Information processing device, information processing method, and recording medium

Abstract

This information processing device (1) comprises an acquisition means (50) for acquiring a plurality of elements included in series data, a calculation means (100) for simultaneously inputting the plurality of elements and calculating the relationships between the elements, and thereby calculating a likelihood ratio indicating the likelihood of a class to which the series data belongs, and a classification means (200) for classifying the series data into at least one class among a plurality of classes that are classification candidates, on the basis of the likelihood ratio. By means of such an information processing device it is possible to suitably reflect the relationships between simultaneously input elements, and to calculate an accurate likelihood ratio.

Description

Information processing device, information processing method, and recording medium

[0001] The present disclosure relates to the technical fields of an information processing device, an information processing method, and a recording medium.

[0002] One known example of this type of device is one that classifies sequential data using likelihood ratios. For example, Patent Document 1 discloses a device that sequentially acquires and analyzes multiple elements included in the sequential data to classify the sequential data into one of multiple predetermined classes.

[0003] As other related techniques, for example, Patent Document 2 discloses extracting a feature vector by performing time series integration using a joint vector. Patent Document 3 discloses estimating a log-likelihood ratio using KLIEP (Kullback-Leibler Importance Estimation Procedure), which is an estimation method that minimizes the KL distance.

[0004] International Publication No. 2020 / 194497 International Publication No. 2022 / 144992 International Publication No. 2021 / 229663

[0005] This disclosure aims to improve upon the related art discussed above.

[0006] One aspect of the information processing device disclosed herein includes an acquisition means for acquiring multiple elements included in sequence data, a calculation means for simultaneously inputting the multiple elements and calculating the relationships between the elements to calculate a likelihood ratio indicating the likelihood of a class to which the sequence data belongs, and a classification means for classifying the sequence data into at least one of multiple candidate classes based on the likelihood ratio.

[0007] One aspect of the information processing method disclosed herein involves using at least one computer to acquire multiple elements contained in sequence data, simultaneously input the multiple elements, and calculate the relationships between the elements to calculate a likelihood ratio indicating the likelihood of the class to which the sequence data belongs, and classifying the sequence data into at least one of multiple candidate classes based on the likelihood ratio.

[0008] One aspect of the recording medium of this disclosure is a recording medium having recorded thereon a computer program for causing at least one computer to execute an information processing method, which includes acquiring multiple elements included in sequence data, inputting the multiple elements simultaneously and calculating the relationships between the elements to calculate a likelihood ratio indicating the likelihood of a class to which the sequence data belongs, and classifying the sequence data into at least one of multiple candidate classes based on the likelihood ratio.

[0009] 1 is a block diagram showing the hardware configuration of an information processing device according to a first embodiment. FIG. 2 is a block diagram showing the functional configuration of the information processing device according to the first embodiment. FIG. 3 is a flowchart showing the flow of operation of the information processing device according to the first embodiment. FIG. 4 is a graph showing an example of a likelihood ratio calculated by the information processing device according to the first embodiment, together with a comparative example. FIG. 5 is a conceptual diagram showing an example of non-contiguous elements that are simultaneously input in an information processing device according to a second embodiment. FIG. 6 is a block diagram showing the configuration of a self-attention mechanism used in an information processing device according to a third embodiment. FIG. 7 is a conceptual diagram showing a method for calculating a likelihood ratio in the information processing device according to the third embodiment. FIG. 8 is a conceptual diagram showing a method for calculating a likelihood ratio in an information processing device according to a comparative example. FIG. 9 is a conceptual diagram showing integration of outputs by an information processing device according to a fourth embodiment.

[0010] Hereinafter, embodiments of an information processing device, an information processing method, and a recording medium will be described with reference to the drawings.

[0011] First Embodiment An information processing apparatus according to a first embodiment will be described with reference to FIGS. 1 to 4. FIG.

[0012] (Hardware Configuration) First, the hardware configuration of the information processing apparatus according to the first embodiment will be described with reference to Fig. 1. Fig. 1 is a block diagram showing the hardware configuration of the information processing apparatus according to the first embodiment.

[0013] 1 , an information processing device 10 according to the first embodiment includes a processor 11, a RAM (Random Access Memory) 12, a ROM (Read Only Memory) 13, and a storage device 14. The information processing device 10 may further include an input device 15 and an output device 16. The processor 11, RAM 12, ROM 13, storage device 14, input device 15, and output device 16 are connected to each other via a data bus 17.

[0014] The processor 11 loads a computer program. For example, the processor 11 is configured to load a computer program stored in at least one of the RAM 12, the ROM 13, and the storage device 14. Alternatively, the processor 11 may load a computer program stored in a computer-readable storage medium using a storage medium reading device (not shown). The processor 11 may acquire (i.e., load) the computer program from a device (not shown) located outside the information processing device 10 via a network interface. The processor 11 controls the RAM 12, the storage device 14, the input device 15, and the output device 16 by executing the loaded computer program. In particular, in this embodiment, when the processor 11 executes the loaded computer program, a functional block that performs class classification based on likelihood ratios is realized within the processor 11. In other words, the processor 11 may function as a controller that executes each control in the information processing device 10.

[0015] The processor 11 may be configured as, for example, a central processing unit (CPU), a graphics processing unit (GPU), a field-programmable gate array (FPGA), a demand-side platform (DSP), an application-specific integrated circuit (ASIC), or a quantum processor. The processor 11 may be configured as one of these, or may be configured to use multiple processors in parallel.

[0016] The RAM 12 temporarily stores computer programs executed by the processor 11. The RAM 12 temporarily stores data that the processor 11 temporarily uses while it is executing the computer programs. The RAM 12 may be, for example, a dynamic random access memory (D-RAM) or a static random access memory (SRAM). Alternatively, other types of volatile memory may be used instead of the RAM 12.

[0017] The ROM 13 stores computer programs executed by the processor 11. The ROM 13 may also store fixed data. The ROM 13 may be, for example, a programmable read-only memory (PROM) or an erasable read-only memory (EPROM). Alternatively, other types of non-volatile memory may be used instead of the ROM 13.

[0018] The storage device 14 stores data that is to be saved long-term by the information processing device 10. The storage device 14 may operate as a temporary storage device for the processor 11. The storage device 14 may include, for example, at least one of a hard disk device, a magneto-optical disk device, an SSD (Solid State Drive), and a disk array device.

[0019] The input device 15 is a device that receives input instructions from a user of the information processing device 10. The input device 15 may include, for example, at least one of a keyboard, a mouse, and a touch panel. The input device 15 may be configured as a mobile terminal such as a smartphone or a tablet. The input device 15 may also be, for example, a device that includes a microphone and is capable of voice input.

[0020] The output device 16 is a device that outputs information related to the information processing device 10 to the outside. For example, the output device 16 may be a display device (e.g., a display) that can display information related to the information processing device 10. The output device 16 may also be a speaker or the like that can output information related to the information processing device 10 as audio. The output device 16 may be configured as a mobile terminal such as a smartphone or a tablet. The output device 16 may also be a device that outputs information in a format other than an image. For example, the output device 16 may be a speaker that outputs information related to the information processing device 10 as audio.

[0021] 1 shows an example of an information processing device 10 including multiple devices, but all or some of the functions may be realized by a single device. Such an information processing device may be configured to include only the above-mentioned processor 11, RAM 12, and ROM 13, and the other components (i.e., the storage device 14, input device 15, output device 16, etc.) may be provided by an external device connected to the information processing device 10. Furthermore, some of the calculation functions of the information processing device 10 may be realized by an external device (e.g., an external server, a cloud, etc.).

[0022] (Functional Configuration) Next, the functional configuration of the information processing device 10 according to the first embodiment will be described with reference to Fig. 2. Fig. 2 is a block diagram showing the functional configuration of the information processing device according to the first embodiment.

[0023] 2, the information processing device 10 according to the first embodiment is a device that performs class classification of input sequence data, and is configured to include, as components for realizing its functions, a data acquisition unit 50, a likelihood ratio calculation unit 100, and a class classification unit 200. Each of the data acquisition unit 50, the likelihood ratio calculation unit 100, and the class classification unit 200 may be a processing block realized by, for example, the above-mentioned processor 11 (see FIG. 1).

[0024] The data acquisition unit 50 is configured to acquire multiple elements included in the sequence data. The data acquisition unit 50 may acquire data directly from any data acquisition device (e.g., a camera, a microphone, etc.), or may read data previously acquired by a data acquisition device and stored in storage, etc. When acquiring data from a camera, the data acquisition unit 50 may be configured to acquire data from each of multiple cameras. The elements of the sequence data acquired by the data acquisition unit 50 are configured to be output to the likelihood ratio calculation unit 100. Note that sequence data is data including multiple elements arranged in a predetermined order, and an example of this is time-series data. More specific examples of sequence data include, but are not limited to, video data, audio data, or subdivided image data.

[0025] The likelihood ratio calculation unit 100 is configured to calculate a likelihood ratio based on multiple elements acquired by the data acquisition unit 50. Note that the "likelihood ratio" here is an index indicating the likelihood of a class to which sequence data belongs. The likelihood ratio calculation unit 100 calculates the likelihood ratio by calculating the relationship between multiple elements. Furthermore, the likelihood ratio calculation unit 100 according to this embodiment is particularly configured to calculate the likelihood ratio by simultaneously inputting multiple elements and calculating the relationship between each element. For example, when elements are sequentially acquired by the data acquisition unit 50, the likelihood ratio calculation unit 100 may simultaneously input all elements acquired up to the current time to calculate the likelihood ratio. A specific calculation method when multiple elements are simultaneously input will be described in detail in another embodiment described later.

[0026] The classification unit 200 is configured to classify sequential data based on the likelihood ratio calculated by the likelihood ratio calculation unit 100. The classification unit 200 selects at least one class to which the sequential data belongs from among multiple candidate classes. The candidate classes may be preset. Alternatively, the candidate classes may be appropriately set by a user or appropriately set based on the type of sequential data being handled. For example, the multiple classes may be set as a class indicating that a face included in video data is a real face (i.e., a biological face) and a class indicating that a face is a fake face (e.g., a face in a photograph or a 3D mask). In this way, the information processing device can be used as an impersonation detection device. Note that the number of candidate classes is not limited to two and may be three or more classes.

[0027] The information processing device 10 may be configured with a learning unit (not shown). Specifically, the information processing device 10 may be configured to have a function of performing learning related to likelihood ratio calculation. The information processing device 10 learns by, for example, inputting training data prepared in advance. This training data may be configured as a set of, for example, sequence data and information on the correct class to which the sequence data belongs (i.e., correct data). When training the information processing device 10, each parameter of the information processing device 10 may be optimized, for example, so that the loss function calculated by inputting the training data is reduced.

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

[0029] 3, when the information processing device 10 starts operating, the data acquisition unit 50 first acquires elements included in the sequence data (step S11). The data acquisition unit 50 outputs the acquired elements of the sequence data to the likelihood ratio calculation unit 100.

[0030] Next, the likelihood ratio calculation unit 100 simultaneously inputs the multiple elements acquired by the data acquisition unit 50 and calculates likelihood ratios (step S12). For example, when video data is acquired as sequence data, the likelihood ratio calculation unit 100 may simultaneously input multiple frames of the video data and calculate likelihood ratios. By simultaneously inputting multiple elements, a likelihood ratio that takes into account the mutual relationships between the multiple elements is calculated. The likelihood ratio calculation unit 100 outputs the calculated likelihood ratios to the class classification unit 200.

[0031] Next, the classification unit 200 performs classification based on the calculated likelihood ratio (step S13). Classification may determine one class to which the sequence data belongs, or may determine multiple classes to which the sequence data is likely to belong. The classification unit 200 may have a function to output the classification result. For example, the classification unit 200 may output the classification result to a display or the like. Alternatively, the classification unit 200 may output the classification result as sound via a speaker or the like.

[0032] If the calculated likelihood ratio does not exceed a predetermined threshold (i.e., a threshold for determining which class to classify), the classification unit 200 may calculate the likelihood ratio again without performing classification (i.e., without determining which class to classify into). In this case, the data acquisition unit 50 may acquire new elements included in the sequence data, and a new likelihood ratio may be calculated. For example, the elements acquired so far and the newly acquired element may be simultaneously input to calculate a new likelihood ratio.

[0033] (Technical Effects) Next, technical effects obtained by the information processing device 10 according to the first embodiment will be described with reference to Fig. 4. Fig. 4 is a graph showing an example of a likelihood ratio calculated by the information processing device according to the first embodiment, together with a comparative example.

[0034] In Figure 4, it is preferable that the likelihood ratio used for class classification gradually changes in a predetermined direction as the number of samples (i.e., input elements) increases. However, in the comparative example in which multiple elements are not input simultaneously, the likelihood ratio plateaus even as the number of samples increases (i.e., the likelihood ratio stops changing). One of the reasons for the likelihood ratio plateauing is, for example, the inability to properly reflect the relationship between multiple elements. Specifically, in the comparative example, the acquired elements are input one by one in sequence, which makes it impossible to consider the relationship between data that are far apart, resulting in the likelihood ratio plateauing. While this type of likelihood ratio plateau does not occur in all cases, if it does occur, it may be difficult to perform appropriate class classification.

[0035] However, in the information processing device 10 according to the first embodiment, likelihood ratios are calculated by inputting multiple elements simultaneously and calculating the relationships between the elements. In this way, likelihood ratios that appropriately reflect the relationships between the elements input simultaneously can be calculated. Therefore, the information processing device 10 according to the first embodiment can calculate likelihood ratios more accurately than when multiple elements are not input simultaneously.

[0036] Second Embodiment An information processing device 10 according to a second embodiment will be described with reference to Fig. 5. Note that the second embodiment differs from the first embodiment only in some of the operations, and other parts may be the same as the first embodiment. Therefore, the following will describe in detail the parts that differ from the first embodiment, and will omit a description of other overlapping parts as appropriate.

[0037] (Input of non-contiguous elements) First, a plurality of elements used to calculate likelihood ratios in the information processing device 10 according to the second embodiment will be described with reference to Fig. 5. Fig. 5 is a conceptual diagram showing an example of non-contiguous elements that are simultaneously input in the information processing device according to the second embodiment.

[0038] As shown in Fig. 5, in the information processing device 10 according to the second embodiment, non-consecutive elements (i.e., elements separated from each other) among a plurality of elements included in sequence data are simultaneously input, and a likelihood ratio is calculated by the input of the element x １ ~x ７ Of these, x １ , x ４ , x ６ are simultaneously input to the likelihood ratio calculation unit 100. For example, when video data is acquired as sequence data, in the information processing device 10 according to the second embodiment, multiple frames that are not consecutive in time series (in other words, discrete frames excluding frames between them) are simultaneously input to the likelihood ratio calculation unit. Then, the likelihood ratio calculation unit 100 calculates likelihood ratios from the multiple non-consecutive frames that have been input.

[0039] In the example shown in Fig. 5, all the elements to be input are discontinuous, but discontinuous and continuous elements may be input at the same time. In other words, it is not necessary for all the input elements to be discontinuous, and as long as at least one element among the input elements is discontinuous, the technical effect described below can be obtained accordingly. For example, in the example shown in Fig. 5, １ ~x ７ Of these, x １ , x ２ , and x ３ (consecutive elements) and x ５ (non-contiguous elements) may be input at the same time.

[0040] (Technical Effects) Next, technical effects obtained by the information processing device 10 according to the second embodiment will be described.

[0041] As described with reference to Figure 5, the information processing device 10 according to the second embodiment calculates likelihood ratios by simultaneously inputting discontinuous elements (i.e., elements that are distant from each other in the sequence data). In this way, it is possible to calculate likelihood ratios taking into account the relationships between distant elements. This makes it possible to calculate more accurate likelihood ratios compared to when only consecutive elements are simultaneously input (i.e., when only the relationships between consecutive elements are considered).

[0042] Third Embodiment An information processing device 10 according to a third embodiment will be described with reference to Figures 6 to 8. Note that the third embodiment differs only in some of the operations from the first and second embodiments described above, and other parts may be similar to the first and second embodiments. Therefore, the following will describe in detail the parts that differ from the embodiments already described, and will omit a description of other overlapping parts as appropriate.

[0043] (Self-Attention Mechanism) First, the self-attention mechanism used in the information processing device 10 according to the third embodiment will be described with reference to Fig. 6. Fig. 6 is a block diagram showing the configuration of the self-attention mechanism used in the information processing device according to the third embodiment.

[0044] 6, the information processing device 10 according to the third embodiment calculates likelihood ratios using a self-attention mechanism. The self-attention mechanism uses feature quantities Q (Query), K (Key), and V (Value). These feature quantities may be extracted from each element obtained from sequence data.

[0045] The self-attention mechanism first calculates the matrix product of Q (query) and K (key). At this time, the self-attention mechanism may perform a process of normalizing the calculated matrix product. For example, the self-attention mechanism may perform a normalization process using a softmax function.

[0046] Next, the self-attention mechanism calculates the matrix product of Q (query) and K (key) and the matrix product of V (value). The calculated matrix product becomes the output of the self-attention mechanism. Note that the self-attention mechanism may perform a predetermined restoration process or residual process on the calculated matrix product.

[0047] (Likelihood ratio calculation using self-attention mechanism) Next, likelihood ratio calculation using the above-mentioned self-attention mechanism will be described with reference to Fig. 7. Fig. 7 is a conceptual diagram showing a method for calculating likelihood ratios in an information processing device according to the third embodiment.

[0048] As shown in FIG. 7, in the information processing device 10 according to the third embodiment, multiple elements are input to the self-attention mechanism simultaneously. １ ~x ５ In the self-attention mechanism, the relationship between multiple elements is calculated, and as a result, y １ ~y ５ Specifically, the output y １ ~y ５ Each of the following is x １ ~x ５ The likelihood ratio calculation unit 100 calculates the output y １ ~y ５ The likelihood ratio is calculated from a plurality of outputs. A method for calculating the likelihood ratio from a plurality of outputs will be described in another embodiment below.

[0049] (Technical Effects) Next, technical effects obtained by the information processing device 10 according to the third embodiment will be described with reference to Fig. 8. Fig. 8 is a conceptual diagram showing a method for calculating likelihood ratios in an information processing device according to a comparative example.

[0050] 8, the information processing device according to the comparative example is configured to input a plurality of elements one by one in order to calculate likelihood ratios. １ When is entered, x １ As an output based on １１ Then, the element x ２ When is entered, the entered x ２ and the previous output y １１ and as output based on １２ In this way, in the information processing device according to the comparative example, calculations are repeated based on the input elements and the outputs up to the previous time.

[0051] However, in the information processing device according to the comparative example, since elements are input one by one, the influence of past elements may be weakened. For example, in the example shown in FIG. １５ The first input element x in １ The effect of the previous input x５ This situation may cause the likelihood ratio to plateau, as explained with reference to FIG.

[0052] However, in the information processing device 10 according to the third embodiment, likelihood ratios are calculated by simultaneously inputting multiple elements into the self-attention mechanism. In this way, likelihood ratios can be calculated that appropriately reflect the relationships between the simultaneously input elements. In other words, because all elements are calculated simultaneously, it is possible to prevent the influence of previously input elements from becoming smaller, as in the comparative example of FIG. 8 . Therefore, it is possible to calculate more accurate likelihood ratios. While the present embodiment has exemplified an example in which a self-attention mechanism is used, similar technical effects can also be obtained when using a similar mechanism, such as an MLP-mixer.

[0053] Fourth Embodiment An information processing device 10 according to a fourth embodiment will be described with reference to Fig. 9. The fourth embodiment describes a more specific example of the operation of the third embodiment described above, and the device configuration and overall operation may be similar to those of the third embodiment. Therefore, the following will describe in detail the differences from the embodiments already described, and will omit a description of other overlapping parts as appropriate.

[0054] (Output Integration Process) First, the output integration process (specifically, the process of integrating outputs from the self-attention mechanism) executed by the information processing device 10 according to the fourth embodiment will be described with reference to Fig. 9. Fig. 9 is a conceptual diagram showing the integration of outputs by the information processing device according to the fourth embodiment.

[0055] As shown in FIG. 9 , in the information processing device 10 according to the fourth embodiment, multiple elements are simultaneously input to the self-attention mechanism, and multiple corresponding outputs are obtained. That is, the same number of outputs as the number of input elements are obtained. However, multiple outputs (vectors) cannot be used as likelihood ratios directly. Therefore, the likelihood ratio calculation unit 100 according to the fourth embodiment performs an output integration process to integrate these multiple outputs. This makes it possible to calculate a single likelihood ratio that takes all of the multiple outputs into consideration.

[0056] The likelihood ratio calculation unit 100 integrates the multiple outputs using, for example, normalized sum pooling (hereinafter referred to as "NSPooling" as appropriate). Specifically, the likelihood ratio calculation unit 100 executes a process of adding up the multiple outputs and dividing the sum by the maximum value of the multiple outputs. That is, it executes a process as shown in the following equation (1).

[0057]

[0058] The method used for the output integration process is not limited to the above-described NSPooling. For example, the likelihood ratio calculation unit 100 may add up each of the multiple outputs and divide the sum by a predetermined constant. The likelihood ratio calculation unit 100 may also use a method for calculating the average of the multiple outputs (Global Average Pooling). Alternatively, the likelihood ratio calculation unit 100 may select and use one of the multiple outputs.

[0059] (Technical Effects) Next, technical effects obtained by the information processing device 10 according to the fourth embodiment will be described.

[0060] As described in FIG. 9 , in the information processing device 10 according to the fourth embodiment, the likelihood ratio is calculated by integrating multiple outputs from the self-attention mechanism. In this way, it is possible to appropriately calculate the likelihood ratio by taking into account all outputs from the self-attention mechanism. Furthermore, when integrating multiple outputs, by using a technique such as the above-mentioned NSPooling, it is possible to equalize the contribution of each of the multiple elements.

[0061] The scope of each embodiment also includes a processing method in which a program that operates the configuration of each embodiment to realize the functions of the above-described embodiments is recorded on a recording medium, the program recorded on the recording medium is read as code, and the program is executed on a computer. In other words, a computer-readable recording medium is also included in the scope of each embodiment. Furthermore, each embodiment includes not only a recording medium on which the above-described program is recorded, but also the program itself.

[0062] Examples of recording media that can be used include floppy disks, hard disks, optical disks, magneto-optical disks, CD-ROMs, magnetic tapes, non-volatile memory cards, and ROMs. Furthermore, the scope of each embodiment is not limited to programs that execute processes by themselves, but also includes programs that execute processes by operating on an OS in conjunction with other software or expansion board functions. Furthermore, the program itself may be stored on a server, and part or all of the program may be downloadable from the server to a user terminal. The program may be provided to the user in, for example, a SaaS (Software as a Service) format.

[0063] <Supplementary Notes> The above-described embodiment may be further described as in the following supplementary notes, but is not limited to the following.

[0064] (Supplementary Note 1) The information processing device described in Supplementary Note 1 is an information processing device that includes: an acquisition means that acquires multiple elements included in sequence data; a calculation means that inputs the multiple elements simultaneously and calculates the relationship between each element to calculate a likelihood ratio that indicates the likelihood of a class to which the sequence data belongs; and a classification means that classifies the sequence data into at least one class of multiple candidate classes based on the likelihood ratio.

[0065] (Supplementary Note 2) The information processing device according to Supplementary Note 2 is the information processing device according to Supplementary Note 1, wherein the calculation means simultaneously inputs non-consecutive elements in the sequence data and calculates a relationship between the non-consecutive elements.

[0066] (Supplementary Note 3) The information processing device according to Supplementary Note 3 is the information processing device according to Supplementary Note 1 or 2, wherein the calculation means calculates the likelihood ratio using a self-attention mechanism.

[0067] (Supplementary Note 4) The information processing device according to Supplementary Note 4 is the information processing device according to Supplementary Note 3, wherein the calculation means calculates the likelihood ratio by integrating a plurality of outputs from the self-attention mechanism.

[0068] (Supplementary Note 5) The information processing device described in Supplementary Note 5 is the information processing device described in Supplementary Note 4, wherein the calculation means integrates the multiple outputs by dividing the sum of the multiple outputs by the maximum value of the multiple outputs.

[0069] (Supplementary Note 6) The information processing method described in Supplementary Note 6 is an information processing method that, by using at least one computer, acquires multiple elements included in sequence data, inputs the multiple elements simultaneously and calculates the relationships between the elements, calculates a likelihood ratio indicating the likelihood of a class to which the sequence data belongs, and classifies the sequence data into at least one class of multiple candidate classes based on the likelihood ratio.

[0070] (Supplementary Note 7) The recording medium described in Supplementary Note 7 is a recording medium having recorded thereon a computer program for causing at least one computer to execute an information processing method, which includes acquiring multiple elements included in sequence data, inputting the multiple elements simultaneously and calculating the relationships among the elements to calculate a likelihood ratio indicating the likelihood of a class to which the sequence data belongs, and classifying the sequence data into at least one class out of multiple candidate classes based on the likelihood ratio.

[0071] (Supplementary Note 8) The computer program described in Supplementary Note 8 is a computer program that causes at least one computer to execute an information processing method that acquires multiple elements included in sequence data, inputs the multiple elements simultaneously and calculates relationships among the elements to calculate a likelihood ratio indicating the likelihood of a class to which the sequence data belongs, and classifies the sequence data into at least one class of multiple candidate classes based on the likelihood ratio.

[0072] (Supplementary Note 9) The information processing system described in Supplementary Note 9 is an information processing system including: an acquisition means for acquiring multiple elements included in sequence data; a calculation means for simultaneously inputting the multiple elements and calculating the relationship between the elements to calculate a likelihood ratio indicating the likelihood of a class to which the sequence data belongs; and a classification means for classifying the sequence data into at least one class of multiple candidate classes based on the likelihood ratio.

[0073] This disclosure may be modified as appropriate within the scope that does not contradict the gist or idea of ​​the invention that can be read from the claims and the entire specification, and information processing devices, information processing methods, and recording media that involve such modifications are also included in the technical idea of ​​this disclosure.

[0074] 10 Information processing device 50 Data acquisition unit 100 Likelihood ratio calculation unit 200 Classification unit

Claims

1. An acquisition means for acquiring a plurality of elements included in the sequence data; a calculation means for calculating a likelihood ratio indicating the likelihood of a class to which the sequence data belongs by inputting the plurality of elements simultaneously and calculating a relationship between the elements; a classification means for classifying the sequence data into at least one class out of a plurality of classes that are classification candidates based on the likelihood ratio; An information processing device comprising:

2. the calculation means simultaneously inputs non-consecutive elements in the sequence data and calculates a relationship between the non-consecutive elements; The information processing device according to claim 1 .

3. The calculation means calculates the likelihood ratio using a self-attention mechanism.

3. The information processing device according to claim 1 or 2.

4. The calculation means calculates the likelihood ratio by integrating a plurality of outputs from the self-attention mechanism. The information processing device according to claim 3 .

5. The calculation means integrates the plurality of outputs by dividing the sum of the plurality of outputs by the maximum value of the plurality of outputs. The information processing device according to claim 4.

6. by at least one computer, Obtain multiple elements contained in the sequence data, a likelihood ratio indicating the likelihood of the class to which the sequence data belongs by inputting the plurality of elements simultaneously and calculating the relationship between the elements; classifying the sequence data into at least one class out of a plurality of classes that are classification candidates based on the likelihood ratio; Information processing methods.

7. At least one computer Obtain multiple elements contained in the sequence data, a likelihood ratio indicating the likelihood of the class to which the sequence data belongs by inputting the plurality of elements simultaneously and calculating the relationship between the elements; classifying the sequence data into at least one class out of a plurality of classes that are classification candidates based on the likelihood ratio; A computer program for executing an information processing method.