User assistance device and computer-readable recording medium

Abstract

A user assistance device according to the present disclosure is provided with: a thought process storage unit that stores thought process data defining thought processes leading to the resolution of an inquiry about an industrial machine; a thought process selection unit that selects an item to be selected by a user, from the thought process data stored in the thought process storage unit; an instruction unit that outputs an instruction based on the item selected by the thought process selection unit; a user input reception unit that receives an input from the user; a prompt generation unit that generates a prompt to be transmitted to an interactive response device, on the basis of the thought process data and a received selection; a transmission unit that transmits the prompt to the interactive response device; a reception unit that receives a response to the prompt from the interactive response device; and a thought process generation unit that creates thought process data defining a thought process leading to the resolution of the inquiry on the basis of the response, and stores the data in the thought process storage unit.

Description

User assistive device and computer-readable recording medium

[0001] The present disclosure relates to a user assistive device and a computer-readable recording medium.

[0002] When a malfunction occurs in industrial machinery such as a machine tool or a robot, it is difficult for the user to identify the cause of the malfunction, so the user may inquire with the manufacturer of the machine tool. In such cases, communication means such as telephone or email are often used. Attempts have also been made to solve the problem interactively. For example, see Patent Document 1.

[0003] Japanese Patent Application Laid-Open No. 62-245363

[0004] However, if a manufacturer were to respond to all inquiries on its own, it would consume excessive man-hours. Furthermore, responses to each inquiry tend to be slow. Furthermore, differences in the quality of answers depending on the person responsible for responding to an inquiry can lead to problems. While large-scale language models (LLMs) and the like have become popular as a means of interactive problem solving, they have the drawback of being poor at exploratory problem solving while engaging in dialogue. Therefore, there is a demand for technology that stabilizes the quality of answers while reducing the workload of those responsible for inquiries.

[0005] The user assistance device according to the present disclosure solves the above problem by generating thought process data that defines thought processes based on responses from a large language model (LLM), and enabling exploratory queries using this data.

[0006] One aspect of the present disclosure is a user assistance device including: a thought process memory unit that stores thought process data that defines the thought process that leads to the resolution of an inquiry related to industrial machinery; a thought process selection unit that selects an item to be selected by a user from the thought process data stored in the thought process memory unit; an instruction unit that outputs instructions based on the item selected by the thought process selection unit; a user input accepting unit that accepts input from a user; a prompt generation unit that generates a prompt to be sent to an interactive response device based on the thought process data and the accepted selection; a sending unit that sends the prompt to the interactive response device; a receiving unit that receives a response to the prompt from the interactive response device; and a thought process generation unit that creates thought process data that defines the thought process that leads to the resolution of the inquiry based on the response and stores the data in the thought process memory unit.

[0007] FIG. 1 is a schematic hardware configuration diagram of a user assistance device according to an embodiment of the present disclosure; FIG. 2 is a block diagram showing schematic functions of a user assistance device according to a first embodiment; FIG. 3 is a schematic diagram showing an example of a thought process; FIG. 4 is a schematic diagram showing an example of an inquiry screen; FIG. 5 is a schematic diagram showing example thought process data; FIG. 6 is a schematic diagram showing another example of an inquiry screen; FIG. 7 is a schematic diagram showing another example of thought process data; FIG. 8 is a schematic diagram showing another example of an inquiry screen; FIG. 9 is a block diagram showing schematic functions of a user assistance device according to a second embodiment; FIG. 10 is a block diagram showing schematic functions of a user assistance device according to a third embodiment;

[0008] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. In the following description, components having the same or similar functions will be denoted by the same reference numerals. Duplicate descriptions of those components may be omitted.

[0009] In this application, "based on XX" means "based on at least XX," and includes cases where it is based on other elements in addition to XX. Furthermore, "based on XX" is not limited to cases where XX is used directly, but also includes cases where it is based on XX that has been calculated or processed. "XX" is any element (for example, any information).

[0010] 1 is a schematic hardware configuration diagram showing the main parts of a user assistance device according to a first embodiment of the present disclosure. The user assistance device 1 according to this embodiment can be implemented on a computer, such as a personal computer attached to a control device, a personal computer connected to the control device via a wired or wireless network, a cell computer, a fog computer 6, or a cloud server 7. In this embodiment, an example is shown in which the user assistance device 1 is implemented on a computer connected via a network to a control device that controls industrial machinery.

[0011] The CPU 11 provided in the user assistance device 1 according to this embodiment is a processor that controls the entire user assistance device 1. The CPU 11 reads a system program stored in the ROM 12 via the bus 22 and controls the entire user assistance device 1 in accordance with the system program. The RAM 13 temporarily stores temporary calculation data, display data, and various data acquired from outside.

[0012] The non-volatile memory 14 is composed of, for example, a battery-backed memory (not shown) or an SSD (Solid State Drive), and retains its stored state even when the user assistance device 1 is powered off. The non-volatile memory 14 stores programs and data read from an external device 72 via the interface 15, programs and data input via the input device 71, and programs and data acquired from the industrial machine 4 or other devices via the network 5. The programs and data stored in the non-volatile memory 14 may be expanded into the RAM 13 when executed / used. In addition, various system programs, such as known analysis programs, are pre-written in the ROM 12.

[0013] The interface 15 is an interface for connecting the CPU 11 of the user assistance device 1 to an external device 72 such as a USB device. For example, system programs, setting data, etc. are read from the external device 72. In addition, programs and setting data created and edited within the user assistance device 1 can be stored in external storage means via the external device 72.

[0014] The interface 20 is an interface for connecting the CPU 11 of the user assistance device 1 to a wired or wireless network 5. The network 5 may communicate using technologies such as serial communication such as RS-485, Ethernet (registered trademark), optical communication, wireless LAN, Wi-Fi (registered trademark), Bluetooth (registered trademark), etc. At least one industrial machine 4 to be controlled, at least one other industrial machine 4, an interactive response device 2 that responds to inquiries from users, a fog computer 6, a cloud server 7, etc. are connected to the network 5, and data is exchanged between the network 5 and the user assistance device 1.

[0015] The display device 70 displays various data read into the memory, data obtained as a result of executing programs, etc., output via the interface 17. An input device 71, which is comprised of a keyboard, pointing device, etc., passes instructions, data, etc. based on operations by an operator to the CPU 11 via the interface 18.

[0016] The interactive response device 2 is configured as a device that returns a response sentence in response to a predetermined sentence. The interactive response device 2 includes a large-scale language model (LLM) that has learned a response sentence for the predetermined sentence. This model can be a known model, such as a Transformer model. The large-scale language model learns, for each text, the probability that the given sentence will be a response to the given sentence when the given sentence is input. It also learns the probability that each of the given texts will be followed by other texts. By repeating this learning process, the large-scale language model, when input, comes to output a text string with a high probability as a response to the given sentence. Depending on how the learning process learns documents that will be responses to the given sentence, the interactive response device 2 can be used for purposes such as dialogue, question and answer session, text summarization, text editing, text translation, text conversion, text modification, text optimization, text interpretation / detection, recognition, prediction, judgment, code generation, image generation, and comprehensive judgment.

[0017] It is assumed that the user assistance device 1 according to the present disclosure is connected to an interactive response device 2 via a network 5. This interactive response device 2 may have learned from past question and answer sessions regarding the industrial machine 4 between an operator and a manufacturer, as well as various documents including books related to the industrial machine 4. In this case, the interactive response device 2 may learn from, for example, reports recording problems that have occurred in the industrial machine 4 in the past, the causes of those problems, and solutions to those problems, as well as manuals for the industrial machine 4. By narrowing down the information used for learning, it is possible to prepare an interactive response device 2 that returns responses to inquiries with a certain degree of accuracy.

[0018] 2 is a schematic block diagram showing functions of the user assistance device 1 according to the first embodiment of the present disclosure. Each function of the user assistance device 1 according to this embodiment is realized by the CPU 11 of the user assistance device 1 shown in FIG. 1 executing a system program and controlling the operation of each part of the user assistance device 1.

[0019] The user assistance device 1 of this embodiment includes a user input accepting unit 100, a prompt generating unit 110, a transmitting unit 120, a receiving unit 130, a thought process generating unit 140, a thought process selecting unit 150, and an instruction unit 160. The RAM 13 to the non-volatile memory 14 of the user assistance device 1 are provided with a thought process storage unit 200, which is an area for storing data related to thought processes.

[0020] The user input accepting unit 100 accepts an input of an inquiry related to the industrial machine 4 from a user. For example, the user input accepting unit 100 displays a message on the display device 70 prompting the user to input an inquiry related to the industrial machine 4. The user input accepting unit 100 may then accept an inquiry related to the industrial machine 4 input by the user from the input device 71. The user input accepting unit 100 may also accept an inquiry related to the industrial machine 4 input by the user via, for example, a voice input device (not shown). The user input accepting unit 100 outputs the accepted inquiry related to the industrial machine 4 to the prompt generating unit 110.

[0021] The prompt generation unit 110 generates a prompt that can be input to the interactive response system 2, based on an inquiry about the industrial machine 4 from a user accepted by the user input accepting unit 100. The prompt generation unit 110 may assign prompt identification information that allows the generated prompt to be uniquely identified. The prompt generation unit 110 may use an inquiry about the industrial machine 4 written in a natural language entered by a user as a prompt. Furthermore, the prompt may be generated by, for example, applying the inquiry information to a predetermined template corresponding to the inquiry information. The prompt generation unit 110 outputs the generated prompt to the transmission unit 120.

[0022] The transmission unit 120 transmits the prompt generated by the prompt generation unit 110 to the interactive response apparatus 2. Upon receiving the prompt from the transmission unit 120, the interactive response apparatus 2 generates a response to the prompt and transmits the generated response to the user assistance device 1.

[0023] The receiving unit 130 receives the response sent from the interactive response apparatus 2. Then, the receiving unit 130 outputs the received response to the thought process generating unit 140.

[0024] The thought process generation unit 140 creates thought process data that defines the thought process leading to a solution to the inquiry, based on the response from the interactive response system 2 received by the receiving unit 130. The created thought process data is then stored in the thought process storage unit 200. In the present disclosure, a thought process is a structured relationship between hypotheses and actions that can be considered from an inquiry related to the industrial machine 4 to a solution. This relationship includes a serial relationship and a parallel relationship.

[0025] FIG. 3 is a schematic diagram showing an example of a thought process. In FIG. 3 , square frames represent queries. Also, oval frames represent hypotheses, and hexagonal frames represent actions. For example, if a query is made that the operation screen is not displayed on the screen of the industrial machine 4, hypotheses such as the industrial machine 4 being in sleep mode or a power supply abnormality is occurring in the industrial machine 4 can be generated. To confirm whether the hypothesis that the industrial machine 4 is in sleep mode is correct, for example, it is understood that the action to perform is to operate the sleep wake key on the control panel. To confirm whether the hypothesis that a power supply abnormality is occurring is correct, it is understood that the action to perform is to check whether the power alarm lamp on the control panel is lit, and if not, to check the fuse of the power supply module. The thought process generation unit 140 generates thought process data indicating such a thought process for problem solving based on the response from the interactive response system 2. The thought process generation unit 140 analyzes sentences included in the response from the interactive response system 2, and if the response contains a phrase indicating a hypothesis, such as "it is possible that...", creates hypothesis data including the phrase. Furthermore, if the response contains phrases supporting an action, such as "Please do ..." or "Please do ...," behavioral data supporting the action is created. If phrases indicating hypotheses or actions are arranged in order, data corresponding to the phrases are connected in series. Furthermore, if the phrases are arranged selectively, data corresponding to the phrases are connected in parallel. In this way, the thought process generation unit 140 generates thought process data in a tree or graph format, with the query information as the root and interconnected hypothesis data and behavioral data as elements. This process can be achieved by preparing predetermined keywords in advance and analyzing the response through keyword matching. In this case, keyword matching can be performed efficiently by instructing the interactive response device 2 to respond in a predetermined format to the prompt. Alternatively, a process for generating thought process data from a natural language response from the interactive response device 2 can be appropriately implemented using, for example, known knowledge graph technology or natural language analysis technology using a machine learning model such as LSTM (Long Short-Term Memory).

[0026] If thought process data is already stored in the thought process storage unit 200, the thought process generation unit 140 determines the relationship between the already stored thought process data and the thought process data created this time. The thought process generation unit 140 identifies which hypothesis data or behavioral data of the already stored thought process data is the basis of the prompt that caused the current response from the interactive response device 2. For example, when sending a prompt, it records which hypothesis data or behavioral data of the thought process data the query is based on. Then, when a response is received and thought process data is created, the created thought process data can be linked in series to the hypothesis data or behavioral data that was the basis of the query.

[0027] The thought process selection unit 150 refers to the thought process data stored in the thought process storage unit 200 and selects an element of the thought process data that the user should select next. The thought process selection unit 150 may select hypothesis data or behavioral data that the user has not selected from the thought process data stored in the thought process storage unit 200 as an element of the thought process data that the user should select next. The thought process selection unit 150 may simultaneously select multiple hypothesis data that are connected in parallel. The thought process selection unit 150 may also simultaneously select multiple behavioral data that are connected in parallel. The thought process selection unit 150 exploratory and comprehensively selects the thought process data. The thought process selection unit 150 outputs the selected hypothesis data or behavioral data to the instruction unit 160. The thought process selection unit 150 also outputs to the prompt generation unit 110 a message that an input based on the selection by the thought process selection unit 150 will be performed.

[0028] The instruction unit 160 instructs the user on the hypothesis or action to be selected next, which has been selected by the thought process selection unit 150. The instruction unit 160 may instruct the user to select a hypothesis or action by displaying the user's hypothesis or action to be selected next on the display device 70. When the thought process selection unit 150 selects multiple hypotheses or actions, the instruction unit 160 may display the multiple actions and instruct the user to select a hypothesis or action from among them. The instruction unit 160 may further prompt the user to input an event that occurred as a result of the user performing the selected action.

[0029] Here, when the user selects a hypothesis or an action based on an instruction from the instruction unit 160, the user input accepting unit 100 accepts the selection as an input from the user. When the instruction unit 160 prompts the user to input an input related to the result of the action, the user input accepting unit 100 may further accept an input related to the result of the action by the user. The user input accepting unit 100 outputs the accepted input to the prompt generation unit 110. Furthermore, the user input accepting unit 100 may store information indicating that hypothesis data or action data related to the action selected by the user has been selected from the thought process data stored in the thought process storage unit 200.

[0030] When an input based on the selection by the thought process selection unit 150 is made, the prompt generation unit 110 generates a prompt to be transmitted to the interactive response system 2 based on the thought process data and the received user input. At this time, the prompt generation unit 110 may generate a prompt by applying, for example, each of the element data on the path from the inquiry information, which is the route of the thought process data, to the currently selected element data and the user input to a predetermined template. The prompt generation unit 110 outputs the generated prompt to the transmission unit 120.

[0031] The operation of the user assistance device 1 according to this embodiment will be described below with reference to FIGS. 4 to 8. FIG. 4 is a schematic diagram showing an example of a query screen displayed on the display device 70 of the user assistance device 1. In the example of FIG. 4, the user is unable to see the operation screen of the industrial machine 4 and has entered a query requesting advice on how to deal with the problem. This query is the first query, and at this stage, no thought process data has been stored in the thought process storage unit 200. In this case, the prompt generation unit 110 generates a prompt based on the query content as is. The transmission unit 120 then transmits the generated prompt to the interactive response system 2.

[0032] Assume that the interactive response device 2 responds to the query with the following response: "There are several possibilities. (1) The industrial machine 4 may be in sleep mode, (2) There may be an abnormality in the power supply of the industrial machine 4, (3) ... Which one would you like to check first?" The receiving unit 130 outputs the received response to the thought process generation unit 140. Based on this response, the thought process generation unit 140 generates thought process data such as the example shown in FIG. 5 and stores it in the thought process storage unit 200. The response indicates several hypotheses. Therefore, the thought process generation unit 140 creates hypothesis data for each hypothesis and generates thought process data by connecting the created multiple hypothesis data in parallel.

[0033] When the thought process generation unit 140 generates the thought process data, the thought process selection unit 150 refers to the generated thought process data. The thought process selection unit 150 selects a plurality of hypothesis data connected in parallel, and outputs an instruction to the instructing unit 160 to select a hypothesis from the selected hypothesis data. FIG. 6 is a schematic diagram showing an example of a hypothesis selection screen displayed by the instructing unit 160. In the example of FIG. 6 , the user selects (1) to verify the possibility that the industrial machine 4 is in sleep mode. The user input receiving unit 100 receives this selection as input and outputs it to the prompt generating unit 110.

[0034] Next, the prompt generation unit 110 creates a prompt based on the thought process data and the input received from the user. The prompt generation unit 110 may create a prompt by applying, for example, inquiry information such as "The operation screen is not displayed" and the currently selected hypothesis, "(1) There is a possibility that the industrial machine 4 is in sleep mode," to a predetermined template. For example, a prompt such as "The operation screen is not displayed. (1) I would like to verify the possibility that the industrial machine 4 is in sleep mode. Please instruct me on what to do" is created and transmitted to the interactive response system 2.

[0035] Assume that the interactive response device 2 returns a response to the query, including the sentence "To check whether the industrial machine 4 is in sleep mode, please operate the sleep wake key on the control panel," and a request to confirm whether the problem has been solved. The receiving unit 130 outputs the received response to the thought process generation unit 140. Based on this response, the thought process generation unit 140 creates behavioral data of "operate the sleep wake key." Then, it generates thought process data that is connected in series with the hypothesis data of "possibility of being in sleep mode" in the thought process data stored in the thought process storage unit 200. This hypothesis data is element data that caused the current response, and is assigned a flag indicating that it was selected last time. FIG. 7 is a schematic diagram showing an example of thought process data generated based on the current response.

[0036] When the thought process generation unit 140 generates the thought process data, the thought process selection unit 150 refers to the generated thought process data. The thought process selection unit 150 selects the action data "operate the sleep wake key" that is connected in series to the previously selected hypothesis data "(1) Possibility that the industrial machine 4 is in sleep mode," and outputs the selected action data to the instructing unit 160 to instruct the user. FIG. 8 is a schematic diagram showing an example of an action selection screen displayed by the instructing unit 160. In the example of FIG. 8 , the user is instructed to operate the sleep wake key on the control panel in accordance with the instruction. The user then performs the operation in accordance with the instruction, and inputs that it has been confirmed that the industrial machine 4 was not in sleep mode as a result. The user input acceptance unit 100 accepts this input and outputs it to the prompt generation unit 110.

[0037] The prompt generation unit 110 creates a prompt based on the thought process data and the input received from the user. The prompt generation unit 110 may create a prompt by applying, to a predetermined template, for example, inquiry information such as "The operation screen is not displayed," a previously selected hypothesis such as "(1) The industrial machine 4 may be in sleep mode," and a currently performed action such as "Operate the wake-up key on the control panel." For example, a prompt such as "The operation screen is not displayed. (1) We have verified the possibility that the industrial machine 4 may be in sleep mode. We have operated the wake-up key, but the situation has not improved" is created and transmitted to the interactive response system 2.

[0038] Here, it is assumed that the interactive response device 2 responds to the query with the sentence, "The problem was not solved. Please enter another query." As described above, a typical interactive response device 2 responds appropriately to consecutive queries, but does not have the function of returning to previously presented options and continuing the query. In this example, since verification based on the hypothesis "(1) The industrial machine 4 may be in sleep mode" has been completed, the interactive response device 2 does not respond to this query any further. When the response from the interactive response device 2 has been completed, the thought process generation unit 140 according to this embodiment instructs the thought process selection unit 150 to continue queries based on elements that have not yet been selected from the thought process data stored in the thought process storage unit 200. Based on this instruction, the thought process selection unit 150 refers to the thought process data stored in the thought process storage unit 200 and determines whether there is any element data that has not yet been selected. FIG. 9 is a schematic diagram showing the state of the thought process data at this stage. In the example of FIG. 9 , hypothesis data indicating "(1) Possibility that the industrial machine 4 is in sleep mode" and action data of "operate the sleep wake key" have already been selected, but other element data, such as hypothesis data of "(2) Possibility that an abnormality has occurred in the power supply of the industrial machine 4," have not been selected. In this case, the thought process selection unit 150 selects hypothesis data that has not yet been selected and instructs the instructing unit 160. FIG. 10 is a schematic diagram showing an example of an action selection screen displayed by the instructing unit 160. In the example of FIG. 10 , hypotheses excluding the hypothesis that has already been selected are presented to the user as options. In this way, the user can continue making an inquiry about the industrial machine 4 while following the options that have been presented in the past.

[0039] The user assistance device 1 according to the present embodiment, which has the above-described configuration, can efficiently respond to complex service inquiries that require exploratory thinking by utilizing the interactive response device 2, thereby reducing the effort required by the manufacturing staff. Furthermore, since a comprehensive search can be performed based on the responses from the interactive response device 2, a certain level of quality in the answers can be maintained.

[0040] Second Embodiment A user assistance device according to a second embodiment of the present disclosure will be described below. The user assistance device 1 according to this embodiment has the same hardware configuration as the user assistance device 1 according to the first embodiment.

[0041] 11 is a schematic block diagram showing functions of the user assistance device 1 according to the second embodiment of the present disclosure. Each function of the user assistance device 1 according to this embodiment is realized by the CPU 11 of the user assistance device 1 shown in FIG. 1 executing a system program and controlling the operation of each part of the user assistance device 1.

[0042] The user assistance device 1 according to this embodiment includes a user input receiving unit 100, a prompt generating unit 110, a transmitting unit 120, a receiving unit 130, a thought process generating unit 140, a thought process selecting unit 150, and an instruction unit 160. The RAM 13 to the non-volatile memory 14 of the user assistance device 1 are provided in advance with a thought process storage unit 200, which is an area for storing data related to thought processes, and a thought history storage unit 210, which stores the history of past problem solving attempts.

[0043] The user input receiving unit 100, prompt generating unit 110, transmitting unit 120, receiving unit 130, thought process generating unit 140, and instruction unit 160 provided in the user assistance device 1 of this embodiment have the same functions as those of the first embodiment.

[0044] The thought process selection unit 150 according to this embodiment determines whether the query has been resolved based on the user input received by the user input receiving unit 100. If the query has been resolved, the element data stored in the thought process storage unit 200, which are located between the root query information and the action data leading to the solution, are stored in the thought history storage unit 210 as thought process data leading to problem resolution. The thought process selection unit 150 then refers to the thought history storage unit 210 when selecting element data from the thought process data, and prioritizes selecting hypothesis data or action data that are highly correlated with solving similar problems. For example, the thought process selection unit 150 may perform statistical processing on the data stored in the thought history storage unit 210, and prioritize selecting hypothesis data or action data that most frequently led to a solution when similar problems were solved in the past. The thought process selection unit 150 may also select hypothesis data or action data so that the number of user actions corresponding to the thought process is minimized.

[0045] The user assistance device 1 according to the present embodiment having the above configuration can efficiently make inquiries about complex services that require exploratory thinking by utilizing the interactive response device 2. This is also expected to reduce the user's efforts.

[0046] Third Embodiment A user assistance device according to a third embodiment of the present disclosure will be described below. The user assistance device 1 according to this embodiment has the same hardware configuration as the user assistance device 1 according to the first embodiment.

[0047] 12 is a schematic block diagram showing functions of the user assistance device 1 according to the third embodiment of the present disclosure. Each function of the user assistance device 1 according to this embodiment is realized by the CPU 11 of the user assistance device 1 shown in FIG. 1 executing a system program and controlling the operation of each part of the user assistance device 1.

[0048] The user assistance device 1 according to this embodiment includes a user input receiving unit 100, a prompt generating unit 110, a transmitting unit 120, a receiving unit 130, a thought process generating unit 140, a thought process selecting unit 150, and an instruction unit 160, as well as a machine information acquiring unit 170 and a machine operating unit 180. The RAM 13 to the non-volatile memory 14 of the user assistance device 1 are provided with a thought process storage unit 200, which is an area for storing data related to thought processes.

[0049] The user input receiving unit 100, transmitting unit 120, receiving unit 130, thought process generating unit 140, and instruction unit 160 provided in the user assistance device 1 according to this embodiment have the same functions as those in the first embodiment.

[0050] The machine information acquisition unit 170 acquires machine information related to the industrial machine 4 that is the subject of an inquiry. The machine information acquired by the machine information acquisition unit 170 includes, for example, machine parameters, machine operation information, machine alarm history, operation history, and information related to machine specifications of the industrial machine 4. The machine information acquisition unit 170 outputs the acquired machine information to the prompt generation unit 110.

[0051] When creating a prompt to be sent to the interactive response system 2, the prompt generation unit 110 according to this embodiment further uses the machine information of the industrial machine 4 acquired by the machine information acquisition unit 170. The prompt generation unit 110 may apply the thought process data, the received user input, and the machine information to a predetermined template to generate a prompt.

[0052] When selecting behavioral data, the thought process selection unit 150 according to this embodiment determines whether the behavior can be automatically operated. For behaviors that can be automatically operated, the operations can be set in advance in a list format. Examples of behaviors that can be automatically operated include updating machine parameters such as the speed loop gain, current loop gain, position gain, load inertia ratio, and disturbance removal filter gain, and performing diagnostic operations such as rotating the spindle at a constant rotational speed, measuring feedback signals, and determining the spindle condition based on the analysis results. If the thought process selection unit 150 selects an action that can be automatically operated, it commands the machine operation unit 180 to execute the selected operation.

[0053] The machine operation unit 180 operates the industrial machine 4 based on the command from the thought process selection unit 150. Then, it commands the machine information acquisition unit 170 to acquire machine information relating to the state of the industrial machine 4 based on the results of the operation. Then, it presents the results to the user.

[0054] The user assistance device 1 according to the present embodiment, which has the above-described configuration, can efficiently make inquiries for complex service inquiries that require exploratory thinking by utilizing the interactive response device 2. By also utilizing information from the industrial machine 4, more efficient problem solving can be achieved. Furthermore, by automatically performing actions that can be performed automatically, a reduction in the user's effort is expected.

[0055] Although the embodiments of the present disclosure have been described in detail above, the present disclosure is not limited to the individual embodiments described above. Various additions, substitutions, modifications, partial deletions, etc. are possible in these embodiments without departing from the gist of the invention or the idea and intent of the present disclosure derived from the content described in the claims and their equivalents. For example, in the above-described embodiments, the order of each operation and the order of each process are shown as examples and are not limited to these. The same applies when numerical values ​​or mathematical expressions are used in the description of the above-described embodiments.

[0056] Supplementary notes relating to embodiments of the present disclosure are given below. (Supplementary Note 1) A user assistance device (1) according to one aspect of the present disclosure includes a thought process memory unit (200) that stores thought process data that defines a thought process leading to a solution to a query related to an industrial machine (4), a thought process selection unit (150) that selects an item to be selected by a user from the thought process data stored in the thought process memory unit (200), an instruction unit (160) that outputs an instruction based on the item selected by the thought process selection unit (150), a user input acceptance unit (100) that accepts input from a user, a prompt generation unit (110) that generates a prompt to be sent to an interactive response device (2) based on the thought process data and the accepted selection, a transmission unit (120) that transmits the prompt to the interactive response device (2), a reception unit (130) that receives a response to the prompt from the interactive response device (2), and a thought process generation unit (140) that creates thought process data that defines a thought process leading to a solution to the query based on the response and stores the data in the thought process memory unit (200).

[0057] (Supplementary Note 2) The thought process selection unit (150) included in a user assistance device (1) according to another aspect of the present disclosure selects an item to be selected by the user based on either information on the correlation with problem solving or information on the correlation with the number of user actions corresponding to the thought process. (Supplementary Note 3) The user assistance device (1) according to another aspect of the present disclosure further includes a thought history storage unit (210), and determines the correlation between the thought process and problem solving or the correlation with the number of user actions based on statistics related to the past thought history stored in the thought history storage unit (210).

[0058] (Supplementary Note 4) The thought process selection unit (150) included in the user assistance device (1) according to another aspect of the present disclosure presents a plurality of executable thought processes to the user and executes the thought process selected by the user. (Supplementary Note 5) The user assistance device (1) according to another aspect of the present disclosure further includes a machine information acquisition unit (170) that acquires machine information related to the industrial machine (4) that is the subject of an inquiry, and the prompt generation unit (110) further refers to the machine information when generating information to be sent to the interactive response device (2).

[0059] (Supplementary Note 6) The information acquired by the machine information acquisition unit (170) included in a user assistance device (1) according to another aspect of the present disclosure is at least one of information related to machine parameters, machine operation information, machine alarm history, operation history, and machine specifications. (Supplementary Note 7) A user assistance device (1) according to another aspect of the present disclosure further includes a machine operation unit (180) that automatically operates the industrial machine (4) that is the target of an inquiry, and automatically performs the operation if the thought process selected by the thought process selection unit (150) is an operation that can be performed by the machine operation unit (180). (Supplementary Note 8) The operation performed by the machine operation unit (180) included in a user assistance device (1) according to another aspect of the present disclosure is at least one of updating machine parameters and performing a diagnostic operation.

[0060] (Supplementary Note 9) A computer-readable recording medium according to one aspect of the present disclosure records a program for operating a computer as a thought process memory unit (200) that stores thought process data defining a thought process leading to a solution to a query related to an industrial machine (4); a thought process selection unit (150) that selects an item to be selected by a user from the thought process data stored in the thought process memory unit (200); an instruction unit (160) that outputs an instruction based on the item selected by the thought process selection unit (150); a user input acceptance unit (100) that accepts input from a user; a prompt generation unit (110) that generates a prompt to be sent to an interactive response device (2) based on the thought process data and the accepted selection; a transmission unit (120) that transmits the prompt to the interactive response device (2); a reception unit (130) that receives a response to the prompt from the interactive response device (2); and a thought process generation unit (140) that creates thought process data that defines a thought process leading to a solution to a query based on the response and stores the data in the thought process memory unit (200).

[0061] REFERENCE SIGNS LIST 1 User assistance device 2 Interactive response device 4 Industrial machine 5 Network 6 Fog computer 7 Cloud server 11 CPU 12 ROM 13 RAM 14 Non-volatile memory 15, 17, 18, 20 Interface 22 Bus 70 Display device 71 Input device 72 External device 100 User input reception unit 110 Prompt generation unit 120 Transmission unit 130 Reception unit 140 Thought process generation unit 150 Thought process selection unit 160 Instruction unit 170 Machine information acquisition unit 180 Machine operation unit 200 Thought process storage unit 210 Thought history storage unit

Claims

1. A user assistance device comprising: a thought process memory unit that stores thought process data defining the thought process leading to the resolution of an inquiry about industrial machinery; a thought process selection unit that selects an item to be selected by a user from the thought process data stored in the thought process memory unit; an instruction unit that outputs instructions based on the item selected by the thought process selection unit; a user input receiving unit that receives input from a user; a prompt generation unit that generates a prompt to be sent to an interactive response device based on the thought process data and the received selection; a transmission unit that transmits the prompt to the interactive response device; a receiving unit that receives a response to the prompt from the interactive response device; and a thought process generation unit that creates thought process data defining the thought process leading to the resolution of the inquiry based on the response, and stores the data in the thought process memory unit.

2. The user assistance device according to claim 1, wherein the thought process selection unit selects an item to be selected by the user based on either information regarding a correlation with problem solving or information regarding a correlation with the number of user actions corresponding to the thought process.

3. The user assistance device according to claim 2, further comprising a thought history memory unit, and determining the correlation between thought processes and problem solving or the correlation between the number of user actions based on statistics relating to past thought history stored in the thought history memory unit.

4. The user assistance device according to claim 1, wherein the thought process selection unit presents a plurality of executable thought processes to the user and executes the thought process selected by the user.

5. A user assistance device as described in claim 1, further comprising a machine information acquisition unit that acquires machine information related to the industrial machine that is the subject of an inquiry, and the prompt generation unit further refers to the machine information when generating information to be transmitted to the interactive response device.

6. The user assistance device according to claim 5, wherein the information acquired by the machine information acquisition unit is at least one of information relating to machine parameters, machine operation information, machine alarm history, operation history, and machine specifications.

7. A user assistance device as described in claim 1, further comprising a machine operation unit that automatically operates the industrial machine that is the subject of a query, and which automatically performs the operation if the thought process selected by the thought process selection unit is an operation that can be executed by the machine operation unit.

8. The user assistance device according to claim 7, wherein the operation performed by the machine operation unit is at least one of updating machine parameters and executing a diagnostic operation.

9. A computer-readable recording medium having recorded thereon a program for causing a computer to operate as: a thought process memory unit for storing thought process data defining the thought process leading to the resolution of an inquiry about industrial machinery; a thought process selection unit for selecting an item to be selected by a user from the thought process data stored in the thought process memory unit; an instruction unit for outputting instructions based on the item selected by the thought process selection unit; a user input receiving unit for receiving input from a user; a prompt generation unit for generating a prompt to be sent to an interactive response device based on the thought process data and the received selection; a transmission unit for transmitting the prompt to the interactive response device; a receiving unit for receiving a response to the prompt from the interactive response device; and a thought process generation unit for creating thought process data defining the thought process leading to the resolution of an inquiry based on the response and storing the data in the thought process memory unit.

Images