JP2019211977A - Information processing device, information processing method, and information processing program - Google Patents

Abstract

To properly provide a service relating to character information conversion.SOLUTION: An information processing device according to the present invention includes an obtaining unit, and a learning unit. The obtaining unit obtains first character information that is first kind character information, and second character information that is second kind information different from the first kind. The learning unit creates, on the basis of a learning which has the first character information as input information and which takes the first character information as correct answer information, and of a learning which has the second character information as input information and which takes the second character information as correct answer information, a conversion model that outputs, in accordance with the input of first kind target character information, converted character information that is the target information converted into the second kind.SELECTED DRAWING: Figure 1

Description

  The present invention relates to an information processing apparatus, an information processing method, and an information processing program.

  Conventionally, various techniques related to character string conversion such as translation have been provided. For example, a technique for realizing language identification with higher accuracy using sequence information of language-likeness at a frame level is known. In such a technique, a plurality of learning data is used as a set of a character string before conversion and a character string after change. Further, in the prior art, for example, a plurality of learning data in which voice data in a plurality of languages and a language label representing the language of each voice data are paired are used.

JP-A-2006-156870

  However, with the above-described conventional technology, it may be difficult to appropriately provide a service relating to character information conversion. For example, in such character information conversion, when a combination (teacher data) of character information before conversion and character information after conversion is insufficient, it is difficult to appropriately provide a service related to character information conversion. There is a problem.

  The present application has been made in view of the above, and an object thereof is to provide an information processing apparatus, an information processing method, and an information processing program that can appropriately provide a service related to character information conversion.

  The information processing apparatus according to the present application includes: an acquisition unit that acquires first character information that is first type character information; and second character information that is second type character information different from the first type; Based on learning using the first character information as input information, using the first character information as correct information, and learning using the second character information as input information and using the second character information as correct information. And a learning unit that generates a conversion model for outputting the converted character information obtained by converting the target character information into the second type in response to the input of the first type of target character information. And

  According to one aspect of the embodiment, it is possible to appropriately provide a service related to character information conversion.

FIG. 1 is a diagram illustrating an example of information processing according to the embodiment. FIG. 2 is a diagram illustrating an example of information processing according to the embodiment. FIG. 3 is a diagram illustrating a configuration example of the information processing system according to the embodiment. FIG. 4 is a diagram illustrating a configuration example of the information processing apparatus according to the embodiment. FIG. 5 is a diagram illustrating an example of the first type information storage unit according to the embodiment. FIG. 6 is a diagram illustrating an example of the second type information storage unit according to the embodiment. FIG. 7 is a diagram illustrating an example of a model information storage unit according to the embodiment. FIG. 8 is a flowchart illustrating an example of information processing according to the embodiment. FIG. 9 is a flowchart illustrating an example of information processing according to the embodiment. FIG. 10 is a diagram illustrating an example of information processing according to the modification. FIG. 11 is a diagram illustrating an example of information processing according to the modification. FIG. 12 is a diagram illustrating a configuration example of an information processing apparatus according to a modification. FIG. 13 is a diagram illustrating an example of the model information storage unit according to the modification. FIG. 14 is a hardware configuration diagram illustrating an example of a computer that implements the functions of the information processing apparatus.

  Hereinafter, an information processing apparatus, an information processing method, and an information processing program according to the present application (hereinafter referred to as “embodiment”) will be described in detail with reference to the drawings. Note that the information processing apparatus, the information processing method, and the information processing program according to the present application are not limited by this embodiment. In the following embodiments, the same portions are denoted by the same reference numerals, and redundant description is omitted.

(Embodiment)
[1. Information processing (learning process)]
First, an example of information processing according to the embodiment will be described with reference to FIG. FIG. 1 is a diagram illustrating an example of information processing according to the embodiment. Specifically, FIG. 1 illustrates an example of a learning process in the information processing according to the embodiment. In FIG. 1, the information processing apparatus 100 includes a first type of character information (hereinafter also referred to as “first character information”) and a second type of character information different from the first type (hereinafter also referred to as “second character information”). ) And a case of generating a model. Note that the first type and the second type here are types in the same language. In FIG. 1, the first type is a news article, and the second type is an example for children, but the first type and the second type are different types in the same language. Any type may be used. In FIG. 1, the information processing apparatus 100 converts a type of character information based on a learning process using first character information and a learning process using second character information (hereinafter also referred to as “conversion model”). ) Is generated. That is, in FIG. 1, a conversion model in which the information processing apparatus 100 outputs character information (hereinafter also referred to as “post-conversion character information”) obtained by converting the type of input character information (hereinafter also referred to as “pre-conversion character information”). The case of generating

  Further, when the information processing apparatus 100 acquires certain pre-conversion character information using the generated conversion model, the information processing apparatus 100 generates post-conversion character information obtained by converting the type of the pre-conversion character information. The information processing apparatus 100 provides a service based on the generated converted character information, which will be described with reference to FIG.

[Configuration of information processing system]
First, prior to the description of FIG. 1, the information processing system 1 shown in FIG. 3 will be described. As illustrated in FIG. 3, the information processing system 1 includes a terminal device 10, an information providing device 50, and an information processing device 100. The terminal device 10, the information providing device 50, and the information processing device 100 are connected via a predetermined network N so as to be communicable by wire or wirelessly. FIG. 3 is a diagram illustrating a configuration example of the information processing system according to the embodiment. Note that the information processing system 1 illustrated in FIG. 3 may include a plurality of terminal devices 10, a plurality of information providing devices 50, and a plurality of information processing devices 100.

  The terminal device 10 is an information processing device used by a user. The terminal device 10 is realized by, for example, a smartphone, a tablet terminal, a notebook PC (Personal Computer), a desktop PC, a mobile phone, a PDA (Personal Digital Assistant), or the like. Hereinafter, the terminal device 10 may be referred to as a user. That is, hereinafter, the user can be read as the terminal device 10.

  The terminal device 10 receives an operation by a user. Further, the terminal device 10 transmits various information to the information processing device 100 and the information providing device 50 in accordance with a user operation. For example, the terminal device 10 transmits information requesting content such as character information to the information processing device 100 and the information providing device 50. The terminal device 10 receives various information from the information processing device 100 and the information providing device 50. For example, the terminal device 10 receives the converted character information from the information processing device 100 or the information providing device 50. For example, the terminal device 10 displays character information received from the information processing device 100 or the information providing device 50.

  The information providing device 50 is an information processing device used by a provider that provides a predetermined service. The provider may be an individual or a corporation. For example, the information providing device 50 is used by the information provider CP1. The information provider CP1 may be a content provider such as a content provider. The information provider CP1 may be a business operator that provides a content distribution service. The information provider CP1 may be a business operator that performs an advertisement distribution service.

  For example, the information provider CP1 uses the information providing apparatus 50 to transmit character information provided in the content distribution service to the information processing apparatus 100. The information provider CP1 uses the information providing apparatus 50 to transmit the converted character information to the information processing apparatus 100. The information providing apparatus 50 is realized by, for example, a smartphone, a tablet terminal, a notebook PC, a desktop PC, a mobile phone, a PDA, or the like. Hereinafter, the information providing apparatus 50 may be referred to as a provider. That is, in the following, the provider can be read as the information providing apparatus 50. Specifically, FIGS. 1 and 2 show a case where the information providing device 50 is a notebook PC used by the information provider CP1. Note that the information providing apparatus 50 may be integrated with the information processing apparatus 100. That is, the information processing apparatus 100 may perform a content distribution service, an advertisement distribution service, or the like.

  The information processing apparatus 100 is an information processing apparatus that generates a conversion model that outputs converted character information obtained by converting target character information into a second type in response to input of the first type of target character information. The information processing apparatus 100 generates a conversion model that outputs other converted character information obtained by converting the other target character information into the first type in response to an input of the second type of other target character information. It is. For example, the information processing apparatus 100 is a learning apparatus that performs learning processing.

  The information processing apparatus 100 is an information processing apparatus that generates post-conversion character information in which the type of character information is converted by inputting character information to a conversion model. For example, the information processing apparatus 100 is a generation apparatus that performs character information generation processing. For example, the information processing apparatus 100 is a conversion apparatus that performs character information conversion processing.

  Further, the information processing apparatus 100 provides a service based on the generated converted character information. In the example of FIG. 2, the information processing apparatus 100 provides the generated converted character information to the information providing apparatus 50. The information processing apparatus 100 may provide information to the terminal apparatus 10 used by the user using the generated converted character information. The information processing apparatus 100 may distribute the generated content including the converted character information to the terminal device 10. In this case, the information processing apparatus 100 acquires various types of information from an external information processing apparatus that provides the content distribution service, and performs information processing and information provision to the external information processing apparatus based on the acquired various types of information. Also good.

  First, the information processing apparatus 100 acquires first character information as learning data LD1 (step S11). Then, the information processing apparatus 100 adds the first character information included in the learning data LD1 acquired in step S11 as learning data (step S12). Specifically, the information processing apparatus 100 adds the learning data LD1 to the first type information storage unit 121.

  The first type information storage unit 121 illustrated in FIG. 1 includes items such as “character information ID” and “first character information”.

  “Character information ID” in the first type information storage unit 121 of FIG. 1 indicates identification information for identifying character information. “First character information” in the first type information storage unit 121 in FIG. 1 indicates character information identified by a character information ID.

  In the example shown in FIG. 1, the character information identified by the character information ID “FID11” indicates the first character information FCH11, and the character information identified by the character information ID “FID12” is the first character information. Indicates that it is FCH12. The character information identified by the character information ID “FID13” indicates the first character information FCH13, and the character information identified by the character information ID “FID14” is the first character information FCH14. Show. The first character information FCH11 to FCH14 is any character information as long as it is general news (hereinafter also referred to as “normal news”) that is not intended for children, character information distributed by normal content distribution, or the like. It may be. For example, the first character information FCH11 to FCH14 may be normal news about politics and economy, normal news about sports and entertainment, and the like.

  Further, the information processing apparatus 100 acquires the second character information as learning data LD2 (step S13). Then, the information processing apparatus 100 adds the second character information included in the learning data LD2 acquired in step S13 as learning data (step S14). Specifically, the information processing apparatus 100 adds the learning data LD2 to the second type information storage unit 122.

  The second type information storage unit 122 illustrated in FIG. 1 includes items such as “character information ID” and “second character information”.

  The “character information ID” in the second type information storage unit 122 in FIG. 1 indicates identification information for identifying character information. “Second character information” in the second type information storage unit 122 in FIG. 1 indicates character information identified by the character information ID.

  In the example shown in FIG. 1, the character information identified by the character information ID “SID11” indicates the second character information SCH11, and the character information identified by the character information ID “SID12” is the second character information. Indicates SCH12. Further, the character information identified by the character information ID “SID13” indicates the second character information SCH13, and the character information identified by the character information ID “SID14” is the second character information SCH14. Show. The second character information SCH11 to SCH14 and the like may be any character information as long as it is character information such as news created for children (hereinafter also referred to as “news for children”). For example, the second character information SCH11 to SCH14 and the like may be news for children related to politics and economy created for children, news for children about sports and entertainment, and the like.

  And the information processing apparatus 100 produces | generates a model by the learning process based on learning data. For example, the information processing apparatus 100 uses the first character information FCH11 to FCH14 in the first type information storage unit 121 and the second character information SCH11 to SCH14 in the second type information storage unit 122 as learning data (teacher data). As a result, a conversion model is generated by learning. It is assumed that there is no correspondence between the first character information FCH11 to FCH14 and the second character information SCH11 to SCH14 and the like in the second type information storage unit 122. For example, the first character information FCH11 to FCH14 and the second character information SCH11 to SCH14 and the like in the second type information storage unit 122 are news of different contents.

  First, a conversion model (learning device) generated by the information processing apparatus 100 will be briefly described. In the example of FIG. 1, the model M1 in the model information storage unit 123 is an architecture model as shown in the structure information ARC1. In the example of FIG. 1, a model M1 that is a conversion model generated by the information processing apparatus 100 is a model including a plurality of first partial models M1-1, M1-2, and the like. As described above, when “model M * (* is an arbitrary numerical value)” is described, it indicates that the model is a model identified by the model ID “M *”. For example, when “model M1” is described, the model is a model identified by the model ID “M1”.

  Further, as described above, when “first partial model M * (* is an arbitrary numerical value)” is described, the first partial model is a model identified by the first partial model ID “M *”. Indicates. For example, when “first partial model M1-1” is described, the first partial model is a model identified by the first partial model ID “M1-1”.

  As described above, when “second partial model M * (* is an arbitrary numerical value)” is described, the second partial model is a model identified by the second partial model ID “M *”. Indicates. For example, when “second partial model M11” is described, the second partial model is a model identified by the second partial model ID “M11”. Note that when the first partial model and the second partial model are described without particular distinction, the “partial model” may be simply described.

  The first partial model M1-1 is an encoding unit, and includes an encoder (hereinafter also referred to as “encoder”) that extracts features of the input information by compressing the dimensionality of the input information. Corresponding to the partial model. As shown in FIG. 1, the first partial model M1-1 corresponds to a model that receives the input information IN1 and outputs the intermediate information INT1. The first partial model M1-1 corresponds to a model in which the first character information and the second character information are input as the input information IN1, and the intermediate information INT1 is output.

  The first partial model M1-1 includes a second partial model M11 that is an encoder that receives the first character information. The second partial model M11 extracts the features of the input first character information by compressing the dimensional amount of the input first character information. The second partial model M11 outputs, as intermediate information INT1 in FIG. 1, intermediate information indicating characteristics of the first character information in which the dimensional amount of the first character information is compressed. For example, the intermediate information INT1 in FIG. 1 is an intermediate output (encoded vector or the like) indicating the characteristics of the input information, and may be, for example, a distributed expression or a real value vector. For example, the intermediate information INT1 includes information related to the meaning (concept) of the character information input to the model M1.

  The first partial model M1-1 includes a second partial model M12 that is an encoder that receives the second character information. The second partial model M12 extracts features of the input second character information by compressing the dimensional amount of the input second character information. The second partial model M12 outputs, as intermediate information INT1 in FIG. 1, intermediate information indicating characteristics of the second character information in which the dimension amount of the second character information is compressed.

  For example, specifications such as the number of dimensions are set for the intermediate information INT1, and the second partial models M11 and M12 in the first partial model M1-1 output intermediate information INT1 based on the common specifications. The second partial models M11 and M12 output intermediate information compressed to a common number of dimensions. In the example of FIG. 1, the second partial models M11 and M12 are individually illustrated for explanation, but the second partial models M11 and M12 may share common portions. For example, the second partial models M11 and M12 may be integrated. In other words, the second partial models M11 and M12 may be one model. For example, the 1st partial model M1-1 may be the structure except the overlap part among the structures for implement | achieving the function of the 2nd partial models M11 and M12.

  In addition, the first partial model M1-1 has a function of determining which of the second partial models M11 and M12 the input character information is to be input in accordance with the type of input character information. For example, the first partial model M1-1 receives information (specific information) that specifies the type of character information to be input, and inputs character information to the second partial model M11, M12 corresponding to the specific information. Then, it has a function to decide. For example, the first partial model M1-1 is configured so that character information is input to an input layer of a model based on specific information among the second partial models M11 and M12 by a predetermined switching function (switching function). ) A circuit or the like may be switched. For example, the first partial model M1-1 may determine a model for inputting character information among the second partial models M11 and M12 by using selection information (control vector), which will be described later, as specific information during learning. .

  For example, the first partial model M1-1 is a model for inputting character information among the second partial models M11 and M12 using information obtained by inverting selection information described later as specific information at the time of generation (conversion). May be determined. For example, when the first partial model M1-1 is generated (converted) and the selection information is information indicating “first type”, the information indicating “second type” obtained by inverting the information is specified. Of the second partial models M11 and M12, a model for inputting character information may be determined as information. For example, when the selection information is information indicating “second type” at the time of generation (conversion), the first partial model M1-1 specifies information indicating “first type” obtained by inverting the information. Of the second partial models M11 and M12, a model for inputting character information may be determined as information. Note that the above is an example, and the information processing apparatus 100 may realize determination of a model to be input by any function as long as input to a desired model is possible.

  The first partial model M1-2 is a decoding unit, and includes a decoder (hereinafter also referred to as a “decoder”) that increases the dimensionality of features extracted by the encoder and outputs character information of a predetermined type. Corresponds to the partial model. That is, the first partial model M1-2 is a partial model including a decoder that receives intermediate information output by the encoder, increases the dimensional amount of the input intermediate information, and outputs character information of a predetermined type. Correspond. As shown in FIG. 1, the first partial model M1-2 corresponds to a model that receives the intermediate information INT1 and outputs the output information OUT1.

  The first partial model M1-2 includes a second partial model M13 that is a decoder that receives intermediate information. The second partial model M13 generates first character information corresponding to the input intermediate information by increasing the dimensional amount of the input intermediate information. The second partial model M13 outputs first character information corresponding to the input intermediate information as output information OUT1 in FIG.

  The first partial model M1-2 includes a second partial model M14 that is a decoder that receives intermediate information. The second partial model M14 generates second character information corresponding to the input intermediate information by increasing the dimensional amount of the input intermediate information. The second partial model M14 outputs second character information corresponding to the input intermediate information as the output information OUT1 in FIG. In the example of FIG. 1, the second partial models M13 and M14 are individually illustrated for explanation, but the second partial models M13 and M14 may share common portions. For example, the second partial models M13 and M14 may be integrated. In other words, the second partial models M13 and M14 may be one model. For example, even if the second partial models M13 and M14 are integrated (the same model), the first partial model M1-2 generates information corresponding to the selection based on the selection information by inputting different selection information ( Output. For example, the first partial model M1-2 may have a configuration in which redundant portions are removed from the configurations for realizing the functions of the second partial models M13 and M14.

  The first partial model M1-2 receives selection information (control vector) for selecting the type of character information to be output. The first partial model M1-2 receives selection information SL1 for selecting a type of character information to be output. That is, the first partial model M1-2 has a function of determining which of the second partial models M13 and M14 the input intermediate information is input according to the selection information SL1. For example, the first partial model M1-2 has a function of receiving selection information and determining to input intermediate information to the second partial model M13, M14 corresponding to the selection information. For example, the first partial model M1-2 is configured so that intermediate information is input to an input layer of a model based on intermediate information among the second partial models M13 and M14 by a predetermined switching function (switching function). ) A circuit or the like may be switched.

  For example, the first partial model M1-2 is determined to input intermediate information to the second partial model M13 when the selection information is information indicating “first type”. For example, the first partial model M1-2 is determined to input intermediate information to the second partial model M14 when the selection information is information indicating “second type”. Note that the above is an example, and the information processing apparatus 100 may realize determination of a model to be input by any function as long as input to a desired model is possible.

  The encoder and decoder are not only a neural network that simply changes the number of dimensions of input information, but also an RNN (Recurrent Neural Network) such as GRU (Gated Recurrent Unit) and LSTM (Long Short-Term Memory). Various neural networks such as) can be employed.

  The information processing apparatus 100 generates a conversion model through learning processing using the first character information (step S15). The information processing apparatus 100 generates a model M1 by performing learning using the first character information FCH11 to FCH14 and the like in the first type information storage unit 121 as learning data (teacher data). In FIG. 1, selection information FSL1 for selecting the first type is set as shown in the first learning FLR1. Thereby, in 1st learning FLR1, it controls so that the 2nd partial model M11 and the 2nd partial model M13 may be used among models M1. Then, the information processing apparatus 100 receives the input information FIN1 that is the first character information, and learns to output the output information FOUT1 that is the first character information via the second partial model M11 and the second partial model M13. To do.

  In the first learning FLR1, the information processing apparatus 100 performs a learning process so that the first character information that is input to the model M1 is output from the model M1. For example, when the first character information FCH11 is input to the model M1, the information processing apparatus 100 performs a learning process so that the first character information FCH11 is output from the model M1. For example, when the first character information FCH12 is input to the model M1, the information processing apparatus 100 performs a learning process so that the first character information FCH12 is output from the model M1.

  For example, in the first learning FLR1, the information processing apparatus 100 performs a learning process using the second partial model M11 and the second partial model M13 as an auto encoder for the first character information. For example, the information processing apparatus 100 performs a learning process by a method such as back propagation (error back propagation method) so that the character information output from the model M1 approaches the character information input to the model M1. For example, the information processing apparatus 100 corrects the value of the weight (that is, the connection coefficient) that is considered when the value is transmitted between the nodes, so that the first partial model M11 and the second partial model M13 have the first Learn the characteristics of text information. As described above, the information processing apparatus 100 learns the model M1 by processing such as back propagation that corrects the parameter (connection coefficient) so that an error between the output of the model M1 and the input is reduced. For example, the information processing apparatus 100 generates the model M1 by performing processing such as backpropagation so as to minimize a predetermined loss function. Thereby, the information processing apparatus 100 can perform the learning process on the second partial model M11 and the second partial model M13 using only the first character information.

  Further, the information processing apparatus 100 generates a conversion model by a learning process using the second character information (Step S16). The information processing apparatus 100 generates the model M1 by performing learning using the second character information SCH11 to SCH14 in the second type information storage unit 122 as learning data (teacher data). In FIG. 1, selection information SSL1 for selecting the second type is set as shown in the second learning SLR1. Thereby, in 2nd learning SLR1, it controls so that 2nd partial model M12 and 2nd partial model M14 may be used among models M1. Then, the information processing apparatus 100 receives the input information SIN1 that is the second character information, and outputs the output information SOUT1 that is the second character information via the second partial model M12 and the second partial model M14. To do.

  In the second learning SLR1, the information processing apparatus 100 performs a learning process so that the second character information input to the model M1 is output from the model M1. For example, when the second character information SCH11 is input to the model M1, the information processing apparatus 100 performs a learning process so that the second character information SCH11 is output from the model M1. For example, when the second character information SCH12 is input to the model M1, the information processing apparatus 100 performs a learning process so that the second character information SCH12 is output from the model M1.

  For example, in the second learning SLR1, the information processing apparatus 100 performs a learning process using the second partial model M12 and the second partial model M14 as an auto encoder for the second character information. For example, the information processing apparatus 100 performs a learning process by a technique such as back propagation so that the character information output from the model M1 approaches the character information input to the model M1. For example, the information processing apparatus 100 corrects the second partial model M12 and the second partial model M14 by correcting the value of the weight (that is, the connection coefficient) that is considered when the value is transmitted between the nodes. Learn the characteristics of text information. Thereby, the information processing apparatus 100 can perform the learning process on the second partial model M12 and the second partial model M14 using only the second character information.

  As described above, the information processing apparatus 100 performs the learning process on the second partial model M11 and the second partial model M13 in the first learning FLR1, and the second partial model M12 and the second partial model M12 in the second learning SLR1. A learning process is performed on the two-part model M14. Thereby, the information processing apparatus 100 can perform learning for each of the second partial models M11 to M14 included in the model M1.

  As described above, the information processing apparatus 100 associates the first character information and the second character information by performing the learning process using the first character information and the learning process using the second character information. Even when there is no learning data (teacher data), the learning process can be performed appropriately. That is, when the combination (teacher data) of the first type of character information and the second type of character information is insufficient, it is difficult for the information processing apparatus 100 to appropriately provide a service related to character information conversion. Such a problem can be solved. Then, the information processing apparatus 100 can appropriately convert the character information type by converting the character information type using the learned model, and can perform various services.

(1-1. First type, second type)
Note that the model learning technique is not limited to the technique described above, and any known technique can be applied. Further, for example, if there is a small number of teacher data (hereinafter also referred to as “pair data”) in which the first character information and the second character information are associated with each other, the information processing apparatus 100 stores the pair data. It may be used. For example, when there is pair data, the information processing apparatus 100 may perform learning using one of the pair data as input information and the other as output correct information.

  The information processing apparatus 100 performs learning by controlling to use the second partial model M11 and the second partial model M14 when the first character information is input and the second character information is output from the pair data. Process. Then, the information processing apparatus 100 performs learning to output the second character information via the second partial model M11 and the second partial model M14 using the first character information as an input. Further, the information processing apparatus 100 controls to use the second partial model M12 and the second partial model M13 when the second character information is input and the first character information is output from the pair data. , Learning process. Then, the information processing apparatus 100 performs learning to output the first character information via the second partial model M12 and the second partial model M13 with the second character information as an input. Thereby, the information processing apparatus 100 can improve the conversion accuracy of the model M1.

(1-2. Selection information (control vector))
In the example of FIG. 1, the case of controlling which decoder is used is described as an example. However, the information processing apparatus 100 may be extended with a decoder so that a control vector can be received. For example, the information processing apparatus 100 may combine a word vector and a control vector and regard it as a normal word vector. The information processing apparatus 100 may use various control vectors. For example, the information processing apparatus 100 may use a different control vector for each word. For example, the information processing apparatus 100 may combine different control vectors for each word vector. For example, the information processing apparatus 100 may use a control vector corresponding to the number of remaining characters when summarizing. For example, when summarizing, the information processing apparatus 100 may use information indicating how many characters remain and how many characters are output as a control vector (referred to as “control vector CX”). For example, the information processing apparatus 100 may perform the character string conversion process using a vector obtained by combining the word vector and the control vector CX.

(1-3. First type, second type)
In the example of FIG. 1, the case where the first type is a news article and the second type is an article for children is shown, but the information processing apparatus 100 may perform processing for various types. The first type may be character information including characters greater than or equal to the first number of characters, and the second type may be character information including characters less than or equal to the first number of characters and less than the second number of characters. For example, the first type may be a text (article text), and the second type may be a summary. There may be two or more types of signals for controlling the output.

(1-4. 3 or more types)
In the example of FIG. 1, conversion of two types of the first type and the second type has been described as an example. However, the information processing apparatus 100 learns a conversion model that mutually converts three or more types of character information. May be. For example, a conversion model may be generated that converts three types of character information between the first type for adults, the second type for elementary school students, and the third type for high school students.

[2. Information processing (provision processing)]
An example of information processing according to the embodiment will be described with reference to FIG. FIG. 2 is a diagram illustrating an example of information processing according to the embodiment. Specifically, FIG. 2 illustrates an example of a providing process in the information processing according to the embodiment. In FIG. 2, the information processing apparatus 100 provides the information providing apparatus 50 with converted character information obtained by converting the type of character information acquired from the information providing apparatus 50.

  First, the information processing apparatus 100 acquires character information that is a generation target of converted character information from the information providing apparatus 50 used by the information provider CP1 (step S21). In the example of FIG. 2, the information processing apparatus 100 acquires target character information INF21 that is the first type of character information from the information providing apparatus 50.

  Then, the information processing apparatus 100 acquires a conversion model (step S22). In the example of FIG. 2, the information processing apparatus 100 acquires the model M1 from the model information storage unit 123. Then, the information processing apparatus 100 uses the model M1 to generate converted character information INF22 obtained by converting the type of the target character information INF21. Specifically, the information processing apparatus 100 generates the second type of converted character information INF22 by inputting the first type of target character information INF21 to the model M1.

  In the example of FIG. 2, the information processing apparatus 100 generates converted character information INF22 by a process as shown in the process group PS1. Since the target character information INF21 is the first type, the information processing apparatus 100 sets the selection information SSL1 for selecting the second type (step S23). Further, since the target character information INF21 is the first type, the information processing apparatus 100 sets specific information for selecting the first type. As a result, the processing group PS1 is controlled to use the second partial model M11 and the second partial model M14 in the model M1.

  Then, the information processing apparatus 100 inputs the target character information INF21 into the model M1 (Step S24). The information processing apparatus 100 receives the input information TIN1 as the target character information INF21 and outputs the output information TOUT1 as the second type of converted character information INF22 via the second partial model M11 and the second partial model M14. Let Specifically, the information processing apparatus 100 inputs the target character information INF21 to the second partial model M11. Then, the information processing apparatus 100 inputs the intermediate information INT1 output from the second partial model M11 to the second partial model M14. Then, the information processing apparatus 100 causes the second partial model M14 to output the converted character information INF22 (Step S25). Thereby, the information processing apparatus 100 generates the converted character information INF22 in which the type of the target character information INF21 of the first type is converted to the second type.

  Then, the information processing apparatus 100 provides the converted character information INF22 to the information providing apparatus 50 (step S26). In the example of FIG. 2, the information processing apparatus 100 transmits the converted character information INF22 to the information providing apparatus 50.

  As described above, the information processing apparatus 100 appropriately provides a service related to character information conversion by providing the converted character information INF22 obtained by converting the type of the target character information INF21 into the second type using the model M1. be able to.

[3. Configuration of information processing apparatus]
Next, the configuration of the information processing apparatus 100 according to the embodiment will be described with reference to FIG. FIG. 4 is a diagram illustrating a configuration example of the information processing apparatus 100 according to the embodiment. As illustrated in FIG. 4, the information processing apparatus 100 includes a communication unit 110, a storage unit 120, and a control unit 130. The information processing apparatus 100 includes an input unit (for example, a keyboard and a mouse) that receives various operations from an administrator of the information processing apparatus 100 and a display unit (for example, a liquid crystal display) for displaying various types of information. You may have.

(Communication unit 110)
The communication unit 110 is realized by, for example, a NIC (Network Interface Card). The communication unit 110 is connected to the network by wire or wireless, and transmits and receives information to and from the terminal device 10 and the information providing device 50.

(Storage unit 120)
The storage unit 120 is realized by, for example, a semiconductor memory device such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. As illustrated in FIG. 4, the storage unit 120 according to the embodiment includes a first type information storage unit 121, a second type information storage unit 122, and a model information storage unit 123.

(First type information storage unit 121)
The first type information storage unit 121 according to the embodiment stores various types of information related to the first type. FIG. 5 is a diagram illustrating an example of the first type information storage unit according to the embodiment. For example, the first type information storage unit 121 stores teacher data related to the first type used for generating a model. The first type information storage unit 121 illustrated in FIG. 5 includes items such as “character information ID” and “first character information”.

  “Character information ID” indicates identification information for identifying character information. “First character information” indicates character information identified by a character information ID. FIG. 5 shows an example in which conceptual information such as “FID11” is stored in “first character information”, but in reality, a character string (character information) such as a specific sentence or the storage location thereof. The file path name indicating The first character information FCH11 may be any character information as long as it is normal character information not intended for children. The first character information FCH11 may be news about politics or economy, news about sports or entertainment, or the like. Further, the first character information FCH11 may be a product instruction manual or a legal provision.

  In the example illustrated in FIG. 5, the character information identified by the character information ID “FID11” is the first character information FCH11.

  The first type information storage unit 121 is not limited to the above, and may store various types of information according to the purpose. For example, the first type information storage unit 121 may store information related to the date and time when each piece of character information (learning data) is added. Further, for example, the first type information storage unit 121 may store information indicating the date and time when each character information is created. The first type information storage unit 121 may store information for specifying the type of each character information.

  Moreover, the 1st type information storage part 121 memorize | stores the character information more than the 1st character number as 1st character information, when the 1st type is the character information containing the character more than the 1st character number (for example, 200 characters). May be. For example, the first type information storage unit 121 may store the article text as the first character information when the first type is the article text.

(Second type information storage unit 122)
The second type information storage unit 122 according to the embodiment stores various types of information related to the second type. FIG. 6 is a diagram illustrating an example of the second type information storage unit according to the embodiment. For example, the second type information storage unit 122 stores teacher data related to the second type used for generating the model. The second type information storage unit 122 illustrated in FIG. 6 includes items such as “character information ID” and “second character information”.

  “Character information ID” indicates identification information for identifying character information. “Second character information” indicates character information identified by a character information ID. FIG. 6 shows an example in which conceptual information such as “SID11” is stored in “second character information”, but in reality, a character string (character information) such as a specific sentence or the storage location thereof. The file path name indicating The second character information SCH11 may be any character information as long as it is character information for children. The second character information SCH11 may be any character information as long as it is character information created for children. The second character information SCH11 may be a text of a book for children. Further, the second character information SCH11 may be politics / economic news, sports / entertainment news, etc. created for children.

  In the example illustrated in FIG. 6, the character information identified by the character information ID “SID11” is the second character information SCH11.

  The second type information storage unit 122 is not limited to the above, and may store various types of information according to the purpose. For example, the second type information storage unit 122 may store information related to the date and time when each piece of character information (learning data) is added. Further, for example, the second type information storage unit 122 may store information indicating the date and time when each character information is created. The second type information storage unit 122 may store information for specifying the type of each character information.

  Further, when the second type is character information including characters less than the second number of characters (for example, 15 characters), the second type information storage unit 122 stores character information less than the second number of characters as the second character information. May be. For example, when the second type is summary, the second type information storage unit 122 may store the summary as the second character information.

(Model information storage unit 123)
The model information storage unit 123 according to the embodiment stores information about the model. For example, the model information storage unit 123 stores model information (model data) generated by information processing. FIG. 7 is a diagram illustrating an example of a model information storage unit according to the embodiment. The model information storage unit 123 illustrated in FIG. 7 includes items such as “model ID”, “first partial model ID”, “second partial model ID”, “use”, and “model data”. In FIG. 7, only the model M1 is illustrated, but a plurality of model information such as models M3 and M4 may be stored.

  “Model ID” indicates identification information for identifying a model. For example, the model identified by the model ID “M1” corresponds to the model M1 illustrated in the example of FIG. The “first partial model ID” indicates identification information for identifying the first partial model of the corresponding model. For example, the first partial model identified by the partial model ID “M1-1” corresponds to the first partial model M1-1 illustrated in the example of FIG.

  “Second partial model ID” indicates identification information for identifying the second partial model of the corresponding model. The “second partial model ID” indicates a model obtained by further subdividing the corresponding first partial model. For example, the partial model identified by the second partial model ID “M11” corresponds to the second partial model M11 illustrated in the example of FIG. “Use” indicates the use of the corresponding partial model (second partial model). “Model data” indicates data of a corresponding partial model (second partial model). For example, “model data” includes information including nodes in each layer, functions adopted by the nodes, connection relationships between the nodes, and connection coefficients set for connections between the nodes.

  For example, in the example illustrated in FIG. 7, the model M1 indicates that the first partial models M1-1, M1-2, and the like are included. The first partial model M1-1 indicates that the second partial models M11 and M12 are included. The first partial model M1-2 indicates that the second partial models M13 and M14 are included.

  In addition, for example, the model (second partial model M11) identified by the second partial model ID “M11” has a usage of “first character information → intermediate information”, and an intermediate from the input first character information. Indicates that it is used to generate information. That is, the second partial model M11 is used for extracting features from the input first character information. The model data of the second partial model M11 is model data MDT11.

  Further, for example, the model identified by the second partial model ID “M14” (second partial model M14) has a usage of “intermediate information⇒second character information”, and generates second character information from the intermediate information. Indicates that it will be used. That is, the second partial model M14 is used to generate second character information from intermediate information that is information indicating the characteristics of the extracted character information. The model data of the second partial model M14 is model data MDT14.

  The model M1 (each model data MDT11 to MDT14) is an input layer to which a predetermined type of character information is input, an output layer, or any layer from the input layer to the output layer and other than the output layer. And a second element whose value is calculated based on the first element and the weight of the first element, and for each layer other than the output layer for character information input to the input layer The computer is configured to output from the output layer character information converted into a type different from the predetermined type by performing an operation based on the first element and the weight of the first element, with each element belonging to the first element. It is a model to make it function.

  For example, the first element included in the model M1 corresponds to any node of the input layer or the intermediate layer. The second element corresponds to the next node, which is a node to which a value is transmitted from the node corresponding to the first element. The weight of the first element corresponds to a connection coefficient that is a weight considered for a value transmitted from a node corresponding to the first element to a node corresponding to the second element.

  The model information storage unit 123 is not limited to the above, and may store various model information according to the purpose.

(Control unit 130)
Returning to the description of FIG. 4, the control unit 130 is a controller, and is stored in a storage device inside the information processing apparatus 100 by, for example, a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like. Various programs (corresponding to an example of an information processing program such as a learning program and a generation program) are executed by using the RAM as a work area. The control unit 130 is a controller, and is realized by an integrated circuit such as an application specific integrated circuit (ASIC) or a field programmable gate array (FPGA). The control unit 130 performs processing based on the model M1 and the like stored in the model information storage unit 123, an input layer to which character information of a predetermined type is input, an output layer, and an input layer to an output layer. A first element belonging to any layer other than the output layer, and a second element whose value is calculated based on the first element and the weight of the first element, and is input to the input layer The character information is converted into a type different from the predetermined type by performing an operation based on the first element and the weight of the first element, with each element belonging to each layer other than the output layer as the first element. Output character information from the output layer.

  As illustrated in FIG. 4, the control unit 130 includes an acquisition unit 131, a learning unit 132, a generation unit 133, and a provision unit 134, and implements or executes information processing functions and operations described below. . Note that the internal configuration of the control unit 130 is not limited to the configuration illustrated in FIG. 4, and may be another configuration as long as the information processing described below is performed. The control unit 130 calculates a value based on the first element and the weight of the first element by information processing according to the model M1 (the model data MDT11 to MDT14 and the like) stored in the storage unit 120. An operation based on the weights of the first element and the first element, with each element belonging to each layer other than the output layer as a first element for character information of a predetermined type input to the input layer. As a result, the character information converted into a type different from the predetermined type is output from the output layer.

  The control unit 130 calculates a second value based on the first element and the weight of the first element by information processing according to the model M1 (model data MDT11 to MTD14 and the like) stored in the storage unit 120. By performing an operation based on the first element and the weight of the first element, with each element belonging to each layer other than the output layer as the first element for the input information input to the input layer The character information in which the type of the character information is converted is output from the output layer. Note that the model such as the model M1 may be assumed to be used as a program module that is a part of the artificial intelligence software. The model such as the model M1 may be a program.

(Acquisition part 131)
The acquisition unit 131 acquires various types of information. The acquisition unit 131 acquires various types of information from an external information processing device such as the terminal device 10 or the information providing device 50. The acquisition unit 131 may acquire various types of information shown in the first type information storage unit 121, the second type information storage unit 122, the model information storage unit 123, and the like from an external information processing apparatus.

  The acquisition unit 131 acquires various types of information from the storage unit 120. The acquisition unit 131 acquires various types of information from the first type information storage unit 121, the second type information storage unit 122, the model information storage unit 123, and the like.

  The acquisition unit 131 acquires first character information that is character information of the first type and second character information that is character information of a second type different from the first type. The acquisition unit 131 acquires selection information for selecting the type of character information output by the conversion model. The acquisition unit 131 acquires selection information for selecting a learning type that is a type corresponding to the learning character information input to the conversion model.

  The acquisition unit 131 converts a first character information, which is character information of the first type, into second character information, which is character information of a second type different from the first type, and a target character of the first type Get information and. The acquisition unit 131 acquires a conversion model for converting the second character information into the first character information and other target character information of the second type. The acquisition unit 131 acquires selection information for selecting the type of character information output by the conversion model. The acquisition unit 131 acquires target character information input to the conversion model and selection information for selecting the other type that is one of the first type and the second type and is different from the type of the target character information.

  In the example of FIG. 1, the acquisition unit 131 acquires first character information as learning data LD1. The acquisition unit 131 adds the first character information included in the learning data LD1 as learning data. The acquisition unit 131 adds the learning data LD1 to the first type information storage unit 121. The acquisition unit 131 acquires the second character information as learning data LD2. The acquisition unit 131 adds the second character information included in the learning data LD2 as learning data. The acquisition unit 131 adds the learning data LD2 to the second type information storage unit 122.

  In the example of FIG. 2, the acquisition unit 131 acquires character information that is a generation target of converted character information from the information providing device 50 used by the information provider CP1. The acquisition unit 131 acquires the target character information INF21 that is the first type of character information from the information providing apparatus 50. The acquisition unit 131 acquires a conversion model. The acquisition unit 131 acquires the model M1 from the model information storage unit 123.

(Learning unit 132)
The learning unit 132 learns various information. The learning unit 132 generates various models by learning processing. For example, the learning unit 132 performs a learning process based on information stored in the first type information storage unit 121, the second type information storage unit 122, and the like. The learning unit 132 generates various models based on information stored in the first type information storage unit 121, the second type information storage unit 122, and the like.

  For example, the learning unit 132 generates a model as shown in the model information storage unit 123 using the learning data stored in the first type information storage unit 121 and the second type information storage unit 122. For example, the learning unit 132 generates a model used to generate character information converted from a predetermined type of character information to a type different from the predetermined type based on the learning data acquired by the acquisition unit 131. . The learning unit 132 generates a model and stores the generated model in the model information storage unit 123. Specifically, the learning unit 132 is a first layer belonging to a layer other than the output layer, which is any layer from the input layer to which a predetermined type of character information is input, the output layer, and the input layer to the output layer. Each element belonging to each layer other than the output layer for character information input to the input layer, including one element and a second element whose value is calculated based on the first element and the weight of the first element Is used as a first element, and a calculation is performed based on the first element and the weight of the first element, thereby generating a model that outputs character information obtained by converting character information from a predetermined type to another type from the output layer .

  The learning unit 132 uses the first character information as input information, learns the first character information as correct information, uses the second character information as input information, and sets the second character information as correct information. Based on the learning, a conversion model is generated that outputs converted character information obtained by converting the target character information into the second type in response to the input of the first type of target character information. The learning unit 132 outputs an intermediate information indicating characteristics of the first character information in response to the input of the first character information, and converted character information corresponding to the intermediate information using the intermediate information as input information. A conversion model including a decoding unit that outputs is generated.

  The learning unit 132 outputs an intermediate information indicating the characteristics of the second character information in response to the input of the second character information, and the first character corresponding to the intermediate information using the intermediate information as input information. A conversion model including a decoding unit that outputs information, and outputs other converted character information obtained by converting the other target character information into the first type in response to the input of the other target character information of the second type. Generate a conversion model to The learning unit 132 generates a conversion model that outputs character information of a type corresponding to the selection information. The learning unit 132 generates a conversion model by performing a learning process so as to output the learning character information based on the learning type in response to the input of the learning character information.

  The learning unit 132 outputs the intermediate information indicating the characteristics of the first character information in response to the input of the first character information, and the second character information in response to the input of the second character information. A transform model including an encoding unit having a second encoder that outputs intermediate information indicating characteristics is generated. The learning unit 132 generates a conversion model including a decoding unit having a first decoder that outputs first character information corresponding to the intermediate information and a second decoder that outputs second character information corresponding to the intermediate information. .

  In the example of FIG. 1, the learning unit 132 learns the first character information FCH11 to FCH14 in the first type information storage unit 121 and the second character information SCH11 to SCH14 in the second type information storage unit 122. As a teacher data), a conversion model is generated by learning. The learning unit 132 generates a conversion model by a learning process using the first character information. The learning unit 132 generates the model M1 by performing learning using the first character information FCH11 to FCH14 and the like in the first type information storage unit 121 as learning data (teacher data). The learning unit 132 receives the input information FIN1 that is the first character information and performs learning to output the output information FOUT1 that is the first character information via the second partial model M11 and the second partial model M13.

  In the first learning FLR1, the learning unit 132 performs a learning process so that the first character information input to the model M1 is output from the model M1. When the first character information FCH11 is input to the model M1, the learning unit 132 performs a learning process so that the first character information FCH11 is output from the model M1. When the first character information FCH12 is input to the model M1, the learning unit 132 performs a learning process so that the first character information FCH12 is output from the model M1.

  In the first learning FLR1, the learning unit 132 performs a learning process using the second partial model M11 and the second partial model M13 as an auto encoder for the first character information. The learning unit 132 performs learning processing by a technique such as back propagation (error back propagation method) so that the character information output from the model M1 approaches the character information input to the model M1. The learning unit 132 corrects the value of the weight (that is, the connection coefficient) that is considered when the value is transmitted between the nodes, so that the first character information is stored in the second partial model M11 and the second partial model M13. Learn the features you have. The learning unit 132 learns the model M1 by processing such as back propagation that corrects a parameter (connection coefficient) so that an error between the output of the model M1 and the input is reduced. The learning unit 132 generates the model M1 by performing processing such as backpropagation so as to minimize a predetermined loss function.

  The learning unit 132 generates a conversion model by a learning process using the second character information. The learning unit 132 generates the model M1 by performing learning using the second character information SCH11 to SCH14 in the second type information storage unit 122 as learning data (teacher data). The learning unit 132 receives the input information SIN1 that is the second character information and performs learning to output the output information SOUT1 that is the second character information via the second partial model M12 and the second partial model M14.

  In the second learning SLR1, the learning unit 132 performs a learning process so that the second character information input to the model M1 is output from the model M1. When the second character information SCH11 is input to the model M1, the learning unit 132 performs a learning process so that the second character information SCH11 is output from the model M1. When the second character information SCH12 is input to the model M1, the learning unit 132 performs a learning process so that the second character information SCH12 is output from the model M1.

  In the second learning SLR1, the learning unit 132 performs a learning process using the second partial model M12 and the second partial model M14 as an auto encoder for the second character information. The learning unit 132 performs a learning process by a method such as back propagation so that the character information output from the model M1 approaches the character information input to the model M1. The learning unit 132 corrects the value of the weight (that is, the connection coefficient) considered when the value is transmitted between the nodes, so that the second character information is stored in the second partial model M12 and the second partial model M14. Learn the features you have.

  The learning unit 132 performs a learning process on the second partial model M11 and the second partial model M13 in the first learning FLR1, and the second partial model M12 and the second partial model M14 in the second learning SLR1. A learning process is performed as a target. The learning unit 132 performs learning for each of the second partial models M11 to M14 included in the model M1.

(Generator 133)
The generation unit 133 generates various information. The generation unit 133 generates various character information through a generation process. For example, the generation unit 133 performs generation processing based on information stored in the model information storage unit 123 or the like. The learning unit 132 generates character information using the model stored in the model information storage unit 123.

  The generation unit 133 generates converted character information in which the target character information is converted into the second type by inputting the target character information into the conversion model. The generation unit 133 generates other converted character information in which the other target character information is converted into the first type by inputting the other target character information into the conversion model. The generation unit 133 generates character information of a type corresponding to the selection information by inputting the selection information to the conversion model. The generation unit 133 generates converted character information in which the target character information is converted into the other type by inputting the target character information and the selection information into the conversion model.

  In the example of FIG. 2, the generation unit 133 generates converted character information INF22 obtained by converting the type of the target character information INF21 using the model M1. The generation unit 133 generates the second type of converted character information INF22 by inputting the first type of target character information INF21 to the model M1. The generation unit 133 generates the converted character information INF22 by processing as shown in the processing group PS1. Since the target character information INF21 is the first type, the generation unit 133 sets the selection information SSL1 for selecting the second type. Since the target character information INF21 is the first type, the generation unit 133 sets specific information for selecting the first type.

  The generation unit 133 inputs the target character information INF21 to the model M1. The generation unit 133 receives the input information TIN1 that is the target character information INF21 and outputs the output information TOUT1 that is the second type of converted character information INF22 via the second partial model M11 and the second partial model M14. . The generation unit 133 inputs the target character information INF21 to the second partial model M11. The generation unit 133 inputs the intermediate information INT1 output from the second partial model M11 to the second partial model M14. The generation unit 133 causes the second partial model M14 to output the converted character information INF22. The generation unit 133 generates converted character information INF22 in which the type of the target character information INF21 of the first type is converted to the second type.

(Providing unit 134)
The providing unit 134 provides various information. For example, the providing unit 134 provides various types of information to the terminal device 10 and the information providing device 50. The providing unit 134 transmits various types of information to the terminal device 10 and the information providing device 50. The providing unit 134 distributes various information to the terminal device 10 and the information providing device 50. The providing unit 134 provides various information based on various types of information acquired by the acquiring unit 131. The providing unit 134 provides various information based on various information learned by the learning unit 132. The providing unit 134 provides various information based on the model learned by the learning unit 132. The providing unit 134 provides various information based on the various types of information generated by the generating unit 133. The providing unit 134 provides various information based on the converted character information generated by the generating unit 133.

  In the example of FIG. 2, the providing unit 134 provides the converted character information INF22 to the information providing apparatus 50. The providing unit 134 transmits the converted character information INF22 to the information providing apparatus 50. The providing unit 134 provides a content distribution service using the converted character information. The providing unit 134 provides an advertisement distribution service using the converted character information.

[4. Information processing (learning process) flow]
Next, a learning process procedure in the information processing by the information processing system 1 according to the embodiment will be described with reference to FIG. FIG. 8 is a flowchart illustrating an example of information processing according to the embodiment.

  As illustrated in FIG. 8, the information processing apparatus 100 acquires the first character information of the first type (step S101). For example, the information processing apparatus 100 acquires first character information from the first type information storage unit 121 as learning data.

  Thereafter, the information processing apparatus 100 learns the conversion model using the first character information as input information and the first character information as correct information (step S102). For example, the information processing apparatus 100 learns a conversion model using the first character information stored in the first type information storage unit 121.

  Further, the information processing apparatus 100 acquires the second type of second character information (step S103). For example, the information processing apparatus 100 acquires the second character information from the second type information storage unit 122 as learning data.

  Thereafter, the information processing apparatus 100 learns the conversion model using the second character information as input information and the second character information as correct information (step S102). In the example of FIG. 1, the information processing apparatus 100 learns a conversion model using the second character information stored in the first type information storage unit 121.

[5. Information processing (generation processing) flow]
Next, the procedure of the generation process (conversion process) in the information processing by the information processing system 1 according to the embodiment will be described with reference to FIG. FIG. 9 is a flowchart illustrating an example of information processing according to the embodiment.

  As illustrated in FIG. 9, the information processing apparatus 100 acquires a conversion model (step S201). Further, the information processing apparatus 100 acquires the first type of target character information (step S202). And the information processing apparatus 100 produces | generates the conversion character information by which object character information was converted into the 2nd classification by inputting object character information into a conversion model (step S203). The information processing apparatus 100 provides a service based on the converted character information (step S204).

[6. (Modification)
The information processing system 1 according to the above-described embodiment may be implemented in various different modes other than the above-described embodiment. Below, other embodiment of said information processing system 1 is described. In addition, about the point similar to embodiment mentioned above, the same code | symbol is attached | subjected etc., and description is abbreviate | omitted suitably. For example, the information processing system 1 according to the embodiment and the information processing system (not shown) in the modification have the same configuration except for the difference between the information processing apparatus 100 and the information processing apparatus 100A. Hereinafter, information processing by the information processing apparatus 100A will be described.

[6-1. Information processing (learning process)]
First, the estimation process in the information processing system according to the modification will be described with reference to FIG. FIG. 10 is a diagram illustrating an example of information processing according to the modification. Specifically, FIG. 10 illustrates an example of learning processing in the information processing according to the embodiment. FIG. 1 illustrates a case where the information processing apparatus 100A generates a conversion model that converts the type of the first type of character information to the second type based on the first character information and the second character information.

  First, the information processing apparatus 100A acquires the first character information as learning data LD1 (step S51). Then, the information processing apparatus 100A adds the first character information included in the learning data LD1 acquired in step S51 as learning data (step S52). Specifically, the information processing apparatus 100A adds the learning data LD1 to the first type information storage unit 121.

  The first type information storage unit 121 illustrated in FIG. 10 includes items such as “character information ID” and “first character information”.

  “Character information ID” in the first type information storage unit 121 in FIG. 10 indicates identification information for identifying character information. “First character information” in the first type information storage unit 121 in FIG. 10 indicates character information identified by the character information ID.

  In the example shown in FIG. 10, the character information identified by the character information ID “FID11” indicates the first character information FCH11, and the character information identified by the character information ID “FID12” is the first character information. Indicates that it is FCH12. The character information identified by the character information ID “FID13” indicates the first character information FCH13, and the character information identified by the character information ID “FID14” is the first character information FCH14. Show. The first character information FCH11 to FCH14 is any character information as long as it is general news (hereinafter also referred to as “normal news”) that is not intended for children, character information distributed by normal content distribution, or the like. It may be. For example, the first character information FCH11 to FCH14 may be normal news about politics and economy, normal news about sports and entertainment, and the like.

  Further, the information processing apparatus 100A acquires the second character information as learning data LD2 (step S53). Then, the information processing apparatus 100A adds the second character information included in the learning data LD2 acquired in step S53 as learning data (step S54). Specifically, the information processing apparatus 100A adds the learning data LD2 to the second type information storage unit 122.

  The second type information storage unit 122 illustrated in FIG. 10 includes items such as “character information ID” and “second character information”.

  “Character information ID” in the second type information storage unit 122 in FIG. 10 indicates identification information for identifying character information. “Second character information” in the second type information storage unit 122 in FIG. 10 indicates character information identified by the character information ID.

  In the example shown in FIG. 10, the character information identified by the character information ID “SID11” indicates the second character information SCH11, and the character information identified by the character information ID “SID12” is the second character information. Indicates SCH12. Further, the character information identified by the character information ID “SID13” indicates the second character information SCH13, and the character information identified by the character information ID “SID14” is the second character information SCH14. Show. The second character information SCH11 to SCH14 and the like may be any character information as long as it is character information such as news created for children (hereinafter also referred to as “news for children”). For example, the second character information SCH11 to SCH14 and the like may be news for children created for children, news for children regarding sports and entertainment, and the like.

  Then, the information processing apparatus 100A generates a model by a learning process based on the learning data. For example, the information processing apparatus 100A uses the first character information FCH11 to FCH14 in the first type information storage unit 121 and the second character information SCH11 to SCH14 in the second type information storage unit 122 as learning data (teacher data). As a result, a conversion model is generated by learning. It is assumed that there is no correspondence between the first character information FCH11 to FCH14 and the second character information SCH11 to SCH14 and the like in the second type information storage unit 122. For example, the first character information FCH11 to FCH14 and the second character information SCH11 to SCH14 and the like in the second type information storage unit 122 are news of different contents.

  First, the conversion model (learning device) generated by the information processing apparatus 100A will be briefly described. In the example of FIG. 10, the model M2 in the model information storage unit 123A is an architecture model as shown in the structure information ARC2. In the example of FIG. 10, a model M2 that is a conversion model generated by the information processing apparatus 100A is a model including a plurality of partial models M21, M22, and the like.

  As described above, when “partial model M * (* is an arbitrary numerical value)” is described, it indicates that the partial model is a model identified by the partial model ID “M *”. For example, when “partial model M21” is described, the partial model is a model identified by the partial model ID “M21”.

  The partial model M21 is an encoding unit, and corresponds to an encoder that extracts features of the input information by compressing the dimensionality of the input information. As shown in FIG. 10, the partial model M21 corresponds to a model that receives the input information IN2 and outputs the intermediate information INT2. The partial model M21 corresponds to a model in which the first character information and the second character information are input as the input information IN2, and the intermediate information INT2 is output. That is, the partial model M21 is an encoder that receives the first character information and the second character information. The partial model M21 extracts features of the input first character information and second character information by compressing the dimensional quantities of the input first character information and second character information. The partial model M21 outputs intermediate information indicating characteristics of the first character information and the second character information in which the dimension amount of the first character information is compressed as intermediate information INT2 in FIG. For example, the intermediate information INT2 in FIG. 10 is an intermediate output (encoded vector or the like) indicating the characteristics of the input information, and may be, for example, a distributed expression or a real value vector. For example, the intermediate information INT2 includes information related to the meaning (concept) of the character information input to the model M2.

  The partial model M22 is a decoding unit, and corresponds to a decoder (decoder) that increases the dimensional amount of features extracted by the encoder and outputs character information of a predetermined type. That is, the partial model M22 corresponds to a decoder that receives the intermediate information output by the encoder, increases the dimensional amount of the input intermediate information, and outputs the second type of character information. As shown in FIG. 10, the partial model M22 corresponds to a model that receives the intermediate information INT2 and outputs the output information OUT2. That is, the partial model M22 is a decoder that receives intermediate information as an input. The partial model M22 generates second character information corresponding to the input intermediate information by increasing the dimensional amount of the input intermediate information. The partial model M22 outputs second character information corresponding to the input intermediate information as the output information OUT2 in FIG.

  The model M2 receives type information (control vector) indicating the type of character information input during learning. The model M2 receives type information TL2 for selecting the type of input character information. That is, the model M2 has a function of specifying the type of input character information according to the type information TL2 and performing learning according to the type. For example, the model M2 has a function of receiving type information and causing the partial model M22 to perform learning according to the type information. For example, the model M2 causes the partial model M22 to perform a learning process according to the type information TL2 by a predetermined switching function (switching function).

  For example, the partial model M22 causes the partial model M22 to perform learning corresponding to the first type when the type information is information indicating “first type”. For example, the model M2 causes the partial model M22 to perform learning processing such as reinforcement learning when the type information TL2 is the first type. For example, the partial model M22 determines to input intermediate information to the second partial model M24 when the type information is information indicating “second type”. For example, the model M2 causes the partial model M22 to perform a learning process as an auto encoder so as to decode the input information when the type information TL2 is the second type. Note that the above is an example, and the information processing apparatus 100A may realize determination of a model to be input by any function as long as input to a desired model is possible.

  In the example of FIG. 10, the information processing apparatus 100A performs the learning process using the model M5 as shown in the structure information ARC2.

  The model M5 is a decoding unit other than the model M2, and corresponds to a decoder (decoder that increases the dimensional quantity of features extracted by the encoder of the model M2 and outputs character information of a predetermined type. The model M5 corresponds to a decoder that receives the intermediate information output by the encoder of the model M2 as input, increases the dimensional amount of the input intermediate information, and outputs the character information input to the encoder of the model M2. 10, the model M5 corresponds to a model that receives the intermediate information INT2 output from the encoder of the model M2 and outputs the learning information OUT5, that is, the model M5 is a decoder that receives the intermediate information. The model M5 increases the dimensional quantity of the input intermediate information, thereby increasing the character information that is the basis of the input intermediate information. Generating (decoded). Model M5 as learning information OUT5 in FIG. 10, and outputs the character information corresponding to the input intermediate information. Note that the model M5 may be included in the model M2.

  The encoder and the decoder can employ not only a neural network that simply changes the number of dimensions of input information but also various neural networks such as RNN including GRU and LSTM.

  The information processing apparatus 100A generates a conversion model through a learning process using the first character information (step S55). The information processing apparatus 100A generates the model M2 by performing learning using the first character information FCH11 to FCH14 in the first type information storage unit 121 as learning data (teacher data). In FIG. 10, type information FTL2 for selecting the first type is set as shown in the first learning FLR2. Thus, in the first learning FLR2, the model M2 is controlled to perform learning corresponding to the first type for the partial model M22. Then, the information processing apparatus 100A performs learning to receive the input information FIN2 that is the first character information and output the output information FOUT2 that is the second character information corresponding to the input information FIN2.

  In the first learning FLR2, the information processing apparatus 100A performs a learning process so that the second character information obtained by converting the first character information input to the model M2 into the second type is output from the model M2. For example, when the first character information FCH11 is input to the model M2, the information processing apparatus 100A performs a learning process so that the second type of character information corresponding to the first character information FCH11 is output from the model M2. For example, when the first character information FCH12 is input to the model M2, the information processing apparatus 100A performs a learning process so that the second type of character information corresponding to the first character information FCH12 is output from the model M2.

  For example, in the first learning FLR2, the information processing apparatus 100A performs the learning process so that the term for children (hereinafter referred to as “child term”) included in the output information FOUT2 increases. For example, the child term may be a word characteristic of an article for children. For example, the information processing apparatus 100 </ b> A may calculate the score of the output information FOUT <b> 2 using the child term list information used for the article for children, and may learn to increase the score. For example, the information processing apparatus 100A may calculate the score so that the score becomes higher as the ratio of the child terms included in the output information FOUT2 increases, and may learn so that the score of the output information FOUT2 becomes higher. For example, the information processing apparatus 100A may perform the learning process by a technique such as back propagation (error back propagation method) so that the score of the output information FOUT2 is high. Thereby, the information processing apparatus 100A can perform the learning process on the model M2. Note that the information processing apparatus 100A is not limited to the above, and may perform learning using various information as appropriate.

  For example, the information processing apparatus 100A may use information output by a classification model for classifying news articles and articles for children (hereinafter also referred to as “classification model MX”). For example, the information processing apparatus 100A may use a score output from the classification model MX. The classification model MX may be any model as long as it is a model for classifying news articles and articles for children, and may be in various forms such as SVM (Support Vector Machine). Here, it is assumed that the classification model MX is a model that is learned so that a high score is output when an article for children is input and a low score is output when a normal news article is input. In this case, the information processing apparatus 100A may input the output information FOUT2 to the classification model MX and perform learning so that the score output from the classification model MX is high.

  The information processing apparatus 100 </ b> A may perform reinforcement learning using the number of characters as an evaluation criterion when the first type is an article text and the second type is a summary. For example, when the first type is an article body and the second type is a summary, the information processing apparatus 100A learns so that the number of characters of the output information FOUT2 is smaller than a predetermined threshold (for example, “20”). May be performed. For example, when the first type is an article body and the second type is a summary, the information processing apparatus 100A calculates a score so that the score is higher as the number of characters in the output information FOUT2 is smaller, and the score of the output information FOUT2 Learning may be performed so as to be high.

  In addition, the information processing apparatus 100A performs learning processing using the model M5 in the first learning FLR2. The information processing apparatus 100A performs a learning process so that the first character information that is input to the model M2 is output from the model M5. For example, when the first character information FCH11 is input to the model M2, the information processing apparatus 100A performs a learning process so that the first character information FCH11 is output from the model M5. For example, when the first character information FCH12 is input to the model M2, the information processing apparatus 100A performs a learning process so that the first character information FCH12 is output from the model M5.

  For example, in the first learning FLR2, the information processing apparatus 100A performs a learning process using the partial model M21 and the model M5 of the model M2 as an auto encoder for the first character information. For example, the information processing apparatus 100A performs a learning process by a method such as back propagation so that the character information output from the model M5 approaches the character information input to the model M2. For example, the information processing apparatus 100A corrects the value of the weight (that is, the connection coefficient) that is considered when the value is transmitted between the nodes, so that the first character information is added to the partial model M21 and the model M5 of the model M2. Learn the features of For example, the information processing apparatus 100A performs a learning process by a technique such as back propagation (error back propagation method) so that the character information output from the model M5 approaches the character information input to the model M2. For example, the information processing apparatus 100A corrects the value of the weight (that is, the connection coefficient) that is considered when the value is transmitted between the nodes, so that the first character information is added to the partial model M21 and the model M5 of the model M2. Learn the features of As described above, the information processing apparatus 100A learns by performing the process such as back propagation that corrects the parameter (connection coefficient) so that the error between the output in the model M5 and the input in the model M2 is small, and the model M2 and A model M5 is generated. For example, the information processing apparatus 100A generates a model M2 and a model M5 by performing processing such as backpropagation so as to minimize a predetermined loss function. Thereby, the information processing apparatus 100A can perform the learning process on the model M2 and the model M5 using only the first character information.

  In addition, the information processing apparatus 100A generates a conversion model by learning processing using the second character information (step S56). The information processing apparatus 100A generates a model M2 by performing learning using the second character information SCH11 to SCH14 in the second type information storage unit 122 as learning data (teacher data). In FIG. 10, type information STL2 for selecting the second type is set as shown in the second learning SLR2. Thereby, in the second learning SLR2, the model M2 is controlled to perform learning corresponding to the second type for the partial model M22. Then, the information processing apparatus 100A performs learning to output the output information SOUT2 as the second character information with the input information SIN2 as the second character information as an input.

  In the second learning SLR2, the information processing apparatus 100A performs a learning process so that the second character information that is input to the model M2 is output from the model M2. For example, when the second character information SCH11 is input to the model M2, the information processing apparatus 100A performs a learning process so that the second character information SCH11 is output from the model M2. For example, when the second character information SCH12 is input to the model M2, the information processing apparatus 100A performs a learning process so that the second character information SCH12 is output from the model M2.

  For example, in the second learning SLR2, the information processing apparatus 100A performs the learning process using the partial model M21 and the partial model M22 as an auto encoder for the second character information. For example, the information processing apparatus 100A performs a learning process by a technique such as back propagation so that the character information output from the model M2 approaches the character information input to the model M2. For example, the information processing apparatus 100A corrects the value of the weight (that is, the connection coefficient) considered when the value is transmitted between the nodes, so that the second character information is included in the partial model M21 and the partial model M22. Learn features. Thereby, the information processing apparatus 100A can perform the learning process on the model M2.

  In addition, the information processing apparatus 100A performs learning processing using the model M5 in the second learning SLR2. The information processing apparatus 100A performs a learning process so that the second character information that is input to the model M2 is output from the model M5. For example, when the second character information SCH11 is input to the model M2, the information processing apparatus 100A performs a learning process so that the second character information SCH11 is output from the model M2. For example, when the second character information SCH12 is input to the model M2, the information processing apparatus 100A performs a learning process so that the second character information SCH12 is output from the model M2.

  For example, in the second learning SLR2, the information processing apparatus 100A performs a learning process using the partial model M21 and the model M5 of the model M2 as an auto encoder for the second character information. For example, the information processing apparatus 100A performs a learning process by a method such as back propagation so that the character information output from the model M5 approaches the character information input to the model M2. For example, the information processing apparatus 100A corrects the second character information to the partial model M21 and the model M5 of the model M2 by correcting the value of the weight (that is, the connection coefficient) considered when the value is transmitted between the nodes. Learn the features of For example, the information processing apparatus 100A performs a learning process by a technique such as back propagation (error back propagation method) so that the character information output from the model M5 approaches the character information input to the model M2. For example, the information processing apparatus 100A corrects the second character information to the partial model M21 and the model M5 of the model M2 by correcting the value of the weight (that is, the connection coefficient) considered when the value is transmitted between the nodes. Learn the features of As described above, the information processing apparatus 100A learns by performing the process such as back propagation that corrects the parameter (connection coefficient) so that the error between the output in the model M5 and the input in the model M2 is small, and the model M2 and A model M5 is generated. For example, the information processing apparatus 100A generates a model M2 and a model M5 by performing processing such as backpropagation so as to minimize a predetermined loss function. Thereby, the information processing apparatus 100A can perform the learning process on the model M2 and the model M5 using only the second character information.

  As described above, the information processing apparatus 100A performs the learning process so that the first type of character information is converted into the second type and output in the first learning FLR2, and in the second learning SLR2, A learning process is performed so as to output the input second type character information. Thereby, the information processing apparatus 100A can perform learning so that the model M2 outputs the second type of character information.

  As described above, the information processing apparatus 100A performs the learning process using the first character information and the learning process using the second character information, thereby associating the first character information with the second character information. Even when there is no learning data (teacher data), the learning process can be performed appropriately. That is, when the combination (teacher data) of the first type character information and the second type character information is insufficient, it is difficult for the information processing apparatus 100A to appropriately provide a service related to character information conversion. Such a problem can be solved. Then, the information processing apparatus 100A can appropriately convert the type of the character information and perform various services by converting the type of the first character information into the second type using the learned model.

[6-2. Information processing (provision processing)]
An example of information processing according to the modification will be described with reference to FIG. FIG. 11 is a diagram illustrating an example of information processing according to the modification. Specifically, FIG. 11 illustrates an example of the providing process among the information processing according to the modification. In FIG. 11, the information processing apparatus 100 </ b> A shows a case where converted character information obtained by converting the type of character information acquired from the information providing apparatus 50 is provided to the information providing apparatus 50.

  First, the information processing apparatus 100A acquires character information that is a generation target of converted character information from the information providing apparatus 50 used by the information provider CP1 (step S61). In the example of FIG. 11, the information processing apparatus 100 </ b> A acquires target character information INF <b> 51 that is the first type of character information from the information providing apparatus 50.

  Then, the information processing apparatus 100A acquires a conversion model (step S62). In the example of FIG. 11, the information processing apparatus 100A acquires the model M2 from the model information storage unit 123A. Note that the information processing apparatus 100A does not acquire the model M5 that is necessary only during learning. Then, the information processing apparatus 100A generates converted character information INF52 by converting the type of the target character information INF51 into the second type using the model M2. Specifically, the information processing apparatus 100A generates the second type of converted character information INF52 by inputting the first type of target character information INF51 to the model M2.

  In the example of FIG. 11, the information processing apparatus 100 </ b> A generates converted character information INF <b> 52 by processing as shown in the processing group PS <b> 2. The information processing apparatus 100A inputs the target character information INF51 to the model M2 (step S63). The information processing apparatus 100A inputs the input information TIN2 that is the target character information INF51 to the model M2, and causes the model M2 to output the output information TOUT2 that is the second type of converted character information INF52. Specifically, the information processing apparatus 100A inputs the target character information INF51 to the partial model M21. Then, the information processing apparatus 100A inputs the intermediate information INT2 output from the partial model M21 to the partial model M22. Then, the information processing apparatus 100A causes the partial model M22 to output the converted character information INF52 (Step S64). Thereby, the information processing apparatus 100A generates converted character information INF52 in which the type of the target character information INF51 of the first type is converted to the second type.

  Then, the information processing apparatus 100A provides the converted character information INF52 to the information providing apparatus 50 (step S65). In the example of FIG. 11, the information processing apparatus 100 </ b> A transmits converted character information INF <b> 52 to the information providing apparatus 50.

  As described above, the information processing apparatus 100A appropriately provides a service related to character information conversion by providing the converted character information INF52 obtained by converting the type of the target character information INF51 into the second type using the model M2. be able to.

[6-3. Configuration of information processing apparatus]
Next, the configuration of the information processing apparatus 100A according to the modification will be described with reference to FIG. FIG. 12 is a diagram illustrating a configuration example of an information processing apparatus 100A according to a modification. As illustrated in FIG. 12, the information processing apparatus 100A includes a communication unit 110, a storage unit 120A, and a control unit 130A. In addition, about the information processing apparatus 100A, about the point similar to the information processing apparatus 100 which concerns on embodiment, description is abbreviate | omitted suitably.

(Storage unit 120A)
The storage unit 120A is realized by, for example, a semiconductor memory element such as a RAM or a flash memory, or a storage device such as a hard disk or an optical disk. As illustrated in FIG. 11, the storage unit 120A according to the modification includes a first type information storage unit 121, a second type information storage unit 122, and a model information storage unit 123A.

(Model information storage unit 123A)
The model information storage unit 123A according to the modification stores information related to the model. For example, the model information storage unit 123A stores model information (model data) generated by information processing. FIG. 13 is a diagram illustrating an example of the model information storage unit according to the modification. The model information storage unit 123A illustrated in FIG. 13 includes items such as “model ID”, “partial model ID”, “use”, and “model data”.

  “Model ID” indicates identification information for identifying a model. For example, the model identified by the model ID “M2” corresponds to the model M2 illustrated in the example of FIG. “Partial model ID” indicates identification information for identifying a partial model of a corresponding model. For example, the partial model identified by the partial model ID “M21” corresponds to the partial model M21 illustrated in the example of FIG. “Use” indicates the use of the corresponding partial model. “Model data” indicates data of a corresponding partial model. For example, “model data” includes information including nodes in each layer, functions adopted by the nodes, connection relationships between the nodes, and connection coefficients set for connections between the nodes.

  For example, in the example shown in FIG. 13, it is shown that the model M2 includes partial models M21 and M22. Further, for example, the model (partial model M21) identified by the partial model ID “M21” has a usage of “character information = intermediate information” and is used to generate intermediate information from the input character information. Show. That is, the partial model M21 is used for extracting features from the input character information. Further, the model data of the partial model M21 indicates that it is model data MDT21.

  In addition, for example, the model (partial model M22) identified by the partial model ID “M22” has an application of “intermediate information⇒second character information” and is used to generate the second character information from the intermediate information. Show. That is, the partial model M22 indicates that it is used to generate second character information from intermediate information that is information indicating the characteristics of the extracted character information. Further, the model data of the partial model M22 is model data MDT22.

  The model M2 (each model data MDT21, MDT22, etc.) is an input layer to which a predetermined type of character information is input, an output layer, or any layer from the input layer to the output layer and other than the output layer And a second element whose value is calculated based on the first element and the weight of the first element, and for each layer other than the output layer for character information input to the input layer The computer is configured to output from the output layer the second type of character information corresponding to the input character information by performing an operation based on the first element and the weight of the first element, with each element belonging to the first element. Is a model for making

  For example, the first element included in the model M2 corresponds to any node of the input layer or the intermediate layer. The second element corresponds to the next node, which is a node to which a value is transmitted from the node corresponding to the first element. The weight of the first element corresponds to a connection coefficient that is a weight considered for a value transmitted from a node corresponding to the first element to a node corresponding to the second element.

  For example, the model identified by the model ID “M5” corresponds to the model M5 illustrated in the example of FIG. FIG. 10 shows that the model M5 has no partial model. The model M5 indicates that the usage is “intermediate information → character information decoding” and is used to decode the character information that is the generation basis of the intermediate information from the intermediate information. That is, the model M5 indicates that the intermediate information generated by the partial model M21 of the model M2 is used as an input and the character information input to the partial model M21 is decoded from the intermediate information. Further, the model data of the model M5 indicates that it is model data MDT5.

  The model information storage unit 123A is not limited to the above, and may store various model information according to the purpose.

(Control unit 130A)
Returning to the description of FIG. 4, the control unit 130 </ b> A is a controller, and is stored in a storage device inside the information processing apparatus 100 </ b> A by, for example, a CPU (Central Processing Unit) or an MPU (Micro Processing Unit). Various programs (corresponding to an example of an information processing program such as a learning program and a generation program) are executed by using the RAM as a work area. The control unit 130A is a controller, and is realized by an integrated circuit such as an application specific integrated circuit (ASIC) or a field programmable gate array (FPGA). The control unit 130A includes an input layer to which the first character information of the first type is input, an output layer, and an input layer to an output layer by information processing according to the model M2 and the like stored in the model information storage unit 123A. A first element belonging to a layer other than the output layer, and a second element whose value is calculated based on the first element and the weight of the first element, the input layer By performing an operation based on the first element and the weight of the first element with respect to the input first character information, each element belonging to each layer other than the output layer is used as the first element. The character information converted into the type is output from the output layer.

  As illustrated in FIG. 4, the control unit 130A includes an acquisition unit 131, a learning unit 132A, a generation unit 133A, and a provision unit 134, and implements or executes information processing functions and operations described below. . Note that the internal configuration of the control unit 130A is not limited to the configuration illustrated in FIG. 4, and may be another configuration as long as information processing described later is performed. The control unit 130A calculates a second value based on the first element and the weight of the first element by information processing according to the model M2 (model data MDT21, MTD22, etc.) stored in the storage unit 120A. The first element and the weight of the first element are the elements belonging to each layer other than the output layer for the first character information of the first type input to the input layer. By performing the calculation based on the character information, the character information obtained by converting the first character information into the second type is output from the output layer.

  The control unit 130A calculates a second value based on the first element and the weight of the first element by information processing according to the model M2 (model data MDT21, MTD22, etc.) stored in the storage unit 120A. By performing an operation based on the weight of the first element and the first element, with each element belonging to each layer other than the output layer as the first element for character information input to the input layer, Character information in which the type of the input character information is converted to the second type is output from the output layer. The model such as the model M2 may be assumed to be used as a program module that is a part of the artificial intelligence software. The model such as the model M2 may be a program.

(Acquisition part 131)
The acquisition unit 131 according to the modification performs the same processing as the acquisition unit 131 according to the embodiment. The acquisition unit 131 acquires various information in the same manner as the acquisition unit 131 according to the embodiment. For example, the acquisition unit 131 acquires learning character information input to the conversion model.

  In the example of FIG. 10, the acquisition unit 131 acquires first character information as learning data LD1. The acquisition unit 131 adds the first character information included in the learning data LD1 as learning data. The acquisition unit 131 adds the learning data LD1 to the first type information storage unit 121. The acquisition unit 131 acquires the second character information as learning data LD2. The acquisition unit 131 adds the second character information included in the learning data LD2 as learning data. The acquisition unit 131 adds the learning data LD2 to the second type information storage unit 122.

  In the example of FIG. 11, the acquisition unit 131 acquires character information that is a generation target of converted character information from the information providing device 50 used by the information provider CP1. The acquisition unit 131 acquires the target character information INF51, which is the first type of character information, from the information providing apparatus 50. The acquisition unit 131 acquires a conversion model. The acquisition unit 131 acquires the model M2 from the model information storage unit 123A.

(Learning unit 132A)
The learning unit 132A according to the modification performs the same process as the learning unit 132 according to the embodiment. The learning unit 132A learns various information in the same manner as the learning unit 132 according to the embodiment.

  The learning unit 132A uses the first character information as input information, learns the first character information as correct information, uses the second character information as input information, and sets the second character information as correct information. Based on the learning, a conversion model is generated that outputs converted character information obtained by converting the target character information into the second type in response to the input of the first type of target character information. The learning unit 132A includes an encoding unit that outputs intermediate information indicating the characteristics of the first character information in response to the input of the first character information, and converted character information corresponding to the intermediate information using the intermediate information as input information. A conversion model including a decoding unit that outputs is generated.

  The learning unit 132A generates a conversion model including an encoding unit that outputs intermediate information indicating characteristics of the second character information in response to the input of the second character information. When the second character information is input, the learning unit 132A generates a conversion model learned so as to output the second character information. When the first character information is input, the learning unit 132A generates a conversion model learned so that the first character information is converted into the second type. The learning unit 132A generates a conversion model by learning using another decoding unit that receives the intermediate information output from the decoding unit. In response to the input of learning character information, learning unit 132A inputs intermediate information output by the decoding unit to another decoding unit, and performs learning processing so that the other decoding unit outputs learning character information. Thus, a conversion model is generated. When the learning character information is the first type, the learning unit 132A converts the learning character information into the second type, and when the learning character information is the second type, the conversion model converts the learning character information into the second type. A conversion model is generated by performing a learning process so as to output.

  The learning unit 132A generates a conversion model by a learning process using the first character information. The learning unit 132A generates the model M2 by performing learning using the first character information FCH11 to FCH14 in the first type information storage unit 121 as learning data (teacher data). As shown in the first learning FLR2, the learning unit 132A is set with type information FTL2 for selecting the first type. The learning unit 132A receives the input information FIN2 that is the first character information, and learns to output the output information FOUT2 that is the second character information corresponding to the input information FIN2.

  In the first learning FLR2, the learning unit 132A performs a learning process so that the second character information obtained by converting the first character information input to the model M2 into the second type is output from the model M2. When the first character information FCH11 is input to the model M2, the learning unit 132A performs a learning process so that the second type of character information corresponding to the first character information FCH11 is output from the model M2. When the first character information FCH12 is input to the model M2, the learning unit 132A performs a learning process so that the second type of character information corresponding to the first character information FCH12 is output from the model M2.

  In the first learning FLR2, the learning unit 132A performs a learning process so that terms for children (child terms) included in the output information FOUT2 increase. The learning unit 132A may calculate the score of the output information FOUT2 using the child term list information used for the article for children, and may learn to increase the score. The learning unit 132A may calculate the score so that the score increases as the ratio of the child terms included in the output information FOUT2 increases, and may perform the learning so that the score of the output information FOUT2 increases. The learning unit 132A performs a learning process by a method such as back propagation (error back propagation method) so that the score of the output information FOUT2 becomes high.

  The learning unit 132A performs learning processing using the model M5 in the first learning FLR2. The learning unit 132A performs a learning process so that the first character information input to the model M2 is output from the model M5. When the first character information FCH11 is input to the model M2, the learning unit 132A performs a learning process so that the first character information FCH11 is output from the model M5. When the first character information FCH12 is input to the model M2, the learning unit 132A performs a learning process so that the first character information FCH12 is output from the model M5.

  In the first learning FLR2, the learning unit 132A performs a learning process using the partial model M21 and the model M5 of the model M2 as an auto encoder for the first character information. The learning unit 132A performs a learning process by a method such as back propagation so that the character information output from the model M5 approaches the character information input to the model M2. The learning unit 132A performs learning processing for the model M2 and the model M5.

  The learning unit 132A generates a conversion model by a learning process using the second character information. The learning unit 132A generates the model M2 by performing learning using the second character information SCH11 to SCH14 in the second type information storage unit 122 as learning data (teacher data). The learning unit 132A receives the input information SIN2 that is the second character information and learns to output the output information SOUT2 that is the second character information.

  In the second learning SLR2, the learning unit 132A performs a learning process so that the second character information that is input to the model M2 is output from the model M2. When the second character information SCH11 is input to the model M2, the learning unit 132A performs a learning process so that the second character information SCH11 is output from the model M2. When the second character information SCH12 is input to the model M2, the learning unit 132A performs a learning process so that the second character information SCH12 is output from the model M2.

  In the second learning SLR2, the learning unit 132A performs learning processing using the partial model M21 and the partial model M22 as an auto encoder for the second character information. The learning unit 132A performs a learning process by a technique such as back propagation so that the character information output from the model M2 approaches the character information input to the model M2. The learning unit 132A learns the characteristics of the second character information in the partial model M21 and the partial model M22 by correcting the value of the weight (that is, the connection coefficient) considered when the value is transmitted between the nodes. Let

  The learning unit 132A performs learning processing using the model M5 in the second learning SLR2. The information processing apparatus 100A performs a learning process so that the second character information that is input to the model M2 is output from the model M5. When the second character information SCH11 is input to the model M2, the learning unit 132A performs a learning process so that the second character information SCH11 is output from the model M2. When the second character information SCH12 is input to the model M2, the learning unit 132A performs a learning process so that the second character information SCH12 is output from the model M2.

  In the second learning SLR2, the learning unit 132A performs a learning process using the partial model M21 and the model M5 of the model M2 as the second character information auto-encoder. The learning unit 132A performs a learning process by a method such as back propagation so that the character information output from the model M5 approaches the character information input to the model M2.

(Generator 133A)
The generation unit 133A performs the same processing as the generation unit 133 according to the embodiment. 133 A of production | generation parts provide various information similarly to the production | generation part 133 which concerns on embodiment.

  In the example of FIG. 11, the generation unit 133A generates converted character information INF52 obtained by converting the type of the target character information INF51 into the second type using the model M2. The generation unit 133A generates the second type of converted character information INF52 by inputting the first type of target character information INF51 to the model M2.

  The generation unit 133A generates the converted character information INF52 by processing as shown in the processing group PS2. The generation unit 133A inputs the target character information INF51 to the model M2. The generation unit 133A inputs the input information TIN2 that is the target character information INF51 to the model M2, and outputs the output information TOUT2 that is the second type of converted character information INF52 from the model M2. The generation unit 133A inputs the target character information INF51 to the partial model M21. The generation unit 133A inputs the intermediate information INT2 output from the partial model M21 to the partial model M22. The generation unit 133A causes the partial model M22 to output the converted character information INF52. The generating unit 133A generates converted character information INF52 in which the type of the target character information INF51 of the first type is converted to the second type.

(Providing unit 134)
The providing unit 134 according to the modification performs the same processing as the providing unit 134 according to the embodiment. The providing unit 134 provides various information in the same manner as the providing unit 134 according to the embodiment.

  In the example of FIG. 11, the providing unit 134 provides the converted character information INF52 to the information providing apparatus 50. In the providing unit 134, the information processing apparatus 100 </ b> A transmits the converted character information INF <b> 52 to the information providing apparatus 50.

[7. effect〕
As described above, the information processing apparatus 100 according to the embodiment and the information processing apparatus 100A according to the modification include the acquisition unit 131 and the learning units 132 and 132A. The acquisition unit 131 acquires first character information that is character information of the first type and second character information that is character information of a second type different from the first type. In addition, the learning units 132 and 132A use the first character information as input information, learn the first character information as correct information, use the second character information as input information, and use the second character information as input information. Based on the learning as the correct answer information, a conversion model is generated that outputs converted character information obtained by converting the target character information into the second type in response to the input of the first type of target character information.

  As described above, the information processing apparatus 100 according to the embodiment and the information processing apparatus 100A according to the modification use the first character information as input information and the learning using the first character information as correct information, A conversion in which the target character information is converted to the second type in accordance with the input of the first type of target character information based on the learning using the character information as input information and the second character information as correct information. By generating a conversion model that outputs character information, it is possible to appropriately provide a service related to character information conversion.

  Further, in the information processing apparatus 100 according to the embodiment and the information processing apparatus 100A according to the modification, the learning units 132 and 132A are intermediate information indicating characteristics of the first character information according to the input of the first character information. A conversion model is generated that includes an encoding unit that outputs and an intermediate information as input information, and a decoding unit that outputs converted character information corresponding to the intermediate information.

  As described above, the information processing apparatus 100 according to the embodiment and the information processing apparatus 100A according to the modified example output the intermediate information indicating the characteristics of the first character information in response to the input of the first character information. And a conversion model including a decoding unit that outputs the converted character information corresponding to the intermediate information using the intermediate information as input information, can appropriately provide a service related to character information conversion. .

  In the information processing apparatus 100 according to the embodiment, the learning unit 132 inputs an intermediate information and an encoding unit that outputs intermediate information indicating characteristics of the second character information in response to the input of the second character information. The information is a conversion model including a decoding unit that outputs the first character information corresponding to the intermediate information, and the other target character information is the first according to the input of the other target character information of the second type. A conversion model that outputs other converted character information converted into the type is generated.

  As described above, the information processing apparatus 100 according to the embodiment, in response to an input of the second character information, an encoding unit that outputs intermediate information indicating the characteristics of the second character information, and the intermediate information as input information. The conversion model includes a decoding unit that outputs first character information corresponding to the intermediate information, and the other target character information is converted to the first type in response to the input of the second type of other target character information. By generating a conversion model that outputs other converted character information, a service related to character information conversion can be appropriately provided.

  In the information processing apparatus 100 according to the embodiment, the acquisition unit 131 acquires selection information for selecting the type of character information output from the conversion model. The learning unit 132 generates a conversion model that outputs character information of a type corresponding to the selection information.

  As described above, the information processing apparatus 100 according to the embodiment acquires selection information for selecting a type of character information output by the conversion model, and generates a conversion model that outputs character information of a type corresponding to the selection information. Thus, it is possible to appropriately provide a service related to character information conversion.

  In the information processing apparatus 100 according to the embodiment, the acquisition unit 131 acquires selection information for selecting a learning type that is a type corresponding to learning character information input to the conversion model. The learning unit 132 generates a conversion model by performing a learning process so as to output the learning character information based on the learning type in response to the input of the learning character information.

  As described above, the information processing apparatus 100 according to the embodiment acquires selection information for selecting a learning type that is a type corresponding to the learning character information input to the conversion model, and learns according to the input of the learning character information. By performing the learning process so as to output the learning character information based on the type, it is possible to appropriately provide a service relating to character information conversion by generating a conversion model.

  Further, in the information processing apparatus 100 according to the embodiment, the learning unit 132, in response to the input of the first character information, the first encoder that outputs intermediate information indicating the characteristics of the first character information, and the second character information In response to the input, a conversion model including an encoding unit having a second encoder that outputs intermediate information indicating characteristics of the second character information is generated.

  As described above, the information processing apparatus 100 according to the embodiment receives the first character information according to the input of the first character information and outputs the intermediate information indicating the characteristics of the first character information and the input of the second character information. Accordingly, it is possible to appropriately provide a service related to character information conversion by generating a conversion model including an encoding unit having a second encoder that outputs intermediate information indicating the characteristics of the second character information. it can.

  In the information processing apparatus 100 according to the embodiment, the learning unit 132 includes a first decoder that outputs first character information corresponding to the intermediate information, and a second decoder that outputs second character information corresponding to the intermediate information. A transformation model including a decoding unit having

  As described above, the information processing apparatus 100 according to the embodiment includes a first decoder that outputs first character information corresponding to intermediate information, and a second decoder that outputs second character information corresponding to intermediate information. By generating a conversion model including the conversion unit, it is possible to appropriately provide a service relating to character information conversion.

  Further, in the information processing apparatus 100A according to the modification, the learning unit 132A generates a conversion model including an encoding unit that outputs intermediate information indicating the characteristics of the second character information in response to the input of the second character information. To do.

  As described above, the information processing apparatus 100A according to the modification generates a conversion model including an encoding unit that outputs intermediate information indicating the characteristics of the second character information in response to the input of the second character information. Thus, it is possible to appropriately provide a service related to character information conversion.

  In the information processing apparatus 100A according to the modification, when the second character information is input, the learning unit 132A generates a conversion model learned to output the second character information.

  As described above, when the second character information is input, the information processing apparatus 100A according to the modification generates a conversion model that is learned to output the second character information. Service can be appropriately provided.

  Further, in the information processing apparatus 100A according to the modification, when the first character information is input, the learning unit 132A generates a conversion model learned so that the first character information is converted into the second type. To do.

  As described above, when the first character information is input, the information processing apparatus 100A according to the modification generates the conversion model learned so that the first character information is converted into the second type. Thus, it is possible to appropriately provide a service related to character information conversion.

  In the information processing apparatus 100A according to the modification, the learning unit 132A generates a conversion model by learning using another decoding unit that receives the intermediate information output from the decoding unit.

  In this way, the information processing apparatus 100A according to the modification generates a conversion model by learning using another decoding unit that receives the intermediate information output from the decoding unit, thereby providing a service related to character information conversion. Can be provided appropriately.

  In the information processing apparatus 100A according to the modification, the acquisition unit 131 acquires learning character information input to the conversion model. In response to the input of learning character information, learning unit 132A inputs intermediate information output by the decoding unit to another decoding unit, and performs learning processing so that the other decoding unit outputs learning character information. Thus, a conversion model is generated.

  As described above, the information processing apparatus 100A according to the modified example acquires the learning character information input to the conversion model, and the intermediate information output by the decoding unit according to the input of the learning character information is transmitted to the other decoding units. By generating the conversion model by performing the learning process so that the other decoding unit outputs the learning character information, it is possible to appropriately provide a service related to the character information conversion.

  Further, in the information processing apparatus 100A according to the modification, when the learning character information is the first type, the learning unit 132A converts the learning character information into the second type and the learning character information is the second type. If it is, the conversion model is generated by performing learning processing so that the conversion model outputs the learning character information.

  As described above, in the information processing apparatus 100A according to the modification, when the learning character information is the first type, the conversion model converts the learning character information into the second type, and the learning character information is the second type. By performing the learning process so that the conversion model outputs the learning character information, it is possible to appropriately provide a service related to character information conversion by generating the conversion model.

  Further, the information processing apparatus 100 according to the embodiment and the information processing apparatus 100A according to the modification include generation units 133 and 133A. The acquisition unit 131 converts a first character information, which is character information of the first type, into second character information, which is character information of a second type different from the first type, and a target character of the first type Get information and. The generation units 133 and 133A generate converted character information in which the target character information is converted into the second type by inputting the target character information into the conversion model.

  As described above, the information processing apparatus 100 according to the embodiment and the information processing apparatus 100A according to the modified example convert the first character information that is the first type of character information into the second type of character information that is different from the first type. The conversion model for converting to the second character information and the first type of target character information are acquired, and the target character information is input to the conversion model. As a result, the information processing apparatuses 100 and 100A can generate converted character information in which the target character information is converted into the second type, and thus can appropriately provide a service related to character information conversion.

  In the information processing apparatus 100 according to the embodiment, the acquisition unit 131 acquires a conversion model for converting the second character information into the first character information and other target character information of the second type. The generation unit 133 generates other converted character information in which the other target character information is converted into the first type by inputting the other target character information into the conversion model.

  As described above, the information processing apparatus 100 according to the embodiment acquires the conversion model for converting the second character information to the first character information and the other target character information of the second type. The generation unit 133 inputs other target character information to the conversion model. Thereby, since the information processing apparatus 100 can generate other converted character information in which other target character information is converted into the first type, it is possible to appropriately provide a service related to character information conversion. .

  In the information processing apparatus 100 according to the embodiment, the acquisition unit 131 acquires selection information for selecting the type of character information output from the conversion model. The generation unit 133 generates character information of a type corresponding to the selection information by inputting the selection information to the conversion model.

  As described above, the information processing apparatus 100 according to the embodiment acquires selection information for selecting the type of character information output from the conversion model, and inputs the selection information to the conversion model. Thereby, since the information processing apparatus 100 can generate character information of a type corresponding to the selection information, it is possible to appropriately provide a service related to character information conversion.

  Further, in the information processing apparatus 100 according to the embodiment, the acquisition unit 131 is a type that is the target character information input to the conversion model and one of the first type and the second type, and is different from the type of the target character information. Selection information for selecting the other type is acquired. The generation unit 133 generates converted character information in which the target character information is converted into the other type by inputting the target character information and the selection information into the conversion model.

  As described above, the information processing apparatus 100 according to the embodiment includes the target character information input to the conversion model and the other type that is a type of the first type or the second type and is different from the type of the target character information. The selection information for selecting is acquired, and the target character information and the selection information are input to the conversion model. As a result, the information processing apparatus 100 can generate converted character information in which the target character information is converted into the other type, so that a service related to character information conversion can be appropriately provided.

  Further, in the information processing apparatus 100 according to the embodiment and the information processing apparatus 100A according to the modification, the first type and the second type are types in the same language.

  As described above, the information processing apparatus 100 according to the embodiment and the information processing apparatus 100A according to the modified example perform character information processing by performing processing on the first type and the second type that are types in the same language. It is possible to appropriately provide a conversion service.

  In the information processing apparatus 100 according to the embodiment and the information processing apparatus 100A according to the modification, the first type is a news article and the second type is an article for children.

  As described above, the information processing apparatus 100 according to the embodiment and the information processing apparatus 100A according to the modification perform processing for the first type that is a news article and the second type that is an article for children. Thus, it is possible to appropriately provide a service related to character information conversion.

  Further, in the information processing apparatus 100 according to the embodiment and the information processing apparatus 100A according to the modification, the first type is character information including characters equal to or more than the first number of characters, and the second type is equal to or less than the first number of characters. Character information including characters less than the second number of characters.

  As described above, the information processing apparatus 100 according to the embodiment and the information processing apparatus 100A according to the modified example are less than the first type to which the character information including the characters equal to or more than the first character belongs and the second character number equal to or less than the first character number. By performing the process on the second type to which the character information including the character belongs, it is possible to appropriately provide a service relating to character information conversion.

  Further, in the information processing apparatus 100 according to the embodiment and the information processing apparatus 100A according to the modification, the first type is a text and the second type is a summary.

  As described above, the information processing apparatus 100 according to the embodiment and the information processing apparatus 100A according to the modification process the first type that is the text of the article and the second type that is the summary of the article. By doing so, it is possible to appropriately provide a service relating to character information conversion.

[8. Hardware configuration)
The information processing apparatus 100 according to the embodiment described above is realized by a computer 1000 configured as shown in FIG. 14, for example. FIG. 14 is a hardware configuration diagram illustrating an example of a computer that implements the functions of the information processing apparatus. The computer 1000 includes a CPU 1100, a RAM 1200, a ROM (Read Only Memory) 1300, an HDD (Hard Disk Drive) 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F). ) 1700.

  The CPU 1100 operates based on a program stored in the ROM 1300 or the HDD 1400 and controls each unit. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started up, a program depending on the hardware of the computer 1000, and the like.

  The HDD 1400 stores programs executed by the CPU 1100, data used by the programs, and the like. The communication interface 1500 receives data from other devices via the network N and sends the data to the CPU 1100, and transmits data generated by the CPU 1100 to other devices via the network N.

  The CPU 1100 controls an output device such as a display and a printer and an input device such as a keyboard and a mouse via the input / output interface 1600. The CPU 1100 acquires data from the input device via the input / output interface 1600. The CPU 1100 outputs the generated data to the output device via the input / output interface 1600.

  The media interface 1700 reads a program or data stored in the recording medium 1800 and provides it to the CPU 1100 via the RAM 1200. The CPU 1100 loads such a program from the recording medium 1800 onto the RAM 1200 via the media interface 1700, and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or PD (Phase change rewritable disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory. Etc.

  For example, when the computer 1000 functions as the information processing apparatuses 100 and 100A according to the embodiment, the CPU 1100 of the computer 1000 displays a program or data loaded on the RAM 1200 (for example, model M1 (each model data MDT11 to MDT14)). By executing the above, the functions of the control units 130 and 130A are realized. The CPU 1100 of the computer 1000 reads and executes these programs or data (for example, the model M1 (the respective model data MDT11 to MDT14)) from the recording medium 1800. As another example, the CPU 1100 receives the program or data from other devices via the network N. You may acquire these programs.

  As described above, some of the embodiments and modifications of the present application have been described in detail with reference to the drawings. It is possible to carry out the present invention in other forms that have been modified and improved.

[9. Others]
In addition, among the processes described in the above-described embodiments and modifications, all or a part of the processes described as being automatically performed can be manually performed, or are described as being performed manually. All or part of the processing can be automatically performed by a known method. In addition, the processing procedures, specific names, and information including various data and parameters shown in the document and drawings can be arbitrarily changed unless otherwise specified. For example, the various types of information illustrated in each drawing is not limited to the illustrated information.

  Further, each component of each illustrated apparatus is functionally conceptual, and does not necessarily need to be physically configured as illustrated. In other words, the specific form of distribution / integration of each device is not limited to that shown in the figure, and all or a part thereof may be functionally or physically distributed or arbitrarily distributed in arbitrary units according to various loads or usage conditions. Can be integrated and configured.

  In addition, the above-described embodiments and modification examples can be combined as appropriate within a range that does not contradict processing contents.

  In addition, the “section (module, unit)” described above can be read as “means” or “circuit”. For example, the acquisition unit can be read as acquisition means or an acquisition circuit.

DESCRIPTION OF SYMBOLS 1 Information processing system 100, 100A Information processing apparatus 121 1st type information storage part 122 2nd type information storage part 123, 123A Model information storage part 130, 130A Control part 131 Acquisition part 132, 132A Learning part 133, 133A Generation part 134 Providing unit 10 Terminal device 50 Information providing device N Network

Claims (25)

An acquisition unit that acquires first character information that is character information of a first type and second character information that is character information of a second type different from the first type;
Learning with the first character information as input information, learning with the first character information as correct information, and learning with the second character information as input information and with the second character information as correct information Based on the input of the first type of target character information, a learning unit that generates a conversion model that outputs the converted character information obtained by converting the target character information into the second type;
An information processing apparatus comprising: The learning unit
In response to the input of the first character information, an encoding unit that outputs intermediate information indicating the characteristics of the first character information, and the converted character information corresponding to the intermediate information is output using the intermediate information as input information. The information processing apparatus according to claim 1, wherein the conversion model including a decoding unit is generated. The learning unit
In response to the input of the second character information, the encoding unit that outputs intermediate information indicating the characteristics of the second character information, and the first character information corresponding to the intermediate information using the intermediate information as input information The conversion model including the decoding unit that outputs the other, the other conversion in which the other target character information is converted into the first type in response to the input of the other target character information of the second type The information processing apparatus according to claim 2, wherein the conversion model that outputs character information is generated. The acquisition unit
Obtaining selection information for selecting the type of character information output by the conversion model;
The learning unit
The information processing apparatus according to claim 3, wherein the conversion model that outputs character information of a type corresponding to the selection information is generated. The acquisition unit
Obtaining the selection information for selecting a learning type that is a type corresponding to the learning character information input to the conversion model;
The learning unit
5. The conversion model is generated by performing learning processing so as to output the learning character information based on the learning type in response to an input of the learning character information. Information processing device. The learning unit
In response to the input of the first character information, the first encoder that outputs the intermediate information indicating the characteristics of the first character information; and the characteristics of the second character information in response to the input of the second character information. The information processing apparatus according to any one of claims 3 to 5, wherein the conversion model including the encoding unit including a second encoder that outputs intermediate information to be displayed is generated. The learning unit
Generating the conversion model including the decoding unit having a first decoder that outputs the first character information corresponding to the intermediate information and a second decoder that outputs the second character information corresponding to the intermediate information The information processing apparatus according to any one of claims 3 to 6, wherein: The learning unit
3. The information according to claim 2, wherein the conversion model including the encoding unit that outputs the intermediate information indicating the characteristics of the second character information is generated in response to the input of the second character information. Processing equipment. The learning unit
The information processing apparatus according to claim 8, wherein, when the second character information is input, the conversion model learned to output the second character information is generated. The learning unit
The said conversion model learned so that the said 1st character information may be converted into the said 2nd classification is produced | generated when the said 1st character information is input. The Claim 8 or Claim 9 characterized by the above-mentioned. The information processing apparatus described. The learning unit
The information processing according to any one of claims 8 to 10, wherein the conversion model is generated by learning using another decoding unit that receives the intermediate information output by the decoding unit. apparatus. The acquisition unit
Obtain learning character information to be input to the conversion model,
The learning unit
In response to the input of the learning character information, the intermediate information output by the decoding unit is input to the other decoding unit, and a learning process is performed so that the other decoding unit outputs the learning character information. The information processing apparatus according to claim 11, wherein the conversion model is generated by performing. The learning unit
When the learning character information is the first type, the conversion model converts the learning character information into the second type, and when the learning character information is the second type, the conversion model is the learning character. The information processing apparatus according to claim 12, wherein the conversion model is generated by performing learning processing so as to output information. A conversion model for converting first character information, which is character information of the first type, into second character information, which is character information of a second type different from the first type, and target character information of the first type An acquisition unit to acquire;
A generation unit that generates converted character information in which the target character information is converted into the second type by inputting the target character information into the conversion model;
An information processing apparatus comprising: The acquisition unit
Obtaining the conversion model for converting the second character information into the first character information, and other target character information of the second type,
The generator is
The other converted character information in which the other target character information is converted into the first type is generated by inputting the other target character information into the conversion model. Information processing device. The acquisition unit
Obtaining selection information for selecting the type of character information output by the conversion model;
The generator is
The information processing apparatus according to claim 15, wherein character information of a type corresponding to the selection information is generated by inputting the selection information to the conversion model. The acquisition unit
Obtaining the selection information for selecting the target character information to be input to the conversion model and one of the first type and the second type, and selecting the other type different from the type of the target character information;
The generator is
The information according to claim 16, wherein converted character information in which the target character information is converted into the other type is generated by inputting the target character information and the selection information into the conversion model. Processing equipment. The information processing apparatus according to claim 1, wherein the first type and the second type are types in the same language. The information processing apparatus according to any one of claims 1 to 18, wherein the first type is a news article, and the second type is an article for children. The first type is character information including characters equal to or more than a first character number, and the second type is character information including characters less than a second character number equal to or less than the first character number. The information processing apparatus according to any one of 1 to 18. The information processing apparatus according to any one of claims 1 to 18, wherein the first type is a text, and the second type is a summary. An information processing method executed by a computer,
An acquisition step of acquiring first character information that is character information of the first type and second character information that is character information of a second type different from the first type;
Learning with the first character information as input information, learning with the first character information as correct information, and learning with the second character information as input information and with the second character information as correct information Based on the input of the first type of target character information, a learning step of generating a conversion model that outputs the converted character information obtained by converting the target character information into the second type;
An information processing method comprising: An acquisition procedure for acquiring first character information that is character information of the first type and second character information that is character information of a second type different from the first type;
Learning with the first character information as input information, learning with the first character information as correct information, and learning with the second character information as input information and with the second character information as correct information Based on the input of the first type of target character information, a learning procedure for generating a conversion model that outputs the converted character information obtained by converting the target character information into the second type;
An information processing program for causing a computer to execute. An information processing method executed by a computer,
A conversion model for converting first character information, which is character information of the first type, into second character information, which is character information of a second type different from the first type, and target character information of the first type An acquisition process to acquire;
Generating the converted character information in which the target character information is converted into the second type by inputting the target character information into the conversion model;
An information processing method comprising: A conversion model for converting first character information, which is character information of the first type, into second character information, which is character information of a second type different from the first type, and target character information of the first type Acquisition procedure to acquire,
A generation procedure for generating converted character information in which the target character information is converted into the second type by inputting the target character information into the conversion model;
An information processing program for causing a computer to execute.

Images