Intelligent control system and method for printing equipment

Abstract

The invention discloses an intelligent control system and method for printing equipment. The system comprises an acquisition unit used for acquiring a user voice instruction; the storage unit is used for storing preset corpus data; the recognition unit is used for performing semantic recognition on the user instruction, generating a text instruction and performing semantic filtering to obtain effective instruction text data; and the control unit is used for responding to an instruction of controlling the printing equipment by user voice and generating a control instruction for the printing equipment. According to the method, the user instruction is filtered and then the execution instruction is generated, so that the printing equipment instruction is generated after the validity of the instruction is ensured, unnecessary starting of the printing equipment caused by misrecognition can be prevented, and the accuracy of the voice instruction can be improved to a certain extent.

Description

Technical Field

[0001] The present invention relates to the technical field of printing device control, and in particular to an intelligent control system and method for printing equipment. Background Art

[0002] In recent years, smart speakers have experienced rapid development and innovation in both technology and functionality. Various intelligent assistant functions have been widely adopted in daily life and production. Smart speakers are often equipped with intelligent voice assistants, such as Amazon's Alexa, Google's Google Assistant, Apple's Siri, and Alibaba's Tmall Genie. These assistants can answer questions, provide information, manage schedules, and control electronic devices and peripherals. Consequently, smart speakers are gradually integrating with other smart devices, such as smartphones, smart TVs, smart home appliances, and smart electronics, forming interconnected networks. By integrating with these devices, smart speakers can serve as centralized control centers, making it easier to manage and control family life.

[0003] Unlike other devices, printing devices have their own unique characteristics: they need to warm up each time they are turned on, which consumes a certain amount of power and generates a certain amount of noise. When using a smart speaker to control a printing device via voice, if the smart speaker misidentifies and causes the printing device to start incorrectly, it will result in additional energy waste and unnecessary noise pollution.

[0004] However, the recognition efficiency of various existing smart speaker devices varies, and environmental noise and inaccurate user pronunciation will further increase the error recognition rate of smart speaker devices. The subjective intention of the user's command may not include printing-related operations, such as "Please remind me to buy printing paper". The command contains the word "printing paper", but does not require the printing device to be started. At this time, the smart speaker may mistakenly understand that it needs to wake up the printer, causing unnecessary waste for the user.

[0005] Therefore, it is necessary to reduce the unnecessary waste caused by the above-mentioned misidentification. Summary of the Invention

[0006] One of the purposes of the present invention is to solve the technical defect that the existing printing system cannot correct errors occurring during the speech recognition process in a timely manner.

[0007] The embodiment of the present invention first provides an intelligent control system for a printing device, comprising:

[0008] A collection unit, used to collect audio data of user voice commands;

[0009] A recognition unit, configured to perform semantic recognition on the collected audio data of the user instruction to generate valid instruction text data;

[0010] The control unit is used to respond to the user's voice control instruction of the printing device and generate a control instruction for the printing device according to the valid instruction text data; the printing device is used to execute the control instruction.

[0011] Optionally, the printing device intelligent control system further includes:

[0012] A storage unit, configured to store preset corpus data, wherein the corpus data includes: printing semantic data and printing device instruction set data;

[0013] The recognition unit performs semantic recognition on the collected audio data of the user instruction and generates a text instruction, and performs semantic filtering on the text instruction according to the printing semantic data to obtain valid instruction text data;

[0014] The control unit generates a control instruction for the printing device according to the effective instruction text data and in association with the printing device instruction set data;

[0015] The recognition unit performs a semantic filtering process on the text instruction, including comparing and matching the semantics contained in the user voice instruction with the print semantic data:

[0016] If there is intersection data in the comparison and matching results, the matching results are reorganized to form valid instruction text data;

[0017] If there is no intersection data in the comparison and matching results, it is determined that the user voice is invalid instruction text data.

[0018] Optionally, the print semantic data in the corpus data includes:

[0019] Print action data and instruction parameter data.

[0020] The various types of data in the printed semantic data also include corresponding associative vocabulary data and fuzzy vocabulary data.

[0021] Optionally, the printing device instruction set data includes: an instruction set for controlling the printing device to implement corresponding functions.

[0022] Optionally, the recognition unit performs a semantic filtering process on the text instruction, including:

[0023] wherein, semantic segmentation is performed on the user voice command to obtain a plurality of sub-semantic information;

[0024] The plurality of sub-semantic information are compared and matched with the preset printing semantic data.

[0025] Optionally, after semantic filtering of the text instruction:

[0026] If valid text instruction data is obtained, the valid instruction text data is executed;

[0027] If invalid text instruction data is obtained, the invalid instruction text data is ignored, or the user is prompted that the instruction is invalid or cannot be recognized and needs to be reissued.

[0028] Optionally, the recognition unit performs semantic filtering on the text instruction further comprising:

[0029] The sub-semantic information obtained through segmentation includes at least one action semantic.

[0030] Optionally, the recognition unit performs semantic filtering on the text instruction further comprising:

[0031] The plurality of sub-semantic information are compared and matched with the preset printing semantic data,

[0032] If at least one action semantic match exists, the comparison and matching result is determined to be intersection data;

[0033] If there is no action semantic match, the comparison and matching result is determined to be no intersection data

[0034] An embodiment of the present invention further provides a method for intelligently controlling a printing device, comprising the following steps:

[0035] Collect audio data of user voice commands;

[0036] The preset corpus data is stored in the server;

[0037] Performing semantic recognition on the collected audio data of the user instruction and generating a text instruction, and performing semantic filtering on the text instruction according to the printing semantic data to obtain valid instruction text data;

[0038] In response to a user voice command to control the printing device, a control command is generated for the printing device according to the effective command text data and in association with the printing device command set data.

[0039] The semantic filtering of the text instruction includes:

[0040] Performing semantic segmentation on the user voice command to obtain a plurality of sub-semantic information;

[0041] The plurality of sub-semantic information are compared and matched with the preset printing semantic data.

[0042] The sub-semantic information obtained by segmentation contains at least one action semantic.

[0043] If at least one action semantic match exists, the comparison and matching result is determined to be intersection data;

[0044] If there is no action semantic match, the comparison and matching result is determined to be non-intersection data.

[0045] According to some embodiments, an electronic device is described.

[0046] The electronic device includes: one or more computers; one or more printing devices; and a memory, wherein the memory stores one or more programs configured to be executed by the one or more processors, and the one or more programs include instructions for executing the printing device intelligent control method.

[0047] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0048] The invention discloses an intelligent control system and method for printing equipment, which filters user instructions and then generates execution instructions, and then generates printing equipment instructions after ensuring the validity of the instructions.

[0049] When users use home or office printing devices with smart speakers as the control center, they can issue commands directly through voice, and the user commands can be filtered for semantic relevance. If the semantics contained in the user command are positively correlated with the printing device, the printing device execution command is generated through association. Before the user voice command forms a printer command, it undergoes effective semantic filtering, which can prevent the unnecessary startup of the printing device due to misrecognition and can improve the accuracy of the voice command to a certain extent.

[0050] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or will be understood by practicing the present invention. The purposes and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the description, claims and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0052] Figure 1 A schematic structural diagram of an intelligent control system for a printing device provided by an embodiment of the present invention;

[0053] Figure 2 A schematic diagram of instruction filtering for an intelligent control system of a printing device provided by an embodiment of the present invention;

[0054] Figure 3A timing diagram of a printing device intelligent control system processing voice commands provided by an embodiment of the present invention;

[0055] Figure 4 A flowchart of the steps of a method for intelligently controlling a printing device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0056] In order to make the objectives, technical solutions and advantages of the present invention more clear, the present invention is further described in detail below with reference to the accompanying drawings.

[0057] The following describes embodiments of the present invention in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only intended to illustrate and explain the present invention and are not intended to limit the present invention. Furthermore, features in the embodiments of the present invention may be combined with each other if they do not conflict.

[0058] Embodiments of the present invention provide an intelligent control system and method for a printing device, which can implement intelligent voice control of the printing device, reduce unnecessary startups due to erroneous recognition, and avoid power waste and noise pollution on the user side.

[0059] Figure 1 A schematic diagram of the structure of an intelligent control system for a printing device provided in this embodiment. The system mainly includes an acquisition unit 101, a recognition unit 102, a storage unit 103, a control unit 104, and a printing device 105, which are connected to each other through a network (wired network or wireless network). The acquisition unit 101 can be a computer device such as a smart speaker, a smart phone, a computer, a tablet computer, a smart watch, or a smart device with an integrated digital signal processor, which can collect the user's voice signal and obtain voice data through digital signal processing (DSP), and can output the voice data to the recognition device 102 via the network. The recognition unit 102 can be a computer device such as a dedicated recognition module, a semantic server, or a smart speaker that can work offline, which has a natural language processing (NLP) function and a communication function. It can extract the semantic information of the voice data through a speech recognition model, compare and match the semantic information with the instruction semantic data of the preset corpus information in the storage unit 103, and output the number of matched valid instruction texts to the control unit 104 via the network. Storage unit 103 is a non-volatile memory (NVM) that is preset to store corpus data for semantic matching. Control unit 104, which can be, for example, a cloud server, is configured to associate the matched valid instruction text data with the instruction set data of the preset corpus information in storage unit 103 to generate control instructions for printing device 105.

[0060] It should be noted that the control instructions are firmware instructions that can be directly executed by the printer.

[0061] The printing device 105 is the command execution object of the control system. It can be a single-function or multi-function printer connected via a network, or a virtual printing device. The present invention is not limited to basic control actions such as printing, scanning, and copying, but can also be applied to other customized operations such as setting and parameters.

[0062] The acquisition unit 101 is used to collect or receive the sound signals of the user's voice. In one embodiment, the acquisition unit 101 is composed of a sound pickup module 11 and a signal processing module 12. The sound pickup module 11 can be, for example, a microphone module, and the signal processing module 12 can be, for example, an application-specific integrated circuit (ASIC) with digital signal processing capabilities. The sound pickup module 11 is used to collect audio signals and transmit them to the signal processing module 12 for digital signal processing to obtain audio data of the user's voice command.

[0063] The recognition unit 102 is used to extract the semantic information contained in the audio data of the user's voice command and match the semantic information contained in the user's command with the command semantics by comparing the command semantic data in the preset corpus in the storage unit 103. In one embodiment, the recognition unit 102 is composed of a processing module 21 and a cache module 22. The processing module 21 can be, for example, a core processor with DSP functions, and the cache module 22 can be, for example, a Flash memory. The processing module 21 is used for recognition and semantic screening, and the cache module 22 is used for temporary storage of data during semantic segmentation and comparison and matching.

[0064] It should be noted that, in the embodiments of this document, the sub-semantic information obtained through segmentation may be, for example, multiple segments of sub-text data consisting of words, numbers, and phrases.

[0065] For example, the cloud server implements the function of the recognition unit 102, firstly converting the audio data from the acquisition unit 101 into text. The textualization process can be achieved through frequency inverse spectrum, neural network and other means to obtain the text data of the user instruction. Further semantic recognition is performed on the text data. First, the text data is semantically segmented to obtain multiple sub-text data after segmentation. For example, a traversal matching method can be used to compare and match the instruction semantic data in the preset corpus of the multiple sub-text data. If the corresponding semantics are matched, the multiple sub-text data are recombined according to the matching results to obtain valid text instruction data, and the valid text instruction data is transmitted to the control unit 104; if no semantics are matched, the recognition is stopped.

[0066] Part-of-speech analysis is preferably performed on the segmented multiple sub-text data. The corresponding semantics of the multiple sub-text data need to satisfy at least one action-directed semantic, where the directed verb is an operation action for the printing device.

[0067] It should be noted that based on the analysis of user usage habits, users rarely make incorrect descriptions of basic operations such as "print", "copy", and "scan". Therefore, the approximate fuzzy matching of the segmented multi-segment sub-text data is aimed at other semantics. For example, fuzzy content related to "file" includes but is not limited to: "text", "document", "article", "manuscript", "script", "attachment", etc.

[0068] The control unit 104 is used to generate operating instructions or operating instruction data for the printing device 105. It should be noted that since the control unit 104 is implemented by being installed in a cloud server, the server can be considered a cloud printing server hereinafter. The control unit 104 traverses and compares the matching valid instruction text data with the instruction set data of the preset corpus information in the storage unit 103, and after matching, obtains instructions or instruction data (parameters) that can be directly executed by the printer, and sends them to the printing device 105 via the network for execution.

[0069] Preferably, in the present system, the instruction set and parameter capabilities of the printing device 105 correspond to the corpus data contained in the storage unit 103, ie, to the printing device instruction set data.

[0070] It should be noted that the printing device 105 may be a single printer or multiple printers, wherein the printer may be a single-function or multi-function printer, or a virtual printer.

[0071] The following describes in detail the filtering process of user voice commands. The recognition unit 102 converts the audio data into text data to obtain the text data of the user command, and then divides the text data into multiple sub-text data. Each sub-text data is subjected to part-of-speech analysis and fuzzy matching. After a successful match, the valid text command data is generated.

[0072] The following example illustrates the semantic filtering process. Figure 2 This is a schematic diagram of instruction filtering for an intelligent control system of a printing device provided in this embodiment.

[0073] like Figure 2As shown, a segment of user voice command audio data V is picked up by the recognition unit 102, and after text processing, the command text data M is obtained. After segmentation, n segments of sub-text data M1, M2, M3, ..., Mn (n∈N*) are obtained. After part-of-speech analysis, sub-text data Mp and Mq (p, q∈N*, and p≠q) are obtained. The sub-text data Mp and Mq both contain action semantics. The n segments of sub-text data are fuzzy matched with the print semantic data in the preset corpus data.

[0074] It should be noted that corpus data is preset in the storage unit 103, and the corpus data storage content includes: printing semantic data, printing device instruction set data, wherein the printing semantic data includes: printing action data, instruction parameter data, wherein the sub-text data Mp and Mq are fuzzy matched with the printing action data, and other sub-text data are fuzzy matched with the instruction parameter data.

[0075] After matching the print action data, the obtained subtext data Mq is irrelevant to the action, and the subtext data Mp is the print action Mv. After matching the instruction parameter data, the obtained subtext data Mk (k∈N*, k≤n and k≠p≠q) is parameter data Ms, and the remaining subtext data is irrelevant. The instruction text data M is reassembled to form valid instruction text data Mvs. After receiving the valid instruction text data Mvs, the control unit 104 can directly generate an operation instruction or operation instruction data for execution by the printing device 105 by traversing and matching it with the printing device instruction set data.

[0076] It should also be noted that since the corpus data is preset based on the current printing device, the functions will be limited after the user upgrades the printing device firmware. The corpus data can be updated at the same time as the device is upgraded to ensure that the user can use it normally.

[0077] In one possible implementation, the acquisition unit 101 and recognition unit 102 may be smart speakers, the storage unit 103 and control unit 104 may be cloud servers deployed with algorithm software, and the printing device 105 may be a home printer that supports cloud printing. Users can connect the smart speaker and home printer to a home router to form a home IoT, using the smart speaker as the voice control device. Voice commands can be sent to the smart speaker, allowing the home printer to be controlled through the cloud server.

[0078] In another possible embodiment, the acquisition unit 101, recognition unit 102, storage unit 103, and control unit 104 can be provided on a printing device 105 to enable voice control of the printer. The acquisition unit 101, recognition unit 102, and control unit 104 are integrated modules with pre-set offline voice processing algorithms, and the storage unit 103 is a dedicated memory with pre-set corpus data. The acquisition unit 101, recognition unit 102, storage unit 103, and control unit 104 are integrated into the printing device 105 and connected to the firmware mainboard of the printing device 105. Information and command exchange is performed via, for example, a universal asynchronous receiver / transmitter. If a user issues a printer operation command with a clear direction, such as a wake-up word, the printer control system can be activated. The system's pre-set corpus data can adopt different corpus configurations based on the different printer functions, so that its corpus fully covers the printer functions. This enables offline voice control of the printing device, thereby reducing user manual operation and preventing the printer from being accidentally activated due to normal environmental conversations.

[0079] In another possible embodiment, the acquisition unit 101 can be provided on the printing device 105, the recognition unit 102, the storage unit 103, and the control unit 104 can be a cloud server deployed with algorithm software, and the printing device 105 can be a printer that supports cloud printing. The acquisition unit 101 is connected to the network communication module in the printing device 105, and the audio signal of the user's voice picked up by the acquisition unit 101 can be sent to the cloud server via the network. The recognition unit 102 in the cloud server performs textual recognition and relevance filtering of the voice command, and the control unit 104 in the cloud server performs printer command matching for valid text commands, and then sends the matched printer command to the printing device 105.

[0080] The above-described embodiments improve the accuracy of voice command recognition. User commands may contain a lot of colloquial and irrelevant content. Directly matching the printer's command set may result in matching timeouts, matching errors, or matching failures. Furthermore, words like "print" and "copy" are likely to be set as wake-up words for the printer. If a user mentions such words in normal conversation, it may cause the printer to activate inadvertently. This system can reduce the occurrence of such inadvertent wake-ups through semantic filtering.

[0081] Figure 3 This is a timing diagram of a printing device intelligent control system processing voice commands provided in this embodiment. This embodiment is used to illustrate the working principle of the system.

[0082] When using the system, the user issues a voice command, which is picked up by the acquisition unit 101 in the form of a sound signal and converted into audio data. The audio data is sent to the recognition unit 102 via the network, and the recognition unit 102 adopts a monitoring mode to receive the audio data from the acquisition unit 101.

[0083] The audio data is first converted into text in the recognition unit 102 to obtain voice command text data, which is then processed by a segmentation algorithm to obtain multiple sub-text data that are stored in the cache module.

[0084] The processing module 21 in the recognition unit 102 accesses the preset corpus in the storage unit 102, traverses and compares the multiple sub-text data with the printed semantic data, and obtains a matching result:

[0085] If there is intersection data in the comparison and matching results, the matching results are reorganized to form valid instruction text data;

[0086] If there is no intersection data in the comparison and matching results, the user voice command is invalid command text data.

[0087] When there is intersection data in the comparison and matching results, the matched printing semantic data is temporarily stored in the cache module 22 in the recognition unit 102, and then the matched printing semantic data is reorganized into valid instruction text data through the processing module 21.

[0088] It should be noted that, during the semantic filtering process, a necessary condition for forming valid instruction text data is that there is a successful match of sub-text data containing action semantics.

[0089] Among them, the sub-text data containing action semantics are action words related to the operation of the printing device, such as: print, copy, scan, etc., and also include related fuzzy action words, such as: print, copy, reprint, etc., and also include action words related to the control of the printing device, such as: adjust, regulate, raise, lower, etc.

[0090] After completing the printing semantic filtering: if valid instruction text data is formed, the text data and multiple paragraphs of sub-text data on the cache module 22 are deleted, and the recognition unit 102 sends the valid instruction text data to the control unit 104; if the user voice instruction is judged to be invalid instruction text data, the text data and multiple paragraphs of sub-text data on the cache module 22 are deleted, and the recognition unit 102 sends a feedback result of terminating the recognition to the acquisition unit 101.

[0091] After receiving the valid instruction text data, the control unit 104 accesses the preset corpus in the storage unit 102 , traverses and compares the valid instruction text data with the printing device instruction set data, and obtains a control instruction for execution by the printing device 105 .

[0092] The control unit 104 sends the control instruction to the printing device 105 through the network.

[0093] Preferably, the data communication between the identification unit 103 and the control unit 104 can be completed through, for example, an asynchronous serial communication protocol.

[0094] In actual application scenarios, the processing results can also be fed back to the user based on the processing results. For example, when the printing device 105 completes the user's instructions, it sends a job log to the control unit 104. The control unit 104 generates corresponding receipt information based on the job log. The receipt information can be used to feedback the instruction execution results to the user through e-mail, short message, audible file, operation panel display, etc.

[0095] Figure 4 A flowchart of the steps of a method for intelligently controlling a printing device provided by an embodiment of the present invention.

[0096] In step S1, first, the sound signal of the user's instruction is picked up, and then converted into audio data of the voice instruction. The various possible methods described above may include but are not limited to the following methods.

[0097] The sound signal is picked up by the acquisition unit 101 provided on the smart speaker and converted into audio data of the voice command; the sound signal is picked up by the acquisition unit 101 provided on the mobile terminal associated with the cloud printing server or in data communication with the printing device 105 and converted into audio data of the voice command; or the sound signal is picked up by the acquisition unit 101 integrated in the printing device 105 and converted into audio data of the voice command.

[0098] The conversion of sound signals can be achieved through digital signal processing. In practical applications, in order to achieve better audio quality, the preprocessing of sound signals can include but is not limited to: sample normalization, image transformation processing, noise reduction filtering processing, n-order filtering emphasis processing, endpoint detection, adding window function, etc.

[0099] In step S2, the audio data of the voice command is converted into text to obtain voice command text data. The various possible methods described above may include but are not limited to the following methods.

[0100] The text is processed using the recognition unit 102 provided on the smart speaker; the text is processed using the recognition unit 102 provided on the cloud printing server; or the text is processed using the recognition unit 102 integrated on the printing device 105.

[0101] The recognition unit 102 can perform textual processing of the audio data of the voice command by performing pattern recognition using a preset algorithm model, such as a Hidden Markov Model (HMM), a non-parametric vector quantization (VQ), a generative adversarial neural network (GAN), etc. The algorithm model is deployed on the recognition unit 102 in the form of algorithm software as a voice server. Preset parameters are configured in the algorithm software, and the audio information is converted into text data through a series of mathematical operations. The above-mentioned voice server can be a network server located on the network, but is not limited to this. It can also be a server built into the printing device.

[0102] In step S3, semantic segmentation is performed on the voice command text data to obtain multiple sub-text data. In this step, different implementation methods are provided based on multiple possibilities.

[0103] Semantic segmentation is performed using the recognition unit 102 provided on the smart speaker; semantic segmentation is performed using the recognition unit 102 provided on the cloud printing server; or semantic segmentation is performed using the recognition unit 102 integrated on the printing device 105.

[0104] The recognition unit 102 implements semantic segmentation of voice command text data in the same way as the text processing process, and can be implemented by pattern recognition using a preset algorithm model. The algorithm model can be a variety of common segmentation algorithms, which will not be elaborated on here.

[0105] In step S4, semantic filtering is performed using the printed semantic data in the storage unit 103 as a control group and the multiple subtext data as a test group to obtain semantic matching results. In this step, different implementation methods are provided based on multiple possibilities.

[0106] Optionally, semantic filtering is performed using the recognition unit 102 and storage unit 103 set on the smart speaker, and the filtering form is comparative matching; optionally, semantic filtering is performed using the recognition unit 102 and storage unit 103 set on the cloud printing server; or semantic filtering is performed using the recognition unit 102 and storage unit 103 integrated on the printing device 105.

[0107] The semantic filtering of the voice command text data by the recognition unit 102 is similar to the text processing process and the semantic segmentation process, and can be achieved by pattern recognition through a preset algorithm model. The algorithm model can be a variety of common matching algorithms, which will not be elaborated on here.

[0108] After semantic filtering of multiple sub-text data in step S4, two types of processing are performed according to different matching results:

[0109] If there is an intersection between the control group and the test group after matching, then execute steps S5-S7;

[0110] If there is no intersection after the control group and the test group are matched, step S8 is executed.

[0111] In step S5 , first, the recognition unit 102 reorganizes the control group data matched by the test group to obtain valid text data and sends it to the control unit 104 , and then deletes the test group data cached in the process.

[0112] In step S6 , first, the control unit 104 traverses and matches the valid text data with the pre-stored printing device instruction set data, and then obtains the matching result, that is, the control instruction corresponding to the valid text data and directly executable by the printing device.

[0113] In step S7 , the control unit 104 sends a control instruction to the printing device 105 .

[0114] The following describes the process of filtering user voice commands by using an example, but the method of this embodiment is not limited thereto.

[0115] For example, when a user's smart speaker issues a voice command to print file A, the smart speaker first picks up the voice command, converts it into audio data, and sends it to the cloud server. The cloud server uses pre-set algorithm software to textualize and segment the audio data to generate multiple sub-segments of sub-text data. It then uses a pre-set algorithm to filter invalid semantic information and reconstructs it to generate valid text data. This valid text data is then sent to a cloud print server also deployed in the cloud. Based on the pre-set print device instruction set data, the cloud print server converts the valid text data into control instructions and sends them to the user's bound printing device. The printing device then executes the control instructions.

[0116] The intelligent control method for a printing device in this embodiment, after converting user voice commands into text data, further filters the semantics of the text data for relevance, thereby filtering out irrelevant and invalid command information, reducing the error recognition and rejection rates caused by inaccurate or irrelevant voice commands. Furthermore, because the user's voice commands undergo a process of segmentation, filtering, and reorganization, they are converted into valid data that can be quickly matched to the printer's command set, reducing the response time of the intelligent voice control system to the user's voice commands. This achieves an intelligent improvement in the user's ability to control the printing device to perform corresponding operations through voice commands, bringing greater convenience and a better user experience.

[0117] It is understood that the embodiments described herein may be implemented using hardware, software, firmware, middleware, microcode, or a combination thereof. For hardware implementation, the identification unit 102 may be implemented in one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), general-purpose processors, controllers, microcontrollers, microprocessors, or other electronic units or combinations thereof for performing the functions described herein.

[0118] For software implementation, the technology described herein can be implemented by a unit that performs the functions described herein. The software code can be stored in a memory and executed by a processor. The memory can be implemented in the processor or outside the processor.

[0119] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0120] In the embodiments provided herein, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components being combined or integrated into another system, or some features being ignored or not implemented. In addition, the communication connection between the units can be through some interfaces, which can be electrical or in other forms.

[0121] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0122] If the filtering function or provided method is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention, or the part that contributes to the existing technology, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program code, such as a USB flash drive, a mobile hard disk, ROM, RAM, a magnetic disk, or an optical disk.

[0123] It should be noted that the terms "comprises", "includes" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or apparatus that includes a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements that are inherent to such process, method, article or apparatus.

[0124] Without further constraints, an element defined by the phrase "comprises a..." does not preclude the existence of additional identical elements in the process, method, article or apparatus that includes the element.

[0125] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A printing equipment intelligent control system, characterized in that: include: A collection unit, used to collect audio data of user voice commands; A recognition unit, configured to perform semantic recognition on the collected audio data of the user instruction to generate valid instruction text data; The control unit is used to respond to the user's voice control instruction of the printing device, according to the effective instruction text data The printing device generates control instructions; The printing device is used to execute the control instruction.

2. The intelligent control system for printing equipment according to claim 1, characterized in that: Also includes: A storage unit, configured to store preset corpus data, wherein the corpus data includes: printing semantic data and printing device instruction set data; The recognition unit performs semantic recognition on the collected audio data of the user instruction and generates a text instruction, and performs semantic filtering on the text instruction according to the printing semantic data to obtain valid instruction text data; The control unit generates a control instruction for the printing device according to the effective instruction text data and in association with the printing device instruction set data; The recognition unit performs a semantic filtering process on the text instruction, including comparing and matching the semantics contained in the user voice instruction with the print semantic data: If there is intersection data in the comparison and matching results, the matching results are reorganized to form valid instruction text data; If there is no intersection data in the comparison and matching results, it is determined that the user voice is invalid instruction text data.

3. The intelligent control system for printing equipment according to claim 1, characterized in that: The printing semantic data in the corpus data includes: Print action data, instruction parameter data; The various types of data in the printed semantic data also include corresponding associative vocabulary data and fuzzy vocabulary data.

4. The intelligent control system for printing equipment according to claim 1, characterized in that: The printing device instruction set data includes: A set of instructions used to control the printing device to implement corresponding functions.

5. The intelligent control system for printing equipment according to claim 1, characterized in that: The recognition unit performs a semantic filtering process on the text instruction, including: Performing semantic segmentation on the user voice command to obtain a plurality of sub-semantic information; The plurality of sub-semantic information are compared and matched with the preset printing semantic data.

6. The intelligent control system for printing equipment according to any one of claims 1 to 5, characterized in that: After the recognition unit performs semantic filtering on the text instruction: Executing the valid instruction text data; Ignore the invalid instruction text data, or prompt the user that the instruction is invalid or unrecognizable and needs to be reissued.

7. The intelligent control system for printing equipment according to claim 5, characterized in that: The recognition unit performs a semantic filtering process on the text instruction, further comprising: The sub-semantic information obtained through segmentation includes at least one action semantic.

8. The intelligent control system for printing equipment according to claim 5, characterized in that: The recognition unit performs a semantic filtering process on the text instruction, further comprising: The plurality of sub-semantic information are compared and matched with the preset printing semantic data, If at least one action semantic match exists, the comparison and matching result is determined to be intersection data; If there is no action semantic match, the comparison and matching result is determined to be non-intersection data.

9. A method for intelligent control of a printing device, characterized in that: The following steps are involved: Collect audio data of user voice commands; The preset corpus data is stored in the server; Performing semantic recognition on the collected audio data of the user instruction and generating a text instruction, and performing semantic filtering on the text instruction according to the printing semantic data to obtain valid instruction text data; In response to a user voice command to control the printing device, a control command is generated for the printing device according to the effective command text data and in association with the printing device command set data.

10. The intelligent control method for printing equipment according to claim 9, wherein: Performing semantic filtering on the text instruction further includes: Performing semantic segmentation on the user voice command to obtain a plurality of sub-semantic information; Comparing and matching the plurality of sub-semantic information with the preset printing semantic data; Among them, the sub-semantic information obtained by segmentation contains at least one action semantic. If at least one action semantic match exists, the comparison and matching result is determined to be intersection data; if there is no action semantic match, the comparison and matching result is determined to be no intersection data.

11. An electronic device comprising: one or more computers; One or more printing devices; and a memory storing one or more programs configured to be executed by the one or more processors, the one or more programs comprising instructions for executing the method according to any one of claims 9 to 10.

Images