Information processing apparatus

Abstract

The present application aims to output an appropriate answer to input including a professional term. An information processing apparatus includes: an input information acquisition unit that acquires input information input by a user; an estimation unit that estimates an amount of deviation of a near-synonym that paraphrases a professional term from the professional term, in a case where the near-synonym is included in the input information; a specification unit that determines the professional term corresponding to the near-synonym based on a paraphrase candidate prepared in advance, in a case where the amount of deviation is smaller than a prescribed threshold value; a generation unit that generates an answer to the input information, and generates the answer based on information related to the determined professional term, in a case where the professional term is determined; and an output unit that outputs the answer to the user.

Description

Technical Field

[0001] This invention relates to the technical field of an information processing device. Background Technology

[0002] As such a device, there is a known device that uses machine learning models or the like to recognize user input and execute various controls based on the recognition results. For example, Patent Document 1 discloses a technique that selects technical terms contained in the input sound from a candidate string and outputs a command corresponding to the selected candidate string for controlling the controlled object.

[0003] Patent Document 1: Japanese Patent Application Publication No. 2024-126054 Summary of the Invention

[0004] Technical terms can sometimes be expressed differently depending on the user. That is, even the same technical term can sometimes be expressed in different ways. In such cases, depending on how the user inputs the technical term, it may be impossible to accurately identify which term corresponds to which technical term. Moreover, if the technical term cannot be accurately identified, it may be impossible to output an appropriate response to the user's input.

[0005] The present invention was made in view of the above-mentioned problems, and its objective is to provide an information processing apparatus that can output an appropriate response to the input even when the user's input contains technical terms.

[0006] An information processing apparatus according to one aspect of the present invention comprises: an input information acquisition unit that acquires input information input by a user; an estimation unit that, when the input information contains a synonym that paraphrases a technical term, estimates the deviation between the synonym and the technical term; a selection unit that, when the deviation is less than a predetermined threshold, determines the technical term corresponding to the synonym based on pre-prepared paraphrasing candidates; a generation unit that generates a response to the input information, and, when the technical term is determined, generates the response based on information related to the determined technical term; and an output unit that outputs the response to the user. Attached Figure Description

[0007] Figure 1 This is a block diagram illustrating the hardware structure of the information processing device involved in the implementation method.

[0008] Figure 2 This is a block diagram illustrating the functional structure of the information processing apparatus involved in the implementation method.

[0009] Figure 3It is a flowchart illustrating the process of generating a response based on the information processing apparatus involved in the implementation method.

[0010] Figure 4 It is a flowchart illustrating the process of modifying candidate update operations based on the information processing apparatus involved in the implementation method. Detailed Implementation

[0011] Hereinafter, embodiments of the information processing device will be described with reference to the accompanying drawings. The device will be described as an information processing apparatus mounted on a vehicle.

[0012] (Hardware structure)

[0013] First, refer to Figure 1 The hardware structure of the information processing device involved in the implementation method will be described. Figure 1 This is a block diagram illustrating the hardware structure of the information processing device involved in the implementation method.

[0014] exist Figure 1 In this embodiment, the information processing apparatus 10 is configured to include a computing unit 110, a storage unit 120, a communication unit 130, an input unit 140, and an output unit 150. The computing unit 110, storage unit 120, communication unit 130, input unit 140, and output unit 150 are interconnected via a data bus. All the devices included in the information processing apparatus 10 can be mounted in a vehicle. Alternatively, some of the devices included in the information processing apparatus 10 can be mounted in a vehicle, while the remaining devices can be located outside the vehicle.

[0015] The arithmetic processing unit 110 is configured to perform various arithmetic operations in the information processing unit 10. The arithmetic processing unit 110 may have a processor. The arithmetic processing unit 110 may have a single processor or multiple processors. That is, the arithmetic processing unit 110 may have more than one processor. Furthermore, the processor may be a multi-core processor. In the case where the arithmetic processing unit 110 has a single processor that functions as a multi-core processor, it can be said that the arithmetic processing unit 110 logically has multiple processors.

[0016] The processor included in the computing device 110 may be at least one of a central processing unit (CPU), a graphics processing unit (GPU), a field-programmable gate array (FPGA), and a tensor processing unit (TPU).

[0017] Storage device 120 may be at least one of random access memory (RAM), read-only memory (ROM), hard disk drive, magneto-optical disk drive, solid-state drive (SSD), and optical disk array. That is, storage device 120 may be implemented by a single device or by multiple devices.

[0018] Storage device 120 is capable of storing desired data. The computer program CP executed by the arithmetic unit 110 can be stored in storage device 120. When the arithmetic unit 110 executes the computer program CP, storage device 120 can temporarily store data temporarily used by the arithmetic unit 110.

[0019] Furthermore, the computer program CP can be recorded on a computer-readable and non-transitory recording medium. In this case, the computer program CP can be stored in the storage device 120 by reading the recording medium using a recording medium reading device (not shown) included in the information processing device 10. Additionally, at least one of optical discs, magnetic media, magneto-optical discs, semiconductor memory, and any medium capable of storing other programs can be used as the recording medium. The computer program CP can also be obtained from an external (not shown) device outside the information processing device 10 via the communication device 130. In other words, the computer program CP can be downloaded from an external device to the storage device 120 of the information processing device 10.

[0020] The arithmetic unit 110 (e.g., a processor) can perform the processing to be performed by the information processing unit 10 together with the storage device 120 storing the computer program CP (in other words, together with the storage device 120 and the computer program CP stored in the storage device 120). For example, the arithmetic unit 110 can implement logical function blocks for performing the processing to be performed by the information processing unit 10 within the arithmetic unit 110 (e.g., within the processor) by executing the computer program CP.

[0021] The communication device 130 is configured to communicate with external devices of the information processing device 10. Furthermore, the communication device 130 can perform both wired and wireless communication.

[0022] Input device 140 is a device capable of accepting information input from an external source to information processing device 10. Input device 140 may include user-operable devices (e.g., keyboard, mouse, touch panel, etc.) of information processing device 10. Input device 140 may include, for example, a recording medium reading device capable of reading information recorded on a recording medium removable from information processing device 10, such as a Universal Serial Bus (USB) memory. Furthermore, when information is input to information processing device 10 via communication device 130 (in other words, when information processing device 10 obtains information via communication device 130), communication device 130 can function as an input device.

[0023] Output device 150 is a device capable of outputting information to the outside of information processing device 10. Output device 150 may include a display device capable of outputting visual information such as characters and images. Output device 150 may also include a speaker capable of outputting auditory information such as sound. Output device 150 may be configured to output the aforementioned information to other devices (e.g., control information of other devices). Output device 150 may, for example, output information to a recording medium removable from information processing device 10, such as a USB memory. Furthermore, when information processing device 10 outputs information via communication device 130, communication device 130 may function as an output device.

[0024] <Functional Structure>

[0025] Next, refer to Figure 2 The functional structure of the information processing device 10 involved in the implementation method will be explained. Figure 2 This is a block diagram illustrating the functional structure of the information processing apparatus involved in the implementation method.

[0026] exist Figure 2 In this embodiment, the information processing apparatus 10 is configured to output response information based on user input. The information processing apparatus 10 includes an input information acquisition unit 210, an additional information acquisition unit 220, a deviation estimation unit 230, a terminology specification unit 240, a paraphrase candidate database (DB) 250, an answer generation unit 260, an answer output unit 270, a synonym collection unit 280, and a paraphrase candidate update unit 290 as components for implementing its functions. Furthermore, the input information acquisition unit 210, the additional information acquisition unit 220, the deviation estimation unit 230, the terminology specification unit 240, the answer generation unit 260, the answer output unit 270, the synonym collection unit 280, and the paraphrase candidate update unit 290 can each be a processing block implemented by the aforementioned computing device 110. Moreover, the paraphrase candidate DB 250 can be implemented by the aforementioned storage device 120.

[0027] The input information acquisition unit 210 is configured to acquire input information entered by the user. The input information acquisition unit 210 can acquire user input via the input device 140. For example, the input information acquisition unit 210 can acquire text data entered by the user as input information. Alternatively, the input information acquisition unit 210 can acquire voice data emitted by the user as input information. In this case, the input information acquisition unit 210 may have a voice recognition function that converts voice data into text data. Furthermore, the input information acquisition unit 210 may have a function that extracts words from text data.

[0028] The additional information acquisition unit 220 is configured to acquire information other than the input information acquired by the input information acquisition unit 210. Specifically, the additional information acquisition unit 220 can acquire user information related to the user. User information may be, for example, the user's personal information (name, etc.) or attribute information (gender or age, etc.). Alternatively, the additional information acquisition unit 220 can acquire vehicle information related to the vehicle used by the user (in other words, the vehicle equipped with the information processing device 10). Vehicle information may be information that allows determination of the current status of the vehicle or the surrounding environment. Vehicle information can be acquired, for example, using various sensors mounted on the vehicle.

[0029] The deviation estimation unit 230 is configured to estimate the deviation between the synonym and the technical term when the input information acquired by the input information acquisition unit 210 includes a synonym that paraphrases a technical term. The deviation can be estimated as follows: the easier it is to recall the corresponding technical term from the synonym, the smaller the deviation; the harder it is to recall, the larger the deviation. The deviation estimation unit 230 can, for example, use a machine learning model to estimate the deviation. Furthermore, the deviation estimation unit 230 can estimate the deviation between one synonym and each of multiple technical terms.

[0030] Furthermore, the deviation estimation unit 230 may have the function of determining whether the input information entered by the user contains synonyms for technical terms. In this case, the deviation estimation unit 230 may determine whether the input information contains synonyms based on user information or vehicle information obtained by the additional information acquisition unit 220. For example, the deviation estimation unit 230 may select words with a high probability of being synonyms based on the current situation estimated according to the user information or vehicle information.

[0031] If the deviation estimated by the deviation estimation unit 230 is less than a predetermined threshold, the terminology specification unit 240 determines the terminology corresponding to the synonym. The predetermined threshold is a threshold used to determine whether the deviation between the synonym and the terminology is small enough to establish their correspondence. The terminology specification unit 240 determines the terminology corresponding to the synonym based on pre-prepared paraphrasing candidates.

[0032] The paraphrase candidate DB250 is configured to store paraphrase candidates used by the terminology-specific unit 240. For example, the paraphrase candidate DB250 stores a term and multiple paraphrase candidates corresponding to that term. The terminology-specific unit 240 can search for the paraphrase candidate most similar to a synonym from the paraphrase candidates stored in the paraphrase candidate DB250, and determine the terminology corresponding to that paraphrase candidate as the terminology corresponding to the synonym.

[0033] The answer generation unit 260 is configured to generate answer information in response to user input. When a technical term is determined in the terminology-specific unit 240, the answer generation unit 260 generates the answer information based on information related to the technical term. For example, the answer generation unit 260 can generate a fixed answer corresponding to the technical term. Alternatively, the answer generation unit 260 can use Large Language Models (LLMs) to generate an answer based on the technical term. On the other hand, if no technical term is determined in the terminology-specific unit 240, the answer generation unit 260 may generate the answer information without relying on information related to the technical term. Furthermore, even if the user input does not contain a technical term, the answer generation unit 260 may generate the answer information without relying on information related to the technical term. Even without using information related to the technical term, the answer generation unit 260 may use a large language model to generate the answer information.

[0034] Furthermore, the response generation unit 260 can generate vehicle control information for controlling the vehicle, in addition to or replacing the aforementioned response information. Specifically, it can determine how the user intends to control the vehicle based on the input information provided by the user, and generate vehicle control information for actually executing that control within the vehicle. For example, the vehicle control information could be information for switching specific functions on and off within the vehicle.

[0035] The response output unit 270 is configured to output response information generated by the response generation unit 260 to the user. The response output unit 270 can output the response information via the output device 150. For example, the response output unit 270 can output the response information using a display or speaker. Furthermore, the response output unit 270 can be configured to output vehicle control information generated by the response generation unit 260. In this case, the response output unit 270 can output the vehicle control information to an electronic control unit (ECU) or similar device that controls the vehicle's operation.

[0036] The synonym collection unit 280 is configured to collect synonyms when the input information entered by the user contains synonyms of technical terms. That is, the synonym collection unit 280 is configured to extract and store (accumulate) synonyms contained in the input information. When a technical term corresponding to a synonym is determined in the technical term identification unit 240, the synonym collection unit 280 can store the synonym and the technical term in an associated manner.

[0037] The revision candidate update unit 290 is configured to update the revision candidates stored in the revision candidate DB 250 based on the synonyms collected by the synonym collection unit 280. For example, if a synonym collected by the synonym collection unit 280 is not stored in the revision candidate DB 250, the revision candidate update unit 290 can add that synonym as a new revision candidate to the revision candidate DB 250.

[0038] Furthermore, the revision candidate update unit 290 can determine users based on the personal information of users obtained by the additional information acquisition unit 220, and create revision candidates for each user. Also, the revision candidate update unit 290 can determine user attributes based on the attribute information of users obtained by the additional information acquisition unit 220, and create revision candidates for each user's attributes (e.g., revision candidates by year, etc.). Furthermore, the revision candidate update unit 290 can estimate the situation based on vehicle information obtained by the additional information acquisition unit 220, and create revision candidates corresponding to the situation (e.g., revision candidates with a high probability of use under specific situations, etc.).

[0039] (Answer generates action)

[0040] Next, refer to Figure 3 The process of generating an answer based on the information processing apparatus 10 according to the implementation method (i.e., the action of generating an answer to user input) will be described. Figure 3 It is a flowchart illustrating the process of generating a response based on the information processing apparatus involved in the implementation method.

[0041] like Figure 3 As shown, if the response generation operation based on the information processing device 10 according to the embodiment begins, the input information acquisition unit 210 first acquires the input information entered by the user (step S101). Then, the additional information acquisition unit 220 acquires user information or vehicle information (step S102).

[0042] Next, the deviation estimation unit 230 determines whether the input information contains a synonym for a technical term (step S103). Then, if the input information contains a synonym (step S103: yes), the deviation estimation unit 230 estimates the deviation between the synonym and the technical term (step S104).

[0043] Next, the terminology-specific unit 240 determines whether the deviation is less than a predetermined threshold (step S105). Then, if the deviation is less than the predetermined threshold (step S105: yes), the terminology-specific unit 240 determines the terminology corresponding to the synonym based on the paraphrasing candidates stored in the paraphrasing candidate DB250 (step S106).

[0044] Next, the response generation unit 260 determines whether the input information is related to vehicle control (step S107). Then, if the input information is not related to vehicle control (step S107: No), the response generation unit 260 generates response information corresponding to the input information (step S108). Then, the response output unit 270 outputs the generated response information to the user (step S109).

[0045] On the other hand, if the input information is related to vehicle control (step S107: Yes), the response generation unit 260 generates vehicle control information corresponding to the input information (step S110). Then, the response output unit 270 outputs the generated vehicle control information to the vehicle (step S111).

[0046] Furthermore, if the input information does not contain synonyms for technical terms (step S103: No), steps S104 to S106 are omitted. In this case, the technical term is uncertain, and the response generation unit 260 generates response information or vehicle control information. Also, if the deviation between the synonym and the technical term is greater than or equal to a predetermined threshold (step S105: No), step S106 is omitted. In this case, the technical term is uncertain, and the response generation unit 260 generates response information or vehicle control information.

[0047] (Revised description of candidate update action)

[0048] Next, refer to Figure 4 The process of updating the revision candidate based on the information processing apparatus 10 according to the embodiment (i.e., the action of updating the revision candidate stored in the revision candidate DB250) will be described. Figure 4 This is a flowchart illustrating the process of revising candidate update operations based on the information processing apparatus according to the implementation method. Furthermore, the revising candidate update operation can be executed simultaneously and in parallel with the aforementioned answer generation operation.

[0049] like Figure 4 As shown, if the revised candidate update operation based on the information processing device 10 according to the embodiment is started, the input information acquisition unit 210 first acquires the input information entered by the user (step S201). Then, the additional information acquisition unit 220 acquires user information or vehicle information (step S202).

[0050] Next, the deviation estimation unit 230 determines whether the input information contains synonyms of technical terms (step S203). Then, if the input information contains synonyms (step S203: yes), the synonym collection unit 280 collects the synonyms contained in the input information (step S204).

[0051] Next, the revision candidate update unit 290 determines whether the conditions for updating the revision candidate are met (step S205). For example, if the revision candidate update unit 290 collects synonyms that are not yet stored in the revision candidate DB250, it can determine that the conditions for updating the revision candidate are met. Alternatively, if the revision candidate update unit 290 accumulates a predetermined number of synonyms (i.e., if a sufficient number of synonyms are collected), it can determine that the conditions for updating the revision candidate are met.

[0052] If the conditions for updating the revised candidate are met (step S205: Yes), the revised candidate updating unit 290 updates the revised candidates stored in the revised candidate DB250 (step S206). On the other hand, if the conditions for updating the revised candidate are not met (step S205: No), the process of step S206 is omitted. That is, the revised candidate updating unit 290 does not update the revised candidates stored in the revised candidate DB250.

[0053] (Technical effect)

[0054] Next, the technical effects obtained by the information processing apparatus 10 according to the implementation method will be explained.

[0055] like Figures 1 to 4 As explained, in the information processing apparatus 10 according to the embodiment, when the user input includes a synonym that paraphrases a technical term, the deviation between the synonym and the technical term is estimated. Thus, based on the deviation, an appropriate method can be used to generate response information. Specifically, when the deviation is small, the technical term corresponding to the synonym can be determined, and appropriate response information based on the technical term can be generated. On the other hand, when the deviation is large, a response can be generated without relying on information related to the technical term.

[0056] Furthermore, in the information processing apparatus 10 according to the embodiment, the paraphrase candidates for determining the technical terms corresponding to synonyms are updated based on the collected data. Therefore, the more data collected, the higher the accuracy of determining the technical terms. Moreover, by creating paraphrase candidates corresponding to users or situations, the accuracy of determining the technical terms is also improved.

[0057] According to the information processing apparatus 10 of the embodiment, as described above, it is able to detect technical terms with high accuracy and output appropriate response information for the input information. As a result, it can improve user satisfaction or repeat visit rate.

[0058] The present invention is not limited to the embodiments described above, and appropriate modifications can be made without departing from the spirit or idea of ​​the invention as read in its entirety from the claims and description. Information processing apparatuses that accompany such modifications are also included within the technical scope of the present invention.

[0059] Symbol Explanation

[0060] 10-Information processing device, 110-Arithmetic device, 120-Storage device, 130-Communication device, 140-Input device, 150-Output device, 210-Input information acquisition unit, 220-Additional information acquisition unit, 230-Deviation estimation unit, 240-Specified terminology unit, 250-Revision candidate database, 260-Answer generation unit, 270-Answer output unit, 280-Synonym collection unit, 290-Revision candidate update unit.

Claims

1. An information processing device, characterized in that, have: The input information acquisition unit acquires the input information entered by the user. An estimation unit that, when the input information contains synonyms that paraphrase technical terms, estimates the deviation of the synonyms from the technical terms. A specific unit, when the deviation is less than a predetermined threshold, determines the technical term corresponding to the synonym based on pre-prepared paraphrasing candidates; A generation unit generates an answer to the input information, and, if the technical terminology is determined, generates the answer based on information related to the determined technical terminology; and The output unit outputs the answer to the user.

2. The information processing device according to claim 1, characterized in that, It also has: A collection unit that collects the synonyms contained in the input information; and The updating unit updates the paraphrase candidates based on the collected synonyms.

3. The information processing device according to claim 2, characterized in that, It also includes a user information acquisition unit, which acquires user information related to the user. The update unit updates the revision candidate for each user or for each attribute of the user based on the user information.

4. The information processing apparatus according to claim 2 or 3, characterized in that, It also includes a vehicle information acquisition unit, which acquires vehicle information related to the vehicle used by the user. The updating unit updates the revised candidate based on the conditions estimated according to the vehicle information.

5. The information processing apparatus according to any one of claims 1 to 3, characterized in that, It also includes a vehicle information acquisition unit, which acquires vehicle information related to the vehicle used by the user. When the generation unit determines, based on the vehicle information, that the input information is related to the control of the vehicle, it generates control information for controlling the vehicle, either in addition to or in place of the answer.

Images