Information processor, magnetic recording reproduction device, and magnetic recording reproduction system

Abstract

To provide an information processor, a magnetic recording reproduction device, and a magnetic recording reproduction system that can improve efficiency.SOLUTION: According to an embodiment, an information processor includes an acquisition part and a processing part. The processing part is configured to carry out first operation. The first operation includes first decoding, first accuracy evaluation, second decoding, and first determination operation. The first decoding includes processing a portion targeted for reproduction signal decoding by a first processing configuration to derive a first decoding result. When first accuracy of the first decoding result does not satisfy a first criterion, the second decoding includes processing the portion targeted for decoding by a second processing configuration to derive a second decoding result. The second processing configuration is at least partially different from the first processing configuration.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to an information processing device, a magnetic recording and reproducing device, and a magnetic recording and reproducing system. [Background technology]

[0002] For example, information recorded on a magnetic recording medium is reproduced by an information processing device, and it is desirable to improve the efficiency of the information processing device. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] US Patent Application Publication No. 2020 / 0389188 Summary of the Invention [Problem to be solved by the invention]

[0004] The embodiments of the present invention provide an information processing device, a magnetic recording and reproducing device, and a magnetic recording and reproducing system that can improve efficiency. [Means for solving the problem]

[0005] According to an embodiment of the present invention, an information processing device includes an acquisition unit and a processing unit. The acquisition unit is configured to acquire a reproduction signal based on a signal obtained from a magnetic recording medium. The processing unit is configured to perform a first operation. The first operation includes first decoding, first accuracy evaluation, second decoding, and a first determination operation. The first decoding process a portion of the reproduction signal to be decoded using a first processing configuration to derive a first decoding result. The first accuracy evaluation includes evaluating a first accuracy of the first decoding result. The second decoding process process the portion to be decoded using a second processing configuration to derive a second decoding result if the first accuracy does not satisfy a first criterion. At least a part of the second processing configuration is different from the first processing configuration. The first determination operation determines a first operation decoding result for the portion to be decoded. If the first accuracy does not satisfy the first criterion, the first operation decoding result is based on the second decoding result. If the first accuracy satisfies the first criterion, the first operation decoding result is based on the first decoding result. [Brief explanation of the drawings]

[0006] [Figure 1] FIG. 1 is a schematic diagram illustrating an information processing device and an information recording / reproducing device according to the first embodiment. [Figure 2] FIG. 2 is a flowchart illustrating the operations of the information processing device and the information recording / reproducing device according to the first embodiment. [Figure 3] FIG. 3 is a schematic diagram illustrating the information processing apparatus according to the first embodiment. [Figure 4] FIG. 4 is a flowchart illustrating the operations of the information processing device and the information recording / reproducing device according to the first embodiment. [Figure 5] FIG. 5 is a flowchart illustrating the operations of the information processing device and the information recording / reproducing device according to the first embodiment. [Figure 6] FIG. 6 is a flowchart illustrating the operations of the information processing device and the information recording / reproducing device according to the first embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0007] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. In this specification and in each drawing, elements similar to those previously described with reference to the previous drawings are designated by the same reference numerals, and detailed descriptions thereof will be omitted where appropriate.

[0008] (First embodiment) FIG. 1 is a schematic diagram illustrating an information processing device and an information recording / reproducing device according to the first embodiment. 1, a magnetic recording and reproducing device 210 according to the embodiment includes an information processing device 70, a magnetic recording medium 80, and a reproducing unit 80R. The magnetic recording medium 80 and the reproducing unit 80R may be included in a recording unit 80D, which may be included in, for example, a magnetic disk (HDD: Hard Disk Drive). The magnetic recording and reproducing device 210 may further include, for example, an SSD (Solid State Drive).

[0009] The reproducing unit 80R can reproduce a signal 80S corresponding to information recorded on the magnetic recording medium 80. The reproducing unit 80R includes, for example, a magnetic head 80H. The reproducing unit 80R outputs a signal 80S corresponding to the reproduced information. The signal 80S is an electrical signal. Information may be recorded on the magnetic recording medium 80 by the magnetic head 80H.

[0010] The information processing device 70 includes an acquisition unit 70i and a processing unit 70p. The acquisition unit 70i is configured to acquire a reproduction signal RS based on a signal 80S obtained from the magnetic recording medium 80. The reproduction signal RS may be based on a signal obtained by amplifying the signal 80S. The reproduction signal RS may be a digital signal obtained by AD (Analog to Digital) converting the signal 80S. The acquisition unit 70i may be, for example, an interface.

[0011] The reproduction signal RS acquired by the acquisition unit 70i is processed by a processing unit 70p (for example, processing circuitry), and the processing result of the processing unit 70p is output from the processing unit 70p.

[0012] An example of the operation (playback operation) performed by the processing unit 70p will be described below. FIG. 2 is a flowchart illustrating the operations of the information processing device and the information recording / reproducing device according to the first embodiment. As shown in FIG. 2, processing unit 70p is configured to perform a first operation OP1.

[0013] The first operation OP1 includes, for example, a first decoding (step S110), a first accuracy evaluation (step S120), and a second decoding (step S130). The first operation OP1 may further include a first determination operation (step S140).

[0014] In the first decoding (step S110), the processing unit 70p processes the decoding target portion of the reproduction signal RS using a first processing configuration to derive a first decoding result DR1. In one example, the first processing configuration is a model of neural network processing. In another example, the first processing configuration may include PRML (Partial Response Maximum Likelihood) processing or the like.

[0015] The first accuracy evaluation (step S120) includes the processing unit 70p evaluating the first accuracy of the first decoding result DR1 (step S121). For example, the processing unit 70p determines whether the first decoding result DR1 satisfies a first criterion. For example, if the first decoding result DR1 satisfies the first criterion, it corresponds to a high probability that the first decoding result DR1 has been properly decoded. For example, if the first decoding result DR1 does not satisfy the first criterion, it corresponds to a high probability that the first decoding result DR1 contains an error.

[0016] If the first accuracy does not satisfy the first criterion, the processing unit 70p performs second decoding. In the second decoding (step S130), the processing unit 70p processes the portion to be decoded using a second processing configuration to derive a second decoding result DR2. At least a part of the second processing configuration is different from the first processing configuration. The second processing configuration may be one model of neural network processing.

[0017] For example, if the first processing configuration and the second processing configuration are neural network processes, the neural network model in the second processing configuration is different from the neural network model in the first processing configuration.

[0018] In a first determination operation (step S140), the processing unit 70p determines the decoding result (first operation decoding result OR1) of the portion to be decoded. If the first precision of the first decoding result DR1 does not satisfy the first criterion, the first operation decoding result OR1 is based on the second decoding result DR2. If the first precision satisfies the first criterion, the first operation decoding result OR1 is based on the first decoding result DR1. In one example, if the first precision of the first decoding result DR1 does not satisfy the first criterion, the first operation decoding result OR1 is the second decoding result DR2. In one example, if the first precision satisfies the first criterion, the first operation decoding result OR1 is the first decoding result DR1.

[0019] In this way, in the embodiment, whether or not to perform the second decoding is determined based on the result of the first decoding. This allows, for example, decoding to be performed in a short time. For example, a more accurate decoding result can be obtained efficiently. According to the embodiment, it is possible to provide an information processing device that can improve efficiency.

[0020] In one example, the scale (second scale) of the second processing configuration is larger than the scale (first scale) of the first processing configuration, and the second decoding using the second processing configuration can achieve decoding with higher accuracy than the first decoding using the first processing configuration.

[0021] For example, in a reference example in which decoding processing is performed using only the second processing configuration without using the first processing configuration, a long processing time is required, and the size of the circuit that performs the second decoding is likely to become large.

[0022] In this embodiment, for example, only data that could not be properly decoded in the first decoding is processed in the second decoding. This reduces processing time. For example, high-precision decoding is possible while maintaining a small circuit scale.

[0023] Below, examples of the first processing configuration and the second processing configuration will be described. FIG. 3 is a schematic diagram illustrating the information processing apparatus according to the first embodiment. In this example, the first processing configuration CF1 and the second processing configuration CF2 are neural network models. As shown in Figure 3, the first processing configuration CF1 includes a first neural network process using a first model NN1. The second processing configuration CF2 includes a second neural network process using a second model NN2.

[0024] For example, the first model NN1 may be different from the second model NN2. For example, at least one of the elements included in the first model NN1 may be different from one of the elements included in the second model NN2. For example, at least one of the elements related to the performance of the neural network and the elements related to the processing efficiency of the neural network may be different between the first model NN1 and the second model NN2. For example, the number of second parameters of the second model NN2 is larger than the number of first parameters of the first model NN1. For example, the layer configuration of the second model NN2 is different from the layer configuration of the first model NN1.

[0025] In this example, the first model NN1 includes a first input layer IN1. The second model NN2 includes a second input layer IN2. In an embodiment, for example, the number of second input layer nodes IND2 of the second input layer IN2 is greater than the number of first input layer nodes IND1 of the first input layer IN1.

[0026] In this example, the first model NN1 includes a first hidden layer M1. The second model NN2 includes a second hidden layer M2. For example, the number of second hidden layer nodes MND2 in the second hidden layer M2 may be greater than the number of first hidden layer nodes MND1 in the first hidden layer M1.

[0027] The number of layers included in the second intermediate layer M2 may be greater than the number of layers included in the first intermediate layer M1.

[0028] In this example, the first model NN1 includes a first output layer OT1. The second model NN2 includes a second output layer OT2. For example, the amount of information output by the second output layer OT2 may be equal to or less than the amount of information output by the first output layer OT1. For example, the second output layer OT2 is an output layer corresponding to N class classifications. In this case, the first output layer OT1 may be an output layer corresponding to M class classifications. "N" and "M" are positive integers. "N" is equal to or less than "M". For example, the number of second output layer nodes OND2 of the second output layer OT2 may be equal to or less than the number of first output layer nodes OND1 of the first output layer OT1.

[0029] Such a combination of the first model NN1 and the second model NN2 may be applied to the first processing configuration CF1 and the second processing configuration CF2.

[0030] A technique related to neural networks may be applied to the first model NN1 and the second model NN2, and may be, for example, at least one selected from the group consisting of a recurrent neural network (RNN), a convolutional neural network (CNN), and a transformer.

[0031] In one example embodiment, one of the first processing configuration CF1 and the second processing configuration CF2 may be related to at least a portion of PRML processing, and the other of the first processing configuration CF1 and the second processing configuration CF2 may be related to neural network processing. For example, the first processing configuration CF1 may include at least a portion of PRML processing. In this case, the second processing configuration CF2 may include second neural network processing using a second model NN2.

[0032] The PRML processing may include, for example, maximum likelihood decoding and waveform equalization. The waveform equalization may include, for example, waveform correction. For example, at least a portion of the PRML processing may include maximum likelihood decoding. For example, at least a portion of the PRML processing may not include waveform equalization.

[0033] In an embodiment, the first processing configuration CF1 and the second processing configuration CF2 may include at least a portion of PRML processing. In this case, the processing amount of the first processing configuration CF1 may be different from the processing amount of the second processing configuration CF2. For example, the number of states of maximum likelihood decoding in the PRML processing in the first processing configuration CF1 may be different from the number of states of maximum likelihood decoding in the PRML processing in the second processing configuration CF2. For example, the number of states of the trellis diagram for maximum likelihood decoding in the first processing configuration CF1 may be smaller than the number of states of the trellis diagram for maximum likelihood decoding in the second processing configuration CF2.

[0034] For example, the first operation OP1 may include another first accuracy evaluation. The another first accuracy evaluation is performed after the second decoding (step S130). In the another first accuracy evaluation, the processing unit 70p evaluates the accuracy of the second decoding result DR2. For example, the processing unit 70p determines whether the second decoding result DR2 satisfies a first criterion. For example, if the second decoding result DR2 satisfies the first criterion, it corresponds to a high probability that the second decoding result DR2 has been properly decoded. For example, if the second decoding result DR2 does not satisfy the first criterion, it corresponds to a high probability that the second decoding result DR2 contains an error. The first criterion in the another first accuracy evaluation may be the same as or different from the first criterion in the first accuracy evaluation. If the second decoding result DR2 does not satisfy the first criterion in the another first accuracy evaluation, the processing unit 70p may perform another process and then perform the first determination operation (step S140). The first operation OP1 may further include such another operation.

[0035] The first operation OP1 may include performing the first decoding (step S110) multiple times before the first accuracy evaluation (step S120).The first operation OP1 may include performing the second decoding (step S130) multiple times after the first accuracy evaluation (step S120).

[0036] FIG. 4 is a flowchart illustrating the operations of the information processing device and the information recording / reproducing device according to the first embodiment. As shown in FIG. 4, in this example, the first accuracy evaluation (step S120) further includes performing error detection processing on the first decoding result DR1 (step S122). For example, the first decoding result DR1 is processed based on an error correction code (ECC) (step S122). For example, errors in the first decoding result DR1 may be detected using a code. For example, errors in the first decoding result DR1 may be detected using at least one of a Reed-Solomon code and an LDPC code. For example, errors in the first decoding result DR1 may be detected using a neural network.

[0037] If no error is detected as a result of the error detection process, the first accuracy satisfies the first criterion. If an error is detected as a result of the error detection process, the first accuracy does not satisfy the first criterion.

[0038] For example, if the first precision of the first decoding result DR1 satisfies the first criterion, an error in the first decoding result DR1 is not detected. If the first precision does not satisfy the first criterion, an error in the first decoding result DR1 is detected.

[0039] In the example of Fig. 4, the unit of evaluation for whether the first criterion is satisfied may be the unit of the error detection process. For example, when a code is used for error detection, error detection may be performed for a plurality of bits as one unit. In this case, before step S121 (evaluation for whether the first criterion is satisfied), the first decoding may be performed multiple times to decode a number of bits equal to or greater than the unit for error detection. Similarly, if the first criterion is not satisfied, the second process may be performed multiple times.

[0040] As shown in FIG. 1, the processing unit 70p may include a buffer 75 (e.g., a memory). The buffer 75 is configured to record, for example, decoded information of a number of bits equal to or greater than the error detection unit. For example, the processing unit 70p performs one or more first decoding operations and stores the results in the buffer 75. The processing unit 70p may perform error detection processing by referring to the decoded information of the number of bits equal to the error detection unit stored in the buffer 75. The first operation OP1 includes, for example, performing the first decoding operation until the first decoding result DR1 fills the buffer.

[0041] The second decoding may be performed multiple times. A portion of bits in a bit string in which an error is detected in the error detection process may be processed in the second process. If the error detection process can distinguish between bits that do not contain errors and bits that contain errors, only the bits that contain errors may be processed in the second process.

[0042] FIG. 5 is a flowchart illustrating the operations of the information processing device and the information recording / reproducing device according to the first embodiment. In the example of FIG. 5, the first accuracy evaluation (step S120) may include deriving an evaluation value EV1 by calculating the first decoding result DR1 using an evaluation formula (step S123). The first accuracy evaluation may be performed using the evaluation value by calculating the first decoding result DR1 using the evaluation formula. For example, the first accuracy evaluation is performed using the result of a logical operation using the evaluation value. For example, the first accuracy evaluation is performed using the result of a logical operation regarding whether the first decoding result DR1 exceeds a first threshold. For example, if the evaluation value EV1 is equal to or greater than the first threshold, the first accuracy of the first decoding result DR1 satisfies the first criterion. If the evaluation value EV1 is less than the first threshold, the first accuracy does not satisfy the first criterion.

[0043] In the first accuracy evaluation (step S120), if the first accuracy does not satisfy the first criterion, the processing unit 70p performs a second decoding (step S130). In the first accuracy evaluation (step S120), if the first accuracy satisfies the first criterion, the processing unit 70p performs, for example, a first determination operation (step S140).

[0044] If the first processing configuration CF1 includes a neural network, the evaluation value EV1 may include the output of the neural network. For example, the evaluation value EV1 may be the result of calculating the output of the neural network. For example, the evaluation value EV1 may be the value of the output of the neural network.

[0045] The evaluation value EV1 may be, for example, a probability related to the output of the neural network. The evaluation value EV1 may be, for example, a result of calculating the probability related to the output of the neural network. The probability related to the output of the neural network includes, for example, the probability that a bit of the output of the neural network is a predetermined value. For example, the evaluation value EV1 may be the probability that a bit of the output of the neural network is "0" or "1." For example, the evaluation value EV1 may be the probability that the bit string of the output of the neural network is "00," "01," "10," or "11." For example, if the probability that the output of the neural network is "0" or "1" is equal to or greater than a first threshold, the first criterion is met. If the probability that the output of the neural network is "0" or "1" is less than the first threshold, the first criterion is not met.

[0046] If the first processing configuration CF1 includes at least a portion of PRML processing, the evaluation value EV1 may include an output of at least a portion of the PRML processing. The evaluation value EV1 may include, for example, an output of maximum likelihood decoding processing. The evaluation value EV1 may be a result of calculating the output of at least a portion of the PRML processing (e.g., maximum likelihood decoding). The evaluation value EV1 may be the output of at least a portion of the PRML processing (e.g., maximum likelihood decoding). For example, the evaluation value EV1 may include log-likelihood information output by a Viterbi algorithm. For example, if the likelihood of "0" or "1" is equal to or greater than a first threshold, the first criterion is met. For example, if the likelihood of "0" or "1" is less than the first threshold, the first criterion is not met.

[0047] FIG. 6 is a flowchart illustrating the operations of the information processing device and the information recording / reproducing device according to the first embodiment. 6, the first operation OP1 further includes a second accuracy evaluation (step S150) and a third decoding (step S160). The rest of the configuration may be the same as the configuration described with reference to FIGS.

[0048] The second accuracy evaluation (step S150) includes evaluating the second accuracy of the second decoding result DR2 (step S151). The third decoding (step S160) processes the portion to be decoded using a third processing configuration to derive a third decoding result DR3 if the second accuracy does not satisfy the second criterion. At least a part of the third processing configuration is different from the second processing configuration CF2. At least a part of the third processing configuration may be different from the first processing configuration CF1.

[0049] In evaluating the second precision of the second decoding result DR2 (step S151), if the second precision does not satisfy the second criterion, the first operation decoding result OR1 is based on the third decoding result DR3. If the second precision satisfies the second criterion, the first operation decoding result OR1 is based on, for example, the second decoding result DR2. This enables decoding with higher precision.

[0050] In this example, the first accuracy evaluation (step S120) may include deriving an evaluation value EV1 by calculating the first decoding result DR1 using an evaluation formula (step S123). The first accuracy evaluation (step S120) is performed using the evaluation value EV1 by calculating the first decoding result DR1 using the evaluation formula.

[0051] In this example, the second accuracy evaluation (step S150) further includes subjecting the second decoding result DR2 to an error detection process (step S152). If no error is detected as a result of this error detection process, the second accuracy satisfies the second criterion. If an error is detected as a result of this error detection process, the second accuracy does not satisfy the second criterion.

[0052] In the example of FIG. 6, the configuration regarding the difference between the third processing configuration and the second processing configuration CF2 may be, for example, the configuration already described regarding the difference between the second processing configuration CF2 and the first processing configuration CF1. In the first accuracy evaluation and the second accuracy evaluation, the configurations and operations described with reference to FIGS. 2 to 5 may be applied. In the example of FIG. 6, the configurations and operations described with reference to FIGS. 2 to 5 may be applied. For example, a buffer 75 may be provided, and the second decoding result DR2 may be stored in the buffer 75. For example, before the second accuracy evaluation, the second decoding may be performed multiple times. If the second accuracy does not satisfy the second criterion, the third decoding may be performed multiple times.

[0053] As shown in FIG. 1 , the processing unit 70p may include a first processing circuit 71 and a second processing circuit 72. The processing performance of the first processing circuit 71 is different from that of the second processing circuit 72. For example, the processing performance of the first processing circuit 71 is lower than that of the second processing circuit 72. For example, the number of elements included in the first processing circuit 71 (the first number of the multiple first elements) is smaller than the number of elements included in the second processing circuit 72 (the second number of the multiple second elements). For example, the number of multiple arithmetic units included in the first processing circuit 71 is smaller than the number of multiple arithmetic units included in the second processing circuit 72. For example, the storage capacity of the memory included in the first processing circuit 71 is smaller than the storage capacity of the memory included in the second processing circuit 72. For example, the manufacturing process of the first processing circuit 71 is older than the manufacturing process of the second processing circuit 72. For example, the frequency of the first processing circuit 71 is lower than the frequency of the second processing circuit 72. For example, the power consumption of the first processing circuit 71 is lower than the power consumption of the second processing circuit 72. For example, the first processing circuit 71 may be configured to perform a first decoding, and the second processing circuit 72 may be configured to perform a second decoding. The processing performance of the first processing circuit 71 may be the same as the processing performance of the second processing circuit 72.

[0054] One processing circuit included in processing unit 70p may be configured to perform the first decoding and the second decoding.

[0055] For example, the buffer 75 (e.g., a memory) may be included in any processing circuit included in the processing unit 70p. For example, the buffer 75 may be provided separately from the processing circuits (such as the first processing circuit 71 and the second processing circuit 72). For example, the buffer 75 may be provided separately from the processing circuits that perform at least a part of the first decoding and the second decoding.

[0056] (Second embodiment) The second embodiment relates to a magnetic recording and reproducing device 210 (see FIG. 1). The magnetic recording and reproducing device 210 includes an information processing device (information processing device 70) according to the embodiment, a magnetic recording medium 80, and a reproducing unit 80R. The reproducing unit 80R is capable of reproducing a signal 80S corresponding to information recorded on the magnetic recording medium 80. The magnetic recording and reproducing device 210 can improve efficiency.

[0057] (Third embodiment) The third embodiment relates to a magnetic recording and reproducing system 310 (see FIG. 1). The magnetic recording and reproducing system 310 includes an information processing device (information processing device 70) according to the embodiment. The magnetic recording and reproducing system 310 can improve efficiency. In the magnetic recording and reproducing system 310, the information processing device 70 may be provided at a location away from the magnetic recording medium 80.

[0058] For example, the magnetic recording and reproducing system 310 may include a magnetic recording and reproducing device 210 including a magnetic recording medium 80. At least a portion of an information processing device 70 included in the magnetic recording and reproducing system 310 may be provided inside the magnetic recording and reproducing device 210. At least a portion of the information processing device 70 included in the magnetic recording and reproducing system 310 may be provided outside the magnetic recording and reproducing device 210. A portion of the information processing device 70 may be provided inside the magnetic recording and reproducing device 210, and another portion of the information processing device 70 may be provided outside the magnetic recording and reproducing device 210. A reproducing unit 80R of the magnetic recording and reproducing device 210, for example, reproduces waveform information corresponding to one bit from the magnetic recording medium 80. The reproducing unit 80R of the magnetic recording and reproducing device 210 may, for example, output information after digital conversion of the reproduced waveform information. The information processing device 70, for example, decodes the information after digital conversion and outputs information related to one bit.

[0059] For example, the first decoding (step S110) and the first accuracy evaluation (step S120) are performed in a part of the processing unit 70p. The second decoding (step S130) is performed in another part of the processing unit 70p. The part of the processing unit 70p may be provided inside the housing of the magnetic recording and reproducing device 210. The other part of the processing unit 70p may be provided outside the housing of the magnetic recording and reproducing device 210. Communication (transmission and reception of information) between the part of the processing unit 70p and the other part of the processing unit 70p may be performed by any method, such as wired or wireless.

[0060] The information output by the reproducing unit 80R of the magnetic recording and reproducing device 210 may include bit decode information, bit decode reliability information, and waveform information after digital conversion. The magnetic recording and reproducing system 310 may use the bit decode reliability information to process waveform information corresponding to low reliability bits using a second processing configuration CF2.

[0061] The embodiments may include the following technical solutions. (Technical proposal 1) an acquisition unit; a processing unit; Equipped with the acquisition unit is configured to acquire a reproduction signal based on a signal obtained from a magnetic recording medium, the processing unit is configured to perform a first operation; The first operation is a first decoding that processes a decoding target portion of the reproduction signal using a first processing configuration to derive a first decoding result; a first accuracy evaluation including evaluating a first accuracy of the first decoding result; a second decoding that processes the portion to be decoded using a second processing configuration to derive a second decoding result when the first accuracy does not satisfy a first criterion, wherein at least a part of the second processing configuration is different from the first processing configuration; a first determination operation for determining a first operation decoding result of the portion to be decoded; Including, if the first accuracy does not satisfy the first criterion, the first motion decoding result is based on the second decoding result; If the first precision satisfies the first criterion, the first motion decoding result is based on the first decoding result.

[0062] (Technical proposal 2) The information processing device according to Technical Solution 1, wherein the second scale of the second processing configuration is larger than the first scale of the first processing configuration.

[0063] (Technical proposal 3) the first accuracy evaluation further includes processing the first decoding result for error detection; If no error is detected as a result of the error detection process, the first accuracy satisfies the first criterion; The information processing device described in Technical Solution 1 or 2, wherein if an error is detected in the result of the error detection process, the first accuracy does not satisfy the first standard.

[0064] (Technical proposal 4) The information processing device described in Technical Scheme 1 or 2, wherein the first accuracy evaluation is performed using an evaluation value calculated from the first decoding result using an evaluation formula.

[0065] (Technical proposal 5) The information processing device described in Technical Solution 4, wherein the first accuracy evaluation is performed using the result of a logical operation regarding whether the first decoding result exceeds a first threshold value.

[0066] (Technical proposal 6) the first processing configuration includes a first neural network processing using a first model; The information processing device described in Technical Proposal 1 or 2, wherein the second processing configuration includes a second neural network processing using a second model.

[0067] (Technical proposal 7) The information processing device according to Technical Solution 6, wherein the number of second parameters of the second model is greater than the number of first parameters of the first model.

[0068] (Technical proposal 8) The information processing device described in Technical Solution 6, wherein the layer structure of the second model is different from the layer structure of the first model.

[0069] (Technical proposal 9) The first operation is a second accuracy evaluation including evaluating a second accuracy of the second decoding result; a third decoding that processes the decoding target portion using a third processing configuration to derive a third decoding result when the second accuracy does not satisfy a second criterion, wherein at least a part of the third processing configuration is different from the second processing configuration; and further comprising if the second accuracy does not satisfy the second criterion, the first motion decoding result is based on the third decoding result; If the second accuracy satisfies the second criterion, the first motion decoding result is based on the second decoding result; the first accuracy evaluation is performed using an evaluation value calculated by an evaluation formula on the first decoding result, the second accuracy evaluation further includes error detection processing the second decoding result; If no error is detected as a result of the error detection process, the second accuracy satisfies the second criterion; The information processing device described in Technical Solution 1 or 2, wherein if an error is detected in the result of the error detection process, the second accuracy does not satisfy the second standard.

[0070] (Technical proposal 10) the processing unit includes a buffer; the buffer is configured to store a number of bits of a processing unit for error detection; The information processing device according to Technical Solution 1 or 2, wherein the first operation includes performing the first decoding until the result of the first decoding fills the buffer.

[0071] (Technical proposal 11) the first processing configuration includes PRML processing; The information processing device described in Technical Proposal 1 or 2, wherein the second processing configuration includes a second neural network processing using a second model.

[0072] (Technical proposal 12) the first processing configuration includes a first PRML processing; The information processing device described in Technical Solution 1 or 2, wherein the second processing configuration includes a second PRML process.

[0073] (Technical proposal 13) An information processing device described in Technical Proposal 12, wherein a first processing amount of decoding per bit in maximum likelihood decoding in the first PRML processing is different from a second processing amount of decoding per bit in maximum likelihood decoding in the second PRML processing.

[0074] (Technical proposal 14) the processing unit includes a first processing circuit and a second processing circuit; a first processing performance of the first processing circuit is lower than a second processing performance of the second processing circuit; the first processing circuit is configured to perform the first decoding; The information processing device according to Technical Solution 1 or 2, wherein the second processing circuit is configured to perform the second decoding.

[0075] (Technical proposal 15) an acquisition unit; a processing unit; Equipped with the acquisition unit is configured to acquire a reproduction signal based on a signal obtained from a magnetic recording medium, the processing unit is configured to perform a first operation; The first operation is a first decoding that processes a decoding target portion of the reproduction signal using a first processing configuration to derive a first decoding result; a first accuracy evaluation including evaluating a first accuracy of the first decoding result; a second decoding that processes the portion to be decoded using a second processing configuration to derive a second decoding result when the first accuracy does not satisfy a first criterion, wherein at least a part of the second processing configuration is different from the first processing configuration; An information processing device comprising:

[0076] (Technical proposal 16) The information processing device according to Technical Proposal 15, wherein the second scale of the second processing configuration is larger than the first scale of the first processing configuration.

[0077] (Technical proposal 17) the processing unit includes a first processing circuit and a second processing circuit; a first processing performance of the first processing circuit is lower than a second processing performance of the second processing circuit; the first processing circuit is configured to perform the first decoding; The information processing device according to Technical Solution 15 or 16, wherein the second processing circuit is configured to perform the second decoding.

[0078] (Technical proposal 18) An information processing device according to any one of technical proposals 1 to 17; the magnetic recording medium; a reproducing unit capable of reproducing the signal corresponding to the information recorded on the magnetic recording medium; A magnetic recording and reproducing device comprising:

[0079] (Technical proposal 19) A magnetic recording and reproducing system comprising the information processing device according to any one of Technical Schemes 1 to 17.

[0080] (Technical proposal 20) at least a part of the first decoding is performed in a magnetic recording and reproducing device including the magnetic recording medium; The magnetic recording and reproducing system described in Technical Solution 19, wherein at least a part of the second decoding is performed outside the magnetic recording and reproducing device.

[0081] According to the embodiments, it is possible to provide an information processing device, a magnetic recording and reproducing device, and a magnetic recording and reproducing system that can improve efficiency.

[0082] The embodiments of the present invention have been described above with reference to examples. However, the present invention is not limited to these examples. For example, the specific configurations of the elements included in the information processing device, magnetic recording and reproducing device, and magnetic recording and reproducing system, such as the acquisition unit, processing unit, and magnetic recording medium, are within the scope of the present invention as long as a person skilled in the art can implement the present invention in a similar manner and obtain similar effects by appropriately selecting them from within the known range.

[0083] Any combination of two or more elements of each example within the scope of technical feasibility is also included within the scope of the present invention as long as it encompasses the gist of the present invention.

[0084] All information processing devices, magnetic recording and reproducing devices, and magnetic recording and reproducing systems that can be implemented by a person skilled in the art by making appropriate design modifications based on the information processing devices, magnetic recording and reproducing devices, and magnetic recording and reproducing systems described above as embodiments of the present invention also fall within the scope of the present invention, as long as they include the gist of the present invention.

[0085] Within the scope of the concept of the present invention, a person skilled in the art may conceive of various modifications and alterations, and it is understood that these modifications and alterations also fall within the scope of the present invention.

[0086] Although several embodiments of the present invention have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These novel embodiments can be embodied in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their modifications are included within the scope and spirit of the invention, and are also included in the scope of the invention and its equivalents as defined in the claims. [Explanation of symbols]

[0087] 70: Information processing device, 70i: Acquisition unit, 70p: Processing unit, 71, 72: First and second processing circuits, 80: Magnetic recording medium, 80D: Recording unit, 80H: Magnetic head, 80R: Reproduction unit, 80S: Signal, 210: Magnetic recording and reproduction device, 310: Magnetic recording and reproduction system, CF1, CF2: First and second processing configurations, DR1 to DR3: First to third decoding results, EV1: Evaluation value, IN1, IN2: First and second input layers, IND1, IND2: First and second input layer nodes, M1, M2: First and second hidden layers, ML1, ML2: First and second layers, MND1, MND2: First and second hidden layer nodes, NN1, NN2: First and second models, OND1, OND2: First and second output layer nodes, OP1: First operation, OR1: First operation decoding result, OT1, OT2: First and second output layers, RS: Regenerated signal

Claims

1. an acquisition unit; a processing unit; Equipped with the acquisition unit is configured to acquire a reproduction signal based on a signal obtained from a magnetic recording medium, the processing unit is configured to perform a first operation; The first operation includes: a first decoding that processes a decoding target portion of the reproduction signal using a first processing configuration to derive a first decoding result; a first accuracy evaluation including evaluating a first accuracy of the first decoding result; a second decoding that processes the decoding target portion using a second processing configuration to derive a second decoding result when the first accuracy does not satisfy a first criterion, wherein at least a part of the second processing configuration is different from the first processing configuration; and a first determining operation for determining a first operation decoding result of the portion to be decoded; Including, if the first accuracy does not satisfy the first criterion, the first motion decoding result is based on the second decoding result; If the first accuracy satisfies the first criterion, the first motion decoding result is based on the first decoding result.

2. the first accuracy evaluation further includes processing the first decoding result for error detection; If no error is detected as a result of the error detection process, the first accuracy satisfies the first criterion; The information processing device according to claim 1 , wherein, when an error is detected in the result of the error detection process, the first accuracy does not satisfy the first standard.

3. The information processing apparatus according to claim 1 , wherein the first accuracy evaluation is performed using an evaluation value calculated from the first decoded result using an evaluation formula.

4. the first processing configuration includes a first neural network process using a first model; The information processing apparatus according to claim 1 , wherein the second processing configuration includes a second neural network process using a second model.

5. The first operation includes: a second accuracy evaluation including evaluating a second accuracy of the second decoding result; a third decoding that processes the decoding target portion using a third processing configuration to derive a third decoding result when the second accuracy does not satisfy a second criterion, wherein at least a part of the third processing configuration is different from the second processing configuration; and further comprising if the second accuracy does not satisfy the second criterion, the first motion decoding result is based on the third decoding result; if the second accuracy satisfies the second criterion, the first motion decoding result is based on the second decoding result; the first accuracy evaluation is performed using an evaluation value calculated by an evaluation formula on the first decoding result, the second accuracy evaluation further includes processing the second decoding result for error detection; If no error is detected as a result of the error detection process, the second accuracy satisfies the second criterion; The information processing device according to claim 1 , wherein, when an error is detected in the result of the error detection process, the second accuracy does not satisfy the second standard.

6. the first processing configuration includes PRML processing; The information processing apparatus according to claim 1 , wherein the second processing configuration includes a second neural network process using a second model.

7. the processing unit includes a first processing circuit and a second processing circuit; a first processing performance of the first processing circuit is lower than a second processing performance of the second processing circuit; the first processing circuitry is configured to perform the first decoding; The information processing device according to claim 1 , wherein the second processing circuit is configured to perform the second decoding.

8. an acquisition unit; a processing unit; Equipped with the acquisition unit is configured to acquire a reproduction signal based on a signal obtained from a magnetic recording medium, the processing unit is configured to perform a first operation; The first operation includes: a first decoding that processes a decoding target portion of the reproduction signal using a first processing configuration to derive a first decoding result; a first accuracy evaluation including evaluating a first accuracy of the first decoding result; a second decoding that processes the decoding target portion using a second processing configuration to derive a second decoding result when the first accuracy does not satisfy a first criterion, wherein at least a part of the second processing configuration is different from the first processing configuration; and An information processing device comprising:

9. The information processing device according to claim 1 ; the magnetic recording medium; a reproducing unit capable of reproducing the signal corresponding to the information recorded on the magnetic recording medium; A magnetic recording and reproducing device comprising:

10. 10. A magnetic recording and reproducing system comprising the information processing device according to claim 1.

Images