A smart home control method based on user portrait and related equipment

Abstract

The application discloses a kind of based on user portrait's smart home control method and related equipment, the method includes: obtaining the portrait information of user and the first voice input instruction of user, after first voice input instruction is processed by algorithm, first control instruction is obtained;According to first control instruction, obtain the device name to be controlled and the operation instruction to be executed, according to the device name to be controlled, attribute relationship table is obtained;Portrait information and the operation instruction to be executed are compared with attribute relationship table, if portrait information and the operation instruction to be executed meet the corresponding device control attribute in attribute relationship table, then the first control instruction is executed to the device to be controlled, otherwise, according to portrait information, corresponding device control attribute is obtained in attribute relationship table, and user is prompted to re-voice input second voice input instruction meeting device control attribute;The application is combined with user portrait data, realizes the smart home control for different users, improves the individuality and intelligentization of home.

Description

Technical Field

[0001] This invention relates to the field of voice control technology, and in particular to a smart home control method and related equipment based on user profiles. Background Technology

[0002] In the smart home field, major manufacturers are using voice-enabled products such as speakers, panels, and tablets to enable voice control of home appliances such as air conditioners, humidifiers, and fans. In the field of voice control, the mainstream approach in the industry is to achieve user semantic understanding through deep learning, machine learning, and other methods. This converts the user's spoken language into a structured, executable JSON format and transmits it to the cloud to control the device. The level of spoken language understanding varies across the industry, but the overall results are largely consistent.

[0003] However, current voice control lacks integration with user profile information. Sometimes users issue commands that are detrimental to their experience or health. For example, a 70-year-old might say, "Turn on the air conditioner at 18 degrees Celsius," which is clearly unsuitable for an elderly person. Therefore, there is an urgent need in this field for a device control standard based on user profile information (age, gender, weight, etc.) to achieve smart home control.

[0004] Therefore, existing technologies still need to be improved and developed. Summary of the Invention

[0005] The main objective of this invention is to provide a smart home control method, system, terminal, and computer-readable storage medium based on user profiles, aiming to solve the problem in the prior art that voice control lacks linkage with the user's own profile information, and sometimes users issue commands that are detrimental to their own experience or physical health.

[0006] To achieve the above objectives, the present invention provides a smart home control method based on user profiles, which includes the following steps:

[0007] Obtain the user's profile information and the user's first voice input command, and process the first voice input command using an algorithm to obtain the first control command;

[0008] The name of the device to be controlled and the first operation instruction to be executed are obtained according to the first control instruction, and the attribute relationship table between the user and the device is obtained according to the name of the device to be controlled.

[0009] The profile information and the first operation instruction to be executed are compared with the attribute relationship table. If the profile information and the first operation instruction to be executed match the corresponding device control attribute in the attribute relationship table, the first control instruction is executed on the device to be controlled. Otherwise, the corresponding device control attribute is obtained from the attribute relationship table according to the profile information, and the user is prompted to input a second voice input instruction that matches the device control attribute again.

[0010] Optionally, in the aforementioned smart home control method based on user profiles, the profile information includes age information, weight information, and gender information;

[0011] The age information, weight information, and gender information have priorities. When the age information, weight information, and gender information exist simultaneously, the portrait information with the highest priority and the first operation instruction to be executed are compared with the attribute relationship table.

[0012] Optionally, in the aforementioned smart home control method based on user profiles, the attribute relationship table is used to store device control attributes corresponding to users with different profile information.

[0013] Optionally, the smart home control method based on user profiles includes the following algorithm processing: preprocessing, semantic parsing, and postprocessing.

[0014] Optionally, the smart home control method based on user profiles, wherein the step of processing the first voice input command into a first control command via an algorithm specifically includes:

[0015] The first voice input command is subjected to general preprocessing, entity normalization, nickname matching, pinyin error correction and NLP word segmentation to obtain the preprocessed voice input command.

[0016] The APP name and scene name appearing in the preprocessed voice input command are replaced with placeholders. Commands that do not conform to the user's intent in the replaced voice input command are filtered out. Then, the filtered voice input command is subjected to whitelist matching and regular expression matching to construct the semantic parsing result.

[0017] The semantic parsing result is subjected to intent rewriting, special intent processing, return to device control, return to scene control, and field correction to obtain the first control instruction.

[0018] Optionally, the smart home control method based on user profiles, after prompting the user to input a second voice input command that conforms to the device control attributes, further includes:

[0019] Determine whether the second voice input command is the same as the first voice input command. If the second voice input command is the same as the first voice input command, then execute the first control command.

[0020] If the second voice input instruction is different from the first voice input instruction, the second voice input instruction is processed by an algorithm to obtain a second control instruction. A second operation instruction to be executed is obtained based on the second control instruction. The portrait information and the second operation instruction to be executed are compared with the attribute relationship table again.

[0021] Optionally, the smart home control method based on user profiles, wherein after executing the first control command if the second voice input command is the same as the first voice input command, further includes:

[0022] Collect the first control command, and update the device control attribute corresponding to the profile information in the attribute relationship table according to the first control command and the user's profile information.

[0023] Furthermore, to achieve the above objectives, the present invention also provides a smart home control system based on user profiles, wherein the smart home control system based on user profiles includes:

[0024] The control command acquisition module is used to acquire the user's profile information and the user's first voice input command, and to process the first voice input command to obtain the first control command.

[0025] The attribute relationship table acquisition module is used to obtain the name of the device to be controlled and the first operation instruction to be executed according to the first control instruction, and to obtain the attribute relationship table between the user and the device according to the name of the device to be controlled.

[0026] The control instruction execution module is used to compare the profile information and the first operation instruction to be executed with the attribute relationship table. If the profile information and the first operation instruction to be executed match the corresponding device control attribute in the attribute relationship table, the first control instruction is executed on the device to be controlled. Otherwise, the corresponding device control attribute is obtained from the attribute relationship table according to the profile information, and the user is prompted to input a second voice input instruction that matches the device control attribute again.

[0027] Furthermore, to achieve the above objectives, the present invention also provides a terminal, wherein the terminal includes: a memory, a processor, and a smart home control program based on a user profile stored in the memory and executable on the processor, wherein when the smart home control program based on the user profile is executed by the processor, it implements the steps of the smart home control method based on the user profile as described above.

[0028] Furthermore, to achieve the above objectives, the present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a smart home control program based on a user profile, and when the smart home control program based on a user profile is executed by a processor, it implements the steps of the smart home control method based on a user profile as described above.

[0029] In this invention, user profile information and the user's first voice input command are obtained. The first voice input command is processed by an algorithm to obtain a first control command. The name of the device to be controlled and a first operation command to be executed are obtained based on the first control command. An attribute relationship table is obtained based on the name of the device to be controlled. The profile information and the first operation command to be executed are compared with the attribute relationship table. If the profile information and the first operation command to be executed match the corresponding device control attribute in the attribute relationship table, the first control command is executed on the device to be controlled. Otherwise, the corresponding device control attribute is obtained from the attribute relationship table based on the profile information, and the user is prompted to input a second voice input command that matches the device control attribute. This invention improves the user's control experience and increases the intelligent effect. Through rational control settings, it helps to save energy and reduce emissions, and cultivate good home appliance usage habits among users. Attached Figure Description

[0030] Figure 1 This is a flowchart of a preferred embodiment of the smart home control method based on user profiles of the present invention;

[0031] Figure 2 This is an overall architecture diagram of a preferred embodiment of the smart home control method based on user profiles of the present invention;

[0032] Figure 3 This is a schematic diagram of the algorithm processing in the smart home control method based on user profiles of the present invention;

[0033] Figure 4 This is a flowchart of a preferred embodiment of the algorithm processing in the smart home control method based on user profiles of the present invention;

[0034] Figure 5 This is a schematic diagram of the semantic parsing part during algorithm processing in the smart home control method based on user profiles of this invention;

[0035] Figure 6 This is a schematic diagram of a preferred embodiment of the smart home control system based on user profiles of the present invention;

[0036] Figure 7 This is a diagram illustrating the operating environment of a preferred embodiment of the terminal of the present invention. Detailed Implementation

[0037] This application provides a smart home control method and related devices based on user profiles. To make the purpose, technical solution, and effects of this application clearer and more explicit, the following detailed description is provided with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only for explaining this application and are not intended to limit this application.

[0038] It will be understood by those skilled in the art that, unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains. It should also be understood that terms such as those defined in general dictionaries should be understood to have the same meaning as in the context of the prior art, and should not be interpreted in an idealized or overly formal sense unless specifically defined as herein.

[0039] Furthermore, if the embodiments of this invention involve descriptions such as "first" or "second," these descriptions are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined with "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the technical solutions of the various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. If the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed by this invention.

[0040] The preferred embodiment of the smart home control method based on user profiles described in this invention, such as... Figure 1 and Figure 2 As shown, the smart home control method based on user profiles includes the following steps:

[0041] Step S100: Obtain the user's profile information and the user's first voice input command, and process the first voice input command using an algorithm to obtain the first control command.

[0042] When a user is within the service range of a smart home, in order to control the smart home, they first need to log in to their personal account and fill in their profile information, which includes age, gender, and weight. At least one of these three information must be filled in when logging in.

[0043] It is understood that the profile information in this application includes, but is not limited to, information such as age, gender, and weight, and may also involve other physical health indicators such as blood pressure and heart rate. Since the user profile information involves user privacy, only examples of information are given here.

[0044] like Figure 3 As shown, after a user successfully logs in and fills in the profile information, the user sends a first voice input command to the central control system (a central control system used in multimedia classrooms, multi-functional conference halls, command and control centers, smart homes, etc., where users can use button-type control panels, computer monitors, touch screens, and wireless remote controls to control projectors, display stands, DVD players, video recorders, etc. through computers and central control system software). For example, the user says the voice command "Turn on the air conditioner and set the temperature to 18 degrees." This voice command is input to the scheduling module as the first voice input command. With the support of the configuration module, database, and server interface, the core algorithm processes the first voice input command through the scheduling module to obtain the first control command.

[0045] Furthermore, the algorithm processing includes: preprocessing, semantic parsing, and post-processing; such as Figure 4 As shown, the step of processing the first voice input command into a first control command via an algorithm specifically includes:

[0046] Step S101: Perform general preprocessing, entity normalization, nickname matching, pinyin error correction and NLP word segmentation on the first voice input command to obtain the preprocessed voice input command.

[0047] Step S102, as follows Figure 5 As shown, the APP name and scene name appearing in the preprocessed voice input command are replaced with placeholders. Commands in the replaced voice input command that do not conform to the user's intent are filtered out. Then, the filtered voice input command is subjected to whitelist matching and regular expression matching to construct the semantic parsing result.

[0048] The APP name is used to directly control an APP to change to a preset state. The scene name includes built-in and user-defined scene names. Scenes can be used to directly control multiple devices to change to preset states. For example, if a user sets the reading mode to turn on the desk lamp and turn off the bedroom light, set the air conditioner to 27 degrees and turn off the washing machine, all of the above instructions will be executed automatically when the user enters the reading mode using a command.

[0049] To facilitate unified recognition by semantic algorithms, this application temporarily replaces the APP name and scene name with placeholders (symbols that reserve a fixed position and then add content to it later, widely used in the editing of various documents in computers) during the preprocessing stage, and then fills the corresponding names into the slots during the postprocessing stage.

[0050] Slots are typically used for queries with variables. One slot corresponds to one variable. Since the final return result of the algorithm in this application is in JSON format, each parameter in the JSON format corresponds to a slot. For example, if a user issues a voice command "Please set a certain air conditioner to 18 degrees", the returned result is slot: {Intent: Set temperature, Nickname: a certain air conditioner, Device: air conditioner, Parameter: 18, Unit: degrees Celsius}.

[0051] Furthermore, after temporarily replacing the APP name and scene name with placeholders, the replaced voice input commands are subjected to multi-command filtering. Commands that do not conform to the user's intent are filtered out. The multi-command filtering process is as follows: when multiple commands are recognized, commands that do not conform to the user's intent are filtered out. For example, if the user's command is: "Turn on the TV and turn off the air conditioner", three commands will be recognized: "Turn on the TV", "Turn on the air conditioner", and "Turn off the air conditioner". However, the user's intention is "Turn on the TV" and "Turn off the air conditioner", so the command "Turn on the air conditioner" needs to be filtered out.

[0052] The filtered voice input commands are then matched against a whitelist. Commands that are frequently called by the user are added to the whitelist. Whitelisted commands will not participate in voice matching and parsing, but will be directly filled into word slots for control. Finally, the voice commands that have been matched against the whitelist are matched using regular expressions to construct the semantic parsing results.

[0053] Step S103: Perform intent rewriting, special intent processing, return to device control, return to scene control, and field correction on the semantic parsing result to obtain the first control instruction.

[0054] The post-processing mainly implements intent rewriting (e.g., changing all slots containing "degree" to "Celsius"), special intent processing (all lights on or off is scene control rather than device control, curtains open or closed is travel control rather than device on / off), returning to device control (adding the matched device ID to the device control list), returning to scene control (adding the matched scene ID to the scene control list), and field correction function (custom patches for specific projects or versions), thereby obtaining the first control instruction.

[0055] In other words, after the first voice input command is processed by the algorithm, the resulting first control command can be converted into a control command that can control the smart home to perform corresponding operations. In this invention, the user speaks a voice command to the central control device, and the device sends the recognized text to the backend. The backend then transmits it to the algorithm, which enables the smart home to understand the user's command and provide an intelligent response.

[0056] Step S200: Obtain the name of the device to be controlled and the first operation instruction to be executed according to the first control instruction, and obtain the attribute relationship table between the user and the device according to the name of the device to be controlled.

[0057] Based on the first control command issued by the user to the device, we need to rewrite the first control command to a certain extent according to the user profile data, so as to give the user a better control experience. Therefore, before the user logs in to use the smart home, a user-device attribute relationship table is pre-set for each smart home device. The attribute relationship table contains all possible situations of user profile information, as well as the device attributes that each type of user profile information should correspond to.

[0058] For example, if the user issues a voice command to set the air conditioner to 18 degrees, the name of the device to be controlled in the first control command will be "air conditioner". At this time, the pre-set attribute relationship table between the user and the air conditioner will be obtained.

[0059] Step S300: Compare the portrait information and the first operation instruction to be executed with the attribute relationship table. If the portrait information and the first operation instruction to be executed match the corresponding device control attribute in the attribute relationship table, then execute the first control instruction on the device to be controlled. Otherwise, obtain the corresponding device control attribute in the attribute relationship table according to the portrait information, and prompt the user to input a second voice input instruction that matches the device control attribute again.

[0060] As shown in Table 1 below, the attribute relationship table will be illustrated again using air conditioning equipment as an example.

[0061] Table 1 Relationship between User Information and Air Conditioner Attributes

[0062]

[0063] Specifically, as shown in Table 1 above, user information includes age, gender, and weight, and device attributes include temperature, fan speed, and mode. The table also provides the device attributes corresponding to different user information. For example, except for young adults aged 18 to 40, whose air conditioning temperature can be between 20 and 26 degrees Celsius, people of other age groups should have their air conditioning temperature above 26 degrees Celsius.

[0064] Meanwhile, in this application, the age information, weight information, and gender information have priorities. When the age information, weight information, and gender information exist simultaneously, the portrait information with the highest priority and the first operation instruction to be executed are compared with the attribute relationship table.

[0065] It should be emphasized that the age segmentation, gender category, and weight segmentation in this application are for reference only. The user profile information dimensions can be segmented according to the specific application scenario. At the same time, the user profile data and the priority of the user profile data are set according to actual needs, and no restrictions are imposed here.

[0066] For example, for air conditioning equipment, we set the user information priority as age > gender > weight. Then, the user inputs a text via voice, and we further process the formatted control command after algorithm processing. For example, if user A says, "Set the air conditioner to 25 degrees," the command after algorithm processing is {Device: Air Conditioner, Action: Set Temperature, Value: 18 degrees}. Based on the previously obtained user A profile information, {Gender: Female, Age: 26 years old, Weight: 80 catties}, the control command needs to be adjusted. Since age has the highest priority, we do not need to consider weight and gender information. We directly find the air conditioner setting temperature that 26 years old should correspond to ([18-40 years old], [20-26 degrees+]) in the attribute relationship table. It can be seen that user A's desired temperature setting is 25 degrees, which is within a reasonable temperature setting range. Therefore, the first control command is executed on the device to be controlled (air conditioner).

[0067] Furthermore, if user A says, "Set the air conditioner to 18 degrees," the command after algorithm processing is {Device: Air conditioner, Action: Set temperature, Value: 18 degrees}. Based on the previously obtained user A profile information, {Gender: Female, Age: 26, Weight: 80 catties}, the control command needs to be adjusted. Since age has the highest priority, weight and gender information do not need to be considered. We directly find the air conditioner setting temperature that should correspond to 26 years old in the attribute relationship table ([18-40 years old], [20-26 degrees+]). It can be seen that user A's desired temperature setting is 18 degrees, which is not within the reasonable temperature setting range. At this time, we need to reply, "Sorry, we suggest you set the temperature to 20 to 26 degrees."

[0068] It is understandable that if the user's profile information does not contain age information, but only weight and gender information, then according to the priority division, the gender information is used to determine whether the profile information meets the device control attributes. The specific judgment process is similar to that described above, and will not be repeated here.

[0069] Furthermore, after prompting the user to input a second voice input command that conforms to the device control attributes, the method further includes:

[0070] Determine whether the second voice input command is the same as the first voice input command. If the second voice input command is the same as the first voice input command, then execute the first control command.

[0071] If the second voice input instruction is different from the first voice input instruction, the second voice input instruction is processed by an algorithm to obtain a second control instruction. A second operation instruction to be executed is obtained based on the second control instruction. The portrait information and the second operation instruction to be executed are compared with the attribute relationship table again.

[0072] It is understandable that if a user wants to stick to their own ideas, the second voice input command should be the same as the first voice input command. The sameness of the second voice input command and the first voice input command here is not limited to the same expression. As long as the meaning after semantic parsing is the same, it means that the second voice input command and the first voice input command are the same.

[0073] If the second voice input command is different from the first voice input command, the second voice input command is processed using the same algorithm as described above to obtain a second control command. Based on the second control command, a second operation command to be executed is obtained. The profile information and the second operation command to be executed are compared with the attribute relationship table again: if the profile information and the second operation command to be executed match the corresponding device control attribute in the attribute relationship table, the second control command is executed on the device to be controlled; if the profile information and the second operation command to be executed do not match the corresponding device control attribute in the attribute relationship table, the above process is repeated, and a prompt message is issued again. This improves the personalization and intelligence of the home and provides users with guidance suitable for their own health conditions.

[0074] Furthermore, if the second voice input command is the same as the first voice input command, then after executing the first control command, the method further includes:

[0075] Collect the first control command, and update the device control attribute corresponding to the profile information in the attribute relationship table according to the first control command and the user's profile information.

[0076] For example, if the user's first voice input command is "set the air conditioner to 18 degrees", and after being prompted, the user still does not make any changes and continues to issue the first voice input command, then it is considered that the user has emphasized the first voice input command twice. At this point, it is considered that the user must execute the first voice input command, and the air conditioner will be adjusted according to the first voice input command, and the user's first control command will be collected.

[0077] Simultaneously, the device control attributes corresponding to the profile information in the attribute relationship table are updated according to the first control command and the user's profile information. For example, if the user is 26 years old and has repeatedly specified setting the air conditioner temperature to 18 degrees Celsius, the age range [18-40 years old] and suitable temperature in the attribute relationship table are adjusted to [18-26 degrees Celsius+]. This way, the user will not be reminded again when they specify setting the air conditioner to 18 degrees Celsius next time, ensuring the rationality of smart home control while also paying attention to the user's personalized settings.

[0078] It is evident that this application enhances the user's control experience and increases the level of intelligence; through rational control settings, it helps to save energy and reduce emissions, and cultivates good home appliance usage habits among users.

[0079] Furthermore, such as Figure 6 As shown, based on the above-mentioned user profile-based smart home control method, the present invention also provides a user profile-based smart home control system, wherein the user profile-based smart home control system includes:

[0080] The control command acquisition module 51 is used to acquire the user's profile information and the user's first voice input command, and to process the first voice input command to obtain the first control command.

[0081] The attribute relationship table acquisition module 52 is used to obtain the name of the device to be controlled and the first operation instruction to be executed according to the first control instruction, and to obtain the attribute relationship table between the user and the device according to the name of the device to be controlled.

[0082] The control instruction execution module 53 is used to compare the profile information and the first operation instruction to be executed with the attribute relationship table. If the profile information and the first operation instruction to be executed match the corresponding device control attribute in the attribute relationship table, the first control instruction is executed on the device to be controlled. Otherwise, the corresponding device control attribute is obtained from the attribute relationship table according to the profile information, and the user is prompted to input a second voice input instruction that matches the device control attribute again.

[0083] Furthermore, such as Figure 7 As shown, based on the above-mentioned smart home control method and system based on user profiles, the present invention also provides a terminal, which includes a processor 10, a memory 20 and a display 30. Figure 7 Only some of the terminal components are shown; however, it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0084] In some embodiments, the memory 20 may be an internal storage unit of the terminal, such as a hard disk or memory. In other embodiments, the memory 20 may be an external storage device of the terminal, such as a plug-in hard disk, SmartMedia Card (SMC), Secure Digital (SD) card, or Flash Card. Further, the memory 20 may include both internal and external storage units. The memory 20 is used to store application software and various types of data installed on the terminal, such as program code installed on the terminal. The memory 20 can also be used to temporarily store data that has been output or will be output. In one embodiment, the memory 20 stores a smart home control program 40 based on a user profile, which can be executed by the processor 10 to implement the smart home control method based on a user profile as described in this application.

[0085] In some embodiments, the processor 10 may be a central processing unit (CPU), a microprocessor, or other data processing chip, used to run program code stored in the memory 20 or process data, such as executing the smart home control method based on user profiles.

[0086] In some embodiments, the display 30 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen. The display 30 is used to display information on the terminal and to display a visual user interface. The components 10-30 of the terminal communicate with each other via a system bus.

[0087] In one embodiment, when the processor 10 executes the smart home control program 40 based on the user profile stored in the memory 20, the following steps are performed:

[0088] Obtain the user's profile information and the user's first voice input command, and process the first voice input command using an algorithm to obtain the first control command;

[0089] The name of the device to be controlled and the first operation instruction to be executed are obtained according to the first control instruction, and the attribute relationship table between the user and the device is obtained according to the name of the device to be controlled.

[0090] The profile information and the first operation instruction to be executed are compared with the attribute relationship table. If the profile information and the first operation instruction to be executed match the corresponding device control attribute in the attribute relationship table, the first control instruction is executed on the device to be controlled. Otherwise, the corresponding device control attribute is obtained from the attribute relationship table according to the profile information, and the user is prompted to input a second voice input instruction that matches the device control attribute again.

[0091] The portrait information includes age, weight, and gender information;

[0092] The age information, weight information, and gender information have priorities. When the age information, weight information, and gender information exist simultaneously, the portrait information with the highest priority and the first operation instruction to be executed are compared with the attribute relationship table.

[0093] The attribute relationship table is used to store the device control attributes corresponding to users with different profile information.

[0094] The algorithm processing includes: preprocessing, semantic parsing, and postprocessing.

[0095] Specifically, the step of processing the first voice input command into a first control command via an algorithm includes:

[0096] The first voice input command is subjected to general preprocessing, entity normalization, nickname matching, pinyin error correction and NLP word segmentation to obtain the preprocessed voice input command.

[0097] The APP name and scene name appearing in the preprocessed voice input command are replaced with placeholders. Commands that do not conform to the user's intent in the replaced voice input command are filtered out. Then, the filtered voice input command is subjected to whitelist matching and regular expression matching to construct the semantic parsing result.

[0098] The semantic parsing result is subjected to intent rewriting, special intent processing, return to device control, return to scene control, and field correction to obtain the first control instruction.

[0099] The method further includes, after prompting the user to input a second voice input command that conforms to the device control attributes, the following:

[0100] Determine whether the second voice input command is the same as the first voice input command. If the second voice input command is the same as the first voice input command, then execute the first control command.

[0101] If the second voice input instruction is different from the first voice input instruction, the second voice input instruction is processed by an algorithm to obtain a second control instruction. A second operation instruction to be executed is obtained based on the second control instruction. The portrait information and the second operation instruction to be executed are compared with the attribute relationship table again.

[0102] Wherein, if the second voice input command is the same as the first voice input command, after executing the first control command, the method further includes:

[0103] Collect the first control command, and update the device control attribute corresponding to the profile information in the attribute relationship table according to the first control command and the user's profile information.

[0104] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a smart home control program based on a user profile, and the smart home control program based on a user profile, when executed by a processor, implements the steps of the smart home control method based on a user profile as described above.

[0105] In summary, this invention discloses a smart home control method and related devices based on user profiles. The method includes: acquiring user profile information and a first voice input command from the user; processing the first voice input command using an algorithm to obtain a first control command; obtaining the name of the device to be controlled and a first operation command to be executed based on the first control command; obtaining an attribute relationship table based on the name of the device to be controlled; comparing the profile information and the first operation command to be executed with the attribute relationship table; if the profile information and the first operation command to be executed match the corresponding device control attribute in the attribute relationship table, then executing the first control command on the device to be controlled; otherwise, obtaining the corresponding device control attribute in the attribute relationship table based on the profile information, and prompting the user to input a second voice input command that matches the device control attribute again. This invention improves the user's control experience and enhances the intelligent effect; through rational control settings, it helps to save energy and reduce emissions, and cultivate good home appliance usage habits among users.

[0106] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal that includes that element.

[0107] Of course, those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided by this invention can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0108] It should be understood that the application of the present invention is not limited to the examples above. Those skilled in the art can make improvements or modifications based on the above description, and all such improvements and modifications should fall within the protection scope of the appended claims.

Claims

1. A smart home control method based on user profiles, characterized in that, The aforementioned smart home control method based on user profiles includes: Obtain the user's profile information and the user's first voice input command, and process the first voice input command using an algorithm to obtain the first control command; The name of the device to be controlled and the first operation instruction to be executed are obtained according to the first control instruction, and the attribute relationship table between the user and the device is obtained according to the name of the device to be controlled. The profile information and the first operation instruction to be executed are compared with the attribute relationship table. If the profile information and the first operation instruction to be executed match the corresponding device control attribute in the attribute relationship table, the first control instruction is executed on the device to be controlled. Otherwise, the corresponding device control attribute is obtained from the attribute relationship table according to the profile information, and the user is prompted to input a second voice input instruction that matches the device control attribute again.

2. The smart home control method based on user profiles according to claim 1, characterized in that, The portrait information includes age, weight, and gender. The age information, weight information, and gender information have priorities. When the age information, weight information, and gender information exist simultaneously, the portrait information with the highest priority and the first operation instruction to be executed are compared with the attribute relationship table.

3. The smart home control method based on user profiles according to claim 1, characterized in that, The attribute relationship table is used to store the device control attributes corresponding to users with different profile information.

4. The smart home control method based on user profiles according to claim 1, characterized in that, The algorithm processing includes: preprocessing, semantic parsing, and postprocessing.

5. The smart home control method based on user profiles according to claim 4, characterized in that, The step of processing the first voice input command into a first control command using an algorithm specifically includes: The first voice input command is subjected to general preprocessing, entity normalization, nickname matching, pinyin error correction and NLP word segmentation to obtain the preprocessed voice input command. The APP name and scene name appearing in the preprocessed voice input command are replaced with placeholders. Commands that do not conform to the user's intent in the replaced voice input command are filtered out. Then, the filtered voice input command is subjected to whitelist matching and regular expression matching to construct the semantic parsing result. The semantic parsing result is subjected to intent rewriting, special intent processing, return to device control, return to scene control, and field correction to obtain the first control instruction.

6. The smart home control method based on user profiles according to claim 1, characterized in that, After prompting the user to input a second voice input command that conforms to the device control attributes, the method further includes: Determine whether the second voice input command is the same as the first voice input command. If the second voice input command is the same as the first voice input command, then execute the first control command. If the second voice input instruction is different from the first voice input instruction, the second voice input instruction is processed by an algorithm to obtain a second control instruction. A second operation instruction to be executed is obtained based on the second control instruction. The portrait information and the second operation instruction to be executed are compared with the attribute relationship table again.

7. The smart home control method based on user profiles according to claim 6, characterized in that, If the second voice input command is the same as the first voice input command, then after executing the first control command, the method further includes: Collect the first control command, and update the device control attribute corresponding to the profile information in the attribute relationship table according to the first control command and the user's profile information.

8. A smart home control system based on user profiles, characterized in that, The user profile-based smart home control system includes: The control command acquisition module is used to acquire the user's profile information and the user's first voice input command, and to process the first voice input command to obtain the first control command. The attribute relationship table acquisition module is used to obtain the name of the device to be controlled and the first operation instruction to be executed according to the first control instruction, and to obtain the attribute relationship table between the user and the device according to the name of the device to be controlled. The control instruction execution module is used to compare the profile information and the first operation instruction to be executed with the attribute relationship table. If the profile information and the first operation instruction to be executed match the corresponding device control attribute in the attribute relationship table, the first control instruction is executed on the device to be controlled. Otherwise, the corresponding device control attribute is obtained from the attribute relationship table according to the profile information, and the user is prompted to input a second voice input instruction that matches the device control attribute again.

9. A terminal, characterized in that, The terminal includes: a memory, a processor, and a user profile-based smart home control program stored in the memory and executable on the processor. When the user profile-based smart home control program is executed by the processor, it implements the steps of the user profile-based smart home control method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a smart home control program based on user profiles, which, when executed by a processor, implements the steps of the smart home control method based on user profiles as described in any one of claims 1-7.

Images