System and method for voice activated label printing using artificial intelligence

Abstract

The invention relates to a system and method for voice-activated label printing using artificial intelligence. In a label printing system configured for voice-activated label printing, a computing device includes a label printing module and a transcription module that generates a textual transcription of a voice input that includes a verbal instruction for a label to be printed. The label printing system also includes a label intent module that generates a cue set for the AI model based on the text transcription. The cue set is configured to transcribe AI model interpretation text and generate a data structure for printing labels. The tag intent module provides the cue set to the AI model and receives the data structure from the AI model. The data structure includes tag content and formatting instructions. The data structure is provided to a label printing module that uses the data structure to cause printing of a label on a printing device.

Description

Background Technology

[0001] Label printing is a vital function across a wide range of industries, including retail, manufacturing, logistics, and healthcare. Labels provide crucial information, facilitate organizational management, and ensure accurate identification of products and items. Traditionally, label printing was performed using software running on desktop computers. However, with the advent of mobile technology, mobile apps have become a convenient solution for designing and printing labels directly from smartphones and tablets. These mobile apps (or often referred to as mobile "apps") offer users the flexibility to create custom labels on the go, fully leveraging the capabilities of modern label printers.

[0002] Some label printing applications allow users to design and customize labels. For example, some label printing applications allow users to select from predefined templates, customize text, and specify formatting options. Once the label design is complete, the label printing application communicates with the connected label printer to generate the physical label.

[0003] In recent years, voice recognition technology has been widely adopted, allowing users to interact with devices and applications via verbal commands. In the label printing field, voice recognition has the potential to streamline the label design process by allowing users to verbally dictate label content and formatting instructions. However, voice recognition applications specifically designed for label printing are limited, and existing solutions have failed to fully leverage the technology's potential.

[0004] Printing labels using voice commands requires a mechanism to accurately interpret the user's spoken input, distinguish different types of instructions, and generate corresponding label designs. One possible approach involves mapping predefined voice commands to specific actions within the label printing application. For example, a user could say "add text" followed by the expected content, or "change the font size to 12." While this approach works for simple commands, it becomes increasingly complex and less intuitive as the range of possible instructions expands.

[0005] Another possible approach is to use rule-based algorithms to parse the user's spoken input and transform it into tag design elements. These algorithms can analyze the transcription of the speech input, identify keywords and phrases, and apply predefined rules to generate tag content and format. However, this approach has several drawbacks. Rule-based systems can appear rigid, and their ability to handle natural language variations is limited, making them prone to errors when users express commands in unexpected ways. Furthermore, developing and maintaining a comprehensive set of rules for all possible tag design scenarios is a resource-intensive task.

[0006] Therefore, there is a need for improved systems and methods that can accurately and flexibly interpret voice commands used for label printing.

[0007] The background section aims to provide an overview of the overall context of the topics disclosed herein. The topics discussed in the background section should not be assumed to be prior art simply because they are mentioned therein. Similarly, problems mentioned in the background section, or problems related to the topics of the background section, should not be assumed to have been previously recognized in the prior art. Summary of the Invention

[0008] This disclosure generally relates to systems and methods for designing and printing labels that utilize artificial intelligence (AI) to facilitate voice activation. According to this disclosure, an AI model can be used to interpret a user's verbal input, thereby determining the content and characteristics of the label to be printed.

[0009] In some embodiments, the techniques disclosed herein can be used in a label printing system including a label printing module running on a mobile device (or other type of computing device) communicatively coupled to a printing device. When a user of the label printing module wants to print a label, the user can provide voice input including verbal instructions for the label. A transcription module can generate a text transcription of the voice input, and the text transcription can be provided to a label intent module. The label intent module can reside on one or more servers communicatively coupled to the mobile device.

[0010] The label intent module can be configured to generate a cue set for an AI model based on text transcription. The cue set can be constructed to enable the AI ​​model to interpret the text transcription and generate a data structure for printing labels. Once the cue set is generated, the label intent module can provide it to the AI ​​model. The AI ​​model can then generate the data structure based on the cue set and return the data structure to the label intent module. The label intent module can then provide the data structure to the label printing module, which can use the data structure to print the labels on a printing device.

[0011] In some embodiments, the AI ​​model included in the label printing system utilizes a transducer-based language model with contextual understanding capabilities. This contextual understanding enhances the AI ​​model's ability to accurately interpret and process the user's voice input. The set of prompts provided to the AI ​​model can be designed to leverage these contextual understanding capabilities.

[0012] In some embodiments, the label printing system includes a preprocessing module designed to streamline the text transcription before it is interpreted by the AI ​​model. The preprocessing module can be configured to apply a set of predefined substitution rules to the text transcription. For example, the preprocessing module can correct common transcription errors, standardize terminology, and generally improve the quality of the input data provided to the AI ​​model. This preprocessing step can improve the accuracy and efficiency of the subsequent label generation process.

[0013] In some embodiments, the replacement rules used by the preprocessing module can be dynamically adjusted. This allows for customization and adaptation to different user preferences or specific industry requirements. For example, users can specify whether to use numeric or handwritten formats for numbers, expand or abbreviate certain terms, or apply industry-specific terminology replacements. This flexibility ensures that the label printing system can adapt to a wide range of labeling needs across various fields.

[0014] In some embodiments, the label printing system includes multiple sets of replacement rules tailored to different industries or use cases. The system can prompt the user to select the most appropriate set of rules based on the specific labeling task at hand. This feature further enhances the system's adaptability and ensures that the generated labels conform to industry-specific conventions and terminology.

[0015] In some embodiments, the set of prompts generated by the labeling intent module and provided to the AI ​​model includes at least three different types of prompts: system prompts, assistant prompts, and user prompts. System prompts provide high-level instructions to the AI ​​model, informing it of its overall task and guiding its interpretation of user input. Assistant prompts specify the format the AI ​​model should follow for the output data structure. User prompts contain the actual text transcription of the user's spoken input, which the AI ​​model processes according to the instructions in the system prompts to extract the necessary information for generating labels.

[0016] In some embodiments, the label printing system also includes a cue improvement database. This database is designed to store cue / result pairs, where each pair contains a set of cue provided to the AI ​​model and corresponding data structures generated by the AI ​​model in response to these cue. This feature allows the system to record its interactions with the AI ​​model, which is valuable for analyzing and improving the system's performance over time.

[0017] The system and method described in this paper offer several advantages over known methods for label printing. By combining AI and speech recognition technologies, the disclosed label printing system achieves a more efficient and user-friendly label creation process. Users simply speak their labeling requirements, eliminating the need for manual text input or navigating complex formatting menus. This not only saves time but also reduces errors that can occur with manual data entry. Furthermore, the use of AI allows for greater flexibility and adaptability in label design. The AI ​​model can interpret a wide range of verbal instructions, adapting to variations in language and user preferences. This versatility makes the system suitable for diverse labeling needs across various industries.

[0018] In some embodiments, a label printing system for facilitating voice-activated label printing is disclosed. The label printing system includes a printing device and a computing device communicatively coupled to the printing device. The computing device includes a label printing module and a transcription module configured to generate a text transcription of a user's voice input from the label printing module. The voice input includes verbal instructions for a label to be printed. The label printing system also includes at least one server communicatively coupled to the computing device. The at least one server includes at least one processor, memory communicatively coupled to the at least one processor, and instructions stored in the memory. The instructions are executable by the at least one processor to generate a cue set for an AI model based on the text transcription. The cue set is constructed to cause the AI ​​model to interpret the text transcription and generate a data structure for printing the label. The instructions are also executable by the at least one processor to provide the cue set to the AI ​​model. The instructions are also executable by the at least one processor to receive a data structure from the AI ​​model. The data structure includes label content and formatting instructions. The instructions are also executable by the at least one processor to provide the data structure to the label printing module. The label printing module uses the data structure to cause the label to be printed on the printing device.

[0019] In some embodiments, a label printing system is disclosed for facilitating voice-activated label printing via a label printing module. The label printing module operates on a computing device communicatively coupled to a printing device. The label printing system includes at least one processor, memory communicatively coupled to the at least one processor, and instructions stored in the memory. The instructions are executable by the at least one processor to generate a set of prompts for an AI model based on text transcription of voice input. The voice input includes verbal instructions for a label to be printed. The prompt set is designed to enable the AI ​​model to interpret the text transcription and generate a data structure for printing the label. The instructions are also executable by the at least one processor to provide the prompt set to the AI ​​model and receive the data structure from the AI ​​model. The data structure includes label content and formatting instructions. The instructions are also executable by the at least one processor to provide the data structure to the label printing module. The label printing module uses the data structure to cause the label to be printed on the printing device.

[0020] In some embodiments, a computer-readable medium configured to facilitate voice-activated label printing is disclosed. The computer-readable medium includes instructions executable by at least one processor to generate a set of prompts for an AI model based on text transcription of voice input from a user of a computing device. The voice input includes verbal instructions for a label to be printed. The prompt set is designed to enable the AI ​​model to interpret the text transcription and generate a data structure for printing the label. The computer-readable medium also includes instructions executable by at least one processor to provide the prompt set to the AI ​​model and receive the data structure from the AI ​​model. The data structure includes label content and formatting instructions. The computer-readable medium further includes instructions executable by at least one processor to provide the data structure to a label printing module. The label printing module uses the data structure to cause the label to be printed on a printing device.

[0021] This invention provides a set of concepts presented in a simplified form, which will be further elaborated in the detailed embodiments described below. This invention is not intended to identify key or essential features of the claimed subject matter, nor is it intended to be used as an aid in determining the scope of the claimed subject matter.

[0022] Additional features and advantages will be set forth in the following description. The features and advantages of this disclosure can be realized and obtained by means of the systems and methods expressly pointed out in the appended claims. The features of this disclosure will become more apparent from the following description and the appended claims, or may be learned by practice of the disclosed subject matter set forth below. Attached Figure Description

[0023] To describe how the above-described and other features of this disclosure can be obtained, a more detailed description will be provided with reference to specific embodiments shown in the accompanying drawings. For better understanding, similar elements in the various drawings have been labeled with similar reference numerals. It should be understood that the drawings illustrate some exemplary embodiments, which will be described and explained with additional specificity and detail using the drawings, wherein:

[0024] Figure 1 Aspects of a label printing system that can utilize the technology disclosed herein are shown.

[0025] Figure 2 An example of the processing associated with voice-activated printing of labels, which can be performed on a mobile device in a label printing system, is shown.

[0026] Figure 3 An example of the processing associated with voice-activated printing of labels, which can be performed on a server in a label printing system, is shown.

[0027] Figure 4An example of a set of prompts associated with the voice-activated printing of a label is shown, which can be generated by the label intent module in a label printing system.

[0028] Figure 5A , 5B Figures 5C and 5C illustrate examples of methods that can be performed by the individual components of a label printing system to print labels. Detailed Implementation

[0029] Figure 1 Aspects of a label printing system 100 that can utilize the techniques disclosed herein are illustrated. The label printing system 100 includes a computing device. In the illustrated embodiment, the computing device takes the form of a mobile device 101, such as a smartphone or tablet computer. The mobile device 101 includes one or more processors 102 and memory 103 communicatively coupled to the processor(s) 102. In alternative embodiments, the techniques disclosed herein can be used with different types of computing devices, such as laptops, desktop computers, wearable devices (e.g., smartwatches), etc.

[0030] The label printing system 100 also includes a printing device 131. The printing device 131 is a hardware unit designed to produce printed material (e.g., label 133). The printing device 131 includes a printing mechanism 132 configured to create a persistent representation of text, graphics, or other markings on a substrate (e.g., label 131). The printing mechanism 132 can be configured to utilize a variety of different printing technologies. Some non-limiting examples include: thermal transfer printing, direct thermal printing, inkjet printing, laser printing, and dye sublimation.

[0031] Mobile device 101 is communicatively coupled to printing device 131, enabling a user of mobile device 101 to print items such as labels 133 on printing device 131. Mobile device 101 communicates with printing device 131 via a wireless or wired connection to transmit print commands and print data. Mobile device 101 is shown having multiple communication interfaces 112 that facilitate such communication with other devices.

[0032] The label printing system 100 also includes one or more servers 121. Each server 121 includes one or more processors 122 and a memory 123 communicatively coupled to the processors 122. The servers 121 are separate from the mobile device 101, and the mobile device 101 is communicatively coupled to the servers 121. In some embodiments, communication between the mobile device 101 and the servers 121 may occur via one or more computer networks 151. Communication between the mobile device 101 and the servers 121 may occur via wired and / or wireless technologies. The servers 121 are shown having multiple communication interfaces 134 facilitating communication with the mobile device 101.

[0033] Mobile device 101 includes a label printing module 104, which is software designed to facilitate the printing of labels 133. The label printing module 104 can be implemented in various ways. In some embodiments, the label printing module 104 is a standalone software application installed on mobile device 101. In other embodiments, the label printing module 104 can be implemented as one or more components integrated into a larger software application on mobile device 101. For example, in some embodiments, the label printing module 104 can be implemented as a library, extension, add-on, plugin, etc.

[0034] The label printing module 104 includes a user interface module 105 that facilitates user control of the label printing module 104. In some embodiments, the user interface module 105 enables the user to design, customize, and manage label printing tasks. The user interface module 105 may also facilitate user control by providing feedback and notifications, such as confirmation of successful printing or alerts to errors or necessary actions.

[0035] Mobile device 101 may include display screen 111, which is an output device for visually presenting information to a user. User interface module 105 may utilize display screen 111 to display a preview of label 133 before printing it. In some embodiments, display screen 111 may be a touchscreen that allows users to provide input via touch. Touchscreen functionality can enhance user interaction by allowing users to easily adjust the design of label 133 using touch gestures such as dragging, clicking, and pinching to zoom.

[0036] The label printing module 104 also includes a print execution module 109, which manages the interaction between the label printing module 104 and the printing device 131. In some embodiments, the print execution module 109 oversees the processing of print commands and generates print data that the printing device 131 can understand and execute. The print execution module 109 also processes the communication protocols required to transmit print data to the printing device 131, ensuring that the labels 133 are printed according to specified parameters and instructions.

[0037] Label printing module 104 is configured for voice-activated label design and printing. User interface module 105 includes voice input module 106 that facilitates the printing of label 133 via voice input. In this context, the term "voice input" refers to spoken words or utterances produced by a user with the intent to communicate with mobile device 101. Voice input encompasses a wide range of spoken language, including commands, instructions, requests, and dictation. Voice input module 106 is configured to capture user voice input regarding the label design process using microphone 110 within mobile device 101. Voice input module 106 also utilizes transcription module 108 on mobile device 101 and label intent module 124 on server(s)121 to interpret and execute user voice input related to the printing of label 133.

[0038] Transcription module 108 is configured to generate text transcription of user speech input. Transcription module 108 can be implemented using various speech recognition technologies capable of accurately transcribing spoken language into text data. In the illustrated system 100, transcription module 108 is shown as separate from label printing module 104. For example, in some embodiments, transcription module 108 may be included within the operating system of mobile device 101. Alternatively, transcription module 108 may be a separate module from both label printing module 104 and the operating system of mobile device 101, potentially acting as an external service or application. Although transcription module 108 is shown on the same mobile device 101 as label printing module 104, in some embodiments, these components may reside on different devices. Alternatively, in other embodiments, transcription module 108 may be included within label printing module 104 itself.

[0039] The label intent module 124 is configured to use the AI ​​model 125 to interpret the user's spoken input to determine the characteristics and content of the label 133 to be printed. In some embodiments, the AI ​​model 125 takes the form of a transducer-based language model. Transducer-based models, such as those in the GPT (Generative Pre-trained Transducer) family, are designed to understand and generate human-like text by leveraging their ability to process and analyze large amounts of contextual information. These models can be categorized as Large Language Models (LLMs) or Small Language Models (SLMs). Some non-limiting examples of LLMs include ChatGPT from OpenAI and Gemini from Google. Some non-limiting examples of SLMs include Phi-3 from Microsoft. While still transducer-based, SLMs can provide superior performance to LLMs in some embodiments. Other non-limiting examples of the AI ​​model 125 that can be used include BERT (Bidirectional Encoder Representation from Transducer) from Google, T5 (Text-to-Text Transfer Transducer) from Google, and RoBERTa (Robust Optimized BERT Pre-training Method) from Meta AI.

[0040] The tagging intent module 124 includes a preprocessing module 126 and an AI interface 127. In some embodiments, the preprocessing module 126 is responsible for processing the text transcription of the user's speech input (generated by the transcription module 108) by applying predefined substitution rules 128 to correct common transcription errors and standardize the text. The AI ​​interface 127 communicates with the AI ​​model 125 to interpret the text transcription and generate a data structure that the tag printing module 104 can use to print tags 133. The preprocessing module 126 and the AI ​​interface 127 will be described in more detail below.

[0041] In some embodiments, the label printing system 100 also includes a database referred to herein as a hint improvement database 129. The hint improvement database 129 may be configured to store hint / result pairs 130. Hint / result pairs 130 include a set of hints provided to the AI ​​model 125, and corresponding data structures generated by the AI ​​model 125 in response to the hint set. This will be discussed in more detail below. Hint / result pairs 130 facilitate the analysis and improvement of the performance of the label printing system 100 over time.

[0042] The tag intent module 124, AI model 125, and prompt improvement database 129 may reside on the same server 121 or be distributed across different servers 121. In some embodiments, the tag intent module 124, AI model 125, and prompt improvement database 129 may be located in the cloud. In this context, the term "cloud" refers to a network of remote servers hosted on the Internet that provides computing resources and services to users. These servers may be maintained and operated by a third-party cloud service provider. Cloud-based deployments offer several advantages, including elastic scalability and centralized management.

[0043] Figure 2 An example of processing associated with voice-activated printing of label 133, which can be performed on mobile device 101, is shown.

[0044] When a user provides voice input 140 to design and print label 133, microphone 110 can capture the voice input 140 and convert it into electrical signals. These electrical signals can then be processed by processor(s) 102 to generate a digital audio file 141 representing the user's verbal input. The digital audio file 141 can be stored (at least temporarily) in memory 103 of mobile device 101 for subsequent processing by transcription module 108.

[0045] Transcription module 108 can be configured to convert digital audio file 141 into text transcription, referred to hereinafter as initial text transcription 142-1. This conversion process may include processing digital audio file 141 using one or more speech recognition algorithms to convert audio signals into corresponding text. Transcription module 108 can utilize various techniques to accurately decipher spoken input and generate text representations of the original spoken words. Some examples of non-limiting techniques that can be utilized include: acoustic-phonetic modeling, which maps acoustic signals to phonetic units; language modeling, including n-gram models and neural network-based models such as recurrent neural networks (RNNs) and transducer-based models; and deep neural networks (DNNs) for learning complex speech patterns. Once the initial text transcription 142-1 is generated, it can be sent to tag intent module 124.

[0046] Figure 3 An example of the processing associated with the voice-activated printing of tag 133, which can be performed on server(s) 121, is shown.

[0047] The initial text transcription 142-1 generated by transcription module 108 can be processed by preprocessing module 126 to generate a modified text transcription 142-2. Preprocessing module 126 can modify the initial text transcription 142-1 according to predefined substitution rules 128. Substitution rules 128 can be designed to correct common or predictable errors that may occur during transcription. For example, preprocessing module 126 can replace frequently misunderstood phrases or words. In some embodiments, substitution rules 128 can also specify other types of text modifications. Some non-limiting examples of other text modifications include: converting text appearing on tag 133 to a consistent format, abbreviating certain terms (or conversely, expanding common abbreviations to their full forms), and replacing synonyms and variations of common command or content phrases with standardized terms.

[0048] In some embodiments, substitution rule 128 may include a series of commands that replace a particular term or phrase with another term or phrase. Non-limiting examples of such a series of commands are as follows:

[0049] Replace("roll","row")

[0050] Replace("-role","-row")

[0051] Replace("Tulane","two line")

[0052] Replace("bald","bold")

[0053] Replace("bowl","bold")

[0054] Replace("ball","bold")

[0055] Replace("Rowan","Row 1")

[0056] Replace("Nero","new row")

[0057] Replace("VRKR","BRKR")

[0058] Suppose that the initial text transcription 142-1 received by the preprocessing module 126 is “Tulane label 133allbaldallcaps firstline panelf fline two CKT space VRKR space sixty eight”. If the replacement rule 128 shown above is applied, the preprocessing module 126 will modify the initial text transcription 142-1 to create a modified text transcription 142-2, which contains “twolinelabelallbold allcaps firstline panelf fline two CKT space BRKR space sixty eight”.

[0059] In some embodiments, the replacement rule 128 can be dynamically adjusted based on additional user input 152-1 that differs from the voice input 140. This allows for customization and flexibility in how the initial text transcription 142-1 is modified before being processed by the AI ​​model 125.

[0060] For example, in some embodiments, the user interface module 105 may prompt the user to specify preferences or settings that affect replacement rule 128. Options may be provided to the user, such as whether to print numbers as numbers or words, whether to expand or abbreviate certain terms, or whether to apply industry-specific terminology replacements. Based on the user's choices, replacement rule 128 may be adjusted accordingly to ensure that the modified text transcription 142-2 conforms to the output format desired by the user.

[0061] In some embodiments, the label printing system 100 can be configured with multiple sets of different replacement rules 128 tailored to different industries, allowing users to select and apply a specific set of replacement rules 128 during the label design process. This feature allows the label printing system 100 to adapt the label design process to the unique terminology and requirements of various industries, ensuring the accuracy and relevance of the generated labels 133.

[0062] For example, a set of substitution rules 128 tailored for the medical industry might include specific terms and abbreviations commonly used in medical labeling, such as replacing “milligrams” with “mg” or “milliliters” with “ml”. Similarly, a set of substitution rules 128 tailored for the logistics industry might focus on terms related to transportation and handling, such as replacing “package” with “pkg” or “delivery” with “delv”. As another example, a set of substitution rules 128 tailored for the manufacturing industry might involve terms related to production and quality control, such as replacing “part number” with “PN”, “batch number” with “BN”, and “inspection date” with “insp.Date”. Those skilled in the art will recognize that specific substitution rules 128 can be created for other industries.

[0063] The modified text transcription 142-2 generated by the preprocessing module 126 can be provided to the AI ​​interface 127. The AI ​​interface 127 communicates with the AI ​​model 125 to generate a data structure 143 that can be used by the label printing module 104 to print labels 133. The AI ​​interface 127 can be configured to generate a set of prompts 144 to guide the AI ​​model 125 to accurately interpret the user's verbal instructions. For example, the prompt set 144 can be designed to enable the AI ​​model 125 to distinguish various elements in the modified text transcription 142-2 (such as the actual content to be included on the label 133 and any formatting instructions) and generate the desired data structure 143 for printing the label 133.

[0064] AI interface 127 can generate a prompt set 144 based on the modified text transcription 142-2. In some embodiments, AI interface 127 can also generate the prompt set 144 based on additional user input 152-2. In some embodiments, the additional user input 152-2 may include user preferences or settings that influence how the prompt set 144 is generated. For example, the user may specify a desired output format, the level of detail in formatting instructions, or specific terminology preferences. Based on the additional user input 152-2, AI interface 127 can customize the prompt set 144 to ensure that AI model 125 generates a data structure 143 consistent with user requirements.

[0065] The data structure 143 generated by AI model 125 can include information in two aspects: label content and formatting instructions. Label content refers to the actual text, graphics, or other information that will appear on the label 133. On the other hand, formatting instructions provide guidance on how this content should be arranged on the label 133. Examples of formatting instructions include style elements such as layout, size, alignment, color, font type, and similar attributes.

[0066] Multiple formats are available for data structure 143. In some embodiments, data structure 143 may be in the form of a JSON (JavaScript Object Notation) object, which organizes tag content and formatting instructions in a structured, hierarchical manner. In alternative embodiments, depending on requirements and compatibility with the tag printing module 104, other data formats such as XML (Extensible Markup Language) or YAML (YAML is not a markup language) may be used to represent data structure 143.

[0067] After the AI ​​model 125 generates the data structure 143, the data structure 143 can be sent to the label printing module 104. In some embodiments, the AI ​​model 125 can return the data structure 143 to the AI ​​interface 127, and the AI ​​interface 127 (or another component within the label intent module 124) can send the data structure 143 to the label printing module 104. Alternatively, another component within the label intent module 124 can also send the data structure 143 to the label printing module 104. After the label printing module 104 receives the data structure 143, the printing execution module 109 inside the label printing module 104 can use the data structure 143 to generate printing data and send the printing data to the printing device 131 to print the label 133.

[0068] Although the preprocessing module 126 is described above as being implemented within the tag intent module 124 on server(s) 121, it should be understood that other implementations are possible. In some embodiments, the preprocessing module 126 may be implemented within the mobile device 101, for example, within the tag printing module 104. This would allow the initial text transcription 142-1 to be preprocessed locally on the mobile device 101 before being sent to server(s) 121. As another example, the preprocessing module 126 may be implemented partly on the mobile device 101 and partly on server(s) 121. In such a distributed implementation, some preprocessing operations may be performed on the mobile device 101, while others may be performed on server(s) 121.

[0069] The use of the preprocessing module 126 is optional, and in some embodiments, the label printing system 100 may not include this component. In such embodiments, instead of passing the initial text transcription 142-1 to the preprocessing module 126, the label printing module 104 may directly transmit the initial text transcription 142-1 to the AI ​​interface 127. If the preprocessing module 126 is omitted in this manner, the label printing system 100 can rely on the transcription accuracy provided by the transcription module 108 and the interpretability of the AI ​​model 125 to ensure accuracy.

[0070] Since the techniques disclosed herein can be implemented in various ways, the term "text transcription" can refer to the initial text transcription 142-1 or the modified text transcription 142-2. For example, the statement "AI interface 127 generates a cue set 144 for AI model 125 based on text transcription" includes: (i) an embodiment in which preprocessing module 126 modifies the initial text transcription 142-1 to generate the modified text transcription 142-2 and AI interface 127 generates a cue set 144 based on the modified text transcription 142-2; and (ii) an embodiment in which the initial text transcription 142-1 is provided to AI interface 127 without using preprocessing module 126, and AI interface 127 generates a cue set 144 based on the initial text transcription 142-1.

[0071] After receiving data structure 143 from AI model 125, AI interface 127 can generate hint / result pairs 130. Hint / result pairs 130 include a set of hints 144 provided to AI model 125, and the corresponding data structure 143 received from AI model 125. AI interface 127 can store hint / result pairs 130 in a hint improvement database 129.

[0072] Over time, as many labels 133 are printed, a large number of prompt / result pairs 130 can be generated and stored in the prompt improvement database 129. As previously mentioned, the prompt / result pairs 130 help analyze and improve the performance of the label printing system 100 over time. For example, reviewing the prompt / result pairs 130 can provide insights into how various system prompts 144-1 and assistant prompts 144-2 affect the AI ​​model 125's interpretation of user prompts 144-3. This can generate ideas on how to improve system prompts 144-1 and / or assistant prompts 144-2.

[0073] In some embodiments, an operator may review the prompt / result pairs 130 stored in the prompt improvement database 129 to identify areas, patterns, or discrepancies where the AI ​​model 125's interpretation of user prompts 144-3 can be improved. For example, the reviewer may notice that certain formatting instructions are frequently misunderstood by the AI ​​model 125. Based on this observation, the reviewer may modify subsequent system prompts 144-1 to provide clearer guidance on handling these specific instructions. As another example, the reviewer may identify redundant or ambiguous prompts that can be improved or removed to streamline the label printing process. In some embodiments, this review process may be fully or partially automated by using machine learning algorithms to detect and suggest optimizations for the computer system.

[0074] Figure 4An example of a set of prompts 144 that can be generated by the AI ​​interface 127 is shown. The set of prompts 144 includes system prompts 144-1, assistant prompts 144-2, and user prompts 144-3.

[0075] System prompt 144-1 provides AI model 125 with general instructions on how to interpret the modified text transcription 142-2. System prompt 144-1 sets the context for AI model 125, guiding its overall approach when processing user's spoken input. System prompt 144-1 may include guidelines on distinguishing different types of information and ensuring that spoken input is accurately converted into a structured format. Specific examples of the instructions that may be included in system prompt 144-1 are described below.

[0076] Assistant prompt 144-2 specifies the format of the data structure 143 that AI model 125 should generate. In other words, assistant prompt 144-2 defines the pattern or template that AI model 125 should follow.

[0077] User prompt 144-3 contains a text transcription of the user's verbal input. In other words, user prompt 144-3 contains a representation of the verbal input that AI model 125 should process. Depending on whether preprocessing module 126 is used, this representation can be the initial text transcription 142-1 or a modified text transcription 142-2.

[0078] Figure 4 Examples of several statement types that may be included in system prompt 144-1 are shown. These examples illustrate how system prompt 144-1 provides the necessary context and guidance to ensure accurate interpretation and generation of data structure 143 for printing label 133.

[0079] System prompt 144-1 may include one or more general statements 144-1A to the AI ​​model 125 regarding how to interpret the text transcription. In some embodiments, the general statements(s) 144-1A may include statements describing the overall task that the AI ​​model 125 should perform. The following are examples of such statements:

[0080] Users will provide you with a description of the tags they want to create, and you will return a JSON structure that can be used to print the tags. This statement ensures that AI Model 125 understands its task: to interpret the user's verbal description (as represented in text transcription) and convert it into a specific format.

[0081] System prompt 144-1 may also include one or more statements instructing AI model 125 to ensure that data structure 143 conforms to the format specified by assistant prompt 144-2. Such statements(s) may be referred to herein as output format statements(s) 144-1B. In some embodiments, output format statements(s) 144-1B may include the following statements:

[0082] Here is an example of your output format:

[0083]

[0084] The output format specified in System Prompt 144-1 should match the output format specified in Assistant Prompt 144-2. For example, if System Prompt 144-1 contains the example output format described above, then the following is an example of the corresponding Assistant Prompt 144-2:

[0085]

[0086] In some embodiments, system prompt 144-1 may include one or more statements that enable AI model 125 to distinguish between portions of text transcription containing tag 133 (e.g., text to be printed on tag 133) and portions containing other information (such as formatting instructions). Such statements(s) may be referred to herein as content recognition statements(s) 144-1C. In some embodiments, content recognition statements 144-1C may include statements such as:

[0087] You are a label creation assistant. Users will ask you to generate labels for them. Capture one to multiple lines of text that will be printed on the label. The printable text of the label will be included in the `Textlines` array. Any descriptions or instructions will not be included in the `Textlines` array.

[0088] These statements ensure that AI model 125 can distinguish the actual text that should appear on label 133 from other spoken information.

[0089] In some embodiments, system prompts 144-1 may contain one or more statements instructing the AI ​​model 125 on how to correctly process specific terms and phrases. Such statements may be referred to herein as term / phrase processing statements(s) 144-1D. In some embodiments, term / phrase processing statements(s) 144-1D may contain statements such as:

[0090] The words “Row” and “Line” are interchangeable. A user may say “Row” or “Line”, which means the same thing. “Row One” is the same as “Line One”, “Row Two” is the same as “Line Two”, and so on.

[0091] In some embodiments, system prompt 144-1 may include one or more statements that cause AI model 125 to perform predefined substitutions in text transcription 142. Such statements(s) may be referred to herein as text substitution statements(s) 144-1E. For example, text substitution statements(s) 144-1E may include statements such as:

[0092] Before interpreting the tags, perform the following replacements on the user message in sequence:

[0093] If the last word in the user suggestion is 'and', replace it with 'end'.

[0094] If the word 'in' follows a number directly, 'in' should be converted to 'inch'.

[0095] If the words found, round, or bound appear before a number, replace them with the word pound.

[0096] The word zero should be converted to 0.

[0097] The word "one" should be changed to "1". ...

[0099] The word "colon" should be converted to:

[0100] The word dash should be converted to -.

[0101] The word "slash" should be converted to / .

[0102] Unless the word "number" is immediately preceded by the word "line", the word "number" should be converted to #.

[0103] The text substitution statements (multiple) 144-1E may be separate from and different from the aforementioned substitution rule 128. In some embodiments, although substitution rule 128 and the text substitution statements (multiple) 144-1E operate independently, they may be designed to complement each other. For example, substitution rule 128 may be designed to pre-process certain potential transcriptional problems, ensuring that text transcription 142 is as accurate and standardized as possible before being processed by AI model 125. Subsequently, the text substitution statements (multiple) 144-1E in system prompts 144-1 can provide an additional layer of optimization.

[0104] In some embodiments, system prompt 144-1 may include one or more statements that enable AI model 125 to identify and classify different types of labels 133. Such statements may be referred to herein as label classification statements(s) 144-1F. In some embodiments, label classification statements(s) 144-1F may include the following statements:

[0105] There are regular labels and wrap labels. The default label is regular, and IsWrap returns false. If the user requests the label wrap, wire, wire flag, wire marker, rap, cable, flag, and / or marker, then the user is describing a wrap label. Wrap labels will return IsWrap as true.

[0106] In some embodiments, system prompt 144-1 may include one or more statements that cause AI model 125 to set a default value for a label attribute when the user does not provide a specific value. Such statements(s) may be referred to herein as default value statements(s) 144-1G. In some embodiments, default value statements(s) 144-1G may include statements such as:

[0107] If the user does not specify text alignment, it will be centered by default.

[0108] If no length is provided, it defaults to zero.

[0109] The tag defaults to regular, and IsWrap returns false.

[0110] The default value for the number of portions is 1.

[0111] In some embodiments, system prompt 144-1 may include one or more statements that instruct AI model 125 to treat a specific word as a new line of text. Such statements(s) may be referred to herein as line break(s) 144-1H. In some embodiments, line break(s) 144-1H may include statements such as:

[0112] The following words indicate the start of a new text line and that input should move to the next line: carriage return, next line, newline, line break, newline, tab, Enter key, and back key.

[0113] In some embodiments, system prompt 144-1 may include one or more statements that enable AI model 125 to detect and appropriately process user-provided text alignment options. Such statements(s) may be referred to herein as text alignment statements(s) 144-1I. In some embodiments, text alignment statements(s) 144-1I may include the following statements:

[0114] Users can provide the following text alignment options: left, right, top, bottom, and center. If no text alignment option is provided by the user, center is the default. Do not print the alignment instructions.

[0115] In some embodiments, system prompt 144-1 may include one or more statements that cause AI model 125 to exclude a specific formatting instruction from the text printed on label 133. Such statements may be referred to herein as exclusionary formatting statements 144-1J. In some embodiments, exclusionary formatting statements 144-1J may include one or more of the following statements:

[0116] Do not print length information.

[0117] Do not print inches.

[0118] Do not print label types.

[0119] Do not print the length instruction.

[0120] Do not print the Row command.

[0121] Do not print the Line instruction.

[0122] Those skilled in the art will recognize that the types of statements provided in the foregoing paragraphs are intended only as illustrative examples. They are not exhaustive and should not be construed as limiting the scope of this disclosure.

[0123] Figure 5A , 5B Figures 5C and 5C illustrate examples of methods that can be performed by various components in the label printing system 100 to print label 133. The first part of this method, 500A, is as follows: Figure 5A As shown, the second part 500B of the method is as follows: Figure 5B As shown, the third part of the method, 500C, is as follows: Figure 5C As shown.

[0124] First refer to Figure 5A At point 501, the label printing module 104 receives user input instructing the user to print label 133. This user input can be provided via the user interface module 105 of the label printing module 104. The user input includes voice input 140, which comprises a verbal description of the label 133 that the user wants to print. Voice input 140 can describe various aspects of the label 133, such as the content to be included and formatting instructions. Formatting instructions can include specific instructions regarding the layout or arrangement of the text on the label 133. The voice input module 106 can capture this voice input 140 via the microphone 110 in the mobile device 101. As described above, the microphone 110 can capture the voice input 140 and generate a digital audio file 141 representing the user's verbal input.

[0125] At 502, in response to the voice input 140 received at 501, the voice input module 106 of the label printing module 104 provides the digital audio file 141 to the transcription module 108.

[0126] At 503, transcription module 108 uses one or more speech recognition algorithms to convert digital audio file 141 into initial text transcription 142-1. At 504, transcription module 108 returns the initial text transcription 142-1 to label printing module 104.

[0127] At 505, the label printing module 104 passes the initial text transcription 142-1 to the preprocessing module 126. At 506, the preprocessing module 126 modifies the initial text transcription 142-1 according to a set of predefined replacement rules 128. As mentioned above, the replacement rules 128 can be designed to correct common or foreseeable errors that may occur during transcription. The replacement rules 128 can also specify other types of text modifications.

[0128] At 507, the preprocessing module 126 passes the modified text transcription 142-2 to the AI ​​interface 127. At 508, the AI ​​interface 127 generates a cue set 144 for the AI ​​model 125 based on the modified text transcription 142-2. The cue set 144 is configured to enable the AI ​​model 125 to interpret the modified text transcription 142-2 and generate a data structure 143 for printing labels 133.

[0129] Now for reference Figure 5B At 509, AI interface 127 provides a prompt set 144 to AI model 125. At 510, AI model 125 generates a data structure 143 for printing label 133 based on the guidance provided by prompt set 144. As described above, user prompt 144-3 may include text transcription (e.g., initial text transcription 142-1 or modified text transcription 142-2 (if preprocessing module 126 is used)), and system prompt 144-1 may be designed to allow AI model 125 to interpret the text transcription to extract the details needed for the design of label 133, including both content and formatting instructions. This interpretation process ensures that the user's verbal commands are accurately translated into a specific label design. Furthermore, based on certain instructions contained in system prompt 144-1, AI model 125 ensures that data structure 143 matches the format specified by assistant prompt 144-2.

[0130] At 511, AI model 125 returns data structure 143 to AI interface 127. At 512, AI interface 127 (or another component in label intent module 124) provides this data structure 143 to label printing module 104.

[0131] At 513, the user interface module 105 of the label printing module 104 uses data structure 143 to present a visual representation of the label 133 on the display screen 111 of the mobile device 101. This allows the user to preview the label 133 before it is printed.

[0132] If the user is satisfied with the design, they can provide input through the user interface module 105, causing the label printing module 104 to initiate the printing of the label 133 via the printing device 131. At 514, the label printing module 104 receives this user input. At 515, in response to the user input received at 514, the print execution module 109 of the label printing module 104 generates print data for printing the label 133. This print data is based on data structure 143 received from the label intent module 124.

[0133] Now for reference Figure 5C At 516, the print execution module 109 sends print data to the print device 131. At 517, the print device 131 prints label 133 based on the print data received from the label printing module 104.

[0134] At 518, AI interface 127 generates a prompt / result pair 130. The prompt / result pair 130 includes a prompt set 144 provided to AI model 125 at 509, and a corresponding data structure 143 generated by AI model 125 at 510. At 519, AI interface 127 stores the prompt / result pair 130 in a prompt improvement database 129. As described above, the prompt / result pair 130 in prompt improvement database 129 can help analyze and improve the performance of label printing system 100 over time.

[0135] As described above, in some embodiments, the label printing system 100 can be configured with multiple sets of different replacement rules 128 that can be customized for different industries. In such embodiments, the label printing module 104 can be configured to prompt the user to select a set of replacement rules 128 to be applied via the user interface module 105. In other words, the label printing module 104 can request the user to input which set of replacement rules 128 should be applied. For example, a list of multiple sets of available replacement rules 128 categorized by industry can be displayed to the user. After a selection is made, the label printing module 104 can send the user's selection to the preprocessing module 126 to apply the correct set of replacement rules 128. Alternatively, the preprocessing module 126 itself can prompt the user to select an appropriate set of replacement rules 128.

[0136] By providing industry-specific replacement rules 128, the label printing system 100 can enhance its flexibility and adaptability, ensuring that the produced labels 133 meet the specific requirements and practices of the specific industry using the label printing system 100.

[0137] The techniques disclosed herein may be implemented in hardware, software, firmware, or any combination thereof, unless explicitly described as being implemented in a particular manner.

[0138] At least some of the features disclosed herein have been described as modules or instructions executable by a processor to perform various operations, actions, or other functions. The terms "module" and "instruction" should be interpreted broadly to include any type of computer-readable statement(s) executable by a processor to perform various operations, actions, or other functions. For example, the terms "module" and "instruction" can refer to one or more applications, programs, scripts, binaries, executable files, code, routines, subroutines, functions, procedures, classes, objects, components, libraries, frameworks, etc. A "module" or "instruction" can include a single computer-readable statement or multiple computer-readable statements. Furthermore, the "modules" and "instructions" described herein can be combined as needed in various embodiments.

[0139] The term "processor" should be interpreted broadly to include general-purpose processors, central processing units (CPUs), microprocessors, digital signal processors (DSPs), controllers, microcontrollers, state machines, etc. In some cases, "processor" can refer to application-specific integrated circuits (ASICs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), etc. The term "processor" can also refer to a combination of processing devices, such as a combination of a digital signal processor (DSP) and a microprocessor, multiple microprocessors, one or more microprocessors combined with a digital signal processor (DSP) core, or other similar configurations.

[0140] The term "memory" should be broadly interpreted to include any electronic component capable of storing electronic information. The term "memory" can refer to various types of processor-readable media, such as random access memory (RAM), read-only memory (ROM), non-volatile random access memory (NVRAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), flash memory, magnetic or optical data storage devices, registers, etc. If a processor can read information from and / or write information to a memory, the memory is said to be communicatively coupled to the processor. Memory integrated with a processor is communicatively coupled to the processor.

[0141] The term "communication coupling" refers to the way components are coupled, enabling them to communicate with each other via, for example, wired, wireless, or other communication media. "Communication coupling" can include direct communication coupling as well as indirect or "intermediate" communication coupling. For example, component A can be directly communication-coupled to component B via at least one communication path, or component A can be indirectly communication-coupled to component B via at least a first communication path that directly couples component A to component C and at least a second communication path that directly couples component C to component B. In this case, component C is said to mediate the communication coupling between component A and component B.

[0142] Any of the communication interfaces described herein may be based on wireless communication technology and / or wired communication technology. Some examples of communication interfaces based on wireless communication technology include Bluetooth wireless communication adapters, wireless adapters conforming to the Institute of Electrical and Electronics Engineers (IEEE) 802.11 wireless communication protocol, and infrared (IR) communication ports. Some examples of communication interfaces based on wired communication technology include Universal Serial Bus (USB) and Ethernet adapters.

[0143] The term "display" can refer to an interface component that provides a means for users to interact with computing devices and view output data in a visual form. Examples of display technologies that can be used in conjunction with the techniques disclosed herein include liquid crystal display (LCD) technology, organic light-emitting diode (OLED) technology, active-matrix OLED (AMOLED) technology, e-ink technology, microLED technology, and so on. Those skilled in the art will recognize that many other types of display technologies can be used in conjunction with the techniques disclosed herein.

[0144] The term "operating system" can refer to software that manages or controls the overall operation of a computing device by performing tasks such as managing hardware resources, running applications, implementing security and access control, managing files, and / or providing a user interface.

[0145] The term "determine" (and its grammatical variations) can encompass a wide range of actions. For example, "determine" can include calculation, computation, processing, derivation, investigation, searching (e.g., looking in a table, database, or other data structure), ascertaining, etc. Furthermore, "determine" can also include receiving (e.g., receiving information), accessing (e.g., accessing data in memory), etc. Additionally, "determine" can also include resolving, selecting, picking, establishing, etc.

[0146] The terms “include,” “contain,” and “have” are intended to be inclusive and mean that there may be other elements besides those listed.

[0147] The phrase “based on” does not mean “based on only” unless otherwise explicitly stated. In other words, the phrase “based on” describes both “based on only” and “based on at least”.

[0148] The steps, operations, and / or actions of the methods described herein may be interchanged without departing from the scope of the claims. In other words, unless a specific order of steps, operations, and / or actions is required for the proper functioning of the described methods, the order and / or use of steps, operations, and / or actions may be modified without departing from the scope of the claims.

[0149] The use of the terms "one embodiment" or "embodiment" in this disclosure is not intended to exclude the existence of other embodiments that also include the described features. For example, where compatible, any element or feature described in connection with an embodiment herein may be combined with any element or feature of any other embodiment described herein.

[0150] In the above description, reference numerals are sometimes used in conjunction with various terms. When a term is used in conjunction with a reference numeral, it may refer to a specific element shown in one or more figures. When a term is not used in conjunction with a reference numeral, it may mean that the term is used generally and is not limited to any particular figure.

[0151] This disclosure may be implemented in other specific forms without departing from its spirit or characteristics. The described embodiments should be considered illustrative rather than restrictive. Therefore, the scope of this disclosure is indicated by the appended claims rather than the foregoing description. Modifications falling within the meaning and equivalence of the claims should be included within the scope of the claims.

Claims

1. A label printing system for facilitating voice-activated label printing, the label printing system comprising: Printing equipment; A computing device communicationally coupled to the printing device, the computing device including a label printing module and a transcription module, the transcription module being configured to generate a text transcription of a voice input from a user of the computing device, the voice input including verbal instructions for a label to be printed; At least one server is communicatively coupled to the computing device, the at least one server including at least one processor, a memory communicatively coupled to the at least one processor, and a tag intent module stored in the memory, the tag intent module being executable by the at least one processor to: Based on the text transcription, a cue set is generated for the AI ​​model. The cue set is constructed to enable the AI ​​model to interpret the text transcription and generate a data structure for printing the label. Provide the set of prompts to the AI ​​model; The data structure, including tag content and formatting instructions, is received from the AI ​​model. as well as The data structure is provided to the label printing module, wherein the label printing module uses the data structure to print the label on the printing device.

2. The label printing system of claim 1, wherein the AI ​​model comprises a converter-based language model with contextual understanding capabilities, and the cue set is designed to utilize the contextual understanding capabilities of the converter-based language model.

3. The label printing system according to claim 1 further includes a preprocessing module, the preprocessing module being configured to modify the text transcription according to a replacement rule to generate a modified text transcription, wherein the modified text transcription is used to generate the cue set.

4. The label printing system of claim 3, wherein the replacement rule is dynamically adjusted based on additional user input different from the voice input.

5. The label printing system according to claim 3, wherein: The label printing system includes multiple sets of different replacement rules; and The label printing module is configured to request user input regarding which set of replacement rules should be used.

6. The label printing system according to claim 1, wherein the prompt set includes: Provide the AI ​​model with system prompts on how to interpret the text transcription; A helper prompt specifying the format of the data structure; as well as User prompts including the text transcription.

7. The label printing system of claim 1, further comprising a prompt improvement database configured to store prompt / result pairs, wherein each prompt / result pair includes: The set of prompts provided to the AI ​​model; as well as The AI ​​model responds to the corresponding data structure generated by the prompt set.

8. The label printing system of claim 1, wherein the label printing module includes a user interface module configured to present a visual representation of the label on a display screen of a computing device using the data structure prior to the label being printed.

9. A label printing system for facilitating voice-activated label printing via a label printing module, the label printing module operating on a computing device communicatively coupled to a printing device, the label printing system comprising: At least one processor; The memory of the at least one processor is coupled to the communication; Instructions stored in the memory, which can be executed by the at least one processor to: Text transcription based on voice input generates a cue set for an AI model, the voice input including verbal instructions for labels to be printed, and the cue set is designed to enable the AI ​​model to interpret the text transcription and generate a data structure for printing the labels; Provide the set of prompts to the AI ​​model; The data structure, including tag content and formatting instructions, is received from the AI ​​model. as well as The data structure is provided to the label printing module, wherein the label printing module uses the data structure to print the label on the printing device.

10. The label printing system of claim 9, wherein the AI ​​model comprises a converter-based language model with contextual understanding capabilities, and the cue set is designed to utilize the contextual understanding capabilities of the converter-based language model.

11. The label printing system according to claim 9, wherein: The instructions can also be executed by the at least one processor to modify the text transcription according to the replacement rules to generate a modified text transcription; as well as The modified text transcription is used to generate the cue set.

12. The label printing system of claim 11, wherein the instructions can also be executed by the at least one processor to dynamically adjust the replacement rules based on additional user input other than the voice input.

13. The label printing system according to claim 12, wherein: The label printing system includes multiple sets of different replacement rules; and The instruction can also be executed by the at least one processor to request user input regarding which set of replacement rules should be used.

14. The label printing system of claim 9, wherein the prompt set comprises: Provide the AI ​​model with system prompts on how to interpret the text transcription; A helper prompt specifying the format of the data structure; as well as User prompts including the text transcription.

15. The label printing system of claim 9, wherein the instructions can also be executed by the at least one processor to store the prompt set and the data structure as prompt / result pairs in the prompt improvement database.

16. The label printing system of claim 9, wherein the system prompt includes an instruction to the AI ​​model to ensure that the data structure conforms to the format specified in the assistant prompt.

17. The label printing system of claim 9, wherein the system prompting includes instructions given to the AI ​​model to distinguish between portions of the text transcription that include the label content and portions of the text transcription that include other information about the label.

18. The label printing system of claim 9, wherein the system prompts include instructions given to the AI ​​model for identifying and classifying different types of labels.

19. The label printing system of claim 9, wherein the system prompts include instructions given to the AI ​​model on how to properly handle numeric characters and special characters.

20. A computer-readable medium configured to facilitate voice-activated label printing, the computer-readable medium comprising instructions executable by at least one processor to: Text transcription based on user voice input from a computing device generates a cue set for an AI model, the voice input including verbal instructions for labels to be printed, the cue set being configured to enable the AI ​​model to interpret the text transcription and generate a data structure for printing the labels; Provide the set of prompts to the AI ​​model; The data structure, including tag content and formatting instructions, is received from the AI ​​model. as well as The data structure is provided to the label printing module, wherein the label printing module uses the data structure to print the label on a printing device.

Images