Information processing device

Abstract

The system modifies the question to an appropriate format and generates an answer. [Solution] The information processing device includes an acquisition means for acquiring input data including a question sentence, a determination means for analyzing the input data and determining the importance of the words included in the question sentence, a deletion means for deleting unnecessary words from the question sentence whose importance is below a predetermined threshold, and an input means for inputting the question sentence from which the unnecessary words have been deleted into a model that generates an answer to the question sentence.

Description

Technical Field

[0001] This disclosure relates to the technical field of information processing apparatuses.

Background Art

[0002] As this type of apparatus, for example, a system has been proposed in which a large language model (LLM) is caused to generate query data based on a document, and a pair of the document and the query data is used for learning a search model for a chatbot (see Patent Document 1).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] When inputting a question sentence from a user to a machine-learned answer generation model, an appropriate answer may not be obtained depending on the question sentence. For example, in the case of a question sentence freely input by a user, redundant expressions due to the characteristics of the individual user may be included, which may adversely affect answer generation.

[0005] This disclosure has been made in view of the above problems, and an object thereof is to provide an information processing apparatus capable of modifying a question sentence into an appropriate form and generating an answer.

Means for Solving the Problems

[0006] An information processing device according to one aspect of this disclosure includes: acquisition means for acquiring input data including a question; determination means for analyzing the input data and determining the importance of words included in the question; deletion means for deleting unnecessary words from the question whose importance is below a predetermined threshold; and input means for inputting the question from which the unnecessary words have been deleted into a model that generates an answer to the question. [Brief explanation of the drawing]

[0007] [Figure 1] This is a block diagram showing the hardware configuration of an information processing device according to an embodiment. [Figure 2] This is a block diagram showing the functional configuration of an information processing apparatus according to an embodiment. [Figure 3] This is a flowchart showing the operation flow of the information processing device according to the embodiment. [Modes for carrying out the invention]

[0008] The following describes an embodiment of the information processing device with reference to the drawings.

[0009] (Hardware configuration) First, the hardware configuration of the information processing device according to the embodiment will be described with reference to Figure 1. Figure 1 is a block diagram showing the hardware configuration of the information processing device according to the embodiment.

[0010] In Figure 1, the information processing device 10 according to this embodiment comprises an arithmetic unit 110, a storage device 120, a communication device 130, an input device 140, and an output device 150. The arithmetic unit 110, the storage device 120, the communication device 130, the input device 140, and the output device 150 are connected to each other via a data bus.

[0011] The arithmetic unit 110 is configured to perform various arithmetic operations in the information processing device 10. The arithmetic unit 110 may have a processor. The arithmetic unit 110 may have a single processor or may have multiple processors. In other words, the arithmetic unit 110 may have one or more processors. The processor may be a multi-core processor. If the arithmetic unit 110 has a single processor that is a multi-core processor, then logically, the arithmetic unit 110 can be said to have multiple processors.

[0012] The processor in the arithmetic unit 110 may be at least one of the following: CPU (Central Processing Unit), GPU (Graphics Processing Unit), FPGA (Field Programmable Gate Array), and TPU (Tensor Processing Unit).

[0013] The storage device 120 may be at least one of the following: RAM (Random Access Memory), ROM (Read Only Memory), hard disk drive, magneto-optical disk drive, SSD (Solid State Drive), and optical disk array. In other words, the storage device 120 may be implemented by a single device or by multiple devices.

[0014] The storage device 120 is capable of storing desired data. The storage device 120 may store the computer program CP that the arithmetic unit 110 will execute. The storage device 120 may temporarily store data that the arithmetic unit 110 will use temporarily when the arithmetic unit 110 is executing the computer program CP.

[0015] The computer program CP may be recorded on a non-temporary recording medium that is readable by a computer. In this case, the computer program CP may be stored in the storage device 120 by reading the recording medium using a recording medium reading device (not shown) provided by the information processing device 10. At least one of the following may be used as the recording medium: an optical disc, a magnetic medium, a magneto-optical disc, a semiconductor memory, and any other medium capable of storing a program. The computer program CP may also be obtained from an external device (not shown) of the information processing device 10 via a communication device 130. In other words, the computer program CP may be downloaded from an external device to the storage device 120 of the information processing device 10.

[0016] The arithmetic unit 110 (for example, a processor) may execute the processing that the information processing device 10 should perform together with the memory device 120 in which the computer program CP is stored (in other words, together with the memory device 120 and the computer program CP stored in the memory device 120). For example, by the arithmetic unit 110 executing the computer program CP, a logical functional block for executing the processing that the information processing device 10 should perform may be realized within the arithmetic unit 110 (for example, within the processor).

[0017] The communication device 130 is configured to communicate with devices outside the information processing device 10. The communication device 130 may use wired communication or wireless communication.

[0018] The input device 140 is a device capable of receiving input of information to the information processing device 10 from the outside. The input device 140 may include an operating device (for example, a keyboard, a mouse, a touch panel, etc.) that can be operated by the user of the information processing device 10. The input device 140 may include a recording medium reader capable of reading information recorded on a detachable recording medium for the information processing device 10, such as a USB (Universal Serial Bus) memory. When information is input to the information processing device 10 via the communication device 130 (in other words, when the information processing device 10 acquires information via the communication device 130), the communication device 130 may function as an input device.

[0019] The output device 150 is a device capable of outputting information to the outside of the information processing device 10. The output device 150 may have a display device capable of outputting visual information such as characters and images as the above information. The output device 150 may also have a speaker capable of outputting auditory information such as sound as the above information. The output device 150 may be configured to output the above information (for example, control information of other devices, etc.) to other devices. The output device 150 may be capable of outputting information to a detachable recording medium for the information processing device 10, such as a USB memory. When the information processing device 10 outputs information via the communication device 130, the communication device 130 may function as an output device.

[0020] <Functional Configuration> Next, with reference to FIG. 2, the functional configuration of the information processing device 10 according to the embodiment will be described. FIG. 2 is a block diagram showing the functional configuration of the information processing device according to the embodiment.

[0021] In FIG. 2, the information processing apparatus 10 is configured as an apparatus that modifies a question sentence input by a user into an appropriate form and inputs it to the answer generation model 500. The information processing apparatus 10 includes, as components for realizing its functions, a question sentence acquisition unit 210, an importance determination unit 220, an unnecessary word deletion unit 230, and a question sentence input unit 240. Each of the question sentence acquisition unit 210, the importance determination unit 220, the unnecessary word deletion unit 230, and the question sentence input unit 240 may be a processing block realized by the arithmetic device 110 described above.

[0022] The question sentence acquisition unit 210 is configured to be able to acquire a question sentence input by a user. The question sentence may include natural language. The question sentence acquisition unit 210 may, for example, acquire the voice uttered by the user as the question sentence. In this case, the question sentence acquisition unit 210 may have a voice recognition function (that is, a function of converting voice data into text). Alternatively, the question sentence acquisition unit 210 may acquire text data input by the user using a keyboard or the like as the question sentence.

[0023] The importance determination unit 220 is configured to be able to determine the importance of each word included in the question sentence acquired by the question sentence acquisition unit 210. The importance determination unit 220, for example, analyzes the question sentence and decomposes it into a plurality of words. Thereafter, the importance determination unit 220 may determine the importance of each of the decomposed plurality of words. The method for determining the importance is not particularly limited. For example, the importance determination unit 220 may determine the importance of a word using entropy analysis or an attention mechanism.

[0024] The unnecessary word deletion unit 230 deletes words (hereinafter, appropriately referred to as "unnecessary words") determined to have a low importance by the importance determination unit 220 from the question sentence acquired by the question sentence acquisition unit 210. For example, the unnecessary word deletion unit 230 stores a preset threshold value, determines a word having an importance lower than the threshold value as an unnecessary word, and deletes it from the question sentence. Alternatively, the unnecessary word deletion unit 230 may determine a predetermined number of words in ascending order of low importance as unnecessary words and delete them from the question sentence.

[0025] The question input unit 240 inputs the question, from which unnecessary words have been removed by the unnecessary word removal unit 230, to the answer generation model 500 (in other words, outputs it to the answer generation model 500). The question input unit 240 may input a question that has only had unnecessary words removed to the answer generation model 500. Alternatively, the question input unit 240 may modify the question, from which unnecessary words have been removed, to make it sound more natural (for example, by rewriting it into a sentence that makes sense) before inputting it to the answer generation model 500.

[0026] The answer generation model 500 is a pre-trained model. The answer generation model 500 may be composed of, for example, a neural network. The answer generation model 500 is a model that outputs an answer to a question input from the question input unit 240. The answer output by the answer generation model 500 is output to the user (i.e., the person who entered the question). For example, the answer model 500 may be configured to output the answer using a display, speaker, etc.

[0027] Although Figure 2 shows an example where the response generation model 500 is located outside the information processing device 10, the information processing device 10 may also be configured to include the response generation model 500.

[0028] (Flow of operations) Next, the operation flow of the information processing device 10 according to the embodiment will be described with reference to Figure 3. Figure 3 is a flowchart showing the operation flow of the information processing device according to the embodiment.

[0029] As shown in Figure 3, when the operation of the information processing device 10 according to the embodiment is started, first the question text acquisition unit 210 acquires a question text from the user (step S101). Then, the importance determination unit 220 determines the importance of each word contained in the question text acquired by the question text acquisition unit 210 (step S102).

[0030] Next, the unnecessary word removal unit 230 removes unnecessary words that the importance determination unit 220 has determined to be of low importance from the question text (step S103). Then, the question text input unit 240 inputs the question text from which the unnecessary words have been removed by the unnecessary word removal unit 230 to the answer generation model 500 (step S104).

[0031] Subsequently, the response generation model 500 generates an answer to the question input from the question input unit 240 and outputs the answer to the user (step S105).

[0032] (Technical effects) Next, the technical effects obtained by the information processing device 10 according to this embodiment will be described.

[0033] As explained in Figures 1 to 3, in the information processing device 10 according to this embodiment, less important and unnecessary words are removed from the question text entered by the user. In this way, words that would negatively affect answer generation can be removed before the question text is entered into the answer generation model 500. Therefore, compared to the case where the question text is entered into the answer generation model 500 as is without removing unnecessary words, it becomes possible to obtain a more appropriate answer from the answer generation model 500.

[0034] The embodiments of the invention derived from the above-described embodiments are described below.

[0035] An information processing device according to one aspect of this disclosure includes: an acquisition means for acquiring input data including a question; a determination means for analyzing the input data and determining the importance of words included in the question; a deletion means for deleting unnecessary words from the question whose importance is below a predetermined threshold; and an input means for inputting the question from which the unnecessary words have been deleted into a model that generates an answer to the question. In the above embodiment, the "question text acquisition unit 210" corresponds to an example of the "acquisition means," the "importance determination unit 220" corresponds to an example of the "determination means," the "unnecessary word deletion unit 230" corresponds to an example of the "deletion means," and the "question text input unit 240" corresponds to an example of the "input means."

[0036] In the information processing apparatus according to the above embodiment, the determination means may determine the importance using entropy analysis or an attention mechanism. In this way, it becomes possible to easily and accurately determine the importance of the words contained in the question.

[0037] In the information processing device according to the above embodiment, the input data may be voice data input via voice. In the case of voice input, redundant expressions tend to occur depending on the wording, but according to this embodiment, it is possible to remove less important words and modify the question sentence into a more appropriate form.

[0038] This disclosure is not limited to the embodiments described above and can be modified as appropriate without contradicting the gist or idea of ​​the invention as can be inferred from the claims and the specification as a whole. Information processing devices with such modifications are also included within the technical scope of the present invention. [Explanation of symbols]

[0039] 10...Information processing unit, 110...Calculation unit, 120...Storage device, 130...Communication device, 140...Input device, 150...Output device, 210...Question text acquisition unit, 220...Importance determination unit, 230...Unnecessary word deletion unit, 240...Question text input unit, 500...Answer generation model

Claims

1. A means for obtaining input data including the question text, A determination means that analyzes the input data and determines the importance of the words contained in the question sentence, A deletion means for deleting unnecessary words whose importance is below a predetermined threshold from the aforementioned question sentence, An input means for inputting the question sentence from which the unnecessary words have been removed into a model that generates an answer to the question sentence, An information processing device equipped with the following features.

2. The determination means determines the importance using entropy analysis or an attention mechanism. The information processing apparatus according to claim 1.

3. The aforementioned input data is audio data that is input via voice. The information processing apparatus according to claim 1 or 2.

Images