Information processing device

Abstract

Notify the user that the information they are entering is new. [Solution] The information processing device includes an extraction means for extracting a first feature vector from information input by a user, a calculation means for calculating the distance between the first feature vector and a second feature vector extracted from each of the constituent elements contained in the document data stored in the database, and an output means for outputting information indicating that the information input by the user is new and not stored in the database, if there is no second feature vector within a predetermined distance from the first feature vector.

Description

Technical Field

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

Background Art

[0002] As this type of apparatus, there are known ones that utilize accumulated knowledge. For example, Patent Document 1 discloses a technique for retrieving desired information from knowledge including questions received from questioners and answers to the questions based on instructions from viewers.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In a chatbot using a machine-learned model, a user inputs various information to the chatbot. At this time, it is not easy for the user himself / herself to notice the usefulness of the information input by the user. Therefore, even if the information input by the user is novel, there is a risk that the opportunity to utilize the information will be lost.

[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 notifying that the information input by a user is novel.

Means for Solving the Problems

[0006] An information processing device according to one aspect of this disclosure includes: an extraction means for extracting a first feature vector from information input by a user; a calculation means for calculating the distance between the first feature vector and a second feature vector extracted from each of the components contained in document data stored in a database; and an output means for outputting information indicating that the information input by the user is new and not stored in the database, if there is no second feature vector within a predetermined distance from the first feature vector. [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 a 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, the functional configuration of the information processing device 10 according to the embodiment will be described while referring to FIG. 2. 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 a device that determines whether information input by a user is new and notifies the result. The information processing apparatus 10 includes, as components for realizing its functions, an information acquisition unit 210, a first extraction unit 220, a second extraction unit 230, a distance calculation unit 240, and a notification information output unit 250. Note that each of the information acquisition unit 210, the first extraction unit 220, the second extraction unit 230, the distance calculation unit 240, and the notification information output unit 250 may be a processing block realized by the arithmetic device 110 described above.

[0022] The information acquisition unit 210 is configured to be able to acquire information input by a user (hereinafter, appropriately referred to as "input information"). For example, the information acquisition unit 210 may acquire, as input information, information input by the user to a chatbot or the like. Alternatively, the information acquisition unit 210 may acquire, as input information, information included in a file created by the user (for example, a document file such as a technical document).

[0023] The first extraction unit 220 is configured to be able to extract a first feature vector from the input information acquired by the information acquisition unit 210. The first feature vector is a vector indicating the features of the input information. When the input information includes a plurality of pieces of information, the first extraction unit 220 may extract a first feature vector for each of them. That is, the first extraction unit 220 may extract a plurality of first feature vectors from one piece of input information. Note that the method for extracting the first feature vector from the input information is not particularly limited. The first extraction unit 220 may extract the first feature vector using, for example, a machine-learned model. This model may be a model that takes the input information as input and outputs the first feature vector.

[0024] The second extraction unit 230 is configured to extract second feature vectors from knowledge (various information) stored in the knowledge database (DB) 300. More specifically, the second extraction unit 230 extracts second feature vectors from each of the constituent elements (e.g., text, images, etc.) included in the document data stored in the knowledge DB 200. However, the second extraction unit 230 may also extract second feature vectors from knowledge other than document data. A second feature vector is a vector that indicates the characteristics of the knowledge stored in the knowledge DB 200. The second extraction unit 230 may extract multiple second feature vectors from a single piece of knowledge. If multiple pieces of knowledge are stored in the knowledge DB 300, the second extraction unit 230 may extract second feature vectors from each of the multiple pieces of knowledge. The method for extracting second feature vectors from knowledge is not particularly limited. The second extraction unit 230 may, for example, use a machine learning model to extract second feature vectors. This model may be one that takes knowledge as input and outputs a second feature vector.

[0025] The distance calculation unit 240 is configured to calculate the distance between the first feature vector calculated by the first extraction unit 220 and the second feature vector extracted by the second extraction unit 230. In other words, the distance calculation unit 240 calculates the similarity or association between the first feature vector and the second feature vector. If multiple first and second feature vectors are extracted, the distance calculation unit 240 only needs to calculate the distance for each combination of the multiple first feature vectors and each of the multiple second feature vectors.

[0026] The notification information output unit 250 is configured to determine whether or not a second feature vector exists within a predetermined distance from the first feature vector, based on the distance calculated by the distance calculation unit 240. Here, the predetermined distance is a threshold for determining whether or not the input information is new (i.e., whether or not information with a high degree of similarity or relevance to the input information has already been accumulated). For example, if a second feature vector exists within the predetermined distance from the first feature vector, it can be determined that information similar to the input information has already been accumulated (i.e., the input information is not new). On the other hand, if a second feature vector does not exist within the predetermined distance from the first feature vector, it can be determined that information similar to the input information has not yet been accumulated (i.e., the input information is new). If a second feature vector does not exist within the predetermined distance from the first feature vector, the notification information output unit 250 outputs information indicating that the input information is new (hereinafter referred to as "notification information" as appropriate). The notification information output unit 250 may output notification information to the user who entered the input information. For example, the notification information output unit 250 may display the notification information using a display. Alternatively, the notification information output unit 250 may output the notification information as sound using a speaker.

[0027] The notification information may include information indicating the new portion of the input information. In this case, the notification information output unit 250 may output information that presents only the new portion of the input information to the user. Alternatively, the notification information output unit 250 may display the entire input information and then highlight the new portion (for example, by adding color or underlining it) so that the user can identify the new portion.

[0028] The Knowledge DB 300 is configured as a database that stores various types of information as knowledge. For example, the Knowledge DB 300 may be configured to store information previously acquired by the Information Acquisition Unit 210 as knowledge. Alternatively, the Knowledge DB 300 may be configured to store information acquired through a different route than the Information Acquisition Unit 210 as knowledge. The Knowledge DB 300 may also store the second feature vector extracted from the stored knowledge. For example, the Knowledge DB 300 may be configured to store pairs of knowledge and second feature vectors. In this case, the second extraction unit 230 does not need to have a function to extract the second feature vector; it only needs to be configured to acquire the second feature vector stored in the Knowledge DB 300.

[0029] Although Figure 2 shows an example where the knowledge DB 300 is located outside the information processing device 10, the information processing device 10 may also be configured to include the knowledge DB 300.

[0030] (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.

[0031] As shown in Figure 3, when the operation of the information processing device 10 according to the embodiment is started, first the information acquisition unit 210 acquires input information entered by the user (step S101). Then, the first extraction unit 220 extracts a first feature vector from the input information acquired by the information acquisition unit 210 (step S102). In addition, the second extraction unit 230 extracts a second feature vector from the knowledge stored in the knowledge DB 300 (step S103). If the knowledge DB 300 has stored a second feature vector, the second extraction unit 230 acquires the second feature vector stored in the knowledge DB 300.

[0032] Next, the distance calculation unit 240 calculates the distance between the first feature vector extracted by the first extraction unit 220 and the second feature vector extracted by the second extraction unit 230 (step S104). Then, the notification information output unit 250 determines, based on the distance calculated by the distance calculation unit 240, whether or not there is a second feature vector that is within a predetermined distance from the first feature vector (step S105).

[0033] If there is no second feature vector within a predetermined distance from the first feature vector (step S105: NO), the notification information output unit 250 outputs notification information to the user (step S106). On the other hand, if there is a second feature vector within a predetermined distance from the first feature vector (step S105: YES), the process in step S106 described above is omitted. That is, the notification information output unit 250 does not output notification information to the user.

[0034] (Technical effects) Next, the technical effects obtained by the information processing device 10 according to this embodiment will be described.

[0035] As explained in Figures 1 to 3, in the information processing device 10 according to this embodiment, the distance between a first feature vector extracted from the input information and a second feature vector extracted from the accumulated knowledge is calculated. Then, based on the calculated distance between the vectors, it is determined whether or not the input information is new. In this way, it is possible to determine whether or not the input information entered by the user is new and notify the user that the input information is new. Therefore, it is possible to prevent the user from noticing the novelty of the input information and losing the opportunity to utilize the information.

[0036] The novelty of the information determined by the information processing device 10 according to this embodiment may be, for example, novelty in the context of a patent. Specifically, the predetermined distance used by the notification information output unit 250 may be set based on novelty in the context of a patent. In this case, it is possible to determine whether or not the input information entered by the user includes technology that can be utilized as a patent. Therefore, the user can be notified that there is a way to utilize the input information as a patent.

[0037] The embodiments of the invention derived from the above-described embodiments are described below.

[0038] An information processing device according to one aspect of this disclosure includes: an extraction means for extracting a first feature vector from information input by a user; a calculation means for calculating the distance between the first feature vector and a second feature vector extracted from each of the components included in document data stored in a database; and an output means for outputting information indicating that the information input by the user is new and not stored in the database, when no second feature vector exists within a predetermined distance from the first feature vector. In the above embodiment, the "first extraction unit 220" corresponds to an example of the "extraction means," the "distance calculation unit 240" corresponds to an example of the "calculation means," and the "notification information output unit 250" corresponds to an example of the "output means."

[0039] In the information processing apparatus according to the above embodiment, the output means may output information indicating the portion of the information input by the user that has been determined to be new. In this way, the user can be notified of which specific portion has been determined to be new.

[0040] 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]

[0041] 10... Information processing device, 110... Calculation unit, 120... Memory device, 130... Communication device, 140... Input device, 150... Output device, 210... Information acquisition unit, 220... First extraction unit, 230... Second extraction unit, 240... Distance calculation unit, 250... Notification information output unit, 300... Knowledge DB

Claims

1. An extraction means for extracting a first feature vector from information input by the user, A calculation means for calculating the distance between the first feature vector and a second feature vector extracted from each of the constituent elements contained in the document data stored in the database, An output means that outputs information indicating that the information entered by the user is new and not stored in the database, when there is no second feature vector within a predetermined distance from the first feature vector, An information processing device equipped with the following features.

2. The output means outputs information indicating the portion of the information input by the user that has been determined to be new. The information processing apparatus according to claim 1.

Images