Voice recognition model switching device and computer-readable recording medium

Abstract

A voice recognition model switching device according to the present disclosure comprises: a data acquisition unit that acquires information relating to the state of an industrial machine operated on the basis of a voice command; a model selection unit that, from a model storage unit which holds a plurality of voice recognition models, selects a voice recognition model corresponding to the information relating to the state as acquired by the data acquisition unit; and a model switching unit that switches to the voice recognition model selected by the model selection unit so as to use the voice recognition model to recognize the voice command.

Description

Voice recognition model switching device and computer-readable recording medium

[0001] The present disclosure relates to a voice recognition model switching device and a computer-readable recording medium.

[0002] At manufacturing sites where industrial machines such as machine tools and robots are installed, the operation of the industrial machines may be controlled based on voice commands from users (see, for example, Patent Document 1). A voice recognition model used to recognize voice commands analyzes input voice and outputs a character string of the voice. This voice recognition model uses a model suited to the usage environment.

[0003] Japanese Patent Application Laid-Open No. 2020-042420

[0004] Using a large speech recognition model that can recognize a variety of voices results in slower response speeds and requires more resources. Conversely, using a small speech recognition model results in a lower recognition rate. It is difficult to pre-select a single speech recognition model that can handle the various situations that may occur on the manufacturing floor. A speech recognition system that can flexibly adapt to different situations is desired on the manufacturing floor.

[0005] The voice recognition model switching device according to the present disclosure solves the above-mentioned problems by switching voice recognition models depending on the situation, such as the usage environment and the work content.

[0006] One aspect of the present disclosure is a voice recognition model switching device including: a data acquisition unit that acquires information related to the status of industrial machinery operated based on voice commands; a model selection unit that selects a voice recognition model corresponding to the information related to the status acquired by the data acquisition unit from a model storage unit that stores multiple voice recognition models; and a model switching unit that switches the voice recognition model selected by the model selection unit to be used for recognizing the voice commands.

[0007] Fig. 1 is a schematic hardware configuration diagram of a voice recognition model switching device according to an embodiment of the present disclosure; Fig. 2 is a block diagram showing schematic functions of a voice recognition model switching device according to a first embodiment; Fig. 3 is a table diagram showing examples of a plurality of voice recognition models stored in a model storage unit; Fig. 4 is a table diagram showing another example of a plurality of voice recognition models stored in a model storage unit; Fig. 5 is a block diagram showing schematic functions of a voice recognition model switching device according to another 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] [First Embodiment] Fig. 1 is a schematic hardware configuration diagram showing the main parts of a voice recognition model switching device according to a first embodiment of the present disclosure. The voice recognition model switching device 1 according to this embodiment can be implemented, for example, on a control device that controls industrial machinery. The voice recognition model switching device 1 can also be implemented, for example, on a personal computer attached to the control device, or on a computer such as a personal computer, cell computer, fog computer 6, or cloud server 7 connected to the control device via a wired or wireless network. This embodiment shows an example in which the voice recognition model switching 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 voice recognition model switching device 1 according to this embodiment is a processor that controls the entire voice recognition model switching device 1. The CPU 11 reads a system program stored in the ROM 12 via the bus 22, and controls the entire voice recognition model switching device 1 in accordance with the system program. The RAM 13 temporarily stores temporary calculation data, display data, various data acquired from outside, and the like.

[0012] The nonvolatile 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 power to the voice recognition model switching device 1 is turned off. The nonvolatile 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 control device 3 that controls the industrial machine 4 or other devices via the network 5. The programs and data stored in the nonvolatile memory 14 may be expanded into the RAM 13 when executed / used. In addition, various system programs such as known analysis programs are written in the ROM 12 in advance.

[0013] The interface 15 is an interface for connecting the CPU 11 of the voice recognition model switching 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 or edited within the voice recognition model switching 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 voice recognition model switching 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. The network 5 is connected to a control device 3 that controls at least one industrial machine 4, a fog computer 6, a cloud server 7, etc., and exchanges data with the voice recognition model switching device 1.

[0015] The display device 70 displays data and the like obtained as a result of executing various data and programs loaded into the memory, output via the interface 17. An input device 71, which is composed of at least one input device such as a keyboard, a pointing device, a voice input device, an imaging device, etc., passes commands, data, etc. based on user operations to the CPU 11 via the interface 18.

[0016] The voice recognition model switching device 1 according to this embodiment switches the voice recognition model used for recognizing voice commands in a control device 3 that controls industrial machinery 4. The control device 3 accepts voice commands from a user and performs voice recognition of the voice commands. The voice recognition model switching device 1 supplies the voice recognition model used for this voice recognition to the control device 3 via a network 5. The control device 3 uses the voice recognition model supplied from the voice recognition model switching device 1 for voice recognition of the voice commands from the user.

[0017] 2 is a schematic block diagram showing functions of the voice recognition model switching device 1 according to the first embodiment of the present disclosure. Each function of the voice recognition model switching device 1 according to this embodiment is realized by the CPU 11 included in the voice recognition model switching device 1 shown in FIG. 1 executing a system program and controlling the operation of each part of the voice recognition model switching device 1.

[0018] The voice recognition model switching device 1 of this embodiment includes a data acquisition unit 100, a model selection unit 110, and a model switching unit 120. The RAM 13 to the nonvolatile memory 14 of the voice recognition model switching device 1 also include a model storage unit 200, which is an area in which a plurality of voice recognition models are stored in advance.

[0019] The data acquisition unit 100 acquires information related to the status of the industrial machine 4 from the control device 3 of the industrial machine 4, which is operated based on voice commands. Examples of information related to the status of the industrial machine 4 include information related to the operating environment of the industrial machine 4. Examples of information related to the operating environment of the industrial machine 4 include the volume of noise, such as machine operation sounds and other people's voices, around the area where the industrial machine 4 is installed. When the ambient noise is loud, it may be difficult to recognize voice commands spoken by the user of the industrial machine 4. Another example of information related to the operating environment of the industrial machine 4 is the performance of a voice input device (not shown), such as a microphone, that acquires voice commands for controlling the industrial machine 4. The performance of the voice input device can affect the recognition of voice commands spoken by the user of the industrial machine 4. Another example of information related to the operating environment of the industrial machine 4 is the load status of the control device 3 that controls the industrial machine 4. The level of load on the control device 3 that performs voice recognition and the amount of memory usage may affect the operating speed of the voice recognition process. In this way, information related to the usage environment of the industrial machinery 4 may be information related to the internal and external environments of the control device 3 and the industrial machinery 4 that affect the recognition accuracy and recognition speed of voice commands related to the operation of the industrial machinery 4.

[0020] The information related to the status of the industrial machine 4 may be, for example, information related to the work content of the industrial machine 4. Examples of the information related to the work content of the industrial machine 4 include information indicating the type of work, such as setting work, setup work, automatic operation, and inspection work. There is a desire to prioritize recognition of frequently used words and important words depending on such differences in work content. Furthermore, an example of the information related to the work content of the industrial machine 4 is information indicating the operating state of the industrial machine 4. For example, the set of voice commands used for operation may differ depending on whether a tool is being replaced, whether a workpiece is being replaced, or whether a workpiece and a tool are in contact and machining is being performed. In this way, the information related to the work content of the industrial machine 4 may be information related to the types of voice commands used to operate the industrial machine or information related to the states of the control device 3 and the industrial machine 4 in which the types of voice commands that need to be recognized with high accuracy change.

[0021] The data acquisition unit 100 acquires information relating to the status of the industrial machinery 4 from, for example, information set in the industrial machinery 4 and the control device 3, information indicating the operating status of a process running on the control device 3, the type of screen being displayed on a display device (not shown) of the control device 3, feedback information from drive units (not shown) such as motors, information indicating the status of each signal input to the control device 3, information acquired from sensors attached to the industrial machinery 4, etc. Then, the acquired information relating to the status of the industrial machinery 4 is output to the model selection unit 110.

[0022] The model selection unit 110 selects a speech recognition model corresponding to the situation-related information acquired by the data acquisition unit 100 from multiple speech recognition models stored in the model storage unit 200. Multiple speech recognition models are stored in advance in the model storage unit 200. Each speech recognition model is stored in association with information related to performance corresponding to the respective situation, for example. FIG. 3 is a table diagram showing examples of speech recognition models stored in the model storage unit. In the example of FIG. 3, model A for spontaneous speech has high noise resistance for speech recognition, but requires large memory usage and a high execution load. Model C for spontaneous speech has low memory usage and a low execution load, but requires low noise resistance for speech recognition. In the case where such models are stored, the model selection unit 110 selects model A for spontaneous speech when the information related to the situation of the industrial machine 4 indicates that the ambient noise is loud. Furthermore, the model selection unit 110 selects model C for spontaneous speech when the information related to the situation of the industrial machine 4 indicates that the ambient noise is quiet. On the other hand, if the information related to the status of the industrial machine 4 indicates high memory usage, the model selection unit 110 selects model C for spontaneous speech, and if the information related to the status of the industrial machine 4 indicates low memory usage, the model selection unit 110 selects model A for spontaneous speech. Priorities may be assigned to the information related to the status of the industrial machine 4 taken into consideration when selecting a model. For example, in the above example, memory usage and execution load status may be determined with priority over noise resistance. This is because speech recognition itself will not be possible unless sufficient resources are secured to execute speech recognition processing using a speech recognition model. Such priorities may be set in advance at the design stage. In addition to this method, for example, information indicating the status of each industrial machine 4 may be quantified and weighted, and a speech recognition model may be selected using an evaluation value calculated from the quantified information.

[0023] FIG. 4 is a table diagram showing another example of the voice recognition models stored in the model storage unit. In the example of FIG. 4, the numerical model A is a model designed to be able to recognize numerical words with high accuracy. The inspection model A is a model designed to be able to recognize words frequently used in inspection work with high accuracy. The general model is designed to moderately recognize words commonly used in manufacturing sites without being specialized for a specific work. When such models are stored, the model selection unit 110 selects the numerical model A when the information related to the status of the industrial machine 4 indicates that the current user is performing setting work such as an offset value. The model selection unit 110 also selects the inspection model A when the information related to the status of the industrial machine 4 indicates that inspection work is currently being performed.

[0024] The model selection unit 110 can also select a model by combining information related to the usage environment of the industrial machine 4 and information related to the work content of the work performed by the industrial machine 4, which are included in the information related to the status of the industrial machine 4. For example, a plurality of models corresponding to the usage environment for each work content are prepared for storage in the model storage unit 200. Then, based on the information related to the usage environment of the industrial machine 4 and the work content of the work performed by the industrial machine 4 acquired by the data acquisition unit 100, a voice recognition model suitable for such a situation can be selected from the plurality of prepared models.

[0025] The model selection unit 110 outputs the model selected in this manner to the model switching unit 120 .

[0026] The model switching unit 120 switches the voice recognition model selected by the model selection unit 110 to be used for voice recognition of voice commands. The model switching unit 120 instructs the control device 3 that controls, for example, the industrial machine 4, to transmit the voice recognition model selected by the model selection unit 110 via the network 5 and use it for voice recognition of voice commands. Then, upon receiving this instruction, the control device 3 uses the voice recognition model sent from the model switching unit 120 for recognizing voice commands received from the user thereafter.

[0027] The voice recognition model switching device 1 according to this embodiment having the above configuration can select a voice recognition model according to the status of the industrial machine 4 and use the selected voice recognition model to recognize voice commands. As a result, it is expected that the stability of the voice recognition operation according to the status of the industrial machine 4 can be maintained, and the accuracy of voice recognition and response speed can be improved.

[0028] Second Embodiment A voice recognition model switching device according to a second embodiment of the present disclosure will be described below. The voice recognition model switching device 1 according to this embodiment has the same hardware configuration as the voice recognition model switching device 1 according to the first embodiment.

[0029] Like the voice recognition model switching device 1 according to the first embodiment, the voice recognition model switching device 1 according to this embodiment includes a data acquisition unit 100, a model selection unit 110, and a model switching unit 120. The RAM 13 to the nonvolatile memory 14 of the voice recognition model switching device 1 also include a model storage unit 200, which is an area in which a plurality of voice recognition models are stored in advance.

[0030] The function of the model switching unit 120 included in the speech recognition model switching device 1 according to this embodiment is similar to that of the model switching unit 120 according to the first embodiment.

[0031] The data acquisition unit 100 acquires information related to the status of the industrial machine 4 from the control device 3 of the industrial machine 4, which is operated based on a voice command. The data acquisition unit 100 according to this embodiment accepts designation of a voice recognition model by a voice command from a user of the industrial machine 4 as information related to the status of the industrial machine 4. This designation of the voice recognition model may directly specify the name or identification information of the model. For example, if the voice recognition model illustrated in FIG. 4 is stored in the model storage unit 200, a voice command such as "switch the voice recognition model to numerical model A" may be accepted as information related to the status of the industrial machine 4. Furthermore, this designation of the voice recognition model may indirectly specify a change of the model. For example, if the voice recognition model illustrated in FIG. 3 is stored in the model storage unit 200, a voice command such as "switch to a voice recognition model with higher noise resistance" may be accepted as information related to the status of the industrial machine 4. At this time, information indicating which voice recognition model is currently being used in the control device 3 may also be accepted. The data acquisition unit 100 outputs the received designation of the voice recognition model to the model selection unit 110 as information relating to the status of the industrial machine 4 .

[0032] The model selection unit 110 selects a speech recognition model corresponding to the information related to the situation acquired by the data acquisition unit 100 from among multiple speech recognition models stored in the model storage unit 200. When the model selection unit 110 according to this embodiment receives a designation of a speech recognition model as information related to the situation of the industrial machine 4, it selects the designated speech recognition model from among multiple speech recognition models stored in the model storage unit 200. When the name or identification information of the speech recognition model is directly designated, the model selection unit 110 selects the designated speech recognition model. Furthermore, when the designation is indirectly related to the performance of the speech recognition model, the model selection unit 110 compares the designation with the currently used speech recognition model and selects a speech recognition model that satisfies the designated performance.

[0033] The model selection unit 110 outputs the selected model to the model switching unit 120. Then, the model switching unit 120 switches to use the selected voice recognition model for voice recognition of the voice command.

[0034] The voice recognition model switching device 1 according to this embodiment having the above configuration can switch voice recognition models based on voice commands from the user. As a result, it becomes possible to switch to an appropriate voice recognition model at the will of the user who is aware of the status of the industrial machine 4.

[0035] [Other Embodiments] In the above-described embodiment, the control device 3 is configured to perform voice recognition of voice commands. However, as shown in Fig. 5, for example, the functions of the voice recognition model switching device 1 and the voice recognition unit 130 may be provided on a PC installed alongside the control device 3. In this case, the control device 3 is operated based on the voice commands recognized on the PC. The model switching unit 120 then switches the voice recognition model used in the voice recognition unit 130.

[0036] In the above-described embodiment, the model storage unit 200 is provided on the voice recognition model switching device 1. However, the model storage unit 200 may be provided on another device, such as the fog computer 6 or the cloud server 7. In this case, the voice recognition model switching device 1 refers to the model storage unit 200 via the network 5. With this configuration, voice recognition models can be collectively managed at a manufacturing site where many voice recognition model switching devices 1, control devices 3, and industrial machines 4 are installed.

[0037] 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.

[0038] The following are supplementary notes related to embodiments of the present disclosure. (Supplementary Note 1) A voice recognition model switching device (1) according to one aspect of the present disclosure includes a data acquisition unit (100) that acquires information related to the status of an industrial machine (4) operated based on a voice command, a model selection unit (110) that selects a voice recognition model corresponding to the information related to the status acquired by the data acquisition unit (100) from a model storage unit (200) that stores multiple voice recognition models, and a model switching unit (120) that switches the voice recognition model selected by the model selection unit (110) to be used for recognizing the voice command.

[0039] (Supplementary Note 2) The information related to the status of the industrial machine (4) acquired by a voice recognition model switching device (1) according to another aspect of the present disclosure is at least one of information related to the usage environment of the industrial machine (4) and information related to the work content of the work performed on the industrial machine (4). (Supplementary Note 3) The information related to the status of the industrial machine (4) acquired by a voice recognition model switching device (1) according to another aspect of the present disclosure is the specification of a voice recognition model by a voice command from a user of the industrial machine (4).

[0040] (Supplementary Note 4) A computer-readable recording medium according to one aspect of the present disclosure records a program that causes a computer to operate as a data acquisition unit (100) that acquires information related to the status of an industrial machine (4) operated based on a voice command, a model selection unit (110) that selects a voice recognition model corresponding to the information related to the status acquired by the data acquisition unit (100) from a model storage unit (200) that stores multiple voice recognition models, and a model switching unit (120) that switches the voice recognition model selected by the model selection unit (110) to be used for recognizing the voice command.

[0041] REFERENCE SIGNS LIST 1 Speech recognition model switching device 3 Control 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 Data acquisition unit 110 Model selection unit 120 Model switching unit 130 Speech recognition unit 200 Model storage unit

Claims

1. A voice recognition model switching device comprising: a data acquisition unit that acquires information related to the status of industrial machinery operated based on voice commands; a model selection unit that selects a voice recognition model corresponding to the information related to the status acquired by the data acquisition unit from a model storage unit that stores multiple voice recognition models; and a model switching unit that switches the voice recognition model selected by the model selection unit to be used for recognizing the voice commands.

2. A voice recognition model switching device according to claim 1, wherein the information relating to the status of the industrial machine is at least one of information relating to the operating environment of the industrial machine and information relating to the work content of the work performed on the industrial machine.

3. The voice recognition model switching device according to claim 1, wherein the information relating to the status of the industrial machine is a voice recognition model designated by a voice command from a user of the industrial machine.

4. A computer-readable recording medium having recorded thereon a program that causes a computer to operate as: a data acquisition unit that acquires information related to the status of industrial machinery operated based on voice commands; a model selection unit that selects a voice recognition model corresponding to the information related to the status acquired by the data acquisition unit from a model storage unit that stores multiple voice recognition models; and a model switching unit that switches the voice recognition model selected by the model selection unit to be used for recognizing the voice commands.

Images