Information processing device

Abstract

An information processing device having: a selection unit for abstracting a plurality of inputs on the basis of an input of a number, and selecting a shared concept, which is an abstract concept shared by the plurality of inputs; and a generation unit for generating output data that includes the shared concept, on the basis of the result of the selection by the selection unit.

Description

[Technical Field]

[0001] The present invention relates to an information processing device, an information processing method, and a recording medium. [Background technology]

[0002] 2. Description of the Related Art Devices that generate sentences based on sentences are known.

[0003] For example, Patent Document 1 describes a data generation device that converts text in a starting domain into text in a target domain. According to Patent Document 1, the data generation device includes a text acquisition unit, a text replacement unit, and a text output unit. The text acquisition unit acquires text in the starting domain and target domain information indicating the target domain. The text replacement unit calculates probability information regarding the occurrence probability of a word candidate at a word position in the text of the starting domain by inputting the acquired text in the starting domain and the target domain information to a trained model generated by performing machine learning based on the text in the target domain for machine learning and the target domain information. The text replacement unit then generates a replacement text in which the word at the word position is replaced with the word candidate at the word position based on the calculated probability information. The text output unit then outputs the generated replacement text as text in the target domain. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Publication No. 2020-112915 Summary of the Invention [Problem to be solved by the invention]

[0005] In the case of the technology described in Patent Document 1, one sentence is replaced with another sentence from a different domain, which causes a problem that it is difficult to generate output data such as a sentence corresponding to multiple inputs, for example, multiple sentences.

[0006] SUMMARY OF THE INVENTION It is therefore an object of the present invention to provide an information processing device, an information processing method, and a recording medium that solve the problem of the difficulty in generating output data in response to a plurality of inputs. [Means for solving the problem]

[0007] In order to achieve this object, an information processing device according to one embodiment of the present disclosure comprises: a selection unit that abstracts the plurality of inputs based on the plurality of inputs and selects a common concept that is an abstract concept common to the plurality of inputs; a generation unit that generates output data including the common concept based on a result of the selection by the selection unit; have The structure is as follows.

[0008] Furthermore, an information processing method according to another aspect of the present disclosure includes: The information processing device Abstracting the multiple inputs based on the multiple inputs and selecting a common concept that is an abstract concept common to the multiple inputs; Generate output data including the common concept based on the selection results. The structure is as follows.

[0009] Furthermore, a recording medium according to another aspect of the present disclosure includes: In the information processing device, Abstracting the multiple inputs based on the multiple inputs and selecting a common concept that is an abstract concept common to the multiple inputs; Generate output data including the common concept based on the selection results. It is a computer-readable recording medium that records a program for implementing the processing. [Effects of the Invention]

[0010] According to the above-described configurations, it is possible to provide an information processing device, an information processing method, and a program that are capable of generating output data in response to a plurality of inputs. [Brief explanation of the drawings]

[0011] [Figure 1] 1 is a diagram illustrating an example of a sentence generation device according to a first embodiment of the present disclosure. [Figure 2] FIG. 1 is a block diagram showing an example of the configuration of a sentence generation device. [Figure 3] FIG. 10 is a diagram for explaining a conceptual example of the level of abstraction. [Figure 4] FIG. 10 is a diagram for explaining the level of abstraction. [Figure 5] FIG. 10 is a diagram illustrating an example of processing when an input sentence is broken down into words. [Figure 6] FIG. 10 is a diagram illustrating an example of a word cloud sentence. [Figure 7] FIG. 10 is a diagram illustrating an example of a process for selecting a common concept. [Figure 8] FIG. 10 is a diagram illustrating an example of the operation of the sentence generation device. [Figure 9] FIG. 10 is a block diagram showing an example of the configuration of a search device, which is another example of the configuration of the sentence generation device. [Figure 10] FIG. 10 is a diagram illustrating an example of a hardware configuration of an information processing device according to a second embodiment of the present disclosure. [Figure 11] FIG. 1 is a block diagram illustrating an example of the configuration of an information processing device. DETAILED DESCRIPTION OF THE INVENTION

[0012] [First embodiment] A first embodiment of the present disclosure will be described with reference to FIGS. 1 to 8. FIG. 1 is a diagram illustrating an example of a sentence generation device 100. FIG. 2 is a block diagram illustrating an example of the configuration of the sentence generation device 100. FIGS. 3 and 4 are diagrams for explaining the level of abstraction. FIG. 5 is a diagram illustrating an example of processing when breaking down an input sentence into words. FIG. 6 is a diagram illustrating an example of a word cloud sentence. FIG. 7 is a diagram illustrating an example of processing for selecting a common concept. FIG. 8 is a diagram illustrating an example of the operation of the sentence generation device. FIG. 9 is a block diagram illustrating an example of the configuration of a search device 160.

[0013] As shown in FIG. 1, in the first embodiment of the present disclosure, a description will be given of a sentence generation device 100, which is an information processing device that generates sentences in response to multiple input sentences. As will be described later, the sentence generation device 100 receives input of multiple sentences and information indicating a target of interest. Then, the sentence generation device 100 acquires multiple words by, for example, breaking down the sentences into words. The sentence generation device 100 also generates a word cloud sentence by acquiring words with higher and lower abstraction levels than the acquired words. Thereafter, the sentence generation device 100 generates a sentence that focuses on the target of interest based on the generated word cloud sentence.

[0014] Fig. 2 shows an example of the configuration of the sentence generation device 100. Referring to Fig. 2, the sentence generation device 100 has, as main components, for example, an operation input unit 110, a screen display unit 120, a communication I / F unit 130, a storage unit 140, and an arithmetic processing unit 150.

[0015] The operation input unit 110 is made up of operation input devices such as a keyboard, a mouse, etc. The operation input unit 1110 detects operations by the user of the text generation device 100 and outputs the operations to the arithmetic processing unit 150.

[0016] The screen display unit 120 is composed of a screen display device such as an LCD (Liquid Crystal Display). The screen display unit 120 can display various information stored in the storage unit 140 on the screen in response to instructions from the arithmetic processing unit 150.

[0017] The communication I / F unit 130 is made up of a data communication circuit and performs data communication with an external device.

[0018] The storage unit 140 is a storage device such as a hard disk or memory. The storage unit 140 stores processing information and a program 146 required for various processes in the arithmetic processing unit 150. The program 146 is read into the arithmetic processing unit 150 and executed to realize various processing units. The program 146 is read in advance from an external device or recording medium via a data input / output function such as the communication I / F unit 130, and is stored in the storage unit 140. Main information stored in the storage unit 140 includes, for example, concept information 141, sentence information 142, attention target information 143, word cloud sentence information 144, generated sentence information 145, etc.

[0019] The concept information 141 is information indicating the relationship or connection between words, groups of words, etc. For example, the concept information 141 includes information indicating the connection between words or words generated by connecting a word with words that are more abstract or less abstract than the word (or words that are more abstract or less abstract). The concept information 141 may also include information indicating the connection between words and words associated with the word or words that are more abstract or less abstract than the word. For example, the concept information 141 is acquired in advance from an external device or the like via the communication I / F unit 130 and stored in the storage unit 140.

[0020] Here, the degree of abstraction is a concept whose value increases as the number of connected words, which indicates the number of words or phrases connected to a word or phrase, increases, as shown in FIG. 3, for example. For example, assume that there is concept information 141, as shown in FIG. 4, in which the word "automobile" is connected to "automobile manufacturer," "people carrier," "man-made object," etc., and the word "automobile manufacturer" is connected to "Ford," "Toyota," etc. In this case ("automobile manufacturer" connected to "Ford," "Toyota," etc.), the word "automobile" connected to "people carrier," "man-made object," etc. has the largest number of connected words among the above words. Therefore, in the case of concept information 141 such as the one above, the word "automobile" is the word with the highest degree of abstraction.

[0021] The level of abstraction may be a value other than that according to the number of connected words, for example, a value that is predetermined for each word or phrase.

[0022] The text information 142 indicates a text that is input to the text generation device 100 and that will be the basis for a text to be generated. For example, the text information 142 is updated when the receiving unit 151 receives input of a text from an external device via the communication I / F unit 130 or when the receiving unit 151 receives input of a text in response to an operation of the operation input unit 110. For example, the text information 142 includes a plurality of sentences that have been input to the text generation device 100.

[0023] The attention target information 143 indicates a word or phrase to be the attention target when generating a new sentence. The attention target indicated by the attention target information 143 is, for example, any one of the words or phrases in the sentence included in the sentence information 142. The attention target may be, for example, a word or phrase of a different level of abstraction that is connected to a word in the sentence included in the sentence information 142. The attention target information 143 is updated, for example, when the reception unit 151 receives information indicating the attention target from an external device via the communication I / F unit 130 or when the reception unit 151 receives information indicating the attention target in response to an operation of the operation input unit 110.

[0024] The word cloud text information 144 is information that associates each word acquired by decomposing a sentence included in the text information 142 with words, groups of words, numerical information, etc. that have different levels of abstraction from the acquired words. The word cloud text information 144 is updated, for example, as a result of processing performed by the word abstraction unit 153 based on the result of decomposition of the sentence by the decomposition unit 152 and the concept information 141.

[0025] Generated text information 145 is information indicating a text generated by generation unit 155 based on a text included in text information 142. Generated text information 145 is updated when generation unit 155 generates a text.

[0026] The arithmetic processing unit 150 has an arithmetic device such as a CPU and its peripheral circuits. The arithmetic processing unit 150 reads and executes the program 146 from the storage unit 140, thereby causing the above hardware and the program 146 to work together to realize various processing units. Major processing units realized by the arithmetic processing unit 150 include, for example, a reception unit 151, a decomposition unit 152, a word abstraction unit 153, a common concept selection unit 154, a generation unit 155, and an output unit 156.

[0027] The reception unit 151 receives information indicating a text or an object of attention. For example, the reception unit 151 receives information indicating a text or an object of attention from an external device via the communication I / F unit 130 or in response to an operation of the operation input unit 110. The reception unit 151 then stores the received text in the storage unit 140 as text information 142. The reception unit 151 also stores the received information indicating the object of attention in the storage unit 140 as object of attention information 143.

[0028] The decomposition unit 152 decomposes a sentence included in the text information 142 to obtain words included in the sentence. The timing at which the decomposition unit 152 decomposes a sentence may be arbitrary. For example, the decomposition unit 152 may decompose a sentence when new sentence is stored in the text information 142, or may decompose a sentence included in the text information 142 when the generation unit 155 attempts to generate a new sentence.

[0029] For example, the decomposition unit 152 performs natural language processing such as morphological analysis on a sentence to decompose the sentence into individual words. FIG. 5 shows a specific example of processing by the decomposition unit 152. Referring to FIG. 5, for example, the sentence information 142 includes two sentences: "Aristotle ate an apple and turned red" and "Socrates ate an apple and turned red." In this case, the decomposition unit 152 performs morphological analysis on each of the sentences to decompose the sentence "Aristotle ate an apple and turned red" into the words "Aristotle," "is," "apple," "to," "eat," "turned red," "became." Similarly, the decomposition unit 152 decomposes the sentence "Socrates ate an apple and turned red" into the words "Socrates," "is," "apple," "to," "eat," "turned red," "became."

[0030] For example, as described above, the decomposing unit 152 performs natural language processing on the sentence to acquire words contained in the sentence.

[0031] The word abstraction unit 153 generates a word cloud sentence from the words by performing word abstraction, etc. Then, the word abstraction unit 153 stores the generated word cloud sentence in the storage unit 140 as word cloud sentence information 144.

[0032] Specifically, for example, the word abstraction unit 153 refers to the concept information 141 to acquire words with higher and lower abstraction levels than each word acquired as a result of processing by the decomposition unit 152 (or groups of words with different abstraction levels or associated words, etc.). Then, the word abstraction unit 153 generates a word cloud sentence in which a word is associated with words with higher and lower abstraction levels than the word (for example, written as abstract concepts).

[0033] FIG. 6 shows an example of a word cloud sentence generated by the word abstraction unit 153. Specifically, FIG. 6 shows an example of processing by the word abstraction unit 153 when the decomposition unit 152 acquires the words "Aristotle," "is," "apple," "eat," "become," "red," "become," and the words "Socrates," "is," "apple," "eat," "become," "red," "become." Referring to FIG. 6, for example, the word abstraction unit 153 refers to the concept information 141 to acquire words such as "Aristotle" and "Socrates," and words or phrases connected to the words in the concept information 141, such as "person," "historical figure," "philosopher," "ancient Greece," etc. Then, the word abstraction unit 153 associates words such as "Aristotle" and "Socrates" with "person," "historical figure," "philosopher," "ancient Greece," etc. Similarly, for example, the word abstraction unit 153 associates the word "apple" with "tree," "plant," "fruit," "red," "sweet," "food," "spring," "pigment," "enzyme," etc., by referring to the concept information 141. The word abstraction unit 153 also associates the word "eat" with "chew," "swallow," "make a living," "live," "fruit," "take in," etc. The word abstraction unit 153 also associates the word "red" with "passion," "pigment," "wavelength," "vermilion," "tomato," etc. For example, the word abstraction unit 153 generates a word cloud sentence by associating words with abstract concepts as described above. Note that the abstract concepts may include numerical information that quantifies heat, color, sound, scent, etc.

[0034] The common concept selection unit 154 selects an abstract concept common to each word by, for example, referring to the word cloud sentence information 144. For example, the common concept selection unit 154 selects an abstract concept common to the word of interest and other words by referring to the word cloud sentence information 144.

[0035] Specifically, referring to FIG. 7, in the case of the word cloud sentence illustrated in FIG. 6, the abstract concept corresponding to the word "apple" includes "fruit," and the abstract concept corresponding to the word "eat" includes "fruit." Also, the abstract concept corresponding to the word "apple" includes "pigment," and the abstract concept corresponding to the word "red" includes "pigment." In other words, abstract concepts such as "pigment," "fruit," ..., etc. are common. Therefore, the common concept selection unit 154 selects "pigment," "fruit," ..., etc. as common abstract concepts.

[0036] The generation unit 155 generates a new sentence using the common concept selected by the common concept selection unit 154 and the target of attention indicated by the target of attention information 143. It is assumed that the generation unit 155 has preset forms of sentences to be generated, such as "xx contains yy" or "aa acts on bb." The generation unit 155 generates a new sentence with the target of attention indicated by the target of attention information 143 as the subject so that the sentence has the preset form. The generation unit 155 may be configured to select the form of the sentence to be generated depending on the target of attention, etc.

[0037] For example, the generation unit 155 abstracts and consolidates parts of multiple sentences included in the text information 142 that are different words but can be considered to have the same or similar concepts. For example, Aristotle and Socrates share the terms "person," "historical figure," "philosopher," etc. Therefore, the generation unit 155 consolidates Aristotle and Socrates as "person," "historical figure," "philosopher," etc.

[0038] The generation unit 155 then generates new sentences by rearranging words common to each sentence and selected abstract concepts so that the sentences take a predetermined form, with the target of interest, "apple," as the subject. At this time, the generation unit 155 may delete words corresponding to the subject, such as verbs. For example, in the example described in this embodiment, the subject would be changed from "person" to "apple." Therefore, the generation unit 155 can delete the words "eat" and "hand." The generation unit 155 may also be configured to delete abstract concepts included in the deleted words. For example, in the example described in this embodiment, the generation unit 155 can delete words such as "fruit" included in "eat." When generating the new sentences, the generation unit 155 can supplement particles using known technology.

[0039] For example, as a result of the above processing, the generation unit 155 can newly generate a sentence such as "(An apple is) a person / historical figure / philosopher / ... that (contains) a pigment / fruit that turns red." Alternatively, the generation unit 155 may combine multiple parallel words to generate a single sentence such as "Apples contain a pigment that turns people red."

[0040] The generation unit 155 can determine whether multiple words are similar based on, for example, the overlap rate of abstract concepts (which may be any value). The generation unit 155 may also determine whether words are similar by a method other than the above-mentioned example method. Furthermore, when multiple common concepts exist, the generation unit 155 may be configured to select a common concept to adopt by any method.

[0041] The output unit 156 outputs the sentence generated by the generation unit 155. For example, the output unit 156 can display the sentence generated by the generation unit 155 (for example, "Apples contain a pigment that turns people red") on the screen display unit 120 or transmit it to an external device.

[0042] The above is an example of the configuration of the sentence generation device 100. Next, an example of the operation of the sentence generation device 100 will be described with reference to FIG.

[0043] Fig. 8 shows an example of the operation of the sentence generation device 100. Referring to Fig. 8, the decomposing unit 152 decomposes a sentence included in the sentence information 142 to obtain words included in the sentence (step S101).

[0044] The word abstraction unit 153 generates a word cloud sentence from words by performing word abstraction or the like (step S102). For example, the word abstraction unit 153 refers to the concept information 141 to acquire, for each word acquired as a result of processing by the decomposition unit 152, words with a higher or lower level of abstraction than the word (or a group of words with different levels of abstraction or associated words, etc.). In this way, the word abstraction unit 153 generates a word cloud sentence in which a word is associated with words with a higher or lower level of abstraction than the word (for example, expressed as abstract concepts).

[0045] The common concept selection unit 154 selects an abstract concept common to each word by referring to the word cloud sentence information 144. For example, the common concept selection unit 154 selects an abstract concept common to the word of interest and other words by referring to the word cloud sentence information 144 (step S103).

[0046] The generation unit 155 generates a new sentence using the common concept selected by the common concept selection unit 154 and the target of attention indicated by the target of attention information 143 (step S104). For example, the generation unit 155 abstracts and consolidates parts of multiple sentences included in the sentence information 142 that are different words but can be considered to have the same or similar level of abstraction or concept. Then, the generation unit 155 generates a new sentence by rearranging the words common to each sentence and the selected abstract concept so that the sentence takes on a predetermined form, with "apple" as the target of attention as the subject.

[0047] The output unit 156 outputs the sentence generated by the generation unit 155 (step S105).

[0048] As described above, the sentence generation device 100 has the word abstraction unit 153, the common concept selection unit 154, and the generation unit 155. With this configuration, the generation unit 155 can generate a new sentence using the common concept selected by the common concept selection unit 154 from the results of abstraction by the word abstraction unit 153. As a result, it becomes possible to generate a sentence that corresponds to a plurality of sentences.

[0049] Furthermore, with the above configuration, the text is converted after matching abstracted words. By using this method, it is possible to generate text that reflects the idea of ​​abduction, for example.

[0050] In the present embodiment, the case where the functions of the sentence generation device 100 are realized by one information processing device has been exemplified. However, the functions of the sentence generation device 100 may be realized by a plurality of information processing devices connected via a network, for example, on a cloud.

[0051] Furthermore, in the present embodiment, the example has been given of the case where the writing generation device 100 has the conceptual information 141. However, the writing generation device 100 may be configured to utilize external information, such as an external dictionary site or encyclopedia site, in place of the conceptual information 141. When the writing generation device 100 is configured as described above, the writing generation device 100 does not need to have the conceptual information 141.

[0052] In addition, in this embodiment, a case has been described in which a sentence, which is output data, is generated in response to multiple sentence inputs. However, the sentence generation device 100 may be configured to generate a sentence in response to inputs other than sentences. For example, the sentence generation device 100 may be configured to accept multiple inputs, such as image data and sound data (or image data and sentences). In this case, the sentence generation device 100 can acquire words and the like from the image data by performing known image recognition processing. In other words, the sentence generation device 100 may have an image recognition unit, instead of or in addition to the decomposition unit 152, that acquires words, sentences, and the like corresponding to the image data based on the image data. The image recognition unit may be configured to directly acquire numerical information and the like as abstract concepts, together with or in place of words, sentences, and the like.

[0053] Furthermore, the generation unit 155 may be configured to generate output data other than sentences. In other words, the present invention may be applied to generation devices other than the sentence generation device 100 that generates sentences. For example, when an abstract concept includes numerical information that quantifies heat, color, sound, scent, etc., the numerical information may be included as a common concept. In such a case, the generation unit 155 may be configured to generate image data, sound data, etc. based on the numerical information. In this way, the generation unit 155 may be configured to generate output data other than sentences based on a common concept.

[0054] 9 shows the configuration of a search device 160, which is another example of the configuration of the sentence generation device 100. The search device 160 is an information processing device having the configuration of the sentence generation device 100. Furthermore, referring to FIG. 9, search information 147 is stored in the storage unit 140 of the search device 160.

[0055] The search information 147 includes information for a search performed by a search unit 157, which will be described later. The search information 147 can be generated by the generation unit 155 as output data and stored in the storage unit 140, for example.

[0056] For example, the search information 147 can include information used by the generation unit 155 when generating sentences, etc., and the generated sentences. For example, the search information 147 associates the original sentences used for generation and information corresponding to the original sentences with abstract concepts and common concepts included in the word cloud sentences. Specifically, for example, assume that multiple sentences related to Tsurugaoka Hachimangu Shrine are input, and the input sentences are abstracted to select a common concept. In this case, the search information 147 can be information that associates information indicating Tsurugaoka Hachimangu Shrine or the input sentences with the selected common concept, etc.

[0057] 9, the arithmetic processing unit 150 can have a search unit 157 in addition to the configuration described with reference to Fig. 2. In the configuration shown in Fig. 9, the generation unit 155 can generate search information 147 as output data and store it in the storage unit 140.

[0058] The search unit 157 searches the search information 147 based on the input search input information, etc. For example, multiple sentences about a specific field of a person (e.g., tourism) are input as the search information 147. Then, the search unit 157 extracts a common concept common to the multiple input sentences using the decomposition unit 152, the word abstraction unit 153, the common concept selection unit 154, etc. Then, the search unit 157 searches the search information 147 using the extracted common concept as a search key. For example, the search unit 157 can search for information from the search information 147 that includes all of the common concepts extracted based on the search input information (or that includes a predetermined number or a predetermined percentage or more). Note that, for example, an abstract concept corresponding to the common concept may be input as is as the search input information, or only one sentence may be input. When only one sentence is input, the search unit 157 can perform a search process using the abstract concept extracted using the decomposition unit 152 and the word abstraction unit 153.

[0059] [Second embodiment] Next, a second embodiment of the present disclosure will be described with reference to Fig. 10 and Fig. 11. In the second embodiment, an outline of the configuration of an information processing device 200 will be described.

[0060] Fig. 10 shows an example of the hardware configuration of the information processing device 200. Referring to Fig. 10, the information processing device 200 has, as an example, the following hardware configuration. ·CPU (Central Processing Unit) 201 (computing unit) ROM (Read Only Memory) 202 (storage device) RAM (Random Access Memory) 203 (storage device) Programs 204 loaded into RAM 203 A storage device 205 for storing the program group 204 A drive device 206 that reads and writes from a recording medium 210 outside the information processing device A communication interface 207 that connects to a communication network 211 outside the information processing device Input / output interface 208 for inputting and outputting data Bus 209 connecting each component

[0061] 11 by the CPU 201 acquiring and executing the program group 204. The program group 204 is stored in advance in the storage device 205 or the ROM 202, for example, and is loaded into the RAM 203 or the like by the CPU 201 for execution as needed. The program group 204 may be supplied to the CPU 201 via the communication network 211, or may be stored in advance in the recording medium 210, and the drive device 206 may read out the programs and supply them to the CPU 201.

[0062] 10 shows an example of the hardware configuration of the information processing device 200. The hardware configuration of the information processing device 200 is not limited to the above-described case. For example, the information processing device 200 may be configured with only a part of the above-described configuration, such as excluding the drive device 206.

[0063] The selection unit 221 abstracts a plurality of inputs based on the plurality of inputs, and also selects a common concept, which is an abstract concept common to the plurality of inputs, based on the abstraction result.

[0064] The generating unit 222 generates output data including a common concept based on the result of the selection by the selecting unit 221. For example, the generating unit 222 generates output data such as a sentence.

[0065] As described above, the information processing device 200 has the selection unit 221 and the generation unit 222. With this configuration, the generation unit 222 can generate new output data using the result of selection by the selection unit 223. As a result, it becomes possible to generate output data according to a plurality of inputs.

[0066] The information processing device 200 described above can be realized by incorporating a predetermined program into the information processing device 200. Specifically, a program according to another aspect of the present invention is a program for causing the information processing device 200 to perform a process of abstracting a plurality of inputs based on the plurality of inputs, selecting a common concept that is an abstract concept common to the plurality of inputs, and generating output data including the common concept based on the selection result.

[0067] Furthermore, the information processing method realized by the above-described information processing device 200 is a method in which the information processing device 200 abstracts multiple inputs based on the multiple inputs, selects a common concept that is an abstract concept common to the multiple inputs, and generates output data including the common concept based on the selection result.

[0068] Even if the invention is a program (or recording medium) or an information processing method having the above-mentioned configuration, it has the same functions and effects as the above-mentioned information processing device 200, and therefore can achieve the above-mentioned object of the present invention.

[0069] <Additional Notes> (Appendix 1) a selection unit that abstracts the plurality of inputs based on the plurality of inputs and selects a common concept that is an abstract concept common to the plurality of inputs; a generation unit that generates output data including the common concept based on a result of the selection by the selection unit; have Information processing device. (Appendix 2) a word acquisition unit that acquires a plurality of words based on a plurality of inputs; a word abstraction unit that performs an abstraction process of associating the words acquired by the word acquisition unit with abstract concepts that are words with different levels of abstraction from the words; and the selection unit selects a common concept common to a plurality of words based on a result of the processing by the word abstraction unit; the generation unit generates a sentence based on a result of the selection by the selection unit. 10. The information processing device according to claim 1. (Appendix 3) The generation unit generates a sentence based on a preset target of interest and a result of selection by the selection unit. 3. The information processing device according to claim 2. (Appendix 4) The selection unit selects a common concept common to the word or phrase to be focused on and other words. 4. The information processing device according to claim 3. (Appendix 5) The word abstraction unit performs the abstraction process, which is a process of generating a word cloud sentence in which words are associated with abstract concepts, which are words having different levels of abstraction from the words, by referring to concept information, which is information indicating connections between words and words. 10. The information processing device according to claim 9, wherein the information processing device is a device for processing a plurality of data. (Appendix 6) Abstraction indicates the number of words or phrases that connect to a word or phrase. The more connected words there are, the higher the value. An information processing device according to any one of Supplementary Note 2 to Supplementary Note 5. (Appendix 7) a receiving unit that receives input of a plurality of sentences as the plurality of inputs; The word acquisition unit acquires words by performing natural language processing on the input document. 10. The information processing device according to claim 9, wherein the information processing device is a device for processing a plurality of data. (Appendix 8) the generation unit generates search information including the extracted abstract concept as output data; The information processing device has a search unit that searches the search information using an abstract concept acquired based on input information. 8. The information processing device according to claim 1, (Appendix 9) The information processing device Abstracting the multiple inputs based on the multiple inputs and selecting a common concept that is an abstract concept common to the multiple inputs; Generate output data including the common concept based on the selection results. Information processing methods. (Appendix 10) In the information processing device, Abstracting the multiple inputs based on the multiple inputs and selecting a common concept that is an abstract concept common to the multiple inputs; Generate output data including the common concept based on the selection results. A program to realize the processing.

[0070] The programs described in the above embodiments and appendices may be stored in a storage device or a computer-readable recording medium, such as a portable medium such as a flexible disk, an optical disk, a magneto-optical disk, or a semiconductor memory.

[0071] Although the present invention has been described above with reference to the above-mentioned embodiments, the present invention is not limited to the above-mentioned embodiments. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present invention within the scope of the present invention.

[0072] In addition, the present invention claims the benefit of priority based on patent application No. 2021-029501, filed in Japan on February 26, 2021, and all contents of that patent application are incorporated herein by reference. [Explanation of symbols]

[0073] 100 Sentence generator 110 Operation input section 120 Screen display section 130 Communication I / F section 140 Storage section 141 Concept information 142 Text information 143 Featured Information 144 Word Cloud Text Information 145 Generated text information 146 Programs 147 Search Information 150 Processing unit 151 Reception 152 Disassembly section 153 Word Abstraction Department 154 Common Concept Selection Section 155 Generation part 156 Output section 157 Search Department 160 Search Device 200 Information processing device 201 CPU 202 ROM 203 RAM 204 Programs 205 Storage device 206 Drive unit 207 Communication Interface 208 Input / Output Interface 209 Bus 210 Recording Media 211 Communication Network 221 Selection Section 222 Generation part

Claims

1. a selection unit that abstracts the plurality of inputs based on the plurality of inputs and selects a common concept that is an abstract concept common to the plurality of inputs; a generation unit that generates output data including the common concept based on a result of the selection by the selection unit; and the generation unit generates a sentence with the word of interest as a subject based on a predetermined word of interest that is one of the words included in the input and a result of selection by the selection unit; The selection unit selects, from among a plurality of words acquired by decomposing a plurality of inputs, an abstract concept common to the word of interest, which is a word that will be a subject in a sentence to be generated, and another word different from the word of interest, as the common concept. Information processing device.

2. a word acquisition unit that acquires a plurality of words based on a plurality of inputs; a word abstraction unit that performs an abstraction process of associating the words acquired by the word acquisition unit with abstract concepts that are words with different levels of abstraction from the words; and the selection unit selects the common concept common to a plurality of words based on a result of the processing by the word abstraction unit; The generation unit generates a sentence based on the result of the selection by the selection unit. The information processing device according to claim 1 .

3. The word abstraction unit performs the abstraction process, which is a process of generating a word cloud sentence in which words are associated with abstract concepts, which are words having different levels of abstraction from the words, by referring to concept information, which is information indicating connections between words and words. The information processing device according to claim 2 .

4. Abstraction indicates the number of words or phrases that connect to a word or phrase. The more connected words there are, the higher the value. The information processing device according to claim 2 .

5. a receiving unit that receives input of a plurality of sentences as the plurality of inputs; The word acquisition unit acquires words by performing natural language processing on the input document. The information processing device according to claim 2 .

6. the generation unit generates search information including the extracted abstract concept as output data; The information processing device has a search unit that searches the search information using an abstract concept acquired based on input information. The information processing device according to any one of claims 1 to 5.

7. The information processing device Abstracting the multiple inputs based on the multiple inputs and selecting a common concept that is an abstract concept common to the multiple inputs; generating output data including the common concept based on the selection results; When generating the output data, a sentence is generated with the target word as a subject based on a predetermined target word that is one of the words included in the input and a result of the selection; When selecting the common concept, an abstract concept common to the word of interest, which is a subject word in a sentence to be generated, and other words different from the word of interest is selected as the common concept from among a plurality of words obtained by decomposing a plurality of inputs. Information processing methods.

8. In the information processing device, Abstracting the multiple inputs based on the multiple inputs and selecting a common concept that is an abstract concept common to the multiple inputs; Generate output data including the common concept based on the selection results. Realize the processing, When generating the output data, a sentence is generated with the target word as a subject based on a predetermined target word that is one of the words included in the input and a result of the selection; When selecting the common concept, an abstract concept common to the word of interest, which is a subject word in a sentence to be generated, and other words different from the word of interest is selected as the common concept from among a plurality of words obtained by decomposing a plurality of inputs. program.

Images