Information processing device, information processing method, and recording medium

Abstract

An information processing device (10) comprises: an acquisition means (50) that sequentially acquires a limited number of elements included in series data; an index calculation means (100) that, each time the elements are acquired, calculates an index indicating to which of a plurality of classes the series data belongs; a classification means (150) that compares the index and a threshold value, thereby classifying the series data as any of the plurality of classes; a risk calculation means (210) that calculates backwards, from the final time at which all the elements are acquired, a recurrence relation for computing, on the basis of the index, a risk when the series data has been erroneously classified, thereby calculating the risk at each time; and a threshold value calculation means (220) that calculates the threshold value so as to minimize the risk. Such an information processing device makes it possible to suitably calculate a threshold value that is used when series data is classified.

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] Known examples of this type of device include 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] International Publication No. 2020 / 194497

[0004] This disclosure aims to improve upon the related art discussed above.

[0005] One aspect of the information processing device disclosed herein comprises an acquisition means for sequentially acquiring a finite number of elements included in sequence data; an index calculation means for calculating, for each acquired element, an index indicating to which of multiple classes the sequence data belongs; a classification means for classifying the sequence data into one of the multiple classes by comparing the index with a threshold; a risk calculation means for calculating the risk at each time by back-calculating, from the final time when all of the elements are acquired, a recurrence formula that calculates the risk of misclassifying the sequence data based on the index; and a threshold calculation means for calculating the threshold so as to minimize the risk.

[0006] One aspect of the information processing method disclosed herein is an information processing method for calculating the threshold used by an information processing device that includes: acquisition means for sequentially acquiring a finite number of elements included in sequence data; index calculation means for calculating, for each acquired element, an index indicating to which of multiple classes the sequence data belongs; and classification means for classifying the sequence data into one of the multiple classes by comparing the index with a threshold. The information processing method calculates the risk of misclassifying the sequence data based on the index by working backward from the final time when all of the elements are acquired, to calculate the risk at each time, and calculates the threshold so as to minimize the risk.

[0007] One aspect of the recording medium disclosed herein is an information processing method for calculating a threshold used by an information processing device that includes: acquisition means for sequentially acquiring a finite number of elements included in sequence data; index calculation means for calculating, for each acquired element, an index indicating to which of multiple classes the sequence data belongs; and classification means for classifying the sequence data into one of the multiple classes by comparing the index with a threshold. The recording medium has recorded thereon a computer program that causes a computer to execute the information processing method, which calculates the risk of misclassifying the sequence data based on the index by back-calculating, from the final time when all of the elements are acquired, a recurrence formula for calculating the risk at each time, and then calculates the threshold so as to minimize the risk.

[0008] 1 is a block diagram showing the hardware configuration of a first information processing device. 2 is a block diagram showing the functional configuration of the first information processing device. 3 is a flowchart showing the flow of a classification operation in the first information processing device. 4 is a flowchart showing the flow of a threshold calculation operation in the first information processing device. 5 is a block diagram showing the functional configuration of a second information processing device. 6 is a flowchart showing the flow of a threshold calculation operation in the second information processing device. 7 is a graph showing a method of calculating a conditional expected value in the second information processing device. 8 is a graph showing a threshold calculation method in the second information processing device. 9 is a graph showing an example of a threshold calculated in the second information processing device.

[0009] Hereinafter, embodiments of an information processing device, an information processing method, and a recording medium will be described with reference to the drawings.

[0010] First Embodiment A first embodiment will be described with reference to FIGS. 1 to 4. FIG.

[0011] (Hardware Configuration) First, the hardware configuration of the first information processing apparatus will be described with reference to Fig. 1. Fig. 1 is a block diagram showing the hardware configuration of the first information processing apparatus.

[0012] 1, a first information processing device 10 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. The data bus 17 may be an interface other than a data bus (for example, a LAN, a USB, etc.).

[0013] 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, functional blocks that execute various processes for classifying sequence data are 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.

[0014] 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 digital signal processor (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.

[0015] 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.

[0016] 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.

[0017] 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.

[0018] 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.

[0019] 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.

[0020] 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.).

[0021] (Functional Configuration) Next, the functional configuration of the first information processing device 10 will be described with reference to Fig. 2. Fig. 2 is a block diagram showing the functional configuration of the first information processing device.

[0022] 2, the first information processing device 10 is configured as a device for classifying sequential data. For example, the first information processing device 10 may be configured as a device that acquires images of time-series data and classifies the types of objects included in the images. The first information processing device 10 is configured to include, as components for realizing its functions, an acquisition unit 50, an index calculation unit 100, a classification unit 150, a risk calculation unit 210, and a threshold calculation unit 220. Each of the acquisition unit 50, the index calculation unit 100, the classification unit 150, the risk calculation unit 210, and the threshold calculation unit 220 may be a processing block realized by, for example, the above-mentioned processor 11 (see FIG. 1).

[0023] The acquisition unit 50 is configured to acquire sequence data. Sequence data here refers to data including multiple elements arranged in a predetermined order, such as time-series data. More specific examples of sequence data include, but are not limited to, video data, audio data, or subdivided image data. The acquisition unit 50 is configured to sequentially acquire a finite number of elements included in the sequence data. For example, the acquisition unit 50 may be configured to acquire elements included in the sequence data one by one. The 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 acquisition unit 50 may be configured to acquire data from each of multiple cameras.

[0024] The index calculation unit 100 is configured to be able to calculate an index from the sequence data acquired by the acquisition unit 50. The "index" here is a value indicating to which of multiple classes, which are candidate classification classes, the sequence data belongs. More specific examples of the index will be described in other embodiments below. When the acquisition unit 50 sequentially acquires elements, the index calculation unit 100 calculates an index each time an element is acquired. That is, the index calculation unit 100 calculates an index each time the acquisition unit 50 acquires an element, and calculates a new index each time the acquisition unit 50 acquires another element. The index calculation unit 100 may calculate an index using the most recently acquired element. In this case, the index calculation unit 100 may calculate a new index not only using the acquired element but also using indices calculated in the past (specifically, indices calculated from elements acquired in the past).

[0025] The classification unit 150 classifies the sequence data into one of multiple classes based on the index calculated by the index calculation unit 100. Specifically, the classification unit 150 classifies the sequence data into one of multiple classes by comparing the index calculated by the index calculation unit 100 with a preset threshold. For example, if the index exceeds a threshold corresponding to class A, the classification unit 150 classifies the sequence data into class A. Alternatively, if the index exceeds a threshold corresponding to class B, the classification unit 150 classifies the sequence data into class B. The classification unit 150 may classify, for example, whether a person's face in an image is a real face or a fake face (e.g., an impersonation using a photograph or a 3D mask). The multiple classes may be three or more. In this case, the classification unit 150 may perform classification using a threshold set for each class. The threshold used by the classification unit 150 is calculated by the threshold calculation unit 220, which will be described later.

[0026] The risk calculation unit 210 is configured to be able to calculate the risk when the classification unit 150 erroneously classifies sequential data. For example, the risk calculation unit 210 calculates a value indicating the risk when sequential data that should be classified as class A is classified as class B. The risk calculation unit 210 calculates the risk based on the index calculated by the index calculation unit 100. However, the risk calculation unit 210 may calculate the risk based on a true index (in other words, a correct label) previously assigned to the sequential data. The risk calculation unit 210 calculates the risk at each time an element included in the sequential data is acquired. Note that in this embodiment, "time" advances each time an element is acquired. Therefore, the time corresponds to the number of elements acquired so far.

[0027] The risk calculation unit 210 calculates the risk for each time by back-calculating a recurrence formula that calculates risk based on an index, from the final time when all finite elements included in the sequence data are acquired. Specifically, the risk calculation unit 210 first calculates the risk for the final time based on the index calculated when all elements are acquired. From there, the risk calculation unit 210 calculates the risk for the time before the most recently acquired element is acquired by back-calculating using the recurrence formula. The risk calculation unit 210 calculates the risk for each time before the final time by repeating this back-calculation. The recurrence formula may include a term corresponding to the penalty for classifying the wrong class. A specific recurrence formula is, for example, the following formula (1).

[0028] In the above formula (1), R is risk, X （１,t） is the sequence data up to the current time t. i and j are classes, and u ｔ = j indicates that the predicted class is j. K is the number of classes, and y is the class label. L ｉｊ is the penalty for mistaking class i for class j, and L ｉｊ = 0. p(y = i | X （１,t）) is the posterior probability of the class, and is an example of an index calculated by the index calculation unit 100. ct is the sampling cost, which is obtained by multiplying a constant c by the current time t. The sampling cost may be a function f(t) of the current time t.

[0029] The threshold calculation unit 220 is configured to be able to calculate a threshold to be used by the classification unit 150 based on the risk calculated by the risk calculation unit 210. Specifically, the threshold calculation unit 220 calculates a threshold so as to minimize the risk calculated by the risk calculation unit 210. The threshold calculation unit 220 calculates a threshold corresponding to the risk at each time. The threshold calculation unit 220 may calculate thresholds in order from the final time in accordance with the risk calculation unit 210 calculating the risk by counting backward from the final time. The threshold calculation unit 220 may be configured to calculate thresholds corresponding to all times, and then connect these thresholds in chronological order and store the result as a final threshold.

[0030] (Classification Operation) Next, the classification operation (i.e., the operation of classifying sequence data into one of a plurality of classes) in the first information processing device 10 will be described with reference to Fig. 3. Fig. 3 is a flowchart showing the flow of the classification operation in the first information processing device.

[0031] 3, when the classification operation in the first information processing device 10 starts, the acquisition unit 50 first acquires one element included in the sequence data (step S101), and the index calculation unit 100 then calculates an index based on the element acquired by the acquisition unit 50 (step S102).

[0032] Next, the classification unit 150 determines whether there is a class in which the index calculated by the index calculation unit 100 exceeds a threshold (step S103). That is, the classification unit 150 compares the index calculated by the index calculation unit 100 with the threshold corresponding to each class, and determines whether the index exceeds the threshold corresponding to any class.

[0033] If there is a class whose index exceeds the threshold (step S103: YES), the classifying unit 150 classifies the sequence data into the class whose index exceeds the threshold (step S104). On the other hand, if there is no class whose index exceeds the threshold (step S103: NO), the process is repeated from step S101. That is, the acquiring unit 50 acquires the next element included in the sequence data and repeats the same process as described above.

[0034] The index calculated by the index calculation unit 100 tends to approach the threshold corresponding to the class to be classified each time an element is acquired. Therefore, by repeating the process while acquiring elements one by one as described above, sequential data can be classified into appropriate classes. In this case, sequential data that is easy to classify exceeds the threshold at an early stage, allowing the sequential data to be classified early. On the other hand, for sequential data that is difficult to classify, elements continue to be acquired until the threshold is exceeded, allowing the sequential data to be classified accurately over a period of time.

[0035] (Threshold Calculation Operation) Next, a threshold calculation operation (i.e., an operation for calculating a threshold used for classifying sequence data) in the first information processing device 10 will be described with reference to Fig. 4. Fig. 4 is a flowchart showing the flow of the threshold calculation operation in the first information processing device.

[0036] 4, when the threshold calculation operation in the first information processing device 10 starts, the acquiring unit 50 first acquires sequence data (step S151). Unlike the classification operation described above, the acquiring unit 50 may acquire all elements included in the sequence data together. The sequence data acquired in the threshold calculation operation may be sequence data prepared for calculating a threshold (e.g., learning data with a correct answer label attached).

[0037] Next, the index calculation unit 100 calculates an index for each time based on each element of the sequence data acquired by the acquisition unit 50 (step S152). That is, the index is calculated for each time when elements included in the sequence data are acquired sequentially.

[0038] Next, the risk calculation unit 210 calculates a risk based on the index calculated by the index calculation unit 100 (step S153). As already explained, the risk calculation unit 210 first calculates the risk at the final time. Then, the threshold calculation unit 220 calculates a threshold so as to minimize the risk calculated by the risk calculation unit 210 (step S154). The threshold calculation unit 220 calculates a threshold for the time corresponding to the risk calculated by the risk calculation unit 210. For example, when the risk calculation unit 210 calculates the risk at the final time, the threshold calculation unit 220 calculates the threshold for the final time.

[0039] Next, the threshold calculation unit 220 determines whether to end the calculation of the threshold (step S155). The threshold calculation unit 220 may determine to end the calculation of the threshold, for example, when it has calculated the threshold for all time points (specifically, when it has completed the reverse calculation from the final time point to the first time point). If it has determined to end the calculation (step S155: YES), the threshold calculation operation ends.

[0040] On the other hand, the threshold calculation unit 220 may determine not to end the threshold calculation if, for example, thresholds have not been calculated for all times. If it is determined not to end the calculation (step S155: NO), the threshold calculation unit 220 returns to the previous time (step S156) and repeats the process from step S153. By repeating the process in this manner, backward calculation from the final time progresses, and ultimately it is possible to calculate the risks and thresholds for all times.

[0041] (Technical Effects) Next, technical effects obtained by the first information processing device 10 will be described.

[0042] As described with reference to FIGS. 1 to 6 , in the first information processing device 10, the threshold used to classify sequence data is calculated according to the risk calculated based on the index. In this way, it is possible to calculate a threshold that can reliably reduce the risk during classification. Using the threshold calculated in this way allows for more appropriate classification than, for example, when the threshold is fixed at the same value from the beginning. Furthermore, more appropriate classification can be achieved than when the threshold is simply changed (for example, when it is monotonically decreased).

[0043] Second Embodiment A second embodiment will be described with reference to Figures 5 to 9. Note that the second embodiment differs from the first embodiment described above only in some configurations and 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.

[0044] (Functional Configuration) First, the functional configuration of the second information processing device 10 will be described with reference to Fig. 5. Fig. 5 is a block diagram showing the functional configuration of the second information processing device. Note that in Fig. 5, elements similar to those shown in Fig. 2 are denoted by the same reference numerals.

[0045] 5, the second information processing device 10 is configured to include, as components for realizing its functions, an acquisition unit 50, an index calculation unit 100, a classification unit 150, a risk calculation unit 210, and a threshold calculation unit 220. In particular, the index calculation unit 100 in the second information processing device 10 includes a likelihood ratio calculation unit 101 and a posterior probability conversion unit 102. Furthermore, the risk calculation unit 210 in the second information processing device includes a continuation risk calculation unit 211, a termination risk calculation unit 212, and a minimum risk holding unit 213.

[0046] The likelihood ratio calculation unit 101 is configured to calculate a likelihood ratio based on elements included in the sequence data acquired by the acquisition unit 50. The "likelihood ratio" here is an index indicating the likelihood of a class to which the sequence data belongs. The likelihood ratio calculation unit 101 may calculate a likelihood ratio based on two consecutive elements among the elements sequentially acquired by the acquisition unit 50. For example, the likelihood ratio calculation unit 101 may calculate a likelihood ratio using a newly acquired element and a previously acquired element or a previously calculated likelihood ratio. In this case, the likelihood ratio calculation unit 101 may include a storage unit that stores previously acquired elements or previously calculated likelihood ratios. The likelihood ratio calculation unit 101 may be configured, for example, by a trained neural network.

[0047] The posterior probability conversion unit 102 is configured to be able to convert the likelihood ratio calculated by the likelihood ratio calculation unit 101 into a posterior probability. The posterior probability is a value indicating the probability that an input element will be classified into a specific class, and is a value that corresponds one-to-one to the likelihood ratio calculated by the likelihood ratio calculation unit 101. The posterior probability is an index calculated by the index calculation unit 100 and is used for classification in the classification unit 150 and for risk calculation in the risk calculation unit 210. However, the likelihood ratio calculated by the likelihood ratio calculation unit 101 may also be used as an index. In this case, the second information processing device 10 may be configured without including the posterior probability conversion unit 102. Whether the posterior probability or the likelihood ratio is used as an index, it is possible to appropriately calculate risk.

[0048] The continuing risk calculation unit 211 is configured to be able to calculate the continuing risk using the posterior probability converted by the posterior probability conversion unit 102. Alternatively, the continuing risk calculation unit 211 may be configured to be able to calculate the continuing risk using the likelihood ratio calculated by the likelihood ratio calculation unit 101. The continuing risk is the risk that occurs when time is advanced and the next element is acquired without classifying the sequence data at the current time. The continuing risk can also be said to be the risk expectation value at the next time conditioned by the likelihood ratio or posterior probability at the current time. The continuing risk G~ ｔ can be calculated, for example, as in the following formula (2).

[0049] In the above formula (2), π is a vector that collects the posterior probabilities of all classes. Also, G is the minimum risk. The minimum risk G will be described in detail in the explanation of the minimum risk holding unit 213 below. The right side of the above formula (2) indicates the expected risk value when proceeding to time t+1 when the posterior probabilities up to time t are available.

[0050] The termination risk calculation unit 212 is configured to be able to calculate the termination risk using the posterior probability converted by the posterior probability conversion unit 102. Alternatively, the termination risk calculation unit 212 may be configured to be able to calculate the termination risk using the likelihood ratio calculated by the likelihood ratio calculation unit 101. The termination risk is the risk when classifying the sequence data at the current time. Termination risk G ｓｔis a function of the likelihood ratio or posterior probability at the current time, and can be calculated, for example, as in the following equation (3).

[0051] The right side of the above formula (3) means selecting j that minimizes the penalty in formula (1) shown in the first embodiment, which is the risk when completing classification with the posterior probability currently available. ｉ is the posterior probability of class i.

[0052] The minimum risk holding unit 213 is configured to be able to hold the smaller of the continuing risk calculated by the continuing risk calculation unit 211 and the termination risk calculated by the termination risk calculation unit 212 as the minimum risk. As can be seen from the above formula (2), the minimum risk is used to calculate the continuing risk at the previous time. By using the minimum risk, it is possible to calculate the continuing risk by back-calculating the recurrence formula. Note that at the final time T, the termination risk can be held as the minimum risk as is. In this way, it is possible to calculate the continuing risk at the previous time by back-calculating from the termination risk at the final time.

[0053] (Threshold calculation operation) Next, the threshold calculation operation in the second information processing device 10 will be described with reference to Figs. 6 to 8. Fig. 6 is a flowchart showing the flow of the threshold calculation operation in the second information processing device. Fig. 7 is a graph showing a method for calculating a conditional expected value in the second information processing device. Fig. 8 is a graph showing a method for calculating a threshold in the second information processing device. Note that in Fig. 6, the same processes as those shown in Fig. 4 are denoted by the same reference numerals.

[0054] 6, when the threshold calculation operation in the second information processing device 10 starts, the acquisition unit 50 first acquires sequence data (step S251). Then, the likelihood ratio calculation unit 101 calculates a likelihood ratio for each time based on each element of the sequence data acquired by the acquisition unit 50 (step S252). Furthermore, the posterior probability conversion unit 102 converts the likelihood ratio calculated by the likelihood ratio calculation unit into a posterior probability (step S253). Note that if the likelihood ratio is used as an index, the processing of step S253 may be omitted.

[0055] Next, the termination risk calculation unit 212 calculates the termination risk at the final time T (step S254). The calculated termination risk at the final time T is held by the minimum risk holding unit 213 as the minimum risk at the final time T.

[0056] Next, the time is returned to the previous time, and the subsequent processing is carried out (step S255). First, the termination risk calculation unit 212 calculates the termination risk at the current time t (step S256). Note that the termination risk can be calculated at any time if a posterior probability or a likelihood ratio is available. Therefore, the termination risk may be calculated at a different timing. For example, when calculating the termination risk at the final time in step S254, the termination risk calculation unit 212 may also calculate the termination risks at other times.

[0057] Next, the continuing risk calculation unit 211 calculates the continuing risk at the current time t (step S257). The continuing risk calculation unit 211 calculates the continuing risk using the minimum risk held by the minimum risk holding unit 213 (i.e., the minimum risk at the next time point). Note that when calculating the continuing risk, it is necessary to calculate the conditional expected value as shown in the above formula (3). This calculation is complicated because it is necessary to handle the joint distribution of the minimum risk and the posterior probability or likelihood ratio. Therefore, in this embodiment, the conditional expected value is calculated using Gaussian process regression. A Gaussian process is a type of generative model that generates an output from an input. The input here is the posterior probability or likelihood ratio at time t. The output is the minimum risk at time t+1.

[0058] As shown in Figure 7, the output points of the Gaussian process follow a Gaussian distribution, and the mean and variance are output. The mean here becomes the conditional expectation. Specifically, if conditioned by the posterior probability π at the current time t (i.e., if the graph is cut vertically at πt), the cut also becomes a Gaussian distribution. The mean value μ of the Gaussian distribution at the cut becomes the minimum risk at time t+1. In this way, using Gaussian process regression makes it possible to easily calculate the conditional expectation (in other words, the continuing risk). Note that methods other than Gaussian process regression may also be used to calculate the conditional expectation. For example, the joint probability distribution may be calculated using a model such as a normalized flow or a mixed Gaussian distribution.

[0059] 6, after calculating the termination risk and the continuation risk at the current time t, the minimum risk holding unit 213 holds the smaller of the termination risk and the continuation risk as the minimum risk at the current time t (step S258). The held minimum risk will be used when calculating the continuation risk at the immediately previous time.

[0060] Next, the threshold calculation unit 220 stores the intersection of the termination risk and the continuation risk as a threshold (step S259). A method for calculating the threshold will be described below with reference to FIG.

[0061] In the example shown in Figure 8, the number of elements included in the sequence data is 50 (i.e., time t = 1 to 50). Figure 8(a) shows the termination risk and continuation risk at time t = 48. Figure 8(b) shows the termination risk and continuation risk at time t = 40. Figure 8(c) shows the termination risk and continuation risk at time t = 20. Note that the sampling cost is added to the continuation risk, so it is inflated relative to the termination risk.

[0062] As shown in Figures 8(a) to 8(c), there are two intersections between the termination risk and the continuation risk at each time. The threshold calculation unit 220 stores these intersections as thresholds. After calculating thresholds for all times, the threshold calculation unit 220 connects them in the time direction to arrive at the final threshold. In this way, it is possible to appropriately calculate thresholds that minimize risk.

[0063] Returning to FIG. 6 again, the threshold calculation unit 220 determines whether or not to end the calculation of the threshold (step S260). If it is determined that the calculation should be ended (step S260: YES), the threshold calculation operation ends. On the other hand, if it is determined that the calculation should not be ended (step S260: NO), the process starts again from step S255. That is, the process returns to the previous time and repeats the same process as described above. By repeating the process in this manner, backward calculation from the final time progresses, and ultimately, the risks and thresholds for all times can be calculated.

[0064] (Technical Effects) Next, technical effects obtained by the second information processing device 10 will be described with reference to FIG.

[0065] As shown in FIG. 9 , the second information processing device 10 calculates a threshold value that changes over time. This allows for calculation of a threshold value that enables early classification while reducing the risk of classification. For example, the sequence data A, B, and C shown in FIG. 9 each have different trends in the fluctuation of likelihood ratios. While sequence data A is relatively easy to classify, sequence data C is relatively difficult to classify. If the threshold value is fixed at the initial value when classifying such sequence data A, B, and C, classification of sequence data with a small likelihood ratio gradient would be delayed. Furthermore, for sequence data C with a small change in likelihood ratio, even if all elements are acquired, the likelihood ratio may not exceed the threshold, and the process may ultimately terminate without classification. However, in this embodiment, the threshold value changes over time, allowing for early and accurate classification of all sequence data.

[0066] Although a similar effect can be achieved by monotonically decreasing the threshold, monotonically decreasing the threshold alone does not accurately reflect the risk, increasing the likelihood of misclassification. In this embodiment, the threshold is changed to minimize the risk, thereby achieving early classification while minimizing the likelihood of misclassification.

[0067] 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.

[0068] 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.

[0069] <Supplementary Notes> The above-described embodiment may be further described as in the following supplementary notes, but is not limited to the following.

[0070] (Supplementary Note 1) The information processing device described in Supplementary Note 1 includes an acquisition means that sequentially acquires a finite number of elements included in sequence data, an index calculation means that calculates an index indicating to which of multiple classes the sequence data belongs each time an element is acquired, a classification means that classifies the sequence data into one of the multiple classes by comparing the index with a threshold, a risk calculation means that calculates the risk at each time by back-calculating, from the final time when all of the elements are acquired, a recurrence formula that calculates the risk of misclassifying the sequence data based on the index, and a threshold calculation means that calculates the threshold so as to minimize the risk.

[0071] (Supplementary Note 2) The information processing device described in Supplementary Note 2 is the information processing device described in Supplementary Note 1, wherein the risk calculation means calculates a continuation risk, which is the risk when the next element is acquired without classifying the sequence data at the current time, and a termination risk, which is the risk when classifying the sequence data at the current time, and the threshold calculation means calculates the intersection of the continuation risk and the termination risk as the threshold.

[0072] (Appendix 3) The information processing device described in Appendix 3 is the information processing device described in Appendix 3, wherein the risk calculation means holds the smaller of the continuing risk and the termination risk at the current time as the minimum risk at the current time, and calculates the continuing risk at the time one time before the current time using the minimum risk at the current time.

[0073] (Appendix 4) The information processing device described in Appendix 4 is the information processing device described in Appendix 2, in which the risk calculation means sets the value of the minimum risk at the final time as the value of the termination risk at the final time, and then calculates the continuing risk at each time by working backwards from the final time to a recurrence formula for determining the continuing risk.

[0074] (Supplementary Note 5) The information processing device according to Supplementary Note 5 is the information processing device according to any one of Supplementary Notes 2 to 4, wherein the risk calculation means calculates the continuing risk using Gaussian process regression.

[0075] (Supplementary Note 6) The information processing device described in Supplementary Note 6 is the information processing device described in any one of claims 1 to 5, wherein the index is a likelihood ratio indicating the likelihood that the sequence data belongs to a class of the plurality of classes, or a posterior probability corresponding to the likelihood ratio.

[0076] (Supplementary Note 7) The information processing method described in Supplementary Note 7 is an information processing method for calculating the threshold used by an information processing device including: acquisition means for sequentially acquiring a finite number of elements included in sequence data; index calculation means for calculating, for each acquired element, an index indicating to which of multiple classes the sequence data belongs; and classification means for classifying the sequence data into one of the multiple classes by comparing the index with a threshold, wherein the information processing method calculates the risk of misclassifying the sequence data based on the index by back-calculating, from the final time when all of the elements are acquired, a recurrence formula for calculating the risk at each time, and calculates the threshold so as to minimize the risk.

[0077] (Supplementary Note 8) The recording medium described in Supplementary Note 8 is an information processing method for calculating a threshold used by an information processing device including: acquisition means for sequentially acquiring a finite number of elements included in sequence data; index calculation means for calculating, for each acquired element, an index indicating to which of multiple classes the sequence data belongs; and classification means for classifying the sequence data into one of the multiple classes by comparing the index with a threshold, wherein the information processing method calculates the risk of misclassifying the sequence data based on the index by back-calculating, from the final time when all of the elements are acquired, the risk at each time point, and calculating the threshold so as to minimize the risk, is a recording medium having recorded thereon a computer program for causing a computer to execute the information processing method.

[0078] (Supplementary Note 9) The computer program described in Supplementary Note 9 is an information processing method for calculating a threshold used by an information processing device including: acquisition means for sequentially acquiring a finite number of elements included in sequence data; index calculation means for calculating, for each acquired element, an index indicating to which of multiple classes the sequence data belongs; and classification means for classifying the sequence data into one of the multiple classes by comparing the index with a threshold, wherein the computer program causes a computer to execute the information processing method by calculating the risk at each time by back-calculating, from the final time when all of the elements are acquired, a recurrence formula that calculates, based on the index, a risk of misclassifying the sequence data, and calculating the threshold so as to minimize the risk.

[0079] 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.

[0080] REFERENCE SIGNS LIST 10 Information processing device 11 Processor 50 Acquisition unit 100 Index calculation unit 101 Likelihood ratio calculation unit 102 Posterior probability conversion unit 150 Classification unit 210 Risk calculation unit 211 Continuation risk calculation unit 212 Termination risk calculation unit 213 Minimum risk retention unit 220 Threshold calculation unit

Claims

1. A means for sequentially acquiring a finite number of elements contained in sequential data, Each time the aforementioned element is acquired, an index calculation means calculates an index indicating which of the multiple classes the series data belongs to, A classification means that classifies the series data into one of the plurality of classes by comparing the index and a threshold, A risk calculation means calculates the risk at each time point by calculating a recurrence relation that calculates the risk of misclassifying the aforementioned series data based on the aforementioned indicator, by working backward from the final time point in which all of the aforementioned elements are acquired. A threshold calculation means for calculating the threshold in such a way as to minimize the aforementioned risk, An information processing device equipped with the following features.

2. The risk calculation means calculates a continuation risk, which is the risk when the next element is acquired without classifying the series data at the current time, and an termination risk, which is the risk when the series data is classified at the current time. The threshold calculation means calculates the intersection of the continuation risk and the termination risk as the threshold. The information processing apparatus according to claim 1.

3. The risk calculation means holds the smaller of the continuation risk and the termination risk at the current time as the minimum risk at the current time, and uses the minimum risk at the current time to calculate the continuation risk at the time immediately preceding the current time. The information processing apparatus according to claim 2.

4. The risk calculation means takes the minimum risk value at the final time as the termination risk value at the final time, and then calculates the continuation risk at each time by working backward from the final time to determine the recurrence relation for determining the continuation risk. The information processing apparatus according to claim 3.

5. The risk calculation means calculates the continuation risk using Gaussian process regression. The information processing apparatus according to any one of claims 2 to 4.

6. The aforementioned indicator is the likelihood ratio indicating the probability that the series data belongs to one of the multiple classes, or the posterior probability corresponding to the likelihood ratio. The information processing apparatus according to claim 1.

7. A means for sequentially acquiring a finite number of elements contained in sequential data, Each time the aforementioned element is acquired, an index calculation means calculates an index indicating which of the multiple classes the series data belongs to, A classification means that classifies the series data into one of the plurality of classes by comparing the index and a threshold, An information processing method for calculating the threshold used by an information processing device comprising the following: The risk of misclassifying the aforementioned series data is calculated based on the aforementioned indicator by calculating a recurrence relation, which is derived by working backward from the final time when all the elements are acquired, thereby calculating the risk at each time point. The threshold is calculated to minimize the aforementioned risk. Information processing methods.

8. A means for sequentially acquiring a finite number of elements contained in sequential data, Each time the aforementioned element is acquired, an index calculation means calculates an index indicating which of the multiple classes the series data belongs to, A classification means that classifies the series data into one of the plurality of classes by comparing the index and a threshold, An information processing method for calculating the threshold used by an information processing device comprising the following: The risk of misclassifying the aforementioned series data is calculated based on the aforementioned indicator by calculating a recurrence relation, which is derived by working backward from the final time when all the elements are acquired, thereby calculating the risk at each time point. The threshold is calculated to minimize the aforementioned risk. A computer program that instructs a computer to execute information processing methods.