Parameter recommendation method, apparatus, device and medium for a laundry treatment apparatus

Abstract

The application belongs to the technical field of electrical appliances, and particularly relates to a parameter recommendation method and device of a clothes processing equipment, equipment and medium, comprising the following steps: determining multiple clothes processing intentions according to historical data corresponding to a user; the historical data comprises historical use parameters of the clothes processing equipment and / or historical clothes processing intentions selected by the user; in response to a triggering operation of a terminal on a control page, multiple clothes processing intentions are displayed; in response to a parameter recommendation request of the terminal, at least one first clothes processing intention selected by the user is obtained; a parameter corresponding to the first clothes processing intention is obtained through a large language model; and the parameter is sent to the terminal, so that the control page displays the parameter. The method can effectively reduce the cognitive burden of the user when using the clothes processing equipment, reduce clothes damage and poor washing effect caused by misoperation or contradictory parameter selection, enhance the user experience, and improve the equipment usability.

Description

Technical Field

[0001] This application belongs to the field of electrical technology, specifically relating to a method, apparatus, equipment, and medium for recommending parameters for a garment processing device. Background Technology

[0002] With the popularization of smart home appliances, clothing processing equipment has gradually acquired many customizable parameters, such as water temperature, washing power, spin speed, additive type and washing time. While these rich options have improved the flexibility of clothing processing, they have also increased the complexity of operation.

[0003] On the one hand, a wide variety of parameters can overburden users' cognitive load, making it difficult for them to understand the specific functions of each parameter. On the other hand, too much freedom of choice can easily lead users to misadjust parameters, which may damage clothes or result in poor washing effects, causing users to have concerns. In addition, users may also easily select conflicting washing and care needs at the same time, which will cause problems such as clothes not being treated or clothes being damaged. Summary of the Invention

[0004] To address the aforementioned issues, this application provides a method, apparatus, equipment, and medium for recommending parameters for a garment processing device.

[0005] In a first aspect, this application provides a method for recommending parameters for a garment processing device, the method comprising:

[0006] Based on the user's historical data, multiple clothing processing intentions are determined; the historical data includes the historical usage parameters of the clothing processing equipment and / or the clothing processing intentions selected by the user in the past.

[0007] In response to the terminal's trigger operation on the control page, multiple clothing processing intentions are displayed;

[0008] In response to the terminal's parameter recommendation request, obtain at least one of the user's initial clothing processing intentions;

[0009] The parameters corresponding to the first clothing processing intent are obtained through a large language model; and the parameters are sent to the terminal so that the control page displays the parameters.

[0010] In one possible implementation, determining multiple clothing processing intentions based on the user's corresponding historical data includes:

[0011] Use the user's historically selected clothing processing intent as the first candidate intent;

[0012] Based on the historical usage parameters of the garment processing equipment, determine the corresponding second candidate intent;

[0013] Based on the first candidate intent and the second candidate intent, determine the target candidate intent and the relevance score corresponding to each target candidate intent;

[0014] Based on the target candidate intent and the corresponding relevance score, multiple clothing processing intents are determined.

[0015] In one possible implementation, the historical usage parameters include multiple sets of parameter combinations, each set of parameter combinations including multiple parameter items and a parameter value corresponding to each parameter item. Determining the corresponding second candidate intent based on the historical usage parameters of the clothing processing equipment includes:

[0016] For each of the parameter combinations, a corresponding reference parameter combination is matched; the reference parameter combination includes multiple parameter items and a range of parameter values ​​for each parameter item.

[0017] Based on the reference parameter combination to which each parameter combination belongs, a corresponding second candidate intent is determined; the reference parameter combination and the second candidate intent have a corresponding relationship.

[0018] In one possible implementation, determining the target candidate intent and the relevance score corresponding to each target candidate intent based on the first candidate intent and the second candidate intent includes:

[0019] The relevance score of the first candidate intent is determined based on the number of selections corresponding to the first candidate intent; the number of selections and the relevance score are positively correlated.

[0020] The relevance score of the second candidate intent corresponding to the parameter combination is determined based on the number of times the parameter combination is used; the number of times it is used and the relevance score are positively correlated.

[0021] Determine whether there is a common intent between the first candidate intent and the second candidate intent; if so, redetermine the relevance score of the common intent for additional processing.

[0022] The same intent, the first candidate intent other than the same intent, and the second candidate intent, along with their respective relevance scores, are taken as the target candidate intent and their corresponding relevance scores.

[0023] In one possible implementation, if the number of first clothing processing intentions selected by the user is multiple, before obtaining the parameters corresponding to the first clothing processing intentions through the large language model, the method further includes:

[0024] Determine whether there is a conflict among multiple first clothing processing intentions; if so, determine the corresponding conflict level based on a preset mapping relationship; the mapping relationship is used to indicate the correspondence between multiple conflicting first clothing processing intentions and conflict levels.

[0025] If the conflict level is greater than the preset level, then a second clothing processing intention is obtained by selecting from multiple conflicting first clothing processing intentions.

[0026] If the conflict level is less than or equal to the preset level, then based on the multiple first clothing processing intentions of the conflict, the value range of the corresponding associated target parameters is determined.

[0027] In one possible implementation, the determination of the value range of the corresponding associated target parameter based on the conflict-based multiple first clothing processing intentions includes:

[0028] Based on the different preset value ranges of multiple first clothing processing intentions under the same target parameter, determine whether there is an intersection between the different preset value ranges;

[0029] If so, the preset value range corresponding to the intersection is the value range of the target parameter;

[0030] If not, determine at least two boundary values ​​that are closest in distance between different preset value ranges, and then take the range formed by the at least two boundary values ​​as the value range of the target parameter.

[0031] In one possible implementation, obtaining the parameters corresponding to the first clothing processing intent through a large language model includes:

[0032] Based on the preset prompt word template, and the first clothing processing intention, or the second clothing processing intention, or the first clothing processing intention and the corresponding target parameter value range, a prompt word is generated;

[0033] The prompt word is input into the large language model, and the parameters output by the large language model are obtained.

[0034] Secondly, this application provides a parameter recommendation device for a garment processing equipment, the device comprising:

[0035] The analysis module is used to determine multiple clothing processing intentions based on the user's historical data; the historical data includes historical usage parameters of the clothing processing equipment and / or the clothing processing intentions selected by the user in the past.

[0036] In one possible implementation, the analysis module is specifically used for:

[0037] Use the user's historically selected clothing processing intent as the first candidate intent;

[0038] Based on the historical usage parameters of the garment processing equipment, determine the corresponding second candidate intent;

[0039] Based on the first candidate intent and the second candidate intent, determine the target candidate intent and the relevance score corresponding to each target candidate intent;

[0040] Based on the target candidate intent and the corresponding relevance score, multiple clothing processing intents are determined.

[0041] In one possible implementation, the historical usage parameters include multiple sets of parameter combinations, each set of parameter combinations including multiple parameter items and a parameter value corresponding to each parameter item. The analysis module is specifically used for:

[0042] For each of the parameter combinations, a corresponding reference parameter combination is matched; the reference parameter combination includes multiple parameter items and a range of parameter values ​​for each parameter item.

[0043] Based on the reference parameter combination to which each parameter combination belongs, a corresponding second candidate intent is determined; the reference parameter combination and the second candidate intent have a corresponding relationship.

[0044] In one possible implementation, the analysis module is specifically used for:

[0045] The relevance score of the first candidate intent is determined based on the number of selections corresponding to the first candidate intent; the number of selections and the relevance score are positively correlated.

[0046] The relevance score of the second candidate intent corresponding to the parameter combination is determined based on the number of times the parameter combination is used; the number of times it is used and the relevance score are positively correlated.

[0047] Determine whether there is a common intent between the first candidate intent and the second candidate intent; if so, redetermine the relevance score of the common intent for additional processing.

[0048] The same intent, the first candidate intent other than the same intent, and the second candidate intent, along with their respective relevance scores, are taken as the target candidate intent and their corresponding relevance scores.

[0049] The display module is used to respond to the terminal's trigger operation on the control page and display multiple clothing processing intentions;

[0050] The acquisition module is used to acquire at least one first clothing processing intention selected by the user in response to the parameter recommendation request from the terminal;

[0051] The processing module is used to obtain the parameters corresponding to the first clothing processing intention through a large language model; and send the parameters to the terminal so that the control page displays the parameters.

[0052] In one possible implementation, if the number of first clothing processing intentions selected by the user is multiple, the processing module is further configured to:

[0053] Determine whether there is a conflict among multiple first clothing processing intentions; if so, determine the corresponding conflict level based on a preset mapping relationship; the mapping relationship is used to indicate the correspondence between multiple conflicting first clothing processing intentions and conflict levels.

[0054] If the conflict level is greater than the preset level, then a second clothing processing intention is obtained by selecting from multiple conflicting first clothing processing intentions.

[0055] If the conflict level is less than or equal to the preset level, then based on the multiple first clothing processing intentions of the conflict, the value range of the corresponding associated target parameters is determined.

[0056] In one possible implementation, the processing module is specifically used for:

[0057] Based on the different preset value ranges of multiple first clothing processing intentions under the same target parameter, determine whether there is an intersection between the different preset value ranges;

[0058] If so, the preset value range corresponding to the intersection is the value range of the target parameter;

[0059] If not, determine at least two boundary values ​​that are closest in distance between different preset value ranges, and then take the range formed by the at least two boundary values ​​as the value range of the target parameter.

[0060] In one possible implementation, the processing module is specifically used for:

[0061] Based on the preset prompt word template, and the first clothing processing intention, or the second clothing processing intention, or the first clothing processing intention and the corresponding target parameter value range, a prompt word is generated;

[0062] The prompt word is input into the large language model, and the parameters output by the large language model are obtained.

[0063] Thirdly, this application provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of the first aspects.

[0064] Fourthly, this application provides an electronic device, comprising: at least one processor and a memory; wherein,

[0065] The memory stores computer-executed instructions;

[0066] The at least one processor executes computer execution instructions stored in the memory, causing the at least one processor to perform the method as described in any of the first aspects.

[0067] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, can implement the steps of the method as described in any of the first aspects.

[0068] The parameter recommendation method, apparatus, device, and medium for garment processing equipment provided in this application analyze historical user data, including equipment parameters and garment processing intentions, to determine multiple possible garment processing intentions and provide users with recommendations that better meet their needs. When a user triggers the control page of the terminal device, multiple garment processing intentions are displayed for the user to choose from. After the user selects an intention, the selected intention is obtained, and a specific parameter recommendation is generated by combining historical data, equipment parameter ranges, and predefined rules using a large language model. The generated parameters are sent to the user's terminal device so that the control page displays the recommended parameters. This method effectively reduces the cognitive burden on users when using garment processing equipment, reduces garment damage and poor washing results caused by misoperation or conflicting parameter selections, and can accurately recommend parameter settings that meet user needs. At the same time, the intuitive option display avoids the need for users to understand complex parameters, allowing users to independently select processing intentions that meet their needs, enhancing the user experience and improving equipment usability. Attached Figure Description

[0069] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0070] Figure 1 The flowchart of the parameter recommendation method for the garment processing equipment provided in the embodiments of this application Figure 1 ;

[0071] Figure 2 This is a schematic diagram of the control interface provided in an embodiment of this application;

[0072] Figure 3 The flowchart of the parameter recommendation method for the garment processing equipment provided in the embodiments of this application Figure 2 ;

[0073] Figure 4 The flowchart of the parameter recommendation method for the garment processing equipment provided in the embodiments of this application Figure 3 ;

[0074] Figure 5 A parameter recommendation device diagram for a garment processing equipment provided in an embodiment of the present invention;

[0075] Figure 6 This is a hardware schematic diagram of an electronic device provided in an embodiment of the present invention.

[0076] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0077] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0078] The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented, for example, in orders other than those illustrated or described herein.

[0079] In this application, the terms "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0080] To address the problems in existing technologies, this application provides a parameter recommendation method for clothing processing equipment. By analyzing historical user data (including historical device parameter settings and user-selected clothing processing intentions), a user behavior pattern is constructed. This historical data reflects user preferences and habits, thus more accurately predicting current user needs. When a user triggers the control page, multiple possible clothing processing intentions are displayed instead of directly presenting the user with complex parameter selections. This design reduces the user's cognitive burden, allowing them to express their needs more intuitively. After the user selects a specific clothing processing intention, a large language model is used to obtain parameter settings related to that intention and recommends these parameters to the user. The large language model's role is to understand the semantics of the user's intention and translate it into specific parameter combinations. Ultimately, the recommended parameters can be sent to the terminal device for user confirmation or direct control of the clothing processing equipment's operation.

[0081] This method, by combining historical user data and large language modeling technology, effectively reduces the cognitive burden on users when using garment processing equipment, minimizing garment damage and poor washing results caused by misoperation or conflicting parameter selection. By analyzing users' historical usage habits and selection intentions, it can accurately recommend parameter settings that meet user needs, thereby simplifying the operation process and improving user experience and the equipment's intelligence level. Simultaneously, the intuitive option display avoids the need for users to understand complex parameters, making operation simpler and easier to understand. Users can independently choose processing intentions that meet their own needs, enhancing the user experience and improving equipment usability.

[0082] The technical solutions of this application and how they solve the aforementioned technical problems are described in detail below with specific embodiments. These specific embodiments may exist independently or in combination with each other. Similar or identical concepts or processes may not be repeated in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0083] This embodiment provides a method for recommending parameters for clothing processing equipment. Figure 1 The flowchart of the parameter recommendation method for the garment processing equipment provided in the embodiments of this application Figure 1 The method includes:

[0084] S101. Based on the user's historical data, determine multiple clothing processing intentions.

[0085] The historical data includes historical usage parameters of the garment processing equipment and / or the garment processing intentions selected by users in the past.

[0086] In this step, historical data reflects user patterns in different contexts, such as selection habits at specific times, in specific seasons, or with specific clothing types. By analyzing historical usage data, we can understand user preferences and habits, thereby providing users with more clothing processing intention recommendations that meet their needs. Historical data includes, but is not limited to, historical usage parameters of the clothing processing equipment (such as water temperature, spin speed, washing time, etc.) and the user's historical selected clothing processing intentions (such as "quick wash," "energy-saving mode," etc.). Clothing processing intention refers to a user's specific needs or goals when using the clothing processing equipment, such as "removing stubborn stains" or "protecting clothing fibers." Clothing processing intention can be explicitly selected by the user or implicitly inferred through analysis of user behavior.

[0087] For example, the device's sensors or a client application can record the user's intent regarding parameter settings and selections each time they use the laundry detergent. This includes parameters such as water temperature, washing time, spin speed, and the user's chosen washing mode (e.g., "cotton / linen" or "synthetic"). Furthermore, machine learning algorithms or statistical analysis can be used to extract user behavior patterns and preferences from historical data. For instance, cluster analysis can be used to categorize user usage scenarios, or association rule mining can be used to discover parameter combinations that users tend to choose in specific situations. Based on the analysis results, a user intent model can be constructed, transforming the user's needs into multiple possible laundry detergent intentions. For example, if a user frequently selects "quiet mode" at night, it can be inferred that the user has an intent to "wash in low noise."

[0088] S102. In response to the terminal's trigger operation on the control page, display multiple clothing processing intentions.

[0089] In this step, displaying the garment processing intent on the terminal device simplifies complex parameter selection into intuitive intent selection, thereby reducing the user's cognitive burden and making the operation simpler and easier to understand. Simultaneously, the portability and interactivity of the terminal device provide a more flexible user experience, allowing users to adjust garment processing device settings anytime, anywhere via mobile devices. The terminal refers to the device through which the user interacts with the garment processing device, such as a smartphone or tablet. It typically refers to a device with touchscreen and network connectivity, facilitating user operation and settings. The control page refers to the interface through which the user operates the garment processing device, and this page may include, but is not limited to, parameter settings and intent selection functions.

[0090] For example, a user opens a control page via their terminal device to display clothing processing intentions. Triggering actions could include clicking the application icon, long-pressing a device button, etc. Multiple clothing processing intentions are dynamically generated and displayed based on the user's historical data and current needs. The display format can be a list, icons, cards, etc., with each intention having a clear description and icon for easy understanding and selection by the user. The user selects the clothing processing intention that best suits their needs on the control page. User interaction can be achieved through simple actions such as swiping and clicking to complete the selection.

[0091] S103. In response to the terminal's parameter recommendation request, obtain at least one first clothing processing intention selected by the user.

[0092] S104. Obtain the parameters corresponding to the first clothing processing intention through the large language model; and send the parameters to the terminal so that the control page displays the parameters.

[0093] It should be noted that a parameter recommendation request is a request initiated by the user through their terminal device, requesting specific parameter settings to be recommended based on the selected intent. The request can be explicit, such as when the user clicks the "Recommend Parameters" button; or implicit, such as when the request is automatically generated after the user selects a certain intent. The primary clothing processing intent refers to the specific clothing processing intent selected by the user on the control page. This is the user's most pressing need at present, and parameter recommendations should be made based on this. For example, when receiving a parameter recommendation request sent by the user through their terminal device, in addition to the primary clothing processing intent selected by the user, the request can also carry other possible contextual information, such as the current ambient temperature, current time, and water quality.

[0094] Large language models refer to existing natural language processing models that can understand user intent and generate appropriate parameter settings. Large language models possess powerful semantic understanding and text generation capabilities, enabling them to handle complex user needs. By introducing large language models, complex user requirements can be addressed, providing more intelligent parameter recommendation services. The parameters output by the large model are recommended based on the user's initial garment processing intent (such as water temperature and washing time).

[0095] For example, the user's selected clothing processing intention can be used as input and passed to a large language model. The input can be in text form or structured data form, etc. The large language model performs semantic analysis on the intention, extracting key information (such as clothing type, washing requirements, etc.). Based on the semantic analysis results, parameter settings that meet the user's needs are generated.

[0096] Furthermore, the generation process of a large language model can incorporate historical data, device parameter ranges, and predefined rules. Device parameter ranges refer to the constraints on device operation and can also include ranges of parameters commonly used by users, such as water temperature, spin speed, and washing time. When generating parameters, it is essential to ensure that the recommended parameters are within the device's allowable range to avoid equipment malfunctions or clothing damage caused by parameters exceeding these limits. Predefined rules are fundamental to ensuring the rationality and safety of parameter settings. For example, certain types of clothing (such as silk and wool) require specific washing parameters; these rules can be predefined and stored in a rule base.

[0097] The aforementioned device parameter ranges and predefined rules can be integrated using structured prompt words to obtain the final prompt words used as input to the large language model, enabling the large language model to output the required content based on the prompt words.

[0098] For example, the generated parameters are sent to the user's terminal device. After the recommended parameters are displayed in real time on the control page, the user can also confirm or adjust the parameters on the control page. The user confirmation process can provide some interactive functions, such as parameter adjustment sliders and confirmation buttons.

[0099] The parameter recommendation method for clothing processing equipment provided in this embodiment analyzes the user's historical usage data, including equipment parameters and clothing processing intentions, to determine multiple possible clothing processing intentions and provide recommendations that better meet the user's needs. When the user triggers the control page of the terminal device, multiple clothing processing intentions are displayed for the user to choose from. After the user selects an intention, the method obtains the user's selected intention and generates specific parameter recommendations by combining historical data, equipment parameter ranges, and predefined rules using a large language model. The generated parameters are sent to the user's terminal device so that the control page displays the recommended parameters. This method can effectively reduce the cognitive burden on users when using clothing processing equipment, reduce clothing damage and poor washing results caused by misoperation or conflicting parameter selections, and accurately recommend parameter settings that meet the user's needs. At the same time, the intuitive option display avoids the user's understanding of complex parameters, allowing the user to independently select the processing intention that meets their needs, enhancing the user experience and improving the usability of the equipment.

[0100] Figure 2 This is a schematic diagram of the control interface provided in an embodiment of this application. Figure 2As shown, this control interface is used to control the garment processing equipment. When a user triggers this control page through a terminal device, the content shown in the figure can be displayed. Users can enter a custom program name in the program name field for easy identification and memorization. This program name can also be used to distinguish and store corresponding parameter settings. When a user selects a program with historical settings, this program name can be displayed for direct selection. The garment processing intent section provides multiple tabs or buttons, allowing users to select different intents based on their laundry needs, such as "Cotton," "Lightly Stained," "Energy Saving," "Quick Wash," "Clothes Protection," "Sterilization," "Night Mode," "Children's Clothing," and "Allergy Protection." After selecting the garment processing intent, the user can click the parameter recommendation button to analyze and process the selected intent, obtaining appropriate parameters. The generated parameters are displayed in the garment processing parameter section at the bottom of the control page, such as the number of rinses, washing time, washing temperature, spin speed, main wash rotation time, and main wash stop time. Users can also manually click on a parameter to modify it. After confirming the parameters, the user can click the "Save" button to save the current garment processing program.

[0101] This embodiment provides a method for recommending parameters for clothing processing equipment. Figure 3 The flowchart of the parameter recommendation method for the garment processing equipment provided in the embodiments of this application Figure 2 .like Figure 3 As shown, in this embodiment... Figure 1 Based on the embodiments, the process of determining multiple clothing processing intentions based on the user's corresponding historical data is described in detail. This method includes:

[0102] S301, The user's historically selected clothing processing intent is taken as the first candidate intent.

[0103] S302. Determine the corresponding second candidate intent based on the historical usage parameters of the garment processing equipment.

[0104] It's important to note that analyzing a user's historical clothing selection intentions allows for the rapid capture of user preferences and habits, providing a foundation for subsequent recommendations. The user's clothing selection intentions can be extracted from their historical records, and this data can be stored in a database, recording the specific intention for each use. To improve data effectiveness, the frequency of each intention selection can be calculated, selecting the most frequent intentions as candidates. Furthermore, more recent selections can be assigned higher weights to ensure that recommended intentions better align with the user's current needs.

[0105] Considering only the user's historical selection intent may not provide a comprehensive understanding of their needs. This is because user choices can be influenced by specific contexts (such as clothing type and stain severity) and may be subject to change. Furthermore, users may determine program parameters in various ways, not limited to the initial selection. Therefore, considering the device's historical usage parameters allows for a more accurate reconstruction of the user's usage scenarios, leading to recommendations that better match actual needs. Historical usage parameters of the garment processing equipment (such as water temperature, spin speed, and washing time) reflect the equipment's operating status and effectiveness in different scenarios. For example, a user might habitually set the water temperature to 40℃ and the spin speed to 800 rpm when washing cotton clothing. These parameters, reflecting the intended garment processing, provide further insight into the user's actual usage habits.

[0106] For example, parameter data can be extracted from the historical usage records of the garment processing equipment, including water temperature, spin speed, and washing time for each use. The corresponding garment processing intent is determined as a second candidate intent based on the parameter combination selected by the user each time. Parameter combinations can be mapped to multiple intents; for example, the parameter combination "water temperature 40℃, spin speed 800 rpm, washing time 15 minutes" might correspond to two intents: "standard wash" and "energy-saving mode." The mapping rules between parameter combinations and intents can be comprehensively considered by combining the user's historically selected intents with the corresponding parameter combinations used.

[0107] For example, the historical usage parameters include multiple sets of parameter combinations, each set of parameter combinations includes multiple parameter items and a parameter value corresponding to each parameter item, and the step of determining the corresponding second candidate intent based on the historical usage parameters of the clothing processing equipment includes:

[0108] For each of the parameter combinations, a corresponding reference parameter combination is matched; the reference parameter combination includes multiple parameter items and a range of parameter values ​​for each parameter item.

[0109] Based on the reference parameter combination to which each parameter combination belongs, a corresponding second candidate intent is determined; the reference parameter combination and the second candidate intent have a corresponding relationship.

[0110] The above example, by matching a user's historical usage parameters with predefined combinations of reference parameters, can more accurately determine the user's needs in different scenarios, thereby generating reasonable second candidate intents. Reference parameter combinations provide a standardized template to help understand and categorize users' historical usage parameters. A reference parameter combination includes a set of standardized parameter templates, each containing multiple parameter items and their corresponding parameter value ranges. These can be determined based on the device's practical performance, user feedback, and industry standards. For example, a suitable matching algorithm can be used to match each set of historical parameter combinations with the reference parameter combinations. For instance, for each parameter item, it can be determined whether the historical parameter value falls within the parameter value range of the reference parameter combination. If all parameter items match, the historical parameter combination is considered to belong to that reference parameter combination. Each reference parameter combination predefines one or more corresponding clothing processing intents. Matching reference parameter combinations can be directly mapped to corresponding intents, which can then serve as second candidate intents for the corresponding historical parameter combination.

[0111] S303. Based on the first candidate intent and the second candidate intent, determine the target candidate intent and the relevance score corresponding to each target candidate intent.

[0112] In this step, by integrating the user's historical clothing processing intentions and the clothing processing intentions corresponding to historical usage parameters, a comprehensive analysis and determination of the user's needs can be achieved. Combining a scoring method to quantify the rationality of recommendations can improve the accuracy and personalization of recommendations. Target candidate intentions can represent a set of intentions obtained by simply merging the first and second candidate intentions, or a set of intentions after further selection from the first and second candidate intentions (such as weighted average, rule-based filtering, etc.). Relevance score is a quantitative indicator used to measure the degree of matching between each target candidate intention and the user's needs. For example, the relevance score of each target candidate intention can be determined based on a pre-set relevance score model. Alternatively, the relevance score can be determined based on the user's actual selection enthusiasm / feedback on relevant parameters used under each target candidate intention.

[0113] For example, determining the target candidate intent and the relevance score corresponding to each target candidate intent based on the first candidate intent and the second candidate intent includes:

[0114] The relevance score of the first candidate intent is determined based on the number of selections corresponding to the first candidate intent; the number of selections and the relevance score are positively correlated.

[0115] The relevance score of the second candidate intent corresponding to the parameter combination is determined based on the number of times the parameter combination is used; the number of times it is used and the relevance score are positively correlated.

[0116] Determine whether there is a common intent between the first candidate intent and the second candidate intent; if so, redetermine the relevance score of the common intent for additional processing.

[0117] The same intent, the first candidate intent other than the same intent, and the second candidate intent, along with their respective relevance scores, are taken as the target candidate intent and their corresponding relevance scores.

[0118] It's important to note that the number of selections directly reflects a user's preference for and frequency of use of a specific intent. A higher selection frequency indicates that the intent aligns more closely with the user's daily needs and habits, thus earning a higher relevance score. Similarly, the frequency of use of parameter combinations reflects their effectiveness in actual use and user acceptance. Higher usage frequency indicates that the parameter combination performs well in device operation and meets the user's specific needs, thus also earning a higher relevance score. Considering that the first and second candidate intents may contain identical intents, these identical intents indicate that they not only conform to user habits but also match the device's standard operating parameters. Increasing the relevance score for identical intents ensures that the intent has a higher priority in the recommendation list, thereby more accurately meeting user needs. This avoids duplicate recommendations, optimizes recommendation results, and improves the user experience.

[0119] S304. Based on the target candidate intent and the corresponding relevance score, determine multiple clothing processing intents.

[0120] In this step, relevance scoring allows for the filtering of multiple clothing processing intents that best meet the user's needs, enabling the user to find the intent that best suits their requirements from among several options. For example, target candidate intents can be sorted from highest to lowest relevance score, and the top N intents with the highest scores can be selected as the final recommendation. Alternatively, a scoring threshold can be defined, and only intents with relevance scores above that threshold can be selected as the final recommendation. Alternatively, a weighted scoring system can be applied to target candidate intents, taking into account both the user's historical preferences and the device's optimal operating parameters. For instance, user preference weights and device performance weights could be set to 0.6 and 0.4 respectively, and then sorted and filtered based on the weighted scores.

[0121] The parameter recommendation method for clothing processing equipment provided in this embodiment analyzes the user's historical clothing processing intentions and the equipment's historical usage parameters, combines the two to determine target candidate intentions and their relevance scores, and then filters out multiple clothing processing intentions based on the relevance scores, achieving accurate recommendations. This method reduces the difficulty of selection for users, improves operational convenience, optimizes equipment operation, and enhances user experience and the level of equipment intelligence.

[0122] This embodiment provides a method for recommending parameters for clothing processing equipment. Figure 4 The flowchart of the parameter recommendation method for the garment processing equipment provided in the embodiments of this application Figure 3 .like Figure 4 As shown, the method includes:

[0123] S401. Obtain at least one first clothing processing intent selected by the user.

[0124] S402. If the number of first clothing processing intentions selected by the user is one, then no processing is performed.

[0125] S403. If the number of first clothing processing intentions selected by the user is multiple, determine whether there is a conflict among the multiple first clothing processing intentions.

[0126] It should be noted that when a user selects multiple primary garment processing intentions, there may be unreasonable situations. Therefore, it is necessary to further determine whether multiple primary garment processing intentions conflict. Conflict refers to the incompatibility between multiple intentions selected by the user. For example, selecting primary garment processing intentions that simultaneously include "silk (garment material)" and "high-temperature washing" is an unreasonable combination and may damage the garment. For example, the logical relationship between different intentions can be analyzed. If there are logical contradictions or incompatibilities, a conflict is determined. For instance, the intentions of "low-temperature washing" and "high-temperature disinfection" are logically contradictory. The parameter ranges corresponding to different intentions can also be compared. If there are non-overlapping or incompatible parameter ranges, a conflict is determined. For example, the intention of "quick wash" corresponds to a shorter washing time, while the intention of "intensive wash" corresponds to a longer washing time. If the user selects both intentions simultaneously, a conflict is determined. Alternatively, conflict judgment can be achieved by directly pre-defining conflict rules. For example, "silk (garment material)" and "high-temperature washing" are considered conflicting and cannot be selected simultaneously.

[0127] S404. If not, no processing is required.

[0128] S405. If so, then based on the preset mapping relationship, determine the corresponding conflict level; the mapping relationship is used to indicate the correspondence between the multiple first clothing processing intentions of the conflict and the conflict level.

[0129] It's important to note that in cases of conflicting intentions, the degree of conflict can be further determined. Some conflicts cannot be resolved through reconciliation, as they relate to issues like clothing damage or equipment limitations. For example, the combination of "silk (clothing material)" and "high-temperature washing" will actually damage the clothing, and high temperatures are generally unsuitable for silk fabrics. Other conflicts can be resolved through reconciliation, satisfying the user's needs as much as possible without causing clothing damage or exceeding the equipment's capabilities. For instance, when the intentions of "heavily soiled" and "quick wash" are selected simultaneously, there is a conflict due to the difference in washing time. This conflict can be resolved by choosing a suitable washing time. Conflicting intentions and their corresponding conflict levels can be defined through pre-defined mapping relationships. For example, "silk (clothing material)" and "high-temperature washing" could be mapped to high conflict, while "heavily soiled" and "quick wash" could be mapped to medium conflict. For example, a dictionary or hash table can be used to store these mapping relationships.

[0130] S406. If the conflict level is greater than the preset level, then select from the multiple first clothing processing intentions in the conflict to obtain the second clothing processing intention.

[0131] S407. If the conflict level is less than or equal to the preset level, then based on the multiple first clothing processing intentions of the conflict, determine the value range of the corresponding associated target parameters.

[0132] S408. Based on the first clothing processing intention, or the second clothing processing intention, or the first clothing processing intention and the corresponding value range of the target parameter, the parameter is obtained through a large language model.

[0133] It should be noted that if the conflict level is high, it indicates that the conflict is irreconcilable, and a reasonable intention needs to be selected from the multiple conflicting intentions. For example, an intention can be selected according to a preset priority rule, such as "silk (clothing material)" taking precedence over "high-temperature washing". If the conflict level is low, the conflict can be resolved by adjusting relevant parameters. For example, the intersection of the parameter ranges corresponding to the conflicting intentions can be calculated so that the parameter settings simultaneously satisfy multiple intentions; or optimization algorithms (such as genetic algorithms, simulated annealing, etc.) can be used to find the optimal parameter settings. Target parameters refer to specific parameters closely related to the clothing treatment intention, which can characterize the key characteristics of that intention during equipment operation. For example, under the intention of "protecting clothing", water temperature, spin speed, and washing time are target parameters because they directly affect the washing effect and degree of protection of the clothing.

[0134] The preset level can be determined by combining factors such as user needs, equipment performance, and industry standards, using a weighted average or other comprehensive evaluation methods to ensure the rationality of conflict handling and the safety of equipment operation. For example, when the intention of "protecting clothing" conflicts with the intention of "rapid dehydration," the preset level can be set to a lower value (such as 0.3) based on the user's high requirement for clothing protection, so that the intention of "protecting clothing" is given priority.

[0135] For example, the determination of the value range of the corresponding associated target parameter based on the multiple first clothing processing intentions based on conflict includes:

[0136] Based on the different preset value ranges of multiple first clothing processing intentions under the same target parameter, determine whether there is an intersection between the different preset value ranges;

[0137] If so, the preset value range corresponding to the intersection is the value range of the target parameter;

[0138] If not, determine at least two boundary values ​​that are closest in distance between different preset value ranges, and then take the range formed by the at least two boundary values ​​as the value range of the target parameter.

[0139] The above example provides users with more reasonable and feasible parameter settings by determining the range of target parameters, thereby effectively handling conflicts between multiple clothing processing intentions selected by the user. Specifically, for multiple clothing processing intentions selected by the user, the preset value range of each intention under the same target parameter is obtained. For example, the water temperature range of intention A is 30℃-40℃, and the water temperature range of intention B is 35℃-45℃. It is determined whether these preset value ranges have an intersection. If an intersection exists, the range corresponding to the intersection is used as the value range of the target parameter. For example, the water temperature ranges of intention A and intention B intersect at 35℃-40℃. If there is no intersection between the preset value ranges, at least two boundary values ​​that are closest in distance between different preset value ranges are found. For example, the water temperature range of intention A is 30℃-40℃, and the water temperature range of intention B is 45℃-50℃, then the boundary values ​​are 40℃ and 45℃, and the range formed by these two boundary values ​​is used as the value range of the target parameter. For example, the water temperature range is determined to be 40℃-45℃.

[0140] For example, obtaining the parameters corresponding to the first clothing processing intent through a large language model includes:

[0141] Based on the preset prompt word template, and the first clothing processing intention, or the second clothing processing intention, or the first clothing processing intention and the corresponding target parameter value range, a prompt word is generated;

[0142] The prompt word is input into the large language model, and the parameters output by the large language model are obtained.

[0143] It's important to note that the flexible design of the prompt templates can adapt to different user needs and device parameter ranges, ensuring that the recommended parameters both match the user's intent and remain within the device's operational limits. The prompt template can include multiple modules to accommodate various user intents and device parameters, representing a general template content. Examples include intent description modules, parameter range modules, and domain common sense or preset rule modules. For instance, the prompt template could read: "The user's selected clothing processing intent is {intent}, the device's parameter range is {parameter}, and the relevant domain common sense for this type of clothing processing is {domain common sense}. Please select the appropriate parameter based on the user's selected clothing processing intent."

[0144] It should be noted that, based on the different analysis results mentioned above, the content input to the prompt word template is also different. When the user's first clothing processing intention is not processed, the input is the first clothing processing intention; when the first clothing processing intention is selected to generate the second clothing processing intention, the input is the second clothing processing intention; when the first clothing processing intention is optimized and adjusted to obtain the corresponding target parameter value range, the input of the first clothing processing intention is accompanied by the addition of this value range to prompt the large model to perform analysis and processing based on this value range.

[0145] The parameter recommendation method for the clothing processing equipment provided in this embodiment can promptly identify unreasonable combinations selected by the user by obtaining the user's selected clothing processing intention and determining whether there is a conflict, thus avoiding equipment operation problems or clothing damage caused by conflicting intentions. For conflicting intentions, by determining the conflict level and taking corresponding handling measures, the selection problem of high-conflict intentions can be effectively resolved. At the same time, by adjusting parameters to balance the needs of low-conflict intentions, the safety of equipment operation and the processing effect can be guaranteed.

[0146] This embodiment also provides a parameter recommendation device for clothing processing equipment. Figure 5 A parameter recommendation device diagram for a garment processing apparatus provided in an embodiment of the present invention is shown below. Figure 5 As shown, the parameter recommendation device 50 includes:

[0147] Analysis module 501 is used to determine multiple clothing processing intentions based on the user's corresponding historical data; the historical data includes historical usage parameters of the clothing processing equipment and / or the clothing processing intentions historically selected by the user.

[0148] In one possible implementation, the analysis module 501 is specifically used for:

[0149] Use the user's historically selected clothing processing intent as the first candidate intent;

[0150] Based on the historical usage parameters of the garment processing equipment, determine the corresponding second candidate intent;

[0151] Based on the first candidate intent and the second candidate intent, determine the target candidate intent and the relevance score corresponding to each target candidate intent;

[0152] Based on the target candidate intent and the corresponding relevance score, multiple clothing processing intents are determined.

[0153] In one possible implementation, the historical usage parameters include multiple sets of parameter combinations, each set of parameter combinations including multiple parameter items and a parameter value corresponding to each parameter item. The analysis module 501 is specifically used for:

[0154] For each of the parameter combinations, a corresponding reference parameter combination is matched; the reference parameter combination includes multiple parameter items and a range of parameter values ​​for each parameter item.

[0155] Based on the reference parameter combination to which each parameter combination belongs, a corresponding second candidate intent is determined; the reference parameter combination and the second candidate intent have a corresponding relationship.

[0156] In one possible implementation, the analysis module 501 is specifically used for:

[0157] The relevance score of the first candidate intent is determined based on the number of selections corresponding to the first candidate intent; the number of selections and the relevance score are positively correlated.

[0158] The relevance score of the second candidate intent corresponding to the parameter combination is determined based on the number of times the parameter combination is used; the number of times it is used and the relevance score are positively correlated.

[0159] Determine whether there is a common intent between the first candidate intent and the second candidate intent; if so, redetermine the relevance score of the common intent for additional processing.

[0160] The same intent, the first candidate intent other than the same intent, and the second candidate intent, along with their respective relevance scores, are taken as the target candidate intent and their corresponding relevance scores.

[0161] The display module 502 is used to display multiple clothing processing intentions in response to the terminal's trigger operation on the control page;

[0162] The acquisition module 503 is used to acquire at least one first clothing processing intention selected by the user in response to the parameter recommendation request from the terminal;

[0163] The processing module 504 is used to obtain the parameters corresponding to the first clothing processing intention through a large language model; and send the parameters to the terminal so that the control page displays the parameters.

[0164] In one possible implementation, if the number of first clothing processing intentions selected by the user is multiple, the processing module 504 is further configured to:

[0165] Determine whether there is a conflict among multiple first clothing processing intentions; if so, determine the corresponding conflict level based on a preset mapping relationship; the mapping relationship is used to indicate the correspondence between multiple conflicting first clothing processing intentions and conflict levels.

[0166] If the conflict level is greater than the preset level, then a second clothing processing intention is obtained by selecting from multiple conflicting first clothing processing intentions.

[0167] If the conflict level is less than or equal to the preset level, then based on the multiple first clothing processing intentions of the conflict, the value range of the corresponding associated target parameters is determined.

[0168] In one possible implementation, processing module 504 is specifically used for:

[0169] Based on the different preset value ranges of multiple first clothing processing intentions under the same target parameter, determine whether there is an intersection between the different preset value ranges;

[0170] If so, the preset value range corresponding to the intersection is the value range of the target parameter;

[0171] If not, determine at least two boundary values ​​that are closest in distance between different preset value ranges, and then take the range formed by the at least two boundary values ​​as the value range of the target parameter.

[0172] In one possible implementation, processing module 504 is specifically used for:

[0173] Based on the preset prompt word template, and the first clothing processing intention, or the second clothing processing intention, or the first clothing processing intention and the corresponding target parameter value range, a prompt word is generated;

[0174] The prompt word is input into the large language model, and the parameters output by the large language model are obtained.

[0175] This embodiment provides a parameter recommendation device for a garment processing equipment, which can execute the parameter recommendation method for a garment processing equipment provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0176] Figure 6This is a hardware schematic diagram of an electronic device provided in an embodiment of the present invention. For example... Figure 6 As shown, the electronic device 60 provided in this embodiment includes at least one processor 601 and a memory 602. The device 60 also includes a communication component 603. The processor 601, memory 602, and communication component 603 are connected via a bus 604.

[0177] In a specific implementation, at least one processor 601 executes computer execution instructions stored in the memory 602, causing at least one processor 601 to perform the above method.

[0178] The specific implementation process of processor 601 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0179] In the above Figure 6 In the illustrated embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0180] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0181] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0182] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the method described above.

[0183] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0184] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0185] The division of units described herein is merely a logical functional division. In actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0186] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0187] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0188] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0189] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0190] The technical solutions of this application have been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it is readily understood by those skilled in the art that the scope of protection of this application is obviously not limited to these specific embodiments. The above embodiments are only used to illustrate the technical solutions of this application and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. These modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

Claims

1. A method for recommending parameters for a garment processing device, characterized in that, The method includes: Based on the user's historical data, multiple clothing processing intentions are determined; the historical data includes the historical usage parameters of the clothing processing equipment and / or the clothing processing intentions selected by the user in the past. In response to the terminal's trigger operation on the control page, multiple clothing processing intentions are displayed; In response to the terminal's parameter recommendation request, obtain at least one of the user's initial clothing processing intentions; The parameters corresponding to the first clothing processing intent are obtained through a large language model; and the parameters are sent to the terminal so that the control page displays the parameters.

2. The method according to claim 1, characterized in that, The process involves determining multiple clothing processing intentions based on the user's historical data, including: Use the user's historically selected clothing processing intent as the first candidate intent; Based on the historical usage parameters of the garment processing equipment, determine the corresponding second candidate intent; Based on the first candidate intent and the second candidate intent, determine the target candidate intent and the relevance score corresponding to each target candidate intent; Based on the target candidate intent and the corresponding relevance score, multiple clothing processing intents are determined.

3. The method according to claim 2, characterized in that, The historical usage parameters include multiple sets of parameter combinations, each set of parameter combinations includes multiple parameter items and a parameter value corresponding to each parameter item. Determining the corresponding second candidate intent based on the historical usage parameters of the clothing processing equipment includes: For each of the parameter combinations, a corresponding reference parameter combination is matched; the reference parameter combination includes multiple parameter items and a range of parameter values ​​for each parameter item. Based on the reference parameter combination to which each parameter combination belongs, a corresponding second candidate intent is determined; the reference parameter combination and the second candidate intent have a corresponding relationship.

4. The method according to claim 2, characterized in that, The step of determining target candidate intents and relevance scores for each target candidate intent based on the first candidate intent and the second candidate intent includes: The relevance score of the first candidate intent is determined based on the number of selections corresponding to the first candidate intent; the number of selections and the relevance score are positively correlated. The relevance score of the second candidate intent corresponding to the parameter combination is determined based on the number of times the parameter combination is used; the number of times it is used and the relevance score are positively correlated. Determine whether there is a common intent between the first candidate intent and the second candidate intent; if so, redetermine the relevance score of the common intent for additional processing. The same intent, the first candidate intent other than the same intent, and the second candidate intent, along with their respective relevance scores, are taken as the target candidate intent and their corresponding relevance scores.

5. The method according to claim 1, characterized in that, If the number of first clothing processing intentions selected by the user is multiple, before obtaining the parameters corresponding to the first clothing processing intentions through the large language model, the method further includes: Determine whether there is a conflict among multiple first clothing processing intentions; if so, determine the corresponding conflict level based on a preset mapping relationship; the mapping relationship is used to indicate the correspondence between multiple conflicting first clothing processing intentions and conflict levels. If the conflict level is greater than the preset level, then a second clothing processing intention is obtained by selecting from multiple conflicting first clothing processing intentions. If the conflict level is less than or equal to the preset level, then based on the multiple first clothing processing intentions of the conflict, the value range of the corresponding associated target parameters is determined.

6. The method according to claim 5, characterized in that, The conflict-based multiple first clothing processing intentions determine the value range of the corresponding associated target parameters, including: Based on the different preset value ranges of multiple first clothing processing intentions under the same target parameter, determine whether there is an intersection between the different preset value ranges; If so, the preset value range corresponding to the intersection is the value range of the target parameter; If not, determine at least two boundary values ​​that are closest in distance between different preset value ranges, and then take the range formed by the at least two boundary values ​​as the value range of the target parameter.

7. The method according to claim 6, characterized in that, The step of obtaining the parameters corresponding to the first clothing processing intent through a large language model includes: Based on the preset prompt word template, and the first clothing processing intention, or the second clothing processing intention, or the first clothing processing intention and the corresponding target parameter value range, a prompt word is generated; The prompt word is input into the large language model, and the parameters output by the large language model are obtained.

8. A parameter recommendation device for a garment processing equipment, characterized in that, The device includes: The analysis module is used to determine multiple clothing processing intentions based on the user's historical data; the historical data includes historical usage parameters of the clothing processing equipment and / or the clothing processing intentions selected by the user in the past. The display module is used to respond to the terminal's trigger operation on the control page and display multiple clothing processing intentions; The acquisition module is used to acquire at least one first clothing processing intention selected by the user in response to the parameter recommendation request from the terminal; The processing module is used to obtain the parameters corresponding to the first clothing processing intention through a large language model; and send the parameters to the terminal so that the control page displays the parameters.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-7.

10. An electronic device, characterized in that, include: At least one processor and memory; wherein, The memory stores computer-executed instructions; The at least one processor executes computer execution instructions stored in the memory, causing the at least one processor to perform the method as described in any one of claims 1-7.

Images