Information processing device, information processing method, and program

Abstract

To provide an information processing device capable of performing accurate correction or a correction proposal to object data.SOLUTION: An information processing device includes acquisition means for acquiring object data, generation means for generating an object vector from the object data, and correction means for comparing the object vector with a reference vector generated from reference data, and executing processing related to the correction of the object data in accordance with a compared result.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present disclosure relates to an information processing device, an information processing method, and a program. [Background technology]

[0002] There are known techniques for supporting the generation and correction of text data. For example, Patent Document 1 discloses a technique for correcting target information so that the target information matches the content intended by a user. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] WO2021 / 220702 publication Summary of the Invention [Problem to be solved by the invention]

[0004] In the technology described in Patent Document 1, text related to a user's comment is compared with past information about the content of the comment, and comment text candidates are generated based on the comparison. However, this technology has a problem in that it is difficult to improve the accuracy of the comment text candidates (in other words, the accuracy of text correction or text correction suggestions).

[0005] The present disclosure has been made in consideration of the above problems, and an exemplary objective thereof is to provide a technique capable of performing accurate corrections or proposing corrections to target data. [Means for solving the problem]

[0006] An information processing device according to an exemplary aspect of the present disclosure includes an acquisition means for acquiring target data, a generation means for generating a target vector from the target data, and a modification means for comparing the target vector with a reference vector generated from reference data, and performing processing related to modification of the target data depending on the comparison result.

[0007] An information processing method according to an exemplary aspect of the present disclosure includes an acquisition process for acquiring target data, a generation process for generating a target vector from the target data, and a modification process for comparing the target vector with a reference vector generated from reference data and executing a process for modifying the target data depending on the comparison result.

[0008] A program relating to an exemplary aspect of the present disclosure causes a computer to execute an acquisition process to acquire target data, a generation process to generate a target vector from the target data, and a modification process to compare the target vector with a reference vector generated from reference data and perform processing related to modifying the target data depending on the comparison result. Effect of the Invention

[0009] According to an exemplary aspect of the present disclosure, an exemplary effect is achieved in that accurate corrections or suggestions for corrections can be made to target data. [Brief description of the drawings]

[0010] [Figure 1] 1 is a block diagram showing a configuration of an information processing device according to the present disclosure. [Diagram 2] 1 is a flow diagram showing the flow of an information processing method according to the present disclosure. [Diagram 3] 1 is a block diagram showing a configuration of an information processing device according to the present disclosure. [Figure 4] 1 is a flow diagram showing the flow of an information processing method according to the present disclosure. [Diagram 5] 1 is a flow diagram showing the flow of an information processing method according to the present disclosure. [Figure 6]1 is a flow diagram showing the flow of an information processing method according to the present disclosure. [Figure 7] FIG. 13 illustrates an example of data comparison according to the present disclosure. [Figure 8] FIG. 13 illustrates an example of data comparison according to the present disclosure. [Figure 9] FIG. 1 is a block diagram showing a configuration of a computer that functions as an information processing device according to the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] The following are examples of embodiments of the present invention. However, the present invention is not limited to the exemplary embodiments shown below, and various modifications are possible within the scope of the claims. For example, an embodiment obtained by appropriately combining the technical means employed in each of the exemplary embodiments shown below may also be included in the scope of the present invention. In addition, an embodiment obtained by appropriately omitting a part of the technical means employed in each of the exemplary embodiments shown below may also be included in the scope of the present invention. In addition, the effects mentioned in each of the exemplary embodiments shown below are examples of effects expected in the exemplary embodiments, and do not define the scope of the present invention. In other words, an embodiment that does not exhibit the effects mentioned in each of the exemplary embodiments shown below may also be included in the scope of the present invention.

[0012] First Exemplary Embodiment A first exemplary embodiment, which is an example of an embodiment of the present invention, will be described in detail with reference to the drawings. This exemplary embodiment is the basic form of each exemplary embodiment described later. The scope of application of each technical means adopted in this exemplary embodiment is not limited to this exemplary embodiment. That is, each technical means adopted in this exemplary embodiment can be adopted in other exemplary embodiments included in this disclosure to the extent that no particular technical obstacle occurs. In addition, each technical means shown in the drawings referred to for explaining this exemplary embodiment can also be adopted in other exemplary embodiments included in this disclosure to the extent that no particular technical obstacle occurs.

[0013] (Configuration of information processing device 1) The configuration of the information processing device 1 will be described with reference to Fig. 1. Fig. 1 is a block diagram showing the configuration of the information processing device 1. As shown in Fig. 1, the information processing device 1 includes an acquisition unit 11, a generation unit 12, and a correction unit 13.

[0014] The information processing device 1 is a device that compares a target vector generated from target data with a reference vector generated from reference data, and executes a process related to the correction of the target data according to the comparison result. Here, specific examples of the target data do not limit this exemplary embodiment, but as an example, articles and editorials created in mass media, etc. are included. In addition, specific examples of the reference data do not limit this exemplary embodiment, but as an example, data reflecting the tone of past articles and editorials, or trends in society, etc. can be used.

[0015] (Acquisition part 11) The acquisition unit 11 acquires target data DT. The target data DT may be, for example, at least one of an image, a voice, and a text. The target data DT may be data in any field, but as an example, the target data DT may be data such as an image, a voice, or a text contained in an article or an editorial created in mass media. Examples of mass media include newspapers and broadcasting.

[0016] (Generation unit 12) The generating unit 12 generates a target vector from the target data DT. Here, the target vector is, for example, the target data DT or one or more elements extracted from the target data DT expressed as a vector in a feature space. The one or more elements extracted from the target data DT may be, for example, a predetermined keyword, a predetermined sentence expression, a token, or the like.

[0017] (An example of how to generate a target vector) Here, an example of a method for generating a target vector will be described. However, this example does not limit this exemplary embodiment. For example, when the target data DT is text data such as a sentence, first, each word or token that may exist in the target data DT is previously associated with a predetermined numerical value on a one-to-one basis. Next, each word or token that exists in the actually acquired target data DT is replaced with the previously associated predetermined numerical value, thereby converting the target data DT into a numerical string. Then, the numerical string is expressed as a vector in the feature space according to a predetermined rule or algorithm. The vector generated in this way is the target vector.

[0018] (revised part 13) The modification unit 13 compares the target vector with a reference vector generated from the reference data DR, and executes processing related to modification of the target data DT according to the comparison result.

[0019] The reference data DR may be, for example, at least one of an image, a voice, and a text. The reference data DR may be data in any field, but may be, for example, data indicating the tone of past articles or editorials created in mass media, or the public trend. Here, the data indicating the public trend may be, for example, at least one of text, voice, and an image created by each of a plurality of people. Specific examples of data indicating the public trend include articles published on the Internet, such as SNS (Social Networking Service), and survey results by a research company. However, these examples do not limit the present exemplary embodiment.

[0020] The reference data DR may be acquired in advance or may be acquired during processing in the correction unit 13. Here, the reference vector is, for example, the reference data DR or one or more elements extracted from the reference data DR expressed as a vector in a feature space. The one or more elements extracted from the reference data DR may be, for example, a predetermined keyword, a predetermined sentence expression, a token, or a predetermined evaluation value such as an approval rating. The reference vector, like the target vector, can be generated in advance as a vector indicating the features of the reference data DR in the feature space.

[0021] The modification unit 13 may, for example, calculate the difference between the target vector and the reference vector in the feature space, and compare the target vector with the reference vector by a method of determining whether the magnitude of the calculated difference vector is within a predetermined range.

[0022] In addition, the correction unit 13 performs, for example, the following process regarding the correction of the target data DT: A process of correcting the target data DT so that the degree of difference between the target vector and the reference vector falls within a predetermined range, or A process of suggesting to the user to correct the target data DT so that the degree of difference between the target vector and the reference vector falls within a specified range. In other words, the corrector 13 may, for example, A process of modifying an article created by the mass media, etc. so that the degree of difference between the characteristics of the article and the characteristics of data indicating public trends, etc., falls within a specified range; or A process to suggest revising an article so that the degree of difference between the characteristics of the article created by the mass media, etc. and the characteristics of data showing public trends, etc., falls within a specified range. may be carried out.

[0023] As a specific example of processing related to the correction unit 13, when a certain topic is viewed as being against the public opinion but an article is written in support of it, the correction unit 13 may correct the article, i.e., the target data DT, or may suggest a correction so that the difference from the data indicating the public opinion, i.e., the reference data DR, falls within a specified range.

[0024] As an example, the above-mentioned correction suggestions can be made by the correction unit 13 presenting the correction contents to the user via a presentation unit such as a display panel, but this does not limit the present exemplary embodiment.

[0025] (Effects of information processing device 1) As described above, the information processing device 1 is configured to acquire target data, generate a target vector from the target data, compare the target vector with a reference vector generated from reference data, and execute a process for correcting the target data according to the comparison result. Therefore, the information processing device 1 has an effect of being able to perform accurate correction or suggestion of correction for the target data.

[0026] (Flow of information processing method S1) The flow of the information processing method S1 will be described with reference to Fig. 2. Fig. 2 is a flow diagram showing the flow of the information processing method S1. As shown in Fig. 2, the information processing method S1 includes an acquisition process (step) S11, a generation process (step) S12, and a modification process (step) S13.

[0027] (Step S11) In step S11, the acquisition unit 11 acquires the target data DT. The specific process performed by the acquisition unit 11 has been described above, and therefore will not be described here.

[0028] (Step S12) In step S12, the generating unit 12 generates a target vector from the target data DT. The specific process by the generating unit 12 has been described above, and therefore will not be described here.

[0029] (Step S13) In step S13, the correction unit 13 compares the target vector with the reference vector generated from the reference data DR, and executes processing related to the correction of the target data DT according to the comparison result. The specific processing by the correction unit 13 has been described above, so the description will be omitted here.

[0030] (Effect of information processing method S1) As described above, the information processing method S1 employs a configuration in which target data is acquired, a target vector is generated from the target data, the target vector is compared with a reference vector generated from the reference data, and a process for correcting the target data is executed according to the comparison result. Therefore, the information processing method S1 has an effect of being able to perform accurate corrections or suggestions for corrections to the target data.

[0031] Second Exemplary Embodiment A second exemplary embodiment, which is an example of an embodiment of the present invention, will be described in detail with reference to the drawings. Components having the same functions as those described in the above exemplary embodiment will be given the same reference numerals, and their description will be omitted as appropriate. The scope of application of each technical means adopted in this exemplary embodiment is not limited to this exemplary embodiment. That is, each technical means adopted in this exemplary embodiment can be adopted in other exemplary embodiments included in this disclosure, as long as no particular technical hindrance occurs. In addition, each technical means shown in each drawing referred to for explaining this exemplary embodiment can be adopted in other exemplary embodiments included in this disclosure, as long as no particular technical hindrance occurs.

[0032] (Configuration of information processing device 1A) The configuration of the information processing device 1A will be described with reference to Fig. 3. Fig. 3 is a block diagram showing the configuration of the information processing device 1A. As shown in Fig. 3, the information processing device 1A includes a control unit 10, a storage unit 20, a communication unit 30, and an input / output unit 40.

[0033] (Control unit 10) As shown in FIG. 3, the control unit 10 includes an acquisition unit 11, a generation unit 12, and a correction unit 13 that are included in the information processing device 1.

[0034] (Acquisition part 11) The acquisition unit 11 acquires target data DT. In addition to the specific examples of the target data DT described in the first exemplary embodiment, the target data DT acquired by the acquisition unit 11 may include one or more sentences.

[0035] (Function as target data generating unit in acquisition unit 11) The acquiring unit 11 may have a function as, for example, a target data generating unit that generates target data DT from the input data DI.

[0036] The input data DI may be, for example, data consisting of at least one of an image, a voice, and a text. A specific example of the input data DI is interview data from the mass media. The input data DI may also be used to generate the target data DT.

[0037] For example, when the acquisition unit 11 functions as a target data generation unit, the acquisition unit 11 may generate target data DT indicating the contents of the input data DI by performing processing on images, voice, and text included in the input data DI. Examples of processing on images, voice, and text include image recognition processing on images, voice recognition processing on voice, and natural language processing on text. Specific examples of natural language processing include syntactic analysis and morphological analysis. Note that the target data DT indicating the contents of the input data DI may be text data such as sentences.

[0038] (Generation unit 12) The generation unit 12 generates a target vector from the target data DT. In addition to the method for generating a target vector described in the exemplary embodiment 1, the generation unit 12 may generate a target vector by referring to at least one of one or more sentences included in the target data DT. Furthermore, for example, the generation unit 12 may optimize a machine learning model by referring to learning data including the target data DT and a correct label associated with the target data DT and the correct label of the target vector, and generate a target vector using the optimized machine learning model.

[0039] (revised part 13) As described in the first exemplary embodiment, the modification unit 13 compares the target vector with the reference vector generated from the reference data DR, and executes a process for modifying the target data DT according to the comparison result. Numerical evaluation of the difference between the target vector and the reference vector; If the value indicated by the difference falls within the correction criteria, no processing is carried out to correct the target data DT, If the value indicated by the difference does not fall within the correction criteria, the process of correcting the target data DT is carried out.

[0040] Here, as the difference between the target vector and the reference vector, an index obtained by processing such as the inner product of the vectors and calculation of the norm of the vectors can be used, but this does not limit the present exemplary embodiment.

[0041] Furthermore, as an example of the correction-related processing executed by the correction unit 13, in addition to that described in the exemplary embodiment 1, the correction unit 13 may correct the target data DT or suggest a correction of the target data DT as the correction-related processing, and obtain the corrected target data DT.

[0042] (Storage unit 20) The storage unit 20 stores various data referenced by the control unit 10 and various data generated by the control unit 10. As an example, the storage unit 20 stores: Input data DI Target data DT Reference Data DR ·Revised criteria CC Output data DO is stored.

[0043] The input data DI may be, for example, data consisting of at least one of an image, a voice, and a text. A specific example of the input data DI is interview data from the mass media. The input data DI may also be used to generate the target data DT in the acquisition unit 11.

[0044] The target data DT may be, for example, at least one of an image, a sound, and a text. The target data DT may be data in any field, but as an example, the target data DT may be data such as an image, a sound, or a text contained in an article or an editorial created in mass media. Examples of mass media include newspapers and broadcasting. The target data DT may also be data that is used to generate a target vector in the generation unit 12.

[0045] The reference data DR may be, for example, at least one of an image, a voice, and a text. The reference data DR may be data in any field, and may be, for example, data indicating the tone of past articles or editorials created in mass media, or a public trend. The reference data DR may be data that has been acquired in advance, or may be acquired during processing in the correction unit 13.

[0046] (Data such as the tone of past articles and editorials) For example, the reference data DR may include a plurality of data accumulated as target data DT in the past, and in this case, the target data DT in the past may be data indicating the tone of past articles or editorials created in mass media, etc. In this case, for example, the correction unit 13 may compare a target vector generated from the target data DT created in the mass media, etc. with a reference vector generated from the reference data DR, and execute a process related to the correction of the target data DT according to the comparison result. In this way, the target data DT may be made consistent with the tone of past articles or editorials created in the mass media, etc.

[0047] (Data showing public trends, etc.) Data indicating public trends, etc., can be acquired as at least one of text, audio, and images created by each of a plurality of people. For example, the intentions of the creators of these texts, audio, and images may be reflected. In this case, for example, the intentions of each creator existing in the world may indicate public trends, etc. In addition, specific examples of data indicating public trends include articles published on the Internet, such as SNS (Social Networking Service), and survey results by research companies, etc. However, these examples do not limit the present exemplary embodiment. In addition, for example, data indicating public trends, etc., may be acquired by setting the region to which the creator belongs or the time of creation within a predetermined range, and indicating the public trends in the region or time. In addition, for example, the reliability of data indicating public trends, etc., may be improved by increasing the number of creators.

[0048] The correction criterion CC is data that serves as a criterion when, for example, the correction unit 13 executes a process related to the correction of the target data DT. For example, the correction criterion CC may be a threshold value related to the difference between the target vector and the reference vector. In addition, as one example, the correction criterion CC may be a numerical value indicating an evaluation of a public interest in a particular field, collected from data indicating public trends. In addition, for example, the correction unit 13 may refer to the correction criterion CC and execute a process related to the correction of the target data DT so that the degree of difference between the target vector and the reference vector falls within a predetermined range.

[0049] The output data DO is, for example, the corrected target data DT output from the correction unit 13.

[0050] (Communication unit 30) The communication unit 30 communicates with a device external to the information processing device 1A. As an example, the communication unit 30 communicates with one or more user terminals (user terminals 51, 52, 53, ... in FIG. 3) connected to the information processing device 1A via a network N. The communication unit 30 transmits data provided from the control unit 10 to the outside, and provides data received from the user terminals 51, 52, 53, ... to the control unit 10. Note that the specific configuration of the network N does not limit this exemplary embodiment, but as an example, a wireless LAN (Local Area Network), a wired LAN, a WAN (Wide Area Network), a public line network, a mobile data communication network, or a combination of these networks can be used.

[0051] The user terminals 51, 52, 53, . . . may be used when one or more users exchange input data DI, target data DT, output data DO, and the like with the information processing device 1A, for example.

[0052] (Input / output section 40) The input / output unit 40 is configured to include at least one of input / output devices such as a keyboard, a mouse, a display, a printer, and a touch panel. Alternatively, the input / output unit 40 may be configured to be connected to input / output devices such as a keyboard, a mouse, a display, a printer, and a touch panel. In this configuration, the input / output unit 40 accepts input of various information from the connected input device to the information processing device 1A. Moreover, the input / output unit 40 outputs various information to the connected output device under the control of the control unit 10. An example of the input / output unit 40 is an interface such as a Universal Serial Bus (USB).

[0053] (Processing flow by information processing device 1A) The flow of processing by the information processing device 1A will be described with reference to FIGS.

[0054] (Flow of method S2 for generating reference vectors from data showing public sentiment) Fig. 4 is a flow diagram showing the flow of S2, which is a flow of generating a reference vector from data indicating a public trend in the reference data DR. Fig. 4 shows an example in which the data indicating a public trend is at least any one of text, voice, and image data created by each of a plurality of people.

[0055] (Step S21) In step S21, the acquisition unit 11 acquires at least any one of text, voice, and image data created by each of a plurality of people.

[0056] (Step S22) In step S22, the acquisition unit 11 generates a reference vector from the data acquired in step S21 and stores it.

[0057] (Flow of S3, a method for generating reference vectors from past target data) FIG. 5 is a flow diagram showing the flow of S3, which is the flow of generating a reference vector from a plurality of data stored as past target data DT in the reference data DR.

[0058] (Step S31) In step S31, the acquisition unit 11 acquires a plurality of data items accumulated as past target data DT.

[0059] (Step S32) In step S32, the acquisition unit 11 generates a reference vector from the data acquired in step S31 and stores it.

[0060] (Flow of information processing method S1A executed by information processing device 1A) 6 is a flow diagram showing the flow of an information processing method S1A executed by information processing device 1A. Note that step S11 in information processing method S1 corresponds to steps S101 to S102 in information processing method S1A, and step S13 in information processing method S1 corresponds to steps S103 to S105 in information processing method S1A.

[0061] (Step S101) In step S101, the acquisition unit 11 acquires the input data DI.

[0062] (Step S102) In step S102, the acquiring unit 11 generates target data DT. Note that, since the specific processing by the acquiring unit 11 in steps S101 and S102 has been described above as the function of the target data generating unit in the acquiring unit 11, the description thereof will be omitted here.

[0063] (Step S12) In step S12, the generating unit 12 generates a target vector from the target data DT. The specific process by the generating unit 12 has been described above, and therefore will not be described here.

[0064] (Step S103) In step S103, the correction unit 13 compares the target vector with the reference vector. The comparison between the target vector and the reference vector in the correction unit 13 has been described above, and therefore will not be described here.

[0065] (Step S104) In step S104, the modification unit 13 determines whether the degree of difference between the target vector and the reference vector is within a predetermined range. For example, the modification unit 13 may determine whether the difference between the target vector and the reference vector is within a range of a modification criterion CC. If it is within the predetermined range (step S104: YES), the process ends. If it is not within the predetermined range (step S104: NO), the process proceeds to step S105.

[0066] (Step S105) In step S105, the modification unit 13 modifies the target data DT. For example, the modification unit 13 may modify the target data DT so that the difference between the target vector and the reference vector falls within the range of the modification criterion CC.

[0067] (Modification of correction unit 13) For example, when accuracy is required for the contents of the target data DT, the correction unit 13 may correct the target vector by referring to data belonging to a first category included in the reference data DR, and may optimize the target vector by re-correcting the target vector by referring to data belonging to a second category included in the reference data DR. An example of a case where accuracy is required for the contents of the target data DT is when the target data DT is related to medicine or health care. For example, the data belonging to the first category may be data indicating a trend in society. Also, for example, the data belonging to the second category may be data whose contents are more accurate than the data belonging to the first category. A specific example of data belonging to the second category is a peer-reviewed document such as an academic paper.

[0068] Fig. 7 is a diagram showing, for example, a target vector A and a reference vector B belonging to a first category. In Fig. 7, for example, the target vector A may be modified according to a result of comparing the target vector A with the reference vector B belonging to the first category.

[0069] Fig. 8 is a diagram showing, for example, a target vector A', a reference vector B belonging to a first category, and a reference vector C belonging to a second category. The target vector A' may be, for example, the target vector A after correction in Fig. 7. In Fig. 8, for example, the target vector A' may be optimized by re-correcting the target vector A' according to a result of comparing the target vector A' with the reference vector C belonging to the second category.

[0070] (Effects of information processing device 1A) As described above, the information processing device 1A employs a configuration in which the reference data includes at least one of text, voice, and image created by each of a plurality of people, and at least one of a plurality of data accumulated as target data in the past. Therefore, in addition to the effect of the information processing device 1, the information processing device 1A can provide an effect of being able to correct or propose corrections to the target data in accordance with data created by a third party or past target data.

[0071] Moreover, in the information processing device 1A, the correction means is configured to correct the target data or propose correction of the target data as a process related to the correction, and obtain the corrected target data. Therefore, according to the information processing device 1A, in addition to the effect of the information processing device 1, the effect of being able to correct or propose correction of the target data and obtain the corrected target data can be obtained.

[0072] Moreover, in the information processing device 1A, the target data acquired by the acquisition means includes one or more sentences, and the generation means generates a target vector by referring to at least one of the one or more sentences. Therefore, according to the information processing device 1A, in addition to the effect of the information processing device 1, the effect of being able to generate a target vector from target data including sentences is obtained.

[0073] The information processing device 1A is further provided with a target data generating means for generating target data from input data. Therefore, in addition to the effects of the information processing device 1, the information processing device 1A can provide the effect of being able to generate target data from input data.

[0074] Moreover, the information processing device 1A employs a configuration in which a machine learning model serving as a generating means is optimized by referring to learning data including target data and a correct label associated with the target data and the correct label of the target vector. Therefore, according to the information processing device 1A, in addition to the effect of the information processing device 1, an effect of being able to optimize a machine learning model serving as a generating means of the target vector can be obtained.

[0075] Moreover, in the information processing device 1A, the correction means refers to data belonging to a first category included in the reference data to correct the target vector, and refers to data belonging to a second category included in the reference data to re-correct the target vector, thereby optimizing the target vector. Therefore, according to the information processing device 1A, in addition to the effects of the information processing device 1, the effect of optimizing the target vector by re-correcting the target vector is obtained.

[0076] [Software implementation example] Some or all of the functions of the information processing devices 1, 1A (hereinafter also referred to as "the above-mentioned devices") may be realized by hardware such as an integrated circuit (IC chip), or may be realized by software.

[0077] In the latter case, each of the above devices is realized, for example, by a computer that executes instructions of a program, which is software that realizes each function. An example of such a computer (hereinafter, referred to as computer C) is shown in Fig. 9. Fig. 9 is a block diagram showing the hardware configuration of computer C that functions as each of the above devices.

[0078] The computer C includes at least one processor C1 and at least one memory C2. The memory C2 stores a program P for causing the computer C to operate as each of the above-mentioned devices. In the computer C, the processor C1 reads and executes the program P from the memory C2, thereby realizing the functions of each of the above-mentioned devices.

[0079] The processor C1 may be, for example, a central processing unit (CPU), a graphic processing unit (GPU), a digital signal processor (DSP), a micro processing unit (MPU), a floating point number processing unit (FPU), a physics processing unit (PPU), a tensor processing unit (TPU), a quantum processor, a microcontroller, or a combination thereof. The memory C2 may be, for example, a flash memory, a hard disk drive (HDD), a solid state drive (SSD), or a combination thereof.

[0080] The computer C may further include a RAM (Random Access Memory) for expanding the program P during execution and for temporarily storing various data. The computer C may further include a communication interface for transmitting and receiving data to and from other devices. The computer C may further include an input / output interface for connecting input / output devices such as a keyboard, a mouse, a display, and a printer.

[0081] Furthermore, the program P can be recorded on a non-transitory tangible recording medium M that can be read by the computer C. Such a recording medium M can be, for example, a tape, a disk, a card, a semiconductor memory, or a programmable logic circuit. The computer C can obtain the program P via such a recording medium M. Furthermore, the program P can be transmitted via a transmission medium. Such a transmission medium can be, for example, a communication network or broadcast waves. The computer C can also obtain the program P via such a transmission medium.

[0082] [Additional Note 1] This disclosure includes the techniques described in the following appendices. However, the present invention is not limited to the techniques described in the following appendices, and various modifications are possible within the scope of the claims.

[0083] (Appendix 1) An acquisition means for acquiring target data; A generating means for generating a target vector from the target data; and a correction means for comparing the target vector with a reference vector generated from reference data, and executing processing related to correction of the target data depending on a result of the comparison.

[0084] (Appendix 2) The reference data includes: At least one of text, audio, and image created by each of a plurality of persons; and A plurality of data accumulated as the target data in the past 2. The information processing device according to claim 1, comprising at least one of the above.

[0085] (Appendix 3) The information processing device according to claim 2, wherein the correction means corrects the target data or suggests a correction of the target data as a process related to the correction, and obtains the corrected target data.

[0086] (Appendix 4) The target data acquired by the acquisition means includes one or more sentences, The information processing device according to claim 3, wherein the generation means generates the target vector by referring to at least one of the one or more sentences.

[0087] (Appendix 5) A target data generating means for generating the target data from input data. 5. The information processing device according to claim 1, further comprising:

[0088] (Appendix 6) The generating means includes: optimizing a machine learning model by referring to learning data including the target data and a correct answer label associated with the target data, the correct answer label being a correct answer label for the target vector; The information processing device according to claim 5, further comprising: generating the target vector using the optimized machine learning model.

[0089] (Appendix 7) The correction means is correcting the target vector by referring to data belonging to a first category included in the reference data; The information processing device according to any one of claims 1 to 4, characterized in that the target vector is optimized by re-correcting the target vector by referring to data belonging to a second category included in the reference data.

[0090] (Appendix 8) An acquisition process for acquiring target data; A generation process of generating a target vector from the target data; and a correction process for comparing the target vector with a reference vector generated from reference data, and performing a process for correcting the target data depending on the comparison result.

[0091] (Appendix 9) The reference data includes: At least one of text, audio, and image created by each of a plurality of persons; and A plurality of data accumulated as the target data in the past 9. The information processing method according to claim 8, further comprising at least one of the following:

[0092] (Appendix 10) The information processing method according to claim 9, wherein the correction process is a process related to correction, which corrects the target data or proposes a correction to the target data, and obtains the corrected target data.

[0093] (Appendix 11) The target data acquired by the acquisition process includes one or more sentences, The information processing method described in Appendix 10, characterized in that the generation process generates the target vector by referring to at least one of the one or more sentences.

[0094] (Appendix 12) A target data generation process for generating the target data from input data 12. The information processing method according to any one of claims 8 to 11, further comprising:

[0095] (Appendix 13) The information processing method according to claim 12, further comprising optimizing a machine learning model as the generation process by referring to learning data including the target data and a correct label associated with the target data, the correct label being the target vector.

[0096] (Appendix 14) The correction process includes: correcting the target vector by referring to data belonging to a first category included in the reference data; The information processing method of any one of appendices 8 to 11, characterized in that the target vector is optimized by re-correcting the target vector by referring to data belonging to a second category included in the reference data.

[0097] (Appendix 15) A program for causing a computer to operate as the information processing device according to any one of claims 1 to 7, the program causing the computer to function as each of the means.

[0098] [Additional Note 2] This disclosure includes the techniques described in the following appendices. However, the present invention is not limited to the techniques described in the following appendices, and various modifications are possible within the scope of the claims.

[0099] (Appendix 1) at least one processor, the at least one processor comprising: An acquisition process for acquiring target data; A generation process of generating a target vector from the target data; A correction process is performed to compare the target vector with a reference vector generated from reference data, and to perform a process for correcting the target data according to a result of the comparison. 23. An information processing apparatus comprising:

[0100] The information processing device may further include a memory, and the memory may store a program for causing the at least one processor to execute each of the processes.

[0101] (Appendix 2) The reference data includes: At least one of text, audio, and image created by each of a plurality of persons; and A plurality of data accumulated as the target data in the past At least one of the following is included: 2. The information processing device according to claim 1 .

[0102] (Appendix 3) In the correction process, the at least one processor corrects the target data or proposes correction of the target data as a process related to the correction, and obtains the corrected target data. 3. The information processing device according to claim 2.

[0103] (Appendix 4) In the acquisition process, the target data acquired by the at least one processor includes one or more sentences; In the generation process, the at least one processor generates the target vector by referring to at least any one of the one or more sentences. 4. The information processing device according to claim 3.

[0104] (Appendix 5) The at least one processor: Further performing a target data generation process for generating the target data from input data. 5. An information processing device according to any one of claims 1 to 4.

[0105] (Appendix 6) optimizing a machine learning model as the generating means by referring to learning data including the target data and a correct label associated with the target data and the correct label of the target vector; 6. The information processing device according to claim 5,

[0106] (Appendix 7) In the modification process, the at least one processor: correcting the target vector by referring to data belonging to a first category included in the reference data; optimizing the target vector by recorrecting the target vector with reference to data belonging to a second category included in the reference data; 5. An information processing device according to any one of claims 1 to 4. [Explanation of symbols]

[0107] 1, 1A Information processing device 10 Control section 11 Acquisition Department 12 Generation part 13 Correction section 20 Memory section 30 Communications Department 40 Input / output section 51, 52, 53,... User terminal C1 Processor C2 Memory

Claims

1. An acquisition means for acquiring target data; A generating means for generating a target vector from the target data; and a correction means for comparing the target vector with a reference vector generated from reference data, and executing a process for correcting the target data according to a result of the comparison. Information processing device.

2. The reference data includes: At least one of text, audio, and image created by each of a plurality of persons; and A plurality of data accumulated as the target data in the past At least one of the following is included: The information processing device according to claim 1 .

3. The correction means corrects the target data or proposes a correction of the target data as a process related to the correction, and acquires the corrected target data. The information processing device according to claim 2 .

4. The target data acquired by the acquisition means includes one or more sentences, The generating means generates the target vector by referring to at least any one of the one or more sentences. The information processing device according to claim 3 .

5. A target data generating means for generating the target data from input data. The device further comprises: The information processing device according to claim 1 .

6. The generating means includes: optimizing a machine learning model by referring to learning data including the target data and a correct answer label associated with the target data, the correct answer label being a correct answer label for the target vector; generating the target vector using the optimized machine learning model; The information processing device according to claim 5 .

7. The correction means is correcting the target vector by referring to data belonging to a first category included in the reference data; optimizing the target vector by recorrecting the target vector with reference to data belonging to a second category included in the reference data; The information processing device according to claim 1 .

8. An acquisition process for acquiring target data; A generation process of generating a target vector from the target data; A correction process for comparing the target vector with a reference vector generated from reference data, and executing a process for correcting the target data according to a result of the comparison. Information processing methods.

9. On the computer, An acquisition process for acquiring target data; A generation process of generating a target vector from the target data; A correction process is performed to compare the target vector with a reference vector generated from reference data, and to perform a process for correcting the target data according to a result of the comparison. program.

Images