JP7381143B2 - Information processing device, information processing method, program and recording medium - Google Patents

Description

The present invention relates to an information processing device, an information processing method, a program, and a recording medium.

In recent years, deep learning using multilayer neural networks has been attracting attention as a machine learning method. Deep learning uses large amounts of training data to make a multilayer neural network learn features.

Patent Documents 1 to 3 disclose neural network processing devices that make it possible to construct a neural network with less effort and computational processing amount by defining a large-scale neural network as a combination of a plurality of sub-networks. ing. Further, Patent Document 4 discloses a structural optimization device that optimizes a neural network.

Japanese Patent Application Publication No. 2001-051968 Japanese Patent Application Publication No. 2002-251601 Japanese Patent Application Publication No. 2003-317073 Japanese Patent Application Publication No. 09-091263

There is a need for an information processing device whose purpose is to recognize external information and obtain a solution by itself. Application of deep learning technology to such information processing devices is also being considered. However, with conventional artificial information processing technology using deep learning etc., it is difficult to conceptualize information and add creativity, and efforts are being made to realize information processing technology that can process information using algorithms that are closer to human thinking. There is.

An object of the present invention is to provide an information processing device, an information processing method, a program, and a recording medium that can process information using an algorithm closer to human thinking.

According to one aspect of the present invention, an input unit generates, based on received information, first data representing a situation grasped from the information; and a concept related to the situation is generated based on the first data. a processing unit that generates second data representing the concept; and an output unit that generates and outputs words representing the concept based on the second data; There is provided an information processing device configured to output the generated words to the input unit as new information when the generated words do not match the solution according to the above.

According to another aspect of the present invention, a first step of generating first data representing a situation grasped from the information based on the received information; a second step of generating second data representing a concept related to a situation; and a third step of generating and outputting words representing the concept based on the second data, An information processing method is provided in which when the words generated in the third step do not match the solution according to the information, the generated words are used as new information and the steps are repeated from the first step.

According to still another aspect of the present invention, means for causing a computer to generate, based on received information, first data representing a situation grasped from the information; means for generating second data representing a concept related to a situation; generating words representing the concept based on the second data; when the generated words do not match a solution according to the information; A program is provided that functions as means for outputting the generated words as new information to the means for generating the first data.

According to the present invention, it is possible to realize an information processing device and an information processing method that can process information using an algorithm closer to human thinking.

FIG. 1 is a schematic diagram showing a configuration example of an information processing apparatus according to a first embodiment of the present invention. FIG. 2 is a schematic diagram showing a configuration example of a data processing module in the information processing apparatus according to the first embodiment of the present invention. FIG. 3 is a diagram illustrating the operation of the data processing module in the information processing apparatus according to the first embodiment of the present invention. FIG. 4 is a flowchart showing an information processing method using the information processing apparatus according to the first embodiment of the present invention. FIG. 5 is a sequence diagram showing a first application example of information processing using the information processing apparatus according to the first embodiment of the present invention. FIG. 6 is a diagram showing preconditions in a second application example of information processing using the information processing apparatus according to the first embodiment of the present invention. FIG. 7 is a sequence diagram showing a second application example of information processing using the information processing apparatus according to the first embodiment of the present invention. FIG. 8 is a schematic diagram (Part 1) showing an example of the hardware configuration of the information processing apparatus according to the first embodiment of the present invention. FIG. 9 is a schematic diagram (part 2) showing an example of the hardware configuration of the information processing apparatus according to the first embodiment of the present invention. FIG. 10 is a diagram illustrating a data processing processor in the information processing apparatus according to the first embodiment of the present invention. FIG. 11A is a diagram (part 1) illustrating the data processing processor in the information processing apparatus according to the first embodiment of the present invention. FIG. 11B is a diagram (part 2) illustrating the data processing processor in the information processing apparatus according to the first embodiment of the present invention. FIG. 11C is a diagram (Part 3) illustrating the data processing processor in the information processing device according to the first embodiment of the present invention. FIG. 12 is a schematic diagram showing a configuration example of an information processing device according to a second embodiment of the present invention.

[First embodiment]
An information processing apparatus according to a first embodiment of the present invention will be described using FIGS. 1 to 3. FIG. 1 is a schematic diagram showing a configuration example of an information processing apparatus according to this embodiment. FIG. 2 is a schematic diagram showing a configuration example of a data processing module in the information processing apparatus according to the present embodiment. FIG. 3 is a diagram illustrating the operation of the data processing module in the information processing apparatus according to this embodiment.

The information processing device 1000 according to this embodiment may include an input section 100, a processing section 200, and an output section 300, as shown in FIG.

The input unit 100 has a function of generating situation information data (first data) based on the received information. The situation information data is data obtained by converting the situation ascertained from the received information into data in a predetermined format. The format of the situation information data is not particularly limited, but for example, bitmap format data or vector representation format data can be applied.

The information received by the input unit 100 includes information received from outside the information processing device 1000 and information output by the output unit 300. The information that the input unit 100 receives from the outside is not particularly limited, but may include, for example, auditory information (words, sounds, etc.), visual information (images, etc.), tactile information (body sensation, temperature, texture, etc.). It will be done. For example, when voice input or text is input to the input unit 100 as external information, the input unit 100 can convert the input data into situation information data using a known word identification AI system or the like. Alternatively, when an image is input to the input unit 100 as external information, the input unit 100 can convert the input data into situation information data using a known image identification AI system or the like. The information that the input unit 100 receives from the output unit 300 is information regarding “words” (thoughts) generated by the output unit 300.

The processing unit 200 performs predetermined concept processing on the situation information data received from the input unit 100, and generates concept information data (second data) representing a concept related to the situation represented in the situation information data. , has a function of outputting the generated conceptual information data to the output unit 300. The processing unit 200 may include a recognition processing unit 210 and a concept processing unit 220.

The recognition processing unit 210 has a function of converting the situation information data received from the input unit 100 into conceptual information data (third data). The conceptual information data generated by the recognition processing unit 210 is data that conceptualizes the situation represented by the situation information data received from the input unit 100. The conceptual information data may be in the same format as the situational information data received from the input unit 100. Data of the same format is data that has the same data structure and size. However, the situation information data and the concept information data do not necessarily have to be in the same format, and may be in different formats as long as they overlap at least in part.

The recognition processing unit 210 performs conceptual processing such as identification and class classification on the situation information data received from the input unit 100 to generate conceptual information data. The recognition processing unit 210 may include multiple types of recognition modules depending on the type of situation information data. For example, the recognition processing unit 210 may include a word recognition module that processes situational information data received from a word identification AI system, an image recognition module that processes situational information data received from an image identification AI system, and the like. The classification performed by the recognition processing unit 210 may include, for example, classification of objects, requests, environments, etc. shown in the situation information data.

The concept processing unit 220 performs concept processing on the concept information data received from the recognition processing unit 210, and converts the concept information data received from the recognition processing unit 210 into conceptual information data (second data) of another concept. It has the function to The conceptual processing performed on the conceptual information data is a process of grasping the situation from the received conceptual information data, thinking about the grasped situation, and deriving the optimal solution for the grasped situation.

For example, a proof support system such as a Coq system can be applied to the concept processing unit 220. If the conceptual processing unit 220 does not have an answer (solution) (is incomplete), the output data is fed back to the input unit 100 via the output unit 300, which will be described later, so that the user can repeatedly ask himself questions and come up with a more appropriate answer. It becomes possible to obtain.

The output unit 300 has a function of generating “words” (thoughts) based on the solution (conceptual information data) output from the processing unit 200. "Words" are not particularly limited, but include, as an example, sentences that include at least a subject and a predicate, expressing an idea according to the conceptual information data output from the concept processing unit 220. The “words” generated by the output unit 300 can be output as text information or audio information, and can also be output to the input unit 100. The method of converting a concept into "words" is not particularly limited. A simple method includes, for example, a method of generating a sentence by inserting words extracted from a concept into a sentence of a fixed frame.

The output unit 300 may further include a function of generating “behavior” based on the solution (concept information data) output from the processing unit 200. In this case, the output unit 300 can be configured to output an instruction regarding the generated "behavior", for example. This instruction is not particularly limited, but may include, for example, a predetermined instruction to execute a task according to the generated "behavior", such as execution of an application.

Note that the conceptual information data that the output unit 300 receives may be the conceptual information data that the recognition processing unit 210 outputs, or the conceptual information data that the concept processing unit 220 outputs.

Next, the basic data processing modules that constitute the recognition processing section 210 and the concept processing section 220 will be explained using FIG. 2. FIG. 2 is a diagram showing a schematic configuration of a data processing module in the information processing apparatus according to this embodiment. Note that although an example of application to the recognition processing section 210 and the concept processing section 220 is shown here, a similar data processing module can also be applied to the input section 100 and the output section 300. Further, one functional block may include a plurality of data processing modules 400. For example, one functional block can be configured to use different data processing modules 400 depending on input data.

The data processing module 400 may include a data acquisition section 410, a storage section 420, an identification section 430, and a data output section 440, as shown in FIG.

The data acquisition unit 410 has a function of acquiring situation information data and conceptual information data. In one example, the situation information data and conceptual information data may be data in a bitmap format of a predetermined size, as described above.

The storage unit 420 stores learning models including a plurality of models. Each of the plurality of models is a pattern that represents specific information or a concept, and a value that represents another information or concept that corresponds to that pattern. For example, each model includes a pattern that maps relationships between multiple elements representing a specific situation or concept and their element values, and multiple elements representing other information or concepts that correspond to the specific situation or concept. and values mapping relationships with those element values.

The identification unit 430 compares the data pattern acquired by the data acquisition unit 410 with the patterns of each of the plurality of models stored in the storage unit 420, and selects the model having the highest fitness pattern among the plurality of models. Equipped with a function to select linked values. Similar to the relationship between situational information data and conceptual information data, the patterns and values that each of the plurality of models have may be data in the same format as the situational information data and conceptual information data, or data in a different format. It's okay. Note that the value linked to the pattern does not necessarily have to be data in a bitmap format, and may be data including predetermined index information. In this case, this index information can be used to acquire data corresponding to the index information from the outside.

The identification unit 430 may include a learning function of a learning model. For example, if there is no model whose fitness is equal to or higher than a predetermined threshold among the learning models, the configuration is such that a model corresponding to the data acquired by the data acquisition unit 410 is added to the learning model and the learning model is updated. can do. Note that, for example, the technology described in Japanese Patent Application No. 2019-144121 by the same applicant can be applied to construct and update the learning model.

The data output unit 440 has a function of outputting the value (data in bitmap format) selected by the identification unit 430 as output data. The data output unit 440 typically outputs the selected value to the next processing unit, but returns the selected value to the data acquisition unit 410 and performs recursive processing in the data processing module 400. It may be configured to do so.

Next, data processing in the data processing module 400 will be specifically explained using FIG. 3. FIG. 3 is a schematic diagram showing the operation of the data processing module 400 in the information processing apparatus according to this embodiment.

First, the data acquisition unit 410 acquires situation information data from the input unit 100. Alternatively, the data acquisition unit 410 acquires conceptual information data from the processing unit 200. The data acquisition unit 410 outputs the acquired data (input data) to the identification unit 430.

The identification unit 430 compares the pattern of the data received from the data acquisition unit 410 with the patterns of each of the plurality of learning models stored in the storage unit 420. Then, the identification unit 430 extracts a model having a pattern with the highest degree of suitability for the pattern of the data received from the data acquisition unit 410 from among the plurality of models included in the learning model. A model that has a pattern that has a high degree of adaptation to the pattern of the received data can be said to be a model that has a close information distance to the received data.

The method for determining the degree of compatibility between input data (situational information data or conceptual information data) and a learning model is not particularly limited, but for example, an inner product value between a pattern of input data and a pattern of a learning model may be used. There are several methods.

Below, a method for determining the degree of compatibility between input data and a learning model using the inner product value of the input data pattern and the learning model pattern will be described. Here, to simplify the explanation, each of the situation information data, conceptual information data, learning model pattern, and learning data value is in a bitmap format containing nine cells arranged in a 3 x 3 matrix. It shall be a pattern. The value of each cell is 0 or 1.

The inner product value of the input data pattern and the learning model pattern is calculated by multiplying the values of cells at the same coordinates and summing the multiplied values of each coordinate. For example, as shown in Figure 3, the values of each cell composing the input data pattern are A, B, C, D, E, F, G, H, and I, which constitute the pattern of the learning model to be compared. Assume that the values of each cell are 1, 0, 0, 0, 1, 0, 0, 0, 1. In this case, the inner product value of the input data pattern and the learning model pattern is A×1+B×0+C×0+D×0+E×1+F×0+G×0+H×0+I×1. The inner product value calculated in this way is normalized by dividing it by the number of cells whose value is 1 among the cells included in the input data. Calculation of the inner product value and normalization processing for the input data are performed for each of the plurality of models included in the learning model.

Next, a model with the largest normalized inner product value is extracted from among the plurality of learning models. The normalized inner product value represents likelihood, and the larger the value, the higher the degree of adaptation to the input data. Therefore, by extracting the model with the maximum normalized inner product value, it is possible to extract the model with the highest degree of adaptation to the input data. Here, for example, as shown in Figure 3, a model with a pattern in which the values of each cell are 1, 0, 0, 0, 1, 0, 0, 0, 1 is the model with the highest degree of fitness for the input data. Assume that it is extracted as .

Next, the identification unit 430 outputs the value linked to the extracted model to the data output unit 440 as another conceptual information data obtained by converting the input data. For example, as shown in FIG. , 0, 0, 1, 0, 0, 1, 1. In this case, values in which the values of each cell are 1, 1, 0, 0, 1, 0, 0, 1, 1 become the output data output to the data output section 440.

Next, the data output unit 440 outputs the data acquired from the identification unit 430 to the next stage processing unit.

By configuring in this way, input data in which the values of each cell are A, B, C, D, E, F, G, H, I can be changed to 1, 1, 0, 0, 1. , 0, 0, 1, 1.

By configuring the recognition processing section 210 using such a data processing module 400, the situation information data received from the input section 100 can be converted into conceptual information data. Further, by configuring the concept processing unit 220 using such a data processing module 400, the concept information data received from the recognition processing unit 210 can be converted into concept information data of another concept.

Next, an information processing method using the information processing apparatus 1000 according to this embodiment will be described using FIG. 4. FIG. 4 is a flowchart showing the information processing method according to this embodiment.

First, the input unit 100 acquires information from the outside (step S101). The information acquired by the input unit 100 is not particularly limited, and examples include auditory information (words, sounds, etc.), visual information (images, etc.), tactile information (body sensation, temperature, texture, etc.). .

The input unit 100 converts information received from the outside into data in a predetermined format, and generates situation information data (step S102). For example, when voice input or text is input to the input unit 100 as external information, the input unit 100 converts the input data into situation information data using a known word identification AI system or the like. Alternatively, when an image is input to the input unit 100 as information from the outside, the input unit 100 converts the input data into situation information data using a known image identification AI system or the like.

Next, the input unit 100 outputs the generated situation information data to the recognition processing unit 210 of the processing unit 200.

Next, the recognition processing section 210 converts the situation information data received from the input section into conceptual information data using, for example, the data processing module 400 described above, and outputs the conceptual information data to the conceptual processing section 220 (step S103).

Next, the concept processing unit 220 converts the concept information data received from the recognition processing unit 210 into concept information data representing a concept different from the received concept information data, using, for example, the data processing module 400 described above. Step S104).

Next, the concept processing section 220 outputs the generated conceptual information data to the output section 300.

Next, the output unit 300 generates “words” and “actions” based on the conceptual information data received from the processing unit 200 (step S105).

Next, the output unit 300 determines whether the generated "words" are sufficient as an answer (solution) (step S106).

As a result of the determination, if the generated "words" are insufficient (incomplete) as a solution ("No" in step S106), the process moves to step S102, and the generated "words" are fed back to the input unit 100. Then, the processing from step S102 to step S106 is repeated. In other words, they repeatedly ask themselves questions using the "words" they have generated. The "words" generated by the output unit 300 represent results based on past experience. By processing the "words" generated by the output unit 300 again, it becomes possible to make decisions based on past experience.

On the other hand, if the generated "words" are sufficient as a solution ("Yes" in step S106), the output unit 300 outputs the generated "words" and/or "behaviors" and ends the series of processing. (Step S107). Although the output of "words" is not particularly limited, for example, the generated "words" can be output as text information or audio information. Although the output of the "behavior" is not particularly limited, for example, predetermined instructions for executing a task according to the generated "behavior" can be output.

In this way, all the processing in the information processing apparatus according to this embodiment is data-to-data conversion, that is, data-driven processing.

One hypothesis that explains human thinking is that the production of words is thought. This hypothesis explains that conscious activities are carried out by repeatedly asking oneself questions using the generated words as mental words. Feedback of the "words" generated by the output unit 300 to the input unit 100 can be said to correspond to self-questioning in this hypothesis. This makes it possible to process information using algorithms that are closer to human thinking.

Next, an application example of information processing using the information processing apparatus 1000 according to this embodiment will be described with reference to FIGS. 5 to 7. Here, two application examples will be given to explain information processing in this embodiment in more detail.

The first application example is an application example to license issuing business processing whose purpose is to obtain a license number in response to a license request from a user and report the obtained license number to the user. Note that the information processing apparatus 1000 is assumed to have knowledge of acquiring a license number by operating a numbering ledger.

FIG. 5 is a sequence diagram showing the information processing method in the first application example.

Assume that a user (Mr. A) inputs an instruction to the input unit 100 requesting issuance of a license. The input unit 100 converts the input information into situation information data and outputs it to the recognition processing unit 210.

Next, the recognition processing unit 210 converts the situation information data received from the input unit 100 into conceptual information data. Here, it is assumed that the input information is converted into concept information data including concepts (concept A) indicating the status of "Mr. A," "license," and "issuance." The recognition processing unit 210 outputs the converted conceptual information data to the output unit 300.

Next, the output unit 300 generates “words” based on the conceptual information data received from the recognition processing unit 210. For example, for a concept A indicating the situation of "Mr. A," "license," and "issuance," words such as "think about" are added to generate "words." As a result, for example, "words" such as "Mr. A is considering issuing a license." are generated. The output unit 300 outputs the generated “words” to the input unit 100.

Next, the input unit 100 converts the input “words” into situation information data and outputs it to the recognition processing unit 210. The recognition processing unit 210 converts the situation information data received from the input unit 100 into conceptual information data. Here, it is assumed that the word "think about" is converted into concept information data including concepts (concept B) indicating the tasks of "Mr. A," "license," and "issuance." The recognition processing section 210 outputs the converted conceptual information data to the conceptual processing section 220.

Next, the concept processing unit 220 converts the input concept information data into another concept information data. Here, it is assumed that the concept information data is converted into concept information data including a concept (concept C) that indicates the behavior that is recalled from the tasks of "Mr. A," "license," and "issuance." For example, from the information "license" and "issuance", we recall the method of "manipulating the numbering ledger" and convert the input concept information data into concepts that indicate the actions "Mr. A", "license", and "manipulating the numbering ledger". Convert to conceptual information data containing. The concept processing unit 220 outputs the converted concept information data to the output unit 300.

Next, the output unit 300 generates “words” based on the concept information data received from the concept processing unit 220. For example, for a concept C indicating an action such as "Mr. A," "license," and "manipulating a numbering ledger," a word such as "do" is added to generate a "word." As a result, for example, "words" such as "Mr. A will operate the license numbering ledger" are generated. The output unit 300 outputs the generated “words” to the input unit 100.

Next, the input unit 100 converts the input “words” into situation information data and outputs it to the recognition processing unit 210. The recognition processing unit 210 converts the situation information data received from the input unit 100 into conceptual information data. Here, it is assumed that the word "do" is converted into concept information data including a concept (concept D) indicating work for "Mr. A," "license," and "numbering ledger operation." The recognition processing unit 210 outputs the converted conceptual information data to the output unit 300.

Next, the output unit 300 generates “behavior” based on the conceptual information data received from the recognition processing unit 210. Here, as a work for the information "license" and "numbering ledger operation", for example, a schedule application for issuing license numbers based on the information "license" and "numbering ledger operation" shown in the conceptual information data. Outputs instructions to execute. The schedule application outputs the license number obtained by executing it to the input unit 100.

Next, the input unit 100 outputs the license number received from the schedule application as is or converts it into status information data and outputs it to the recognition processing unit 210. The recognition processing unit 210 identifies that the received information is a result of execution of the schedule application, and outputs the received information to the output unit 300.

Next, the output unit 300 generates “words” based on the information received from the recognition processing unit 210. For example, a word such as "desu" is added to the license number "123-456-7890" output by the schedule application to generate a word. As a result, for example, "words" such as "It's 123-456-7890." are generated.

Next, the output unit 300 reports the generated "words" to the user by displaying them on a display device or outputting them as audio, and ends the series of processing.

The second application example is a schedule adjustment process that aims to compare the schedules of two users (Mr. A and Mr. B) for 5 days from Monday to Friday, adjust their free time, and report it. This is an example of application to Here, it is assumed that the schedules of Mr. A and Mr. B from Monday to Friday are as shown in FIG. In the table of FIG. 6, it is assumed that "morning" and "afternoon" time slots are working hours, and "lunch break" is outside working hours. Furthermore, "0" indicates a vacant time slot with no reservations, and "1", "2", and "3" indicate time slots with reservations. The values ``1'', ``2'', and ``3'' indicate the priority of the reservation; ``1'' is a reservation where attendance is mandatory, ``2'' is a reservation where attendance is preferred, and ``3'' is a reservation where non-attendance is possible. , shall be. It is assumed that the information processing apparatus 1000 has the knowledge to adjust schedules during working hours, but does not have knowledge regarding "lunch break" and "priority" in the initial state.

FIG. 7 is a sequence diagram showing the information processing method in the second application example.

Assume that an instruction is input to the input unit 100 from a user (Mr. A) requesting schedule adjustment with Mr. B. The input unit 100 converts the input information into situation information data and outputs it to the recognition processing unit 210.

Next, the recognition processing unit 210 converts the situation information data received from the input unit 100 into conceptual information data. Here, it is assumed that the input information is converted into conceptual information data including concepts (concept A) indicating the situations of "Mr. A", "Mr. B", and "Schedule Adjustment". The recognition processing unit 210 outputs the converted conceptual information data to the output unit 300.

Next, the output unit 300 generates “words” based on the conceptual information data received from the recognition processing unit 210. For example, for a concept A indicating a situation such as "Mr. A", "Mr. B", or "Schedule adjustment", words such as "think about" are added to generate "words". As a result, for example, "words" such as "Mr. A and Mr. B will consider adjusting their schedules." are generated. The output unit 300 outputs the generated “words” to the input unit 100.

Next, the input unit 100 converts the input “words” into situation information data and outputs it to the recognition processing unit 210. The recognition processing unit 210 converts the situation information data received from the input unit 100 into conceptual information data. Here, it is assumed that the word "think about" is converted into concept information data including a concept (concept B) indicating the issues of "Mr. A", "Mr. B", and "Schedule adjustment". The recognition processing section 210 outputs the converted conceptual information data to the conceptual processing section 220.

Next, the concept processing unit 220 converts the input concept information data into another concept information data. Here, it is assumed that the concept information data is converted into conceptual information data including a concept (concept C) indicating the actions that are recalled from the tasks of "Mr. A", "Mr. B", and "Schedule Adjustment". For example, from the information ``schedule adjustment,'' we recall the methods ``at work'' and ``search in the schedule app,'' and search the input conceptual information data for ``Mr. A,'' ``person B,'' ``at work,'' and ``search in the schedule app.'' ” is converted into conceptual information data that includes the concept indicating the behavior. The concept processing unit 220 outputs the converted concept information data to the output unit 300.

Next, the output unit 300 generates “words” based on the concept information data received from the concept processing unit 220. For example, a word such as "do" is added to a concept C indicating the actions "Mr. A", "Mr. B", "At work", and "Search in a schedule application" to generate a "word". As a result, for example, "words" such as "Mr. A, Mr. B, searches on the schedule application during work." are generated. The output unit 300 outputs the generated “words” to the input unit 100.

Next, the input unit 100 converts the input “words” into situation information data and outputs it to the recognition processing unit 210. The recognition processing unit 210 converts the situation information data received from the input unit 100 into conceptual information data. Here, according to the word "do", the data is converted into conceptual information data including concepts (concept D) indicating the work for "Mr. A", "Mr. B", "Working", and "Search by schedule application". shall be. The recognition processing unit 210 outputs the converted conceptual information data to the output unit 300.

Next, the output unit 300 generates “behavior” based on the conceptual information data received from the recognition processing unit 210. Here, as an operation for the information shown in the conceptual information data, an instruction to execute a schedule application for adjusting the schedules of Mr. A and Mr. B during their work is output. The schedule application outputs the results obtained by executing it to the input unit 100. Note that in the example of FIG. 6, since there is no free time common to the schedules of Mr. A and Mr. B while they are working, it is assumed that a result of "no free time" is output.

Next, the input unit 100 outputs the result received from the schedule application as is or converts it into situation information data and outputs it to the recognition processing unit 210. The recognition processing unit 210 identifies that the received information is a result of execution of the schedule application, and outputs the received information to the output unit 300.

Next, the output unit 300 generates “words” based on the information received from the recognition processing unit 210. For example, a word such as "desu" is added to the result "no vacancy" output by a schedule application to generate a word. As a result, for example, "words" such as "There are no vacancies" are generated.

Next, the output unit 300 reports the generated "words" to the user by displaying them on a display device or outputting them as audio, and ends the series of processing.

Next, it is assumed that the user (Mr. A) who received the report inputs an instruction to the input unit 100 requesting adjustment of the lunch break schedule with Mr. B. The input unit 100 converts the input information into situation information data and outputs it to the recognition processing unit 210.

Next, the recognition processing unit 210 converts the situation information data received from the input unit 100 into conceptual information data. Here, it is assumed that the input information is converted into conceptual information data including concepts (concept A) indicating the situations of "Mr. A", "Mr. B", "lunch break", and "schedule adjustment". The recognition processing unit 210 outputs the converted conceptual information data to the output unit 300.

Next, the output unit 300 generates “words” based on the conceptual information data received from the recognition processing unit 210. For example, for a concept A indicating a situation such as "Mr. A", "Mr. B", "lunch break", or "schedule adjustment", a word such as "think about" is added to generate a "word". As a result, for example, "words" such as "Mr. A and Mr. B will consider adjusting their lunch break schedule." are generated. The output unit 300 outputs the generated “words” to the input unit 100.

Next, the input unit 100 converts the input “words” into situation information data and outputs it to the recognition processing unit 210. The recognition processing unit 210 converts the situation information data received from the input unit 100 into conceptual information data. Here, it is assumed that the word "think about" is converted into conceptual information data including concepts (concept B) indicating the tasks of "Mr. A," "Mr. B," "lunch break," and "schedule adjustment." The recognition processing section 210 outputs the converted conceptual information data to the conceptual processing section 220.

Next, the concept processing unit 220 converts the input concept information data into another concept information data. Here, it is assumed that the concept information data is converted into conceptual information data including a concept (concept C) indicating the actions that are recalled from the tasks of "Mr. A", "Mr. B", "lunch break", and "schedule adjustment". At this stage, the information processing device 1000 does not have the knowledge of "lunch break," but from the information "schedule adjustment," it recalls the technique of "searching for lunch break" and "searching with schedule app." Then, the input conceptual information data is converted into conceptual information data including concepts indicating actions such as "Mr. A", "Mr. B", "Lunch break", and "Search by schedule application". The concept processing unit 220 outputs the converted concept information data to the output unit 300.

Next, the output unit 300 generates “words” based on the concept information data received from the concept processing unit 220. For example, a word such as "do" is added to a concept C indicating the actions "Mr. A", "Mr. B", "lunch break", and "search in a schedule application" to generate a "word". As a result, "words" such as "Mr. A and Mr. B search on the lunch break schedule application" are generated, for example. The output unit 300 outputs the generated “words” to the input unit 100.

Next, the input unit 100 converts the input “words” into situation information data and outputs it to the recognition processing unit 210. The recognition processing unit 210 converts the situation information data received from the input unit 100 into conceptual information data. Here, the word "do" is converted into conceptual information data that includes a concept (concept D) indicating the work for "Mr. A", "Mr. B", "lunch break", and "Search by schedule application". do. The recognition processing unit 210 outputs the converted conceptual information data to the output unit 300.

Next, the output unit 300 generates “behavior” based on the conceptual information data received from the recognition processing unit 210. Here, as an operation for the information shown in the conceptual information data, an instruction to execute a schedule application for adjusting the lunch break schedule of Mr. A and Mr. B is output. The schedule application outputs the results obtained by executing it to the input unit 100.

Next, the input unit 100 outputs the result received from the schedule application as is or converts it into situation information data and outputs it to the recognition processing unit 210. The recognition processing unit 210 identifies that the received information is a result of execution of the schedule application, and outputs the received information to the output unit 300. In the example of Figure 6, the common free time in the lunch break schedules of Mr. A and Mr. B exists on Tuesday, Thursday, and Friday, so it is assumed that the result "lunch break on Tuesday, Thursday, and Friday" is output. .

Next, the input unit 100 outputs the result received from the schedule application as is or converts it into situation information data and outputs it to the recognition processing unit 210. The recognition processing unit 210 identifies that the received information is a result of execution of the schedule application, and outputs the received information to the output unit 300.

Next, the output unit 300 generates “words” based on the information received from the recognition processing unit 210. For example, a word such as "desu" is added to the output result of a schedule application, "lunch breaks on Tuesdays, Thursdays, and Fridays," to generate words. As a result, for example, "words" such as "It's lunch break on Tuesday, Thursday, and Friday." are generated.

Next, the output unit 300 reports the generated "words" to the user by displaying them on a display device, outputting them as audio, or the like.

Furthermore, in parallel with generating the “behavior” for the concept D, the output unit 300 generates “words” based on the concept information data received from the recognition processing unit 210. For example, for the concept D indicating the tasks "Mr. A", "Mr. B", "Lunch break", and "Search by schedule application", words such as "did" are added to generate "words". As a result, for example, "words" such as "Mr. A and Mr. B searched on the lunch break schedule application" are generated. The output unit 300 outputs the generated “words” to the input unit 100.

Next, the input unit 100 converts the input “words” into situation information data and outputs it to the recognition processing unit 210. The recognition processing unit 210 converts the situation information data received from the input unit 100 into conceptual information data. Here, we refer to the result of the ``action'' according to the word ``did'', and in response to the fact that the result was obtained even though we do not have knowledge of ``lunch break'', we say ``remember the lunch break''. Generate a concept (concept E) that indicates learning.

Next, the concept processing unit 220 performs learning using the learning model stored in the storage unit 420 of the data processing module 400, and causes the user to memorize "lunch break" as knowledge. In this way, the series of processing ends.

Next, it is assumed that the user (Mr. A) who received the report further inputs an instruction to the input unit 100 requesting schedule adjustment with Mr. B at priority level 3. The input unit 100 converts the input information into situation information data and outputs it to the recognition processing unit 210.

Next, the recognition processing unit 210 converts the situation information data received from the input unit 100 into conceptual information data. Here, it is assumed that the input information is converted into conceptual information data including concepts (concept A) indicating the situations of "Mr. A", "Mr. B", "Priority 3", and "Schedule Adjustment". The recognition processing unit 210 outputs the converted conceptual information data to the output unit 300.

Next, the output unit 300 generates “words” based on the conceptual information data received from the recognition processing unit 210. For example, for a concept A indicating a situation such as "Mr. A", "Mr. B", "Priority 3", and "Schedule adjustment", a word such as "think about" is added to generate a "word". As a result, for example, "words" such as "Mr. A, Mr. B, consider adjusting the priority 3 schedule." are generated. The output unit 300 outputs the generated “words” to the input unit 100.

Next, the input unit 100 converts the input “words” into situation information data and outputs it to the recognition processing unit 210. The recognition processing unit 210 converts the situation information data received from the input unit 100 into conceptual information data. Here, in response to the word "think about," the data is converted into conceptual information data that includes concepts (concept B) that indicate the issues of "Mr. A," "Mr. B," "Priority 3," and "Schedule adjustment." do. The recognition processing section 210 outputs the converted conceptual information data to the conceptual processing section 220.

Next, the concept processing unit 220 converts the input concept information data into another concept information data. Here, it is assumed that the concept information data is converted into conceptual information data including a concept (concept C) indicating the actions that are recalled from the tasks of "Mr. A", "Mr. B", "Priority 3", and "Schedule Adjustment". At this stage, the information processing apparatus 1000 does not have "Priority 3" as knowledge, but it recalls the method of "Priority 3" and "Search by schedule application" from the information "Schedule adjustment". Then, the input conceptual information data is converted into conceptual information data including concepts indicating actions such as "Mr. A", "Mr. B", "Priority 3", and "Search by schedule application". The concept processing unit 220 outputs the converted concept information data to the output unit 300.

Next, the output unit 300 generates “words” based on the concept information data received from the concept processing unit 220. For example, for a concept C indicating the actions of "Mr. A", "Mr. B", "Priority 3", and "Search by schedule application", a word such as "do" is added to generate a "word". As a result, for example, "words" such as "Mr. A and Mr. B search using the priority 3 schedule application" are generated. The output unit 300 outputs the generated “words” to the input unit 100.

Next, the input unit 100 converts the input “words” into situation information data and outputs it to the recognition processing unit 210. The recognition processing unit 210 converts the situation information data received from the input unit 100 into conceptual information data. Here, depending on the word "do", it is converted into conceptual information data including concepts (concept D) indicating work for "Mr. A", "Mr. B", "Priority 3", and "Search by schedule application". shall be taken as a thing. The recognition processing unit 210 outputs the converted conceptual information data to the output unit 300.

Next, the output unit 300 generates “behavior” based on the conceptual information data received from the recognition processing unit 210. Here, as an operation for the information shown in the conceptual information data, an instruction to execute a schedule application for adjusting the schedules of Mr. A and Mr. B with priority level 3 is output. The schedule application outputs the results obtained by executing it to the input unit 100.

Next, the input unit 100 outputs the result received from the schedule application as is or converts it into situation information data and outputs it to the recognition processing unit 210. The recognition processing unit 210 identifies that the received information is a result of execution of the schedule application, and outputs the received information to the output unit 300. In addition, in the example of FIG. 6, the common free time or time period of priority 3 in the schedules of Mr. A and Mr. B exists on Monday afternoon and Friday morning, so "Monday afternoon, Friday morning priority 3" Assume that the following result is output.

Next, the input unit 100 outputs the result received from the schedule application as is or converts it into situation information data and outputs it to the recognition processing unit 210. The recognition processing unit 210 identifies that the received information is a result of execution of the schedule application, and outputs the received information to the output unit 300.

Next, the output unit 300 generates “words” based on the information received from the recognition processing unit 210. For example, a word such as "desu" is added to the result "Monday afternoon, Friday morning priority 3" output by the schedule application to generate a word. As a result, "words" such as "Priority level 3 for Monday afternoon and Friday morning" are generated, for example.

Next, the output unit 300 reports the generated "words" to the user by displaying them on a display device, outputting them as audio, or the like.

Furthermore, in parallel with the generation of "behavior" for the concept D, the output section generates "words" based on the concept information data received from the recognition processing section 210. For example, for the concept D indicating the tasks "Mr. A", "Mr. B", "Priority 3", and "Search by schedule application", words such as "did" are added to generate "words". As a result, for example, "words" such as "Mr. A searched for Mr. B using the priority 3 schedule application." are generated. The output unit 300 outputs the generated “words” to the input unit 100.

Next, the input unit 100 converts the input “words” into situation information data and outputs it to the recognition processing unit 210. The recognition processing unit 210 converts the situation information data received from the input unit 100 into conceptual information data. Here, we refer to the results of ``action'' according to the word ``did'', and if a result is obtained even though we do not have knowledge of ``priority 3'', we refer to ``priority 3''. A concept (concept E) indicating the learning of "remembering" is generated.

Next, the concept processing unit 220 performs learning using the learning model stored in the storage unit 420 of the data processing module 400, and causes the “priority level 3” to be memorized as knowledge. In this way, the series of processing ends.

After learning "lunch break" and "priority 3", in response to the instruction from the user (Mr. A) requesting to adjust the schedule with Mr. B, "No vacancies available. Lunch break on Tuesday, Thursday, and Friday. It is also possible to receive reports such as "Priority 3 on Monday afternoon and Friday morning." at the same time.

Next, an example of the hardware configuration of the information processing apparatus 1000 according to this embodiment will be described using FIGS. 8 to 11C. 8 and 9 are schematic diagrams showing examples of the hardware configuration of the information processing apparatus according to this embodiment. FIG. 10 is a diagram illustrating a data processing processor in the information processing apparatus according to this embodiment. 11A, FIG. 11B, and FIG. 11C are diagrams showing examples of input data and learning model patterns.

The information processing device 1000 can be realized by a hardware configuration similar to that of a general information processing device, as shown in FIG. 8, for example. For example, the information processing device 1000 may include a CPU (Central Processing Unit) 500, a main storage section 502, a communication section 504, and an input/output interface section 506.

The CPU 500 is a control/arithmetic device that performs overall control and arithmetic processing of the information processing device 1000. The main storage unit 502 is a storage unit used as a data work area and a data temporary save area, and may be configured with a memory such as a RAM (Random Access Memory). The communication unit 504 is an interface for transmitting and receiving data via a network. The input/output interface section 506 is an interface for connecting to an external output device 510, input device 512, storage device 514, etc. to transmit and receive data. The CPU 500, main storage section 502, communication section 504, and input/output interface section 506 are interconnected by a system bus 508. The storage device 514 may be configured, for example, by a hard disk device or the like configured from a nonvolatile memory such as a ROM (Read Only Memory), a magnetic disk, or a semiconductor memory.

The main storage unit 502 can be used as a work area for executing calculations in the data processing module 400 and the like. CPU 500 can function as a control unit that controls arithmetic processing in main storage unit 502. The storage device 514 can be used as the storage unit 420 and can store a trained learning model.

The communication unit 504 is a communication interface based on standards such as Ethernet (registered trademark) and Wi-Fi (registered trademark), and is a module for communicating with other devices. The learning model stored in the storage device 514 may be configured to be received from another device via the communication unit 504. For example, frequently used learning models can be stored in the storage device 514, and less frequently used learning cell information can be read from another device.

Output device 510 may include a display, such as a liquid crystal display. The output device 510 can be used as a display device for presenting processing results to the user. The input device 512 is a keyboard, a mouse, a touch panel, or the like, and can be used by a user to input predetermined instructions to the information processing apparatus 1000.

The functions of each part of the information processing apparatus 1000 according to this embodiment can be realized in hardware by mounting circuit components that are hardware components such as LSI (Large Scale Integration) incorporating a program. Alternatively, it is also possible to implement the function in software by storing a program that provides the function in the storage device 514, loading the program into the main storage unit 502, and executing it on the CPU 500.

Further, the configuration of the information processing device 1000 shown in FIG. 1 does not necessarily need to be configured as one independent device. For example, a part of the input section 100, the processing section 200, and the output section 300, for example, the processing section 200, may be arranged on a cloud, and an information processing system may be constructed using these.

Alternatively, the information processing apparatus 1000 can also be configured as a data-driven data flow machine, as shown in FIG. 9, for example.

For example, the information processing device 1000 may include a plurality of data processors 600 and an input/output interface section 620. The plurality of data processing processors 600 are connected in series. The first stage data processing processor 600 of the serially connected data processing processor 600 is connected to the input/output interface section 620 and receives data from the input/output interface section 620 . Further, the final stage data processing processor 600 of the serially connected data processing processor 600 is connected to the input/output interface section 620 and outputs data to the input/output interface section 620. The data processor 600 has a function of outputting a value associated with a pattern having the closest information distance to the input. The input/output interface unit 620 is an interface for connecting to an external output device 630, input device 640, storage device 650, etc. to transmit and receive data.

Although FIG. 9 shows one route from the input/output interface section 620 to the input/output interface section 620 via the plurality of data processing processors 600, a plurality of routes may be provided in parallel. Furthermore, a branching route or a merging route may be provided for the plurality of routes.

As shown in FIG. 10, each of the plurality of data processing processors 600 includes an input processing unit 602, a plurality of (for example, m) inner product units 604 ₁ to 604 _m , a comparator 606, a selector 608, and an output The processing unit 610 may be configured to include a processing unit 610. Each of the plurality of data processors 600 has a function of receiving data, performing predetermined processing on the input data, and outputting the processed data.

The inner product units 604 ₁ to 604 _m , the comparator 606 and the selector 608 may be configured by logic gate circuits or the like. The patterns (PAT1 to PATm) and values (Value1 to Valuem) of the learning data can be stored in registers. The learning data patterns (PAT1 to PATm) and values (Value1 to Valuem) can be stored in the storage device 650 in advance. In this case, when the information processing apparatus 1000 is started, the information can be read from the storage device 650 through the input/output interface section 620 and set in each data processing processor 600.

The data output from the input/output interface section 620 is input to the input processing section 602 of the first stage data processing processor 600. The data input to the input processing unit 602 is the above-mentioned situation information data and conceptual information data. The input processing unit 602 outputs input data in parallel to each of the plurality of inner product units 604 corresponding to the plurality of models making up the learning model. For example, if the learning model includes m models, input data is input in parallel to m inner product units 604 ₁ to 604 _m .

Each of the inner product units 604 ₁ to 604 _m calculates an inner product between the input data pattern and the learning model pattern. For example, assume that the input data pattern is composed of data as shown in FIG. 11A, and the learning model pattern corresponding to the inner product ₆₀₄₁ is composed of data as shown in FIG. 11B. Further, it is assumed that the pattern of the learning model in FIG. 11B is associated with a value as shown in FIG. 11C. In this case, the inner product 604 ₁ is
IN ₁ × PAT1 ₁ + IN ₂ × PAT1 ₂ + … + IN ₉ × PAT1 ₉
Calculate the sum of the products multiplied by each element, as in The calculation results of each of the inner product units 604 ₁ to 604 _m are input to a comparator 606 .

In this way, by calculating the inner product of input data for the patterns of multiple learning models, it is possible to complete all inner product calculations in one cycle, which reduces the number of cycles per process compared to processing by a program. can be significantly reduced. Note that if the amount of resources of the processor is insufficient, the inner product calculation process may be performed multiple times while changing the pattern of learning data supplied to each inner product unit 604.

A comparator 606 compares the output values of the inner product units 604 ₁ to 604 _m , and outputs to the selector 608 the learning model number (1 to m) that shows the largest inner product value with respect to the input data.

The selector 608 selects the value linked to the learning model corresponding to the number output from the comparator 606 from among the values linked to the patterns of the plurality of learning models, and outputs it to the output processing unit 610. do. The output processing unit 610 outputs the selected value to the data processing processor 600 at the next stage.

Note that when passing the processing in the data processing processor 600 and proceeding to the processing in the next data processing processor 600, data may be transmitted from the input processing section 602 to the output processing section 610. Furthermore, when performing processing such as state transition, the processing results by the data processing processor 600 may be returned from the output processing section 610 to the input processing section 602.

As described above, according to the present embodiment, it is possible to realize an information processing apparatus and an information processing method that can process information using an algorithm that is closer to human thinking.

[Second embodiment]
An information processing device according to a second embodiment of the present invention will be described using FIG. 12. Components similar to those of the information processing apparatus according to the first embodiment are denoted by the same reference numerals, and description thereof will be omitted or simplified. FIG. 12 is a schematic diagram showing a schematic configuration of an information processing device according to this embodiment.

The information processing device 1000 according to this embodiment includes an input section 100, a processing section 200, and an output section 300, as shown in FIG.

The input unit 100 has a function of generating, based on the received information, first data representing a situation understood from the information. The processing unit 200 has a function of generating second data representing a concept related to a situation based on the first data received from the input unit 100. The output unit 300 has a function of generating words representing the concept based on the second data received from the processing unit 200. Further, the output unit 300 is configured to output the generated word to the input unit 100 as new information when the generated word does not match the solution according to the information.

With this configuration, it is possible to realize an information processing device that can process information using an algorithm that is closer to human thinking.

[Modified embodiment]
The present invention is not limited to the above-described embodiments, and various modifications are possible.

For example, an example in which a part of the configuration of one embodiment is added to another embodiment, or an example in which a part of the configuration in another embodiment is replaced is also an embodiment of the present invention.

Further, a processing method in which a program for operating the configuration of the embodiment described above to realize the functions of the embodiment described above is recorded on a recording medium, the program recorded on the recording medium is read as a code, and executed on a computer is also available. It is included in the scope of the embodiment. That is, computer-readable recording media are also included within the scope of each embodiment. Furthermore, not only the recording medium on which the above-described program is recorded, but also the program itself is included in each embodiment.

As the recording medium, for example, a floppy (registered trademark) disk, a hard disk, an optical disk, a magneto-optical disk, a CD-ROM, a magnetic tape, a nonvolatile memory card, and a ROM can be used. In addition, each embodiment is not limited to a program that executes processing by itself as a program recorded on the recording medium, but also includes a program that operates on the OS and executes processing in collaboration with other software and functions of an expansion board. included in the category of

The above embodiments are merely examples of implementation of the present invention, and the technical scope of the present invention should not be construed as limited by these embodiments. That is, the present invention can be implemented in various forms without departing from its technical idea or main features.

A part or all of the above embodiment may be described as in the following supplementary notes, but is not limited to the following.

(Additional note 1)
an input unit that generates first data representing a situation ascertained from the information based on the received information;
a processing unit that generates second data representing a concept related to the situation based on the first data;
an output unit that generates and outputs words representing the concept based on the second data;
Information processing characterized in that the output unit is configured to output the generated word as new information to the input unit when the generated word does not match a solution according to the information. Device.

(Additional note 2)
The information processing device according to supplementary note 1, wherein the output unit is configured to further output an instruction regarding behavior according to the concept represented by the second data.

(Additional note 3)
The processing unit includes a first processing unit that generates third data conceptualizing the situation represented by the first data, and a processing unit that converts the third data into another concept and converts the third data into the second data. and a second processing unit that generates the information.

(Additional note 4)
The first processing unit includes a first learning model and a first identification unit,
The first data is data mapping relationships between a plurality of elements representing the situation and their element values,
The first learning model includes a pattern that maps relationships between a plurality of elements representing a specific situation and their element values, and a plurality of elements that are linked to the pattern and represent a concept corresponding to the specific situation. and values that map relationships between their element values, and a plurality of models each including
The first identification unit associates the value associated with the pattern with the highest fitness with the first data among the plurality of models of the first learning model with the third The information processing device according to supplementary note 3, wherein the information processing device selects the information as data.

(Appendix 5)
The second processing unit includes a second learning model and a second identification unit,
The third data is data mapping relationships between a plurality of elements representing a concept and their element values,
The second learning model includes a pattern that maps relationships between a plurality of elements representing a specific concept and their element values, and a pattern that is linked to the pattern and represents another concept assumed from the specific concept. including a plurality of models each including a value that maps the relationship between a plurality of elements and their element values;
The second identification unit selects the value associated with the pattern that has the highest degree of suitability for the third data among the plurality of models of the second learning model, from the second learning model. 4. The information processing device according to appendix 3 or 4, wherein the information processing device is selected as data.

(Appendix 6)
The second processing unit corresponds to at least some of the elements of the concept represented by the third data when the second learning model does not include a model corresponding to at least some of the elements of the concept represented by the third data. The information processing device according to appendix 5, wherein the model is added as one of the models constituting the second learning model.

(Appendix 7)
The processing unit is composed of a plurality of data processing processors connected in series,
According to any one of appendices 1 to 6, each of the plurality of data processing processors is configured to output a value associated with a pattern having the closest information distance to the input. Information processing device.

(Appendix 8)
a first step of generating, based on the received information, first data representing a situation ascertained from the information;
a second step of generating second data representing a concept related to the situation based on the first data;
a third step of generating and outputting words representing the concept based on the second data,
An information processing method characterized in that, if the words generated in the third step do not match the solution according to the information, the steps are repeated from the first step using the generated words as new information.

(Appendix 9)
8. The information processing method according to appendix 8, wherein in the third step, an instruction regarding behavior according to the concept represented by the second data is further output.

(Appendix 10)
The second step is
generating third data that conceptualizes the situation represented by the first data;
The information processing method according to appendix 8 or 9, further comprising the step of converting the third data into a different concept to generate the second data.

(Appendix 11)
The first data is data mapping relationships between a plurality of elements representing the situation and their element values,
The first learning model includes a pattern that maps relationships between multiple elements representing a specific situation and their element values, and a plurality of elements that are linked to the pattern and represent concepts corresponding to the specific situation. including a plurality of models each including values mapping relationships with those element values,
In the step of generating the third data, the value associated with the pattern that has the highest degree of fitness for the first data among the plurality of models of the first learning model is The information processing method according to appendix 10, characterized in that the third data is selected as the third data.

(Appendix 12)
The third data is data mapping relationships between a plurality of elements representing a concept and their element values,
The second learning model includes a pattern that maps relationships between multiple elements representing a specific concept and their element values, and a plurality of patterns that are linked to the pattern and represent another concept assumed from the specific concept. a plurality of models each including values that map relationships between elements and their element values;
In the step of generating the second data, the value associated with the pattern that has the highest degree of fitness for the third data among the plurality of models of the second learning model is The information processing method according to appendix 10 or 11, characterized in that the information processing method is selected as the second data.

(Appendix 13)
If the second learning model does not include a model corresponding to at least some elements of the concept represented by the third data, the model corresponding to at least some of the elements is included in the second learning model. The information processing method according to appendix 12, further comprising the step of adding as one of the models constituting the information processing method.

(Appendix 14)
computer,
means for generating, based on the received information, first data representing a situation ascertained from the information;
means for generating second data representing a concept related to the situation based on the first data;
Generate words expressing the concept based on the second data, and when the generated words do not match the solution according to the information, generate the first data using the generated words as new information. a means of outputting to a means;
A program that functions as

(Appendix 15)
A computer-readable recording medium having the program described in Supplementary Note 14 written thereon.

This application claims priority based on Japanese Patent Application No. 2020-132276 filed on August 4, 2020, and the entire disclosure thereof is incorporated herein.

100...Input unit 200...Processing unit 210...Recognition processing unit 220...Concept processing unit 300...Output unit 400...Data processing module 410...Data acquisition unit 420...Storage unit 430...Identification unit 440...Data output unit 500...CPU
502...Main storage unit 504...Communication unit 506...I/O interface unit 508...System bus 510...Output device 512...Input device 514...Storage device 1000...Information processing device

Claims (10)

an input unit that generates first data representing a situation ascertained from the information based on the received information;
a processing unit that generates second data representing a concept related to the situation based on the first data;
an output unit that generates and outputs words representing the concept based on the second data;
Information processing characterized in that the output unit is configured to output the generated word as new information to the input unit when the generated word does not match a solution according to the information. Device. The information processing apparatus according to claim 1, wherein the output unit is configured to further output an instruction regarding behavior according to the concept represented by the second data. The processing unit includes a first processing unit that generates third data conceptualizing the situation represented by the first data, and a processing unit that converts the third data into another concept and converts the third data into the second data. The information processing apparatus according to claim 1 or 2, further comprising a second processing unit that generates the information. The first processing unit includes a first learning model and a first identification unit,
The first data is data mapping relationships between a plurality of elements representing the situation and their element values,
The first learning model includes a pattern that maps relationships between a plurality of elements representing a specific situation and their element values, and a plurality of elements that are linked to the pattern and represent a concept corresponding to the specific situation. and values that map relationships between their element values, and a plurality of models each including
The first identification unit associates the value associated with the pattern with the highest fitness with the first data among the plurality of models of the first learning model with the third 4. The information processing apparatus according to claim 3, wherein the information processing apparatus selects data as data. The second processing unit includes a second learning model and a second identification unit,
The third data is data mapping relationships between a plurality of elements representing a concept and their element values,
The second learning model includes a pattern that maps relationships between a plurality of elements representing a specific concept and their element values, and a pattern that is linked to the pattern and represents another concept assumed from the specific concept. including a plurality of models each including a value that maps the relationship between a plurality of elements and their element values;
The second identification unit selects the value associated with the pattern that has the highest degree of suitability for the third data among the plurality of models of the second learning model, from the second learning model. The information processing device according to claim 3 or 4, wherein the information processing device is selected as data. The second processing unit corresponds to at least some of the elements of the concept represented by the third data when the second learning model does not include a model corresponding to at least some of the elements of the concept represented by the third data. The information processing device according to claim 5, wherein the model is added as one of the models configuring the second learning model. The processing unit is composed of a plurality of data processing processors connected in series,
7. Each of the plurality of data processing processors is configured to output a value associated with a pattern having the closest information distance to the input. information processing equipment. a first step of generating, based on the received information, first data representing a situation ascertained from the information;
a second step of generating second data representing a concept related to the situation based on the first data;
a third step of generating and outputting words representing the concept based on the second data,
An information processing method characterized in that, if the words generated in the third step do not match the solution according to the information, the steps are repeated from the first step using the generated words as new information. computer,
means for generating, based on the received information, first data representing a situation ascertained from the information;
means for generating second data representing a concept related to the situation based on the first data;
Generate words expressing the concept based on the second data, and when the generated words do not match the solution according to the information, generate the first data using the generated words as new information. a means of outputting to a means;
A program that functions as A computer-readable recording medium containing the program according to claim 9 .

Images