JP6481904B2 - Learning device, editing device, learning method, editing method, and program - Google Patents

Description

  The present invention relates to a learning device that learns change instruction information, which is information related to a change instruction group for a content set such as an electronic book / catalog.

  Conventionally, there has been an electronic book creation system that makes it easy to create and edit electronic books. The system includes a block selection unit that accepts selection of any of a plurality of blocks, an object designation unit that accepts designation of an object to be placed in the selected block, and an object that places an object designated in the selected block Arrangement means is provided (see, for example, Patent Document 1).

JP 2016-162121 A

  However, in the prior art, it has been impossible to learn advanced editing work when creating a content set such as an electronic catalog or an electronic book, and use the learned result.

  In view of this point, an object of the present invention is to provide a learning device that learns editing work using techniques such as deep learning and machine learning such as a decision tree. Another object of the present invention is to provide an editing apparatus that uses learned information to make editing work more efficient.

  The learning device according to the first aspect of the present invention automatically stores a content set storage unit that stores a content set having two or more parts including content having one or more attribute values, and an attribute value of the parts that the content set has. A learning information storage unit for storing learning information used for changing, a content set output unit for outputting a part or all of the content set, and an instruction for changing the content set output by the content set output unit Information regarding a change instruction receiving unit to be received, a manual change unit that changes and outputs the content set output by the content set output unit according to the change instruction, and a series of change instructions that are one or more continuous change instructions A learning unit that acquires the change instruction information, learns the change instruction information, configures the learning information, and stores the learning information in the learning information storage unit It is a learning device.

  With this configuration, it is possible to learn advanced editing work when creating a content set such as an electronic catalog or an electronic book.

  Further, in the learning device of the second invention, in contrast to the first invention, the change instruction information includes learning input information applied to the learning information and learning output information expected as a result applied to the learning information. Is a learning device.

  With this configuration, it is possible to learn advanced editing work when creating a content set such as an electronic catalog or an electronic book.

  Further, in the learning device according to the third aspect of the invention, the learning input information is input attribute information that is a set of attribute values of one or more parts before the change, and the learning output information is The learning apparatus is output attribute information that is a set of attribute values of one or more parts after the change.

  With this configuration, it is possible to learn advanced editing work when creating a content set such as an electronic catalog or an electronic book.

  According to the learning device of the fourth aspect of the invention, in contrast to the second aspect of the invention, the learning input information is first change instruction information having a change instruction and one or more attribute values of a changed part corresponding to the change instruction. Yes, the learning output information is a learning device that is second change instruction information having one or more attribute values of a changed part corresponding to one or more change instructions received after the change instruction included in the first change instruction information. is there.

  With this configuration, it is possible to learn advanced editing work when creating a content set such as an electronic catalog or an electronic book.

  Further, in the learning device according to the fifth aspect of the present invention, in response to any one of the second to fourth aspects, the learning unit receives a learning input in response to detecting an instruction that satisfies a predetermined first condition. Determine acquisition of information, acquire learning input information according to the determination, and determine acquisition of learning output information in response to detecting an instruction that satisfies a predetermined second condition, It is a learning device that acquires learning output information.

  With this configuration, it is possible to learn advanced editing work when creating a content set such as an electronic catalog or an electronic book.

  The learning apparatus according to the sixth aspect of the present invention is the learning apparatus according to any one of the first to fifth aspects, wherein the change instruction received by the change instruction receiving unit is a structure change instruction for changing a configuration of a content set. It is.

  With this configuration, it is possible to learn operations on other components after an operation of changing the configuration of a content set such as an electronic catalog or an electronic book.

  The learning device according to the seventh aspect of the invention is a learning device according to the sixth aspect, wherein the configuration change instruction is an addition instruction that is an instruction to add content or a deletion instruction that is an instruction to delete content. .

  With this configuration, it is possible to learn operations on other parts after addition or deletion of parts constituting a content set such as an electronic catalog or an electronic book.

  In the learning device according to the eighth aspect of the present invention, the change instruction received by the change instruction receiving unit is an attribute value change instruction for changing an attribute value of a component. Device.

  With this configuration, it is possible to learn an operation for another component after an operation of changing the attribute value of a component of a content set such as an electronic catalog or an electronic book.

  The editing apparatus according to the ninth aspect of the present invention is the learning device according to any one of the second to fifth aspects, wherein the learning unit is a component corresponding to the change instruction when the change instruction receiving unit receives the change instruction. On the other hand, the learning device acquires one or more attribute values of one or more other parts that satisfy a predetermined condition as learning input information or learning output information.

  With this configuration, it is possible to learn advanced editing work when creating a content set such as an electronic catalog or an electronic book.

  Further, in the learning device of the tenth invention, the predetermined condition is that the predetermined condition is arranged on the same page as the page on which the part corresponding to the change instruction is arranged. A learning device.

  With this configuration, it is possible to more appropriately learn advanced editing work when creating a content set such as an electronic catalog or an electronic book.

  The learning apparatus according to the eleventh aspect of the invention is a learning apparatus in which the content set has two or more pages as compared with any one of the first to tenth aspects.

  With this configuration, it is possible to learn advanced editing work when creating a content set having two or more pages.

  The editing apparatus according to the twelfth aspect of the present invention stores a content set storage unit that stores a content set having two or more parts including content having one or more attribute values, and learning information learned by the learning device. A learning information storage unit, a content set output unit that outputs a part or all of the content set, a change instruction reception unit that receives one or more change instructions for the content set output by the content set output unit, In accordance with the above change instruction, the manual change unit that changes the content set output by the content set output unit and outputs the learning input information according to the one or more change instructions, and the learning input information becomes the learning information. The editing apparatus includes an automatic change unit that applies, acquires learning output information, and changes a content set using the learning output information.

  With such a configuration, editing work can be efficiently performed using learning information that is a result of learning advanced editing work when creating a content set such as an electronic catalog or an electronic book.

  Further, in the editing device of the thirteenth invention, in contrast to the twelfth invention, the automatic change unit acquires one or more attribute values after the change of the parts of the content set changed by the manual change unit. Changed part attribute value acquisition means and peripheral part attribute value acquisition means for acquiring one or more attribute values of one or more other parts that satisfy a predetermined condition for the parts of the content set changed by the manual change unit Learning input information having one or more attribute values acquired by the changed component attribute value acquiring unit and one or more attribute values of one or more other components acquired by the peripheral component attribute value acquiring unit is applied to the learning information. The learning output information acquisition means for acquiring learning output information including one or more attribute values for other parts different from the parts, and the learning output information acquired by the learning output information acquisition means, the attribute values of the other parts Automatic change means to change Is an editing apparatus comprising.

  With such a configuration, editing work can be performed more efficiently by using learning information that is a result of learning advanced editing work when creating a content set such as an electronic catalog or an electronic book.

  Further, the editing device of the fourteenth aspect of the invention acquires change instruction information that is information relating to a series of change instructions that are one or more continuous change instructions for the twelfth or thirteenth invention, The editing apparatus further includes a learning unit that learns change instruction information, configures learning information, and stores the learning information in a learning information storage unit.

  With such a configuration, it is possible to efficiently perform editing work using learning information while learning advanced editing work when creating a content set such as an electronic catalog or an electronic book.

  According to the learning device of the present invention, it is possible to learn advanced editing work when creating a content set such as an electronic catalog or an electronic book.

Block diagram of learning device 1 according to Embodiment 1 The flowchart explaining the operation example of the learning apparatus 1 Figure showing the temporary management table Figure showing the electronic product catalog Figure showing the electronic product catalog Figure showing the electronic product catalog Figure showing the electronic product catalog Figure showing the electronic product catalog Figure showing the temporary management table Figure showing the electronic product catalog Figure showing the electronic product catalog Figure showing the electronic product catalog Conceptual diagram of editing system A in the second embodiment Block diagram of the editing system A A flowchart for explaining the operation of the editing apparatus 2 Block diagram of editing apparatus 4 according to Embodiment 3 A flowchart for explaining the operation of the editing apparatus 4 Overview of the computer system in the above embodiment Block diagram of the computer system

  Hereinafter, embodiments of a learning apparatus and the like will be described with reference to the drawings. In addition, since the component which attached | subjected the same code | symbol in embodiment performs the same operation | movement, description may be abbreviate | omitted again.

  (Embodiment 1)

  In the present embodiment, a learning apparatus that learns change instruction information that is information about a change instruction group for a content set such as an electronic book / catalog will be described. Note that the change instruction information may be information having information related to an operation performed by the user, or may be information having attribute values of one or more parts constituting the content set.

  In the present embodiment, the change instruction information usually includes learning input information applied to the learning information and learning output information expected as a result applied to the learning information.

  FIG. 1 is a block diagram of a learning apparatus 1 in the present embodiment.

  The learning device 1 includes a storage unit 11, a reception unit 12, a processing unit 13, and an output unit 14. The storage unit 11 includes a content set storage unit 111 and a learning information storage unit 112. The receiving unit 12 includes a change instruction receiving unit 121. The processing unit 13 includes a manual change unit 131 and a learning unit 132. The output unit 14 includes a content set output unit 141.

  The storage unit 11 stores various types of information. The various types of information are, for example, a content set described later and learning information described later.

  The content set storage unit 111 stores content sets. The content set includes, for example, an electronic catalog, an electronic book, an electronic manual, an electronic flyer, an electronic brochure, an electronic manual, and an electronic newspaper. However, the content set may be information that is printed after production and becomes a catalog, a book, a manual, a flyer, a brochure, a manual, or a newspaper. It is preferable that the content set has two or more pages. A content set has two or more parts. A component is information constituting a content set. The component has one or more attribute values. The parts are, for example, contents, pages, lines, figures, rectangles, frames, and the like. The component includes content having one or more attribute values. Content is an object that you want to convey to the user. The content is, for example, a photograph of a product posted in an electronic catalog, a description, product information, and the like. The content is, for example, an illustration image, video, character string, or the like that constitutes the electronic book. The content is, for example, a still image, a moving image, a character string, audio, etc., and its data structure is not limited. The attribute value of a part is a position, a size, a color, a page number to which it belongs, and the like. The position is expressed by (x, y), for example. The product information is, for example, composite content including a product photo and a product description.

  The learning information storage unit 112 stores learning information. The learning information is information used for automatically changing the content set.

  The learning information is, for example, information used for automatically changing the attribute value of a part included in the content set. The learning information is information used for automatically changing the configuration of the content set, for example. Note that the configuration change is the addition or deletion of a part. The learning information is, for example, information learned as a set of learning input information that is information applied to the learning information and learning output information that is information expected as a result applied to the learning information. The learning information is, for example, information of a set of learning input information that is information applied to the learning information and learning output information that is information expected as a result applied to the learning information. The data structure of the learning information is, for example, a neural network or a correspondence table. The neural network is, for example, an RNN (recursive neural network) or a CNN (convolutional neural network). The correspondence table has one or more correspondence information that is a set of input and output.

  The receiving unit 12 receives various instructions and information. The various instructions and information are, for example, an output instruction and a change instruction to be described later. The output instruction is an instruction to output a content set. Here, reception means reception of information input from an input device such as a keyboard, mouse, touch panel, reception of information transmitted via a wired or wireless communication line, recording on an optical disk, magnetic disk, semiconductor memory, or the like. It is a concept including reception of information read from a medium.

  The input means for various instructions and information may be anything such as a touch panel, a keyboard, a mouse, or a menu screen. The receiving unit 12 can be realized by a device driver for input means such as a touch panel and a keyboard, control software for a menu screen, and the like.

  The change instruction receiving unit 121 receives a content set change instruction output from the content set output unit 141. The change instruction is an instruction to change the content set being output. The change instruction is, for example, a configuration change instruction, an attribute value change instruction, or the like. The configuration change instruction is an instruction to change the parts constituting the content set. The configuration change instruction includes, for example, an addition instruction that is an instruction to add a part to a content set and a deletion instruction that is an instruction to delete a part from the content set. The configuration change instruction includes content addition, content deletion, frame addition, frame deletion, page generation, page deletion, page layer generation, page layer deletion, and the like. The operation based on the attribute value change instruction includes, for example, enlargement of the frame, reduction of the frame, change of the number of characters in the frame, change of the shape of the frame, change of the color of the frame, change of the color of the frame of the frame, type of the frame of the frame Change, page type change (for example, change between master page and normal page), page size change, font size increase, font size reduction, font type change, font attributes (long, flat) Body, italic, underlined, strikethrough, etc.), paragraph settings (sentence, end of sentence, line spacing, character spacing, number of characters, etc.), image attribute changes (enlargement, reduction, transformation, etc.), video attribute changes Voice attribute change, grouping of a plurality of parts (for example, grouping two or more parts related to the same product), and the like.

  The processing unit 13 performs various processes. The various processes are processes performed by the manual change unit 131 and the learning unit 132, for example. The various processes are processes for reading a content set from the content set storage unit 111 according to an output instruction, for example.

  The manual change unit 131 changes and outputs the content set output by the content set output unit 141 in accordance with the change instruction. Since the process of the manual change part 131 is a well-known technique, detailed description is abbreviate | omitted.

  The learning unit 132 acquires change instruction information that is information regarding a series of change instructions that are one or more continuous change instructions, learns the change instruction information, configures learning information, and stores the learning information as the learning information storage unit 112. To accumulate.

  It is preferable that the change instruction information includes learning input information applied to the learning information and learning output information expected as a result applied to the learning information. That is, it is preferable that the learning unit 132 acquires the learning information so that the probability that the learning output information is output increases when all or part of the learning input information is applied to the learning information.

  The learning input information is preferably input attribute information that is a set of attribute values of one or more parts before the change. The learning output information is preferably output attribute information that is a set of attribute values of one or more parts after the change.

  The learning input information may be first change instruction information having a change instruction and one or more attribute values of a changed part corresponding to the change instruction. Further, the learning output information may be second change instruction information having one or more attribute values of a change part corresponding to one or more change instructions received after the change instruction included in the first change instruction information. .

  The learning unit 132 determines acquisition of learning input information in response to detecting an instruction that satisfies a predetermined first condition, acquires learning input information in accordance with the determination, and determines a predetermined first It is preferable to determine acquisition of learning output information in response to detecting an instruction satisfying two conditions, and acquire learning output information in accordance with the determination.

  The instructions that satisfy the predetermined first condition include, for example, a new content set start instruction, a new page output instruction, a new part addition instruction, a part deletion instruction, and a predetermined type. For example, an attribute value change instruction (for example, an image), a predetermined attribute value (for example, size, color, etc.) change instruction, a page generation instruction, a page deletion instruction, or the like.

  Further, the instruction satisfying the predetermined second condition includes, for example, an instruction to output a new page, an instruction to stop a device that edits a content set, an instruction to end editing, an instruction that satisfies the first condition, and the like It is.

  When the learning unit 132 detects an instruction satisfying a predetermined first condition, the learning unit 132 receives learning input information corresponding to one or more change instructions from the instruction or from the next of the instruction. get. The learning input information in this case is, for example, one or more attribute values of one or more parts of the content set after the execution of the process corresponding to the instruction that satisfies the first condition. The learning input information in this case is, for example, one or more attribute values of one or more parts of the content set immediately before execution of the process corresponding to the instruction that satisfies the first condition. Moreover, the learning input information in this case is information including an instruction that satisfies the first condition, for example.

  When the learning unit 132 detects an instruction that satisfies a predetermined second condition, the learning unit 132 acquires learning output information corresponding to the instruction. The learning output information in this case is, for example, one or more attribute values of one or more parts of the content set immediately before executing the process corresponding to the instruction that satisfies the second condition. The learning output information in this case is, for example, a change instruction after an instruction satisfying the first condition, and is information including a set of change instructions up to immediately before the instruction satisfying the second condition. That is, the learning input information in such a case is information regarding the operation history.

  The learning unit 132 receives one or more attribute values of one or more other components that satisfy a predetermined condition for the changed component corresponding to the change instruction when the change instruction receiving unit 121 receives the change instruction. It is also preferable to obtain the learning input information or the learning output information.

  For example, the learning unit 132 acquires one or more input attribute values and one or more output attribute values in response to the change instruction received by the change instruction receiving unit 121. Then, the learning unit 132 configures learning information having one or more input attribute values as input, and outputs one or more output attribute values, and accumulates them in the learning information storage unit 112. An input attribute value is information applied to learning information when using learning information. The output attribute value is information that is desired to be obtained using the learning information. That is, one or more input attribute values are an example of learning input information. One or more output attribute values are examples of learning output information.

  One or more input attribute values and one or more output attribute values are usually two or more operations, and are a set of component attribute values changed by a series of coherent operations. One or more input attribute values are a set of component attribute values changed by the first half of a series of operations. One or more output attribute values are a set of component attribute values changed by an operation in the second half of a series of coherent operations. There are various ways to cut the first half and the second half. The first half operation is one change instruction, and the second half operation is preferably an operation other than the first half operation. The one or more input attribute values and the one or more output attribute values are a set of component attribute values corresponding to a set of two or more change instructions. The one or more input attribute values are, for example, one or more attribute values of the part corresponding to the change instruction. The one or more input attribute values are, for example, one or more attribute values of a part corresponding to a predetermined change instruction and one of other parts that satisfy a predetermined condition for the part corresponding to the change instruction. These are the attribute values. The one or more output attribute values are, for example, a change instruction subsequent to a predetermined change instruction, and correspond to one or more change instructions between the change instructions immediately before the next predetermined change instruction. One or more attribute values of one or more parts.

  Note that the learning unit 132 recognizes a series of coherent operations when, for example, a predetermined change instruction or operation is accepted. The predetermined change instruction or operation is, for example, a configuration change instruction or a current page change operation.

  In addition, the learning unit 132, for example, changes one or more attribute values of two or more parts corresponding to all change instructions from when the learning device 1 is activated until the processing of the learning device 1 is completed, You may accumulate | store in order of the received change instruction. Then, for example, the learning unit 132 randomly divides a set of all change instructions into the first half and the second half of the operation, sets one or more attribute values corresponding to the change instructions in the first half as input attribute values, and sets the change instructions in the second half. The learning information may be acquired by performing the learning process two or more times using the corresponding one or more attribute values as output attribute values.

  It is preferable that the learning unit 132 learns editing work on the content set using machine learning algorithms such as deep learning and decision trees, and accumulates the learning information in the learning information storage unit 112. For deep learning, it is preferable to use RNN, but CNN or the like may be used. Further, since deep learning and machine learning such as a decision tree are known techniques, detailed description thereof is omitted.

  The learning unit 132 includes one or more attribute values after changing the part corresponding to one or more consecutive change instructions, and one or more consecutive change instructions for other parts after the one or more consecutive change instructions. It is preferable to learn one or more changed attribute values corresponding to, configure learning information, and accumulate the learning information in the learning information storage unit 112. The other parts are one or more parts different from the parts corresponding to the change instruction. The learning unit 132 may also learn one or more attribute values before the change in addition to the one or more attribute values after the change. Further, learning one or more attribute values after the change may be learning a change amount of the attribute value.

  In other words, the learning unit 132 receives one or more attribute values after changing the parts corresponding to one or more consecutive change instructions as inputs, and one or more consecutive values for other parts after the one or more consecutive change instructions. It is preferable to acquire learning information that outputs one or more attribute values after the change corresponding to each change instruction to be performed and accumulate the learning information in the learning information storage unit 112. Note that setting the output to one or more attribute values after the change may be a change instruction for the output.

  The learning unit 132 also learns one or more attribute values of one or more other components that satisfy a predetermined condition for the component corresponding to the change instruction when the change instruction receiving unit 121 receives the change instruction. It is preferable to configure learning information and accumulate the learning information in the learning information storage unit 112. Note that one or more other parts that satisfy a predetermined condition are, for example, parts that exist in the same page as the page on which the part corresponding to the change instruction exists, and are operated after one or more change instructions. It is a part. The operated part is, for example, one of an added part, a deleted part, and a part whose attribute value has been changed.

  In other words, the learning unit 132 determines one or more attribute values after the change of the part corresponding to each of the one or more continuous change instructions and a condition predetermined for the part corresponding to each of the one or more continuous change instructions. One or more attribute values (attribute values before change) of one or more other parts satisfying the condition are input and correspond to one or more consecutive change instructions for other parts after one or more consecutive change instructions. It is preferable to acquire learning information that outputs one or more attribute values after the change and store the learning information in the learning information storage unit 112. Note that setting the output to one or more attribute values after the change may be a change instruction for the output.

  For example, the learning unit 132 learns an instruction to change the attribute value of another component until the next component is added or deleted after the component is added or deleted.

  The output unit 14 outputs various information. The various information is, for example, a content set. The output unit 14 outputs a part or all of the read content set, for example.

  Here, the output is usually a display on a display, but projection using a projector, printing with a printer, sound output, transmission to an external device, accumulation in a recording medium, other processing devices and others This is a concept that includes delivery of processing results to other programs.

  The content set output unit 141 outputs part or all of the content set. The content set output unit 141 outputs a part or all of the content set before accepting the change instruction. The content set output unit 141 outputs a part or all of the content set changed by the manual change unit 131.

  The storage unit 11, the content set storage unit 111, and the learning information storage unit 112 are preferably non-volatile recording media, but can also be realized by volatile recording media.

  The process in which information is stored in the storage unit 11 or the like is not limited. For example, information may be stored in the storage unit 11 or the like via a recording medium, information transmitted via a communication line or the like may be stored in the storage unit 11 or the like, Alternatively, information input via the input device may be stored in the storage unit 11 or the like.

  The processing unit 13, the manual change unit 131, and the learning unit 132 can be usually realized by an MPU, a memory, or the like. The processing procedure of the processing unit 13 is usually realized by software, and the software is recorded in a recording medium such as a ROM. However, it may be realized by hardware (dedicated circuit).

  The output unit 14 and the content set output unit 141 may be considered as including or not including an output device such as a display or a speaker. The output unit 14 can be realized by output device driver software, or output device driver software and an output device.

  Next, an operation example of the learning apparatus 1 will be described using the flowchart of FIG.

  (Step S201) The receiving unit 12 determines whether or not an instruction to output a content set has been received. If an output instruction is accepted, the process goes to step S202. If an output instruction is not accepted, the process goes to step S203.

  (Step S202) The processing unit 13 reads a content set corresponding to the output instruction from the content set storage unit 111. Then, the content set output unit 141 outputs the content set. The process returns to step S201.

  (Step S203) The change instruction receiving unit 121 determines whether a content set change instruction output by the content set output unit 141 has been received. If a change instruction is accepted, the process goes to step S204. If a change instruction is not accepted, the process returns to step S201.

  (Step S <b> 204) The learning unit 132 acquires one or more attribute values before the change of the changed component and accumulates at least temporarily in the storage unit 11. The changed part is a part corresponding to the change instruction.

  (Step S <b> 205) The learning unit 132 acquires one or more attribute values of peripheral components and accumulates at least temporarily in the storage unit 11. The peripheral parts are parts that satisfy a predetermined condition for the changed part. The peripheral parts are, for example, parts around the changed part. The peripheral parts are other parts arranged on the same page as the changed parts, for example.

  (Step S206) The manual change unit 131 changes the content set according to the change instruction received in step S203.

  (Step S207) The learning unit 132 acquires one or more attribute values after the change of the changed component, and at least temporarily accumulates them in the storage unit 11. Further, the learning unit 132 may acquire one or more attribute values of other parts after the change instead of or in addition to the one or more attribute values after the change of the changed part. The process returns to step S201.

  Note that the learning unit 132 associates one or more attribute values before the change of the changed component, one or more attribute values of the peripheral component, and one or more attribute values after the change with the storage unit 11 at least temporarily. To accumulate. Further, the learning unit 132 may store at least temporarily in the storage unit 11 in association with one or more attribute values of the peripheral component and one or more attribute values after the change of the changed component.

  (Step S208) The learning unit 132 determines whether to perform learning. If it is determined that learning is to be performed, the process proceeds to step S209. If it is determined that learning is not to be performed, the process returns to step S201. For example, when the instruction received immediately before is a configuration change instruction and the configuration of the content set is changed, the learning unit 132 determines to perform learning.

  (Step S209) The learning unit 132 acquires one or more input attribute values stored in the storage unit 11. The one or more input attribute values are, for example, one or more attribute values of one or more parts included in the content set before the configuration change instruction immediately before the configuration change instruction received immediately before is received. is there. It is preferable that one or more parts include peripheral parts.

  (Step S210) The learning unit 132 acquires one or more output attribute values stored in the storage unit 11. The one or more output attribute values are, for example, one or more attribute values of one or more parts included in the content set immediately before the configuration change instruction received immediately before is received.

  (Step S211) When the learning unit 132 receives one or more input attribute values acquired in step S209 as input, the learning unit 132 performs a learning process that increases the probability that the one or more output attribute values acquired in step S210 will be output. . The process returns to step S201. For the learning process, it is preferable to use a machine learning algorithm such as deep learning or decision tree. New learning information is constructed by learning using a machine learning algorithm. The learning process is a process of accumulating correspondence information composed of a set of one or more input attribute values and one or more output attribute values as information constituting the learning information.

  In the flowchart of FIG. 2, the learning input information includes the attribute values of one or more parts of the content set immediately before the processing corresponding to the predetermined change instruction (may be referred to as the processing before the predetermined processing). The learning process is performed by using the attribute value of one or more parts of the content set immediately before the processing corresponding to the predetermined instruction (which may be referred to as after processing) as learning output information, and acquiring the learning information. However, learning information may be acquired by learning a change instruction history for the content set (may be referred to as an operation history).

  In the flowchart of FIG. 2, the process is ended by power-off or a process end interrupt.

  Hereinafter, a specific operation of the learning device 1 in the present embodiment will be described. Now, the storage unit 11 stores a temporary management table having the structure shown in FIG. The temporary management table is a table that temporarily stores information for configuring learning information. The temporary management table may store one or more records having “ID”, “learning input information”, and “learning output information”. “ID” is information for identifying a record. The “learning input information” includes “changed part information”, “result information”, and “peripheral part information”. Here, the “changed part information” includes a change instruction and information for specifying the changed part. “Result information” is information related to the result of the component change. “Result information” here is an attribute value of a part (here, a page) after a change by a change instruction. “Peripheral component information” is information on peripheral components. Here, the learning output information includes information for specifying a change instruction and a changed part.

  In addition, an electronic merchandise catalog including the page shown in FIG. 4 is stored in the content set storage unit 111. The electronic product catalog is a catalog in which a plurality of product information is posted.

In this situation, the following three specific examples will be described. Specific Example 1 is a case where one piece of product information is deleted from the electronic product catalog. Specific example 2 is a case where the design within one page of the electronic merchandise catalog is changed. Specific example 3 is a case where product information is added to an electronic product catalog.
(Specific example 1)

  In the specific example 1, it is assumed that information including one or more pieces of information corresponding to one configuration change instruction or two or more consecutive configuration change instructions in one page is used as learning input information. In the first specific example, one or more instructions after one configuration change instruction or two or more consecutive configuration change instructions, and one or more until the current page moves or the processing of the learning apparatus 1 stops. It is assumed that one or more pieces of information corresponding to the instruction are used as learning output information.

  In specific example 1, it is assumed that learning processing is performed using a set of learning input information and learning output information, and learning information is configured.

  Now, it is assumed that the user has input an instruction to output an electronic merchandise catalog to the learning device 1. Then, the reception unit 12 receives an output instruction, and the output unit 14 outputs the electronic merchandise catalog shown in FIG.

  Next, it is assumed that the user inputs a deletion instruction for deleting the image 2 and the explanatory note 2 in 401 in FIG. 4 to the output electronic merchandise catalog in FIG. 4. Then, the change instruction receiving unit 121 receives these two deletion instructions. The two deletion instructions are “Delete image 2” and “Delete description 2”.

  Next, the learning unit 132 accumulates “deleted image 2” and “deleted description 2” in the storage unit 11.

  Next, the manual change unit 131 deletes the two contents (image 2 and description 2) from the electronic merchandise catalog in FIG. 4 in accordance with the received two deletion instructions.

Next, the learning unit 132 acquires one or more attribute values after the change. Here, the learning unit 132 obtains information on the empty space ((x ₁ , y ₁ ) (x ₂ , y ₂ )) in the page, which is an attribute value of the page on which the changed part exists. Then, the learning unit 132 accumulates “empty space ((x ₁ , y ₁ ) (x ₂ , y ₂ ))” in the storage unit 11. The empty space information is a broken-line rectangle 500 in FIG.

Then, the changed part information including “deleted image 2” and “deleted description 2” and the result information including “empty space ((x ₁ , y ₁ ) (x ₂ , y ₂ ))” are learned input information. Configure.

  Next, it is assumed that the user inputs an attribute value change instruction to move the description 3 of 501 and the image 3 of 502 to the top of the page in the output electronic merchandise catalog of FIG. Further, it is assumed that the user inputs an attribute value change instruction for moving the image 4 of 503 and the explanatory text 3 of 504 upward to the output electronic merchandise catalog of FIG.

  Next, the change instruction receiving unit 121 receives the attribute value change instruction. Then, in response to the attribute value change instruction, the manual change unit 131 arranges the product information 3 including the explanatory text 3 and the image 3 and the product information 4 including the image 4 and the explanatory text 3 evenly around the center of the page. , And.

Next, the learning unit 132 includes the information “movement image 3 (x ₃ , y ₃ )”, “movement explanation 3 (x ₄ , y ₄ )”, and “movement image 4 (x ₅ , y ₅ )” regarding movement of the image 3. “Move explanation 4 (x ₆ , y ₆ )” is stored in the storage unit 11.

  Next, the manual change unit 131 changes the position of the component such as the image 3 in accordance with the accepted attribute value change instruction.

  Next, it is assumed that the user has input an attribute value change instruction for enlarging the sizes of the images 3 and 4 to 1.1 times and an attribute value change instruction for enlarging the font size of the explanatory sentence 3 and the explanatory sentence 4. .

  Next, the change instruction receiving unit 121 receives the attribute value change instruction. Then, it is assumed that the manual change unit 131 enlarges the sizes of the images 3 and 4 by 1.1 times and enlarges the font sizes of the explanatory sentence 3 and the explanatory sentence 4 in accordance with the attribute value change instruction. The page output after such processing is shown in FIG.

  Next, the learning unit 132 sets “magnified image 3 1.1 times”, “magnified image 4 1.1 times”, “font enlargement explanation 3”, “font enlargement explanation 4”, etc. Is stored in the storage unit 11.

  Further, it is assumed that the user has input a configuration change instruction for adding an orange line to the empty space 601 in FIG.

  Next, the change instruction receiving unit 121 receives the configuration change instruction. In response to the configuration change instruction, the manual change unit 131 adds an orange line to the area 601. Note that the attribute value of this line is the same as the attribute value of the line 602.

  Then, the learning unit 132 acquires one or more attribute values of peripheral components and accumulates at least temporarily in the storage unit 11. Here, it is assumed that one or more attribute values of a part (line part) of the same type as the added part are acquired, which are parts arranged on the same page as the added part. That is, here, the learning unit 132 acquires the attribute value “LINE1 (color = orange, thickness = X, length = Y, type = solid line,...)” Of the line 601 and stores it in the storage unit 11. accumulate. The attribute value of the line 601 is peripheral component information constituting the input attribute information.

  Further, the learning unit 132 outputs the output attribute information “addition LINE2 (color = orange, thickness = X, length = Y, type = solid line,...)” According to the addition of the orange line. Acquired and accumulated in the storage unit 11.

  Next, according to the received change instruction, the manual change unit 131 adds a line 702 as shown in FIG.

  It is assumed that the user has finished editing this page and has input an instruction to move the current page to the next page.

  Then, the learning unit 132 determines to perform learning. Here, the condition for determining to perform learning is that a predetermined instruction such as pressing the next page button is accepted.

  Next, the learning unit 132 acquires input attribute information stored in the storage unit 11. In addition, the learning unit 132 acquires output attribute information stored in the storage unit 11. This set of information is a record of “ID = 1” in FIG.

  Next, when the acquired input attribute information is input, the learning unit 132 performs a learning process that increases the probability that the acquired output attribute information is output using, for example, a deep learning algorithm. Then, the learning unit 132 constructs new learning information and accumulates the learning information in the learning information storage unit 112.

  As described above, in specific example 1, it was possible to learn the changing process of other components accompanying the operation of deleting one or more contents. It should be noted that it is preferable to perform a large number of learnings of changing processes of other components in accordance with the content deletion operation.

  In Specific Example 1, the learning unit 132 uses, for example, information including attribute values of one or more parts in the page of the screen in FIG. 5 as learning input information, and uses one or more in the page of the screen in FIG. Learning information may be acquired by performing learning processing using information including attribute values of each component as learning output information.

In Specific Example 1, the learning unit 132 uses, as learning input information, information including attribute values of one or more parts that satisfy a predetermined condition in the page of the screen in FIG. Learning information may be acquired by performing learning processing using information including attribute values of one or more parts satisfying a predetermined condition in the page of the screen as learning output information.
(Specific example 2)

  In specific example 2, it is assumed that one or more pieces of information corresponding to the first change instruction after moving to one page are used as learning input information. In specific example 2, one or more instructions after one change instruction or two or more consecutive change instructions, corresponding to one or more instructions until the current page moves or the processing of learning device 1 stops It is assumed that one or more pieces of information to be learned output information. Then, it is assumed that learning processing is performed by using a set of learning input information and learning output information, and learning information is configured.

  Now, it is assumed that the user has input an instruction to output an electronic merchandise catalog to the learning device 1. Then, the reception unit 12 receives an output instruction, and the output unit 14 outputs the electronic merchandise catalog shown in FIG.

  Next, it is assumed that the user inputs an attribute value change instruction for changing the color of the line 701 in FIG. 7 from orange to green in the output electronic merchandise catalog in FIG. Then, the change instruction receiving unit 121 receives the attribute value change instruction. The attribute value change instruction is “change LINE1 (original color = orange, new color = green)”.

  Next, the learning unit 132 accumulates “change LINE 1 (original color = orange, new color = green)” in the storage unit 11. Such information is changed part information.

  Next, the learning unit 132 is a component arranged on the same page as the changed component (LINE1), and one or more attribute values (for example, “color = orange”) of the peripheral component (LIN2) that is the same type of component. ) And is stored at least temporarily in the storage unit 11. Such information is peripheral part information.

  Further, the learning unit 132 is a component arranged on the same page as the changed component (LINE1), and has an attribute value (for example, “1” or more) of the peripheral component (BOX1) that is a component overlapping the changed component (LINE1). Background color = skin color ") and is stored in the storage unit 11 at least temporarily. Such information is peripheral part information.

  Next, the manual change unit 131 changes the color of the line 701 from orange to green according to the received change instruction.

  Next, it is assumed that the user inputs an attribute value change instruction for changing the color of the line 702 in FIG. 7 from orange to green in the output electronic merchandise catalog in FIG. Then, the change instruction receiving unit 121 receives the attribute value change instruction. The attribute value change instruction is “change LINE2 (color = green)”. Then, the change instruction receiving unit 121 receives the attribute value change instruction. The attribute value change instruction is “change LINE2 (color = green)”.

  Next, the learning unit 132 accumulates “change LINE2 (color = green)” in the storage unit 11. Such information is learning output information.

  Next, the manual change unit 131 changes the color of the line 702 from orange to green according to the received change instruction.

  Next, it is assumed that the user inputs an attribute value change instruction for changing the background color of the box 703 in FIG. 7 from skin color to yellow with respect to the output electronic merchandise catalog in FIG. Then, the change instruction receiving unit 121 receives the attribute value change instruction. The attribute value change instruction is “change BOX (background color = yellow)”.

  Next, the learning unit 132 accumulates one “change BOX (background color = yellow)” in the storage unit 11. Such information is learning output information.

  Next, the manual change unit 131 changes the background color of the BOX 703 from skin color to yellow according to the received change instruction. An example of such output is shown in FIG.

  By the above operation, it is assumed that the user has finished editing this page and has input an instruction to move the current page to the next page.

  Then, the learning unit 132 determines to perform learning. Here, it is assumed that the learning unit 132 uses the reception of a predetermined instruction such as an instruction to move the page as a learning start trigger.

  Next, the learning unit 132 acquires learning input information of “ID = 2” in the temporary management table. In addition, the learning unit 132 acquires learning output information of “ID = 2” in the temporary management table.

  Next, when the acquired learning input information is input, the learning unit 132 performs a learning process that increases the probability that the acquired learning output information is output using, for example, a deep learning algorithm. Then, the learning unit 132 constructs new learning information and accumulates the learning information in the learning information storage unit 112.

  As described above, in specific example 2, it was possible to learn the changing process of other parts accompanying the changing operation of the attribute value of one or more parts. In addition, it is preferable to perform many learnings of changing processes of other parts accompanying the changing operation of the attribute value of such parts.

  In Specific Example 2, the learning unit 132 uses, for example, information including attribute values of one or more parts in the page of the screen in FIG. 7 as learning input information, and uses one or more in the page of the screen in FIG. Learning information may be acquired by performing learning processing using information including attribute values of each component as learning output information.

Moreover, in the specific example 2, the learning unit 132 uses, for example, information including attribute values of one or more parts satisfying a predetermined condition in the page of the screen of FIG. 7 as learning input information, and the screen of FIG. Learning information may be obtained by performing learning processing using information including attribute values of one or more parts satisfying a predetermined condition in the page as learning output information.
(Specific example 3)

  In Specific Example 3, the storage unit 11 stores a temporary management table having the structure shown in FIG. The temporary management table is a table that temporarily stores information for configuring learning information. The temporary management table may store one or more records having “ID”, “learning input information”, and “learning output information”. The “input attribute information” includes “changed part information” and “peripheral part information”.

  In Specific Example 3, the content is added to one page. In the third specific example, it is assumed that the changed component information when the configuration change instruction (here, the content addition instruction) is received and the peripheral component information when the configuration change instruction is received are the learning input information. In the third specific example, it is assumed that one or more instructions after the configuration change instruction and one or more information corresponding to the instruction until the work is completed (the learning device 1 is stopped) are used as the learning output information. Then, it is assumed that learning processing is performed by using a set of learning input information and learning output information, and learning information is configured.

  Now, it is assumed that the user has input an instruction to output an electronic merchandise catalog to the learning device 1. Then, the receiving unit 12 receives an output instruction, and the output unit 14 outputs the electronic merchandise catalog shown in FIG. In the electronic merchandise catalog of FIG. 10, merchandise information of two buses is arranged on the left half of the page.

  In such a situation, it is assumed that the user inputs an additional instruction to add the product information of the chair to the learning device 1. Then, the change instruction receiving unit 121 receives a configuration change instruction for adding chair product information. The configuration change instruction is “additional product information 3 (product type = chair,...)”.

  Next, the learning unit 132 stores “additional product information 3 (product type = chair,...)” In the temporary management table. Such information is changed part information.

  Next, the learning unit 132 acquires one or more attribute values of peripheral components and accumulates at least temporarily in the temporary management table. That is, one or more attribute values of product information 1 (1001 in FIG. 10) and product information 2 (1002 in FIG. 10) arranged on the same page as the additional component are acquired. One or more attribute values of the product information 1 are “product information 1 (product type = bus,...)”. One or more attribute values of the product information 2 are “product information 2 (product type = bus,...)”. Such information is peripheral part information.

  Next, the manual change part 131 adds the merchandise information 3 to the electronic merchandise catalog of FIG. 10 according to the accepted addition instruction. An example of such output is shown in FIG. In FIG. 11, 1101 is product information 3, which is arranged at the upper right of the screen according to the user's configuration change instruction.

  Next, since the product information of the chair has been arranged on the product information page of the bus, the user inputs a configuration change instruction “generation page” in order to generate a new page. Then, the change instruction receiving unit 121 receives a configuration change instruction “generation page”. Then, the learning unit 132 acquires the ID “page 2” of the new page. Then, the learning unit 132 acquires the output attribute information “generation page 2” from the configuration change instruction “generation page”. Then, the learning unit 132 stores “generation page 2” as output attribute information in the temporary management table.

  Next, the manual change unit 131 generates a new page 2 according to the configuration change instruction.

  Next, it is assumed that the user inputs an attribute change instruction “move product information 3 (page 2)” to move the product information 3 on page 1 to page 2. Then, the change instruction receiving unit 121 receives an attribute change instruction “moving product information 3 (page 2)”.

  Then, the learning unit 132 accumulates the attribute change instruction as output attribute information at least temporarily in the storage unit 11.

  Next, the manual change unit 131 moves the product information 3 to the page 2 in accordance with the attribute change instruction. An example of such output is shown in FIG. FIG. 12 is page 2. The current page 1 is shown in FIG.

  Next, it is assumed that a stop instruction is input to the learning device 1. Then, the reception unit 12 receives a stop instruction.

  Next, the learning unit 132 acquires learning input information of “ID = 3” in the temporary management table. In addition, the learning unit 132 acquires learning output information of “ID = 3” in the temporary management table.

  Next, when the acquired learning input information is input, the learning unit 132 performs a learning process that increases the probability that the acquired learning output information is output using, for example, a deep learning algorithm. Then, the learning unit 132 constructs new learning information and accumulates the learning information in the learning information storage unit 112.

  As described above, in the specific example 3, when new content is added, it has been possible to learn the process of preventing different types of products from existing on the same page. It should be noted that it is preferable to perform a large number of parts change processing learnings associated with such content addition operations.

  In Specific Example 3, the learning unit 132 uses, for example, information including attribute values of one or more parts in the page of the screen of FIG. 10 or FIG. 11 as learning input information, and the screens of FIG. 12 and FIG. Learning information may be acquired by performing learning processing using information including attribute values of one or more parts in the page as learning output information.

  In the third specific example, the learning unit 132 uses, as learning input information, information including attribute values of one or more parts that satisfy a predetermined condition in the page of the screen of FIG. 10 or FIG. The learning information may be acquired by performing learning processing using information including attribute values of one or more parts satisfying a predetermined condition in the page of the screen of FIG. 12 and FIG. 10 as learning output information.

  As described above, according to the present embodiment, it is possible to learn advanced editing work when creating a content set such as an electronic catalog or an electronic book.

  Note that the processing in the present embodiment may be realized by software. Then, this software may be distributed by software download or the like. Further, this software may be recorded and distributed on a recording medium such as a CD-ROM. This also applies to other embodiments in this specification. An example of software that implements the learning device 1 according to the present embodiment is the following program. In other words, this program automatically changes the content set, a content set storage unit storing a content set having two or more parts including a content having one or more attribute values, and a computer-accessible recording medium. A learning information storage unit that stores learning information used to perform the operation, and a computer outputs a content set output unit that outputs part or all of the content set, and the content set output unit outputs A change instruction receiving unit that receives a change instruction for a content set, a manual change unit that changes and outputs the content set output by the content set output unit according to the change instruction, and one or more continuous change instructions Obtain change instruction information, which is information related to a series of change instructions, learn the change instruction information, Constitute a program for functioning as a learning section for storing the learning information in the learning information storage unit.

  (Embodiment 2)

  In the present embodiment, an editing device 2 that performs automatic editing using learning information learned by the learning device 1 of the first embodiment will be described.

  FIG. 13 is a conceptual diagram of the editing system A in the present embodiment. The editing system A includes an editing device 2, one, or two or more terminal devices 3. The editing device 2 is a server device that performs editing processing using learning information. The editing device 2 is, for example, a so-called cloud server, ASP server, or the like, but the type thereof is not limited. The terminal device 3 is a device used by a user who performs editing work. The terminal device 3 is, for example, a so-called personal computer, tablet terminal, smart phone, or the like, and the type thereof is not limited. Note that the editing apparatus 2 may operate stand-alone.

  FIG. 14 is a block diagram of the editing system A in the present embodiment.

  The editing device 2 includes a storage unit 11, a reception unit 12, a processing unit 23, and an output unit 14. The storage unit 11 includes a content set storage unit 111 and a learning information storage unit 112. The receiving unit 12 includes a change instruction receiving unit 121. The processing unit 23 includes a manual change unit 131 and an automatic change unit 232. The automatic change unit 232 includes, for example, a changed part attribute value acquisition unit 2321, a peripheral part attribute value acquisition unit 2322, a learning output information acquisition unit 2323, and an automatic change unit 2324. The output unit 14 includes a content set output unit 141.

  The terminal device 3 includes a terminal storage unit 31, a terminal reception unit 32, a terminal processing unit 33, a terminal reception unit 34, a terminal transmission unit 35, and a terminal output unit 36.

  The processing unit 23 configuring the editing apparatus 2 performs various processes. The various processes are processes performed by the manual change unit 131 and the automatic change unit 232, for example.

  The automatic changing unit 232 acquires learning input information according to one or more change instructions, applies the learning input information to the learning information in the learning information storage unit 112, acquires learning output information, and acquires learning output information. To change the content set. Note that the change of the content set includes a change of attribute values of other parts, addition or deletion of other parts, and the like. Note that the processing of the automatic change unit 232 is preferably performed by using learning information using a machine learning algorithm such as deep learning or decision tree.

  For example, the automatic changing unit 232 acquires one or more attribute values after changing one or more parts in response to one or more change instructions, applies the one or more attribute values to the learning information, and changes the content set. .

  The automatic change unit 232 acquires, for example, input attribute information that is one or more attribute values after changing one or more parts in response to one or more change instructions, applies the input attribute information to learning information, and outputs output attributes. Information is acquired, and the content set is changed using the output attribute information.

  The changed part attribute value acquisition unit 2321 acquires one or more attribute values after the change of the parts included in the content set changed by the manual change unit 131. Note that the changed component attribute value acquisition unit 2321 may also acquire one or more attribute values before the change.

  The peripheral part attribute value acquisition unit 2322 acquires one or more attribute values of one or more other parts that satisfy a predetermined condition for the parts included in the content set changed by the manual change unit 131. Here, the one or more other parts satisfying the predetermined condition are, for example, other parts in the same page, parts having the same attribute value as the changed parts, and the like.

  The learning output information acquisition unit 2323 has one or more attribute values acquired by the changed component attribute value acquisition unit 2321 and one or more attribute values of one or more other components acquired by the peripheral component attribute value acquisition unit 2322. The input information is applied to the learning information, and learning output information including one or more attribute values for other parts different from the parts is acquired. The learning output information acquisition unit 2323 may acquire information for generating another new component. The learning output information acquisition unit 2323 may acquire information for specifying a component to be deleted.

  The automatic change unit 2324 changes the attribute value of another component using the learning output information acquired by the learning output information acquisition unit 2323.

  The output unit 14 performs the same function as the output unit 14.

  Various types of information are stored in the terminal storage unit 31 constituting the terminal device 3.

  The terminal reception unit 32 receives various information and instructions. The various information and instructions are, for example, a start instruction, a configuration change instruction, an attribute value change instruction, and the like. The input means for various information and instructions may be anything such as a touch panel, a keyboard, a mouse, or a menu screen. The terminal reception unit 32 can be realized by a device driver for input means such as a touch panel and a keyboard, control software for a menu screen, and the like.

  The terminal processing unit 33 performs various processes. The various processes are processes for changing to information or instructions having a structure for transmitting received information or instructions.

  The terminal receiving unit 34 receives various types of information. The various information is, for example, a content set.

  The terminal transmission unit 35 transmits various information, instructions, and the like to the editing device 2. Various information, instructions, and the like are a start instruction, a configuration change instruction, an attribute value change instruction, and the like.

  The terminal output unit 36 outputs various types of information. The various information is, for example, a content set.

  The processing unit 23, manual change unit 131, automatic change unit 232, changed component attribute value acquisition unit 2321, peripheral component attribute value acquisition unit 2322, learning output information acquisition unit 2323, automatic change unit 2324, and terminal processing unit 33 are usually It can be realized from an MPU or a memory. The processing procedure of the processing unit 23 and the like is usually realized by software, and the software is recorded on a recording medium such as a ROM. However, it may be realized by hardware (dedicated circuit).

  The terminal storage unit 31 is preferably a non-volatile recording medium, but can also be realized by a volatile recording medium.

  The process in which information is stored in the terminal storage unit 31 does not matter. For example, information may be stored in the terminal storage unit 31 via a recording medium, information transmitted via a communication line or the like may be stored in the terminal storage unit 31, Alternatively, information input via the input device may be stored in the terminal storage unit 31.

  The terminal receiving unit 34 is usually realized by a wireless or wired communication means, but may be realized by a means for receiving a broadcast.

  The terminal transmission unit 35 is usually realized by wireless or wired communication means, but may be realized by broadcasting means.

  The terminal output unit 36 may be considered as including or not including an output device such as a display or a speaker. The terminal output unit 36 may be implemented by output device driver software, or output device driver software and an output device.

  Next, the operation of the editing system A will be described. First, the operation of the editing apparatus 2 will be described using the flowchart of FIG.

  (Step S1501) The accepting unit 12 determines whether an instruction has been accepted. If an instruction is accepted, the process goes to step S1502, and if no instruction is accepted, the process returns to step S1501.

  (Step S1502) The processing unit 23 determines whether or not the instruction received in step S1501 is an output instruction. If it is an output instruction, the process goes to step S1503, and if it is not an output instruction, the process goes to step S1504.

  (Step S1503) The processing unit 23 reads the content set corresponding to the output instruction from the content set storage unit 111 and outputs it. The output here is usually transmission to the terminal device 3. The process returns to step S1501.

  (Step S1504) The processing unit 23 determines whether or not the instruction received in step S1501 is a change instruction. If it is a change instruction, the process goes to step S1505. If it is not a change instruction, the process goes to step S1506.

  (Step S1505) The manual change unit 131 changes the content set being output in accordance with the received change instruction. Go to step S1510.

  (Step S1506) The automatic changing unit 232 determines whether or not the conditions for using the learning information are met. If it is determined that the condition is met, the process goes to step S1507. If it is determined that the condition is not met, the process returns to step S1501. Here, the conditions for using the learning information are that the received instruction is a predetermined change instruction, and that the output page satisfies a predetermined condition (for example, in advance A blank space that is greater than or equal to a predetermined threshold value or larger than the threshold value).

  (Step S1507) The automatic change unit 232 acquires learning input information. Note that the learning input information is, for example, an attribute value of one or more parts of the current content set. The learning input information is, for example, the immediately preceding change instruction and one or more attribute values of the changed part.

  (Step S1508) The automatic change unit 232 applies the learning input information acquired in Step S1507 to the learning information in the learning information storage unit 112, and acquires learning output information. Such a process is preferably a process using a machine learning algorithm such as deep learning.

  (Step S1509) The automatic change unit 232 automatically changes the content set using the learning output information acquired in step S1508.

  (Step S1510) The content set output unit 141 outputs the changed content set. The process returns to step S1501. The output here is normally transmission to the terminal device 3.

  Note that the processing is ended by powering off or interruption for aborting the processing in the flowchart in FIG.

  Hereinafter, a specific operation of the editing apparatus 2 in the present embodiment will be described. The editing device 2 is assumed to have the learning information configured in the first embodiment stored in the learning information storage unit 112.

  Then, it is assumed that the user is inputting an operation for editing the content set to the terminal device 3 that can communicate with the editing device 2.

  For example, when the user inputs a deletion instruction to delete a part in the page of the output content set, the manual change unit 131 of the editing device 2 deletes the part according to the deletion instruction. . Then, the automatic changing unit 232 acquires learning input information, applies the learning input information to the learning information, and acquires learning output information by a machine learning algorithm such as deep learning. Note that this learning output information includes information for moving the position of other peripheral parts (for example, position information for specifying the position of the peripheral parts, or Information indicating the movement distance). Then, the automatic change unit 232 changes the position of the component in the content set using the learning output information. With this change, other peripheral parts move so as to fill the empty space created by deleting the parts. Such an example is a case where an operation like the first specific example of the first embodiment is learned and the constructed learning information is used.

  Further, for example, when the user inputs an attribute value change instruction to change the color of a certain part in the page of the output content set, the manual change unit 131 of the editing device 2 follows the deletion instruction according to the deletion instruction. Change the color of the part to the specified color. Then, the automatic changing unit 232 acquires learning input information, applies the learning input information to the learning information, and acquires learning output information by a machine learning algorithm such as deep learning. The learning output information includes information for changing the color of the other peripheral parts to a color that matches the color of the one part so that the design is not inappropriate due to the change of the color of the one part ( For example, information specifying the color of the peripheral part or information indicating the amount of change in the color of the peripheral part). Then, the automatic change unit 232 changes the color of the peripheral component in the content set using the learning output information. This change is to make the design of the whole page appropriate by automatically changing the color of the other peripheral parts on the page where the overall design becomes inappropriate by changing the color of one part. . This example is a case where an operation like the specific example 2 of the first embodiment is learned and the constructed learning information is used.

  Further, for example, when the user inputs an addition instruction to add a part in the page of the content set that is being output, the manual change unit 131 of the editing device 2 adds the part according to the addition instruction. . Then, the automatic changing unit 232 acquires learning input information, applies the learning input information to the learning information, and acquires learning output information by a machine learning algorithm such as deep learning. This learning output information is information for teaching a new page and moving the added component to that page. Next, the automatic changing unit 232 generates a new page using the learning output information, and moves the component added to the page. By such a change, only the same kind of information exists on one page, and a content set such as a catalog that is easy for the user to view can be efficiently created. Such an example is a case where an operation like the specific example 3 of the first embodiment is learned and the constructed learning information is used.

  As described above, according to the present embodiment, it is possible to use a result of more appropriately learning advanced editing work when creating a content set such as an electronic catalog or an electronic book.

  An example of software that realizes the editing apparatus 2 in the present embodiment is the following program. That is, the program includes a content set storage unit in which a recording medium accessible by a computer stores a content set having two or more parts including content having one or more attribute values; A learning information storage unit that stores learning information learned by the learning device according to any one of claims 1 to 3, and a computer that outputs a content set output unit that outputs a part or all of the content set; and the content set A change instruction receiving unit that receives one or more change instructions for the content set output by the output unit, and a manual that changes and outputs the content set output by the content set output unit according to the one or more change instructions The learning input information is acquired in response to the changing unit and the one or more change instructions, and the learning input information is converted into the learning information. And use, acquires learning output information, by using the learning output information, a program for functioning as an automatic changer for changing the content set.

  (Embodiment 3)

  In the present embodiment, an editing apparatus 4 that learns while editing in accordance with a user instruction will be described.

  FIG. 16 is a block diagram of the editing device 4 in the present embodiment. The editing device 4 includes a storage unit 11, a reception unit 12, a processing unit 43, and an output unit 14.

  The processing unit 43 includes a manual change unit 131, an automatic change unit 232, and a learning unit 132.

  The learning unit 132 constituting the processing unit 43 acquires change instruction information that is information regarding a series of change instructions that are one or more continuous change instructions, learns change instruction information, configures learning information, and learns information. Are stored in the learning information storage unit 112.

  Next, the operation of the editing apparatus 4 will be described using the flowchart of FIG. The flowchart of FIG. 17 is a flowchart in which the flowchart of FIG. 15 and a part of the flowchart of FIG. 2 are combined. Therefore, the description of the flowchart of FIG. 17 is omitted. In the flowchart of FIG. 17, the user proceeds with learning while editing the content set, and learning information grows.

  As described above, according to the present embodiment, the user can learn the operation of the user while editing the content set using the editing device 4.

  An example of software that implements the editing apparatus 4 in the present embodiment is the following program. That is, the program includes a content set storage unit in which a recording medium accessible by a computer stores a content set having two or more parts including content having one or more attribute values; A learning information storage unit that stores learning information learned by the learning device according to any one of claims 1 to 3, and a computer that outputs a content set output unit that outputs a part or all of the content set; and the content set A change instruction receiving unit that receives one or more change instructions for the content set output by the output unit, and a manual that changes and outputs the content set output by the content set output unit according to the one or more change instructions The learning input information is acquired in response to the changing unit and the one or more change instructions, and the learning input information is converted into the learning information. The learning output information is acquired, and using the learning output information, an automatic change unit that changes the content set and change instruction information that is information regarding a series of change instructions that are one or more continuous change instructions It is a program for acquiring, learning the change instruction information, configuring learning information, and causing the learning information to function as a learning unit that accumulates in the learning information storage unit.

  FIG. 18 shows the external appearance of a computer that executes the programs described in this specification to realize the learning apparatus and the like of the various embodiments described above. The above-described embodiments can be realized by computer hardware and a computer program executed thereon. FIG. 18 is a schematic view of the computer system 300, and FIG. 19 is a block diagram of the system 300.

  In FIG. 18, a computer system 300 includes a computer 301 including a CD-ROM drive, a keyboard 302, a mouse 303, and a monitor 304.

  In FIG. 19, in addition to the CD-ROM drive 3012, the computer 301 stores an MPU 3013, a bus 3014 connected to the CD-ROM drive 3012, a ROM 3015 for storing programs such as a bootup program, and the MPU 3013. It includes a RAM 3016 for temporarily storing application program instructions and providing a temporary storage space, and a hard disk 3017 for storing application programs, system programs, and data. Although not shown here, the computer 301 may further include a network card that provides connection to a LAN.

  A program that causes the computer system 300 to execute the functions of the learning device or the like of the above-described embodiment may be stored in the CD-ROM 3101, inserted into the CD-ROM drive 3012, and further transferred to the hard disk 3017. Alternatively, the program may be transmitted to the computer 301 via a network (not shown) and stored in the hard disk 3017. The program is loaded into the RAM 3016 at the time of execution. The program may be loaded directly from the CD-ROM 3101 or the network.

  The program does not necessarily include an operating system (OS) or a third-party program that causes the computer 301 to execute the functions of the learning device according to the above-described embodiment. The program only needs to include an instruction portion that calls an appropriate function (module) in a controlled manner and obtains a desired result. How the computer system 300 operates is well known and will not be described in detail.

  In the above program, in the step of transmitting information, the step of receiving information, etc., processing performed by hardware, for example, processing performed by a modem or an interface card in the transmission step (only performed by hardware) Processing) is not included.

  Further, the computer that executes the program may be singular or plural. That is, centralized processing may be performed, or distributed processing may be performed.

  Further, in each of the above embodiments, it goes without saying that two or more communication units existing in one apparatus may be physically realized by one medium.

  In each of the above embodiments, each process may be realized by centralized processing by a single device, or may be realized by distributed processing by a plurality of devices.

  The present invention is not limited to the above-described embodiments, and various modifications are possible, and it goes without saying that these are also included in the scope of the present invention.

  As described above, the learning device according to the present invention has an effect of learning advanced editing work when creating a content set such as an electronic catalog or an electronic book, and is useful as a learning device or the like.

DESCRIPTION OF SYMBOLS 1 Learning apparatus 2, 4 Editing apparatus 3 Terminal apparatus 11 Storage part 12 Reception part 13, 23, 43 Processing part 14 Output part 31 Terminal storage part 32 Terminal reception part 33 Terminal processing part 34 Terminal reception part 35 Terminal transmission part 36 Terminal output Unit 111 content set storage unit 112 learning information storage unit 121 change instruction reception unit 131 manual change unit 132 learning unit 141 content set output unit 232 automatic change unit 2321 changed component attribute value acquisition unit 2322 peripheral component attribute value acquisition unit 2323 learning output information Acquisition means 2324 Automatic change means

Claims (18)

A content set storage unit that stores a content set having two or more parts including content having one or more attribute values;
A learning information storage unit that stores learning information used to automatically change the attribute value of a component included in the content set;
A content set output unit for outputting a part or all of the content set;
A change instruction accepting unit for accepting a change instruction of the content set output by the content set output unit;
In accordance with the change instruction, a manual change unit that changes and outputs the content set output by the content set output unit;
Obtain change instruction information, which is information relating to a series of change instructions that are one or more continuous change instructions, learn the change instruction information, configure learning information, and store the learning information in the learning information storage unit A learning device comprising a learning unit. The learning apparatus according to claim 1, wherein the change instruction information includes learning input information applied to the learning information and learning output information expected as a result of application to the learning information. The learning input information is input attribute information that is a set of attribute values of one or more parts before change,
The learning device according to claim 2, wherein the learning output information is output attribute information that is a set of attribute values of one or more parts after the change. The learning input information is first change instruction information having a change instruction and one or more attribute values of a change part corresponding to the change instruction,
3. The learning output information is second change instruction information having one or more attribute values of change parts corresponding to one or more change instructions received after the change instruction included in the first change instruction information. The learning device described. The learning unit
In response to detecting an instruction that satisfies a predetermined first condition, the acquisition of the learning input information is determined, the learning input information is acquired in accordance with the determination, and a predetermined second condition is satisfied. The learning apparatus according to claim 2, wherein acquisition of the learning output information is determined in response to detection of an instruction, and learning output information is acquired in response to the determination. The learning apparatus according to any one of claims 1 to 5, wherein the change instruction received by the change instruction receiving unit is a configuration change instruction for changing a configuration of the content set. The learning apparatus according to claim 6, wherein the configuration change instruction is an addition instruction that is an instruction to add content or a deletion instruction that is an instruction to delete content. The learning apparatus according to any one of claims 1 to 5, wherein the change instruction received by the change instruction receiving unit is an attribute value change instruction for changing an attribute value of a component. The learning unit
When the change instruction accepting unit accepts a change instruction, learning input information or learning also includes one or more attribute values of one or more other parts that satisfy a predetermined condition for the part corresponding to the change instruction. The editing apparatus according to any one of claims 2 to 5, which is acquired as output information. The predetermined condition is:
The learning apparatus according to claim 9, wherein the learning apparatus is arranged on the same page as a page on which a part corresponding to the change instruction is arranged. The learning apparatus according to any one of claims 1 to 10, wherein the content set includes two or more pages. A content set storage unit that stores a content set having two or more parts including content having one or more attribute values;
A learning information storage unit in which learning information learned by the learning device according to claim 1 is stored;
A content set output unit for outputting a part or all of the content set;
A change instruction receiving unit for receiving one or more change instructions for the content set output by the content set output unit;
A manual change unit that changes and outputs the content set output by the content set output unit in accordance with the one or more change instructions;
Automatic learning that acquires learning input information according to the one or more change instructions, applies the learning input information to the learning information, acquires learning output information, and changes the content set using the learning output information An editing device comprising a changing unit. The automatic change unit
Changed part attribute value acquisition means for acquiring one or more attribute values after changing the parts of the content set changed by the manual change unit;
Peripheral part attribute value acquisition means for acquiring one or more attribute values of one or more other parts that satisfy a predetermined condition for the parts of the content set changed by the manual change unit;
Learning input information having one or more attribute values acquired by the changed component attribute value acquisition unit and one or more attribute values of one or more other components acquired by the peripheral component attribute value acquisition unit is applied to the learning information. Learning output information acquisition means for acquiring learning output information including one or more attribute values for another component different from the component;
The editing apparatus according to claim 12, further comprising: an automatic change unit that changes an attribute value of the other component using the learning output information acquired by the learning output information acquisition unit. Obtain change instruction information, which is information relating to a series of change instructions that are one or more continuous change instructions, learn the change instruction information, configure learning information, and store the learning information in the learning information storage unit 14. The editing apparatus according to claim 12, further comprising a learning unit. And one or more content sets storage unit content set having two or more parts, including content having attribute values are stored, stores the learning information learned information used to automatically change the contents set is stored and parts, and the content set output section, the change instruction receiving unit, a learning method that is implemented with manual change unit, by a learning section,
A content set output step in which the content set output unit outputs part or all of the content set;
A change instruction accepting step in which the change instruction accepting part accepts a change instruction of the content set output in the content set output step;
A manual change step in which the manual change unit changes and outputs the output content set according to the change instruction;
The learning unit acquires change instruction information that is information relating to a series of change instructions that are one or more continuous change instructions, learns the change instruction information, configures learning information, and converts the learning information into the learning information A learning method comprising: a learning step for accumulating in a storage unit. A content set storage unit storing a content set having two or more parts including content having one or more attribute values, and learning information learned by the learning device according to any one of claims 1 to 11. a learning information storage unit to be stored, a content set output section, the change instruction receiving unit, a editing method is implemented and a manual change unit, by the automatic change unit,
A content set output step in which the content set output unit outputs part or all of the content set;
A change instruction receiving step in which the change instruction receiving unit receives one or more change instructions for the content set being output;
A manual change step in which the manual change unit changes and outputs the output content set according to the one or more change instructions;
The automatic change unit acquires learning input information in response to the one or more change instructions, applies the learning input information to the learning information, acquires learning output information, and uses the learning output information, An editing method comprising: an automatic change step for changing a content set. And one or more content sets storage unit content set having two or more parts, including content having attribute values are stored, stores the learning information learned information used to automatically change the contents set is stored A computer that is accessible to
A content set output unit for outputting a part or all of the content set;
A change instruction accepting unit for accepting a change instruction of the content set output by the content set output unit;
In accordance with the change instruction, a manual change unit that changes and outputs the content set output by the content set output unit;
Obtain change instruction information, which is information relating to a series of change instructions that are one or more continuous change instructions, learn the change instruction information, configure learning information, and store the learning information in the learning information storage unit Program to function as a learning unit. A content set storage unit storing a content set having two or more parts including content having one or more attribute values, and learning information learned by the learning device according to any one of claims 1 to 11. A computer accessible to the stored learning information storage unit,
A content set output unit for outputting a part or all of the content set;
A change instruction receiving unit for receiving one or more change instructions for the content set output by the content set output unit;
A manual change unit that changes and outputs the content set output by the content set output unit in accordance with the one or more change instructions;
Automatic learning that acquires learning input information according to the one or more change instructions, applies the learning input information to the learning information, acquires learning output information, and changes the content set using the learning output information Program to function as a change part.