Smart home scene generation method and device, equipment and storage medium

Abstract

The embodiment of the invention provides a smart home scene generation method and device, equipment and a storage medium, and the method comprises the steps: obtaining text input information, and extracting key information from the text input information; at least one sub-scene is obtained through matching according to the key information; and combining the at least one sub-scene to obtain a smart home scene. Through the natural voice processing technology, the natural language text input by the user is analyzed, the smart home scene corresponding to the corresponding smart home control instruction is automatically generated, the operation process of the user is simplified, the creation process of the smart home scene is simplified, and the user experience is improved. The natural language requirement of the user can be quickly and accurately converted into the specific equipment control instruction, the intelligent degree is high, and the user experience is improved.

Description

Technical Field

[0001] The present invention relates to the field of device control technology, and in particular to a smart home scene generation method, a smart home scene generation device, a corresponding electronic device, and a corresponding computer-readable storage medium. Background Art

[0002] With the development of Internet of Things technology, smart home devices are becoming increasingly popular. In the related technologies of smart home systems, the states of multiple devices are usually controlled through a preset control instruction set. However, the above method requires users to manually set home scenes, which is complicated to operate and not intelligent enough. Summary of the invention

[0003] In view of the above problems, embodiments of the present invention are proposed to provide a smart home scene generation method, a smart home scene generation device, a corresponding electronic device and a corresponding computer-readable storage medium that overcome the above problems or at least partially solve the above problems.

[0004] An embodiment of the present invention discloses a method for generating a smart home scene, the method comprising:

[0005] Acquire text input information, and extract key information from the text input information;

[0006] Obtain at least one sub-scenario according to the key information matching;

[0007] The at least one sub-scene is combined to obtain a smart home scene.

[0008] In some embodiments of the present invention, extracting key information from the text input information includes:

[0009] Extract keywords from the text input information; or extract key features from the text input information.

[0010] In some embodiments of the present invention, the key information is used to indicate text features and / or weather features, and obtaining at least one sub-scenario according to the key information matching includes:

[0011] At least one sub-scene is obtained according to the text feature and / or weather feature matching.

[0012] In some embodiments of the present invention, the text feature is used to indicate a home scene mode, and the weather feature is used to indicate a weather execution mode; and obtaining at least one sub-scene according to the matching of the text feature and / or the weather feature includes:

[0013] According to the text features, at least one sub-scene in the target home scene mode is matched;

[0014] Alternatively, at least one sub-scenario in the target weather execution mode is matched according to the weather characteristics;

[0015] Alternatively, at least one sub-scene in the target weather execution mode and the target home scene mode is matched according to the text feature and the weather feature.

[0016] In some embodiments of the present invention, combining the at least one sub-scene to obtain a smart home scene includes:

[0017] Obtaining a priority of the at least one sub-scenario;

[0018] The at least one sub-scene is sorted according to the priority of the at least one sub-scene, and combined to obtain a smart home scene.

[0019] In some embodiments of the present invention, during the process of combining at least two sub-scenes, the method further includes:

[0020] If there is a first sub-scenario and a second sub-scenario with an execution conflict in at least two sub-scenarios, the first sub-scenario with a higher priority is used to cover the second sub-scenario with a lower priority.

[0021] In some embodiments of the present invention, the sub-scene is used to indicate a scene instruction, and after the smart home scene is obtained by combination, the following further includes:

[0022] Based on the smart home scene obtained by combining at least one scene instruction, a scene instruction set is generated.

[0023] In some embodiments of the present invention, the method further comprises:

[0024] If the scene instruction contained in the scene instruction set is verified to be valid, and the sub-scene corresponding to the scene instruction is successfully executed, the scene instruction set is stored; the scene instruction set is used for triggering by the user.

[0025] In some embodiments of the present invention, storing the scene instruction set further includes:

[0026] Presenting the smart home scene to the user;

[0027] In response to a user's confirmation instruction for the smart home scene, storing the scene instruction set;

[0028] And / or, in response to a user's instruction to modify the smart home scene, modify the scene instruction set.

[0029] The embodiment of the present invention further discloses a smart home scene generation device, the device comprising:

[0030] A key information extraction module, used to obtain text input information and extract key information from the text input information;

[0031] A scene matching module, used for matching and obtaining at least one sub-scene according to the key information;

[0032] The scene combination module is used to combine the at least one sub-scene to obtain a smart home scene.

[0033] In some embodiments of the present invention, the key information is used to indicate text features and / or weather features, and the scene matching module includes:

[0034] The scene matching submodule is used to obtain at least one sub-scene according to the text feature and / or weather feature matching.

[0035] In some embodiments of the present invention, the text feature is used to indicate a home scene mode, and the weather feature is used to indicate a weather execution mode; the scene matching submodule includes:

[0036] A scene matching unit is used to match at least one sub-scene in a target home scene mode according to the text feature; or, to match at least one sub-scene in a target weather execution mode according to the weather feature; or, to match at least one sub-scene in a target weather execution mode and a target home scene mode according to the text feature and the weather feature.

[0037] In some embodiments of the present invention, the scene combination module includes:

[0038] The scene combination submodule is used to obtain the priority of the at least one sub-scene; sort the at least one sub-scene according to the priority of the at least one sub-scene, and combine them to obtain a smart home scene.

[0039] In some embodiments of the present invention, in the process of combining at least two sub-scenes, the scene combination module further includes:

[0040] The scene covering submodule is used to use the first subscene with a higher priority to cover the second subscene with a lower priority when there is a first subscene and a second subscene with an execution conflict in at least two subscenes.

[0041] In some embodiments of the present invention, the sub-scene is used to indicate a scene instruction. After the smart home scene is obtained by combination, the device further includes:

[0042] The scene instruction generation module is used to generate a scene instruction set based on a smart home scene obtained by combining at least one scene instruction.

[0043] In some embodiments of the present invention, the device further comprises:

[0044] The scene instruction storage module is used to store the scene instruction set when the scene instruction contained in the scene instruction set is verified to be valid and the sub-scene corresponding to the scene instruction is successfully executed; the scene instruction set is used for triggering by the user.

[0045] In some embodiments of the present invention, the scene instruction storage module includes:

[0046] A scene instruction storage submodule, used for presenting the smart home scene to the user, responding to the user's confirmation instruction for the smart home scene, and storing the scene instruction set;

[0047] The scene instruction storage module also includes:

[0048] The scene instruction modification submodule is used to respond to the user's modification instruction for the smart home scene and modify the scene instruction set.

[0049] An embodiment of the present invention further discloses an electronic device, comprising: a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein when the computer program is executed by the processor, any one of the smart home scene generation methods is implemented.

[0050] An embodiment of the present invention further discloses a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, any one of the smart home scene generation methods is implemented.

[0051] The embodiments of the present invention include the following advantages:

[0052] In the embodiment of the present invention, by acquiring text input information, extracting key information from the text input information, and matching at least one sub-scene according to the key information, the at least one sub-scene obtained by the aforementioned matching is combined to obtain a smart home scene, thereby completing the creation of the smart home scene. Through natural speech processing technology, the natural language text input by the user is analyzed, and the corresponding smart home control instructions and corresponding smart home scenes are automatically generated, simplifying the user's operation process and simplifying the creation process of the smart home scene, so that the user's natural language needs can be quickly and accurately converted into specific device control instructions, with a high degree of intelligence, and improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 is a flowchart of a method for generating a smart home scene according to an embodiment of the present invention;

[0054] Figure 2is a schematic diagram of a framework of a smart home scene generation system based on text features provided by an embodiment of the present invention;

[0055] Figure 3 is a flowchart of another embodiment of a smart home scene generation method of the present invention;

[0056] Figure 4 It is a structural block diagram of an embodiment of a smart home scene generation device of the present invention. DETAILED DESCRIPTION

[0057] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0058] The embodiments of the present invention utilize natural language processing technology to simplify the creation and management of smart home scenarios by users.

[0059] Reference Figure 1 , shows a flowchart of a method for generating a smart home scene according to an embodiment of the present invention, which may specifically include the following steps:

[0060] Step S101, obtaining text input information, and extracting key information from the text input information;

[0061] Text input information refers to the natural language text input by the user. Optionally, the user can input natural language text based on mobile phone APP, voice assistant, etc.

[0062] In actual applications, users can input voice through mobile phone apps, voice assistants, etc., and the smart home scene generation system can perform voice recognition on the user's voice audio to obtain the natural language text input by the user. For example, the user's voice input is captured by a device such as a microphone of a mobile terminal, and then the voice signal can be converted into text through voice recognition technology, such as a deep learning model, to obtain text input information.

[0063] The user's text input information can reflect the user's intention.

[0064] Specifically, natural language processing may be performed to process the recognized text and understand the user's intention.

[0065] In order to accurately understand the user's intention, key information can be extracted from the preprocessed text input information. The extracted key information can be expressed as keywords or key features. The aforementioned keywords and key features can be used for matching subsequent sub-scenarios.

[0066] As an example, keywords can be extracted from the text input information by, for example, a dictionary tree technology, and the keywords matching the sub-scene can be pre-set, so that when the associated words extracted from the text input information have pre-associated sub-scenes, the sub-scene can be matched. Optionally, the keywords matching the sub-scene can be pre-set, for example, for the sleep mode, the keyword can be sleep, which can be mainly achieved by maintaining the addition, deletion, modification and query of the sub-scene, wherein the pre-set keywords are allowed to be changed, and this is not limited by the embodiments of the present invention.

[0067] As another example, key features can be extracted from text input information using, for example, a dictionary tree technology, so that the extracted key features can be subsequently analyzed using a pre-trained machine learning model or a deep learning model to obtain the matched sub-scenario.

[0068] Step S102, obtaining at least one sub-scenario according to key information matching;

[0069] A sub-scene may refer to multiple scenes used to combine to obtain a smart home scene. The number of sub-scenes may be at least one, that is, a combined scene may be a combination of multiple scenes or a combination of one scene.

[0070] As an example, when the extracted key information is a keyword, it can be directly based on the sub-scenario associated with the aforementioned keyword; as another example, when the extracted key information is a key feature, the extracted key features can be analyzed through a pre-trained machine learning model or a deep learning model to analyze and obtain the matched sub-scenario.

[0071] Specifically, whether it is a keyword or a key feature, it can include text features and / or weather features. The text features can be used to indicate the home scene mode, and the weather features can be used to indicate the weather execution mode. At this time, the home scene mode and the weather execution mode can be combined to achieve matching of sub-scenes.

[0072] Among them, the home scene mode can refer to a series of preset working states of smart home devices according to the user's living habits, time and activity needs. For example, the sub-scenes matched by the morning mode may include opening curtains, starting the coffee machine, adjusting the indoor temperature, etc.; the sub-scenes matched by the evening mode may include closing curtains, dimming lights, starting the security system, etc.; the sub-scenes matched by the home mode may include turning on the living room lights, raising the indoor temperature, playing music, etc. Based on different home scene modes, a more personalized and convenient living experience can be provided.

[0073] Weather execution mode refers to automatically adjusting the working status of smart home devices according to current or predicted weather conditions. These modes are usually combined with meteorological data, such as temperature, humidity, wind speed, rainfall, etc. For example, in hot summer, the system may automatically adjust the air conditioning temperature or start the fan; in cold winter, the system may start the heating or adjust the indoor humidity. Based on different weather execution modes, a more comfortable and energy-saving living environment can be provided.

[0074] It should be noted that different home scene modes may be executed in different weather execution modes. Combining the home scene mode and the weather execution mode, the system can intelligently adjust home appliances according to the user's daily habits and current weather conditions to match the sub-scenes. For example, in morning mode, if the weather forecast shows that it will rain today, the system can automatically turn off outdoor lighting and adjust indoor lighting and temperature to accommodate the user's waking up and daily activities. This intelligent combination can further enhance the user experience and efficiency of the smart home system.

[0075] In an embodiment of the present invention, at least one sub-scene may be obtained by matching text features and / or weather features.

[0076] In practical applications, in a smart home scene generation system, when matching sub-scenes based on text features and weather features, an inverted list or vector retrieval method can be used to perform efficient sub-scene matching.

[0077] As an example, the inverted list is a commonly used indexing technology, which is mainly used to quickly retrieve documents containing specific words. Optionally, in a smart home scene, the keywords of each sub-scene, such as morning, reading, cooling, etc., and weather characteristics, such as sunny, rainy, high temperature, etc., can be used as index items to construct an inverted list. When the user's text input information is obtained, the smart home scene generation system can quickly find the matching sub-scene by querying the inverted list.

[0078] As another example, vector retrieval is a retrieval method based on a vector space model that converts text and weather features into high-dimensional vectors, and then matches them by calculating the similarity between the vectors. Optionally, in a smart home scenario, word embedding (such as Word2Vec, BERT, etc.) can be used to convert text features into vectors, and weather features such as temperature and humidity can also be converted into vectors. The smart home scenario generation system can generate a query vector based on the user's input instructions and the current weather conditions, and then find the best matching sub-scenario by calculating the similarity between the query vector and the pre-stored sub-scenario vector.

[0079] It should be noted that the advantages of the inverted list are simple implementation, fast query speed, and suitable for scenarios with clear keywords; the advantage of vector search is that it can process semantic similarity and is suitable for scenarios that require understanding of complex semantics. In practical applications, a suitable method can be selected according to specific needs and characteristics of the scenario, or the two can be used in combination to achieve the best matching effect, which is not limited in the embodiments of the present invention.

[0080] Step S103: combine at least one sub-scene to obtain a smart home scene.

[0081] For at least one matched sub-scene, the at least one sub-scene can be combined to obtain a smart home scene. The sub-scene can be mainly used to indicate scene instructions, and the combined smart home scene can be expressed as a scene instruction set for the currently composed smart home scene, that is, a set of control instructions corresponding to the smart home scene, thereby automatically generating corresponding smart home control instructions to simplify the creation process of the smart home scene.

[0082] In the embodiment of the present invention, by acquiring text input information, extracting key information from the text input information, and matching at least one sub-scene according to the key information, the at least one sub-scene obtained by the aforementioned matching is combined to obtain a smart home scene, thereby completing the creation of the smart home scene. Through natural speech processing technology, the natural language text input by the user is analyzed, and the corresponding smart home control instructions and corresponding smart home scenes are automatically generated, simplifying the user's operation process and simplifying the creation process of the smart home scene, so that the user's natural language needs can be quickly and accurately converted into specific device control instructions, with a high degree of intelligence, and improving the user experience.

[0083] In some embodiments of the present invention, reference Figure 2 , showing a framework schematic diagram of a smart home scene generation system based on text features provided in an embodiment of the present invention.

[0084] like Figure 2 As shown, the smart home scene generation system 2 may include a text preprocessing unit 201, an intent recognition unit 202, a sub-scene matching unit 203, a sub-scene database 204, a sub-scene combination unit 205, an instruction generation unit 206, a scene verification unit 207 and a user feedback interface 208.

[0085] Among them, the text preprocessing unit 201 and the intention recognition unit 202 can be mainly used to perform natural language processing on the natural language text input by the user.

[0086] Optionally, the text preprocessing unit 201 can be used to perform preprocessing operations such as word segmentation, stop word removal, and part-of-speech tagging on the natural language text input by the user; the intention recognition unit 202 can be used to perform feature extraction, for example, it can extract key information from the preprocessed text through dictionary tree technology, mainly extracting keywords for sub-scene matching, and can also analyze the extracted key features through a pre-trained machine learning model or deep learning model.

[0087] The sub-scene matching unit 203 may be used to match sub-scenes according to text features and / or weather features, and may use an inverted list or vector search to perform sub-scene matching.

[0088] The sub-scenario database 204 can be used to implement maintenance of adding, deleting, modifying and searching sub-scenarios, so as to pre-set keywords matching sub-scenarios.

[0089] Optionally, the sub-scenario combination unit 205, the instruction generation unit 206, and the scene verification unit 207 can be mainly used to realize scene generation.

[0090] Among them, the sub-scene combination unit 205 can be used to combine at least one matched sub-scene to obtain a smart home scene; the instruction generation unit 206 can be used to generate a scene instruction set based on the smart home scene obtained by combining at least one scene instruction; the scene verification unit 207 can be used to verify the combined smart home scene, specifically, whether the scene instruction contained in the scene instruction set is valid, whether the sub-scene corresponding to the scene instruction can be executed, etc. When the smart home scene verification passes, the generated smart home scene can be stored by the scene storage unit for user triggering.

[0091] The user feedback interface 208 and the user input interface can be mainly used to implement user interaction. The user can input natural language text through the user input interface; the user feedback interface 208 can be used to display the generated smart home scene to the user and allow the user to modify and confirm.

[0092] Specifically, refer to Figure 3 , shows a flowchart of another smart home scene generation method embodiment of the present invention, which may specifically include the following steps:

[0093] Step S301, extracting key information from text input information, and obtaining at least one sub-scenario according to text features and / or weather features;

[0094] Text input information refers to the natural language text input by the user. Optionally, the user can input natural language text based on mobile phone APP, voice assistant, etc.

[0095] The text input information of the user can reflect the user's intention. Specifically, natural language processing can be performed to process the recognized text and understand the user's intention.

[0096] In order to accurately understand the user's intention, key information can be extracted from the preprocessed text input information. The extracted key information can be expressed as keywords or key features. The aforementioned keywords and key features can be used for matching subsequent sub-scenarios.

[0097] As an example, keywords can be extracted from the text input information by, for example, a dictionary tree technology, and the keywords matching the sub-scene can be pre-set, so that when the associated words extracted from the text input information have pre-associated sub-scenes, the sub-scene can be matched. Optionally, the keywords matching the sub-scene can be pre-set, for example, for the sleep mode, the keyword can be sleep, which can be mainly achieved by maintaining the addition, deletion, modification and query of the sub-scene, wherein the pre-set keywords are allowed to be changed, and this is not limited by the embodiments of the present invention.

[0098] As another example, key features can be extracted from text input information using, for example, a dictionary tree technology, so that the extracted key features can be subsequently analyzed using a pre-trained machine learning model or a deep learning model to obtain the matched sub-scenario.

[0099] A sub-scene may refer to multiple scenes used to combine to obtain a smart home scene. The number of sub-scenes may be at least one, that is, a combined scene may be a combination of multiple scenes or a combination of one scene.

[0100] As an example, when the extracted key information is a keyword, it can be directly based on the sub-scenario associated with the aforementioned keyword; as another example, when the extracted key information is a key feature, the extracted key features can be analyzed through a pre-trained machine learning model or a deep learning model to analyze and obtain the matched sub-scenario.

[0101] Specifically, whether it is a keyword or a key feature, it can include text features and / or weather features. The text features can be used to indicate the home scene mode, and the weather features can be used to indicate the weather execution mode. At this time, the home scene mode and the weather execution mode can be combined to achieve matching of sub-scenes.

[0102] Among them, the home scene mode can refer to a series of preset working states of smart home devices according to the user's living habits, time and activity needs. For example, the sub-scenes matched by the morning mode may include opening curtains, starting the coffee machine, adjusting the indoor temperature, etc.; the sub-scenes matched by the evening mode may include closing curtains, dimming lights, starting the security system, etc.; the sub-scenes matched by the home mode may include turning on the living room lights, raising the indoor temperature, playing music, etc. Based on different home scene modes, a more personalized and convenient living experience can be provided.

[0103] Weather execution mode refers to automatically adjusting the working status of smart home devices according to current or predicted weather conditions. These modes are usually combined with meteorological data, such as temperature, humidity, wind speed, rainfall, etc. For example, in hot summer, the system may automatically adjust the air conditioning temperature or start the fan; in cold winter, the system may start the heating or adjust the indoor humidity. Based on different weather execution modes, a more comfortable and energy-saving living environment can be provided.

[0104] In an embodiment of the present invention, at least one sub-scene may be obtained by matching text features and / or weather features.

[0105] In one case, at least one sub-scene in the target home scene mode can be matched based on the text features. In this case, the smart home scene generation system can match the corresponding sub-scene according to the preset home scene mode based on the text features in the keywords. For example, when the user says "I want to watch a movie", the smart home scene generation system can recognize the keyword "movie" and match it to the sub-scene in the movie mode, such as dimming the lights, closing the curtains, starting the projector, etc.

[0106] In another case, at least one sub-scene in the target weather execution mode can be matched according to the weather characteristics. In this case, the smart home scene generation system can obtain weather data in real time or regularly, such as temperature, humidity, wind speed, rainfall, etc., and match the sub-scene in the corresponding weather execution mode according to these data. For example, when the outdoor temperature drops sharply, the smart home scene generation system can automatically match the sub-scene in the warming mode, such as starting the heating, adjusting the indoor humidity, etc.

[0107] In another case, at least one sub-scene in the target weather execution mode and the target home scene mode can be matched based on the text features and weather features. In this case, the smart home scene generation system can consider the user's instructions and the current weather conditions at the same time to match more refined and personalized sub-scenes. For example, the user says "I want to drink tea on the balcony", and the weather forecast shows that it is sunny today. The smart home scene generation system can match the sub-scene in the balcony tea break mode, such as adjusting outdoor lighting, starting outdoor music playback, and adjusting the indoor temperature to adapt to outdoor activities. By combining text features and weather features, the smart home system can provide more detailed and intelligent services, not only taking into account the user's immediate needs, but also making corresponding adjustments according to changes in the external environment, thereby improving the user's living experience and quality of life.

[0108] In practical applications, in a smart home scene generation system, when matching sub-scenes based on text features and weather features, an inverted list or vector retrieval method can be used to perform efficient sub-scene matching.

[0109] As an example, the inverted list is a commonly used indexing technology, which is mainly used to quickly retrieve documents containing specific words. Optionally, in a smart home scene, the keywords of each sub-scene, such as morning, reading, cooling, etc., and weather characteristics, such as sunny, rainy, high temperature, etc., can be used as index items to construct an inverted list. When the user's text input information is obtained, the smart home scene generation system can quickly find the matching sub-scene by querying the inverted list.

[0110] As another example, vector retrieval is a retrieval method based on a vector space model that converts text and weather features into high-dimensional vectors, and then matches them by calculating the similarity between the vectors. Optionally, in a smart home scenario, word embedding (such as Word2Vec, BERT, etc.) can be used to convert text features into vectors, and weather features such as temperature and humidity can also be converted into vectors. The smart home scenario generation system can generate a query vector based on the user's input instructions and the current weather conditions, and then find the best matching sub-scenario by calculating the similarity between the query vector and the pre-stored sub-scenario vector.

[0111] In an embodiment of the present invention, the above-mentioned intention recognition and sub-scene matching process can be implemented based on the text preprocessing unit 201, the intention recognition unit 202, the sub-scene matching unit 203 and the sub-scene database 204 in the smart home scene generation system.

[0112] Step S302, combining at least one sub-scene to obtain a smart home scene;

[0113] For the at least one sub-scene obtained by matching, the at least one sub-scene can be combined to obtain a smart home scene.

[0114] Specifically, the combination of at least one sub-scene can be implemented according to the priority of at least one sub-scene, which can be specifically manifested as obtaining the priority of at least one sub-scene, and then sorting the at least one sub-scene according to the priority of at least one sub-scene, and then combining to obtain a smart home scene.

[0115] Optionally, the priority of the sub-scenario can be set according to factors such as the importance of the sub-scenario, the frequency of use of the device, the similarity (confidence) of the match, etc.

[0116] Among them, importance can be mainly manifested in that some sub-scenes may have a greater impact on the user experience and therefore have a higher priority. For example, in the waking mode, opening the curtains and starting the coffee machine may be more important than adjusting the indoor temperature; the frequency of device use can be mainly manifested in that frequently used devices or sub-scenes may be given a higher priority to ensure that user needs are met in a timely manner. For example, if a user uses a smart speaker to play music every day, then the priority of this sub-scene may be relatively high; the similarity (confidence) of matching can be mainly manifested in that the degree of understanding of user instructions or weather conditions by the smart home scene generation system will also affect the priority of the sub-scene. If the system recognizes a certain instruction very accurately, then the sub-scene related to the instruction may get a higher priority.

[0117] In actual operation, the system will first obtain the priority of each sub-scene, and then sort the sub-scenes according to these priorities. The sorted sub-scenes can be executed in order of priority to form a complete smart home scene. This priority-based combination method can ensure that the system can meet user needs while also taking into account the overall coordination and efficiency of the scene. In this way, the smart home scene generation system can respond to user instructions and changes in the external environment more intelligently, providing more personalized and efficient services.

[0118] In some embodiments of the present invention, during the process of combining at least two sub-scenes, if there are a first sub-scene and a second sub-scene in which the at least two sub-scenes have an execution conflict, Huakeyi uses the first sub-scene with a higher priority to cover the second sub-scene with a lower priority.

[0119] The number of the first sub-scene and the second sub-scene can be at least one. The first sub-scene and the second sub-scene with execution conflict may refer to contradictory instructions issued to the same device at the same time. For example, one sub-scene may require turning on the lights, while another sub-scene may require turning off the lights. In this case, the smart home scene generation system needs to have a mechanism to resolve such conflicts.

[0120] Exemplarily, the smart home scene generation system can first identify sub-scenes with execution conflicts, that is, sub-scenes that issue contradictory instructions to the same device at the same time, and then the smart home scene generation system can compare the priorities of these conflicting sub-scenes. The priorities can be set according to the above-mentioned volume factors (such as importance, frequency of use, matching similarity, etc.). At this time, the smart home scene generation system can select the sub-scene with the highest priority to execute, and ignore or cover other sub-scenes with lower priorities, ensuring that the final generated scene instruction set is reasonable and executable, so as to ensure that the behavior of the smart home scene generation system meets the user's highest priority requirements and avoids confusion and inconsistent operations. It should be noted that if there are multiple sub-scenes with lower priorities, the smart home scene generation system can ignore these sub-scenes together and only execute the sub-scene with the highest priority. This priority-based conflict resolution mechanism can ensure the stability and consistency of the smart home scene generation system when processing complex scenes. In this way, the smart home scene generation system can effectively manage the interaction between multiple sub-scenes, thereby providing more reliable and user-friendly services.

[0121] In the embodiment of the present invention, the above-mentioned sub-scene combination process can be implemented based on the sub-scene combination unit 205 in the smart home scene generation system.

[0122] Step S303, generating a scene instruction set based on the smart home scene obtained by combining at least one scene instruction;

[0123] In practical applications, the matched sub-scenarios can be combined according to priority sorting and conflict resolution results to generate a complete target scene. The generated complete target scene is the combined smart home scene.

[0124] Sub-scenes can be mainly used to indicate scene instructions. The combined smart home scene can be expressed as a scene instruction set for the currently composed smart home scene, that is, a set of control instructions corresponding to the smart home scene, thereby automatically generating corresponding smart home control instructions to simplify the creation process of the smart home scene. That is, a scene instruction set can be generated based on a smart home scene obtained by combining at least one scene instruction.

[0125] In an embodiment of the present invention, the above-mentioned instruction generation process can be implemented based on the instruction generation unit 206 in the smart home scene generation system.

[0126] Step S304: If the scene instruction contained in the scene instruction set is verified to be valid, and the sub-scene corresponding to the scene instruction is successfully executed, the scene instruction set is stored.

[0127] The scene instruction set can be used for triggering by the user, such as active triggering or passive triggering by the user.

[0128] After obtaining the scene instruction set, the smart home scene generation system can verify the combined smart home scene and the corresponding scene instruction set. Specifically, it can verify whether the scene instructions contained in the scene instruction set are valid, whether the sub-scenes corresponding to the scene instructions can be executed, etc.

[0129] Optionally, verifying the validity of scene instructions can be performed as a syntax check to ensure that each scene instruction is grammatically correct without spelling errors or formatting issues; it can also be performed as a semantic check to ensure that the semantics of each scene instruction is clear and the system can correctly understand the intention of the instruction; it can also be performed as a permission check to verify whether the user has the authority to execute certain specific scene instructions, especially when it comes to device operations involving security or privacy.

[0130] Optionally, verifying the executability of a sub-scenario can be performed as a device status check to confirm whether the relevant smart device is in an operational state, such as whether the device is online, whether it has sufficient power, etc.; it can also be performed as a device capability check to ensure that the device has the ability to execute corresponding instructions, for example, some devices may not support specific operations or modes.

[0131] Through the above verification steps, the smart home scene generation system can ensure that the generated scene instruction set is safe, effective and executable, thereby improving the user experience and reducing the risk of operation errors and equipment failures. This verification mechanism is an important guarantee for the reliability and stability of the smart home system.

[0132] When the scene instruction contained in the scene instruction set is verified to be valid and the sub-scene corresponding to the scene instruction is successfully executed, the scene instruction set can be stored for subsequent triggering by the user.

[0133] In some embodiments of the present invention, when the scene instruction set included in the scene instruction set is verified to be valid and the sub-scene corresponding to the scene instruction is successfully executed, the smart home scene can be presented to the user through the feedback interface, and the generated smart home scene can be displayed to the user to allow the user to modify and confirm. In an embodiment of the smart home scene generation system, once the scene instruction set is verified and the corresponding sub-scene is successfully executed, the smart home scene generation system can display the generated smart home scene to the user through the feedback interface to ensure that the user has a full understanding and control of the final generated scene.

[0134] In practical applications, the scene instruction set can be stored in response to the user's confirmation instruction for the smart home scene. For example, after the user confirms the scene, the smart home scene generation system can record the user's confirmation instruction and store the scene instruction set in the system for future reuse or call as needed.

[0135] Optionally, the scene instruction set can also be modified in response to the user's modification instructions for the smart home scene. Exemplarily, the user can view the displayed scene and modify it according to personal preferences or actual needs. Specifically, if the user chooses to modify the scene, the smart home scene generation system can adjust the scene instruction set according to the user's input. The modification may involve adding new instructions, deleting existing instructions, or changing the parameters of the instructions. The modified scene instruction set will be verified again to ensure that the modified scene is still valid and executable. Once the user confirms or the modified scene instruction set passes the verification, the smart home scene generation will store it in the database so that the user can easily call these scenes in the future.

[0136] It should be noted that the stored scene instruction set can be associated with specific trigger conditions (such as time, weather, user behavior, etc.) to achieve automatic execution. Through this user-involved feedback and confirmation mechanism, the smart home scene generation system can not only provide personalized services, but also ensure that users have ultimate control over the generated scenes. This interactive scene generation and management method greatly improves the user-friendliness and flexibility of the smart home system.

[0137] In an embodiment of the present invention, the above-mentioned smart home scene verification, modification and storage process can be implemented based on the scene verification unit 207 and the user feedback interface 208 in the smart home scene generation system.

[0138] In order to facilitate those skilled in the art to further understand the smart home scene generation method provided by the embodiment of the present invention, Figure 2The smart home scene generation system shown in the figure has a specific workflow as follows: 1) the user inputs natural language text to describe the desired smart home scene through the input interface; 2) the text preprocessing unit preprocesses the input text and extracts text features; 3) the intention recognition unit analyzes the text features and recognizes the user's intention; 4) the sub-scene matching unit matches the relevant sub-scenes from the preset sub-scene database according to the text features, wherein the sub-scene database can pre-store multiple commonly used smart home sub-scenes, each sub-scene can include a set of device control instructions, for example, the home mode may include sub-scenes such as turning on the living room lights, turning on the air conditioner, playing music, etc.; 5) the sub-scene combination unit combines the matched sub-scenes to generate a complete target scene; 6) the instruction generation unit can generate a specific device control instruction set based on the combined target scene, and verify it through the scene verification unit, and submit it to the user for confirmation after verification; 7) the user views the generated smart home scene through the feedback interface and confirms or modifies it.

[0139] For example, the user enters "I'm home" on the mobile phone APP, and the smart home scene generation system extracts the keyword "go home" through the natural language processing module. The intention recognition unit identifies it as "go home mode", and the sub-scene matching unit matches sub-scenes such as turning on the living room lights, raising the indoor temperature, and playing music from the database; the sub-scene combination unit combines these sub-scenes into a complete "go home mode" scene, and the instruction generation unit generates corresponding control instructions and verifies them, and submits them to the user for confirmation after the verification is passed. The scene takes effect after the user confirms.

[0140] For example, the user inputs "I want to go to bed" through the voice assistant, the smart home scene generation system extracts the keyword "sleep" through the natural language processing module, the intention recognition unit identifies it as "sleep mode", and the sub-scene matching unit matches sub-scenes such as turning off all lights, lowering the indoor temperature, and turning off the TV from the database; the sub-scene combination unit combines these sub-scenes into a complete "sleep mode" scene, the instruction generation unit generates corresponding control instructions and verifies them, and submits them to the user for confirmation after the verification is passed. The scene takes effect after the user confirms.

[0141] It should be noted that the smart home scene generation method provided in the embodiment of the present invention focuses on the generation of smart home scenes. The present invention does not limit the instruction triggering of the smart home scene and the specific triggering algorithm implemented therein.

[0142] In the embodiment of the present invention, by acquiring text input information, extracting key information from the text input information, and matching at least one sub-scene according to the key information, the at least one sub-scene obtained by the aforementioned matching is combined to obtain a smart home scene, thereby completing the creation of the smart home scene. Through natural speech processing technology, the natural language text input by the user is analyzed, and the corresponding smart home control instructions and corresponding smart home scenes are automatically generated, simplifying the user's operation process and simplifying the creation process of the smart home scene, so that the user's natural language needs can be quickly and accurately converted into specific device control instructions, with a high degree of intelligence, and improving the user experience.

[0143] It should be noted that, for the sake of simplicity, the method embodiments are described as a series of action combinations, but those skilled in the art should be aware that the embodiments of the present invention are not limited by the order of the actions described, because according to the embodiments of the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

[0144] Reference Figure 4 , shows a structural block diagram of an embodiment of a smart home scene generation device of the present invention, which may specifically include the following modules:

[0145] The key information extraction module 401 is used to obtain text input information and extract key information from the text input information;

[0146] A scene matching module 402, configured to obtain at least one sub-scene according to the key information;

[0147] The scene combination module 403 is used to combine the at least one sub-scene to obtain a smart home scene.

[0148] In some embodiments of the present invention, the key information extraction module 401 may include the following submodules:

[0149] The key information extraction submodule is used to extract keywords from the text input information; or to extract key features from the text input information.

[0150] In some embodiments of the present invention, the key information is used to indicate text features and / or weather features, and the scene matching module 402 may include the following submodules:

[0151] The scene matching submodule is used to obtain at least one sub-scene according to the text feature and / or weather feature matching.

[0152] In some embodiments of the present invention, the text feature is used to indicate a home scene mode, and the weather feature is used to indicate a weather execution mode; the scene matching submodule may include the following units:

[0153] A scene matching unit is used to match at least one sub-scene in a target home scene mode according to the text feature; or, to match at least one sub-scene in a target weather execution mode according to the weather feature; or, to match at least one sub-scene in a target weather execution mode and a target home scene mode according to the text feature and the weather feature.

[0154] In some embodiments of the present invention, the scene combination module 403 may include the following submodules:

[0155] The scene combination submodule is used to obtain the priority of the at least one sub-scene; sort the at least one sub-scene according to the priority of the at least one sub-scene, and combine them to obtain a smart home scene.

[0156] In some embodiments of the present invention, in the process of combining at least two sub-scenes, the scene combination module 403 may further include the following sub-modules:

[0157] The scene covering submodule is used to use the first subscene with a higher priority to cover the second subscene with a lower priority when there is a first subscene and a second subscene with an execution conflict in at least two subscenes.

[0158] In some embodiments of the present invention, the sub-scene is used to indicate a scene instruction. After the smart home scene is obtained by combination, the device provided by the embodiment of the present invention may further include the following modules:

[0159] The scene instruction generation module is used to generate a scene instruction set based on a smart home scene obtained by combining at least one scene instruction.

[0160] In some embodiments of the present invention, the apparatus provided by the embodiments of the present invention may further include the following modules:

[0161] The scene instruction storage module is used to store the scene instruction set when the scene instruction contained in the scene instruction set is verified to be valid and the sub-scene corresponding to the scene instruction is successfully executed; the scene instruction set is used for triggering by the user.

[0162] In some embodiments of the present invention, the scene instruction storage module may include the following submodules:

[0163] A scene instruction storage submodule, used for presenting the smart home scene to the user, responding to the user's confirmation instruction for the smart home scene, and storing the scene instruction set;

[0164] The scene instruction storage module may also include the following submodules:

[0165] The scene instruction modification submodule is used to respond to the user's modification instruction for the smart home scene and modify the scene instruction set.

[0166] In an embodiment of the present invention, the smart home scene generation device provided by the embodiment of the present invention obtains text input information, extracts key information from the text input information, and obtains at least one sub-scene according to the key information matching, and then combines the at least one sub-scene obtained by the aforementioned matching to obtain a smart home scene, thereby completing the creation of the smart home scene. Through natural speech processing technology, the natural language text input by the user is analyzed, and the corresponding smart home control instructions and corresponding smart home scenes are automatically generated, which simplifies the user's operation process and the creation process of the smart home scene, so that the user's natural language needs can be quickly and accurately converted into specific device control instructions, with a high degree of intelligence, and improves the user experience.

[0167] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0168] An embodiment of the present invention further provides an electronic device, including:

[0169] It includes a processor, a memory, and a computer program stored in the memory and capable of running on the processor. When the computer program is executed by the processor, the various processes of the above-mentioned smart home scene generation method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0170] An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the various processes of the above-mentioned smart home scene generation method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0171] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0172] It will be appreciated by those skilled in the art that the embodiments of the present invention may be provided as methods, devices, or computer program products. Therefore, the embodiments of the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the embodiments of the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0173] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0174] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0175] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0176] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention.

[0177] Finally, it should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0178] It should also be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0179] The above is a detailed introduction to a smart home scene generation method, a smart home scene generation device, a corresponding electronic device and a corresponding computer-readable storage medium provided by the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for general technical personnel in this field, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A method for generating a smart home scene, characterized in that: The method comprises: Acquire text input information, and extract key information from the text input information; Obtain at least one sub-scenario according to the key information matching; The at least one sub-scene is combined to obtain a smart home scene.

2. The method according to claim 1, characterized in that The extracting key information from the text input information includes: Extract keywords from the text input information; or extract key features from the text input information.

3. The method according to claim 1, characterized in that: The key information is used to indicate text features and / or weather features, and obtaining at least one sub-scenario according to the key information matching includes: At least one sub-scene is obtained according to the text feature and / or weather feature matching.

4. The method according to claim 3, characterized in that The text feature is used to indicate a home scene mode, and the weather feature is used to indicate a weather execution mode; and obtaining at least one sub-scene according to the matching of the text feature and / or the weather feature includes: According to the text feature, at least one sub-scene in the target home scene mode is matched; Alternatively, at least one sub-scenario in the target weather execution mode is matched according to the weather characteristics; Alternatively, at least one sub-scene in the target weather execution mode and the target home scene mode is matched according to the text feature and the weather feature.

5. The method according to claim 1, characterized in that The combining the at least one sub-scene to obtain a smart home scene includes: Obtaining a priority of the at least one sub-scenario; The at least one sub-scene is sorted according to the priority of the at least one sub-scene, and combined to obtain a smart home scene.

6. The method according to claim 5, characterized in that In the process of combining at least two sub-scenes, the method further includes: If there is a first sub-scenario and a second sub-scenario with an execution conflict in at least two sub-scenarios, the first sub-scenario with a higher priority is used to cover the second sub-scenario with a lower priority.

7. The method according to claim 5, characterized in that The sub-scene is used to indicate the scene instruction, and after the smart home scene is obtained by combination, it also includes: Based on the smart home scene obtained by combining at least one scene instruction, a scene instruction set is generated.

8. The method according to claim 7, characterized in that The method further comprises: If the scene instruction contained in the scene instruction set is verified to be valid, and the sub-scene corresponding to the scene instruction is successfully executed, the scene instruction set is stored; the scene instruction set is used for triggering by the user.

9. The method according to claim 8, characterized in that The storing of the scene instruction set further includes: Presenting the smart home scene to the user; In response to a user's confirmation instruction for the smart home scene, storing the scene instruction set; And / or, in response to a user's instruction to modify the smart home scene, modify the scene instruction set.

10. A smart home scene generation device, characterized in that: The device comprises: A key information extraction module, used to obtain text input information and extract key information from the text input information; A scene matching module, used for matching and obtaining at least one sub-scene according to the key information; The scene combination module is used to combine the at least one sub-scene to obtain a smart home scene.

11. An electronic device, characterized in that: include: A processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein when the computer program is executed by the processor, the smart home scene generation method as described in any one of claims 1 to 9 is implemented.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the smart home scene generation method as described in any one of claims 1 to 9 is implemented.

Images