A multi-instruction program control method, apparatus, cleaning device, and medium based on speech recognition

Abstract

The present application discloses a multi-instruction program control method, device, cleaning equipment and medium based on speech recognition, and the present application belongs to the technical field of general control or regulation systems. The method includes: obtaining the speech information of a user, and extracting semantic features and voiceprint features; generating a first control instruction according to the semantic features; matching a user profile according to the voiceprint features to obtain a second control instruction; when an item to be cleaned is recognized, obtaining the basic parameters of the item to be cleaned to generate a third control instruction; recognizing preset qualifiers in the semantic features to determine the priorities of the control instructions; determining a comprehensive control instruction; and determining the program control parameters of the cleaning equipment according to the comprehensive control instruction. According to this technical solution, multi-faceted control instructions are analyzed through semantic information, voiceprint information and the basic parameters of the item, and control instructions that meet the actual needs of the user can be generated. Without complex interaction links, the intelligence level of the cleaning equipment is improved, and the user experience is enhanced.

Description

Technical Field

[0001] This application belongs to the technical field of general control or regulation systems, and particularly relates to a multi-instruction program control method, device, cleaning equipment and medium based on speech recognition. Background Art

[0002] With the rapid development of technology, the control or regulation systems of cleaning equipment have seen more intelligent designs. There are more and more intelligent and convenient developments for various equipment, which can not only simplify user operations, but also greatly improve the cleaning efficiency of items, while reducing the cost of user training. Users can quickly determine the cleaning parameters they need through voice or other means among many functions, and then clean the items.

[0003] However, in the process of continuous intelligent upgrading, there will also be some problems. For example, if the received instructions are not clear enough, it is difficult to make a correct response. If the method of multi-round confirmation is adopted, it will instead make users feel the trouble brought by voice instructions. Therefore, it is particularly important to be able to obtain the control information required by users more accurately while the intelligent development is in progress. How to accurately control the cleaning equipment is a technical problem that those skilled in the art urgently need to solve. Summary of the Invention

[0004] The purpose of the embodiments of this application is to provide a multi-instruction program control method, device, cleaning equipment and medium based on speech recognition, aiming to solve the problems such as the need to completely use standard language when controlling cleaning equipment, poor semantic understanding ability, and inability to accurately control unclear semantics. This solution can identify various control instructions, analyze multiple control instructions through semantic information, voiceprint information and the basic parameters of items, and then determine the final control instruction for item cleaning in combination with the actual situation, and can select the most in line with the actual needs of users among multiple control instructions, without complex interaction links, improving the intelligent degree of cleaning equipment and enhancing the user experience.

[0005] In the first aspect, the embodiments of this application provide a multi-instruction program control method based on speech recognition, and the method includes:

[0006] Obtain the voice information of the user, and extract semantic features and voiceprint features from the voice information;

[0007] Generate a first control instruction according to the semantic features;

[0008] Match the user portrait according to the voiceprint features, and determine the user preferences according to the user portrait to obtain a second control instruction;

[0009] When an item to be cleaned is recognized, obtain the basic parameters of the item to be cleaned, and generate a third control instruction according to the basic parameters;

[0010] Identify whether the semantic features include a preset qualifier; if so, determine the priority of each control instruction according to the preset qualifier;

[0011] Determine a comprehensive control instruction according to the first control instruction, the second control instruction, the third control instruction, and the priority;

[0012] Determine the program control parameters of the cleaning device according to the comprehensive control instruction.

[0013] Further, determining a comprehensive control instruction according to the first control instruction, the second control instruction, the third control instruction, and the priority includes:

[0014] Determine a comprehensive control instruction based on the control instruction with the highest priority according to the first control instruction, the second control instruction, the third control instruction, and the priority;

[0015] Or,

[0016] According to the first control instruction, the second control instruction, the third control instruction, and the priority, perform instruction merging based on the priority order of each control instruction to comprehensively determine a comprehensive control instruction.

[0017] Further, determining the priority of each control instruction according to the preset qualifier includes:

[0018] Identify the target control instruction among the first control instruction, the second control instruction, and the third control instruction associated with the preset qualifier;

[0019] Based on the priority adjustment information included in the preset qualifier, adjust the priority of the target control instruction to obtain the priority of each control instruction.

[0020] Further, determining a comprehensive control instruction according to the first control instruction, the second control instruction, the third control instruction, and the priority includes:

[0021] Determine the filling values of each parameter field in the comprehensive control instruction according to the first control instruction, the second control instruction, the third control instruction, and the priority, and fill in to obtain the comprehensive control instruction;

[0022] Correspondingly, determining the program control parameters of the cleaning device according to the comprehensive control instruction includes:

[0023] Parse according to the filled values of each parameter field in the comprehensive control instruction to obtain the program control parameters of the cleaning device.

[0024] Further, determine the comprehensive control instruction according to the first control instruction, the second control instruction, the third control instruction and the priority, including:

[0025] Among the first control instruction, the second control instruction and the third control instruction, if there are two conflicting control instructions that conflict with each other, determine the conflict control instruction with the lower priority as an invalid control instruction, and determine the comprehensive control instruction according to other control instructions.

[0026] Further, after determining the program control parameters of the cleaning device according to the comprehensive control instruction, the method further includes:

[0027] Generate a prompt message according to the program control parameters and display it on the cleaning device and / or the intelligent terminal associated with the cleaning device;

[0028] If a modification instruction for the program control parameters is not received within a preset duration, or a confirmation instruction for the program control parameters is received within a preset duration, perform a cleaning operation according to the program control parameters.

[0029] Further, the method further includes:

[0030] Identify whether the semantic features include a preset qualifier; if not, read the preset default priority of each control instruction.

[0031] In a second aspect, an embodiment of the present application provides a multi-instruction program control device based on voice recognition, and the device includes:

[0032] A feature extraction module, configured to obtain the voice information of the user and extract semantic features and voiceprint features from the voice information;

[0033] A first control instruction generation module, configured to generate a first control instruction according to the semantic features;

[0034] A second control instruction generation module, configured to match a user portrait according to the voiceprint features, determine user preferences according to the user portrait, so as to obtain a second control instruction;

[0035] A third control instruction generation module, configured to obtain the basic parameters of the item to be cleaned when the item to be cleaned is recognized, and generate a third control instruction according to the basic parameters;

[0036] A priority determination module, configured to identify whether the semantic features include a preset qualifier; if so, determine the priority of each control instruction according to the preset qualifier;

[0037] An integrated control instruction determination module, configured to determine an integrated control instruction according to the first control instruction, the second control instruction, the third control instruction, and the priority;

[0038] A program control parameter determination module, configured to determine program control parameters of the cleaning device according to the integrated control instruction.

[0039] In a third aspect, an embodiment of the present application provides a cleaning device, which includes a processor, a memory, and a program or instruction stored on the memory and executable on the processor. When the program or instruction is executed by the processor, the steps of the method described in the first aspect are implemented.

[0040] In a fourth aspect, an embodiment of the present application provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the method described in the first aspect are implemented.

[0041] In a fifth aspect, an embodiment of the present application provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor, and the processor is used to run a program or instruction to implement the method described in the first aspect.

[0042] In the embodiment of the present application, voice information of a user is obtained, and semantic features and voiceprint features are extracted from the voice information; a first control instruction is generated according to the semantic features; a user portrait is matched according to the voiceprint features, and user preferences are determined according to the user portrait to obtain a second control instruction; when an item to be cleaned is recognized, basic parameters of the item to be cleaned are obtained, and a third control instruction is generated according to the basic parameters; it is recognized whether a preset qualifier is included in the semantic features; if so, the priority of each control instruction is determined according to the preset qualifier; an integrated control instruction is determined according to the first control instruction, the second control instruction, the third control instruction, and the priority; program control parameters of the cleaning device are determined according to the integrated control instruction. In the above technical solution, through the recognition of multiple control instructions, multiple aspects of control instructions can be analyzed through semantic information, voiceprint information, and basic parameters of the item, and then combined with the actual situation, the final control instruction for cleaning the item is determined, which can select the most suitable control instruction for the actual needs of the user among multiple control instructions, without complex interaction links, improving the intelligence level of the cleaning device and enhancing the user experience. Description of the Drawings

[0043] Figure 1 is a schematic flowchart of a multi-instruction program control method based on voice recognition provided in Embodiment 1 of the present application;

[0044] Figure 2 It is a schematic flowchart of the multi-instruction program control method based on speech recognition provided in the second embodiment of the present application;

[0045] Figure 3 It is a schematic structural diagram of the multi-instruction program control device based on speech recognition provided in the third embodiment of the present application;

[0046] Figure 4 It is a schematic structural diagram of the cleaning device provided in the fourth embodiment of the present application. Detailed implementation manners

[0047] In order to make the objectives, technical solutions, and advantages of the present application clearer, the following further describes the specific embodiments of the present application in detail with reference to the accompanying drawings. It can be understood that the specific embodiments described herein are only used to explain the present application, rather than limiting the present application. Additionally, it should be noted that for the sake of description, only parts related to the present application are shown in the drawings rather than all of the content. Before discussing the exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts describe the operations (or steps) as sequential processes, many of the operations can be implemented in parallel, concurrently, or simultaneously. In addition, the order of the operations can be rearranged. The process can be terminated when its operations are completed, but it can also have additional steps not included in the drawings. The process can correspond to a method, function, procedure, subroutine, subprogram, and so on.

[0048] The following will clearly describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art belong to the scope of protection of the present application.

[0049] The terms "first", "second", etc. in the description and claims of the present application are used to distinguish similar objects, rather than to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second", etc. are usually of the same type, and the number of objects is not limited. For example, the first object can be one or multiple. In addition, "and / or" in the description and claims indicates at least one of the connected objects, and the character " / " generally represents an "or" relationship between the associated objects before and after.

[0050] The following will, with reference to the accompanying drawings, describe in detail the method, apparatus, cleaning device and medium for multi-instruction program control based on speech recognition provided in the embodiments of the present application through specific embodiments and their application scenarios.

[0051] Embodiment 1

[0052] Figure 1 FIG. is a flowchart of the method for multi-instruction program control based on speech recognition provided in Embodiment 1 of the present application. As Figure 1 shown, the specific steps are as follows:

[0053] S101, obtain the user's speech information, and extract semantic features and voiceprint features from the speech information;

[0054] First of all, the present application is applicable to industrial cleaning scenarios or the usage scenarios of household cleaning devices. Based on the above usage scenarios, it can be understood that the execution subject of the present application can be a cleaning device. A cleaning device is a device used for cleaning operations, which can be equipped with sensing and control technologies, such as industrial cleaning devices, washing machines, and dishwashers.

[0055] The speech information can be the speech issued by the user and the sound signal input into the system through audio acquisition devices such as microphones. Its content is extensive, covering various operation instructions for the cleaning device, such as starting cleaning, pausing, adjusting the cleaning time, etc., and may also be an inquiry about the device status, such as how long the device will finish washing, or a special requirement for the cleaning method, such as gentle washing with cold water.

[0056] For the recognition of speech information, for example, in a noisy environment where the intensity and frequency characteristics of the speech are interfered, noise reduction and enhancement technologies can be used for processing.

[0057] The semantic feature can be a feature representation of the inherent meaning expressed by the speech information. In the field of natural language processing, after converting the speech into text through speech recognition technology, the text is deeply analyzed. At the lexical level, keywords and phrases are extracted, such as woolen sweaters, strong decontamination, etc. At the syntactic level, the structure and components of the sentence are analyzed to determine the subject-predicate-object relationship, etc. At the semantic level, the overall intention and context of the text are understood. For example, please wash this easily fading clothes in a gentle mode. The semantic feature includes not only lexical information such as gentle mode and easily fading, but also the overall semantics of the special requirement for washing this piece of clothing.

[0058] The semantic feature can also include emotional tendency information. For example, for the speech related to the user's satisfaction evaluation of the cleaning device, it can be analyzed whether it is positive, negative or neutral. This is of great significance for understanding user needs and improving device services.

[0059] Voiceprint features can be unique acoustic features when each person speaks, which are determined by the physiological structure of the vocal organs. Voiceprint features remain relatively stable under different speech contents, speaking speeds, and intonations, and can be used to identify user identities. Voiceprint features include information such as fundamental frequency, formants, and spectral envelopes. These features are extracted and processed through professional voiceprint analysis algorithms.

[0060] In this solution, the cleaning device is equipped with a high-sensitivity microphone whose frequency response range covers the main frequency range of human speech and can accurately capture the user's voice signal. After the microphone converts the sound signal into an electrical signal, it is converted into a digital signal through an analog-to-digital converter for subsequent computer processing. To improve the quality of the voice signal, noise reduction techniques such as filter-based noise reduction methods can also be used to remove background noise in the environment.

[0061] For semantic feature extraction, first, a speech recognition engine, such as a deep learning-based speech recognition model like WaveNet, DeepSpeech, etc., is used to convert the digital voice signal into text. Then, the text is preprocessed, including removing stop words and stemming, etc. Then, natural language processing techniques are used, such as named entity recognition algorithms to identify entities in the text, part-of-speech tagging algorithms to determine the part of speech of each word, and dependency parsing algorithms to analyze the grammatical relationship between words in a sentence. Finally, key features that can represent semantics are extracted.

[0062] For voiceprint feature extraction, digital signal processing techniques can be specifically used to frame the voice signal, dividing the continuous voice signal into short-time frames. Then, spectral analysis is performed on each frame of the signal, such as the Fast Fourier Transform (FFT), to convert the time-domain signal into a frequency-domain signal. Voiceprint feature parameters are extracted, such as Mel-Frequency Cepstral Coefficients (MFCC), which simulates the perception characteristics of the human auditory system for sound frequencies and can effectively represent voiceprint features; other feature parameters such as Linear Predictive Cepstral Coefficients (LPCC) can also be extracted.

[0063] S102, generate a first control instruction according to the semantic features;

[0064] The first control instruction can be an instruction for directly controlling the operation of the cleaning device generated according to the extracted semantic features. It converts the semantics expressed by the user's speech into an operation command executable by the device and corresponds to the functional modules of the cleaning device.

[0065] The instruction content may include the selection of cleaning modes, such as standard mode, gentle mode, and quick cleaning mode, etc. Each mode corresponds to different combinations of cleaning parameters, such as cleaning time, rotation speed, and water consumption, etc. It can also be the control of the device operation state, such as start, pause, and stop, etc., and the adjustment of cleaning parameters, such as raising the water temperature, increasing the amount of detergent, etc.

[0066] In this solution, a semantic-instruction mapping database is established inside the system, which pre-stores the corresponding relationships between various semantic features and control instructions. When semantic features are extracted, the system searches and matches in the database. For example, if the semantic feature is to select the quick cleaning mode, the system will find the corresponding control instruction in the database: set the cleaning mode to quick cleaning. For some complex semantic features, they can be inferred and analyzed through natural language understanding algorithms, and then the corresponding control instructions are generated. For example, for the semantic feature "this piece of clothing is a bit dirty, wash it for a while longer", the system needs to generate a control instruction to increase the cleaning time based on semantic information such as "a bit dirty" and "wash it for a while longer", combined with the operation rules of the cleaning device.

[0067] S103, match the user profile according to the voiceprint feature, and determine the user preference according to the user profile to obtain a second control instruction;

[0068] A user profile can be a comprehensive and systematic description of the user, constructed by collecting and analyzing various information of the user. It is an abstract model that reflects the personalized characteristics and behavior habits of the user.

[0069] The user profile may include the basic information of the user, such as age, gender, region, and occupation, etc. These information can be obtained from the data filled in during user registration or the data collected during the device usage process. The user profile can also include the usage habit information of the user, such as the frequency of using the cleaning device, the commonly used cleaning modes, the preferred water temperature range, and the favorite detergent brands, etc. It can also include the consumption behavior information of the user, such as the price range of purchasing the cleaning device, whether relevant value-added services have been purchased, etc. It can also include the feedback information of the user, such as the evaluation of the cleaning device and the improvement suggestions put forward.

[0070] User preference can be the personal preferences and inclinations shown by the user during the use of the cleaning device, and it is an important part of the user profile.

[0071] User preference information can specifically include preferences for the cleaning mode. For example, some users like to use the energy-saving mode to save water and electricity, preferences for water temperature. Some users believe that a water temperature of 40 degrees Celsius provides the best cleaning effect, preferences for detergents. They may prefer a certain brand of detergent or a specific type, such as a phosphorus-free or natural ingredient detergent. It also includes preferences for the cleaning time. For example, they are used to starting the cleaning before going to bed at night so that they can directly dry the items the next morning, etc.

[0072] The second control instruction can be an instruction for controlling the cleaning device generated based on the user preferences determined from the user profile, aiming to meet the personalized needs of the user. The content of the second control instruction can be to set parameters such as the cleaning mode, water temperature, and detergent dosage according to the user preferences, or to adjust the operation time of the device according to the user's usage habits, such as automatically starting the cleaning program during the time period when the user often uses it. It can also be to recommend additional cleaning functions that the user may like, such as fabric softener addition, sterilization mode, etc.

[0073] In this solution, the system can store multiple user profiles and their corresponding voiceprint feature templates. When the voiceprint feature of the user is obtained, voiceprint matching algorithms, such as the Dynamic Time Warping (DTW) algorithm, Gaussian Mixture Model-Universal Background Model, etc., are used to compare the voiceprint feature of the user with the voiceprint feature templates in the database one by one. Calculate the similarity score between the user's voiceprint feature and each template. The higher the similarity score, the higher the matching degree. By setting a similarity threshold, when the score exceeds this threshold, it is considered that a matching user profile has been found. After the system matches the user profile in this solution, it extracts the user preference information related to the operation of the cleaning device from the user profile database. Through data analysis and screening algorithms, a large amount of information in the user profile is processed to remove the information irrelevant to the current cleaning task and retain the key user preference information. For example, when the user wants to wash clothes, the preference information related to clothes washing, such as the cleaning mode and water temperature preference, is mainly extracted.

[0074] S104. When an item to be cleaned is recognized, obtain the basic parameters of the item to be cleaned and generate a third control instruction according to the basic parameters;

[0075] The item to be cleaned is the object that needs to be cleaned in the cleaning device, and it has a wide variety of types, including but not limited to industrial equipment, such as product components, wafers to be processed, etc. It can also be household items, such as clothes, tableware, fruits and vegetables, and household supplies, etc.

[0076] The information of the item to be cleaned may include material information. For example, the material of clothing may be cotton, wool, silk, etc. Different materials have different requirements for cleaning methods and parameters. Stain information, such as the type of stains, like oil stains, ink stains, and sweat stains, as well as the severity of the stains, shape and size information. For example, large curtains require a larger cleaning space and special cleaning procedures, while small tableware can be cleaned in different ways, and the weight information of the item to be cleaned, etc.

[0077] The third control instruction can be an instruction for controlling the operation of the cleaning device generated according to the basic parameters of the item to be cleaned, aiming to enable the cleaning device to perform appropriate cleaning operations for different items to be cleaned.

[0078] The third control instruction can include selecting a suitable cleaning mode. For example, for woolen clothing, select the gentle mode, adjust the cleaning time, and determine the cleaning duration according to factors such as the stain degree and the weight of the item; set the water temperature. For some materials that are not heat-resistant, select a lower water temperature, and control the amount of detergent, and automatically adjust the detergent dosage according to the weight and stain degree of the item.

[0079] In this solution, the cleaning device can be equipped with multiple sensors to identify the item to be cleaned. For example, an image sensor takes an image of the item to be cleaned, and uses computer vision technology for image recognition to identify information such as the type, shape, and size of the item. A weight sensor can measure the weight of the item to be cleaned. In addition, a material sensor, such as a near-infrared spectroscopy sensor, can be used to detect the material composition of the item, and determine the material by analyzing the absorption and reflection characteristics of the item to light of different wavelengths.

[0080] During the process of identifying the item to be cleaned, the corresponding sensors convert the detected information into digital signals and transmit them to the control system of the device. The control system processes and analyzes these signals to extract the basic parameters of the item to be cleaned. For example, the image taken by the image sensor is processed by an image recognition algorithm to obtain information such as the type and size of the item; the signal of the weight sensor is processed through amplification, filtering, etc. to obtain the weight parameter of the item.

[0081] S105, identify whether the semantic feature includes a preset qualifier; if it includes, determine the priority of each control instruction according to the preset qualifier;

[0082] Among them, the semantic feature is a feature that can reflect the meaning of the speech extracted from the user's speech information. It contains information such as the operation intention and requirements expressed by the speech. For example, the semantic feature of "select the strong cleaning mode" contains the key information of "strong cleaning mode", which is used to convey the user's specific requirements for the cleaning mode.

[0083] Preset determiners are words or phrases with special meanings that are preset during the system design phase. These determiners are used to limit the execution manner, importance level, etc. of control instructions. For example: "This time, it should be washed clean" emphasizes the preset determiner "this time", that is, the first control instruction in this cleaning task is particularly important, and the priority of the second control instruction determined based on user preferences should be reduced. Another example: "The same as every time" emphasizes the preset determiner "every time", that is, the second control instruction in this cleaning task is particularly important and its priority should be increased.

[0084] In this solution, the priority indicates the order and importance level of each control instruction during the execution process. Instructions with a higher priority will be preferentially executed by the system to ensure that the device operates according to the main needs and expectations of the user. When it is recognized that the semantic feature contains a preset determiner, the system will adjust the priorities of each control instruction according to the preset rules and logic. Different preset determiners correspond to different priority adjustment strategies. This solution can adjust the priority to ensure that the cleaning device operates to meet the actual needs of the user.

[0085] Optionally, in this solution, the method further includes:

[0086] Identify whether the semantic feature includes a preset determiner; if not, read the preset default priority of each control instruction.

[0087] Among them, in the case where the semantic feature does not include a preset determiner, the generation of comprehensive control instructions can be performed according to the preset default priority. For example, it is preset that the priority of the first control instruction is greater than the priority of the second control instruction, and the priority of the second control instruction is greater than the priority of the third control instruction.

[0088] S106, determine the comprehensive control instruction according to the first control instruction, the second control instruction, the third control instruction, and the priority;

[0089] The priority can be a ranking of the importance levels of the first control instruction, the second control instruction, and the third control instruction, and is used to determine which instructions the system preferentially executes when multiple instructions exist simultaneously to ensure the reasonable operation of the cleaning device and the satisfaction of user needs. The setting of the priority can be based on various factors, such as the urgency of the instruction, the operation intention of the user, and the impact degree of the instruction on the cleaning effect, etc. Different cleaning devices or usage scenarios may have different priority setting rules.

[0090] The comprehensive control instruction can be the final control instruction obtained by integrating and processing the first control instruction, the second control instruction, and the third control instruction according to their priorities. It comprehensively considers the user's voice operations, personalized preferences, and the characteristics of the items to be cleaned, and is used to comprehensively control the operation of the cleaning device. The comprehensive control instruction can include operation instructions for each functional module of the cleaning device, such as the selection of the cleaning mode, the setting of the water temperature, the adjustment of the cleaning time, the dispensing of the detergent, and the control of the device operation status, etc. It is a complete set of instructions to ensure that the cleaning device can operate in the optimal manner.

[0091] In one scenario, the first control instruction, the second control instruction, and the third control instruction can be evaluated according to preset priority rules. These rules can be based on logical judgments. For example, instructions related to device safety have the highest priority, or they can be based on user settings, where the user can customize the priorities of certain instructions. Each instruction is analyzed to determine its priority category, and then the instructions are sorted in descending order of priority. The instructions with high priority are retained, and the instructions with low priority are removed or modified to generate the comprehensive control instruction.

[0092] S107. Determine the program control parameters of the cleaning device according to the comprehensive control instruction.

[0093] The program control parameters can be the specific parameter values used to control the operation program of the cleaning device. These parameters directly affect the working state and cleaning effect of the cleaning device. The program control parameters can include cleaning mode parameters, water temperature parameters, cleaning time parameters, detergent dosage parameters, dehydration speed parameters, and rinsing times parameters, etc.

[0094] In this solution, after obtaining the comprehensive control instruction, the comprehensive control instruction can be parsed to extract the operation requirements therein. Then, according to the correspondence between the program control parameters of the cleaning device and the operation requirements, the operation requirements are converted into specific program control parameter values. For example, if the comprehensive control instruction is "select the gentle mode, set the water temperature to 30 degrees, and the cleaning time to 40 minutes", the system will convert the gentle mode into the corresponding mode identifier, convert 30 degrees into the water temperature parameter value 30, and convert 40 minutes into the cleaning time parameter value 40. For some complex instructions, further calculations and conversions can be performed. For example, according to the relationship between the detergent dosage and the item weight and stain degree, the specific detergent dosage parameter value is calculated. Finally, a complete set of program control parameters is determined to control the operation of the cleaning device.

[0095] The technical solution provided in this embodiment extracts semantic features and voiceprint features from the voice information of the user by obtaining the voice information of the user; generates a first control instruction according to the semantic features; matches the user portrait according to the voiceprint features, and determines the user preference according to the user portrait to obtain a second control instruction; when an item to be cleaned is recognized, obtains the basic parameters of the item to be cleaned, and generates a third control instruction according to the basic parameters; determines a comprehensive control instruction according to the first control instruction, the second control instruction, the third control instruction and the priority; and determines the program control parameters of the cleaning device according to the comprehensive control instruction. The above technical solution can analyze various control instructions through semantic information, voiceprint information and the basic parameters of the item by recognizing multiple control instructions, and then determine the final control instruction for cleaning the item in combination with the actual situation, and can select the control instruction that best meets the actual needs of the user from multiple control instructions, without complex interaction links, improving the intelligence level of the cleaning device and enhancing the user experience.

[0096] In one embodiment, optionally, determining the priority of each control instruction according to the preset qualifier includes:

[0097] Identifying the target control instruction among the first control instruction, the second control instruction, and the third control instruction associated with the preset qualifier;

[0098] Based on the priority adjustment information included in the preset qualifier, adjust the priority of the target control instruction to obtain the priority of each control instruction.

[0099] Among them, the priority adjustment information can be the relevant information included in the preset qualifier for indicating the adjustment of the priority of the target control instruction. It can clearly stipulate the increase or decrease range of the priority of the target control instruction, or give the rules and strategies for priority adjustment.

[0100] Natural language processing and data analysis techniques can be used to deeply understand the semantics of the preset qualifier and perform matching analysis with the content of the first control instruction, the second control instruction, and the third control instruction. For example, after receiving the voice information "also wash quickly as before", the target control instruction and the priority adjustment method for the target control instruction can be determined by using the keyword matching algorithm. For example, "as before" here can determine that the associated target control instruction is the second control instruction. Then, if the second control instruction is recognized, the priority of the second control instruction can be increased and used as the control instruction with the highest priority.

[0101] After determining the target control instruction, the priority of the target control instruction can be changed accordingly according to the priority adjustment information. If the priority adjustment information indicates to increase the priority of the target control instruction, it can be advanced in the priority sorting; if it is to decrease the priority, it will be moved backward in the sorting. By adjusting the priority of the target control instruction, the priority order of each control instruction can be determined. This priority order will be used to determine the execution order of each control instruction when the subsequent cleaning device performs operations, enabling the device to operate efficiently according to the user's intentions and requirements.

[0102] In this technical solution, by identifying the target control instruction associated with the preset qualifier and precisely adjusting the priority of the target control instruction based on the priority adjustment information of the preset qualifier, the priority setting of the control instruction of the cleaning device becomes more flexible and intelligent.

[0103] In one embodiment, optionally, determining a comprehensive control instruction according to the first control instruction, the second control instruction, the third control instruction, and the priority includes:

[0104] Determining the comprehensive control instruction based on the control instruction with the highest priority according to the first control instruction, the second control instruction, the third control instruction, and the priority;

[0105] Or,

[0106] According to the first control instruction, the second control instruction, the third control instruction, and the priority, performing instruction merging based on the priority order of each control instruction to comprehensively determine the comprehensive control instruction.

[0107] Among them, the default priority order can be a sorting rule preset in the control system of the cleaning device regarding the importance of the first control instruction, the second control instruction, and the third control instruction. This order is part of the system's initial configuration and can be determined according to factors such as the device's design concept, common usage scenarios, and user requirements. For example, the first control instruction of the user's immediate operation has the highest priority, the second control instruction based on the user's preference has a medium priority, and the third control instruction generated according to the basic parameters of the item to be cleaned has the lowest priority. There can also be other setting methods.

[0108] In one scenario, after the first control instruction, the second control instruction, and the third control instruction are recognized, they can be compared according to the default priority order, and based on the control instruction with the highest priority, a comprehensive control instruction is constructed. That is, the content of this control instruction is directly used as the main part of the comprehensive control instruction, and other control instructions with lower priorities do not participate in the generation of the comprehensive control instruction in this case. For example, if the first control instruction has the highest priority and its content is "Set the strong cleaning mode", then the comprehensive control instruction will include the key operation instruction of setting the strong cleaning mode, and other lower-priority instructions will be ignored if they are not related to it.

[0109] In another scenario, the system first sorts the first control instruction, the second control instruction, and the third control instruction according to the default priority order. Then, the comprehensive control instruction is generated by comprehensively considering the specific content and priority relationship of each control instruction. If there is no conflict between instructions with different priorities, for example, the high-priority instruction sets the cleaning mode and the low-priority instruction sets the detergent dosage, and they do not conflict, then their valid information is integrated into the comprehensive control instruction. If there are conflicting instructions, such as the high-priority instruction requires low-temperature cleaning and the low-priority instruction requires high-temperature cleaning, then the content of the high-priority instruction is retained according to the priority order, and the content of the low-priority instruction is discarded or modified. In this way, the system synthesizes the reasonable parts of each control instruction to form the final comprehensive control instruction to ensure that the cleaning device can operate reasonably and effectively based on various factors.

[0110] This technical solution, the technical solution for determining the comprehensive control instruction based on the priority of the control instruction in different ways, makes the control of the cleaning device more intelligent. By setting the default priority order, the main control strategy can be quickly determined under normal circumstances, and important operation requirements are preferentially met, such as ensuring the safety of the device or giving priority to executing the user's immediate operation instructions. And the way of merging instructions based on the priority order of each control instruction to comprehensively determine the comprehensive control instruction can consider various factors more comprehensively, make full use of the information contained in different control instructions, integrate multiple requirements when there is no conflict between instructions, and improve the adaptability and user experience of the cleaning device. At the same time, the processing method for conflicting instructions ensures the rationality and stability of the device operation, avoids abnormal device operation caused by instruction contradictions, and thus improves the overall performance and reliability of the cleaning device.

[0111] In one embodiment, optionally, determining the comprehensive control instruction according to the first control instruction, the second control instruction, the third control instruction, and the priority includes:

[0112] Among the first control instruction, the second control instruction, and the third control instruction, if there are two conflicting control instructions that conflict with each other, the conflict control instruction with a lower priority is determined as an invalid control instruction, and the comprehensive control instruction is determined according to the other control instructions.

[0113] The conflicting control instructions can be the situation where there are contradictions or cannot be executed simultaneously between two or more instructions among the first control instruction, the second control instruction, and the third control instruction. These instructions are called conflicting control instructions. For example, one instruction requires setting the water temperature to 60 °C, while another instruction requires setting the water temperature to 30 °C. These two instructions regarding water temperature setting are conflicting control instructions.

[0114] The invalid control instruction can be an instruction that is not adopted and executed by the system due to its lower priority among the conflicting control instructions. Once it is determined as an invalid control instruction, the operation content contained in this instruction will not affect the operation of the cleaning device.

[0115] In this solution, first, the first control instruction, the second control instruction, and the third control instruction are analyzed and compared one by one to determine whether there are conflicts between them. Through a preset conflict detection algorithm, check whether the parameter settings and operation requirements of the instructions conflict with each other. During the analysis process, if it is found that the operation requirements between two or more control instructions cannot be satisfied simultaneously, that is, there is a conflict, then further compare the priorities of these conflicting control instructions. According to the priority level, the conflicting control instruction with a lower priority is marked as an invalid control instruction, which means that this instruction will not be executed, and the operation content it contains will not have an effect on the operation of the cleaning device. After excluding the invalid control instructions, the system integrates the remaining valid control instructions. Summarize and sort out the parameter settings and operation requirements regarding the operation of the cleaning device in these valid control instructions, remove the repetitive and redundant parts, and form a complete and unified comprehensive control instruction. For example, organize the setting information of parameters such as the cleaning mode, water temperature, and detergent dosage in the valid instructions to determine the final comprehensive control instruction to ensure that the cleaning device can operate according to reasonable parameters and operation requirements.

[0116] This technical solution effectively solves the possible contradiction problems among multiple control instructions by judging the priorities of control instructions from different sources and handling conflicts. When there are conflicting control instructions, the instruction with a lower priority is determined to be invalid, ensuring that the system can give priority to executing more important operation instructions, thereby improving the stability of the cleaning equipment operation. By integrating valid control instructions to determine the comprehensive control instruction, the cleaning equipment can perform comprehensive and reasonable operation parameter setting and operation control according to the user's voice operation intention, personalized preference, and the characteristics of the items to be cleaned. This intelligent control method not only improves the operation convenience and user experience of the cleaning equipment but also can flexibly adjust the cleaning strategy according to different situations, improve the cleaning effect, and avoid equipment operation abnormalities or errors caused by instruction conflicts, enhancing the overall performance of the cleaning equipment.

[0117] In one embodiment, optionally, after determining the program control parameters of the cleaning equipment according to the comprehensive control instruction, the method further includes:

[0118] Generating a prompt message according to the program control parameters and displaying it on the cleaning equipment and / or the intelligent terminal associated with the cleaning equipment;

[0119] If a modification instruction for the program control parameters is not received within a preset time period, or a confirmation instruction for the program control parameters is received within the preset time period, the cleaning operation is performed according to the program control parameters.

[0120] Among them, the prompt message can be generated according to the program control parameters and is used to convey to the user the operation information that the cleaning equipment is about to execute and the information of relevant parameter settings. It can be in text form, such as: about to clean in the standard mode, water temperature 40°C, cleaning time 30 minutes, 100 ml of detergent has been dispensed, or in other forms such as charts or graphs to intuitively display the parameter settings.

[0121] The above information can be displayed on the display screen of the cleaning equipment, such as various machine equipment capable of realizing the item cleaning function, such as industrial cleaning equipment, washing machines, dishwashers, and fruit and vegetable cleaning machines.

[0122] The intelligent terminal can be a device with intelligent processing capabilities associated with the cleaning equipment, such as a smart phone, a tablet computer, and a smart watch. These devices can be connected to the cleaning equipment through wireless communication technologies such as Wi-Fi and Bluetooth to realize functions such as remote control of the equipment, status monitoring, and receiving information sent by the equipment.

[0123] The control system of the cleaning device or the related software system creates a prompt message according to the determined program control parameters and in accordance with the preset information generation rules and formats. For example, the values of each parameter are organized into a text description according to a certain logic, or the parameters are presented in the form of a chart. Specifically, it can be displayed on the display screen of the cleaning device and / or sent to the intelligent terminal associated with the cleaning device through wireless communication and displayed on the screen of the intelligent terminal. When displayed on the cleaning device, it may be necessary to adapt the information to the size and resolution of the device's display screen. When displayed on the intelligent terminal, it may be displayed according to the interface design of the terminal application program.

[0124] The preset duration can be a time length preset in the system and used as a time standard for determining whether to perform a cleaning operation. This duration can be set according to actual needs, such as 1 minute, 30 seconds, etc.

[0125] The modification instruction can be sent by the user through the operation panel of the cleaning device or the associated intelligent terminal and is used to change the determined program control parameters. For example, if the user feels that the currently set water temperature is too high, an instruction is sent to lower the water temperature.

[0126] The confirmation instruction can be sent by the user through the operation panel of the cleaning device or the associated intelligent terminal and is used to confirm the displayed program control parameters and agree to perform the cleaning operation according to these parameters.

[0127] In this solution, the instruction sent by the user, including the modification instruction and the confirmation instruction, can be received through the receiving module of the control system of the cleaning device or the associated intelligent terminal through the corresponding communication interface. The system will parse and verify the received instruction to ensure the validity of the instruction.

[0128] After the prompt message is displayed, timing can start to detect whether a modification instruction or a confirmation instruction is received. If no modification instruction is received when the preset duration ends, it means that the user may approve the current program control parameter settings. If a confirmation instruction is received within the preset duration, it directly indicates that the user agrees to perform the cleaning operation according to the current parameters.

[0129] After determining the program control parameters of the cleaning device, this technical solution generates and displays prompt information, enabling users to clearly understand the operations and parameter settings that the device is about to execute, increasing the transparency of operations and the users' right to know. At the same time, a preset duration is set to judge the user's intention. If the user does not modify the parameters or directly confirm the parameters within the specified time, the cleaning operation is automatically executed, realizing the automation and convenience of operations. This not only reduces the user's operation steps and improves the usage efficiency but also avoids the situation where the device cannot operate normally due to the user's forgetting or failure to confirm in time. In addition, the prompt information can also be received and displayed through the intelligent terminal, enabling users to understand the device status when they are away from the device, enhancing the intelligence level of the device and the user experience.

[0130] Embodiment 2

[0131] Figure 2 It is a schematic flowchart of a multi-instruction program control method based on voice recognition provided by Embodiment 2 of the present application. This solution makes a better improvement to the above embodiment. The specific improvement is as follows: determining a comprehensive control instruction according to the first control instruction, the second control instruction, the third control instruction, and the priority, including: determining the filling values of each parameter field in the comprehensive control instruction according to the first control instruction, the second control instruction, the third control instruction, and the priority, and filling them to obtain the comprehensive control instruction; correspondingly, determining the program control parameters of the cleaning device according to the comprehensive control instruction, including: parsing according to the filling values of each parameter field in the comprehensive control instruction to obtain the program control parameters of the cleaning device. As Figure 2 shown, it specifically includes the following steps:

[0132] S201, obtaining the voice information of the user, and extracting semantic features and voiceprint features from the voice information;

[0133] S202, generating a first control instruction according to the semantic features;

[0134] S203, matching the user portrait according to the voiceprint features, and determining the user preferences according to the user portrait to obtain a second control instruction;

[0135] S204, when an item to be cleaned is recognized, obtaining the basic parameters of the item to be cleaned, and generating a third control instruction according to the basic parameters;

[0136] S205, identifying whether the semantic features include a preset qualifier; if so, determining the priority of each control instruction according to the preset qualifier;

[0137] S206. Determine the filling values of each parameter field in the comprehensive control instruction according to the first control instruction, the second control instruction, the third control instruction and the priority, and fill them to obtain the comprehensive control instruction;

[0138] Among them, the parameter field. The control instruction of the cleaning device usually contains multiple parameters in different aspects. For the convenience of management and processing, these parameters are divided into different fields according to functions or properties. For example, the cleaning mode parameter can be used as one field, the water temperature parameter as another field, and the detergent dosage parameter as another field, etc. Each parameter field corresponds to a specific type of setting during the operation of the cleaning device.

[0139] The filling value can be the specific numerical value or status information determined for each parameter field. For example, in the cleaning mode parameter field, the filling value may be the standard mode, the gentle mode, the strong mode, etc. In the water temperature parameter field, the filling value can be the specific temperature value, such as 30 °C, 40 °C, etc. In the detergent dosage parameter field, the filling value may be specific dosage values such as 100 ml, 150 ml, etc.

[0140] The comprehensive control instruction can be a set of instructions that integrates the relevant information of the first control instruction, the second control instruction and the third control instruction and is used to comprehensively control the operation of the cleaning device. It contains multiple parameter fields and their corresponding filling values, and these filling values determine the specific operation mode and parameter settings of the cleaning device during operation.

[0141] In this solution, first evaluate and compare the priorities of the first control instruction, the second control instruction and the third control instruction. Then, according to the priority order, analyze the parameter information contained in each control instruction in turn. For each parameter field, preferentially use the corresponding parameter filling value in the control instruction with a higher priority. If a certain parameter field is not involved in the control instruction with a higher priority, then check the control instruction with a lower priority until the filling value of each parameter field is determined. For example, if the priority of the first control instruction is the highest and it contains the setting of the cleaning mode as the strong mode, then the filling value of the cleaning mode parameter field in the comprehensive control instruction is determined to be the strong mode. If the first control instruction does not have a setting for the detergent dosage, while the second control instruction has a relevant setting and the priority of the second control instruction is the second highest, then use the filling value of the detergent dosage in the second control instruction. In this way, determine the filling values of each parameter field in the comprehensive control instruction.

[0142] S207. Analyze according to the filling values of each parameter field in the comprehensive control instruction to obtain the program control parameters of the cleaning device.

[0143] Program control parameters can refer to various specific parameters involved in the operation program of the cleaning device. These parameters directly determine the working state and cleaning effect of the cleaning device, including but not limited to parameters such as cleaning mode, water temperature, cleaning time, detergent dosage, dehydration speed, and number of rinses.

[0144] The technical solution provided in this embodiment realizes the refined and intelligent control of the cleaning device by determining the filling values of the parameter fields in the comprehensive control instruction according to the priority of the control instruction, and further parsing these filling values to obtain the program control parameters of the cleaning device. The clear priority judgment and parameter filling value determination method enable the system to reasonably integrate information when multiple control instructions exist simultaneously, prioritize important operation requirements, and avoid problems caused by instruction conflicts. The accurate parsing of the comprehensive control instruction ensures that the device can operate according to the expected parameter settings, improving the operation efficiency and cleaning effect of the cleaning device. This method not only enhances the user experience, making the user's operation intention more consistent with the device's operation, but also enhances the adaptability of the device, enabling it to handle the diverse needs of different users and the characteristics of different items to be cleaned, thereby improving the overall performance and reliability of the cleaning device.

[0145] Embodiment III

[0146] Figure 3 It is a schematic structural diagram of a multi-instruction program control device based on voice recognition provided in Embodiment III of the present application. As Figure 3 shown, the device includes:

[0147] A feature extraction module 301, configured to obtain the user's voice information and extract semantic features and voiceprint features from the voice information;

[0148] A first control instruction generation module 302, configured to generate a first control instruction according to the semantic features;

[0149] A second control instruction generation module 303, configured to match the user portrait according to the voiceprint features, determine the user preferences according to the user portrait, so as to obtain a second control instruction;

[0150] A third control instruction generation module 304, configured to obtain the basic parameters of the item to be cleaned when the item to be cleaned is recognized, and generate a third control instruction according to the basic parameters;

[0151] A priority determination module 305, configured to identify whether the semantic features include a preset qualifier; if so, determine the priority of each control instruction according to the preset qualifier;

[0152] An integrated control instruction determination module 306, configured to determine an integrated control instruction according to the first control instruction, the second control instruction, the third control instruction, and the priority.

[0153] A program control parameter determination module 307, configured to determine program control parameters of the cleaning device according to the integrated control instruction.

[0154] In an embodiment of the present application, a feature extraction module is configured to obtain voice information of a user and extract semantic features and voiceprint features from the voice information; a first control instruction generation module is configured to generate a first control instruction according to the semantic features; a second control instruction generation module is configured to match a user portrait according to the voiceprint features, determine user preferences according to the user portrait, so as to obtain a second control instruction; a third control instruction generation module is configured to obtain basic parameters of the item to be cleaned when the item to be cleaned is recognized, and generate a third control instruction according to the basic parameters; a priority determination module is configured to identify whether a preset qualifier is included in the semantic features; if so, determine the priorities of the control instructions according to the preset qualifier; an integrated control instruction determination module is configured to determine an integrated control instruction according to the first control instruction, the second control instruction, the third control instruction, and the priority; a program control parameter determination module is configured to determine program control parameters of the cleaning device according to the integrated control instruction. In the above technical solution, through the recognition of multiple control instructions, multiple aspects of control instructions can be analyzed through semantic information, voiceprint information, and basic parameters of the item, and then combined with the actual situation, the final control instruction for cleaning the item is determined, which can select the most suitable control instruction for the actual needs of the user among multiple control instructions, without complex interaction links, improving the intelligence level of the cleaning device and enhancing the user experience.

[0155] The multi-instruction program control device based on voice recognition in the embodiments of the present application can be a device, or a component, an integrated circuit, or a chip in a terminal. The device can be the cleaning device itself, or a mobile electronic device that controls the cleaning device, or a non-mobile electronic device. Exemplarily, the mobile electronic device can be a mobile phone, a tablet computer, a laptop computer, a handheld computer, a vehicle-mounted electronic device, a wearable device, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (PDA), etc. The non-mobile electronic device can be a server, a network attached storage (NAS), a personal computer (PC), a television (TV), a teller machine, or a self-service machine, etc. The embodiments of the present application do not make specific limitations.

[0156] The multi-instruction program control device based on voice recognition in the embodiments of the present application can be a device with an operating system. The operating system can be the Android operating system, the IOS operating system, or other possible operating systems. The embodiments of the present application do not make specific limitations.

[0157] The multi-instruction program control device based on voice recognition provided in the embodiments of the present application can implement each process implemented in the above-mentioned Embodiments 1 to 4. To avoid repetition, it will not be elaborated here.

[0158] Embodiment 4

[0159] As Figure 4 shown, the embodiments of the present application further provide a cleaning device 400, including a processor 401, a memory 402, a program or instruction stored on the memory 402 and executable on the processor 401. When the program or instruction is executed by the processor 401, it implements each process of the above-mentioned embodiments of the multi-instruction program control method based on voice recognition, and can achieve the same technical effects. To avoid repetition, it will not be elaborated here.

[0160] It should be noted that the cleaning device in the embodiments of the present application may include the above-mentioned mobile electronic device and non-mobile electronic device.

[0161] Embodiment 5

[0162] The embodiments of the present application further provide a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, it implements each process of the above-mentioned embodiments of the multi-instruction program control method based on voice recognition, and can achieve the same technical effects. To avoid repetition, it will not be elaborated here.

[0163] Among them, the processor is the processor in the cleaning device described in the above embodiments. The readable storage medium includes computer-readable storage media such as computer read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs.

[0164] Embodiment Six

[0165] Another embodiment of the present application provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run programs or instructions to implement each process of the above-mentioned multi-instruction program control method embodiment based on voice recognition, and can achieve the same technical effects. To avoid repetition, it will not be elaborated here.

[0166] It should be understood that the chip mentioned in the embodiments of the present application can also be referred to as a system-on-chip, system chip, chip system, or system-on-a-chip, etc.

[0167] It should be noted that in this article, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device. Without further limitations, the element defined by the statement "including one..." does not exclude the existence of additional identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in a reverse order according to the functions involved. For example, the described methods may be performed in an order different from that described, and various steps may be added, omitted, or combined. Additionally, the features described with reference to certain examples may be combined in other examples.

[0168] Through the description of the above embodiments, those skilled in the art can clearly understand that the above embodiment methods can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer software product. The computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disc) and includes several instructions to enable a terminal (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in various embodiments of the present application.

[0169] The embodiments of the present application have been described above in conjunction with the accompanying drawings. However, the present application is not limited to the above specific embodiments. The above specific embodiments are merely illustrative rather than restrictive. Under the inspiration of the present application, those of ordinary skill in the art can also make many forms without departing from the purpose of the present application and the scope protected by the claims, and all of them fall within the protection scope of the present application.

[0170] The above is only the preferred embodiment of the present application and the technical principles applied. The present application is not limited to the specific embodiments described herein. Various obvious changes, re-adjustments and substitutions that can be made by those skilled in the art will not depart from the protection scope of the present application. Therefore, although the present application has been described in more detail through the above embodiments, the present application is not limited to the above embodiments. Without departing from the concept of the present application, more other equivalent embodiments can be included, and the scope of the present application is determined by the scope of the claims.

Claims

1. A multi-instruction program control method based on speech recognition, characterized in that, The method includes: Obtaining the voice information of the user, and extracting semantic features and voiceprint features from the voice information; Generating a first control instruction according to the semantic features; Matching the user portrait according to the voiceprint features, and determining the user preference according to the user portrait to obtain a second control instruction; When an item to be cleaned is recognized, obtaining the basic parameters of the item to be cleaned, and generating a third control instruction according to the basic parameters; Identifying whether the semantic features include a preset qualifier; if so, identifying the target control instruction among the first control instruction, the second control instruction, and the third control instruction associated with the preset qualifier; Adjusting the priority of the target control instruction based on the priority adjustment information included in the preset qualifier to obtain the priorities of each control instruction; Determining a comprehensive control instruction based on the first control instruction, the second control instruction, the third control instruction, and the priorities, based on the control instruction with the highest priority; Or, Based on the first control instruction, the second control instruction, the third control instruction, and the priorities, merging the instructions in the order of the priorities of each control instruction to comprehensively determine a comprehensive control instruction; Determining the program control parameters of the cleaning device according to the comprehensive control instruction.

2. The multi-instruction program control method based on speech recognition according to claim 1, wherein Determining a comprehensive control instruction based on the first control instruction, the second control instruction, the third control instruction, and the priorities, includes: Determining the filling values of each parameter field in the comprehensive control instruction according to the first control instruction, the second control instruction, the third control instruction, and the priorities, and filling them to obtain the comprehensive control instruction; Correspondingly, determining the program control parameters of the cleaning device according to the comprehensive control instruction, includes: Parsing according to the filling values of each parameter field in the comprehensive control instruction to obtain the program control parameters of the cleaning device.

3. The multi-instruction program control method based on speech recognition according to claim 1, wherein Determining a comprehensive control instruction based on the first control instruction, the second control instruction, the third control instruction, and the priorities, includes: Among the first control instruction, the second control instruction, and the third control instruction, if there are two conflicting control instructions that conflict with each other, the conflicting control instruction with the lower priority is determined as an invalid control instruction, and the comprehensive control instruction is determined according to the other control instructions.

4. The multi-instruction program control method based on speech recognition according to claim 1, characterized in that, After determining the program control parameters of the cleaning device according to the comprehensive control instruction, the method further includes: Generating a prompt message according to the program control parameters, and displaying it on the cleaning device and / or the intelligent terminal associated with the cleaning device; If a modification instruction for the program control parameters is not received within a preset time period, or a confirmation instruction for the program control parameters is received within a preset time period, the cleaning operation is performed according to the program control parameters.

5. The multi-instruction program control method based on speech recognition according to claim 1, wherein The method further includes: Identifying whether the semantic features include a preset qualifier; if not, reading the preset default priorities of each control instruction.

6. A multi-instruction program control device based on speech recognition, characterized in that, The device includes: A feature extraction module, configured to obtain the voice information of the user, and extract semantic features and voiceprint features from the voice information; The first control instruction generation module is configured to generate a first control instruction according to the semantic feature; The second control instruction generation module is configured to match a user profile according to the voiceprint feature, determine user preferences according to the user profile, so as to obtain a second control instruction; The third control instruction generation module is configured to, when an item to be cleaned is recognized, obtain basic parameters of the item to be cleaned, and generate a third control instruction according to the basic parameters; The priority determination module is configured to identify whether a preset qualifier is included in the semantic feature; if so, identify a target control instruction among the first control instruction, the second control instruction, and the third control instruction associated with the preset qualifier; based on the priority adjustment information included in the preset qualifier, adjust the priority of the target control instruction to obtain the priorities of the respective control instructions; The comprehensive control instruction determination module is configured to determine a comprehensive control instruction based on the control instruction with the highest priority according to the first control instruction, the second control instruction, the third control instruction, and the priorities; or, according to the first control instruction, the second control instruction, the third control instruction, and the priorities, perform instruction merging based on the priority order of the respective control instructions to comprehensively determine a comprehensive control instruction; The program control parameter determination module is configured to determine program control parameters of the cleaning device according to the comprehensive control instruction.

7. A cleaning device, characterized in that, It includes a processor, a memory, and a program or instruction stored on the memory and executable on the processor. When the program or instruction is executed by the processor, the steps of the multi-instruction program control method based on voice recognition according to any one of claims 1-5 are implemented.

8. A readable storage medium, characterized in that, A program or instruction is stored on the readable storage medium. When the program or instruction is executed by a processor, the steps of the multi-instruction program control method based on voice recognition according to any one of claims 1-5 are implemented.

Images