摘要：【中文】本发明公开了一种基于人脸识别的业务定向推荐的方法，包括排队取号装置，排队取号装置包括人脸识别装置；当有客户走进交互式排队机的人脸识别摄像头识别范围内，通过人脸识别装置获取客户信息后传递给排队取号装置；排队取号装置采集一定历史期限内，排队取号装置上业务的点击数量、客户信息，建立业务与客户信息的匹配关系；排队取号装置根据匹配关系向客户发送业务选项。本发明还公开了一种基于人脸识别的业务定向推荐的装置，包括人脸识别装置，业务处理装置，客户行为统计装置。 【EN】The invention discloses a service directional recommendation method based on face recognition, which comprises a queuing and number-taking device, wherein the queuing and number-taking device comprises a face recognition device; when a client walks into the recognition range of the face recognition camera of the interactive queuing machine, the client information is acquired by the face recognition device and then transmitted to the queuing and number-taking device; the queuing and number-taking device collects the number of clicks of the service on the queuing and number-taking device and the client information within a certain historical period, and establishes a matching relation between the service and the client information; and the queuing and number-taking device sends the service option to the client according to the matching relation. The invention also discloses a device for service directional recommendation based on face recognition, which comprises a face recognition device, a service processing device and a customer behavior statistical device.

摘要：【中文】本发明涉及一种排队方法、系统、客户端、装置及其服务器，排队方法包括：排队机获取客户信息，并识别和提取客户有效排队数据；排队机根据所述客户有效排队数据进行数据清洗，对所述客户有效排队数据进行分组和排序；排队机根据所述分组和排序后的数据进行数据加工，计算出每个业务办理结束所需时间；排队机根据所述业务办理结束所需时间，在取号前提示办理耗时和预计等待时长，并在取号后通知客户。本发明能够为银行客户提供准确有价值的，针对性更强的排队服务；通过提示客户等待时间，办理时间，使客户合理规划时间，节约号票资源，提高银行服务效率和质量。 【EN】The invention relates to a queuing method, a system, a client, a device and a server thereof, wherein the queuing method comprises the following steps: the queuing machine acquires the client information, and identifies and extracts the effective queuing data of the client; the queuing machine carries out data cleaning according to the client effective queuing data, and carries out grouping and sequencing on the client effective queuing data; the queuing machine processes data according to the grouped and sequenced data and calculates the time required by the completion of each service transaction; and the queuing machine displays the time consumed by transaction and the expected waiting time before the number is taken according to the time required by the transaction completion of the service, and notifies the client after the number is taken. The invention can provide accurate and valuable queuing service with stronger pertinence for bank customers; by prompting the waiting time and handling time of the client, the client can reasonably plan the time, save the number ticket resource and improve the efficiency and quality of banking services.

摘要：【中文】本发明提供一种电力需求响应分配方法及装置，包括：接收所需调度的总电量；获取各综合能源服务商的第一用电数据集合，获取各负荷聚合商的第二用电数据集合；对所述第一用电数据集合中的各项第一用电数据进行统计分析处理，得到第一用电数据统计结果集合；对所述第二用电数据集合中的各项第二用电数据进行统计分析处理，得到第二用电数据统计结果集合；根据第一用电数据统计结果集合和第二用电数据统计结果集合，分配所述总电量。本发明能够利用综合能源服务商和负荷聚合商进行电力需求响应分配电量，优化能源分配。 【EN】The invention provides a power demand response distribution method and a device, comprising the following steps: receiving total electric quantity required to be scheduled; acquiring a first electricity data set of each comprehensive energy service provider and a second electricity data set of each load aggregation provider; performing statistical analysis processing on each item of first electricity data in the first electricity data set to obtain a first electricity data statistical result set; performing statistical analysis processing on each item of second electrical data in the second electrical data set to obtain a second electrical data statistical result set; and distributing the total electric quantity according to the first electric data statistical result set and the second electric data statistical result set. The invention can utilize the comprehensive energy service provider and the load aggregation provider to respond the electric power demand and distribute the electric quantity, and optimize the energy distribution.

摘要：【中文】本发明公开了一种基于同源异构神经网络的电力负荷概率预测方法及装置，涉及电力负荷预测技术领域，为了提高预测结果的准确性；该预测的装置包括数据对整理模块、数据对分类模块、模型构造模块、训练模块、修正模块和分析模块；该概率预测方法充分考虑环境因素的影响，使得预测的结果更加准确；由于使用同源异构神经网络进行不断训练、校验和检验，使得的进行预测的模型更加科学，取得的结果更加贴近实际情况；由于对不同模型取得的结果进行统计学分析，使得得到的预测结果更加精确。 【EN】The invention discloses a power load probability prediction method and device based on a heterogeneous neural network, relates to the technical field of power load prediction, and aims to improve the accuracy of a prediction result; the prediction device comprises a data pair sorting module, a data pair classification module, a model construction module, a training module, a correction module and an analysis module; the probability prediction method fully considers the influence of environmental factors, so that the prediction result is more accurate; because the homologous heterogeneous neural network is used for continuous training, verification and inspection, the model for prediction is more scientific, and the obtained result is closer to the actual situation; due to the fact that the results obtained by different models are subjected to statistical analysis, the obtained prediction result is more accurate.

摘要：【中文】本发明公开了一种商业楼宇的日负荷预测方法，涉及能源物联大数据领域，包括如下步骤：采集待预测楼宇的选定时间段每日的日负荷数据和该选定时间段每天的的小时负荷数据；根据小时负荷数据生成小时负荷时间序列曲线，对小时负荷时间序列曲线进行聚类分析处理，得出聚类数；根据日负荷数据生成日负荷时间序列曲线；通过对聚类数和日负荷时间序列曲线进行训练，得出SVR模型；通过SVR模型对待预测商业楼宇进行未来目标日的负荷预测。解决了传统基于统计的方法在商业楼宇负荷预测方面表现普遍较差的问题。 【EN】The invention discloses a daily load prediction method for commercial buildings, which relates to the field of energy Internet of things big data and comprises the following steps: acquiring daily load data of a selected time period and daily hour load data of the selected time period of a building to be predicted; generating an hour load time series curve according to the hour load data, and carrying out cluster analysis processing on the hour load time series curve to obtain cluster numbers; generating a daily load time sequence curve according to the daily load data; training the clustering number and the daily load time sequence curve to obtain an SVR model; and carrying out load prediction on the commercial building to be predicted in a future target day through the SVR model. The problem that the traditional statistical-based method is generally poor in performance in the aspect of commercial building load prediction is solved.

摘要：【中文】本发明公开了一种电力日负荷预测方法及装置,其中，所述方法包括采集多份历史日负荷数据；使用以动态时间规整作为距离度量对所述历史日负荷数据进行聚类；将聚类后的所述历史日负荷数据输入马尔科夫链原始模型，对所述马尔科夫链原始模型进行训练，获得马尔科夫链预测模型；将当前的日负荷数据输入所述马尔科夫链预测模型中，以预测下一日的日负荷数据。本发明中，使用以动态时间规整作为距离对历史日负荷数据进行聚类，度量用户每日用电的相似性，将聚类后的所述历史日负荷数据输入马尔科夫链原始模型，训练获得马尔科夫链预测模型，通过马尔科夫链预测模型对下一日的日负荷数据，有效提升了用户每日负荷预测的精度。 【EN】The invention discloses a method and a device for predicting daily load of electric power, wherein the method comprises the steps of collecting multiple pieces of historical daily load data; clustering the historical daily load data by using dynamic time warping as a distance measure; inputting the clustered historical daily load data into a Markov chain original model, and training the Markov chain original model to obtain a Markov chain prediction model; inputting the current daily load data into the Markov chain prediction model to predict the daily load data of the next day. According to the method, dynamic time warping is used as a distance to cluster historical daily load data, the similarity of daily electricity consumption of a user is measured, the clustered historical daily load data are input into a Markov chain original model, a Markov chain prediction model is obtained through training, and the accuracy of daily load prediction of the user is effectively improved through the Markov chain prediction model on the daily load data of the next day.

摘要：【中文】本发明公开了一种用户的用电参数调节方法，包括如下步骤：获取待分类用户的电力负荷数据的频域特征；将待分类用户的电力负荷数据的频域特征输入分类决策树中，得到待分类用户的种类；依据待分类用户的种类调节其用电参数；分类决策树的建立过程包括：获取多个不同的已知种类用户的电力负荷数据的频域特征；建立决策树模型；依据多个不同的已知种类用户的电力负荷数据的频域特征求出决策树模型中的未知条件参数并生成分类决策树，本发明的用户的用电参数调节方法，使生成的分类决策树在获得待分类用户的电力负荷数据的频域特征后，能依据电力负荷数据中的更多数据进行判断，提高对用户分类的准确率，便于对分类后的用户进行用电参数的调节。 【EN】The invention discloses a method for adjusting power utilization parameters of a user, which comprises the following steps: acquiring frequency domain characteristics of power load data of users to be classified; inputting the frequency domain characteristics of the power load data of the users to be classified into a classification decision tree to obtain the types of the users to be classified; adjusting the electricity utilization parameters of the users to be classified according to the types of the users; the establishing process of the classification decision tree comprises the following steps: acquiring frequency domain characteristics of power load data of a plurality of different users of known types; establishing a decision tree model; according to the power utilization parameter adjusting method for the users, after the frequency domain characteristics of the power load data of the users to be classified are obtained, the generated classification decision tree can be judged according to more data in the power load data, the accuracy of user classification is improved, and the adjustment of the power utilization parameters of the classified users is facilitated.

摘要：【中文】本发明公开了一种基于数据衍生的电力负荷预测方法，包括获取历史用电数据；将所述历史用电数据带入正态分布函数进行衍生拓展，得出拓展衍生得出的数据，历史用电数据与拓展衍生得出的数据共同作为用电负荷数据；将用电负荷数据划分成训练集与验证集；将训练集数据作为输入带入预设结构的模型，以输入固定时间的实际负荷作为输出进行训练，并在训练过程中带入验证集数据进行验证，得到预测模型；将一个时间段的用电负荷数据带入预测模型，得出下一个时间段的用电负荷预测结果，本发明提出的方法通过对将历史用电数据带入正态分布函数进行衍生拓展，增大了进行预测的数据量，进而提高了用电负荷预测的准确性。 【EN】The invention discloses a power load prediction method based on data derivation, which comprises the steps of obtaining historical power consumption data; substituting the historical electricity utilization data into a normal distribution function to conduct derivative development to obtain data derived from development, wherein the historical electricity utilization data and the data derived from development are jointly used as electricity utilization load data; dividing the power load data into a training set and a verification set; taking training set data as input and bringing the training set data into a model with a preset structure, taking actual load of input fixed time as output for training, and bringing verification set data in the training process for verification to obtain a prediction model; the method provided by the invention has the advantages that historical electricity utilization data are substituted into a normal distribution function to be subjected to derivative expansion, so that the data volume for prediction is increased, and the accuracy of electricity utilization load prediction is further improved.

摘要：【中文】本发明提出了一种家庭能源综合管理方法、装置及系统，其中，所述系统包括智能插座、智能开关及边缘智能终端，其中，边缘智能终端内部集成采集模块、分析模块、存储模块、控制模块、通信模块等；智能插座能够采集本插座的电流、电压等数据，同时能够实现远程控制功能；智能开关连接室内灯光、门禁等设备，能够采集开关控制设备的电压、电流，并实现远程控制功能。本系统通过HPLC电力线载波的通信方式，实现边缘智能终端与智能插座、智能开关的连接；另外，同时能够实现远程控制功能；智能开关连接室内灯光、门禁等设备，能够采集开关控制设备的电压、电流，并实现远程控制功能。 【EN】The invention provides a method, a device and a system for comprehensive management of household energy, wherein the system comprises an intelligent socket, an intelligent switch and an edge intelligent terminal, wherein an acquisition module, an analysis module, a storage module, a control module, a communication module and the like are integrated in the edge intelligent terminal; the intelligent socket can acquire data such as current, voltage and the like of the socket and can realize a remote control function; the intelligent switch is connected with indoor lamplight, entrance guard and other equipment, can collect the voltage and current of the switch control equipment, and realizes the remote control function. The system realizes the connection of the edge intelligent terminal with the intelligent socket and the intelligent switch through a communication mode of an HPLC power line carrier; in addition, the remote control function can be realized; the intelligent switch is connected with indoor lamplight, entrance guard and other equipment, can collect the voltage and current of the switch control equipment, and realizes the remote control function.

摘要：【中文】本发明公开了一种住宅日用电负荷预测方法和设备，首先采用卷积自编码器提取用户行为特征作为特征向量，再利用历史日特征向量预测用户当日的特征向量，最后用解码器重构预测得到的特征向量，最终得到预测的数据集，通过利用卷积自编码器提取住宅用电负荷数据集的特征，形成特征向量，捕获了用户的行为特征，并对特征向量的每日变化做出预测，而不是对每个时刻进行预测，更符合单个住宅的用电行为习惯的特性，有效提升了单个住宅每日负荷预测的精度。 【EN】The invention discloses a residential daily electricity load prediction method and equipment, which comprises the steps of firstly extracting user behavior characteristics by adopting a convolution self-encoder to serve as characteristic vectors, then predicting the characteristic vectors of a user on the current day by utilizing historical day characteristic vectors, finally reconstructing the predicted characteristic vectors by using a decoder to obtain a predicted data set, extracting the characteristics of a residential electricity load data set by utilizing the convolution self-encoder to form the characteristic vectors, capturing the behavior characteristics of the user, predicting the daily change of the characteristic vectors instead of predicting each moment, more conforming to the characteristics of electricity consumption behavior habits of a single residence and effectively improving the accuracy of the daily load prediction of the single residence.