Job instruction generation system, job instruction generation program and voice operation system
The job instruction generation system addresses voice recognition errors in smart speakers by correcting text data errors, enhancing the reliability of image forming apparatus operation.
Patent Information
- Application Number
- JP2023086689
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2023-05-26
- Publication Date
- 2024-12-06
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Existing voice operation systems for image forming apparatuses via smart speakers face compatibility issues due to voice recognition errors, leading to unintended operation of the devices.
A job instruction generation system that manages error correction information to correct voice recognition errors in text data received from smart speakers, generating interpretable job instructions based on corrected text data.
Improves the likelihood that image forming apparatuses operate as intended by users by correcting voice recognition errors, ensuring accurate interpretation and execution of user commands.
Smart Images

Figure 2024169870000001_ABST
Abstract
Description
[Technical field]
[0001] The present invention relates to a job instruction generating system, a job instruction generating program, and a voice operation system that generate job instructions that can be interpreted by an image forming apparatus based on text data generated by a voice receiving device. [Background technology]
[0002] Conventionally, a voice operation system that operates an image forming apparatus via a smart speaker as a voice reception device is known (for example, see Patent Document 1). In the voice operation system described in Patent Document 1, a cloud service device connected to an image forming apparatus via a network such as a LAN (Local Area Network) generates job instructions that can be interpreted by the image forming apparatus based on a voice input to the smart speaker, and transmits the generated instructions to the image forming apparatus. [Prior art documents] [Patent documents]
[0003] [Patent Document 1] JP 2020-087347 A Summary of the Invention [Problem to be solved by the invention]
[0004] However, in the voice operation system described in Patent Document 1, the cloud service device converts voice data indicating a voice input to a smart speaker into text data by voice recognition, which is problematic in that the system is not compatible with smart speakers that convert voice data into text data by voice recognition. Also, the voice operation system described in Patent Document 1 has a problem that the image forming device does not operate as intended by the user if there is an error in the voice recognition.
[0005] Therefore, an object of the present invention is to provide a job command generation system, a job command generation program, and a voice operation system that can improve the likelihood that an image forming apparatus will operate as intended by a user when a voice reception device that converts voice data into text data through voice recognition is used. [Means for solving the problem]
[0006] The job instruction generation system of the present invention is characterized in that it manages error correction information for correcting errors in voice recognition made by a voice receiving device that converts voice data representing received voice into text data through voice recognition, corrects the errors in the text data received from the voice receiving device using the error correction information, and generates job instructions that can be interpreted by an image forming device based on the text data with the errors corrected.
[0007] With this configuration, the job instruction generation system of the present invention uses error correction information to correct voice recognition errors in text data received from a voice reception device that converts voice data indicating the received voice into text data through voice recognition, and generates job instructions that can be interpreted by the image forming device based on the text data from which the voice recognition errors have been corrected, thereby improving the likelihood that the image forming device will operate as intended by the user when a voice reception device that converts voice data into text data through voice recognition is used.
[0008] The job instruction generation system of the present invention may manage the error correction information for each type of voice receiving device, and correct the errors in the text data received from the voice receiving device using the error correction information corresponding to the type of voice receiving device.
[0009] With this configuration, the job instruction generation system of the present invention corrects voice recognition errors in text data received from a voice reception device using error correction information corresponding to the type of the voice reception device, thereby improving the likelihood that the image forming apparatus will operate as intended by the user when a voice reception device that converts voice data into text data through voice recognition is used.
[0010] The job instruction generation system of the present invention may manage the correspondence between the type of voice receiving device and identification information of the user of the voice receiving device, and correct the errors in the text data received from the voice receiving device using the error correction information corresponding to the type of voice receiving device that is associated with the identification information received from the voice receiving device in relation to the text data.
[0011] With this configuration, the job instruction generation system of the present invention corrects voice recognition errors in text data received from a voice receiving device using error correction information corresponding to the type of voice receiving device that is associated with the user's identification information received from the voice receiving device in relation to the text data, thereby improving the likelihood that the image forming apparatus will operate as intended by the user even if the type of voice receiving device is not notified from the voice receiving device.
[0012] The job instruction generation program of the present invention is characterized in that it causes a computer to perform the following operations: managing error correction information for correcting errors in voice recognition by a voice receiving device that converts voice data indicating received voice into text data through voice recognition; correcting the errors in the text data received from the voice receiving device using the error correction information; and generating job instructions that can be interpreted by an image forming device based on the text data with the errors corrected.
[0013] With this configuration, a computer executing the job instruction generation program of the present invention uses error correction information to correct voice recognition errors in text data received from a voice reception device that converts voice data indicating received voice into text data through voice recognition, and generates job instructions that can be interpreted by the image forming device based on the text data from which the voice recognition errors have been corrected, thereby improving the likelihood that the image forming device will operate as intended by the user when a voice reception device that converts voice data into text data through voice recognition is used.
[0014] The voice operation system of the present invention comprises a voice reception device that converts voice data indicating received voice into text data through voice recognition, and a job instruction generation system that generates job instructions that can be interpreted by an image forming device, wherein the job instruction generation system manages error correction information for correcting errors in the voice recognition by the voice reception device, the job instruction generation system corrects the errors in the text data received from the voice reception device using the error correction information, and the job instruction generation system generates the instructions based on the text data with the errors corrected.
[0015] With this configuration, the voice operation system of the present invention uses error correction information to correct voice recognition errors in text data received by the job instruction generation system from a voice acceptance device that converts voice data indicating received voice into text data through voice recognition, and the job instruction generation system generates job instructions that can be interpreted by the image forming device based on the text data from which the voice recognition errors have been corrected, thereby improving the likelihood that the image forming device will operate as intended by the user when a voice acceptance device that converts voice data into text data through voice recognition is used. Effect of the Invention
[0016] The job command generation system, job command generation program, and voice operation system of the present invention can improve the likelihood that an image forming device will operate as intended by the user when a voice reception device is used that converts voice data into text data through voice recognition. [Brief description of the drawings]
[0017] [Figure 1] 1 is a block diagram of a voice operation system according to an embodiment of the present invention. [Diagram 2] FIG. 2 is a block diagram of the smart speaker shown in FIG. 1. [Diagram 3] FIG. 2 is a block diagram of the job command generation system shown in FIG. 1 when configured by one computer. [Figure 4] FIG. 2 is a block diagram of the image forming apparatus shown in FIG. 1 when it is an MFP. [Diagram 5] 11 is a flowchart of an example of the operation of the smart speaker shown in FIG. 2 when accepting voice operation for operating the image forming apparatus. [Figure 6] 6 is a flowchart of an example of the operation of a smart speaker when accepting voice operation for operating an image forming apparatus, different from the example shown in FIG. 5. [Figure 7] 4 is a flowchart of the operation of the job instruction generation system shown in FIG. 3 when text data is received from a smart speaker. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0018] Hereinafter, an embodiment of the present invention will be described with reference to the drawings.
[0019] First, a configuration of a voice operation system according to an embodiment of the present invention will be described.
[0020] FIG. 1 is a block diagram of a voice operation system 10 according to the present embodiment.
[0021] As shown in Fig. 1, the voice operation system 10 includes a smart speaker 20 as a voice reception device that receives voice input from a user. The voice operation system 10 may include at least one smart speaker having a similar configuration to the smart speaker 20 in addition to the smart speaker 20. The smart speaker converts voice data indicating the received voice into text data by voice recognition.
[0022] The voice operation system 10 includes a job instruction generation system 30 that generates job instructions (hereinafter referred to as "job instructions") that can be interpreted by an image forming device described below, based on text data generated by a smart speaker. The job instruction generation system 30 may be configured by one computer or multiple computers.
[0023] The voice operation system 10 includes an image forming device 40, such as a dedicated printer or an MFP (Multifunction Peripheral). The voice operation system 10 may include at least one other image forming device having a similar configuration to the image forming device 40.
[0024] In the voice operation system 10, the smart speaker can communicate with the job instruction generation system 30 via a network 11 such as a LAN (Local Area Network) or the Internet.
[0025] In the voice operation system 10, a job command generating system 30 can communicate with the image forming apparatus via a network 11, for example.
[0026] FIG. 2 is a block diagram of the smart speaker 20.
[0027] As shown in Figure 2, the smart speaker 20 includes an operation unit 21 which is an operating device such as a button through which various operations are input, a speaker 22, a microphone 23, a communication unit 24 which is a communication device that communicates with external devices via a network such as a LAN or the Internet, or directly via a wired or wireless connection without using a network, a memory unit 25 which is a non-volatile memory device such as a semiconductor memory or an HDD (Hard Disk Drive) that stores various types of information, and a control unit 26 which controls the entire smart speaker 20.
[0028] The storage unit 25 stores a text data generation program 25a for generating text data based on voice data. The text data generation program 25a may be installed in the smart speaker 20 during the manufacturing stage of the smart speaker 20, or may be additionally installed in the smart speaker 20 from an external storage medium such as a USB (Universal Serial Bus) memory, or may be additionally installed in the smart speaker 20 from a network.
[0029] The storage unit 25 stores a text data conversion model 25b, which is a machine learning model for converting voice data into text data by voice recognition.
[0030] The storage unit 25 stores speaker type information 25c indicating the type of the smart speaker 20. As the type of the smart speaker 20, the model of the smart speaker 20 may be adopted, or the type of the manufacturer of the smart speaker 20 may be adopted.
[0031] The storage unit 25 stores user identification information 25d as identification information of the user of the smart speaker 20. The user identification information 25d may be, for example, an email address of the user of the smart speaker 20.
[0032] The control unit 26 includes, for example, a CPU (Central Processing Unit), a ROM (Read Only Memory) that stores programs and various data, and a RAM (Random Access Memory) that serves as a memory used as a working area for the CPU of the control unit 26. The CPU of the control unit 26 executes the programs stored in the storage unit 25 or the ROM of the control unit 26.
[0033] The control unit 26 executes the text data generating program 25a to realize a text data generating unit 26a that generates text data based on the voice data.
[0034] FIG. 3 is a block diagram of a job instruction generating system 30 configured by one computer.
[0035] As shown in FIG. 3, the job command generation system 30 includes an operation unit 31 which is an operation device such as a keyboard or mouse through which various operations are input, a display unit 32 which is a display device such as an LCD (Liquid Crystal Display) that displays various information, a communication unit 33 which is a communication device that communicates with external devices via a network such as a LAN or the Internet, or directly by wired or wireless means without going through a network, a memory unit 34 which is a non-volatile memory device such as a semiconductor memory or HDD that stores various information, and a control unit 35 which controls the entire job command generation system 30.
[0036] The storage unit 34 stores a job command generating program 34a for generating job commands based on text data. The job command generating program 34a may be installed in the job command generating system 30 during the manufacturing stage of the job command generating system 30, or may be additionally installed in the job command generating system 30 from an external storage medium such as a USB memory, or may be additionally installed in the job command generating system 30 from a network.
[0037] The storage unit 34 stores user-speaker correspondence information 34b indicating the correspondence between user identification information as identification information of a user and speaker type information indicating the type of smart speaker used by the user. In other words, the job command generation system 30 manages the correspondence between the type of smart speaker and the user identification information of the user of the smart speaker. The control unit 35 may register the correspondence between the user identification information and the speaker type information in the user-speaker correspondence information 34b in response to an instruction from the user, or may register the correspondence between the user identification information and the speaker type information in the user-speaker correspondence information 34b upon notification from a smart speaker that stores such information.
[0038] The storage unit 34 stores an error correction model 34c, which is a machine learning model serving as error correction information for correcting errors in voice recognition by a smart speaker. The storage unit 34 can store at least one error correction model other than the error correction model 34c. The storage unit 34 stores an error correction model for each type of smart speaker. That is, the job command generation system 30 manages an error correction model for each type of smart speaker. The error correction model may be generated by machine learning using a large amount of learning data including text data generated by a smart speaker through voice recognition and correct answer data for this text data.
[0039] The storage unit 34 stores a job command generation model 34d, which is a machine learning model for interpreting text data and generating job commands.
[0040] The control unit 35 includes, for example, a CPU, a ROM that stores programs and various data, and a RAM as a memory used as a working area for the CPU of the control unit 35. The CPU of the control unit 35 executes the programs stored in the storage unit 34 or the ROM of the control unit 35.
[0041] The control unit 35 executes the job command generating program 34a to realize a job command generating unit 35a that generates job commands based on text data.
[0042] FIG. 4 is a block diagram of the image forming device 40 in the case of an MFP.
[0043] As shown in FIG. 4, image forming apparatus 40 includes an operation unit 41 which is an operation device such as buttons through which various operations are input, a display unit 42 which is a display device such as an LCD that displays various information, a printer 43 which is a printing device that prints images on a recording medium such as paper, a scanner 44 which is a reading device that reads images from a document, a communication unit 45 which is a communication device that communicates with an external device via a network such as a LAN or the Internet, or directly by wire or wirelessly without using a network, a fax communication unit 46 which is a fax device that communicates with an external facsimile machine (not shown) via a communication line such as a public telephone line, a memory unit 47 which is a non-volatile memory device such as a semiconductor memory or HDD that stores various information, and a control unit 48 which controls the entire image forming apparatus 40.
[0044] The storage unit 47 stores a job execution program 47a for executing a job. The job execution program 47a may be installed in the image forming apparatus 40 during the manufacturing stage of the image forming apparatus 40, or may be additionally installed in the image forming apparatus 40 from an external storage medium such as a USB memory, or may be additionally installed in the image forming apparatus 40 from a network.
[0045] The control unit 48 includes, for example, a CPU, a ROM that stores programs and various data, and a RAM as a memory used as a working area for the CPU of the control unit 48. The CPU of the control unit 48 executes the programs stored in the storage unit 47 or the ROM of the control unit 48.
[0046] The control unit 48 executes the job execution program 47a to thereby realize a job execution unit 48a that executes a job.
[0047] Next, the operation of the voice operation system 10 when the image forming apparatus is operated via a smart speaker will be described.
[0048] In the following description, a smart speaker that accepts voice operations for operating an image forming apparatus is assumed to be the smart speaker 20. In addition, a description will be given assuming that an image forming apparatus that is the target of the voice operations accepted by the smart speaker 20 is the image forming apparatus 40.
[0049] First, the operation of the smart speaker 20 when accepting voice operations for operating the image forming device 40 will be described.
[0050] FIG. 5 is a flowchart of an example of the operation of the smart speaker 20 when accepting voice operation for operating the image forming apparatus 40.
[0051] The user can input voice indicating the operation content for the image forming device 40 into the microphone 23 of the smart speaker 20.
[0052] When voice is input to the microphone 23, the text data generation unit 26a of the smart speaker 20 accepts the voice input to the microphone 23, as shown in FIG. 5 (S61).
[0053] When the process of S61 is completed, the text data generating unit 26a converts the voice data indicating the voice received in S61 into text data using the text data conversion model 25b (S62). For example, if the voice received in S61 is "copy on both sides," the text data generating unit 26a may erroneously generate text data "coffee on both sides" in S62 instead of text data "copy on both sides."
[0054] When the processing of S62 is completed, the text data generation unit 26a transmits the text data generated in S62 and speaker type information having the same content as the speaker type information 25c to the job command generation system 30 (S63), and ends the operation shown in FIG. 5.
[0055] FIG. 6 is a flowchart of an example of the operation of the smart speaker 20 when accepting a voice operation for operating the image forming apparatus 40, which is different from the example shown in FIG.
[0056] When voice is input to the microphone 23, the text data generation unit 26a of the smart speaker 20 may execute the operation shown in FIG. 6 instead of the operation shown in FIG.
[0057] The operation shown in FIG. 6 is similar to the operation shown in FIG. 5, except that the process of S64 is executed instead of the process of S63 (see FIG. 5).
[0058] As shown in FIG. 6, when the processing of S62 is completed, the text data generation unit 26a transmits the text data generated in S62 and user identification information having the same content as the user identification information 25d to the job instruction generation system 30 (S64), and terminates the operation shown in FIG. 6.
[0059] Next, the operation of the job command generation system 30 when text data is received from the smart speaker 20 will be described.
[0060] FIG. 7 is a flowchart of the operation of the job command generation system 30 when text data is received from the smart speaker 20.
[0061] When the job command generation unit 35a of the job command generation system 30 receives text data transmitted from the smart speaker 20 in S63 (see Figure 5) or S64 (see Figure 6), it determines whether or not user identification information has been received together with the text data from the smart speaker 20 (S71), as shown in Figure 7.
[0062] When the job command generation unit 35a determines in S71 that it has received user identification information along with text data from the smart speaker 20, it identifies the speaker type information that is associated in the user-speaker correspondence information 34b with the user identification information received along with the text data from the smart speaker 20 (S72).
[0063] When the job command generating unit 35a determines in S71 that it has not received user identification information together with the text data from the smart speaker 20, i.e., that it has received speaker type information together with the text data from the smart speaker 20, or when the processing of S72 ends, it corrects voice recognition errors in the text data received from the smart speaker 20 using the speaker type information received together with the text data from the smart speaker 20 or an error correction model according to the type of smart speaker indicated in the speaker type information identified in S72 (S73). For example, when the text data received from the smart speaker 20 is text data of "coffee on both sides," the job command generating unit 35a generates text data of "copy on both sides" in S73.
[0064] When the process of S73 is completed, the job command generating unit 35a converts the text data generated in S73 into a job command using the job command generation model 34d (S74). For example, if the text data generated in S73 is "copy on both sides", the job command generating unit 35a generates a job command including "job type: copy" and "print side: double-sided" in S74.
[0065] When the process of S74 is completed, the job command generating unit 35a transmits the job command generated in S74 to the image forming apparatus 40 (S75), and the operation shown in FIG. 7 is completed.
[0066] When the job execution unit 48a of the image forming apparatus 40 receives the job command transmitted from the job command generation system 30 in S75, the job execution unit 48a executes a job according to the received job command. For example, when the job command transmitted from the job command generation system 30 in S75 is a job command including "job type: copy" and "print side: double-sided", the job execution unit 48a executes a double-sided copy job.
[0067] As described above, the job instruction generation system 30 uses an error correction model to correct voice recognition errors in the text data received from the smart speaker 20, which converts the voice data indicating the voice received in S61 into text data through voice recognition in S62, and generates job instructions that can be interpreted by the image forming device based on the text data from which the voice recognition errors have been corrected (S74).Therefore, when a smart speaker 20 that converts voice data into text data through voice recognition is used, it is possible to improve the likelihood that the image forming device 40 will operate as intended by the user.
[0068] In particular, the job instruction generation system 30 corrects voice recognition errors in text data received from the smart speaker 20 using an error correction model corresponding to the type of smart speaker 20 (S73), thereby improving the likelihood that the image forming device 40 will operate as intended by the user when a smart speaker 20 that converts voice data into text data through voice recognition is used.
[0069] In addition, when an error occurs in the voice recognition in the smart speaker 20 and the image forming device 40 does not operate as intended by the user, it is possible to improve the accuracy of the voice recognition itself in the smart speaker 20. However, improving the accuracy of the voice recognition itself in the smart speaker 20 is usually difficult for anyone other than the manufacturer of the smart speaker 20 to achieve. The job command generation system 30 can increase the possibility that the image forming device 40 operates as intended by the user without improving the accuracy of the voice recognition itself in the smart speaker 20.
[0070] The job instruction generation system 30 corrects voice recognition errors in the text data received from the smart speaker 20 using an error correction model corresponding to the type of smart speaker associated with the user identification information received from the smart speaker 20 in relation to the text data (YES in S71, S72 and S73), thereby improving the likelihood that the image forming device 40 will operate as intended by the user even if the type of smart speaker 20 is not notified by the smart speaker 20.
[0071] In this embodiment, the job command generation system 30 uses an error correction model according to the type of smart speaker. However, the job command generation system 30 may use only one error correction model that is independent of the type of smart speaker.
[0072] The error correction information of the present invention is an error correction model in this embodiment. However, the error correction information of the present invention may be information other than a machine learning model. For example, the error correction information of the present invention may be information for simply replacing a specific character string with a specific character string, such as information for simply replacing a character string "coffee" with a character string "copy". When the machine learning model is error correction information, the job instruction generation system 30 corrects the text data based on the characteristics of the sentence, such as the position of a word in the sentence in the text data, so that the accuracy of correction of the text data can be improved compared to when the information for simply replacing a specific character string with a specific character string is error correction information. [Explanation of symbols]
[0073] 10 Voice Control System 20 Smart speaker (voice reception device) 25c Speaker type information (information indicating the type of voice reception device) 25d User identification information (User identification information) 30 Job instruction generation system (computer) 34a Job instruction generator 34b User-speaker correspondence information (information indicating the correspondence between the type of voice reception device and the identification information of the user of the voice reception device) 34c Error correction model (error correction information) 40 Image forming device
Claims
1. managing error correction information for correcting errors in the voice recognition by a voice receiving device that converts voice data representing a received voice into text data by voice recognition; correcting the errors in the text data received from the voice accepting device using the error correction information; A job instruction generating system, comprising: a job instruction that can be interpreted by an image forming apparatus, the job instruction generating system generating job instructions based on the text data in which the error has been corrected.
2. managing the error correction information for each type of the voice receiving device; 2. The job instruction generating system according to claim 1, wherein the error in the text data received from the voice receiving device is corrected using the error correction information corresponding to the type of the voice receiving device.
3. managing a correspondence between the type of the voice receiving device and identification information of a user of the voice receiving device; The job instruction generation system according to claim 2, characterized in that the errors in the text data received from the voice receiving device are corrected using the error correction information corresponding to the type of the voice receiving device associated with the identification information received from the voice receiving device in relation to the text data.
4. An operation of managing error correction information for correcting an error in the voice recognition by a voice receiving device that converts voice data representing a received voice into text data by voice recognition; correcting the errors in the text data received from the voice accepting device using the error correction information; generating job instructions that can be interpreted by an image forming device based on the text data with the error corrected; A job instruction generating program characterized by causing a computer to execute the above steps.
5. a voice receiving device that converts voice data representing received voice into text data by voice recognition; A job command generation system that generates a job command that can be interpreted by an image forming device; Equipped with the job instruction generation system manages error correction information for correcting an error in the voice recognition by the voice receiving device; the job instruction generation system corrects the errors in the text data received from the voice receiving device using the error correction information; The voice operation system is characterized in that the job command generation system generates the command based on the text data in which the error has been corrected.
Citation Information
Patent Citations
Voice operation system, voice operation method, and voice operation program
JP2020087347A
