Smart home interactive recommendation method and device, storage medium and electronic device

Abstract

The invention discloses a smart home interactive recommendation method and device, a storage medium and an electronic device, and the method comprises the steps: determining a recommendation statement content rule matched with a user interaction stage according to the current user interaction stage; based on the recommendation statement content rule, determining recommendation statement content according to preset user historical behavior data and preset multi-dimensional home context data; and outputting the recommended statement content to user interaction equipment according to the user interaction stage. According to the scheme of the embodiment of the invention, the interaction efficiency between the user and the smart home in the smart home environment can be improved.

Description

Technical Field

[0001] This application relates to the field of smart homes, and more specifically, to a smart home interactive recommendation method, device, storage medium, and electronic device. Background Technology

[0002] Smart homes are becoming increasingly popular, allowing users to control smart home appliances.

[0003] In existing smart home technologies, to facilitate user control of smart home appliances, applications are installed on terminal devices that can interact with the user, allowing the user to interact with the smart home through the application on the terminal device.

[0004] Most existing smart home systems receive user commands or inquiries, then execute those commands or respond accordingly. However, these systems generally lack the ability to proactively understand the user's underlying intentions. They passively respond only after the user explicitly issues a command, resulting in low user interaction efficiency and a weak sense of intelligence in the smart home environment. Summary of the Invention

[0005] This application provides a smart home interaction recommendation method, device, storage medium, and electronic device, with the aim of improving the interaction efficiency between users and smart homes in a smart home environment.

[0006] According to one aspect of the embodiments of this application, a smart home interaction recommendation method is provided, including: Based on the current user interaction stage, determine the recommended statement content rules that match the user interaction stage; Based on the recommended statement content rules, the recommended statement content is determined according to preset user historical behavior data and preset multi-dimensional home context data; Based on the user interaction stage, the recommended statement content is output to the user interaction device.

[0007] In an optional implementation, determining the recommended statement content rules matching the current user interaction stage includes: Acquire user interaction data to determine the user interaction stage; wherein, the user interaction stage includes a pre-dialogue stage and a dialogue stage; If the user interaction stage is the pre-dialogue stage, the natural language recommendation rule is determined to be the corresponding recommendation statement content rule. If the user interaction stage is the dialogue stage, the associated question recommendation rule is determined to be the corresponding recommendation statement content rule.

[0008] In an optional implementation, the step of outputting the recommended statement content to the user interaction device according to the user interaction stage includes: If the user interaction stage is the pre-dialogue stage, the corresponding user interaction device is searched in the preset user interaction device table as the target user interaction device; wherein, the preset user interaction device table includes the identifier and type of at least one user interaction device; Based on the type of the target user interaction device, the recommended statement content in the corresponding format is output to the target user interaction device.

[0009] In an optional implementation, after searching for the corresponding user interaction device in a preset user interaction device table as the target user interaction device, the method further includes: Determine the online status of the target user interaction device; The step of outputting the recommended statement content in a corresponding format to the target user interaction device according to the type of the target user interaction device includes: The recommended statement content in the corresponding format is output to the target user interaction device that is online.

[0010] In an optional implementation, before determining the recommended content rules matching the current user interaction stage, the method further includes: Collect preset user behavior data within a preset time range to construct the preset user historical behavior data; Context data from multiple preset dimensions is collected in real time to construct the preset multidimensional home context data.

[0011] In an optional implementation, determining the recommended statement content based on the recommended statement content rules, according to preset user historical behavior data and preset multi-dimensional home context data, includes: The intent prediction and recommendation generation engine is invoked. Based on the rules for the recommended statement content, the preset user historical behavior data and the preset multi-dimensional home context data are read together, and the recommended statement content is generated by the preset big model.

[0012] In an optional implementation, before the call intent prediction and recommendation generation engine generates the recommendation statement content based on the recommendation statement content rules and jointly read the preset user historical behavior data and the preset multi-dimensional home context data, the following method is further included: Based on the triggering conditions, recommendation type, recommendation statement template, and parameter binding logic, generate preset recommendation statement content rules; Multiple recommended statement content rules are constructed into a preset recommended statement content rule library.

[0013] According to another aspect of the embodiments of this application, a smart home interactive recommendation device is provided, comprising: The recommended statement content rule determination module is used to determine the recommended statement content rule that matches the current user interaction stage. The recommended statement content determination module is used to determine the recommended statement content based on the recommended statement content rules, according to preset user historical behavior data and preset multi-dimensional home context data; The recommended statement content output module is used to output the recommended statement content to the user interaction device according to the user interaction stage.

[0014] In an optional implementation, a statement content rule determination module is recommended, specifically used for: Acquire user interaction data to determine the user interaction stage; wherein, the user interaction stage includes a pre-dialogue stage and a dialogue stage; If the user interaction stage is the pre-dialogue stage, the natural language recommendation rule is determined to be the corresponding recommendation statement content rule. If the user interaction stage is the dialogue stage, the associated question recommendation rule is determined to be the corresponding recommendation statement content rule.

[0015] In an optional implementation, a statement content output module is recommended, specifically for: If the user interaction stage is the pre-dialogue stage, the corresponding user interaction device is searched in the preset user interaction device table as the target user interaction device; wherein, the preset user interaction device table includes the identifier and type of at least one user interaction device; Based on the type of the target user interaction device, the recommended statement content in the corresponding format is output to the target user interaction device.

[0016] In one optional implementation, the smart home interactive recommendation device further includes: The device online status determination module is used to determine the online status of the target user interaction device after searching for the corresponding user interaction device in the preset user interaction device table as the target user interaction device. The recommended statement content output module is specifically used for: The recommended statement content in the corresponding format is output to the target user interaction device that is online.

[0017] In one optional implementation, the smart home interactive recommendation device further includes: The user history behavior data construction module is used to collect preset user behavior data within a preset time range and construct the preset user history behavior data before determining the recommended statement content rules that match the current user interaction stage based on the current user interaction stage. The multidimensional home context data construction module is used to collect context data from multiple preset dimensions in real time and construct the preset multidimensional home context data.

[0018] In an optional implementation, the recommended statement content determination module is specifically used for: The intent prediction and recommendation generation engine is invoked. Based on the rules for the recommended statement content, the preset user historical behavior data and the preset multi-dimensional home context data are read together, and the recommended statement content is generated by the preset big model.

[0019] In one optional implementation, the smart home interactive recommendation device further includes: The recommendation statement content rule generation module is used to generate preset recommendation statement content rules based on triggering conditions, recommendation type, recommendation statement template and parameter binding logic before the call intent prediction and recommendation generation engine generates the recommendation statement content based on the recommendation statement content rules, the preset user historical behavior data and the preset multi-dimensional home context data. The recommended statement content rule base construction module is used to construct a preset recommended statement content rule base from multiple recommended statement content rules.

[0020] According to another aspect of the embodiments of this application, an electronic device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the smart home interaction recommendation method provided in any embodiment of the present invention through the computer program.

[0021] This application provides a smart home interaction recommendation method, device, storage medium, and electronic device. By matching corresponding recommendation statement content rules to different stages of user interaction, and using preset user historical behavior data and preset multi-dimensional home context data to determine the recommendation statement content, the method outputs the recommendation statement content to the user interaction device corresponding to the user interaction stage. This solves the problem that smart home systems cannot proactively predict user interaction needs in a smart home environment, resulting in low user interaction efficiency and weak intelligence. It achieves the provision of corresponding highly relevant recommendations at appropriate stages of user interaction, improving the interaction efficiency between users and smart home systems in a smart home environment. Attached Figure Description

[0022] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0023] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a schematic diagram of the hardware environment for a smart home interactive recommendation method according to an embodiment of this application; Figure 2 This is a flowchart of a smart home interactive recommendation method provided in an embodiment of this application; Figure 3A This is a schematic diagram illustrating the display of recommendation statements in a smart home interactive recommendation method provided in an embodiment of this application; Figure 3B This is a schematic diagram illustrating another method for displaying recommendation statements in a smart home interactive recommendation method provided in this application embodiment; Figure 4 This is a schematic diagram of the structure of a smart home interactive recommendation device provided in an embodiment of this application; Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0025] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0026] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0027] According to one aspect of the embodiments of this application, a smart home interaction recommendation method is provided. This smart home interaction recommendation method is widely applicable to whole-house intelligent digital control application scenarios such as smart homes, smart home ecosystems, smart home device ecosystems, and intelligence house ecosystems. Optionally, in this embodiment, the above-mentioned smart home interaction recommendation method can be applied to, for example... Figure 1 The hardware environment shown consists of terminal device 102 and server 104. For example... Figure 1 As shown, server 104 is connected to terminal device 102 via a network and can be used to provide services (such as application services) to the terminal or clients installed on the terminal. A database can be set up on the server or independently of the server to provide data storage services for server 104. Cloud computing and / or edge computing services can be configured on the server or independently of the server to provide data processing services for server 104.

[0028] The aforementioned network may include, but is not limited to, at least one of the following: wired network, wireless network. The aforementioned wired network may include, but is not limited to, at least one of the following: wide area network, metropolitan area network, local area network. The aforementioned wireless network may include, but is not limited to, at least one of the following: Wi-Fi (Wireless Fidelity), Bluetooth. The terminal device 102 may not be limited to PC, mobile phone, tablet computer, smart air conditioner, smart range hood, smart refrigerator, smart oven, smart stove, smart washing machine, smart water heater, smart washing equipment, smart dishwasher, smart projector, smart TV, smart clothes rack, smart curtains, smart audio-visual equipment, smart socket, smart speaker, smart speaker box, smart fresh air equipment, smart kitchen and bathroom equipment, smart bathroom equipment, smart robot vacuum cleaner, smart window cleaning robot, smart mopping robot, smart air purifier, smart steam oven, smart microwave oven, smart water heater, smart air purifier, smart water dispenser, smart door lock, etc.

[0029] Current smart home systems already support smart appliance status reporting, home environment data collection, basic automation rules (such as "turn on the lights if a home is detected"), and voice command recognition. With user authorization and consent, they can also obtain the attributes of the user's family members (such as the elderly and children) and room zoning, providing a preliminary data foundation for scenario-based services.

[0030] This embodiment provides a smart home interaction recommendation method, applicable to scenarios where users need to or are interacting with a smart home system in a home environment. Figure 2 A flowchart of a smart home interaction recommendation method provided in an embodiment of the present invention includes the following steps: Step 220: Determine the recommended statement content rules that match the current user interaction stage.

[0031] User interaction with smart home systems can take many forms. For example, users can express their intentions and needs through text and / or voice input on the interface of a smart home application installed on their device, and receive a response from the smart home system. This response can be in text, audio, image, video, or a combination of these formats, but text feedback is the most common. Smart home appliances with input and output devices that allow user interaction can also be interacted with, such as smart speakers with screens, smart TVs, and central control panels. The user interaction phase is divided based on the interaction nodes, primarily the point at which interaction begins. This phase includes the pre-dialogue stage (before the user asks a question or makes a request) and the in-dialogue stage (after the user has asked a question or made a request and the smart home system has responded). In the pre-dialogue stage, before the user asks a question or makes a request, existing smart home systems typically do not provide interactive content but wait for the user to initiate interaction. The solution in this application, regardless of whether the user and the smart home system are in the pre-interaction stage or in the interaction process, aims to achieve a leap from "passive response" to "active understanding" in the smart home system's interaction. It proactively predicts the user's potential intentions and generates natural language recommendations. However, the content of the response to the user differs significantly depending on the stage of the user interaction, especially before and after the dialogue begins. During the dialogue stage, because there is prior user interaction content, the smart home system needs to combine the preceding context of the user's interaction to recommend relevant statements. In the pre-dialogue stage, there is no preceding context, therefore, the recommended statements differ significantly across user interaction stages. Correspondingly, the rules for recommending statements also differ for different user interaction stages. It can be understood that the rules for recommending statements corresponding to a specific user interaction stage are a set of rules, which includes at least one rule for recommending statements.

[0032] Step 240: Based on the recommended statement content rules, determine the recommended statement content according to preset user historical behavior data and preset multi-dimensional home context data.

[0033] The preset user historical behavior data can be stored as user behavior data within a preset time period. This data can include user habits regarding smart home appliances (e.g., air conditioner preference for 25°C, frequent quick wash cycle on washing machine), regular operation times (e.g., turning off lights at 10 PM every night), linkage preferences (e.g., turning on lights and air conditioner upon returning home), and maintenance records (e.g., air conditioner filter cleaning cycle). This preset user historical behavior data can be persistently stored in the server's local storage as long-term memory. The preset multi-dimensional home context data can be multi-dimensional data related to home status, including real-time data affecting the operation of smart home appliances, such as real-time device status, environmental data, occupant presence information, and time events (including statutory holidays, local weather warnings, and the 24 solar terms). Home status-related data can include real-time device status (on / off, mode, fault, online status), instantaneous environmental data (temperature, humidity, PM2.5, light intensity, vibration), occupant presence information (determined by sensors or location services), time context (whether it is a statutory holiday, whether a high temperature / rainstorm warning has been issued, current solar term such as "Minor Heat" or "Autumn Begins"), and device lifecycle stage (new devices ≤3 days old / normal use / abnormal status). Preset multi-dimensional home context data can be cached and stored in the server's local cache as working memory. The recommended statement content rules combine preset user historical behavior data with preset multi-dimensional home context data, creating a collaborative mechanism between the two to proactively understand and accurately predict users' potential intentions.

[0034] Step 260: Based on the user interaction stage, output the recommended statement content to the user interaction device.

[0035] The user interaction device used to provide recommended content may vary depending on the stage of user interaction. In the dialogue stage, where the user is already interacting with the smart home system, the device used for the current interaction can be determined. For example, if the user expresses their needs through a user terminal, such as a smart home application on a smartphone, the user terminal is the user interaction device; if the user inputs voice commands through a smart speaker, the smart speaker is the user interaction device. In another implementation, pre-defined multi-dimensional home context data detects the user's location, allowing nearby smart appliances with input / output devices to be identified as user interaction devices. In the pre-dialogue stage, the online status of the user terminal and smart appliances can be obtained, combined with the user's location, to determine the user interaction device. Recommended cards are displayed at pre-dialogue touchpoints, including: the main interface of the smart home application or the top of the dialogue interface; the standby interface of devices such as smart speakers with screens, control panels, and smart TVs; the initial interface after the voice assistant is activated but has not yet received commands; dynamic guidance is provided at dialogue touchpoints, including: when the user's voice command is ambiguous (e.g., "wash clothes"), the system asks for more detailed options; after the user completes the operation, the system proactively provides supplementary suggestions.

[0036] Compared to existing technologies, some smart home systems push suggestion cards to users when specific conditions are met. For example, a single trigger condition is preset (such as "ambient temperature is above 30℃ and air conditioner is off"); after matching, a general prompt is generated (such as "It's hot, should we turn on the air conditioner?"); the user needs to click to jump to the control interface and manually complete the operation. This type of solution only makes judgments based on isolated state variables, without integrating multi-dimensional contextual data such as family members, device collaboration, and behavioral habits. It cannot deeply understand and proactively respond to the user's potential intentions in complex home scenarios (such as "the baby's room needs more conservative temperature control" or "the elderly need fall prevention lighting at night"). It cannot use the current state of the home (such as device operation, environmental parameters, family member presence, holidays / weather / solar terms, etc.) as real-time contextual data for instant reasoning; it cannot use the user's historical behavior (such as operating habits and preference parameters) as historical behavioral data for personalized prediction. Therefore, even when faced with rich scenarios (such as new device guidance, multi-device linkage, fault warning), the system can only passively wait for user commands and cannot proactively output recommendations that fit the context. This application provides a smart home interaction recommendation method that matches corresponding recommendation statement content rules according to different stages of user interaction. It determines the recommendation statement content using preset user historical behavior data and preset multi-dimensional home context data, and outputs the recommendation statement content to the user interaction device corresponding to the user interaction stage. This solves the problem that smart home systems cannot proactively predict user interaction needs in a smart home environment, resulting in low user interaction efficiency and weak intelligence. It achieves the provision of corresponding highly relevant recommendations at appropriate stages of user interaction, improving the interaction efficiency between users and smart home devices in a smart home environment.

[0037] In an optional implementation, determining the recommended statement content rules matching the current user interaction stage includes: The process involves acquiring user interaction data to determine the user interaction stage. This stage includes a pre-dialogue stage and a dialogue stage. User interaction data refers to the data generated when a user interacts with the smart home system's server via smart home appliances or a user terminal. This data includes the sender, the content sent, and a corresponding timestamp. The process determines whether a dialogue has begun based on whether there is any unreturned user content sent within a preset time period prior to the current time. If no new user content is sent within the preset time period, the user is considered to be in the pre-dialogue stage. If new user content is sent within the preset time period, the user is considered to be in the dialogue stage. The preset time period can be set as needed, for example, within a range of 1-30 seconds.

[0038] If the user interaction stage is the pre-dialogue stage, the natural language recommendation rule is determined as the corresponding recommendation statement content rule; wherein, in the pre-dialogue stage of this application embodiment, the natural language recommendation rule is a rule for determining the content of the recommendation statement using preset user historical behavior data and preset multi-dimensional home context data before the user raises a specific question or need, mainly a rule for predicting the user's needs. Figure 3A As shown, if the user does not raise any questions or requests, that is, if no content is sent by the user, some feasible operations or questions that the user may ask can be recommended.

[0039] If the user interaction stage is the dialogue stage, the associated question recommendation rule is determined to be the corresponding recommended statement content rule; wherein, in the dialogue stage of this application embodiment, since a previous user has sent content, and the user has raised questions or needs, the associated question recommendation rule is a rule that uses preset user historical behavior data and preset multi-dimensional home context data to respond to the content sent by the user, mainly a rule for predicting needs related to the content sent by the previous user. Figure 3B As shown, when a user requests "home appliance knowledge," the system recommends content that the user might want to know based on the content they send.

[0040] In an optional implementation, the step of outputting the recommended statement content to the user interaction device according to the user interaction stage includes: If the user interaction stage is the pre-dialogue stage, the corresponding user interaction device is searched in the preset user interaction device table as the target user interaction device. The preset user interaction device table includes the identifier and type of at least one user interaction device. Since this occurs before the dialogue begins, it is recommended that the anticipated content be displayed to the user using an appropriate user interaction device. This can be based on devices already registered under the user's account. The preset user interaction device table can record available interaction devices, such as user terminals, smart speakers with screens, central control panels, smart TVs, etc. The preset user interaction device table records the identifier (e.g., device ID) and type of the user interaction device. The type mainly indicates the interaction type of the device, i.e., what kind of input / output device it is. For example, a smart TV might be identified as TV01, and its type would be camera / microphone + speaker / display.

[0041] Based on the type of the target user interaction device, the recommended statement content in a corresponding format is output to the target user interaction device. Specifically, the recommended statement content is prepared in text, audio, or other formats according to the type of the target user interaction device.

[0042] In an optional implementation, after searching for the corresponding user interaction device in a preset user interaction device table as the target user interaction device, the method further includes: Determine the online status of the target user interaction device; wherein, if the smart home appliance is online, it will periodically report its status, and if the user terminal has logged in and opened the smart home application, it will also receive the reported status.

[0043] The step of outputting the recommended statement content in a corresponding format to the target user interaction device according to the type of the target user interaction device includes: The recommended statement content in a corresponding format is output to the target user interaction device that is online. The target user interaction device that is online can receive the recommended statement content in order to display it to the user.

[0044] In an optional implementation, before determining the recommended content rules matching the current user interaction stage, the method further includes: Collect preset user behavior data within a preset time range to construct the preset user historical behavior data; Context data from multiple preset dimensions is collected in real time to construct the preset multidimensional home context data.

[0045] This involves setting a time window, using the time range prior to the current time as a preset time range. As time progresses, older preset user behavior data is discarded, and new preset user behavior data is recorded. By recording the usage habits, operation patterns, linkage preferences, and maintenance records of smart home appliances, user habits can be determined. This preset user historical behavior data can be stored locally on the server. Real-time data collection includes device status, instantaneous environmental data, member presence information, time context, and device lifecycle stages. This real-time data is cached on the server and updated continuously over time.

[0046] In an optional implementation, determining the recommended statement content based on the recommended statement content rules, according to preset user historical behavior data and preset multi-dimensional home context data, includes: The intent prediction and recommendation generation engine is invoked. Based on the recommended statement content rules, and combined with the read preset user historical behavior data and preset multi-dimensional home context data, the recommended statement content is generated from a preset large model. The intent prediction and recommendation generation engine includes recommended statement content rules and a large model; the recommended statement content rules can be composed of conditions, types, templates, and parameter binding logic. The large model can be a natural language large model, outputting natural language recommendations to the user.

[0047] In an optional implementation, before the call intent prediction and recommendation generation engine generates the recommendation statement content based on the recommendation statement content rules and jointly read the preset user historical behavior data and the preset multi-dimensional home context data, the following method is further included: Based on the triggering conditions, recommendation type, recommendation statement template, and parameter binding logic, generate preset recommendation statement content rules; Multiple recommended statement content rules are constructed into a preset recommended statement content rule library.

[0048] For example, the preset recommended statement content rules can be: 1. Triggering conditions: Device type = air conditioner AND Room = baby room AND Real-time temperature > 27℃ AND Time period = 22:00-6:00 AND Family members include baby; 2. Recommendation type: Executable operation; 3. Recommended statement template: Set the air conditioner to {target temperature} degrees and turn on sleep mode; 4. Parameter binding logic: {target temperature} - "Good temperature for baby room air conditioner" in historical behavior (if not found, default 25); 5. Generate natural statement from large model: Set the air conditioner to 25 degrees and turn on sleep mode.

[0049] According to another aspect of the embodiments of this application, such as Figure 4 The diagram shown illustrates the structure of a smart home interactive recommendation device, which includes: The recommendation statement content rule determination module 420 is used to determine the recommendation statement content rule that matches the current user interaction stage based on the current user interaction stage. The recommended statement content determination module 440 is used to determine the recommended statement content based on the recommended statement content rules, according to preset user historical behavior data and preset multi-dimensional home context data; The recommended statement content output module 460 is used to output the recommended statement content to the user interaction device according to the user interaction stage.

[0050] In an optional implementation, a statement content rule determination module is recommended, specifically used for: Acquire user interaction data to determine the user interaction stage; wherein, the user interaction stage includes a pre-dialogue stage and a dialogue stage; If the user interaction stage is the pre-dialogue stage, the natural language recommendation rule is determined to be the corresponding recommendation statement content rule. If the user interaction stage is the dialogue stage, the associated question recommendation rule is determined to be the corresponding recommendation statement content rule.

[0051] In an optional implementation, a statement content output module is recommended, specifically for: If the user interaction stage is the pre-dialogue stage, the corresponding user interaction device is searched in the preset user interaction device table as the target user interaction device; wherein, the preset user interaction device table includes the identifier and type of at least one user interaction device; Based on the type of the target user interaction device, the recommended statement content in the corresponding format is output to the target user interaction device.

[0052] In one optional implementation, the smart home interactive recommendation device further includes: The device online status determination module is used to determine the online status of the target user interaction device after searching for the corresponding user interaction device in the preset user interaction device table as the target user interaction device. The recommended statement content output module is specifically used for: The recommended statement content in the corresponding format is output to the target user interaction device that is online.

[0053] In one optional implementation, the smart home interactive recommendation device further includes: The user history behavior data construction module is used to collect preset user behavior data within a preset time range and construct the preset user history behavior data before determining the recommended statement content rules that match the current user interaction stage based on the current user interaction stage. The multidimensional home context data construction module is used to collect context data from multiple preset dimensions in real time and construct the preset multidimensional home context data.

[0054] In an optional implementation, the recommended statement content determination module is specifically used for: The intent prediction and recommendation generation engine is invoked. Based on the rules for the recommended statement content, the preset user historical behavior data and the preset multi-dimensional home context data are read together, and the recommended statement content is generated by the preset big model.

[0055] In one optional implementation, the smart home interactive recommendation device further includes: The recommendation statement content rule generation module is used to generate preset recommendation statement content rules based on triggering conditions, recommendation type, recommendation statement template and parameter binding logic before the call intent prediction and recommendation generation engine generates the recommendation statement content based on the recommendation statement content rules, the preset user historical behavior data and the preset multi-dimensional home context data. The recommended statement content rule base construction module is used to construct a preset recommended statement content rule base from multiple recommended statement content rules.

[0056] According to another aspect of the embodiments of this application, an electronic device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the smart home interaction recommendation method provided in any embodiment of the present invention through the computer program.

[0057] According to another aspect of the embodiments of the present invention, Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present invention, such as... Figure 5 As shown, the electronic device includes a processor 510, a memory 520, an input device 530, and an output device 540; the number of processors 510 in the electronic device can be one or more. Figure 5 Taking a processor 510 as an example; the processor 510, memory 520, input device 530, and output device 540 in the electronic device can be connected via a bus or other means. Figure 5 Taking the example of a connection between China and Israel via a bus.

[0058] The memory 520, as a computer-readable storage medium, can be used to store software programs, computer-executable programs, and modules, such as the program instructions / modules corresponding to the voice interaction method in this embodiment of the invention (e.g., the feature acquisition module 410, the rejection judgment module 420, and the interaction response module 430 in the voice interaction device). The processor 510 executes various functional applications and data processing of the electronic device by running the software programs, instructions, and modules stored in the memory 520, thereby realizing the aforementioned smart home interaction recommendation method.

[0059] The memory 520 may primarily include a program storage area and a data storage area. The program storage area may store the operating system and at least one application program required for a given function; the data storage area may store data created based on terminal usage. Furthermore, the memory 520 may include high-speed random access memory and non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 520 may further include memory remotely located relative to the processor 510, which can be connected to the electronic device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0060] Input device 530 can be used to receive input digital or character information, and generate key signal inputs related to user settings and function control of the electronic device. It can also be a camera for acquiring images and a sound pickup device for acquiring audio data. Output device 540 may include display devices such as a screen, and audio devices such as a speaker. It should be noted that the specific composition of input device 530 and output device 540 can be set according to actual conditions. Processor 510 executes various functional applications and data processing of the electronic device by running software programs, instructions, and modules stored in memory 520.

[0061] According to another aspect of the present invention, the present invention also provides a computer-readable storage medium comprising a stored program, wherein the program, when executed, performs the following smart home interaction recommendation method: Based on the current user interaction stage, determine the recommended statement content rules that match the user interaction stage; Based on the recommended statement content rules, the recommended statement content is determined according to preset user historical behavior data and preset multi-dimensional home context data; Based on the user interaction stage, the recommended statement content is output to the user interaction device.

[0062] Of course, the computer-executable instructions provided in the embodiments of the present invention are not limited to the method operations described above, but can also perform related operations in the smart home interaction recommendation method provided in any embodiment of the present invention.

[0063] Based on the above description of the implementation methods, those skilled in the art can clearly understand that the present invention can be implemented using software and necessary general-purpose hardware, and of course, it can also be implemented using hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk, or optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0064] It is worth noting that in the embodiments of the above-mentioned smart home interactive recommendation device, the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of each functional unit are only for easy differentiation and are not used to limit the scope of protection of the present invention.

[0065] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A smart home interactive recommendation method, characterized in that, include: Based on the current user interaction stage, determine the recommended statement content rules that match the user interaction stage; Based on the recommended statement content rules, the recommended statement content is determined according to preset user historical behavior data and preset multi-dimensional home context data; Based on the user interaction stage, the recommended statement content is output to the user interaction device.

2. The smart home interactive recommendation method according to claim 1, characterized in that, The step of determining the recommended statement content rules that match the current user interaction stage includes: Acquire user interaction data to determine the user interaction stage; wherein, the user interaction stage includes a pre-dialogue stage and a dialogue stage; If the user interaction stage is the pre-dialogue stage, the natural language recommendation rule is determined to be the corresponding recommendation statement content rule. If the user interaction stage is the dialogue stage, the associated question recommendation rule is determined to be the corresponding recommendation statement content rule.

3. The smart home interactive recommendation method according to claim 2, characterized in that, The step of outputting the recommended statement content to the user interaction device according to the user interaction stage includes: If the user interaction stage is the pre-dialogue stage, the corresponding user interaction device is searched in the preset user interaction device table as the target user interaction device; wherein, the preset user interaction device table includes the identifier and type of at least one user interaction device; Based on the type of the target user interaction device, the recommended statement content in the corresponding format is output to the target user interaction device.

4. The smart home interactive recommendation method according to claim 3, characterized in that, After searching for the corresponding user interaction device in the preset user interaction device table as the target user interaction device, the method further includes: Determine the online status of the target user interaction device; The step of outputting the recommended statement content in a corresponding format to the target user interaction device according to the type of the target user interaction device includes: The recommended statement content in the corresponding format is output to the target user interaction device that is online.

5. The smart home interactive recommendation method according to claim 1, characterized in that, Before determining the recommended statement content rules matching the current user interaction stage, the method further includes: Collect preset user behavior data within a preset time range to construct the preset user historical behavior data; Context data from multiple preset dimensions is collected in real time to construct the preset multidimensional home context data.

6. The smart home interactive recommendation method according to claim 1 or 5, characterized in that, The step of determining the recommended statement content based on the recommended statement content rules, according to preset user historical behavior data and preset multi-dimensional home context data, includes: The intent prediction and recommendation generation engine is invoked. Based on the rules for the recommended statement content, the preset user historical behavior data and the preset multi-dimensional home context data are read together, and the recommended statement content is generated by the preset big model.

7. The smart home interactive recommendation method according to claim 6, characterized in that, Before the call intent prediction and recommendation generation engine generates the recommendation statement content based on the recommendation statement content rules and by jointly reading the preset user historical behavior data and the preset multi-dimensional home context data, the following steps are also included: Based on the triggering conditions, recommendation type, recommendation statement template, and parameter binding logic, generate preset recommendation statement content rules; Multiple recommended statement content rules are constructed into a preset recommended statement content rule library.

8. A smart home interactive recommendation device, characterized in that, include: The recommended statement content rule determination module is used to determine the recommended statement content rule that matches the current user interaction stage. The recommended statement content determination module is used to determine the recommended statement content based on the recommended statement content rules, and according to preset user historical behavior data and preset multi-dimensional home context data. The recommended statement content output module is used to output the recommended statement content to the user interaction device according to the user interaction stage.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein the program, when executed, performs the smart home interaction recommendation method according to any one of claims 1 to 7.

10. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to execute the smart home interaction recommendation method according to any one of claims 1 to 7 through the computer program.

Images