replaced with a number indicating the difference between the maximum temperature and the previous day, [MASK:C] is replaced with a number indicating the minimum temperature, [MASK:D] is replaced with a number indicating the difference between the minimum temperature and the previous day, and [MASK:G] is replaced with a number indicating the probability of precipitation in the morning and afternoon.

[0028] 3 and 4, the information processing device 100 according to the embodiment generates explanatory text TX indicating the general state of the weather from weather information TD, which is processing information, using the trained model M-2, which is a natural language processing model, and subsequently complements the insertion of numerical values ​​corresponding to the components of the weather information, which is a weak point of the natural language processing model, based on a substitution dictionary, which is a rule base generated in advance. This allows the information processing device 100 to generate appropriate explanatory text indicating the general state of the weather and support processing related to the provision of weather information.

[0029] [2. System Configuration] The configuration of the information processing system SYS according to the embodiment will be described in detail below with reference to Fig. 5. Fig. 5 is a diagram showing an example of the system configuration of the information processing system SYS according to the embodiment.

[0030] As shown in Fig. 5, the information processing system SYS according to the embodiment includes a terminal device 10 and an information processing device 100. Note that Fig. 5 merely shows an example of the configuration of the information processing system SYS according to the embodiment, and the information processing system SYS may include a plurality of terminal devices 10, or may include other devices (systems) that provide weather information.

[0031] The terminal device 10 and the information processing device 100 are connected to a network N by wire or wirelessly. Each of the terminal device 10 and the information processing device 100 can communicate with other devices via the network N.

[0032] The network N includes, for example, a WAN (Wide Area Network) such as the Internet, and a mobile communication network such as LTE (Long Term Evolution), 4G (4th Generation), or 5G (5th Generation: fifth generation mobile communication system).

[0033] The terminal device 10 is connected to a network N by short-range wireless communication such as a mobile communication network, Bluetooth (registered trademark), or wireless LAN (Local Area Network), and can communicate with other devices such as the information processing device 100 through the network N.

[0034] The terminal device 10 is used by a user U (see, for example, FIG. 1) who acquires and uses explanatory text that explains the general weather conditions from the information processing device 100. The terminal device 10 may be, for example, a notebook PC (Personal Computer), a desktop PC, a smartphone, or a tablet PC.

[0035] To obtain explanatory text that explains the general weather conditions, the user U operates the terminal device 10 to send weather information to the information processing device 100. At this time, the user U may use a predetermined API (Application Programming Interface) to access a tool prepared in advance for obtaining explanatory text and send the weather information through this tool, or may send the weather information through a predetermined web page prepared in advance for obtaining explanatory text using a web browser. Note that the terminal device 10 may be pre-installed with a user application program that has various functions for obtaining explanatory text. In this case, the user U can send the weather information through the user application program.

[0036] Furthermore, the terminal device 10 can display content provided by the information processing device 100, for example, using a tool or a web browser. When the terminal device 10 receives control information for realizing information display processing from the information processing device 100, the terminal device 10 realizes the display processing in accordance with the control information.

[0037] The control information is written in, for example, a script language such as JavaScript (registered trademark), a style sheet language such as CSS (Cascading Style Sheets), a programming language such as Java (registered trademark), a markup language such as HTML (HyperText Markup Language), etc. Note that a predetermined application itself delivered from the information processing device 100 or the like may be regarded as control information.

[0038] The information processing device 100 executes various processes for providing information on explanatory text that explains the general weather conditions as information processing according to the embodiment. The information processing device 100 is typically a server device, but may be realized by a mainframe, a workstation, or the like. Furthermore, when the information processing device 100 is realized by a server device, it may be realized by a single server device, or may be realized by a cloud system in which multiple server devices and multiple storage devices operate in cooperation with each other.

[0039] [3. Equipment configuration] An example of the functional configuration of the information processing device 100 according to the embodiment will be described below with reference to Fig. 6. Fig. 6 is a diagram showing an example of the configuration of the information processing device 100 according to the embodiment. As shown in Fig. 6, the information processing device 100 according to the embodiment has a communication unit 110, a storage unit 120, and a control unit 130.

[0040] (Communication unit 110) The communication unit 110 is realized by, for example, a communication module or a network interface card (NIC). The communication unit 110 is connected to a network N by wire or wirelessly. The information processing device 100 transmits and receives information to and from other devices such as the information processing device 100 via the network N.

[0041] (Storage unit 120) The storage unit 120 stores, for example, programs and data used for control and calculation by the control unit 130. For example, the storage unit 120 is realized by a semiconductor memory element such as a random access memory (RAM) or a flash memory, or a storage device such as a hard disk or an optical disk. For example, the storage unit 120 has a weather information storage unit 121 and a substitution dictionary storage unit 122. Note that the storage unit 120 is not particularly limited to the example shown in FIG. 6 and can store data necessary for executing the information processing according to the embodiment, such as storing a trained model (for example, trained model M-2 shown in FIG. 2), as appropriate.

[0042] (Weather information storage unit 121) The weather information storage unit 121 stores weather information that serves as learning data for training a model that receives weather information and generates explanatory text that explains the general state of the weather. The weather information stored in the weather information storage unit 121 can be acquired, for example, from a predetermined server that provides weather information. The weather information storage unit 121 may also store information that associates weather information with explanatory text.

[0043] (Substitution dictionary storage unit 122) The substitution dictionary storage unit 122 stores a substitution dictionary for replacing blank areas included in the commentary text TX with information on the components of the weather information. Fig. 7 is a diagram showing an outline of the substitution dictionary stored in the substitution dictionary storage unit 122 according to the embodiment.

[0044] 7, the substitution dictionary stored in the substitution dictionary storage unit 122 has an item for "label" and an item for "component." These items in the substitution dictionary are associated with each other.

[0045] The "Label" field stores different identification information for each component that makes up the weather information, for blank areas included in the explanatory text. The "Component" field stores information about the component that makes up the weather information.

[0046] For example, the information processing device 100 (the replacement unit 133 described later) refers to a replacement dictionary to obtain information corresponding to the label from the corresponding weather information, and uses the obtained information to replace a blank area included in the explanatory text with information about a component corresponding to the label attached to the blank area.

[0047] (control unit 130) The control unit 130 is a controller, and is realized by a CPU (Central Processing Unit), MPU (Micro Processing Unit), etc., executing various programs (for example, a route search application (an example of an information processing program)) stored in the internal storage device of the information processing device 100 using the RAM as a working area.

[0048] Furthermore, the control unit 130 may be realized by an integrated circuit such as an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or a general purpose graphic processing unit (GPGPU).

[0049] As shown in FIG. 6, the control unit 130 has a learning unit 131, a generating unit 132, a replacing unit 133, and an output unit 134, and these units realize or execute the functions and actions of the information processing described below.

[0050] Note that control unit 130 may have an internal configuration divided into multiple processing units that realize or execute the functions and actions of information processing described below. Furthermore, control unit 130 is not limited to the configuration shown in Fig. 6, and may have other configurations as long as they perform the information processing described below, and may have other functional units other than those shown in Fig. 6.

[0051] (Learning Section 131) The learning unit 131 uses learning data that associates weather information indicating the details of the weather with text information that serves as a sample sentence explaining the general weather conditions corresponding to the weather information, including blank areas with different labels for each component of the weather information, to learn a model that inputs weather information and generates explanatory sentences through machine learning.

[0052] The learning unit 131 receives training data from an operator, for example, in which weather information and explanatory sentences serving as sample explanations of the weather information are associated with each other. The weather information included in the training data is created by processing text information created by the operator from past weather forecasts (e.g., weather, temperature, region, and other various information) into a state suitable for the training data, for example, using a tokenizer. The explanatory sentences included in the training data are created by processing text information, including blank areas with different labels assigned to each component of the weather information (e.g., temperature, probability of precipitation, etc.), into a state suitable for the training data, for example, using a tokenizer, as insertion points for information corresponding to the components that make up the weather information. The learning unit 131 then uses the training data to train a model that generates explanatory sentences from the weather forecast information, such as, "Today is a refreshingly sunny day, and feels comfortable. The maximum temperature is [MASK:A]°C (change from the previous day: [MASK:B]), and the minimum temperature is [MASK:C]°C (change from the previous day: [MASK:D])."

[0053] Furthermore, the learning unit 131 can use a natural language processing model such as BERT (Bidirectional Encoder Representations from Transformers) as a learning model (for example, learning model M-1 shown in FIG. 2).

[0054] (Generation unit 132) The generation unit 132 generates explanatory text that explains the general weather conditions from weather information indicating the weather content specified by the user U as the processing target, using a trained model that has been trained to generate explanatory text that includes blank areas defined as insertion points for information of the components that make up the weather information.

[0055] (Replacement part 133) The replacement unit 133 uses information extracted from the weather information in accordance with a replacement dictionary (an example of a "pre-generated rule base") stored in the replacement dictionary storage unit 122 to replace the blank area with information about the component corresponding to the blank area.

[0056] For example, the replacement unit 133 acquires information about the components corresponding to the labels attached to the blank areas from the weather information according to a replacement dictionary that pre-associates the labels attached to the blank areas included in the explanatory text with the elements corresponding to the labels, and uses the acquired information to replace the blank areas with information about the components corresponding to the blank areas.

[0057] Specifically, when there is an explanatory sentence such as "Today is a refreshingly clear day, and it feels comfortable. The maximum temperature is [MASK: A]°C (difference from the previous day: [MASK: B]), and the minimum temperature is [MASK: C]°C (difference from the previous day: [MASK: D]). The probability of precipitation is [MASK: G]% in both the morning and afternoon. It feels chilly in the morning and evening, so let's go out...", the replacement unit 133 refers to the replacement dictionary and identifies that the element corresponding to the label [MASK: A] attached to the blank area in the explanatory sentence is "maximum temperature." Then, the replacement unit 133 obtains the numerical value "24" corresponding to the identified "maximum temperature" from the weather information and replaces the part of [MASK: A] with "24." The replacement unit 133 can perform similar replacement for other labels.

[0058] (output unit 134) The output unit 134 outputs the commentary text in which the blank areas have been replaced with the information of the constituent elements by the replacement unit 133, and transmits the information of the output commentary text to the terminal device 10 via the communication unit 110.

[0059] 4. Processing Procedure According to the Embodiment The following describes the procedure of information processing executed by the information processing device 100 according to the embodiment. Fig. 8 is a flowchart showing an example of the procedure of information processing executed by the information processing device 100 according to the embodiment. The procedure of processing shown in Fig. 8 is executed by the control unit 130 of the information processing device 100. The procedure of processing shown in Fig. 8 is repeatedly executed while the information processing device 100 is operating.

[0060] As shown in Figure 8, the generation unit 132 generates an explanatory sentence explaining the general weather conditions from weather information indicating the weather content specified by user U as the processing target, using a trained model that has been trained to generate explanatory sentences including blank areas defined as insertion points for numerical values, which are information on the components that make up the weather information (step S101).

[0061] Furthermore, the replacement unit 133 replaces blank areas included in the commentary text with the numerical values ​​of the components corresponding to the blank areas, using information extracted from the weather information according to a rule base (replacement dictionary) generated in advance (step S102).

[0062] Furthermore, the output unit 134 outputs the explanatory text in which the blank areas are replaced with numerical values ​​(step S103), and the processing procedure shown in FIG. 8 ends.

[0063] [5. Hardware Configuration] The information processing device 100 according to the embodiment described above is realized, for example, by a computer 1000 configured as shown in Fig. 9. Fig. 9 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device 100 according to the embodiment.

[0064] The computer 1000 is connected to an output device 1010 and an input device 1020, and has a configuration in which an arithmetic unit 1030, a primary storage device 1040, a secondary storage device 1050, an output IF (Interface) 1060, an input IF 1070, and a network IF 1080 are connected by a bus 1090.

[0065] The arithmetic device 1030 operates based on programs stored in the primary storage device 1040 and secondary storage device 1050, programs read from the input device 1020, and the like, and executes various processes. The primary storage device 1040 is a memory device, such as a RAM, that temporarily stores data used by the arithmetic device 1030 for various calculations. The secondary storage device 1050 is a storage device in which data used by the arithmetic device 1030 for various calculations and various databases are registered, and is realized by a ROM (Read Only Memory), HDD, flash memory, or the like.

[0066] The output IF 1060 is an interface for transmitting information to be output to an output device 1010 that outputs various types of information, such as a monitor or a printer, and is realized by a connector conforming to a standard such as USB (Universal Serial Bus), DVI (Digital Visual Interface), or HDMI (High Definition Multimedia Interface), etc. The input IF 1070 is an interface for receiving information from various input devices 1020, such as a mouse, keyboard, and scanner, and is realized by, for example, USB.

[0067] The input device 1020 may be a device that reads information from an optical recording medium such as a CD (Compact Disc), a DVD (Digital Versatile Disc), or a PD (Phase Change Rewritable Disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory. The input device 1020 may also be an external storage medium such as a USB memory.

[0068] The network IF 1080 receives data from other devices via the network N and sends it to the arithmetic device 1030, and also transmits data generated by the arithmetic device 1030 to other devices via the network N.

[0069] The arithmetic unit 1030 controls the output device 1010 and the input device 1020 via the output IF 1060 and the input IF 1070. For example, the arithmetic unit 1030 loads a program from the input device 1020 or the secondary storage device 1050 onto the primary storage device 1040 and executes the loaded program.

[0070] For example, when the computer 1000 functions as the information processing device 100 according to the embodiment, the arithmetic device 1030 of the computer 1000 executes a program (for example, a route search application AP) loaded onto the primary storage device 1040, thereby realizing the same functions as the control unit 130. That is, the arithmetic device 1030 cooperates with the program (for example, a route search application AP) loaded onto the primary storage device 1040 to realize the processing by the information processing device 100 according to the embodiment.

[0071] [6. Other] In the above embodiment, an example has been described in which the information processing device 100 learns a model that outputs text information in which numerical values ​​such as temperature and probability of precipitation are left blank as explanatory text explaining the general weather conditions, but the present invention is not particularly limited to this example. For example, the information processing device 100 may learn a model that outputs text information in which parts of a string indicating weather such as "clear," "cloudy," or "rainy," or parts of a string indicating physical sensations such as "hot" or "cool," are left blank.

[0072] Furthermore, in the above-described embodiment, the information processing in which the information processing device 100 outputs explanatory text that explains the general state of the weather can also be similarly applied to the case where information other than the general state of the weather is output.

[0073] Furthermore, among the processes described in the above embodiments, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically using a known method. In addition, the information including the processing procedures, specific names, various data and parameters shown in the above documents and drawings can be changed as desired unless otherwise specified.

[0074] Furthermore, the components of each device shown in the figure are functional concepts and do not necessarily have to be physically configured as shown. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of them can be functionally or physically distributed and integrated in any unit depending on various loads, usage conditions, etc. For example, the substitution unit 133 and output unit 134 of the control unit 130 may be functionally integrated.

[0075] Furthermore, the above-described embodiments can be combined as appropriate within the scope of not causing any contradiction in the processing content.

[0076] The above describes in detail the embodiments of the present application based on several drawings, but these are merely examples, and the present invention can be implemented in other forms that include the embodiments described in the Disclosure of the Invention section and that have been modified and improved in various ways based on the knowledge of those skilled in the art.

[0077] Furthermore, the above-mentioned "section, module, unit" can be read as "means" or "circuit," etc. For example, a control section can be read as control means or a control circuit.

[0078] [7. Effects] The information processing device 100 according to the embodiment includes a generation unit 132, a replacement unit 133, and an output unit 134. The generation unit 132 generates commentary text that explains the general state of the weather using a trained model that has been trained to generate commentary text including blank areas defined as insertion points for information of multiple components that make up the weather information from weather information that indicates the details of the weather. The replacement unit 133 replaces the blank areas with information of the components using information extracted from the weather information according to a rule base that is generated in advance. The output unit outputs the commentary text in which the blank areas have been replaced with information of the components.

[0079] The information processing device 100 according to the embodiment further includes a learning unit 131. The learning unit 131 uses learning data that associates weather information with text information that serves as a sample of a sentence explaining the general weather condition corresponding to the weather information and includes blank areas with different labels attached to each component, to learn a model that inputs weather information and outputs explanatory sentences through machine learning.

[0080] The generating unit 132 generates an explanation sentence including a blank area with a label from the weather information. The replacing unit 133 obtains information on the component corresponding to the label attached to the blank area from the weather information according to a rule base in which labels are previously associated with the component corresponding to the label, and replaces the blank area with the information on the component using the obtained information.

[0081] Furthermore, the information on the components that make up the weather information includes values ​​indicating the difference between the temperature, precipitation, humidity, and wind speed from the previous day. Note that the information on the components that make up the weather information TD may include information other than temperature, precipitation, humidity, and wind speed. For example, it may include information on various indices provided by other systems that provide weather information. The various indices may include year-round indices such as a laundry index and an ultraviolet index, and seasonal indices such as a discomfort index and a water pipe freezing index.

[0082] 3 and 4, the information processing device 100 according to the embodiment generates explanatory text TX indicating the general state of the weather from weather information TD, which is processing information, using a trained model M-2, which is a natural language processing model, and subsequently complements the insertion of numerical values ​​corresponding to components of the weather information, which is a weak point of the natural language processing model, based on a substitution dictionary, which is a rule base generated in advance. This allows the information processing device 100 to generate appropriate explanatory text indicating the general state of the weather and support processing related to the provision of weather information.

[0083] Furthermore, the above-described effects can also be realized by the processing executed by each of the above-described units, or by any combination of the processing executed by each unit. [Explanation of symbols]

[0084] SYS Information Processing System N Network 10 Terminal Equipment 100 Information processing device 110 Communications Department 120 Storage section 121 Weather information storage unit 122 Substitution dictionary storage unit 130 Control Unit 131 Learning Department 132 Generation part 133 Substitution part 134 Output section

Claims

1. a generation unit that generates an explanatory sentence that explains the general state of the weather from weather information indicating the details of the weather using a trained model that has been trained to generate an explanatory sentence including a blank area defined as an insertion point for information of a plurality of components that make up the weather information; and a replacement unit that replaces the blank area with information of the component element by using information extracted from the weather information according to a rule base that is generated in advance; an output unit that outputs the commentary text in which the blank area is replaced with information about the component; An information processing device comprising:

2. a learning unit that uses learning data in which the weather information is associated with text information including blank areas and in which different labels are assigned to the respective components, to learn a model that inputs the weather information and outputs the explanatory text by machine learning; 2. The information processing apparatus according to claim 1, further comprising:

3. The generation unit generating the commentary text including the blank area to which the label is attached from the weather information; The substitution portion is According to the rule base in which the labels are previously associated with the components corresponding to the labels, information on the components corresponding to the labels is acquired from the weather information, and the blank area is replaced with information on the components using the acquired information.

2. The information processing apparatus according to claim 1, wherein:

4. The information of the components constituting the weather information is Contains values ​​indicating the difference between the previous day and the corresponding values ​​for temperature, precipitation, humidity, and wind speed 4. The information processing device according to claim 1, wherein the information processing device is a computer.

5. An information processing method carried out by a computer, comprising: a generation process for generating an explanatory sentence that explains the general state of the weather from weather information indicating the details of the weather using a trained model that has been trained to generate an explanatory sentence including a blank area defined as an insertion point for information of a plurality of components that make up the weather information; a replacement step of replacing the blank area with information of the component element using information extracted from the weather information according to a rule base generated in advance; an output step of outputting the commentary text in which the blank area has been replaced with information about the component; An information processing method comprising:

6. On the computer, a generation procedure for generating an explanatory sentence that explains the general state of the weather from weather information indicating the details of the weather using a trained model that has been trained to generate an explanatory sentence including a blank area defined as an insertion point for information of a plurality of components that make up the weather information; a replacement step of replacing the blank areas with information of the components using information extracted from the weather information according to a rule base generated in advance; an output step of outputting the commentary text in which the blank area has been replaced with information about the component; An information processing program characterized by causing the program to execute the above.

Images