CN117557300B - Method and system for deducing business liveness based on energy consumption data of main equipment - Google Patents
Method and system for deducing business liveness based on energy consumption data of main equipment Download PDFInfo
- Publication number
- CN117557300B CN117557300B CN202410047451.4A CN202410047451A CN117557300B CN 117557300 B CN117557300 B CN 117557300B CN 202410047451 A CN202410047451 A CN 202410047451A CN 117557300 B CN117557300 B CN 117557300B
- Authority
- CN
- China
- Prior art keywords
- energy consumption
- business
- data
- consumption data
- equipment
- 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.)
- Active
Links
- 238000005265 energy consumption Methods 0.000 title claims abstract description 67
- 238000000034 method Methods 0.000 title claims abstract description 48
- 230000000694 effects Effects 0.000 claims abstract description 108
- 238000012545 processing Methods 0.000 claims abstract description 7
- 238000012549 training Methods 0.000 claims description 32
- 238000004422 calculation algorithm Methods 0.000 claims description 12
- 238000010801 machine learning Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 9
- 238000012360 testing method Methods 0.000 claims description 6
- 230000008713 feedback mechanism Effects 0.000 claims description 5
- 238000012544 monitoring process Methods 0.000 claims description 5
- 238000005457 optimization Methods 0.000 claims description 5
- 230000000295 complement effect Effects 0.000 claims description 4
- 230000035899 viability Effects 0.000 claims description 3
- 230000001737 promoting effect Effects 0.000 claims description 2
- 238000012795 verification Methods 0.000 description 5
- 241001122767 Theaceae Species 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000007405 data analysis Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 239000008267 milk Substances 0.000 description 3
- 210000004080 milk Anatomy 0.000 description 3
- 235000013336 milk Nutrition 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000007637 random forest analysis Methods 0.000 description 2
- 230000001502 supplementing effect Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 230000001932 seasonal effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Marketing (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of data processing, in particular to a method and a system for deducing business activity based on energy consumption data of main equipment, wherein the method comprises the following steps: collecting equipment energy consumption data of main energy of the shop in real time and uploading the data to a computer end or a cloud end; and at the computer end or the cloud end, inputting the equipment energy consumption data, the date, the weather, the holiday condition, the business promotion activity condition and the take-out traffic into a business activity prediction model, and outputting the business activity, wherein the business activity is a time sequence array of the traffic of people. The invention can accurately evaluate and predict the business activity.
Description
Technical Field
The invention relates to the technical field of big data analysis, in particular to a method and a system for deducing business activity based on energy consumption data of main equipment.
Background
In the current global economic environment, business activities have penetrated every corner of our lives. But currently lacks means for predicting commercial viability. In this context, business activity deduction methods based on network data analysis are particularly important. The method abstracts and understands the intensity and trend of commercial activities by deeply mining and refining rich data sources on the internet, such as consumer evaluation platforms (e.g., mobile phone application popular reviews), search engine data, web page access data, and the like. This may help predict business activity, reducing business risk due to lack of accurate business activity prediction information.
For the method of deriving business activity using network data, there are some limitations in terms of universality. First, the availability and type of network data varies from region to region and industry to industry, meaning that the available data sources and applicable analysis methods need to be determined on a case-by-case basis. In addition, the timeliness of the network data also has some impact on the accuracy of the result, as the update rate of the network data may not meet the needs of business decision makers for real-time information. This type of approach has certain limitations in meeting the needs of specific business decision makers. Further research and development of more accurate, real-time data analysis and deduction techniques are needed to better meet the needs of business decision makers. This will help to improve the accuracy and reliability of business activity deduction and make it more suitable for the needs of different areas and industries.
Disclosure of Invention
First, the technical problem to be solved
In view of the above-mentioned drawbacks and shortcomings of the prior art, the present invention provides a method and a system for deriving commercial activity based on energy consumption data of a main device, which solve the technical problem that the update speed of network data in the prior art cannot meet the requirement of a commercial decision maker on real-time information, so that a commercial activity derivation result cannot be accurately obtained in real time.
(II) technical scheme
In order to achieve the above purpose, the main technical scheme adopted by the invention comprises the following steps:
in a first aspect, an embodiment of the present invention provides a method for deriving business activity based on energy consumption data of a primary device, including:
collecting equipment energy consumption data of main energy of the shop in real time and uploading the data to a computer end or a cloud end;
at a computer end or a cloud end, inputting equipment energy consumption data, date, weather, holiday conditions, business promotion conditions, customer orders and take-out traffic into a business activity prediction model, and outputting business activity, wherein the business activity is a time sequence number series of traffic;
the business activity prediction model is obtained through training the following steps:
at a computer end or a cloud end, collecting time sequence series of equipment energy consumption data, date, ticket amount, takeout traffic amount and historical personnel flow amount of a historical period of time, and taking weather, holiday conditions and business promotion conditions as characteristic parameters of a deduction model; training, verifying and testing by adopting a machine learning algorithm to obtain a business activity prediction model;
the business activity prediction model is input into time sequence series of equipment energy consumption data, date, guest amount and takeout traffic, weather, holiday conditions and business promotion conditions; the output of the business activity prediction model is business activity;
and predicting the commercial activity in real time by using the commercial activity prediction model obtained through training, and establishing a feedback mechanism by combining the commercial activity data which actually occur, and updating and optimizing the model.
The method for deducing the business activity based on the energy consumption data of the main equipment solves the problem that the business activity deduced by using the network data cannot be universally applicable due to different business types and actual conditions; after the data set of a specific shop is acquired, the business activity prediction model can be quickly passed, and the prediction result of the business activity can be acquired, so that the problem of data timeliness of the business activity can be deduced by utilizing network data is solved, and the cost of manual operation and time is reduced.
Optionally, collecting energy consumption data of main energy utilization equipment of the shops in real time; the method comprises the following steps:
according to basic energy consumption information of existing equipment of multiple groups of shops, judging main energy utilization equipment of a specific commercial place by counting using frequency of personnel and whether the equipment interacts with people;
and installing a device capable of monitoring the equipment energy consumption data in real time at a socket connected with the main energy utilization equipment, wherein the device is used for collecting the equipment energy consumption data in real time and uploading the equipment energy consumption data to a computer terminal.
Optionally, the frequency of use of the person and whether to interact with the person are:
the personnel use frequency is determined by counting the frequency of equipment start-up;
whether to interact with a person or not to operate a device for which a human operation is required.
Optionally, the feedback mechanism comprises:
setting a predicted relative error interval, and generating alarm information when the relative error of the commercial activity predicted by the commercial activity prediction model and the commercial activity actually occurring exceeds the relative error interval; to remind the user that the prediction accuracy of the business activity prediction model is reduced, model optimization should be performed; the relative error interval is as follows:
；
wherein,is the relative error; />Is a prediction result; />Is a practical result.
Optionally, prior to training the business activity prediction model, the collected historical time series of device energy consumption data, date, volume of orders and take-out traffic, and historical volume of people, and missing data for weather, holiday conditions, and business promotional conditions are complemented:
the method comprises the steps of adopting a mean value interpolation method to complement a missing value for a time sequence series of continuous variables including equipment energy consumption data, dates, customer orders, take-out traffic and historical people flow;
the missing values are complemented with fixed values for the category variables therein, including weather, holiday conditions, and business promotion conditions.
Optionally, before training the business activity prediction model, when the number of missing data in any category is greater than a set threshold value, deleting the data in the category corresponding to the period of time of the missing data.
Optionally, before training the business activity prediction model, collecting device energy consumption data, date (whether the weekend, the beginning of the month or the end of the month and seasonal factors can be known by taking the date into consideration), weather (influence on personnel traveling mainly by taking into consideration all weather, rain, snow and the like), holiday conditions (difference of consumption habits of personnel in holidays and non-holidays and difference of personnel traveling into consideration), business promotion events conditions (such as increasing people's flows in the case of a certain market making year celebration, consumption festival and other promotion events), ticket amount (ticket amount is an actual transaction amount, actual conversion rate of the ticket amount can be counted by taking the ticket amount into consideration, direct relation with energy consumption can be expressed, and the ticket amount can be used as an effective conversion part in the ticket amount, and can represent influence of the different factors on conversion rate, for example, the conversion rate is higher when the market event is not much than the current difference of personnel in the store event, so that the energy consumption of the main equipment is higher), takeout ticket amount (the actual transaction amount can be counted by taking into consideration, and the history data is continuously processed by taking the ticket amount into consideration, and the history data is taken into consideration; adopting one-hot coding for class variables with the cardinality less than 10; and adopting sequential coding processing for class variables with cardinality of more than or equal to 10.
According to the data supplement method, multi-source or incorrect incomplete data can meet the requirements of data items of a data set, and through standardized processing of the data, the calculation amount during model training can be reduced, the training time of the model is shorter, the model can be converged more quickly, and the accuracy of model prediction can be improved.
In a second aspect, an embodiment of the present invention provides a system for deriving commercial viability based on energy consumption data of a primary device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the steps of any of the methods described above when the computer program is executed.
In a third aspect, embodiments of the present invention provide a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of any of the methods described above.
(III) beneficial effects
The beneficial effects of the invention are as follows: according to the method for deducing the business activity based on the energy consumption data of the main equipment, the business activity is deduced by adopting the energy consumption data of the main equipment; the business decision maker can accurately evaluate the traffic in the business activity by monitoring the main equipment energy consumption data of the shop, and can predict the time series data (such as people/hour) of the traffic for a future period of time.
Drawings
FIG. 1 is a flow chart of a method for deriving business activity based on energy consumption data of a primary device according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of training steps of a business activity prediction model used in an embodiment of the present invention.
Detailed Description
The invention will be better explained by the following detailed description of the embodiments with reference to the drawings.
The method for deducing the business activity based on the energy consumption data of the main equipment provided by the embodiment of the invention adopts the energy consumption data, date, weather, holiday condition, business promotion condition, guest amount and takeout transaction amount data of the main energy equipment to deduce the business activity; the business decision maker can monitor the primary equipment energy consumption data of the shop to accurately evaluate the business people flow and business activity. The invention not only can help business decision makers to judge business trends more accurately and make reasonable business arrangement, but also can effectively prevent employee counterfeiting.
In order that the above-described aspects may be better understood, exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
The method for deducing the business activity based on the energy consumption data of the main equipment is suitable for places with obvious energy consumption characteristics and certain correlation between the business activities and the energy consumption of the main equipment, such as: commercial sites such as coffee shops, milky tea shops, building center, law firm, gym, etc.
Example 1
Fig. 1 is a flow chart of a method for deriving business activity based on energy consumption data of a primary device in embodiment 1 of the present invention. The method for deducing business activity based on the energy consumption data of the main equipment of the embodiment comprises the following steps:
s1: collecting equipment energy consumption data of main energy of the shop in real time and uploading the data to a computer end or a cloud end;
s2: and at the computer end or the cloud end, inputting the equipment energy consumption data, the date, the weather, the holiday condition, the business promotion activity condition, the passenger order quantity and the takeout traffic into a business activity prediction model, and outputting the business activity which is a time sequence array of the traffic of people.
The method for deducing the business activity based on the energy consumption data of the main equipment solves the problem that the business activity deduced by using the network data cannot be universally applicable due to different business types and actual conditions; after the data set of a specific shop is acquired, the business activity prediction model can be quickly passed, and the prediction result of the business activity can be acquired, so that the problem of data timeliness of the business activity can be deduced by utilizing network data is solved, and the cost of manual operation and time is reduced.
Referring to fig. 2, the business activity prediction model used in the present embodiment mainly includes the following stages:
a-B: data acquisition and data processing: and integrating a plurality of characteristic parameters such as energy data, time period and historical people flow data of main equipment, and performing data cleaning and preprocessing. The integrity and the accuracy of the data are ensured, so that the data can be used in the model training and prediction process, and the model prediction accuracy is improved.
During implementation, collecting energy consumption data of main energy utilization equipment of a shop; the method comprises the following steps:
according to basic energy consumption information of existing equipment of multiple groups of shops, main energy equipment of a specific commercial place is judged by counting using frequency of personnel and whether the equipment interacts with people. The person's usage frequency is determined by counting the device-initiated frequency (e.g., by plotting a frequency histogram); whether to interact with a person or not to operate a device for which a human operation is required. Such as: the main energy equipment of the milk tea shop, namely a milk tea machine, generally increases the energy consumption of the milk tea machine when a customer places an order; the coffee machine is a coffee machine, and the energy consumption of the coffee machine can work more frequently and is higher when the coffee machine is in a period of high people flow.
And installing a device capable of monitoring the equipment energy consumption data in real time at a socket connected with the main energy utilization equipment, wherein the device is used for collecting the equipment energy consumption data in real time and uploading the equipment energy consumption data to a computer terminal. For example, a smart jack (or a current transformer installed on a power cord) is used that is plugged into a power outlet, connected to a power grid, then paired with a mobile application and connected to a wireless network, and a smart jack built-in sensor can monitor the power consumption (e.g., the current of the power cord) in real time and transmit the data to a cloud platform or mobile application for storage for subsequent training of models or real-time prediction.
The data processing comprises the following steps: complement small area missing data in collected device energy consumption data, date, weather, holiday conditions, business promotion conditions (e.g., whether a certain store is currently engaged in a member node activity: the method comprises the steps of (1) supplementing a missing value to a continuous variable (time sequence) by adopting a mean value interpolation method; and supplementing the missing value for the category variable by adopting a fixed value.
For large area missing data: when the number of missing data in any category is greater than a set threshold (set according to a specific data type) before training the business activity prediction model, deleting the data in the category in a period corresponding to the missing data (avoiding the excessive influence of the complement data on the model prediction accuracy).
The continuous variable comprises historical people flow, equipment energy consumption data, date, ticket amount and take-out transaction amount; category variables include weather, holiday conditions, and business promotion conditions.
After the missing data is complemented, in order to improve the convergence speed of the model and improve the stability of the model, standardized processing is adopted for the continuity variable, and One-Hot encoding (One-Hot encoding) is adopted for the category variable with the base number (cardinality) smaller than 10, and otherwise sequential encoding (Ordinal encoding) is adopted.
Wherein,is the converted value; />Is the original data value; />Data mean value; />Data standard deviation.
C: model training: and training the selected model by using the processed training set, and enabling the model to adapt to the data and learn the mode and rule in the data by adjusting the model parameters and an optimization algorithm. The implementation process comprises the following steps: at a computer end or a cloud end, the collected equipment energy consumption data, date, weather, holiday conditions, business promotion events, customer orders, take-out traffic and historical people flow are used as characteristic parameters of a deduction model; training, verifying and testing by adopting a machine learning algorithm to obtain a business activity prediction model; the business activity prediction model is input by a time sequence series of equipment energy consumption data, date, customer order quantity and take-out traffic quantity, weather, holiday conditions and business promotion conditions at a computer end or a cloud end; the output of the business activity prediction model is the business activity, which in this embodiment is a time series sequence of human traffic.
In this example, the traffic (people/hour) is used as a measure of commercial activity. The relationship between business activity and people traffic is largely dependent on the specific business environment and context. In general, there is a positive correlation between business activity and traffic: the greater the traffic, the greater the commercial activity will generally be. And comparing the predicted people flow with the historical people flow data to obtain whether the number of staff is required to be increased in the same day or not, and reasonably distributing human resources.
Defining an input variable X and an output variable y, wherein the input variable X is a matrix formed by equipment power consumption, date, weather, holiday condition, business activity condition and take-out traffic, and the output variable y is a matrix formed by people traffic, and the formula is as follows:
input matrix:
output matrix:
the data set is divided into a training set (training) and a verification set (verification) and a test set (test), wherein the division ratio is 70% for model training, 20% for model verification, 10% for model test, the training set is used for training a selected machine learning model, and the optimal model parameter configuration is obtained by iterative tuning based on the verification set in the model training process.
Model training used in this embodiment is based on machine learning algorithms, which have automatic learning capabilities, handle complex data relationships, and flexibility and are widely used for data driven models. Machine learning algorithms can efficiently process large-scale data and extract meaningful information and patterns therefrom. The goal of the machine learning algorithm is to reduce the error between the predicted value and the actual value, while the objective function is a function that measures the error between the predicted result and the actual value of the model, and the selection of the loss function has a larger effect on the training and optimization of the model. The present application may employ existing machine learning algorithms, such as random forest algorithms.
In order to make the prediction effect of the model better, after model training is completed, the commercial activity is predicted in real time by using the commercial activity prediction model obtained by training, and a feedback mechanism is established by combining with the commercial activity data which actually occurs, and the model is updated and optimized, namely the following DEF step is carried out.
D: model prediction: and (3) using the data collected in real time as an input variable of a trained prediction model to obtain a time sequence prediction result of the traffic, such as an hourly traffic prediction value of 24 continuous hours, and monitoring the business activity in real time.
E: model feedback: when the relative error between the actual result and the predicted result is large, the system sends out alarm information, the user obtains feedback, and the model is reasonably adjusted.
The mechanism of this feedback includes:
setting a predicted relative error interval, and generating alarm information when the relative error of the commercial activity predicted by the commercial activity prediction model and the commercial activity actually occurring exceeds the relative error interval; to remind the user that the prediction accuracy of the business activity prediction model is reduced, model optimization should be performed; the relative error interval is as follows:
；
wherein,is the relative error; />Is a prediction result; />Is a practical result.
The actual business activity can be calculated by combining the actual collected traffic data (the collection method can be that a personnel sensor is arranged at the entrance of a shop or a business place, the actual traffic data can be obtained by multiplying the final result by 0.5), and the formula of the relative error interval can be calculated, and when a certain standard is exceeded, the system sends out alarm information.
F: and (3) model tuning: and according to the prediction result and the feedback result, performing measures such as parameter weight adjustment (different adjustable parameters exist in different specific algorithms, for example, decision tree quantity adjustment exists in a random forest), data set updating, model structure improvement and the like on the model so as to improve the model prediction accuracy. Comparing and evaluating the actual data with the prediction result of the model, measuring the prediction effect of the model by using a plurality of evaluation indexes, adjusting the model parameters based on the verification set, and selecting the optimal parameter configuration.
In a second aspect, an embodiment of the present invention further provides a system for deriving commercial activity based on energy consumption data of a primary device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing steps of any of the methods described above when the computer program is executed.
In a third aspect, embodiments of the present invention also provide a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of any of the methods described above.
The method and the system for deducing the business activity based on the energy consumption data of the main equipment, which are provided by the invention, are applied to a specific reality scene, and solve the problem that the deduction of the business activity by utilizing the network data cannot be universally applied due to different business types and actual conditions. After the data set of a specific shop is acquired, a deduction model can be quickly built and a prediction result is acquired, so that the problem of data timeliness of deduction of business activity by using network data is solved.
Business activity is affected by a number of factors, which may have complex nonlinear relationships between them, which can be captured by machine learning algorithms and a corresponding black box model built. And moreover, the machine learning algorithm can automatically deduce the business liveness, reduce the manual operation and time cost, and quickly predict new data after establishing a proper model, so that the working efficiency is improved.
In the description of the present invention, it should be understood that the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. In the description of the present invention, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
In the present invention, unless explicitly specified and limited otherwise, the terms "mounted," "connected," "secured," and the like are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally formed; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium; may be a communication between two elements or an interaction between two elements. The specific meaning of the above terms in the present invention can be understood by those of ordinary skill in the art according to the specific circumstances.
In the present invention, unless expressly stated or limited otherwise, a first feature is "on" or "under" a second feature, which may be in direct contact with the first and second features, or in indirect contact with the first and second features via an intervening medium. Moreover, a first feature "above," "over" and "on" a second feature may be a first feature directly above or obliquely above the second feature, or simply indicate that the first feature is higher in level than the second feature. The first feature being "under", "below" and "beneath" the second feature may be the first feature being directly under or obliquely below the second feature, or simply indicating that the first feature is level lower than the second feature.
In the description of the present specification, the terms "one embodiment," "some embodiments," "examples," "particular examples," or "some examples," etc., refer to particular features, structures, materials, or characteristics described in connection with the embodiment or example as being included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
While embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the invention, and that alterations, modifications, substitutions and variations may be made in the above embodiments by those skilled in the art within the scope of the invention.
Claims (9)
1. A method for deriving business activity based on energy consumption data of a primary device, comprising:
collecting equipment energy consumption data of main energy of the shop in real time and uploading the data to a computer end or a cloud end;
at a computer end or a cloud end, inputting equipment energy consumption data, a date, a guest amount and a time sequence of take-out traffic, weather, holiday conditions and business promotion conditions into a business activity prediction model, and outputting business activity, wherein the business activity is the time sequence of human traffic;
the business activity prediction model is obtained through training the following steps:
at a computer end or a cloud end, taking collected time sequence series of equipment energy consumption data, date, ticket amount, takeout traffic amount and historical people flow amount in a historical period of time, and weather, holiday conditions and business promotion conditions as characteristic parameters; training, verifying and testing by adopting a machine learning algorithm to obtain a business activity prediction model;
the business activity prediction model is input into time sequence series of equipment energy consumption data, date, guest amount and takeout traffic, weather, holiday conditions and business promotion conditions; the output of the business activity prediction model is business activity;
and predicting the commercial activity in real time by using the commercial activity prediction model obtained through training, and establishing a feedback mechanism by combining the commercial activity data which actually occur, and updating and optimizing the model.
2. The method of claim 1, wherein: the energy consumption data of main energy utilization equipment of the shops are collected in real time; the method comprises the following steps:
according to basic energy consumption information of existing equipment of multiple groups of shops, judging main energy utilization equipment of a specific commercial place by counting using frequency of personnel and whether the equipment interacts with people;
and installing a device capable of monitoring the equipment energy consumption data in real time at a socket connected with the main energy utilization equipment, wherein the device is used for collecting the equipment energy consumption data in real time and uploading the equipment energy consumption data to a computer terminal.
3. The method of claim 2, wherein: the personnel use frequency and whether interact with the person are as follows:
the personnel use frequency is determined by counting the frequency of equipment start-up;
whether to interact with a person or not to operate a device requiring human manipulation.
4. The method of claim 1, wherein: the feedback mechanism includes:
setting a predicted relative error interval, and generating alarm information when the relative error of the commercial activity predicted by the commercial activity prediction model and the commercial activity actually occurring exceeds the relative error interval; to remind the user that the prediction accuracy of the business activity prediction model is reduced, model optimization should be performed; the relative error interval is as follows:
;
wherein,is the relative error; />Is a prediction result; />Is a practical result.
5. The method of claim 1, wherein: the collected historical time series of equipment energy consumption data, date, ticket and takeout traffic and historical people traffic for a period of time, and missing data for weather, holiday conditions and business promotional events are complemented prior to training the business activity prediction model:
the method comprises the steps of adopting a mean value interpolation method to complement a missing value for a time sequence series of continuous variables including equipment energy consumption data, dates, customer orders, take-out traffic and historical people flow;
the missing values are complemented with fixed values for the category variables therein, including weather, holiday conditions, and business promotion conditions.
6. The method of claim 5, wherein: and deleting the data of the missing data corresponding to the time period in any category when the quantity of the missing data of any category is larger than a set threshold before training the business activity prediction model.
7. The method of any one of claims 4 to 6, wherein: and collecting equipment energy consumption data, date, weather, holiday conditions, business promotion conditions, ticket amount, takeout transaction amount and historical traffic data before training the business activity prediction model, and adopting standardized processing for time sequence series of the continuous variables including the equipment energy consumption data, date, ticket amount, takeout transaction amount and historical traffic.
8. A system for deriving commercial viability based on energy consumption data of a primary device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterised in that the processor implements the steps of the method of any of the preceding claims 1 to 7 when the computer program is executed.
9. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the steps of the method of any of the preceding claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410047451.4A CN117557300B (en) | 2024-01-12 | 2024-01-12 | Method and system for deducing business liveness based on energy consumption data of main equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410047451.4A CN117557300B (en) | 2024-01-12 | 2024-01-12 | Method and system for deducing business liveness based on energy consumption data of main equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117557300A CN117557300A (en) | 2024-02-13 |
| CN117557300B true CN117557300B (en) | 2024-04-05 |
Family
ID=89819017
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410047451.4A Active CN117557300B (en) | 2024-01-12 | 2024-01-12 | Method and system for deducing business liveness based on energy consumption data of main equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117557300B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108648023A (en) * | 2018-05-18 | 2018-10-12 | 上海电机学院 | A kind of businessman's passenger flow forecast method of fusion history mean value and boosted tree |
| CN110020738A (en) * | 2018-01-10 | 2019-07-16 | 北京京东金融科技控股有限公司 | For the method, apparatus of data processing, electronic equipment and computer-readable medium |
| CN110472892A (en) * | 2019-08-27 | 2019-11-19 | 上海电气分布式能源科技有限公司 | Build flow of the people, cool and thermal power load evaluation method and system, equipment and medium |
| CN110598906A (en) * | 2019-08-15 | 2019-12-20 | 珠海米枣智能科技有限公司 | Method and system for controlling energy consumption of superstores in real time based on deep reinforcement learning |
| CN113793010A (en) * | 2021-09-07 | 2021-12-14 | 国网浙江省电力有限公司营销服务中心 | Construction method for multi-load combined control strategy and air conditioner control method |
| CN114611624A (en) * | 2022-03-22 | 2022-06-10 | 广东贤能数字科技有限公司 | Artificial intelligence-based business activity evaluation system and method for shops or business halls |
| CN115345355A (en) * | 2022-08-02 | 2022-11-15 | 北京百度网讯科技有限公司 | Energy consumption prediction model construction method, short-term energy consumption prediction method and related device |
| CN115470707A (en) * | 2022-09-22 | 2022-12-13 | 上海时氪信息技术有限公司 | City scene simulation system |
| CN115550392A (en) * | 2022-04-29 | 2022-12-30 | 深圳云谷星辰信息技术有限公司 | Intelligent park digital twin platform system |
| CN115860790A (en) * | 2022-11-11 | 2023-03-28 | 深圳海智创科技有限公司 | Method for predicting place passenger flow, method and device for training model |
| CN116029395A (en) * | 2023-03-24 | 2023-04-28 | 深圳市明源云科技有限公司 | Pedestrian flow early warning method and device for business area, electronic equipment and storage medium |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20230030127A1 (en) * | 2019-12-25 | 2023-02-02 | Nippon Telegraph And Telephone Corporation | People flow prediction device, people flow prediction method, and people flow prediction program |
| US11887167B2 (en) * | 2022-06-14 | 2024-01-30 | Accenture Global Solutions Limited | Utilizing machine learning models to generate an optimized digital marketing simulation |
-
2024
- 2024-01-12 CN CN202410047451.4A patent/CN117557300B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110020738A (en) * | 2018-01-10 | 2019-07-16 | 北京京东金融科技控股有限公司 | For the method, apparatus of data processing, electronic equipment and computer-readable medium |
| CN108648023A (en) * | 2018-05-18 | 2018-10-12 | 上海电机学院 | A kind of businessman's passenger flow forecast method of fusion history mean value and boosted tree |
| CN110598906A (en) * | 2019-08-15 | 2019-12-20 | 珠海米枣智能科技有限公司 | Method and system for controlling energy consumption of superstores in real time based on deep reinforcement learning |
| CN110472892A (en) * | 2019-08-27 | 2019-11-19 | 上海电气分布式能源科技有限公司 | Build flow of the people, cool and thermal power load evaluation method and system, equipment and medium |
| CN113793010A (en) * | 2021-09-07 | 2021-12-14 | 国网浙江省电力有限公司营销服务中心 | Construction method for multi-load combined control strategy and air conditioner control method |
| CN114611624A (en) * | 2022-03-22 | 2022-06-10 | 广东贤能数字科技有限公司 | Artificial intelligence-based business activity evaluation system and method for shops or business halls |
| CN115550392A (en) * | 2022-04-29 | 2022-12-30 | 深圳云谷星辰信息技术有限公司 | Intelligent park digital twin platform system |
| CN115345355A (en) * | 2022-08-02 | 2022-11-15 | 北京百度网讯科技有限公司 | Energy consumption prediction model construction method, short-term energy consumption prediction method and related device |
| CN115470707A (en) * | 2022-09-22 | 2022-12-13 | 上海时氪信息技术有限公司 | City scene simulation system |
| CN115860790A (en) * | 2022-11-11 | 2023-03-28 | 深圳海智创科技有限公司 | Method for predicting place passenger flow, method and device for training model |
| CN116029395A (en) * | 2023-03-24 | 2023-04-28 | 深圳市明源云科技有限公司 | Pedestrian flow early warning method and device for business area, electronic equipment and storage medium |
Non-Patent Citations (3)
| Title |
|---|
| 大型超市运营管理节能研究;邓翔;《中国优秀硕士学位论文全文数据库 (工程科技Ⅱ辑)》;20140331;C038-3 * |
| 李梅香等.商场建筑运行能耗实测数据修复方法研究.《建筑节能》.第49卷(第363期),第37-45页. * |
| 长沙市某大型超市中央空调系统运行分析及节能潜力研究;南赟;《中国优秀硕士学位论文全文数据库 (工程科技Ⅱ辑)》;20170331;C038-2154 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117557300A (en) | 2024-02-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110097297B (en) | Multi-dimensional electricity stealing situation intelligent sensing method, system, equipment and medium | |
| CN104036357B (en) | The analysis method of user power utilization electricity stealing pattern | |
| CN109376924A (en) | A kind of method, apparatus, equipment and the readable storage medium storing program for executing of material requirements prediction | |
| CN103440283B (en) | The deficiency system of a kind of measuring point data and method of filling a vacancy | |
| CN113872813B (en) | Full life cycle management method and system for carrier communication equipment | |
| CN110489783B (en) | QNNN-based low-voltage transformer area line loss rate reasonable range estimation method | |
| CN114004296A (en) | Method and system for reversely extracting monitoring points based on power load characteristics | |
| CN111738462A (en) | Fault first-aid repair active service early warning method for electric power metering device | |
| CN102567412A (en) | Method for processing computer-assisted network load analysis information | |
| CN103020459A (en) | Method and system for sensing multiple-dimension electric utilization activities | |
| CN114240086A (en) | Carbon emission monitoring method and device, storage medium and processor | |
| CN113487447A (en) | Power distribution network load prediction and line loss cause analysis method based on big data | |
| CN113554361B (en) | Comprehensive energy system data processing and calculating method and processing system | |
| CN111027741A (en) | Method for constructing space-time dimension-oriented generalized load model analysis library | |
| CN115392735A (en) | Method, system, equipment and medium for monitoring working performance of photovoltaic power station | |
| CN108921425A (en) | A kind of method, system and the server of asset item classifcation of investment | |
| CN113450031B (en) | Method and device for selecting intelligent energy consumption service potential transformer area of residents | |
| CN117057666B (en) | Distribution quality evaluation method and system for digital distribution network | |
| CN108154259B (en) | Load prediction method and device for heat pump, storage medium, and processor | |
| CN113516192A (en) | Method, system, device and storage medium for identifying user electricity consumption transaction | |
| CN117557300B (en) | Method and system for deducing business liveness based on energy consumption data of main equipment | |
| CN115905319B (en) | Automatic identification method and system for abnormal electricity fees of massive users | |
| CN117273456A (en) | Project cost intelligent management system based on big data technology | |
| CN107248036A (en) | A kind of intelligent credit rating method and apparatus | |
| CN115063046A (en) | Power grid material supplier intelligent cockpit system based on big data analysis |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |