Chatbot information processing device and chatbot information processing method

Abstract

To provide a chatbot information processing device capable of performing interaction and input / output more flexible than before with respect to an interaction partner and contents.SOLUTION: The chatbot information processing device 10 is a learning-type chatbot that returns output information by natural language processing using a computer with respect to given input information, and includes the storage unit 14 that accumulates reaction data in which a reaction key and a reaction are paired, and the algorithm generation engine unit 13 that analyzes the input information and generates and outputs the output information. The engine part 13 has an analyzing part 13a which generates a response key including a syntax key from inputted information, a judging part 13b which judges whether or not response information including a response corresponding to the generated response key is stored in the storage part 14, and a response part 13c which executes an outputting response or a recursive response in accordance with the judged result.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present invention relates to a learning chatbot information processing device that returns output information in response to given input information through natural language processing using a computer. [Background technology]

[0002] Various technologies have been proposed as learning chatbot information processing devices that return output information based on given input information through natural language processing using a computer (see, for example, Patent Document 1). The technology in Patent Document 1 is a natural language processing system that uses a neural network, receives sentences related to a question and context, determines a score for the received question and each sentence, uses an encoder and a decoder to generate a minimum set of sentences from the scores associated with the question and sentences, and generates an answer to the question from the minimum set of sentences. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Special Publication No. 2021-515310 Summary of the Invention [Problem to be solved by the invention]

[0004] However, the technology of Patent Document 1 employs a method of accepting questions from a user and returning answers to the user, which has the problem that it cannot handle dialogues other than question-and-answer format. For example, it cannot be applied to responses that include input / output to external devices such as timers, sensors, and home appliances, and therefore lacks flexibility.

[0005] Therefore, the present invention aims to provide a chatbot information processing device and a chatbot information processing method that can conduct dialogue and input / output with greater flexibility than conventional methods in terms of the dialogue partner and content. [Means for solving the problem]

[0006] In order to achieve the above object, a chatbot information processing device according to one embodiment of the present invention is a learning-type chatbot information processing device that returns output information in response to given input information by natural language processing using a computer, and includes: a memory unit that accumulates reaction data paired with a reaction key, which is information in which a judgment result for at least one of a plurality of predetermined judgment factors is connected as a key, and a reaction, which is a response process corresponding to the reaction key and belongs to either an output process or a recursive process; and an algorithm generation engine unit that acquires and analyzes the input information, stores the analysis result in the memory unit, and generates and outputs output information in response to the acquired input information by referring to the memory unit, and the algorithm generation engine unit performs input analysis on the input information using natural language processing, thereby The system includes an input analysis unit that creates a reaction key that includes a syntactic key, which is information about a syntax based on morphemes that make up force information, as one of the keys that make up the reaction key; a judgment unit that judges whether reaction data including a reaction corresponding to the reaction key created by the input analysis unit is stored in the memory unit; and when the judgment unit judges that reaction data including the reaction is stored in the memory unit, if the reaction belongs to output processing, a reaction unit that generates and outputs output information responsive to the input information by referring to the analysis result stored in the memory unit, if the reaction belongs to recursive processing, and acquires a judgment result of a judgment material corresponding to the reaction, adds a key corresponding to the acquired judgment result to the reaction key, and then causes the judgment unit to repeat the judgment using the added reaction key.

[0007] In order to achieve the above object, a chatbot information processing method according to one embodiment of the present invention is a learning chatbot information processing method that returns output information in response to given input information by natural language processing using a computer, wherein a storage unit included in the computer accumulates reaction data that pairs a reaction key, which is information in which a judgment result for at least one of a plurality of predetermined judgment factors is connected as a key, with a reaction, which is a response process corresponding to the reaction key and belongs to either an output process or a recursive process, and the chatbot information processing method includes an algorithm generation step of acquiring and analyzing the input information, storing the analysis result in the storage unit, and generating and outputting output information that responds to the acquired input information by referring to the storage unit, and the algorithm generation step includes performing input analysis using natural language processing on the input information. and a reaction step of generating and outputting output information responsive to the input information by referring to the analysis result stored in the storage unit when it is determined by the determination step that reaction data including the reaction corresponding to the reaction key created in the input analysis step is stored in the storage unit, and when the reaction belongs to output processing, obtaining a judgment result of a judgment material corresponding to the reaction, adding a key corresponding to the obtained judgment result to the reaction key, and then repeating the judgment by the judgment step using the added reaction key as the target. [Effects of the Invention]

[0008] The present invention provides a chatbot information processing device and a chatbot information processing method that can conduct dialogue and input / output with greater flexibility than conventional methods in terms of the dialogue partner and content. [Brief explanation of the drawings]

[0009] [Figure 1A] FIG. 1A is a block diagram illustrating an example of the configuration of a chatbot system in which a chatbot information processing device according to an embodiment is applied to a cloud computer. [Figure 1B] FIG. 1B is a block diagram illustrating a configuration example of a robot to which a chatbot information processing device according to an embodiment is implanted. [Figure 2] FIG. 2 is a block diagram showing a detailed configuration of the chatbot information processing device in FIGS. 1A and 1B. [Figure 3A] FIG. 3A is a flowchart illustrating the overall procedure of processing by the chatbot information processing device according to the embodiment. [Figure 3B] FIG. 3B is a flowchart that further details some of the steps in the flowchart shown in FIG. 3A. [Figure 4A] FIG. 4A is a flowchart showing a detailed procedure of input analysis by the input analysis unit, which is one of the processes in the flowcharts shown in FIGS. 3A and 3B. [Figure 4B] FIG. 4B is a flowchart showing a processing procedure following the flowchart shown in FIG. 4A. [Figure 4C] FIG. 4C is a flowchart showing a processing procedure following the flowchart shown in FIG. 4B. [Figure 5A] FIG. 5A is a flowchart showing a detailed procedure for preparing a response by the reaction unit, which is one of the processes in the flowcharts shown in FIGS. 3A and 3B. [Figure 5B] FIG. 5B is a flowchart showing a processing procedure following the flowchart shown in FIG. 5A. [Figure 5C] FIG. 5C is a flowchart showing a processing procedure following the flowchart shown in FIG. 5B. [Figure 6A] FIG. 6A is a diagram illustrating the premise of dialogue / operation by a chatbot information processing device. [Figure 6B]FIG. 6B is a diagram showing an example of a dialogue / action in the first scenario (scenario 1), illustrating an example of real-time changes in communication. [Figure 6C] FIG. 6C is a diagram showing a second example of a dialogue / operation (scenario 2), in which the chatbot information processing device asks the user for a morpheme. [Figure 6D] FIG. 6D is a diagram showing a third example of a dialogue / operation (scenario 3), in which the chatbot information processing device asks the user for feedback regarding zero pronouns. [Figure 6E] FIG. 6E is a diagram showing a fourth example of a dialogue / operation (scenario 4), in which the chatbot information processing device asks the user for feedback regarding pronouns. DETAILED DESCRIPTION OF THE INVENTION

[0010] [Embodiment Mode] A chatbot information processing device according to an embodiment is a learning-type chatbot information processing device that returns output information in response to given input information by natural language processing using a computer, and includes a memory unit that accumulates reaction data paired with a reaction key, which is information in which a judgment result for at least one of a plurality of predetermined judgment factors is connected as a key, and a reaction, which is a response process corresponding to the reaction key and belongs to either an output process or a recursive process, and an algorithm generation engine unit that acquires and analyzes the input information, stores the analysis result in the memory unit, and generates and outputs output information in response to the acquired input information by referring to the memory unit, and the algorithm generation engine unit performs input analysis on the input information using natural language processing to configure the input information. an input analysis unit that creates a reaction key that includes a syntactic key, which is information about a syntax based on a morpheme, as one of the keys that make up the reaction key; a judgment unit that judges whether reaction data including a reaction corresponding to the reaction key created by the input analysis unit is stored in the memory unit; and when the judgment unit judges that reaction data including the reaction is stored in the memory unit, if the reaction belongs to output processing, a reaction unit that generates and outputs output information responsive to the input information by referring to the analysis result stored in the memory unit, if the reaction belongs to recursive processing, and acquires a judgment result of a judgment material corresponding to the reaction, adds a key corresponding to the acquired judgment result to the reaction key, and then causes the judgment unit to repeat the judgment using the added reaction key.

[0011] As a result, the processing procedure and processing content in the algorithm generation engine change depending on the reaction data stored in the storage unit, which may result in changes to whether output processing or recursive processing is executed, in what order they are executed, how many times the recursive processing is repeated, and what external device is the target for input / output, etc. For example, by using the current time as input information as one of the recursive processes and executing processing dependent on the current time, or by issuing a startup instruction to a mail server as one of the output processes, it is possible to handle dialogues other than question-and-answer format and to apply to input / output targeted at external devices, thereby realizing a chatbot information processing device that can perform dialogues and input / output with greater flexibility than before in terms of the other party and content of the dialogue.

[0012] Here, when the determination unit determines that reaction data including the reaction is not stored in the storage unit, the reaction unit acquires reaction data including the reaction from the user and stores it in the storage unit, and then causes the determination unit to repeat the determination. As a result, when necessary reaction data is not stored in the storage unit, the user can add the missing reaction data and store it in the storage unit, thereby enabling functional expansion of the other party and content of the conversation.

[0013] Furthermore, in the input analysis, the input analysis unit returns a question prepared in advance to the user in at least one of the following cases: when a morpheme constituting the input information is not one of a plurality of predefined morphemes; when a grammar included in the input information is not one of a plurality of predefined grammars; when a pronoun included in the input information is not one of a plurality of predefined pronouns; or when the input information is a question and an answer corresponding to the question cannot be generated with a reliability equal to or higher than a predetermined standard, and continues the input analysis based on the answer obtained from the user to the question.

[0014] As a result, when the chatbot information processing device encounters a case that it cannot solve, it will solve it by asking the user a question, ensuring a reliable solution that reflects the user's intentions, and eliminating the need to prepare enormous amounts of program processing and data to handle every possible case, allowing for a compact chatbot information processing device to be realized.As a result, it will be possible to implement or transplant the chatbot information processing device even in server devices or equipment with low processing power.

[0015] The input analysis unit also generates information indicating the sequence of morphemes that make up the input information as the syntactic key. As a result, the input analysis unit extracts and stores syntax that can be used semi-permanently once learned from the input information, so that the input information is stored in a more active format than when specific words are stored, enabling learning in a short period of time.

[0016] The memory unit also stores morpheme data that collects information about morphemes, grammar data that collects information about grammar, branch data that collects information about syntactic branches, and antecedent data that collects information about antecedents, and the input analysis unit generates stored data from the input information that indicates information about the morphemes, grammar, branch data, and antecedents of the input information by referring to the morpheme data, grammar data, branch data, and antecedent data stored in the memory unit, and generates the syntactic key by converting the generated stored data into a syntactic key, and the stored data includes an identifier of the user who provides the input information.

[0017] This allows the stored data to include not only content and grammatical information, but also the identifier of the user providing the input information, so by accumulating and using stored data for each user account, it becomes possible to perform interactions and predictions based on the user's unique habits.

[0018] The algorithm generation engine unit acquires the input information from a first device via a communication path and outputs the output information to a second device via a communication path, the first device including at least one of a timer for measuring date and time, a GPS (Global Positioning System), a sensor for detecting a physical quantity, a measuring instrument for measuring a physical quantity, a microphone, a mobile object, a computer, a storage device, a robot, a production facility, a home appliance, and a communication terminal, and the second device including at least one of a mail server, a speaker, a mobile object, a computer, a storage device, a robot, a production facility, a home appliance, and a communication terminal. This enables not only a question-and-answer style dialogue with a user but also response processing including input and output to and from external devices.

[0019] Furthermore, a chatbot information processing method according to an embodiment is a learning-type chatbot information processing method that returns output information in response to given input information by natural language processing using a computer, wherein a storage unit included in the computer accumulates reaction data that pairs a reaction key, which is information in which a judgment result for at least one of a plurality of predetermined judgment factors is connected as a key, with a reaction, which is a response process corresponding to the reaction key and belongs to either an output process or a recursive process, and the chatbot information processing method includes an algorithm generation step of acquiring and analyzing input information, storing the analysis result in the storage unit, and generating and outputting output information in response to the acquired input information by referring to the storage unit, and the algorithm generation step performs input analysis using natural language processing on the input information, thereby generating and outputting output information in response to the input information. an input analysis step of creating a reaction key including a syntactic key, which is information about a syntax based on morphemes constituting force information, as one of the keys constituting the reaction key; a judgment step of judging whether reaction data including a reaction corresponding to the reaction key created in the input analysis step is stored in the storage unit; and when it is judged by the judgment step that reaction data including the reaction is stored in the storage unit, if the reaction belongs to output processing, generating and outputting output information responsive to the input information by referring to the analysis result stored in the storage unit, and if the reaction belongs to recursive processing, acquiring a judgment result of a judgment material corresponding to the reaction, adding a key corresponding to the acquired judgment result to the reaction key, and then repeating the judgment by the judgment step with the added reaction key as the target.

[0020] As a result, the processing procedure and processing content in the algorithm generation step change depending on the reaction data stored in the storage unit, which may result in changes to whether output processing or recursive processing is executed, in what order they are executed, how many times the recursive processing is repeated, and what external device is the target for input / output, etc. For example, by using the current time as input information as one of the recursive processes and executing processing dependent on the current time, or by issuing a startup instruction to a mail server as one of the output processes, it is possible to respond to dialogues other than question-and-answer format and to apply to input / output targeted at external devices, thereby realizing a chatbot information processing method that allows for dialogues and input / output with greater flexibility than before in terms of the other party and content of the dialogue.

[0021] In addition, the present invention can also be realized as a program that causes a computer to execute the steps included in the above-mentioned chatbot information processing method, or as a computer-readable recording medium such as a DVD or ROM on which the program is recorded.

[0022] [Example] The following describes in detail embodiments of the present invention with reference to the accompanying drawings. Each of the embodiments described below represents an example of implementing the present invention. The data content and structure, dialogue examples, functional components of a chatbot information processing device, connections between components, processing order, computer implementation, external devices, and interactions with external devices shown in the following embodiments are merely examples and are not intended to limit the present invention.

[0023] (1) Idea by the inventor Conventional computer-based natural language processing tends to rely on known morphological analysis engines and attempt to solve problems through mathematical processing. However, the number of patterns in Japanese can easily exceed 10^100, even for a single sentence of approximately 40 characters. Considering that the number of seconds in 10 years is 10^8, obtaining valid statistical data requires processing at a speed exceeding 10^92 per second. This indicates that solving problems through mathematical processing is virtually impossible. Furthermore, conventional chatbot information processing devices rely on an unspecified number of data sources, and therefore are inadequate in taking user-specific data into account, as shown in the following dialogue examples 1 and 2. In the following dialogue examples, the chatbot information processing device is referred to as "Chatbot."

[0024] (Dialogue example 1) User: "My blood type is A." Chatbot: “I understand.” User: "What's my blood type?" Chatbot: “I don’t know.” Also, even if users routinely refer to cups as "that," the system cannot respond, as shown in the example dialogue below.

[0025] (Dialogue example 2) User: "Get that." Chatbot: “I don’t know.”

[0026] On the other hand, most Japanese people start using Japanese from an early age and become able to converse naturally around the time they enter elementary school. Some children receive grammar education, but not receiving this education does not mean that they will no longer be able to speak Japanese. This shows that Japanese language education and theory are not necessarily necessary.

[0027] Therefore, the inventor has clarified conventional theories in natural language processing and reflected these conventional theories in a chatbot information processing device. To do this, the inventor focused on the relationship between morphemes and syntax. What is needed is a language processing algorithm that can feed back data acquired from a memory DB (database). This also includes the tendency of anaphoric expressions used by users. The memory DB is a collection of stored data (database) that contains values ​​for each item of input information, such as morphemes, grammar, branching data, and information about antecedents. Note that a collection of data is called a DB (database).

[0028] The stored data (hereinafter also referred to as "conceptual data") that constitutes the storage DB includes user data. Note that the storage DB may be divided into different data types depending on the usage environment.

[0029] The present invention can be realized by a computing device comprising a processor and memory. This includes chat languages ​​such as browsers and software. Input information includes information acquired by the destination device, including the server, information acquired from external websites or systems via API integration or crawling, and information acquired from a mail server. Input information acquired from the device includes the date and time, capacity, memory, remaining battery level, audio data from a microphone, and values ​​acquired from various sensors and external devices. Output information may include chat replies, operation of the destination device, operation of external websites or systems via API integration, email transmission, etc. The destination device may include robots, drones, home appliances, servers, computers, smartphones, tablets, etc.

[0030] (2) Explanation of terms The definitions of terms used in this example will be explained below.

[0031] (2-1) Terms related to overall operation 1) Materials for judgment This is information used to make decisions about generating output information. Specifically, each key is created based on the date and time, GPS, external connections, discourse analysis, personal opinions, input analysis, etc., and these keys are ultimately connected as response keys.

[0032] 2) External collaboration This information is obtained from a site or device external to the chatbot information processing device according to the embodiment.

[0033] 3) Reactions This is a response process by a chatbot information processing device, and is expressed as information that specifies the execution order by linking one or more processes. Basically, there are three types: "initial reaction (pre-processing of branching process by reaction key; input analysis)", "output reaction (output of answer sentence as output information; output processing)", and "recursive reaction (recursion by adding to reaction key; recursive processing)". However, there are cases where internal and external systems, sites, databases, etc. are used during processing.

[0034] In particular, the process of adding a response key can be realized by linking it within a single reaction (the linked reaction is also called an "integrated reaction"), but it can also be split into multiple recursive reactions to achieve the same result (the split reaction is also called a "split reaction"). While split reactions offer greater flexibility, the amount of required response data registration (i.e., response training) increases dramatically. Input analysis and response preparation (i.e., generation of output information) can be realized in any of the three types of reactions mentioned above, and also in both integrated and split reactions.

[0035] 4) First reaction This corresponds to the process before deciding whether to use an output reaction or a recursive reaction (i.e., branching process). This allows any variable factor to be used as a trigger for a reaction. For example, even if the access method to the chatbot information processing device is replaced with "HTTP method GET: '0', POST: '1'", or "launched via browser: '0', launched via email: '1'", by recursing using the part returned to the reaction, the results of the input analysis can also be reflected by adding them to the reaction key.

[0036] 5) Key It is information that connects the "yes (1)", "no (0)" or concrete values ​​of all elements (i.e., decision-making materials). Keys and corresponding values ​​are linked, and these sets form the basic structure of all data. They are created immediately after a user accesses the system and during processing within each reaction. The two are interchangeable. One example assumes a cloud environment (i.e., the chatbot information processing device is realized in the cloud), but depending on the environment, the former may not be necessary. For example, a timer-based startup (daemon) running on the server can be used as a trigger.

[0037] 6) Reaction key This is information that connects keys created from each decision-making element. It is not necessary to connect all keys, and it can be expanded or contracted depending on the situation. The longer it is, the more complex the reaction based on the decision. For example, it is information with the following structure.

[0038] Response key = Date and time key + GPS key + External key + Discourse key + Self-argument key + Syntax key 7) Reaction data (reaction DB if multiple) This is information that pairs a reaction key with a reaction, and determines the direction of branching in the branching process described above.

[0039] 8) Output reaction This is the last reaction to be executed, and output information is provided to the user (however, reactions in which output information is not provided to the user are also included). For example, in the "Question Answering" process, in which the chatbot information processing device returns an answer sentence as output information in response to a question from a user, "Reaction Answer," which is one of the output reactions, is executed last. Also, in the "Teaching Learning" process, in which the user teaches something to the chatbot information processing device, "Reaction Learning," which is one of the output reactions, is executed last.

[0040] 9) Recursive Reactions This is a reaction that is executed exclusively with the output reaction, and after this reaction is executed, the reaction key is extended (i.e., appended) and it returns to the initial reaction. The longer the recursive reaction (i.e., the more times the recursive reaction is executed), the more precise the situation judgment will be, but on the other hand, the amount of reaction data required will also be enormous.

[0041] (2-2) Terms related to input analysis The terms related to input analysis (i.e., analysis of input information) in the chatbot information processing device are as follows:

[0042] 1) Morpheme tags This is additional information that indicates the part of speech or attributes assigned to a morpheme.

[0043] 2) Morpheme data (morpheme DB if multiple) This information uses morphemes as keys and links them to morpheme tags such as parts of speech and attributes.

[0044] 3) Input analysis Input analysis is performed using morpheme, grammar, branching, and antecedent data and databases, converting the input sentence (i.e., input information) into stored data, which is then further converted into morpheme keys and syntactic keys.

[0045] 4) Input sentence This is an example of input information, and is the original text that the user entered in the chat input field.

[0046] 5) Delimiter This is a sentence obtained by dividing the input sentence into morpheme units using morpheme data.

[0047] 6) Bigram processing This is an analysis process that treats the delimited sentences as pairs, starting with the first two, and once processing is complete, it shifts them one by one in the order of the second and third, the third and fourth, etc. Once all are completed, the memorized data is complete.

[0048] 7) Grammar data (Grammar DB if multiple) This is information indicating the processing content assigned to a pair in bigram processing. If there are multiple grammar data for the same pair, it is necessary to specify it using branch data.

[0049] 8) Branch data (branch DB if multiple) This information determines which grammar data to use when there are multiple grammar data at the same location.

[0050] 9) Morpheme Key This information is generated at the same time as converting stored data into syntactic keys, and is required when answering questions.

[0051] (2-3) Terms related to stored data As described above, the stored data is data generated from the input sentence by input analysis. The terms related to the stored data are as follows:

[0052] 1) Input history Memory data used for discourse analysis.

[0053] 2) Discourse analysis The input history is grouped by topic and the information necessary for input analysis is created. For example, if the input sentence contains pronouns such as "that" or "that," the user is asked to select the antecedent. Morphemes that are determined to be related by discourse analysis are also added as candidates from the options.

[0054] 3) The memory data The input sentence is converted into delimited sentences, and the delimited sentences are then converted into stored data, which can then be converted into expanded data and syntax keys.

[0055] 4) Syntax Key A single line of stored data consisting of multiple lines. Used as the ID of the input statement.

[0056] 5) Deployment This is a process that creates stored data with the key and value reversed.

[0057] 6) Expanded data This is data that has been expanded from stored data. The input memory unit (input buffer memory) of the chatbot information processing device stores both stored data and expanded data. However, depending on the timing of expansion, there are two types: "memory utilization type" and "capacity utilization type." The type used depends on the hardware performance of the chatbot information processing device.

[0058] 7) Memory utilization type This method stores stored data in the input memory without expanding it, and then expands it after retrieving it as needed. This method consumes a lot of memory.

[0059] 8) Capacity utilization type This method expands the stored data before storing it in the input storage unit. Although it consumes capacity in the input storage unit, it consumes little memory.

[0060] (2-4) Terms related to answer preparation The terms related to the preparation of answers as output information are as follows:

[0061] 1) Evaluation This is a process that counts the number of matches of keywords and sequences when restoring sentences from stored data to prepare an answer. The sentence with the most matches becomes the most likely candidate for the answer sentence.

[0062] 2) Preparation of answers Using the question tag and chain data and DB described below, the sentences in the stored data are restored and evaluated, and answer sentences and supplementary explanatory sentences are selected.

[0063] 3) Association The input memory, which stores stored data and expanded data, counts the number of matches with "keywords related to question tags" and "chains," and selects the most likely answer to the question. It also restores candidate sentences for the answer.

[0064] 4) Question tags This information links the tag of the morpheme that is the core of the question to the syntactic key. During answer preparation, morphemes with this tag are collected as keywords and then used in evaluation during the recovery of sentences from memory data. The number of question tags also affects the answer sentence after it is determined, and if a sufficient match is not found, a supplementary explanation sentence is selected.

[0065] 5) Keywords This is a morpheme that has a question tag as a morpheme tag. It counts the number of matches with the value of the stored data item and affects the selection of the answer sentence.

[0066] 6) Linkage Data (also known as "Evaluation Data") This is data used when answering a question, and is information that links a syntax key to elements that could be the answer to the question. Because the order of elements is important in matching, the term "chain" is used. Up to three chains can be specified. The more matches there are, the closer the answer is to the correct one. Cases where there are one, two, and three matching elements are called "1 chain," "2 chain," and "3 chain," respectively. Note that being able to specify up to three chains is just an example, and the number of chains is not limited to this. For example, up to 10 chains may be specified.

[0067] 7) Reconstructed text This is a sentence reconstructed by association within the memory data.

[0068] 8)Answer text The recovered sentence (i.e., the final output information) is selected based on the best match of keywords and sequences.

[0069] 9) Supplementary explanation This is a reconstructed sentence selected without regard to whether the chain matches when the question tag of the answer sentence does not match sufficiently.

[0070] (3) Configuration of chatbot information processing device 1A is a block diagram showing a configuration example of a chatbot system 100 in which a chatbot information processing device 10 according to an embodiment is applied to a cloud computer. In the chatbot system 100, the chatbot information processing device 10 according to the embodiment functions as a cloud computer, and provides services as a chatbot (for example, "answering questions") to terminal devices 52a to 52b used by each user via a communication network 55, while cooperating with a mail server 50 and a website 51 as necessary.

[0071] 1B is a block diagram showing a configuration example of a robot 110 to which a chatbot information processing device 10 according to an embodiment is implanted. In the robot 110, the chatbot information processing device 10 according to the embodiment is implemented as a controller of the robot 110, and controls, obtains information from, and outputs information to various external devices (a light-emitting unit 60, a camera 61, a voice synthesis unit 62b that outputs a voice signal to a speaker 62a, a voice recognition unit 63b that converts a voice signal from a microphone 63a into voice data, a wireless communication adapter 70, a GPS 71, a timer 72, a temperature sensor 73, an acceleration sensor 74, and a drive unit 75 that drives wheels), thereby operating the robot 110, interacting with people, and controlling the external devices.

[0072] Figure 2 is a block diagram showing a detailed configuration of the chatbot information processing device 10 in Figures 1A and 1B. The chatbot information processing device 10 is a learning chatbot that returns output information in response to given input information through natural language processing using a computer, and includes an input / output unit 11, a control unit 12, and a storage unit 14.

[0073] The input / output unit 11 is an input / output interface that connects the chatbot information processing device 10 to an external device via a signal cable or a communication network 55, and is, for example, a bus interface, a communication adapter, etc.

[0074] The control unit 12 is a controller of the chatbot information processing device 10, and is realized by an input memory unit (input buffer memory) that reads and temporarily stores data stored in the memory unit 14, a main memory that reads and temporarily stores programs stored in the memory unit 14, and a processor that executes the programs, and functionally has a management unit (not shown) that manages access by users logging on and off, and an algorithm generation engine unit 13 that interacts with users and external devices or performs input / output.

[0075] The algorithm generation engine unit 13 is a processing unit that acquires and analyzes input information input from the terminal devices 52a to 52b, etc. via the input / output unit 11, stores the analysis results in the memory unit 14, and by referring to the memory unit 14, generates output information that responds to the acquired input information and outputs it to the terminal devices 52a to 52b, etc. via the input / output unit 11, and has an input analysis unit 13a, a judgment unit 13b, and a reaction unit 13c.

[0076] The input analysis unit 13a performs input analysis using natural language processing on the input information, and creates a reaction key that includes a syntactic key, which is information about a syntax based on the morphemes that make up the input information, as one of the keys that make up the reaction key.

[0077] The determination unit 13b determines whether or not reaction data including a reaction corresponding to the reaction key created by the input analysis unit 13a is stored in the storage unit 14.

[0078] When the judgment unit 13b judges that reaction data including a reaction has been stored in the memory unit 14, if the reaction belongs to an output process, the reaction unit 13c generates and outputs output information responding to the input information by referring to the analysis results stored in the memory unit 14, and if the reaction belongs to a recursive process, it acquires the judgment result of the judgment material corresponding to the reaction, adds a key corresponding to the acquired judgment result to the reaction key, and then causes the judgment unit 13b to repeat the judgment using the added reaction key.

[0079] The storage unit 14 is an auxiliary storage device that holds various data and programs required for processing by the control unit 12, and is realized by, for example, a hard disk drive. The storage unit 14 stores various data organized into a database (DB), such as reaction data, morpheme data, delimiter data, grammar data, input tag data, question tag data, and evaluation data. These data are referenced and updated via a database management system (not shown) that the control unit 12 has.

[0080] Reaction data is data paired with a reaction key, which is information linking the result of a decision on at least one of a plurality of predetermined decision factors as a key, and a reaction, which is a response process corresponding to the reaction key and belongs to either an output process or a recursive process. Morphological data is information linking morpheme tags such as parts of speech and attributes using morphemes as keys. Delimiter data is sentences obtained by dividing an input sentence into morpheme units using morpheme data. Grammar data is information indicating the processing content assigned to pairs in bigram processing. Input tag data is information linking input tags such as "polite, assertive, question, greeting, murmur, affirmative, negative" to syntactic keys. Question tag data is information linking specific question expressions to syntactic keys. Evaluation data is data used when answering questions, and is information linking elements that could be answers to questions to syntactic keys, and is also called linkage data.

[0081] (4) Characteristics of chatbot information processing device The chatbot information processing device 10 has the following features.

[0082] (4-1) Morpheme and Syntactic Conjugation The chatbot information processing device 10 uses multiple data stored in the memory unit 14 to extract and store syntax from input sentences, which are input information entered by users. Once a syntax is learned, it can be used semi-permanently. Therefore, the number of combination patterns increases exponentially in accordance with the number of syntaxes, the number of morphemes used in the syntax, the number of interchangeable morphemes, etc.

[0083] For example, if the input sentence is "A wa B ga C desu," there are three possible positions for a morpheme: A, B, and C. If each position has 10 possible morphemes, the number of possible combinations is 10^3, or 1,000. Since "Kuruma wa Kuruma ga Kuruma desu" is unlikely in reality, at least 10 combinations must be subtracted. However, it is easy to imagine that the number could be hundreds of times greater. If input sentences were memorized using specific words rather than morphemes, the number of possible combinations would be enormous. Japan's largest dictionary, the "Nihon Kokugo Daijiten" (Shogakukan), contains 500,000 words. For example, in the case of "A wa B desu," a simple calculation would yield "(500,000 squared) - 500,000 ≒ 2.5 × 10^11." The chatbot information processing device 10 according to the embodiment efficiently processes a huge number of possible combinations of input sentences by extracting, storing, and learning morpheme-based syntax from input sentences.

[0084] (4-2) No weighting The chatbot information processing device 10 performs processing that is faithful to Japanese grammar by attaching and utilizing morpheme tags to morphemes. It considers each morpheme more broadly and deeply than humans and thoroughly eliminates unnecessary patterns. This eliminates the need for the massive computational resources symbolized by supercomputers and big data. By porting it to hardware other than servers, such as robots, drones, and IoT, it can operate completely autonomously without performance degradation even offline.

[0085] In the recent race to develop generative AI, wasteful consumption of electricity and semiconductors has become commonplace, intensifying environmentally harmful developments. Furthermore, in this field, technological foundations such as TPUs (Tensor Processing Units; a trademark of Google), semiconductor manufacturing bases, and AWS (Amazon Web Service; a trademark of Amazon.com) are already being controlled by South Korea, Taiwan, and Big Tech (FAANG, known domestically as GAFA). The chatbot information processing device 10 does not require such specialized overseas technology. As a result, the chatbot information processing device 10 can be implemented independently using domestically developed technologies such as Sakura rental servers, maintaining sufficient competitiveness.

[0086] (4-3) Collecting and reflecting user information In conversation, when a speaker uses pronouns or abbreviated expressions, the listener needs to be able to guess the corresponding words. This ability is inaccurate and extremely inefficient unless it is based on data collected from the speaker himself, no matter how much data is collected and analyzed externally. The chatbot information processing device 10 accumulates input sentences for each logged-on user's account in the form of the above-mentioned stored data, making it possible to make predictions based on the user's unique habits.

[0087] (4-4) Reliable interpretation through questioning The chatbot information processing device 10 does not make hasty predictions while there is insufficient user information. In cases of abbreviated expressions, pronouns, or cases where interpretations differ, the chatbot information processing device 10 asks questions in return to thoroughly eliminate ambiguous interpretations. In addition, the questions used by the chatbot information processing device 10 in this case can also be edited by the user through training. The content of the questions asked can be broadly divided into 1) learning during education, 2) answers to questions, and 3) others, as listed below.

[0088] 1) Learning during education Adding morphemes ·Select how to divide Bigram processing method ·Selecting between multiple grammatical interpretations · Check pronouns Checking abbreviations Check input tags 2) Answering questions Check question tags Check the evaluation method (a) Search within stored data Check how to fix it 3) Other -Adding special morphemes

[0089] (4-5) Summary The chatbot information processing device 10 is a handcrafted algorithm that the generative AI wants to acquire by utilizing vast computational resources in natural language processing. In the first place, it is difficult to theoretically acquire such an algorithm using the generative AI method.

[0090] For example, the number of patterns in shogi is 10 to the power of 220. It is not difficult to imagine that Japanese is even more difficult to understand than shogi. In contrast, although there are differences in processors and other factors, even if the world's fastest supercomputer, Frontier, were to operate at full capacity for 10 years, the number of patterns that could be solved would be 10 to the power of 26. Even if technological innovations that accelerate speed by several orders of magnitude occur every few years, it is highly doubtful that the day will come when even shogi can be solved. In other words, it is difficult to construct an algorithm that covers all theoretically possible patterns.

[0091] The inventor has clarified conventional theories in natural language processing and has reflected these conventional theories in the information processing of the chatbot information processing device 10. To do this, the inventor has focused on the relationship between morphemes and syntax. What is needed is a language processing algorithm that can feed back data acquired from a memory DB (database), and this language processing algorithm is implemented in the chatbot information processing device 10.

[0092] (5) Operation of the chatbot information processing device Next, the operation of the chatbot information processing device 10 according to the embodiment configured as above (that is, the chatbot information processing method) will be described.

[0093] FIG. 3A is a flowchart showing the overall processing procedure by the chatbot information processing device 10 according to an embodiment. FIG. 3B is a flowchart further detailing some steps (S22, S25, S26) in the flowchart shown in FIG. 3A. Here, the processing procedure is shown taking as an example a case where the chatbot information processing device 10 is implemented by a cloud computer or implemented as a robot controller. In FIG. 3A, steps S11 to S13 included in step S10 are user operations, and steps S21 to S27 included in step S20 are processing by the chatbot information processing device 10.

[0094] First, a user accesses the chatbot information processing device 10 using a web browser on the terminal device 52a and provides an input sentence to the chatbot information processing device 10 (S11).

[0095] In the chatbot information processing device 10 that has received access from a user, the input analysis unit 13a of the algorithm generation engine unit 13 reads the reaction database from the memory unit 14 (S21) and then performs input analysis (i.e., initial reaction) on the input sentence currently given by the user, thereby creating a reaction key based on the decision-making information contained in the input sentence (S22).

[0096] In step S22 (first reaction), more specifically, referring to FIG. 3B, the input analysis unit 13a creates memory data by input analysis (S22a in FIG. 3B), converts the created memory data into a syntax key (S22b in FIG. 3B), and adds the obtained syntax key to the reaction key (S22c in FIG. 3B).

[0097] 3A, the determination unit 13b of the algorithm generation engine unit 13 determines whether or not reaction data including reaction data corresponding to the reaction key created by the input analysis unit 13a exists in the reaction database read from the storage unit 14 (S23), and if it determines that such reaction data does not exist (No in S23), it sends an input field for requesting input of such reaction data to the terminal device 52a (S24). The terminal device 52a that has received the input field accepts input of reaction data from the user and sends the accepted reaction data to the chatbot information processing device 10 (S12).

[0098] In the chatbot information processing device 10 that receives the reaction data, the judgment unit 13b adds the received reaction data to the reaction database and then again judges whether reaction data containing reaction data corresponding to the reaction key created by the input analysis unit 13a exists in the reaction database (S23).

[0099] As a result, if the judgment unit 13b judges that the reaction data exists (Yes in S23), the reaction unit 13c of the algorithm generation engine unit 13 identifies whether the reaction data included in the reaction data judged to exist corresponds to an output reaction or a recursive reaction, and if it is determined that the reaction data corresponds to an output reaction, it executes the corresponding output reaction (S25) and outputs the answer sentence obtained by the output reaction by sending it to the terminal device 52a (S13).On the other hand, if it is determined that the reaction data included in the reaction data judged to exist corresponds to a recursive reaction, it executes the corresponding recursive reaction (S26) and adds the execution result to the reaction key (S27).Then, the judgment unit 13b repeats the judgment (S23) for the reaction key added by the reaction unit 13c to determine whether reaction data including reaction data corresponding to the reaction key exists in the reaction database.

[0100] As shown in the output reactions (S25) of FIG. 3B, the output reactions (S25) include a process called "reaction learning" (S31a to S31c), a process called "reaction answer" (S32a to S32b), a process called "reaction command execution" (S33a to S33b), and a process called "reaction external reference" (S34a to S34b).

[0101] In "reaction learning," the reaction unit 13c first creates memory data by expanding the input sentence provided by the user to notify the user that the input sentence has been learned (S31a), then writes the created memory data into the input memory unit (S31b), and then creates a response sentence notifying the user of the completion of learning and sends it to the user's terminal device 52a (S31c). This corresponds to the above-mentioned "educational learning."

[0102] In the "reaction response" mode, in order to return a Yes / No response to an input sentence provided by the user, the reaction unit 13c first adds Yes / No to the beginning of the response sentence corresponding to the input sentence (S32a), and then transmits the obtained response sentence to the user's terminal device 52a (S32b). This corresponds to the above-mentioned "question response."

[0103] In "reaction command execution," the reaction unit 13c first accesses the mail server 50 and prepares for transmission (S33a) in order to receive and respond to the input text given by the user as a message request by email, and then instructs the mail server 50 to send a reply text for the message start notification, thereby sending an email for the message start notification to the user (S33b).

[0104] In the "reaction external reference" mode, in order to operate an external device, the reaction unit 13c first executes control over the external device corresponding to the reaction key generated from the input sentence (S34a), and then creates a response sentence notifying the user of the completion of the operation and sends it to the user's terminal device 52a (S34b).

[0105] In this way, by executing the output reaction, a corresponding reply sentence is created (or there may be no reply sentence) and sent to the user's terminal device 52a, the mail server 50, or an external device.

[0106] Furthermore, as shown in the recursive reaction (S26) of Figure 3B, the recursive reaction (S26) includes a process called "reaction date and time consideration" (S41a to S41b), a process called "reaction GPS consideration" (S42a to S42b), a process called "reaction external collaboration consideration" (S43a to S43b), a process called "reaction discourse analysis consideration" (S44a to S44c), a process called "reaction self-theory formation consideration" (S45a to S45c), and a process called "reaction answer narrowing down" (S46a to S46c).

[0107] In "Consideration of reaction date and time," in order to respond taking into account the current date and time, the reaction unit 13c first obtains the current date and time (e.g., epoch seconds) from a timer 72 or the like accessible to the chatbot information processing device 10, analyzes the impact of the obtained date and time (impact on the process of generating an answer sentence) (S41a), and then adds the result to the reaction key (S41b).

[0108] In the "reaction GPS consideration" mode, in order to respond taking into account the current geographical location, the reaction unit 13c first acquires the current geographical location from a GPS 71 or the like that is accessible to the chatbot information processing device 10, analyzes the impact of the acquired geographical location (impact on the process of generating an answer sentence) (S42a), and then adds the result to the reaction key (S42b).

[0109] In the "reaction taking external collaboration into consideration" mode, in order to respond taking collaboration with external devices into consideration, the reaction unit 13c first acquires information from external devices such as a temperature sensor 73 that the chatbot information processing device 10 can access, analyzes the impact of the acquired information (impact on the process of generating an answer sentence) (S43a), and then adds the results to the reaction key (S43b).

[0110] In the "reaction discourse analysis consideration" mode, in order to converse with the user, the reaction unit 13c first reads the stored data obtained from the input sentence into the input storage unit (S44a), then performs a prepared analysis as discourse analysis (S44b), and adds the result to the reaction key (S44c).

[0111] In the "reaction considering the formation of one's own theory" mode, the reaction unit 13c first forms a theory based on stored data obtained from the input sentence in order to support the user in forming his or her own theory (S45a), then analyzes the influence of the formed theory (the influence on the process of generating the answer sentence) (S45b), and then adds the result to the reaction key (S45c).

[0112] In the "reaction answer narrowing" step, in order to narrow down the answer sentences to be generated, the reaction unit 13c first reads the stored data obtained from the input sentence into the input storage unit (S46a), then calculates the degree of match in the chain described above (S46b), and adds the calculated result to the reaction key (S46c).

[0113] In this way, the execution result of the recursive reaction is added to the reaction key, and the output reaction or recursive reaction is executed again for the added reaction key, and processing such as "educational learning" and "question answering" is performed.

[0114] For example, "educational learning" is realized by executing steps S22, S23, S31a to S31c in this order, and "question answering" is realized by executing steps S22, S23, S46a to S46c, S23, S32a to S32b in this order.

[0115] Note that the details of the output reaction S25 and the recursive reaction S26 shown in Fig. 3B are just an example, and as shown in "Other reaction materials" in Fig. 3B, other reactions such as "greeting," "advice," "acknowledgment," "ignore," "counterargument," and "notification" are also prepared. Also included are output reactions that end without sending output information to the user, recursive reactions that set or change internal information (modes, flags, etc.), and output reactions that send output information to the user depending on the internal information.

[0116] Furthermore, as described above, each reaction shown in FIG. 3B may have a split reaction configuration in which the multiple steps that make up the reaction are split and the recursive reaction is repeated multiple times, and similar results may be obtained.

[0117] 4A to 4C are flowcharts showing detailed steps of input analysis by the input analyzer 13a, which are included in the processing in the flowcharts shown in FIGS. 3A and 3B.

[0118] As the input analysis (S100 in FIG. 4A), the input analyzer 13a first reads the morpheme DB from the storage unit 14 (S101 in FIG. 4A) and performs morpheme analysis on the input sentence from the user (S102 in FIG. 4A). Then, the input analyzer 13a determines whether the input sentence contains an unknown morpheme (S103 in FIG. 4A). If it determines that an unknown morpheme exists (Yes in S103 in FIG. 4A), the input analyzer 13a generates a reverse question by displaying an input field for inputting the unknown morpheme on the user's terminal device 52a (S104 in FIG. 4A). The input of the morpheme by the user in response to the reverse question is received (S105 in FIG. 4A) and the received morpheme is added to the morpheme DB (S106 in FIG. 4A).

[0119] On the other hand, if it is determined that there are no unknown morphemes (No in S103 of FIG. 4A), the input analysis unit 13a creates a "delimited sentence" by dividing the input sentence into morphemes (S107 of FIG. 4A), and then reads the grammar DB (S108 of FIG. 4A), the branch DB (S109 of FIG. 4A), and further the antecedent DB (S110 of FIG. 4A) from the memory unit 14.

[0120] Then, the input analyzer 13a performs bigram processing on the delimited sentence by referring to the read grammar DB, branch DB, and antecedent DB (S120 in FIG. 4B). More specifically, the input analyzer 13a creates a grammar key for the delimited sentence that connects the parts of speech and attributes of the first and second morphemes and the presence or absence of each main morpheme (S121 in FIG. 4B), and determines whether grammar data corresponding to the created grammar key exists in the grammar DB (S122 in FIG. 4B). Note that the bigram processing and subsequent processing that depends on the bigram processing are not essential processes performed by the input analyzer 13a.

[0121] As a result, if it is determined that there is no grammar data corresponding to the grammar key in the grammar DB (No in S122 of FIG. 4B), the input analysis unit 13a generates a reverse question by displaying an input field for inputting the unknown grammar data on the user's terminal device 52a (S123 of FIG. 4B), receives the grammar data input by the user in response to this as an answer to the reverse question (S124 of FIG. 4B), and adds the received grammar data to the grammar DB (S125 of FIG. 4B).

[0122] On the other hand, if it is determined that the grammar data corresponding to the grammar key is in the grammar DB (Yes in S122 of FIG. 4B), the input analysis unit 13a then determines whether branch data is necessary, that is, whether an unknown modifier relationship exists in the input sentence (S126 of FIG. 4B). If it is determined that branch data is necessary (Yes in S126 of FIG. 4B), it then determines whether the branch data corresponding to the grammar key is in the branch DB (S127 of FIG. 4B). If it is determined that the branch data corresponding to the grammar key is not in the branch DB (No in S127 of FIG. 4B), it generates a reverse question by displaying an input field for entering the unknown branch data on the user's terminal device 52a (S128 of FIG. 4B), receives the branch data entered by the user in response to this as an answer to the reverse question (S129 of FIG. 4B), and adds the received branch data to the branch DB (S130 of FIG. 4B).

[0123] If it is determined in step S126 of FIG. 4B that branch data is not required (No in S126 of FIG. 4B), or if it is determined in step S127 of FIG. 4B that branch data corresponding to the grammar key is in the branch DB (Yes in S127 of FIG. 4B), the input analysis unit 13a advances one bigram (S140 of FIG. 4C) and determines whether or not the bigram processing is completed (S141 of FIG. 4C). If it is not completed (No in S141 of FIG. 4C), the bigram processing (S121 of FIG. 4B to S141 of FIG. 4C) is repeated until it is determined that the bigram processing is completed (Yes in S141 of FIG. 4C).

[0124] After completing the bigram processing, the input analysis unit 13a identifies the main morphemes and main parts of the input sentence (S142 in FIG. 4C) and generates storage data (S143 in FIG. 4C). Then, the input analysis unit 13a determines whether or not a pronoun or zero pronoun is present in the stored data (S144 in FIG. 4C). If a pronoun or zero pronoun is present (Yes in S144 in FIG. 4C), it determines whether or not the pronoun or zero pronoun is in the antecedent DB (S144a in FIG. 4C). If present (Yes in S144a in FIG. 4C), it replaces the pronoun with the found antecedent or substitutes it for the zero pronoun (S144b in FIG. 4C). On the other hand, if not present (No in S144a in FIG. 4C), it generates a reverse question by displaying an input field for inputting the unknown antecedent on the user's terminal device 52a (S145 in FIG. 4C), receives the antecedent input by the user in response to this as a response to the reverse question (S146 in FIG. 4C), and adds the received antecedent to the antecedent DB (S147 in FIG. 4C). A zero pronoun is a sentence in which the pronoun is omitted.

[0125] Next, the input analysis unit 13a accumulates the stored data in the input storage unit (S148 in FIG. 4C), converts the stored data into a syntactic key (S149 in FIG. 4C), generates a morpheme key for each morpheme (S150 in FIG. 4C), and adds the syntactic key to the response key (S151 in FIG. 4C).

[0126] In this manner, the input analysis of the input sentence by the input analysis unit 13a is completed, and a syntactic key is generated.

[0127] 5A to 5C are flowcharts showing detailed steps of response preparation by the reaction unit 13c among the processes in the flowcharts shown in FIGS. 3A and 3B.

[0128] As a preparation for an answer in the "question answer" (S200 in FIG. 5A), the reaction unit 13c first reads the question tag DB from the storage unit 14 (S201 in FIG. 5A), and then generates an input field for inputting the question tag of the input sentence as an input field for an inverse question to be displayed on the user's terminal device 52a (S202 in FIG. 5A). Then, the reaction unit 13c determines whether or not a sufficient amount of data with a matching syntax key has been accumulated in the question tag DB (S203 in FIG. 5A). If it determines that a sufficient amount of data has not been accumulated (No in S203 in FIG. 5A), the reaction unit 13c issues an inverse question by displaying an input field for inputting a question tag on the user's terminal device 52a, and receives the question tag input by the user in response to the inverse question as an answer to the inverse question (S204 in FIG. 5A), and adds the received question tag to the question tag DB (S205 in FIG. 5A).

[0129] Next, the reaction unit 13c generates a keyword list by listing morphemes having the attribute of the question tag (S206 in FIG. 5A), and then generates an input field for inputting a chain as an input field for a reverse question to be displayed on the user's terminal device 52a (S207 in FIG. 5A). Then, the reaction unit 13c reads the chain DB from the storage unit 14 (S208 in FIG. 5A), determines whether or not there is chain data with a matching syntax key in the chain DB (S210 in FIG. 5B). If it determines that there is no chain data with a matching syntax key in the chain DB (No in S210 in FIG. 5B), it issues a reverse question that displays an input field for inputting a chain on the user's terminal device 52a, receives a chain input by the user in response to the reverse question as an answer to the reverse question (S211 in FIG. 5B), and adds the received chain to the chain DB (S212 in FIG. 5B).

[0130] Next, the reaction unit 13c reads the data stored in the input storage unit (S213 in FIG. 5B), expands the stored data based on the morphemes that make up the input sentence (S214 in FIG. 5B), and then restores one of the expanded stored data to the original sentence (S215 in FIG. 5B).The reaction unit 13c then determines whether the value of the item in the restored stored data matches a keyword (S216 in FIG. 5B), and if they match (Yes in S216 in FIG. 5B), counts the number of keyword matches by one (S217 in FIG. 5B).

[0131] Next, the reaction unit 13c determines whether the combination of items and values ​​of the restored stored data matches one chain data (S218 in FIG. 5B), and if it matches (Yes in S218 in FIG. 5B), it counts one chain number as one (S219 in FIG. 5B).

[0132] Similarly, the reaction unit 13c determines whether the combination of items and values ​​of the restored stored data matches the 2-chain data (S220 in FIG. 5C), and if they match (Yes in S220 in FIG. 5C), it counts the number of 2-chains as 1 (S221 in FIG. 5C).

[0133] Similarly, the reaction unit 13c determines whether the combination of items and values ​​of the restored stored data matches the 3-chain data (S222 in FIG. 5C), and if it matches (Yes in S222 in FIG. 5C), it counts the number of 3-chains as 1 (S223 in FIG. 5C).

[0134] Then, the reaction unit 13c determines whether the restoration of all stored data has been completed (S224 in FIG. 5C), and if it has not been completed (No in S224 in FIG. 5C), it continues to restore all stored data (S215 in FIG. 5B to S224 in FIG. 5C) until it determines that the restoration is completed (Yes in S224 in FIG. 5C).

[0135] When the restoration of all stored data is completed, the reaction unit 13c creates a ranking of the restored sentences in the order of the number of keyword matches, the number of 3-chain sequences, the number of 2-chain sequences, and the number of 1-chain sequences (S225 in Figure 5C), and determines the restored sentence with the highest ranking as the answer sentence (S226 in Figure 5C).

[0136] Then, the reaction unit 13c determines whether the number of keyword matches for the determined restored sentence is less than the number of question tags (S227 in FIG. 5C), and if it is less (Yes in S227 in FIG. 5C), determines the restored sentence with the same number of keyword matches as the number of question tags from the ranking as the supplementary explanation sentence (S228 in FIG. 5C), and transmits the answer sentence and, if there is a supplementary explanation sentence, the supplementary explanation sentence to the user's terminal device 52a for display (S229 in FIG. 5C).

[0137] In this way, the reaction unit 13c completes the preparation of the answer, and the answer sentence or the like is provided to the user.

[0138] (6) Examples of dialogue / operation of chatbot information processing device Below, examples of dialogue / operation by the chatbot information processing device 10 will be explained using Figures 6A to 6E. Note that in Figures 6A to 6E, the numbers on the left side are line numbers for explanatory purposes. Also, in Figures 6B to 6E showing examples of dialogue / operation, the subject of the dialogue (i.e., the user / chatbot information processing device (written as "Chatbot") 10) and example dialogue / operation steps are indented in order to the right of the line numbers.

[0139] FIG. 6A is a diagram explaining the premise (i.e., prior settings) of the dialogue / operation by the chatbot information processing device 10. In this example, the chatbot information processing device 10 is pre-configured to change the tone of voice when speaking to the user depending on the user's authority (i.e., whether the user is logged on or logged off) (line 11). Specifically, the chatbot information processing device 10 is configured to use non-honorific language (plain language) when logged off (line 12), and to use honorific language (polite language) when logged on (line 13). Note that the morpheme data, grammar data, and other various data mentioned above are all stored as a DB in the storage unit 14 (line 14).

[0140] Figure 6B shows an example of a dialogue / operation in the first scenario (scenario 1), illustrating an example of real-time changes in communication. It is now nighttime and the user is logged off (line 101). The user has given the chatbot information processing device 10 the input sentence "Good morning" (for the first time) (lines 102-103).

[0141] Then, in the chatbot information processing device 10, the algorithm generation engine unit 13 executes the recursive reaction "Consider reaction date and time", which is a pre-registered recursive reaction corresponding to the reaction key generated from the input analysis for "Good morning", and after adding the confirmed time period to the reaction key, executes the recursive reaction pre-registered corresponding to the added reaction key, thereby detecting the discrepancy between the fact that it is night and "Good morning", and adds the result to the reaction key (lines 104 to 105).

[0142] Furthermore, the algorithm generation engine unit 13 executes the recursive reaction "Reaction external collaboration consideration" to recognize that the consideration function (flag) is off, and after adding the result to the reaction key (line 106), executes the output reaction pre-registered corresponding to the added reaction key to generate the answer sentence "Is it night now?" and send it to the user's terminal device 52a (lines 107-108).

[0143] In response to this, let us assume that the user provides the input sentence "Read the atmosphere" to the chatbot information processing device 10 (lines 109-110). Then, in the chatbot information processing device 10, the algorithm generation engine unit 13 executes an output reaction to detect the input tag "Consideration on" linked to "Read the atmosphere" (lines 111-112), switches the consideration function (flag) from off to on (line 113), and ends the response without outputting any particular reply sentence.

[0144] Next, suppose that the user again provides the input sentence "Good morning" (for the second time) to the chatbot information processing device 10 (lines 114-115). Then, in the chatbot information processing device 10, the algorithm generation engine unit 13 detects the input tag "time zone is morning" linked to "Good morning" through input analysis (lines 116-117), and executes an output reaction to generate a greeting sentence "Good morning!" linked to logoff and linked to morning as a reply sentence and send it to the user's terminal device 52a (lines 118-120).

[0145] In response to this, let us assume that the user provides the chatbot information processing device 10 with an input sentence, "In times like that, the answer is, 'Good morning!'" (lines 121-122). Then, in the chatbot information processing device 10, the algorithm generation engine unit 13 detects the input tag "reply message update" linked to "In times like that, the answer is, 'Good morning!'" through input analysis (lines 123-124), executes a recursive reaction to change the reaction data corresponding to this situation (line 125), and then executes an output reaction to generate a reply sentence, "I got it!", and transmits it to the user's terminal device 52a (lines 126-127).

[0146] Next, suppose that the user again provides the input sentence "Good morning" (for the third time) to the chatbot information processing device 10 (lines 128-129). Then, in the chatbot information processing device 10, the algorithm generation engine unit 13 detects the input tag "time zone is morning" linked to "Good morning" through input analysis, and executes an output reaction to generate a modified greeting sentence "Good morning!" linked to logoff and linked to morning as a reply sentence and send it to the user's terminal device 52a (lines 130-132).

[0147] In this way, by having the chatbot learn to change the reaction data through communication with the chatbot information processing device 10, it becomes possible to change the content of the response by the chatbot information processing device 10 in real time.

[0148] FIG. 6C is a diagram showing an example of a dialogue / operation in the second scenario (scenario 2), in which the chatbot information processing device 10 asks the user for a morpheme. Assume that the user logs in to the chatbot information processing device 10 (line 201), the user's ID at that time is "AAA," and the user's authority is "general user" (lines 202-203). Then, the user provides the chatbot information processing device 10 with the input sentence "I'm eating ramen." (lines 204-205).

[0149] Then, in the chatbot information processing device 10, the algorithm generation engine unit 13 stops the input analysis because the morpheme "ramen" is not in the morpheme data (lines 206-207), and by activating the ask-again function (line 208), creates a message saying "Please tell me the first word after 'ramen'," and sends it to the user's terminal device 52a (lines 209-210), and transitions to "morpheme confirmation mode" (line 211).

[0150] In response to this, let us assume that the user provides the input sentence "It's ramen" to the chatbot information processing device 10 (lines 212-213). In response, the algorithm generation engine unit 13 in the chatbot information processing device 10 adds the morpheme "ramen" as morpheme data (lines 214-215), creates a message saying "Understood," and sends it to the user's terminal device 52a (lines 216-217), and cancels the "morpheme confirmation mode" (line 218).

[0151] In this example, with the privileges of a "general user," the system only asks for confirmation of morphemes and pronouns, and if other data is lacking, it sends the user a message saying, "There are some things I don't understand. I will check with the developer, so please wait a few days." (lines 219-222).

[0152] In this way, when an unknown morpheme is input, a question is posed to the user to find a solution that reflects the user's intention, and learning is carried out.

[0153] FIG. 6D is a third example of a dialogue / operation (scenario 3), showing an example of the chatbot information processing device 10 asking the user to reflect on the zero pronoun. Assume now that a user logs in to the chatbot information processing device 10 (line 301), the user's ID at that time is "BBB", the date is May 24, 2024, and the user's authority is "developer" (lines 302-304). Then, the user provides the chatbot information processing device 10 with the input sentence "I'm eating ramen" (lines 305-306).

[0154] Then, in the chatbot information processing device 10, if morphological data and grammatical data related to the input sentence are stored in the memory unit 14 (lines 307 to 308), the algorithm generation engine unit 13 performs input analysis on the input sentence "I'm eating ramen." and converts it into the format of the stored data (lines 310 to 314) (line 309).

[0155] Then, in the input analysis, the algorithm generation engine unit 13 detects zero pronouns (here, a state in which there is no subject) from the converted stored data (line 320), and by activating the ask-again function (line 321), creates a message saying, "Is that you? Please tell us the subject." and sends it to the user's terminal device 52a (lines 322-323), and then transitions to "pronoun confirmation mode" (line 324).

[0156] In response to this, let us assume that the user provides the input sentence "No, it's CCC" to the chatbot information processing device 10 (lines 325-326). In response, the algorithm generation engine unit 13 in the chatbot information processing device 10 updates the above-mentioned stored data (lines 327-333), creates a message saying "Memorized", sends it to the user's terminal device 52a (lines 340-341), and cancels the "pronoun confirmation mode" (line 342).

[0157] In this way, when an unknown zero pronoun is input during input analysis, a question is posed to the user to find a solution that reflects the user's intention, and learning is carried out.

[0158] FIG. 6E is a fourth example of a dialogue / operation (scenario 4), showing an example of the chatbot information processing device 10 asking the user to reflect on the pronoun. Now, let us assume that the user has given the chatbot information processing device 10 an input sentence saying, "This is delicious." (lines 401-402).

[0159] Then, in the chatbot information processing device 10, the algorithm generation engine unit 13 detects the pronoun "kore" in the input sentence during input analysis (lines 403-404), creates a message saying "What does 'kore' mean?" and sends it to the user's terminal device 52a (lines 405-406), and transitions to "pronoun confirmation mode" (line 407). Thereafter, as in scenario 3, if an unknown pronoun is input, a question is asked back to the user to find a solution that reflects the user's intention, and learning is performed (line 408).

[0160] In this way, when an unknown pronoun is input during input analysis, a question is posed to the user to find a solution that reflects the user's intention, and learning is carried out.

[0161] The chatbot information processing device and chatbot information processing method according to the present invention have been described above based on the embodiments and examples, but the present invention is not limited to these embodiments and examples. As long as they do not deviate from the gist of the present invention, various modifications that a person skilled in the art would conceive of to the present embodiments and examples, and other forms constructed by combining some of the components of the embodiments and examples, are also included within the scope of the present invention.

[0162] For example, the present invention may be realized as a program that causes a computer to execute the steps included in the chatbot information processing method, or as a computer-readable recording medium such as a DVD or ROM on which the program is recorded.

[0163] Furthermore, the chatbot information processing device 10 does not necessarily need to interact with the user, and may be implemented, for example, as a controller mounted on a drone or the like that does not have a user interaction function and that only interacts with external devices such as various sensors and drive mechanisms that the drone has. [Industrial Applicability]

[0164] The present invention can be used as a learning chatbot information processing device that returns output information based on given input information through natural language processing using a computer, and can be implemented, for example, in a cloud computer or ported to a robot, drone, home appliance, server, computer, smartphone, tablet, etc. [Explanation of symbols]

[0165] 10 Chatbot information processing device 11 Input / output section 12 Control Unit 13 Algorithm generation engine 13a Input analysis section 13b Judgment part 13c Reaction Section 14 Storage section 50 Mail Server 51 websites 52a, 52b Terminal equipment 60 Light-emitting part 61 Camera 62a Speaker 62b Speech synthesis unit 63a Microphone 63b Voice recognition unit 70 Wireless communication adapter 71 GPS 72 Timer 73 Temperature Sensor 74 Accelerometer 75 Drive unit 100 Chatbot Systems 110 Robot

Claims

1. A learning chatbot information processing device that returns output information by natural language processing using a computer in response to given input information, a storage unit that stores reaction data that pairs a reaction key, which is information that connects a judgment result for at least one of a plurality of predetermined judgment factors as a key, with a reaction, which is a response process that corresponds to the reaction key and belongs to either an output process or a recursive process; an algorithm generation engine unit that acquires and analyzes input information, stores the analysis result in the storage unit, and generates and outputs output information responsive to the acquired input information by referring to the storage unit; The algorithm generation engine unit an input analysis unit that performs input analysis using natural language processing on the input information to create a reaction key that includes a syntactic key, which is information about a syntax based on morphemes that constitute the input information, as one of the keys that constitute the reaction key; a determination unit that determines whether reaction data including a reaction corresponding to the reaction key created by the input analysis unit is stored in the storage unit; and a reaction unit that, when the judgment unit judges that reaction data including the reaction is stored in the storage unit, generates and outputs output information responsive to the input information by referring to the analysis result stored in the storage unit if the reaction belongs to an output process, and, when the reaction belongs to a recursive process, acquires a judgment result of a judgment material corresponding to the reaction, adds a key corresponding to the acquired judgment result to the reaction key, and then causes the judgment unit to repeat the judgment using the added reaction key. Chatbot information processing device.

2. When the determination unit determines that reaction data including the reaction is not stored in the storage unit, the reaction unit acquires reaction data including the reaction from the user and stores it in the storage unit, and then causes the determination unit to repeat the determination. The chatbot information processing device according to claim 1.

3. In the input analysis, the input analysis unit If the morpheme constituting the input information is not one of the predefined morphemes, If the grammar included in the input information is not one of the predefined grammars, If the pronoun included in the input information is not one of the predefined pronouns, If the input information is a question, and an answer corresponding to the question cannot be generated with a reliability equal to or higher than a predetermined standard, In at least one of the cases, a prepared question corresponding to the case is returned to the user, and the input analysis is continued based on an answer obtained from the user to the question. The chatbot information processing device according to claim 1.

4. the input analysis unit generates, as the syntactic key, information indicating a sequence of morphemes constituting the input information; The chatbot information processing device according to claim 1.

5. the storage unit accumulates morpheme data that collects information about morphemes, grammar data that collects information about grammar, branch data that collects information about syntactic branches, and antecedent data that collects information about antecedents, the input analysis unit generates, from the input information, stored data indicating information related to the morpheme data, grammar data, branch data, and antecedent data stored in the storage unit, and converts the generated stored data into a syntactic key, thereby generating the syntactic key; The stored data includes an identifier of a user who provides the input information. The chatbot information processing device according to claim 4.

6. the algorithm generation engine unit acquires the input information from a first device via a communication path and outputs the output information to a second device via a communication path; the first device includes at least one of a timer that measures date and time, a GPS (Global Positioning System), a sensor that detects a physical quantity, a measuring instrument that measures a physical quantity, a microphone, a mobile object, a computer, a storage device, a robot, production equipment, a home appliance, and a communication terminal; the second device includes at least one of a mail server, a speaker, a mobile object, a computer, a storage device, a robot, a production facility, a home appliance, and a communication terminal; The chatbot information processing device according to claim 1.

7. A learning chatbot information processing method that returns output information by natural language processing using a computer in response to given input information, The storage unit of the computer stores reaction data paired with a reaction key, which is information in which a judgment result for at least one of a plurality of predetermined judgment factors is connected as a key, and a reaction, which is a response process corresponding to the reaction key and belongs to either an output process or a recursive process; The chatbot information processing method includes: an algorithm generating step of acquiring and analyzing input information, storing the analysis result in the storage unit, and generating and outputting output information responsive to the acquired input information by referring to the storage unit; The algorithm generating step includes: an input analysis step of performing input analysis using natural language processing on the input information to create a reaction key including a syntactic key, which is information about a syntax based on morphemes constituting the input information, as one of the keys constituting the reaction key; a determination step of determining whether reaction data including a reaction corresponding to the reaction key created in the input analysis step is stored in the storage unit; and when it is determined by the determination step that reaction data including the reaction has been stored in the storage unit, if the reaction belongs to an output process, the method further comprises a reaction step of generating and outputting output information responsive to the input information by referring to the analysis result stored in the storage unit, and when the reaction belongs to a recursive process, acquiring a judgment result of a judgment material corresponding to the reaction, adding a key corresponding to the acquired judgment result to the reaction key, and then repeating the judgment by the determination step using the added reaction key as the target. Chatbot information processing method.

8. A program that causes a computer to execute the steps included in the chatbot information processing method according to claim 7.

Images