WO2017008322A1 - 基于社交网络行为感知的智能家庭能源管理方法 - Google Patents

基于社交网络行为感知的智能家庭能源管理方法 Download PDF

Info

Publication number
WO2017008322A1
WO2017008322A1 PCT/CN2015/084682 CN2015084682W WO2017008322A1 WO 2017008322 A1 WO2017008322 A1 WO 2017008322A1 CN 2015084682 W CN2015084682 W CN 2015084682W WO 2017008322 A1 WO2017008322 A1 WO 2017008322A1
Authority
WO
WIPO (PCT)
Prior art keywords
user
social
behavior
demand
network
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2015/084682
Other languages
English (en)
French (fr)
Inventor
刘烃
周亚东
陈思运
车煜林
苏曼
孙潇潇
管晓宏
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Xian Jiaotong University
Original Assignee
Xian Jiaotong University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Xian Jiaotong University filed Critical Xian Jiaotong University
Publication of WO2017008322A1 publication Critical patent/WO2017008322A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
    • G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B19/00—Program-control systems
    • G05B19/02—Program-control systems electric
    • G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B15/00—Systems controlled by a computer
    • G05B15/02—Systems controlled by a computer electric
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B2219/00—Program-control systems
    • G05B2219/20—Pc systems
    • G05B2219/26—Pc applications
    • G05B2219/2642—Domotique, domestic, home control, automation, smart house

Definitions

  • the invention relates to the field of smart home optimization control based on user behavior requirement perception, and particularly relates to a smart home energy management method based on social network behavior perception.
  • the optimized control of a personalized smart home depends on the user's behavior and demand perception. Accurate user behavior-aware results can lead to reliable demand-aware input for smart home optimization control. Reliable demand-aware input helps optimize the control system to customize the optimal control strategy that is more user-friendly. In the end, the smart home optimization control system can satisfy the user comfort to the greatest extent and help users save electricity.
  • User network social data analysis can be used to analyze the user's current activity behavior; user activity behavior analysis and processing results can be used to clarify user requirements; user demand acquisition combined with user family environment parameter data can be used for intelligent home optimization control, In the hope of maximizing user expectations.
  • the object of the present invention is to provide a smart home energy management method based on social network behavior perception to solve the above technical problem.
  • the invention acquires historical social data, generates socialized data base data through social data preprocessing, screening, classification, training and mapping; collects social network social data in real time, and uses the word segmentation rule rule base to perform user social behavior perception;
  • the environmental parameters are used to estimate the user's living environment requirements; according to the user's social behavioral perception results, it is determined whether the user needs need to be updated; if the user demand update is triggered, the smart home optimization scheduling algorithm is executed to generate a control strategy; and the smart home control module control strategy is updated.
  • a smart home energy management method based on social network behavior awareness includes the following steps:
  • user network social data and external environment data collection obtaining social social data of the user interacting with other people by using social software and mail management software on the mobile phone and the computer; and obtaining weather, traffic, and electricity price of the social networking related place of the user network information;
  • user network social behavior perception extracting key data in the acquired user network social data: event type, event location, event start time and termination time, event participants;
  • user environment demand estimation based on the user network social behavior and living environment demand rule base, estimating the user's demand for the environment according to the identified and predicted user social behavior and external environment data;
  • step S104 the user demand update judgment: comparing step S103) obtaining the latest estimated user environment requirement, whether there is a change compared with the basic set user environment requirement, thereby determining whether the user demand is updated; if no change occurs, Step S101) continuing to collect user network social data; if a change occurs, the existing user environment requirement is updated, and proceeds to step S105);
  • event-driven electrical equipment control strategy optimization generating events by detecting changes in user environment requirements; using event-driven online optimization methods, combined with external environmental data monitored in step S101), meeting the requirements of user environment requirements Under the constraints of electrical equipment and equipment, in order to save the entire household electricity consumption minimum, the joint operation control strategy of various equipments is generated;
  • step S106 the control policy of the smart home control module is updated according to the result of step S105), and proceeds to step S101) to continue monitoring the user network social data.
  • a further improvement of the present invention is that the user network social data in step S101) refers to information that the user uses social software and mail management software to interact with other people on the mobile phone and the computer, including the user's status announcement, comment, geographic location, and friend association. , mail interaction, one or more of the itinerary data.
  • a further improvement of the present invention is: in step S102), the social behavior of the user network includes five types of information: a category of the behavior, a predicted time of occurrence of the behavior, a predicted location where the behavior occurs, a person associated with the behavior, and a detailed description of the behavior;
  • the categories of social behavior of the user network include work, sports, parties, catering, meetings, shopping, eating, leisure, and going home social activities;
  • step S102 the process of identifying and predicting the user's social social behavior information is: constructing a user behavior feature database by using the user's historical social network data and behavior data, and adopting a semantic analysis method to obtain socialization according to the real-time monitored user network social data.
  • the information feature is based on a predefined library of user behavior characteristics, and the user's network social behavior is obtained through feature matching.
  • a further improvement of the present invention is: in step S102), the establishment of the user behavior feature database includes: first, for each social activity, analyzing the social network data of the corresponding history and filtering out the text and the image according to the type of the information. Secondly, for text information, using the method of word segmentation and pre-set rules, looking for features related to social activities as features of the social activities; third, for pictures, using a method of convolutional neural networks, Social activity related image social information is a feature of the social activity.
  • a further improvement of the present invention is: in step S103), the construction process of the user network social behavior and the living environment demand rule mapping library is: firstly, based on the experience of the historical statistical law, the original mapping relationship is established; in the use process, the estimated user is used. The social behavior and the actual operation of the user are associated, the original mapping relationship is updated, and the mapping rules of the personalized user network social behavior to the user's needs are gradually established.
  • a further improvement of the present invention is that when the user requirements obtained in step S104) are changed for the set basic user requirements, the existing user requirements are updated, and the update demand policy includes: comparing the latest user requirements with the current user requirements. If the demand periods do not overlap, the corresponding user requirements are increased; if the demand periods overlap, the current user requirements are replaced with the latest user requirements.
  • a further improvement of the present invention is: in step S105), the change of the user demand is taken as the event e, including the event detection time T d , the event type A, the user requirement R; wherein the event detection time T d refers to the time when the event is detected;
  • the event type A refers to the user social behavior description corresponding to the event;
  • a further improvement of the present invention is that the optimization problem in step S105) is aimed at minimizing the total electricity cost of the home appliance operation running in the optimized scheduling period, that is, Where t 0 represents the initial time of the optimization period, t d represents the end time of the optimization period, N is the number of scheduled electrical devices, p(k) represents the price of electricity at time k, and q i (k) represents the time of device i at time k The power is the decision variable.
  • a further improvement of the present invention is that the optimization problem in step S105) is driven by an event, the specific process is: when the event e is detected at the time T d , the user requirement R contained therein is read; and the length L of the time window is defined, at the T
  • the optimization problem is solved based on the user demand R during the period from d to T d +L; the obtained optimization strategy is used to control the electrical equipment until a new event is detected, and the drive optimization problem is recalculated to obtain a new strategy.
  • the present invention monitors and predicts the social behavior of the user network in real time by monitoring the user's network social software and mail management software, estimating and updating the user's demand for the home environment; using event-driven
  • the optimization method of electrical equipment control strategy according to the updated user living environment demand, environmental status and dynamic electricity price information, formulate the scheduling strategy of various types of electrical equipment of smart home, and actively control the household appliances equipment to meet the user's comfort to the home environment. Moderate requirements, while reducing the cost of electricity.
  • FIG. 1 is a block diagram of a smart home energy management method based on social network behavior awareness
  • Figure 2 is a block diagram of the analysis method of social network behavior.
  • FIG. 1 is a block diagram of a smart home energy management method based on social network behavior perception; and shows a basic framework of a smart home energy management method based on social network behavior perception.
  • Figure 2 is a block diagram of the analysis method of social network behavior; it shows the basic framework of the analysis method of social network behavior.
  • the invention provides a smart home energy management method based on social network behavior perception, comprising the following steps:
  • the user network social data defined by the present invention refers to information that the user interacts with other people by using social software and mail management software on the mobile phone and the computer, including the user's status announcement and comment.
  • One or more of the geographic location, friend association, email interaction, and itinerary data; this type of information is obtained in real time by monitoring one or more of the user's mobile phone and social software, mail management software and itinerary management software on the computer.
  • the external environment data defined by the present invention includes weather, traffic, and electricity price information of a place related to the social behavior of the user network, and is used to predict a user's comfortable target expected by the environment; such information is passed on the weather, traffic, and grid websites of the Internet. Proactively acquired and stored in an external environment database.
  • the user network social behavior defined by the present invention refers to various social activities agreed by the user after using the social application and software, the mail management application and the software on the mobile phone and the computer to communicate with other people. Extract key data in the acquired user network social data, including event type, event location, event start time and termination time, event participants, and identify and predict the user's network social behavior.
  • the user environment requirement defined by the present invention refers to the user's expectation of temperature, humidity, illuminance, hot water, diet in the environment in which the future is located, and the corresponding demand period.
  • the environment requirement rule base estimates the user's demand for the environment based on the identified and predicted user social behavior and external environment data.
  • step S104 the user demand update judgment: comparing step S103) obtaining the latest estimated user environment requirement, whether there is a change compared with the basic set user environment requirement, thereby determining whether the user demand is updated. If no change has occurred, the process proceeds to step S101) to continue collecting user network social data; if a change occurs, the existing user environment requirements are updated, and the process proceeds to step S105).
  • event-driven electrical equipment control strategy optimization refers to a change in the user's environmental requirements.
  • the event is generated by detecting changes in the user's environment requirements; the event-driven online optimization method is combined with the external environment data monitored in step S101) to meet the user's environmental requirements and under the constraints of the electrical equipment to save the entire household.
  • the minimum cost of electricity is the target, and a joint operation control strategy for various devices is generated.
  • step S106 the control policy of the smart home control module is updated according to the result of step S105), and proceeds to step S101) to continue monitoring the user network social data.
  • the network social data in step S101) of the present invention refers to social application and software including one or more kinds of social software such as Sina Weibo, Tencent Weibo, WeChat, Facebook, Twitter, etc.
  • the mail management application and software includes Outlook, Foxmail, etc. One or more of the mail clients.
  • the social behavior of the user network includes five types of information: a category of the behavior, a predicted time at which the behavior occurs, a predicted location where the behavior occurs, a person associated with the behavior, and a detailed description of the behavior.
  • the categories of social behavior of user networks include social activities such as work, sports, parties, catering, meetings, shopping, eating, leisure, and going home.
  • the process of identifying and predicting the social social behavior information of the user is: establishing a user behavior feature database by using historical social network data and behavior data of the user, and adopting semantic analysis according to the social data of the user network monitored in real time.
  • the method obtains the social information feature, and obtains the social social behavior of the user through feature matching based on the predefined user behavior feature database.
  • the establishment of the user behavior feature library includes: first, for each of the steps defined in step S102) A social activity that analyzes the social network data of its corresponding history and filters out text and images according to the type of information. Second, for text information, using word segmentation and pre-defined rules to find social activities. The feature is a feature of the social activity; thirdly, for the picture, using the method of convolutional neural network, image social information related to the social activity is obtained as a feature of the social activity.
  • the user network social behavior and the living environment demand rule mapping library are constructed by first establishing an original mapping relationship based on the experience of historical statistical rules; during the use process, the estimated user social behavior and the actual user's actual The operation is associated, the original mapping relationship is updated, and the mapping rules of personalized user network social behavior to user requirements are gradually established.
  • the update demand policy includes: comparing the latest user demand with the current user demand; If there is no overlap, the corresponding user requirements are increased; if the demand periods overlap, the current user requirements will be replaced with the latest user requirements.
  • the change of the user demand is taken as the event e, including the event detection time T d , the event type A, and the user requirement R.
  • the event detection time T d refers to the time when the event is detected;
  • the event type A refers to the user social behavior description corresponding to the event;
  • the optimization problem in the step S105) of the present invention is that the total electricity cost of the home appliance operation running in the optimized scheduling period is minimum, that is, Where t 0 represents the initial time of the optimization period, t d represents the end time of the optimization period, N is the number of scheduled electrical devices, p(k) represents the price of electricity at time k, and q i (k) represents the time of device i at time k
  • the power is the decision variable.
  • the optimization problem in step S105) of the present invention is driven by an event.
  • the specific process is: when the event e is detected at the time T d , the user demand R contained therein is read; and a time window length L is defined, at T d to T d +
  • the optimization problem is solved based on the user demand R during the time period of L; the obtained optimization strategy is used to control the electrical equipment until a new event is detected, and the drive optimization problem is recalculated to obtain a new strategy.
  • Scene 1 The user posts a text message on Sina Weibo at 11 am and plays with friends at 3 pm.
  • Step S101 The microblog data published by the user is detected and acquired at 11:00 am, and the external environment parameters of the location related to the user are read through the Internet.
  • Step S102 Analyze the social behavior of the user through the acquired social data.
  • the specific process is shown in Figure 2:
  • Step S201 Acquire real-time social network data
  • Step S202 determining that the acquired social network data category is text information, and jumping to S203;
  • Step S203 using a word segmentation and a preset rule method to obtain a feature with a greater degree of relevance to the corresponding social activity, such as a keyword describing the behavior, time, and location, and jumping to S205;
  • Step S205 matching the features obtained in step S203 with the social behavior feature database respectively, and obtaining the social behavior corresponding to the current social network data, that is, playing basketball at a certain stadium at 3 pm;
  • Step S206 Output the social behavior corresponding to the currently acquired social network data, and save the obtained feature in the social behavior feature database.
  • Step S103 Mapping the social behavior obtained in step S102 based on the external environment parameter and the living environment requirement rule base, and estimating the user's environmental demand and the corresponding demand period, for example, playing the game will delay the home time, and the corresponding air conditioning demand is 19: 00 ⁇ 24:00, the temperature is lower than normal demand.
  • Step S104 Comparing the latest estimated user living environment requirement, whether there is a change compared with the basic set user requirement, thereby determining whether the user demand is updated. If the newly estimated user demand in this scenario changes the user-defined time period and temperature set by the base, then the process proceeds to step S105 to drive the optimization process.
  • Step S105 the new user demand will trigger the optimization of the electrical device, execute the smart home optimization scheduling algorithm, and generate the control strategy;
  • Step S106 The control policy obtained based on the new user requirement will be used to control the home appliance, and at the same time, the process goes to step S101 to continue monitoring the user's social network data at the next moment.
  • Scenario 2 The user posts the picture information reflecting the playing process on Sina Weibo at 4 pm.
  • Step S101 At 4 o'clock in the afternoon, the microblog data published by the user is detected and acquired, and the external environment parameters of the location related to the user are read through the Internet.
  • Step S102 Analyze the social behavior of the user through the acquired social data.
  • the specific process is shown in Figure 2:
  • Step S201 Acquire real-time social network data
  • Step S202 determining that the acquired social network data category is picture information, and jumping to S204;
  • Step S204 using a convolutional neural network method to obtain a feature that is highly correlated with the corresponding social activity, and jump to S205;
  • Step S205 Matching the features obtained in step S204 with the social behavior feature database respectively, and obtaining the social behavior corresponding to the current social network data, that is, playing basketball at a certain stadium at 4 pm;
  • Step S206 output the social behavior corresponding to the currently acquired social network data, and save the obtained feature in In the social behavior feature library.
  • Step S103 Mapping the social behavior obtained in step S102 based on the external environment parameter and the living environment requirement rule base, and estimating the user's environmental demand and the corresponding demand period, for example, playing the game will delay the home time, and the corresponding air conditioning demand is 19: 00 ⁇ 24:00, the temperature is lower than normal demand.
  • Step S104 Comparing the latest estimated user living environment requirement, whether there is a change compared with the previously set user demand, thereby determining whether the user demand is updated. If the newly estimated user requirement in this scenario does not change the previously set user demand period and temperature, then the process proceeds to step S101 to continue monitoring the user's social network data at the next moment.

Landscapes

  • Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Quality & Reliability (AREA)
  • Manufacturing & Machinery (AREA)

Abstract

本发明公开了一种基于社交网络行为感知的智能家庭能源管理方法，包括：S101)、用户网络社交数据和外部环境数据采集；S102)、用户网络社交行为感知；S103)、用户环境需求估计；S104)、用户需求更新判断；S105)、事件驱动的电器设备控制策略优化；S106)、将智能家居控制模块的控制策略根据步骤S105)的结果进行更新，并转入步骤S101)继续监测用户网络社交数据。本发明通过监测用户的网络社交软件和邮件管理软件，实时识别和预测用户网络社交行为，估计和更新用户对家居环境的需求，制定智能家居各类电器设备的调度策略，并主动控制家用电器设备，满足用户对家居环境的舒适度要求，同时降低用电成本。

Description

基于社交网络行为感知的智能家庭能源管理方法 【技术领域】
本发明涉及基于用户行为需求感知的智能家居优化控制领域，特别涉及一种基于社交网络行为感知的智能家庭能源管理方法。
【背景技术】
个性化的智能家居的优化控制依赖于用户的行为和需求感知。精确的用户行为感知结果可以为智能家居的优化控制传入可靠的需求感知输入。可靠的需求感知输入有助于优化控制系统为用户定制更符合用户特性的优化控制策略；最终，可以使得智能家居优化控制系统最大程度上满足用户舒适度，帮助用户节省电费。用户的网络社交数据分析，可用于分析用户的当前活动行为；用户活动行为的分析与处理结果，可用于明确用户需求；用户需求的获取结合用户家庭中环境参数数据可用于智能家居的优化控制，以期最大程度符合用户期望。
传统的智能家居控制是统一的、单调的，对于具有不同行为和需求的用户，几乎采取同样的调度控制策略。但是，用户往往是个性化的，有自己独有的生活方式和家庭能源使用方式，统一的调度策略无法最大程度满足用户的舒适度和经济性期望。
【发明内容】
本发明的目的在于提供一种基于社交网络行为感知的智能家庭能源管理方法，以解决上述技术问题。本发明通过获取历史社交数据，通过社交数据预处理、筛选、分类、训练、映射生成分词语义场景规则库；实时采集用户网络社交数据，利用分词语义场景规则库进行用户社交行为感知；实时采集外部环境参数，进行用户生活环境需求估计；根据用户社交行为感知结果，判断是否需要更新用户需求；若触发了用户需求更新，执行智能家居优化调度算法，生成控制策略；更新智能家居控制模块控制策略。
为了实现上述目的，本发明采用如下技术方案：
基于社交网络行为感知的智能家庭能源管理方法，包括如下步骤：
S101)、用户网络社交数据和外部环境数据采集：获取用户在手机和电脑上利用社交软件、邮件管理软件与其他人交互的网络社交数据；并获取用户网络社交行为相关地点的天气、交通、电价信息；
S102)、用户网络社交行为感知：提取所获取用户网络社交数据中的关键数据：事件类型，事件地点，事件的起始时间和终止时间，事件参与人；
S103)、用户环境需求估计：基于用户网络社交行为与生活环境需求规则库，根据识别和预测的用户社交行为和外界环境数据，估计用户对环境的需求；
S104)、用户需求更新判断：对比步骤S103)获得最新估计的用户环境需求，与基础设定的用户环境需求相比是否有变化，由此判断用户需求是否会被更新；如果未发生变化，转入步骤S101)继续采集用户网络社交数据；如果发生变化，现有的用户环境需求被更新，并转入步骤S105)；
S105)、事件驱动的电器设备控制策略优化：通过检测用户环境需求发生的改变，生成事件；采用事件驱动的在线优化方法，结合步骤S101)中监测的外部环境数据，在满足用户环境需求的条件下和电器设备约束下，以节省整个家庭用电费用最小为目标，生成各种设备的联合运行控制策略；
S106)、将智能家居控制模块的控制策略根据步骤S105)的结果进行更新，并转入步骤S101)继续监测用户网络社交数据。
本发明进一步的改进在于：步骤S101)中用户网络社交数据指用户在手机和电脑上利用社交软件、邮件管理软件，与其他人交互的信息，包括用户的状态发表、评论、地理位置、好友关联、邮件交互、行程安排数据的一种或多种。
本发明进一步的改进在于：步骤S102)中，用户网络社交行为包括5类信息：行为的类别、行为发生的预测时间、行为发生的预测地点、与该行为相关的人和对行为的详细描述；其中用户网络社交行为的类别包括工作、运动、聚会、餐饮、会议、学习购物、吃饭、休闲、回家社交活动；
步骤S102)中，识别和预测用户的网络社交行为信息的流程为：利用用户的历史社交网络数据和行为数据建立用户行为特征库，根据实时监测到的用户网络社交数据，采用语义分析方法得到社交信息特征，基于预先定义的用户行为特征库，通过特征匹配得到用户的网络社交行为。
本发明进一步的改进在于：步骤S102)中，用户行为特征库的建立包括：第一，对于每一个社交活动，分析其对应的历史的社交网络数据并根据信息的类型筛选出文本以及图像两大类；第二，对于文本信息，利用分词和预先设定规则的方法，寻找与社交活动相关的特征作为该社交活动的特征；第三，对于图片，利用卷积神经网络的方法，得到与该社交活动相关的图像社交信息作为该社交活动的特征。
本发明进一步的改进在于：步骤S103)中，用户网络社交行为与生活环境需求规则映射库的构建过程为：首先基于历史统计规律的经验建立原始映射关系；在使用过程中，将估计得到的用户社交行为以及用户实际的操作进行关联，对原始映射关系进行更新，逐步建立个性化的用户网络社交行为到用户需求的映射规则。
本发明进一步的改进在于：步骤S104)中得到的用户需求对于设定的基础用户需求有改变时，则现有的用户需求被更新，更新需求策略包括：对比最新的用户需求与当前的用户需求；如果需求时段不重叠，则增加对应的用户需求；如果需求时段发生了重叠，将用最新的用户需求代替当前的用户需求。
本发明进一步的改进在于：步骤S105)中将用户需求的改变作为事件e，包含事件检测 时间Td，事件类型A，用户需求R；其中，事件检测时间Td指事件被检测到的时间；事件类型A指事件对应的用户社交行为描述；用户需求R是各个用户需求对应时间序列的集合，即R＝{rT(k),rH(k),rL(k),rW(k)}，其中rT(k),rH(k),rL(k),rW(k)分别表示k时刻用户的温度、湿度、照明和热水需求，定义当用户在k时刻没有需求时，对应的需求变量r(k)＝0。
本发明进一步的改进在于：步骤S105)中的优化问题目标为家庭电器运行在优化调度周期内运行的总电费最小，即
Figure PCTCN2015084682-appb-000001
其中t0表示优化时段的初始时刻，td表示优化时段的终止时刻，N为被调度的电器设备个数，p(k)表示k时刻的电价，qi(k)表示设备i在k时刻的功率，为决策变量。
本发明进一步的改进在于：步骤S105)中的优化问题模型包括：用电电器物理模型的状态方程xi(k+1)＝f(xi(k),ui(k),vi(k))，其中xi(k+1)和xi(k)分别表示设备i在k+1和k时刻的状态，ui(k)表示设备i在k时刻的控制参数，vi(k)表示设备i在k时刻的扰动；用电电器的物理约束，包括状态限制xmin≤xi(k)≤xmax和功率限制umin≤ui(k)≤umax；环境舒适需求，指在用户需求时段，电器设备的状态需满足用户需求，Rxi(k)-Δi≤xi(k)≤Rxi(k)+Δi，其中Rxi(k)表示用户在k时刻对设备i对应状态的环境需求，Δi指设备i对应状态的需求误差。
本发明进一步的改进在于：步骤S105)中优化问题由事件驱动，具体过程为：当Td时刻事件e被检测到，读取其中所包含的用户需求R；定义一个时间窗口长度L，在Td到Td+L的时段内基于用户需求R对优化问题进行求解；所得优化策略被用来控制电器设备，直到新的事件被检测到，驱动优化问题重新计算得到新的策略。
相对于现有技术，本发明具有以下有益效果：本发明通过监测用户的网络社交软件和邮件管理软件，实时识别和预测用户网络社交行为，估计和更新用户对家居环境的需求；采用事件驱动的电器设备控制策略优化方法，根据更新的用户生活环境需求、环境现状和动态电价信息，制定智能家居各类电器设备的调度策略，并主动控制家用电器设备，满足用户对家居环境的舒 适度要求，同时降低用电成本。
【附图说明】
图1为基于社交网络行为感知的智能家庭能源管理方法框图；
图2为社交网络行为的分析方法框图。
【具体实施方式】
请参阅图1及图2所示，图1为基于社交网络行为感知的智能家庭能源管理方法框图；显示了基于社交网络行为感知的智能家庭能源管理方法的基本框架。图2为社交网络行为的分析方法框图；显示了社交网络行为的分析方法的基本框架。
本发明一种基于社交网络行为感知的智能家庭能源管理方法，包括如下步骤：
S101)、用户网络社交数据和外部环境数据采集：本发明定义的用户网络社交数据指用户在手机和电脑上利用社交软件、邮件管理软件，与其他人交互的信息，包括用户的状态发表、评论、地理位置、好友关联、邮件交互、行程安排数据的一种或多种；该类信息通过监测用户手机和电脑上的社交软件、邮件管理软件和行程管理软件等一种或多种实现实时获取。本发明定义的外部环境数据包括与用户网络社交行为相关地点的天气、交通、电价信息，用于预测用户对所处环境期望的舒适目标；该类信息通过在互联网的天气、交通、电网网站上主动获取，并存储在外部环境数据库中。
S102)、用户网络社交行为感知：本发明定义的用户网络社交行为指用户通过手机和电脑上利用社交应用与软件、邮件管理应用与软件，与其他人交流后约定的各种社交活动。提取所获取用户网络社交数据中的关键数据，包括事件类型，事件地点，事件的起始时间和终止时间，事件参与人，识别和预测用户的网络社交行为。
S103)、用户环境需求估计：本发明定义的用户环境需求指用户对未来所处环境中温度、湿度、照度、热水、饮食的期望，及其分别对应的需求时段。基于用户网络社交行为与生活环 境需求规则库，根据识别和预测的用户社交行为和外界环境数据，估计用户对环境的需求。
S104)、用户需求更新判断：对比步骤S103)获得最新估计的用户环境需求，与基础设定的用户环境需求相比是否有变化，由此判断用户需求是否会被更新。如果未发生变化，转入步骤S101)继续采集用户网络社交数据；如果发生变化，现有的用户环境需求被更新，并转入步骤S105)。
S105)、事件驱动的电器设备控制策略优化：本发明定义的事件指用户环境需求发生的改变。通过检测用户环境需求发生的改变，生成事件；采用事件驱动的在线优化方法，结合步骤S101)中监测的外部环境数据，在满足用户环境需求的条件下和电器设备约束下，以节省整个家庭用电费用最小为目标，生成各种设备的联合运行控制策略。
S106)、将智能家居控制模块的控制策略根据步骤S105)的结果进行更新，并转入步骤S101)继续监测用户网络社交数据。
本发明步骤S101)中的网络社交数据指社交应用与软件包括新浪微博、腾讯微博、微信、Facebook、Twitter等社交类软件的一种或多种，邮件管理应用与软件包括Outlook、Foxmail等邮件客户端的一种或多种。
本发明步骤S102)中，用户网络社交行为包括5类信息：行为的类别、行为发生的预测时间、行为发生的预测地点、与该行为相关的人和对行为的详细描述。其中用户网络社交行为的类别包括工作、运动、聚会、餐饮、会议、学习购物、吃饭、休闲、回家等社交活动。
本发明步骤S102)中，识别和预测用户的网络社交行为信息的流程为：利用用户的历史社交网络数据和行为数据建立用户行为特征库，根据实时监测到的用户网络社交数据，采用语义分析等方法得到社交信息特征，基于预先定义的用户行为特征库，通过特征匹配得到用户的网络社交行为。
本发明步骤S102)中，用户行为特征库的建立包括：第一，对于步骤S102)所定义的每 一个社交活动，分析其对应的历史的社交网络数据并根据信息的类型筛选出文本以及图像两大类；第二，对于文本信息，利用分词和预先设定规则的方法，寻找与社交活动相关的特征作为该社交活动的特征；第三，对于图片，利用卷积神经网络的方法，得到与该社交活动相关的图像社交信息作为该社交活动的特征。
本发明步骤S103)中用户网络社交行为与生活环境需求规则映射库的构建过程为：首先基于历史统计规律的经验建立原始映射关系；在使用过程中，将估计得到的用户社交行为以及用户实际的操作进行关联，对原始映射关系进行更新，逐步建立个性化的用户网络社交行为到用户需求的映射规则。
本发明步骤S104)中得到的用户需求对于设定的基础用户需求有改变时，则现有的用户需求会被更新，更新需求策略包括：对比最新的用户需求与当前的用户需求；如果需求时段不重叠，则增加对应的用户需求；如果需求时段发生了重叠，将用最新的用户需求代替当前的用户需求。
本发明步骤S105)中将用户需求的改变作为事件e，包含事件检测时间Td，事件类型A，用户需求R。其中，事件检测时间Td指事件被检测到的时间；事件类型A指事件对应的用户社交行为描述；用户需求R是各个用户需求对应时间序列的集合，即R＝{rT(k),rH(k),rL(k),rW(k)}，其中rT(k),rH(k),rL(k),rW(k)分别表示k时刻用户的温度、湿度、照明和热水需求，定义当用户在k时刻没有需求时，对应的需求变量r(k)＝0。
本发明步骤S105)中的优化问题目标为家庭电器运行在优化调度周期内运行的总电费最小，即
Figure PCTCN2015084682-appb-000002
其中t0表示优化时段的初始时刻，td表示优化时段的终止时刻，N为被调度的电器设备个数，p(k)表示k时刻的电价，qi(k)表示设备i在k时刻的功率，为决策变量。
本发明步骤S105)中的优化问题模型包括：用电电器物理模型的状态方程 xi(k+1)＝f(xi(k),ui(k),vi(k))，其中xi(k+1)和xi(k)分别表示设备i在k+1和k时刻的状态，ui(k)表示设备i在k时刻的控制参数，vi(k)表示设备i在k时刻的扰动；用电电器的物理约束，包括状态限制xmin≤xi(k)≤xmax(例如空调、热水器温度的限制；风机转速的限制等状态限制)和功率限制umin≤ui(k)≤umax；环境舒适需求，指在用户需求时段，电器设备的状态需满足用户需求，Rxi(k)-Δi≤xi(k)≤Rxi(k)+Δi，其中Rxi(k)表示用户在k时刻对设备i对应状态的环境需求，Δi指设备i对应状态的需求误差。
本发明步骤S105)中优化问题由事件驱动，具体过程为：当Td时刻事件e被检测到，读取其中所包含的用户需求R；定义一个时间窗口长度L，在Td到Td+L的时段内基于用户需求R对优化问题进行求解；所得优化策略被用来控制电器设备，直到新的事件被检测到，驱动优化问题重新计算得到新的策略。
场景1：用户在上午11点在新浪微博上发布文字信息，与朋友相约下午3点打球。
步骤S101：上午11点检测并获取到用户发布的微博数据，同时通过互联网读取与用户相关地点的外部环境参数。
步骤S102：通过获取的社交数据分析用户的社交行为。具体流程如图2所示：
步骤S201：获取实时社交网络数据；
步骤S202：判断获取的社交网络数据类别为文本信息，跳转至S203；
步骤S203：利用分词和预先设定规则的方法得到与对应社交活动相关度较大的特征，例如描述行为、时间、地点的关键词，跳转至S205；
步骤S205：将步骤S203中所得到的特征分别与社交行为特征库进行匹配，得到当前的社交网络数据对应的社交行为，即为下午3点在某体育场打篮球；
步骤S206：输出当前获取的社交网络数据所对应的社交行为，并将所得到的特征保存在社交行为特征库中。
步骤S103：将步骤S102中得到的社交行为基于外部环境参数和生活环境需求规则库进行映射，估计用户的环境需求及其对应的需求时段，例如打球会推迟到家时间，对应的空调需求为19:00～24:00，温度比正常的需求偏低等。
步骤S104：对比最新估计的用户生活环境需求，与基础设定的用户需求相比是否有变化，由此判断用户需求是否会被更新。此场景中新估计的用户需求改变了基础设定的用户需求时段及温度，则跳换至步骤S105，驱动优化过程。
步骤S105：新的用户需求将会触发电器设备的优化，执行智能家居优化调度算法，生成控制策略；
步骤S106：基于新的用户需求所得到的控制策略将会用来对家电设备进行控制，同时跳转至步骤S101，继续下一时刻对用户社交网络数据的监测。
由此，完成了对于场景1的基于社交网络行为感知的智能家庭能源管理过程。
场景2：用户在下午4点在新浪微博上发布反映打球过程的图片信息。
步骤S101：下午4点检测并获取到用户发布的微博数据，同时通过互联网读取与用户相关地点的外部环境参数。
步骤S102：通过获取的社交数据分析用户的社交行为。具体流程如图2所示：
步骤S201：获取实时社交网络数据；
步骤S202：判断获取的社交网络数据类别为图片信息，跳转至S204；
步骤S204：利用卷积神经网络的方法得到与对应社交活动相关度较大的特征，跳转至S205；
步骤S205：将步骤S204中所得到的特征分别与社交行为特征库进行匹配，得到当前的社交网络数据对应的社交行为，即为下午4点在某体育场打篮球；
步骤S206：输出当前获取的社交网络数据所对应的社交行为，并将所得到的特征保存在 社交行为特征库中。
步骤S103：将步骤S102中得到的社交行为基于外部环境参数和生活环境需求规则库进行映射，估计用户的环境需求及其对应的需求时段，例如打球会推迟到家时间，对应的空调需求为19:00～24:00，温度比正常的需求偏低等。
步骤S104：对比最新估计的用户生活环境需求，与之前设定的用户需求相比是否有变化，由此判断用户需求是否会被更新。此场景中新估计的用户需求没有改变之前设定的用户需求时段及温度，则跳换至步骤S101，继续下一时刻对用户社交网络数据的监测。
由此，完成了对于场景2的基于社交网络行为感知的智能家庭能源管理过程。

Claims (10)

  1. 基于社交网络行为感知的智能家庭能源管理方法，其特征在于，包括如下步骤：
    S101)、用户网络社交数据和外部环境数据采集：获取用户在手机和电脑上利用社交软件、邮件管理软件与其他人交互的网络社交数据；并获取用户网络社交行为相关地点的天气、交通、电价信息；
    S102)、用户网络社交行为感知：提取所获取用户网络社交数据中的关键数据：事件类型，事件地点，事件的起始时间和终止时间，事件参与人；
    S103)、用户环境需求估计：基于用户网络社交行为与生活环境需求规则库，根据识别和预测的用户社交行为和外界环境数据，估计用户对环境的需求；
    S104)、用户需求更新判断：对比步骤S103)获得最新估计的用户环境需求，与基础设定的用户环境需求相比是否有变化，由此判断用户需求是否会被更新；如果未发生变化，转入步骤S101)继续采集用户网络社交数据；如果发生变化，现有的用户环境需求被更新，并转入步骤S105)；
    S105)、事件驱动的电器设备控制策略优化：通过检测用户环境需求发生的改变，生成事件；采用事件驱动的在线优化方法，结合步骤S101)中监测的外部环境数据，在满足用户环境需求的条件下和电器设备约束下，以节省整个家庭用电费用最小为目标，生成各种设备的联合运行控制策略；
    S106)、将智能家居控制模块的控制策略根据步骤S105)的结果进行更新，并转入步骤S101)继续监测用户网络社交数据。
  2. 根据权利要求1所述的基于社交网络行为感知的智能家庭能源管理方法，其特征在于，步骤S101)中用户网络社交数据指用户在手机和电脑上利用社交软件、邮件管理软件，与其他人交互的信息，包括用户的状态发表、评论、地理位置、好友关联、邮件交互、行程安排数据的一种或多种。
  3. 根据权利要求1所述的基于社交网络行为感知的智能家庭能源管理方法，其特征在于，步骤S102)中，用户网络社交行为包括5类信息：行为的类别、行为发生的预测时间、行为发生的预测地点、与该行为相关的人和对行为的详细描述；其中用户网络社交行为的类别包括工作、运动、聚会、餐饮、会议、学习购物、吃饭、休闲、回家社交活动；
    步骤S102)中，识别和预测用户的网络社交行为信息的流程为：利用用户的历史社交网络数据和行为数据建立用户行为特征库，根据实时监测到的用户网络社交数据，采用语义分析方法得到社交信息特征，基于预先定义的用户行为特征库，通过特征匹配得到用户的网络社交行为。
  4. 根据权利要求3所述的基于社交网络行为感知的智能家庭能源管理方法，其特征在于，步骤S102)中，用户行为特征库的建立包括：第一，对于每一个社交活动，分析其对应的历史的社交网络数据并根据信息的类型筛选出文本以及图像两大类；第二，对于文本信息，利用分词和预先设定规则的方法，寻找与社交活动相关的特征作为该社交活动的特征；第三，对于图片，利用卷积神经网络的方法，得到与该社交活动相关的图像社交信息作为该社交活动的特征。
  5. 根据权利要求1所述的基于社交网络行为感知的智能家庭能源管理方法，其特征在于，步骤S103)中，用户网络社交行为与生活环境需求规则映射库的构建过程为：首先基于历史统计规律的经验建立原始映射关系；在使用过程中，将估计得到的用户社交行为以及用户实际的操作进行关联，对原始映射关系进行更新，逐步建立个性化的用户网络社交行为到用户需求的映射规则。
  6. 根据权利要求1所述的基于社交网络行为感知的智能家庭能源管理方法，其特征在于，步骤S104)中得到的用户需求对于设定的基础用户需求有改变时，则现有的用户需求被更新，更新需求策略包括：对比最新的用户需求与当前的用户需求；如果需求时段不重叠，则增加对 应的用户需求；如果需求时段发生了重叠，将用最新的用户需求代替当前的用户需求。
  7. 根据权利要求1所述的基于社交网络行为感知的智能家庭能源管理方法，其特征在于，步骤S105)中将用户需求的改变作为事件e，包含事件检测时间Td，事件类型A，用户需求R；其中，事件检测时间Td指事件被检测到的时间；事件类型A指事件对应的用户社交行为描述；用户需求R是各个用户需求对应时间序列的集合，即R＝{rT(k),rH(k),rL(k),rW(k)}，其中rT(k),rH(k),rL(k),rW(k)分别表示k时刻用户的温度、湿度、照明和热水需求，定义当用户在k时刻没有需求时，对应的需求变量r(k)＝0。
  8. 根据权利要求7所述的基于社交网络行为感知的智能家庭能源管理方法，其特征在于，步骤S105)中的优化问题目标为家庭电器运行在优化调度周期内运行的总电费最小，即
    Figure PCTCN2015084682-appb-100001
    其中t0表示优化时段的初始时刻，td表示优化时段的终止时刻，N为被调度的电器设备个数，p(k)表示k时刻的电价，qi(k)表示设备i在k时刻的功率，为决策变量。
  9. 根据权利要求8所述的基于社交网络行为感知的智能家庭能源管理方法，其特征在于，步骤S105)中的优化问题模型包括：用电电器物理模型的状态方程xi(k+1)＝f(xi(k),ui(k),vi(k))，其中xi(k+1)和xi(k)分别表示设备i在k+1和k时刻的状态，ui(k)表示设备i在k时刻的控制参数，vi(k)表示设备i在k时刻的扰动；用电电器的物理约束，包括状态限制xmin≤xi(k)≤xmax和功率限制umin≤ui(k)≤umax；环境舒适需求，指在用户需求时段，电器设备的状态需满足用户需求，Rxi(k)-Δi≤xi(k)≤Rxi(k)+Δi，其中Rxi(k)表示用户在k时刻对设备i对应状态的环境需求，Δi指设备i对应状态的需求误差。
  10. 根据权利要求9所述的基于社交网络行为感知的智能家庭能源管理方法，其特征在于，步骤S105)中优化问题由事件驱动，具体过程为：当Td时刻事件e被检测到，读取其中所包含的用户需求R；定义一个时间窗口长度L，在Td到Td+L的时段内基于用户需求R对优 化问题进行求解；所得优化策略被用来控制电器设备，直到新的事件被检测到，驱动优化问题重新计算得到新的策略。
PCT/CN2015/084682 2015-07-10 2015-07-21 基于社交网络行为感知的智能家庭能源管理方法 Ceased WO2017008322A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201510405149.2 2015-07-10
CN201510405149.2A CN105068513B (zh) 2015-07-10 2015-07-10 基于社交网络行为感知的智能家庭能源管理方法

Publications (1)

Publication Number Publication Date
WO2017008322A1 true WO2017008322A1 (zh) 2017-01-19

Family

ID=54497904

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2015/084682 Ceased WO2017008322A1 (zh) 2015-07-10 2015-07-21 基于社交网络行为感知的智能家庭能源管理方法

Country Status (2)

Country Link
CN (1) CN105068513B (zh)
WO (1) WO2017008322A1 (zh)

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110262276A (zh) * 2019-07-26 2019-09-20 南华大学 基于树莓派的智能家居系统及其控制方法
CN112255480A (zh) * 2020-10-12 2021-01-22 浙江长元科技有限公司 基于霍尔效应的电器特征识别方法及其安全预警系统
CN112815610A (zh) * 2019-11-18 2021-05-18 博西华电器（江苏）有限公司 家用电器中离子发生器的控制方法、装置和家用电器
CN114738827A (zh) * 2022-04-12 2022-07-12 建科环能科技有限公司 一种基于用户习惯的户用电供暖智能群控控制方法及系统
CN115913997A (zh) * 2022-12-21 2023-04-04 广东明创软件科技有限公司 行为预测方法、装置、存储介质及电子设备
CN115905688A (zh) * 2022-11-08 2023-04-04 南京鼎山信息科技有限公司 一种基于人工智能和智能家居的参考信息生成方法
CN116111621A (zh) * 2023-02-10 2023-05-12 国家电投集团数字科技有限公司 一种面向居民家庭的供用储能智慧调节系统
CN116951776A (zh) * 2023-08-01 2023-10-27 浙江尼普顿科技股份有限公司 一种基于建筑智能化的热水循环监控管理方法
CN117666377A (zh) * 2024-02-01 2024-03-08 湖南麓川信息科技有限公司 一种基于物联感知的多模态数据智能推荐方法及系统
CN119045369A (zh) * 2024-07-19 2024-11-29 前方高能人工智能科技(成都)有限公司 一种基于智能体和软件用户界面的感知处理装置
CN119561110A (zh) * 2025-01-22 2025-03-04 山东康威大数据科技有限公司 一种基于太阳能光伏发电的储能管理系统

Families Citing this family (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105743750A (zh) * 2016-03-23 2016-07-06 北京绿源普惠科技有限公司 一种智能家居实现自适应感知的方法
CN105607508A (zh) * 2016-03-24 2016-05-25 重庆邮电大学 基于用户行为分析的智能家居设备控制方法及系统
CN107783433B (zh) * 2016-08-30 2020-06-05 中国电信股份有限公司 一种物联网终端控制方法、装置以及物联网系统
CN108170712B (zh) * 2017-11-29 2021-08-10 浙江大学 一种利用包含社会地理信息的多媒体网络学习最大边界多媒体网络表达的方法
CN110059819B (zh) * 2018-01-17 2022-11-25 腾讯科技（深圳）有限公司 器件的工作控制方法、装置、系统、控制设备及存储介质
US11185207B2 (en) * 2018-07-24 2021-11-30 Qualcomm Incorporated Managing cleaning robot behavior
CN109670647A (zh) * 2018-12-21 2019-04-23 电子科技大学 一种家庭突发用电和可变参数的能源优化管理系统及方法
CN110333675B (zh) * 2019-06-28 2021-11-23 青岛海尔空调器有限总公司 一种用于插座的控制方法、控制装置及插座
CN111045339B (zh) * 2019-11-21 2023-07-18 南京理工大学 基于用户行为描述智能家居环境需求的方法
CN112255925A (zh) * 2020-10-19 2021-01-22 珠海格力电器股份有限公司 一种控制智能家居设备的方法、装置及计算机设备

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2006065996A2 (en) * 2004-12-16 2006-06-22 General Instrument Corporation Messaging system based building control
WO2009156978A1 (en) * 2008-06-26 2009-12-30 Intuitive User Interfaces Ltd System and method for intuitive user interaction
CN104182221A (zh) * 2014-08-15 2014-12-03 李祝明 一种基于社交软件的情感控制灯及其实现方法

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101833286A (zh) * 2009-03-13 2010-09-15 王俊锋 一种智能家居控制器
CN202975732U (zh) * 2012-11-08 2013-06-05 嘉应学院 一种可远程交互的实时家庭能源智能管理系统
CN104035415A (zh) * 2014-06-13 2014-09-10 上海应用技术学院 基于云计算的智能家居的能源管理系统
CN104570755A (zh) * 2015-01-21 2015-04-29 苏州奥莱维信息技术有限公司 一种基于手机的智能家居控制方法

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2006065996A2 (en) * 2004-12-16 2006-06-22 General Instrument Corporation Messaging system based building control
WO2009156978A1 (en) * 2008-06-26 2009-12-30 Intuitive User Interfaces Ltd System and method for intuitive user interaction
CN104182221A (zh) * 2014-08-15 2014-12-03 李祝明 一种基于社交软件的情感控制灯及其实现方法

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
XU, YONGWEI: "Smart Home System Design Based on SNS", SCIENCEPAPER ONLINE, 2 December 2014 (2014-12-02), pages 44 - 126 *

Cited By (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110262276A (zh) * 2019-07-26 2019-09-20 南华大学 基于树莓派的智能家居系统及其控制方法
CN110262276B (zh) * 2019-07-26 2023-12-19 南华大学 基于树莓派的智能家居系统及其控制方法
CN112815610A (zh) * 2019-11-18 2021-05-18 博西华电器（江苏）有限公司 家用电器中离子发生器的控制方法、装置和家用电器
CN112255480A (zh) * 2020-10-12 2021-01-22 浙江长元科技有限公司 基于霍尔效应的电器特征识别方法及其安全预警系统
CN114738827B (zh) * 2022-04-12 2023-09-26 建科环能科技有限公司 一种基于用户习惯的户用电供暖智能群控控制方法及系统
CN114738827A (zh) * 2022-04-12 2022-07-12 建科环能科技有限公司 一种基于用户习惯的户用电供暖智能群控控制方法及系统
CN115905688A (zh) * 2022-11-08 2023-04-04 南京鼎山信息科技有限公司 一种基于人工智能和智能家居的参考信息生成方法
CN115905688B (zh) * 2022-11-08 2023-07-28 南京鼎山信息科技有限公司 一种基于人工智能和智能家居的参考信息生成方法
CN115913997A (zh) * 2022-12-21 2023-04-04 广东明创软件科技有限公司 行为预测方法、装置、存储介质及电子设备
CN115913997B (zh) * 2022-12-21 2025-07-11 广东明创软件科技有限公司 行为预测方法、装置、存储介质及电子设备
CN116111621B (zh) * 2023-02-10 2023-10-13 国家电投集团数字科技有限公司 一种面向居民家庭的供用储能智慧调节系统
CN116111621A (zh) * 2023-02-10 2023-05-12 国家电投集团数字科技有限公司 一种面向居民家庭的供用储能智慧调节系统
CN116951776A (zh) * 2023-08-01 2023-10-27 浙江尼普顿科技股份有限公司 一种基于建筑智能化的热水循环监控管理方法
CN117666377A (zh) * 2024-02-01 2024-03-08 湖南麓川信息科技有限公司 一种基于物联感知的多模态数据智能推荐方法及系统
CN117666377B (zh) * 2024-02-01 2024-04-23 湖南麓川信息科技有限公司 一种基于物联感知的多模态数据智能推荐方法及系统
CN119045369A (zh) * 2024-07-19 2024-11-29 前方高能人工智能科技(成都)有限公司 一种基于智能体和软件用户界面的感知处理装置
CN119561110A (zh) * 2025-01-22 2025-03-04 山东康威大数据科技有限公司 一种基于太阳能光伏发电的储能管理系统

Also Published As

Publication number Publication date
CN105068513B (zh) 2016-06-29
CN105068513A (zh) 2015-11-18

Similar Documents

Publication Publication Date Title
WO2017008322A1 (zh) 基于社交网络行为感知的智能家庭能源管理方法
CN107683486B (zh) 用户事件的具有个人影响性的改变
US11062580B2 (en) Methods and systems for updating an event timeline with event indicators
US10108862B2 (en) Methods and systems for displaying live video and recorded video
AU2015287997B2 (en) Method and device for processing motion events
EP3469496B1 (en) Situation forecast mechanisms for internet of things integration platform
US9158974B1 (en) Method and system for motion vector-based video monitoring and event categorization
CN107548500A (zh) 基于用户例程模型的事件异常
US20160342906A1 (en) Situation forecast mechanisms for internet of things integration platform
CN103984775A (zh) 一种推荐好友的方法和设备
US20090150380A1 (en) System and method for processing social relation oriented service
US20220114472A1 (en) Systems and methods for generating machine learning-driven telecast forecasts
Hammer et al. Exploiting usage statistics for energy-efficient logical status inference on mobile phones
CN106842964A (zh) 个性化定制系统及方法
JP2026072565A (ja) システム
KR20250098323A (ko) 사용자 질의에 응답하여 마케팅 분석 코멘트를 제공하는 사용자 단말 장치 및 그 동작 방법
CN114091738A (zh) 投诉概率的获取方法及装置、电子设备
KR20230055215A (ko) 마케팅 채널 및 그 레벨 조합의 콘텐츠 파워 인덱스 기반 코멘트를 제공하는 마케팅 정보 분석 서비스 제공 장치 및 그 동작 방법

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 15898049

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 15898049

Country of ref document: EP

Kind code of ref document: A1