Information processing device, information processing method, and recording medium

Abstract

An information processing device (10) comprises: a first score acquisition means (110) that performs 1:N matching between object data acquired from an object to be matched and N pieces of registered data registered in advance to acquire a first matching score; and a second score acquisition means (120) that converts the first matching score on the basis of an amount depending on the number N of times of matching with the registered data to acquire a second matching score. According to such an information processing device, it is possible to convert the 1:N matching score to the appropriate value.

Description

[Technical Field]

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

[0002] Known devices of this type correct the matching score output from the matching process. For example, Patent Document 1 discloses a method of comparing facial images to calculate a similarity (score), and then correcting the score based on the distribution of the overall score result to perform matching. Patent Document 2 discloses updating the score distribution for person-to-person matching and the score distribution for person-to-other matching, and using these distributions to correct the matching score according to variations contained in the biometric information at the time of authentication. Patent Document 3 discloses calculating correction parameters by fitting extracted scores to a normal distribution, and correcting the matching score based on the correction parameters. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2008-040874 [Patent Document 2] Japanese Patent Application Laid-Open No. 2010-108074 [Patent Document 3] Japanese Patent Application Laid-Open No. 2011-086202 Summary of the Invention [Problem to be solved by the invention]

[0004] This disclosure aims to improve upon the techniques disclosed in the prior art documents. [Means for solving the problem]

[0005] One aspect of the information processing device disclosed herein includes a first score acquisition means that performs one-to-N matching between target data acquired from a matching target and N registered data items that have been registered in advance, and acquires a first matching score, and a second score acquisition means that converts the first matching score based on an amount that depends on the number N of matching items in the registered data, and acquires a second matching score.

[0006] One aspect of the information processing method disclosed herein involves using at least one computer to perform one-to-N matching between target data acquired from a matching target and N registered data items that have been registered in advance, obtaining a first matching score, and converting the first matching score based on a quantity that depends on the number N of matching items in the registered data, thereby obtaining a second matching score.

[0007] One aspect of the recording medium of this disclosure has recorded thereon a computer program that causes at least one computer to execute an information processing method, which includes performing one-to-N matching between target data acquired from a matching target and N registered data items that have been registered in advance, obtaining a first matching score, and converting the first matching score based on a quantity that depends on the number N of matching items in the registered data, thereby obtaining a second matching score. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a block diagram showing a hardware configuration of an information processing device according to a first embodiment. [Figure 2] 1 is a block diagram showing a functional configuration of an information processing device according to a first embodiment. [Figure 3] 4 is a flowchart showing the flow of operations of the information processing device according to the first embodiment. [Figure 4] FIG. 10 is a block diagram showing the functional configuration of an information processing device according to a second embodiment. [Figure 5] 10 is a flowchart showing the flow of operations of the information processing device according to the second embodiment. [Figure 6] 10 is a flowchart showing the flow of operations of the information processing device according to the third embodiment. [Figure 7]10 is a flowchart showing the flow of operations of the information processing device according to the fourth embodiment. [Figure 8] FIG. 11 is a block diagram showing the functional configuration of an information processing device according to a fifth embodiment. [Figure 9] 13 is a flowchart showing the flow of operations of the information processing device according to the fifth embodiment. DETAILED DESCRIPTION OF THE INVENTION

[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 An information processing apparatus according to a first embodiment will be described with reference to FIGS.

[0011] (Hardware configuration) First, the hardware configuration of the information processing device 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 device according to the first embodiment.

[0012] 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.

[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, a functional block for acquiring and converting a matching score is realized within the processor 11. In this manner, 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 demand-side platform (DSP), or an application-specific integrated circuit (ASIC). 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 the processor 11 is executing the computer programs. The RAM 12 may be, for example, a dynamic random access memory (DRAM) 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 P-ROM (Programmable Read Only Memory) or an EPROM (Erasable Read Only Memory). Alternatively, other types of non-volatile memory may be used instead of the ROM 13.

[0017] The storage device 14 stores data that the information processing device 10 stores for a long period of time. 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. 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.

[0020] 1 shows an example of information processing device 10 configured to include multiple devices, but all or some of the functions may be realized as a single device. In that case, information processing device 10 may be configured to include only processor 11, RAM 12, and ROM 13 described above, and other components (i.e., storage device 14, input device 15, output device 16) may be provided in an external device connected to information processing device 10. Furthermore, some of the calculation functions of 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 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.

[0022] The information processing device 10 according to the first embodiment is configured to perform a matching process using target data acquired from a target to be matched and registered data registered in advance, and to acquire (calculate) a matching score. The type of matching process is not particularly limited, and may be, for example, a matching process using image data. More specifically, the matching process may be a face matching process (face authentication process) that matches a face image of the target, or an iris matching process (iris authentication process) that matches an iris image of the target.

[0023] 2, the information processing device 10 according to the first embodiment is configured to include, as components for realizing its functions, a first score obtaining unit 110 and a second score obtaining unit 120. Each of the first score obtaining unit 110 and the second score obtaining unit 120 may be a processing block realized by, for example, the above-mentioned processor 11 (see FIG. 1). Furthermore, each of the first score obtaining unit 110 and the second score obtaining unit 120 may be configured as a neural network.

[0024] The first score acquisition unit 110 is configured to acquire a first matching score by performing one-to-n matching between target data acquired from a matching target and N registered data items registered in advance. The first matching score may be, for example, a score indicating the degree of similarity between the target data and each registered data item. However, the method for calculating the first matching score is not particularly limited, and the first matching score may be calculated by appropriately adopting existing technology. The first matching score may be acquired for each of the N registered data items. In other words, N first matching scores may be acquired. Note that the number of matching items N in the one-to-N matching may be configured to be changeable as appropriate. For example, the number of matching items N may be changed according to a user setting or a change in the number of registered data items.

[0025] The second score acquisition unit 120 is configured to convert the first matching score to acquire the second matching score. Specifically, the second score acquisition unit 120 is configured to convert the first matching score based on an amount dependent on the number of matching cases N. Note that the "amount dependent on the number of matching cases N" here is not particularly limited, and various parameters that significantly convert the number of matching cases N can be used. Specific examples of the amount dependent on the number of matching cases N will be described in detail in other embodiments described later. The second score acquisition unit 120 is configured to receive information about the number of matching cases N based on the N registered data items used in the one-to-N matching in the first score acquisition unit 110. The information about the number of matching cases N may be the amount dependent on the number of matching cases N described above. Alternatively, the information about the number of matching cases N may be the value of N itself. In this case, the second score acquisition unit 120 may calculate the amount dependent on the number of matching cases N described above from the value of N.

[0026] (Operation flow) Next, the flow of operations of the information processing device 10 according to the first embodiment (specifically, the flow up to outputting the second matching score) will be described with reference to Fig. 3. Fig. 3 is a flowchart showing the flow of operations of the information processing device according to the first embodiment.

[0027] 3, when the operation of the information processing device 10 according to the first embodiment starts, first, the first score acquiring unit 110 acquires target data from a matching target (step S101). The first score acquiring unit 110 may, for example, capture an image including the target and acquire the image data as the target data. Alternatively, the first score acquiring unit 110 may acquire a feature amount extracted from the image data as the target data.

[0028] Next, the first score acquiring unit 110 performs one-to-N matching between the acquired target data and N registered data items registered in advance, and acquires a first matching score (step S102). The first score acquiring unit 110 outputs the acquired first matching score to the second score acquiring unit 120.

[0029] Next, the second score acquiring unit 120 converts the first matching score based on an amount that depends on the number of matching cases N, and acquires a second matching score (step S103). Then, the second score acquiring unit 120 outputs the acquired second matching score (step S104).

[0030] (Technical Effects) Next, the technical effects obtained by the information processing device 10 according to the first embodiment will be described.

[0031] As described with reference to FIGS. 1 to 3 , in the information processing device 10 according to the first embodiment, a first matching score is obtained through 1-to-N matching, and the first matching score is converted based on an amount that depends on the number of matching cases N to obtain a second matching score. In this way, the first matching score obtained through 1-to-N matching can be converted into an appropriate score (i.e., a second matching score) depending on the number of matching cases N. In other words, appropriate score calibration depending on the number of matching cases N can be performed on the first matching score. Therefore, according to the information processing device according to this embodiment, it is possible to obtain a more appropriate matching score in 1-to-N matching. For example, it is possible to obtain a score that will provide an appropriate result in authentication processing using the matching score (for example, processing to determine whether a person is the registered person or a different person).

[0032] Second Embodiment An information processing device 10 according to the second embodiment will be described with reference to Figures 4 and 5. The second embodiment differs from the first embodiment described above only in part of its configuration and operation, and other parts may be the same as those of the first embodiment. Therefore, the following will describe in detail the parts that differ from the first embodiment already described, and will omit a description of other overlapping parts as appropriate.

[0033] (Functional configuration) First, the functional configuration of the information processing device 10 according to the second embodiment will be described with reference to Fig. 4. Fig. 4 is a block diagram showing the functional configuration of the information processing device according to the second embodiment. Note that in Fig. 4, the same elements as those shown in Fig. 2 are denoted by the same reference numerals.

[0034] 4, the information processing device 10 according to the second embodiment is configured to include, as components for realizing its functions, a first score acquisition unit 110 and a second score acquisition unit 120. In particular, the second score acquisition unit 120 according to the second embodiment includes a score storage unit 121, a distribution estimation unit 122, and a score conversion unit 123.

[0035] The score storage unit 121 is configured to be able to store a plurality of matching scores obtained through one-to-one matching (hereinafter referred to as "third matching scores" as appropriate). The third matching score may be, for example, an other-person score from one-to-one matching (i.e., a score between two people who are different from each other). The score storage unit 121 may store a third matching score obtained through one-to-one matching performed in advance by a user, for example. Alternatively, the score storage unit 121 may have a function to automatically collect and store third matching scores, for example. The plurality of third matching scores stored in the score storage unit 121 are configured to be able to be read out as appropriate by the distribution estimation unit 122.

[0036] The distribution estimation unit 122 estimates the distribution of fourth matching scores obtained by 1:N matching (where N corresponds to N in the 1:N matching performed by the first score acquisition unit 110) based on the plurality of third matching scores stored in the score storage unit 121. Note that the distribution of fourth matching scores here is a specific example of the "quantity dependent on N" described in the first embodiment. The fourth matching score may be, for example, an other score in 1:N matching (for example, the kth other score: the kth score out of N people). The method for estimating the distribution of fourth matching scores is not particularly limited. A specific example of a method for estimating the distribution of fourth matching scores will be described in detail in another embodiment described later.

[0037] The score conversion unit 123 is configured to convert the first matching score based on the distribution of the fourth matching score estimated by the distribution estimation unit 122, and acquire the second matching score. For example, the score conversion unit 123 may apply a conversion function determined according to the distribution of the fourth matching score to the first matching score to acquire the second matching score. Specific examples of conversion by the score conversion unit 123 will be described in detail in other embodiments described later.

[0038] (Operation flow) Next, the flow of operations of the information processing device 10 according to the second embodiment will be described with reference to Fig. 5. Fig. 5 is a flowchart showing the flow of operations of the information processing device according to the second embodiment. Note that in Fig. 5, the same processes as those shown in Fig. 3 are denoted by the same reference numerals.

[0039] 5, when the operation of the information processing device 10 according to the second embodiment starts, first, the first score acquiring unit 110 acquires target data from a matching target (step S101). Then, the first score acquiring unit 110 performs one-to-N matching between the acquired target data and N registered data items that have been registered in advance, and acquires a first matching score (step S102). The first score acquiring unit 110 outputs the acquired first matching score to the second score acquiring unit 120.

[0040] Subsequently, distribution estimation unit 122 in second score acquisition unit 120 reads out the third matching scores stored in score storage unit 121 (step S201). Then, distribution estimation unit 122 estimates the distribution of the fourth matching scores based on the read out third matching scores (step S202). Distribution estimation unit 122 outputs the estimated distribution of the fourth matching scores to score conversion unit 123.

[0041] Next, the score conversion unit 123 converts the first matching score based on the distribution of the fourth matching score estimated by the distribution estimation unit 122, and acquires the second matching score (step S203). Then, the second score acquisition unit 120 outputs the acquired second matching score (step S104).

[0042] (Technical Effects) Next, the technical effects obtained by the information processing device 10 according to the second embodiment will be described.

[0043] As described with reference to FIGS. 4 and 5 , in the information processing device 10 according to the second embodiment, the distribution of the 1-to-N matching scores (i.e., the fourth matching scores) is estimated based on a plurality of pre-stored 1-to-1 matching scores (i.e., the third matching scores). Then, the first matching scores are converted into the second matching scores based on the distribution of the 1-to-N matching scores. In this way, the 1-to-N matching scores can be converted into appropriate values using a plurality of 1-to-1 matching scores. In other words, the 1-to-N matching scores can be converted into appropriate values without preparing the distribution of the 1-to-N matching scores in advance. Note that it is not easy to prepare the distribution of the 1-to-N matching scores for various patterns where N is different. On the other hand, it is relatively easy to prepare multiple (N or more) 1-to-1 matching scores. Therefore, in the second embodiment, it is possible to acquire appropriate matching scores while reducing the effort and cost required for preparing data in advance.

[0044] <Third embodiment> An information processing device 10 according to the third embodiment will be described with reference to Fig. 6. The third embodiment differs from the second embodiment described above only in some of its operations, and other parts may be the same as 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.

[0045] (Operation flow) First, the flow of operations of the information processing device 10 according to the third embodiment will be described with reference to Fig. 6. Fig. 6 is a flowchart showing the flow of operations of the information processing device according to the third embodiment. Note that in Fig. 8, the same processes as those shown in Fig. 5 are denoted by the same reference numerals.

[0046] 8, when the operation of the information processing device 10 according to the third embodiment starts, first, the first score acquiring unit 110 acquires target data from a matching target (step S101). Then, the first score acquiring unit 110 performs one-to-N matching between the acquired target data and N registered data items that have been registered in advance, and acquires a first matching score (step S102). The first score acquiring unit 110 outputs the acquired first matching score to the second score acquiring unit 120.

[0047] Next, the distribution estimation unit 122 in the second score acquisition unit 120 reads out the third matching scores stored in the score storage unit 121 (step S201). Then, the distribution estimation unit 122 applies the formula of order statistics to the read out third matching scores (for example, using it as an approximation) to estimate the distribution of the fourth matching scores (step S301). The formula of order statistics here can be expressed, for example, as in the following equation (1).

[0048]

number

[0049] Next, the score conversion unit 123 converts the first matching score based on the distribution of the estimated fourth matching score to obtain a second matching score (step S203). Then, the second score acquisition unit 120 outputs the acquired second matching score (step S104).

[0050] (Technical Effects) Next, the technical effects obtained by the information processing device 10 according to the third embodiment will be described.

[0051] 6, in the information processing device 10 according to the third embodiment, the distribution of the 1-to-N matching scores (i.e., the distribution of the fourth matching scores) is estimated by applying the formula for order statistics. In this way, the distribution of the 1-to-N matching scores can be easily and accurately estimated using the 1-to-1 matching scores (i.e., the third matching scores).

[0052] <Fourth embodiment> An information processing device 10 according to the fourth embodiment will be described with reference to Fig. 7. The fourth embodiment differs from the second embodiment described above only in some of its operations, and other parts may be the same as the first to third 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.

[0053] (Operation flow) First, the flow of operations of the information processing device 10 according to the fourth embodiment will be described with reference to Fig. 7. Fig. 7 is a flowchart showing the flow of operations of the information processing device according to the fourth embodiment. Note that in Fig. 7, the same processes as those shown in Fig. 5 are denoted by the same reference numerals.

[0054] 7, when the operation of the information processing device 10 according to the fourth embodiment starts, first, the first score acquiring unit 110 acquires target data from a matching target (step S101). Then, the first score acquiring unit 110 performs one-to-N matching between the acquired target data and N registered data items that have been registered in advance, and acquires a first matching score (step S102). The first score acquiring unit 110 outputs the acquired first matching score to the second score acquiring unit 120.

[0055] Next, the second score acquiring unit 120 determines whether the value of N has changed since the previous time (i.e., the previous time the second matching score was acquired) (step S401). If N has changed (step S401: YES), the same processing as in the second embodiment already described (see FIG. 5) is executed. That is, the distribution estimating unit 122 in the second score acquiring unit 120 reads out the third matching score stored in the score storage unit 121 (step S201). Then, the distribution estimating unit 122 estimates the distribution of the fourth matching score based on the read third matching score (step S202).

[0056] On the other hand, if N has not changed (step S401: NO), distribution estimation unit 122 reads out the previously estimated distribution and outputs it to score conversion unit 123 (step S402). In other words, if N has not changed, distribution estimation unit 122 executes a process in which the previously estimated distribution is reused without estimating a new distribution of the fourth matching score.

[0057] Next, score conversion unit 123 converts the first matching score based on the distribution of the fourth matching score estimated by distribution estimation unit 122 (specifically, the newly estimated distribution if N has changed, or the previous distribution if N has not changed) to obtain a second matching score (step S203). Then, second score acquisition unit 120 outputs the acquired second matching score (step S104).

[0058] (Technical Effects) Next, the technical effects obtained by the information processing device 10 according to the fourth embodiment will be described.

[0059] 7, in the information processing device 10 according to the fourth embodiment, the distribution of 1:N matching scores (i.e., the distribution of fourth matching scores) is estimated every time the number of matching cases N changes. In this way, even if N changes, it is possible to acquire an appropriate matching score according to the changed N. Furthermore, if N does not change, the previous distribution is used, and therefore the processing load can be reduced compared to when a distribution is estimated every time.

[0060] Fifth Embodiment An information processing device 10 according to the fifth embodiment will be described with reference to Figures 8 and 9. The fifth embodiment differs only in part of the configuration and operation from the first to fourth embodiments described above, and other parts may be the same as the first to fourth 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.

[0061] (Functional configuration) First, the functional configuration of the information processing device 10 according to the fifth embodiment will be described with reference to Fig. 8. Fig. 8 is a block diagram showing the functional configuration of the information processing device according to the fifth embodiment. Note that in Fig. 8, the same elements as those shown in Fig. 4 are denoted by the same reference numerals.

[0062] As shown in Fig. 8, the information processing device 10 according to the fifth embodiment is configured to include, as components for realizing its functions, a first score acquisition unit 110, a second score acquisition unit 120, and a matching result determination unit 130. That is, the information processing device 10 according to the fifth embodiment further includes the matching result determination unit 130 in addition to the configuration of the second embodiment (see Fig. 4). The matching result determination unit 130 may be a processing block realized by, for example, the above-mentioned processor 11 (see Fig. 1).

[0063] The matching result determination unit 130 is configured to be able to determine the matching result using the second matching score. For example, the matching result determination unit 130 may be configured to be able to determine whether the matching is successful or unsuccessful based on the magnitude of the second matching score. The matching result determination unit 130 may store, for example, a determination threshold to be compared with the second matching score, and determine whether the matching is successful or unsuccessful based on whether the second matching score exceeds the determination threshold. The matching result may be, for example, an identity authentication result in biometric authentication. In this case, the matching result determination unit 130 may output as the matching result whether the person being matched is the registered person or a different person.

[0064] The score conversion unit 123 according to this embodiment is configured to convert the first score so that the second matching score and the False Positive Identification Rate in the matching result determination unit 130 described above have a predetermined relationship. The predetermined relationship may be set in advance or may be input by the user each time. In other words, the predetermined relationship may be changeable as appropriate. Specific examples of conversion will be described in detail in the following operation description.

[0065] (Operation flow) Next, the flow of operations of the information processing device 10 according to the fifth embodiment will be described with reference to Fig. 9. Fig. 9 is a flowchart showing the flow of operations of the information processing device according to the fifth embodiment. Note that in Fig. 9, the same processes as those shown in Fig. 5 are denoted by the same reference numerals.

[0066] 9, when the operation of the information processing device 10 according to the fifth embodiment starts, first, the first score acquiring unit 110 acquires target data from a matching target (step S101). Then, the first score acquiring unit 110 performs one-to-N matching between the acquired target data and N registered data items that have been registered in advance, and acquires a first matching score (step S102). The first score acquiring unit 110 outputs the acquired first matching score to the second score acquiring unit 120.

[0067] Subsequently, distribution estimation unit 122 in second score acquisition unit 120 reads out the third matching scores stored in score storage unit 121 (step S201). Then, distribution estimation unit 122 estimates the distribution of the fourth matching scores based on the read out third matching scores (step S202). Distribution estimation unit 122 outputs the estimated distribution of the fourth matching scores to score conversion unit 123.

[0068] Next, the score conversion unit 123 reads a predetermined relationship (step S501). That is, the score conversion unit 123 reads the relationship between a preset second matching score and the false acceptance classification rate in the matching result determination unit 130 described above. Then, the score conversion unit 123 converts the first matching score so as to satisfy the predetermined relationship based on the distribution of the fourth matching score estimated by the distribution estimation unit 122, and acquires the second matching score (step S502). Then, the second score acquisition unit 120 outputs the acquired second matching score (step S104).

[0069] For example, it is assumed that the distribution estimation unit 122 estimates the complementary cumulative distribution I(s|k=1) of the first other score expressed by the following formula (2) as the distribution of the fourth matching score.

[0070]

number

[0071] In this case, the score conversion unit 123 prepares a conversion function expressed by the following formula (3) based on the above distribution.

[0072]

number

[0073] In the above example, when the converted second matching score is "0.4", the false acceptance classification rate is "1e-2", and when the converted second matching score is "0.6", the false acceptance classification rate is "1e-3". Note that the relationship given here is merely an example, and the predetermined relationship can be set appropriately under desired conditions.

[0074] (Technical Effects) Next, the technical effects obtained by the information processing device 10 according to the fifth embodiment will be described.

[0075] 8 and 9, in the information processing device 10 according to the fifth embodiment, the first matching score is converted so that there is a predetermined relationship between the second matching score and the false acceptance classification rate in the matching result. In this way, the matching score can be converted (i.e., calibrated) so that a desired determination result can be obtained in the matching process.

[0076] 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.

[0077] 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 processing by themselves, but also includes programs that execute processing by operating on an OS in cooperation with other software or functions of an expansion board. 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.

[0078] <Additional Notes> The above-described embodiment may be further described as follows, but is not limited to the following.

[0079] (Appendix 1) The information processing device described in Appendix 1 is an information processing device that includes a first score acquisition means that performs one-to-N matching between target data acquired from a matching target and N registered data items that have been registered in advance, and acquires a first matching score, and a second score acquisition means that converts the first matching score based on an amount that depends on the number N of matching items in the registered data, and acquires a second matching score.

[0080] (Appendix 2) The information processing device described in Supplementary Note 2 is the information processing device described in Supplementary Note 1, wherein the second score acquisition means includes a storage means for storing a plurality of third matching scores obtained by one-to-one matching, an estimation means for estimating a distribution of fourth matching scores obtained by one-to-N matching corresponding to the number of matching cases N based on the plurality of third matching scores, and a score conversion means for converting the first matching score based on the distribution of the fourth matching score and obtaining the second matching score.

[0081] (Appendix 3) The information processing device described in Supplementary Note 3 is the information processing device described in Supplementary Note 2, wherein the estimation means estimates the distribution of the fourth matching scores by applying a formula for order statistics to the plurality of third matching scores.

[0082] (Appendix 4) The information processing device according to Supplementary Note 4 is the information processing device according to Supplementary Note 2 or 3, wherein the estimation means estimates the distribution of the fourth matching scores every time the number of matching cases N changes.

[0083] (Appendix 5) The information processing device described in Supplementary Note 5 is the information processing device described in any one of Supplementary Notes 2 to 4, further comprising a matching result determination means that determines a matching result using the second matching score, and the score conversion means converts the first score so that the second matching score and the false acceptance identification rate in the matching result have a predetermined relationship.

[0084] (Appendix 6) The information processing method described in Supplementary Note 6 is an information processing method in which, by at least one computer, one-to-N matching is performed between target data acquired from a matching target and N registered data items that have been registered in advance, a first matching score is obtained, and the first matching score is converted based on an amount that depends on the number N of matching items of the registered data, thereby obtaining a second matching score.

[0085] (Appendix 7) The recording medium described in Appendix 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 performing one-to-n matching between target data acquired from a matching target and N registered data items that have been registered in advance, obtaining a first matching score, and converting the first matching score based on an amount that depends on the number N of matching items of the registered data, thereby obtaining a second matching score.

[0086] (Appendix 8) The computer program described in Appendix 8 is a computer program that causes at least one computer to execute an information processing method, which includes performing one-to-N matching between target data acquired from a matching target and N registered data items that have been registered in advance, obtaining a first matching score, and converting the first matching score based on an amount that depends on the number N of matching items in the registered data, thereby obtaining a second matching score.

[0087] (Appendix 9) The information processing system described in Appendix 9 is an information processing system including a first score acquisition means that performs one-to-N matching between target data acquired from a matching target and N registered data items that have been registered in advance, and acquires a first matching score, and a second score acquisition means that converts the first matching score based on an amount that depends on the number N of matching items in the registered data, and acquires a second matching score.

[0088] 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. [Explanation of symbols]

[0089] 10. Information processing equipment 11 processors 14 Storage device 110 First Score Acquisition Section 120 Second Score Acquisition Section 121 Score memory section 122 Distribution estimation part 123 Score conversion section 130 Matching result determination unit

Claims

1. a first score acquisition means for performing one-to-N matching between target data acquired from a matching target and N registered data items registered in advance, and acquiring a first matching score; a second score acquisition means for converting the first matching score based on an amount that depends on the number N of matching records of the registered data, and acquiring a second matching score; Equipped with The second score acquisition means a storage means for storing a plurality of third matching scores obtained by one-to-one matching; an estimation means for estimating a distribution of fourth matching scores obtained by one-to-N matching corresponding to the number N of matching records, based on the plurality of third matching scores; score conversion means for converting the first matching score based on the distribution of the fourth matching score to obtain the second matching score; Equipped with Information processing device.

2. the estimation means estimates a distribution of the fourth matching scores by applying an order statistics formula to the plurality of third matching scores; The information processing device according to claim 1 .

3. the estimation means estimates the distribution of the fourth matching scores every time the number of matching cases N changes; 3. The information processing device according to claim 1 or 2.

4. further comprising a matching result determination means for determining a matching result using the second matching score, the score conversion means converts the first matching score so that the second matching score and a false positive identification rate in the matching result have a predetermined relationship. The information processing device according to claim 1 .

5. by at least one computer, performing one-to-N matching between target data acquired from a matching target and N registered data items registered in advance, and obtaining a first matching score; converting the first matching score based on an amount that depends on the number N of matching records of the registered data to obtain a second matching score; When obtaining the second score, storing a plurality of third matching scores obtained by one-to-one matching; estimating a distribution of fourth matching scores obtained by one-to-N matching corresponding to the number N of matching records based on the plurality of third matching scores; converting the first matching score based on the distribution of the fourth matching score to obtain the second matching score; Information processing methods.

6. At least one computer performing one-to-N matching between target data acquired from a matching target and N registered data items registered in advance, and obtaining a first matching score; converting the first matching score based on an amount that depends on the number N of matching records of the registered data to obtain a second matching score; When obtaining the second score, storing a plurality of third matching scores obtained by one-to-one matching; estimating a distribution of fourth matching scores obtained by one-to-N matching corresponding to the number N of matching records based on the plurality of third matching scores; converting the first matching score based on the distribution of the fourth matching score to obtain the second matching score; A computer program that executes an information processing method.

Images