Waterscape configuration method and device, equipment and storage medium

Abstract

The invention discloses a waterscape configuration method and device, equipment and a storage medium, and relates to the field of electric digital data processing, and the method carries out the interval division of the full-time passenger flow volume of a landscape, enables a corresponding function at the corresponding passenger flow volume, does not need to be opened and closed manually or according to a formulated plan, and improves the operation efficiency. In order to achieve the aim of relying on the real-time passenger flow volume, a prediction technical means is further used for predicting the upcoming passenger flow volume or the real-time passenger flow volume, and compared with the prior art, waterscape control can obviously improve the utilization efficiency of crystals; and meanwhile, subjective errors and mistakes caused by manual opening and closing are avoided.

Description

Technical Field

[0001] The present application relates to the technical field of electronic digital data processing, and in particular to a method, device, equipment and storage medium for configuring a waterscape. Background Art

[0002] As a unique cultural landscape, waterscape can largely solve the decoration problems of large spaces such as parks, squares, and large buildings. In order to cater to the overall design concept, many designers have put forward higher requirements on the expression methods of waterscape.

[0003] As for waterscape, it can be divided into three forms from the perspective of visual perception: static water, dynamic water, and pressurized water. Static waterscape can reflect the surrounding scenery and highlight the design concept of peace and tranquility, while dynamic waterscape has a variety of forms, adding vitality and beauty to the indoor environment, and pressurized water can bring strong tension and momentum. Among them, static water, such as lakes, ponds, transparent cylinders, etc., are characterized by tranquility, peace, and brightness, and are mainly used to purify the environment, divide space, and enrich the color of the environment; dynamic water, such as streams, waterfalls, and wall falls, produces dynamic beauty through flow effects, and pressurized water, such as fountains, increases the water flow speed through the nozzle to make the water produce a splashing effect, showing strong tension and momentum.

[0004] At present, mainstream waterscapes usually adopt the combined use of static water, dynamic water and pressurized water, so that the waterscape has two or three functions of static water, dynamic water and pressurized water at the same time to further enhance the viewing experience. Since dynamic water and pressurized water require the use of electricity to transport water and provide power for water, and are also embellished with lights, the waterscape with the above-mentioned composite functions consumes significantly more electricity and water than waterscape with a single function. At present, the control of waterscapes that meet the functions is usually to start and close some or all functions at a scheduled time in the central control room, or to start and close them manually, so that the waterscape may not be turned on when the passenger flow is high, and may be continuously turned on when the passenger flow is low, or may be manually forgotten to be turned on or manually forgotten to be closed, resulting in low utilization efficiency of the waterscape and easy waste of water and electricity when the passenger flow is low. Summary of the invention

[0005] The main purpose of the present application is to provide a method, device, equipment and storage medium for configuring a waterscape, so as to solve the problem of low utilization efficiency of waterscape in the prior art.

[0006] To achieve the above objectives, this application provides the following technical solutions:

[0007] A method for configuring a water-using landscape, wherein the water landscape includes a landscape having at least two water-using functions, and the configuration method includes:

[0008] Step S1, obtaining the historical minimum passenger flow and the historical maximum passenger flow of the landscape;

[0009] Step S2, dividing the interval between the historical lowest passenger flow and the historical highest passenger flow into three consecutive sub-intervals in ascending order of value;

[0010] Step S3, respectively obtaining the historical occurrence time period of each sub-interval;

[0011] Step S4, learning and training the historical occurrence time period of each sub-interval through a machine learning machine, and obtaining an occurrence time period prediction model after completing the training;

[0012] Step S5, predicting the future occurrence time period of each sub-interval based on a preset natural day step number by using the occurrence time period prediction model;

[0013] Step S6, defining three consecutive sub-intervals as a low flow interval, a medium flow interval, and a high flow interval in sequence;

[0014] Step S7, turning on the lighting function of the landscape in the future time period of the low traffic interval;

[0015] Step S8, turning on the lighting function and the water function of the landscape in the future time period of the medium flow interval;

[0016] Step S9, turning on the lighting function, water movement function, and water pressure function of the landscape during the future time period of the high flow interval.

[0017] As a further improvement of the present application, step S4, learning and training the historical occurrence time period of each sub-interval by a machine learning machine, and obtaining an occurrence time period prediction model after completing the training, includes:

[0018] Step S41, obtaining several historical occurrence time periods of each sub-interval based on a preset time period;

[0019] Step S42, packing all historical occurrence time periods of the same sub-interval into a data set;

[0020] Step S43, performing standard normalization on the data set of the current sub-interval to obtain a normalized data set;

[0021] Step S44, dividing the normalized data set of the current sub-interval into a training set and a validation set according to a preset ratio;

[0022] Step S45, defining a neural network model having an input layer, a hidden layer, and an output layer that are sequentially signal-connected;

[0023] Step S46, outputting the training set of the current sub-interval to the input layer, and performing a preset number of trainings through the neural network model;

[0024] Step S47, obtaining a root mean square error between the verification set and the current training result based on each training;

[0025] Step S48, obtaining the minimum value of the root mean square error among all training results, and obtaining the training result corresponding to the minimum value as the occurrence time period prediction model of the current sub-interval.

[0026] As a further improvement of the present application, step S43, standard normalization is performed on the data set of the current sub-interval to obtain a normalized data set, including:

[0027] Step S431, obtaining the historical start time and the historical end time of each historical occurrence time period in the current sub-interval;

[0028] Step S432, converting the historical start time of the current historical occurrence time period into the historical start seconds;

[0029] Step S433, converting the historical end time of the current historical occurrence time period into the historical end seconds;

[0030] Step S434, standardize the historical start seconds and the historical end seconds of the current historical occurrence time period respectively by formula (1):

[0031]

[0032] Among them, t j ' ,start is the normalized historical starting data obtained by normalizing the jth historical starting second of the current historical time period, t j,start is the jth historical starting second of the current historical time period, is the average of all historical starting seconds in the current historical period, δ start is the standard deviation of all historical starting seconds in the current historical period, t j ' ,end The normalized historical end data obtained by normalizing the j-th historical end seconds of the current historical time period, t j,end is the jth historical end second of the current historical time period, is the average of all historical end seconds in the current historical period, δ end It is the standard deviation of all historical end seconds in the current historical period.

[0033] As a further improvement of the present application, the neural network model is characterized by formula (2):

[0034]

[0035] Wherein, y is the neural network model; x n is the nth input node of the input layer, each input node corresponds to a normalized data set in the training set, is the weight from the mth input node of the input layer to the nth input node of the hidden layer; is the bias of the nth input node connected to the hidden layer; is the bias of the output layer; tanh(·) is the activation function; the numbers in the brackets of the symbol subscripts are the number of layers, the subscript (1) is the first layer, that is, the input layer, the subscript (1, 2) is the first layer to the second layer, that is, the input layer to the hidden layer, and the subscript (3) is the third layer, that is, the output layer.

[0036] As a further improvement of the present application, step S5, predicting the future occurrence time period of each sub-interval based on a preset natural day step number through the occurrence time period prediction model, includes:

[0037] Step S51, calculating the normalized future start data and the normalized future end data based on the preset natural day step number through the occurrence time period prediction model;

[0038] Step S52, substituting the normalized future start data and the normalized future end data into formula (1) to obtain the future start seconds and the future end seconds based on the preset natural day step number;

[0039] Step S53, converting the future start seconds and the future end seconds into the future start time and the future end time respectively;

[0040] Step S54, defining the duration from the future start time to the future end time as the future occurrence time period.

[0041] As a further improvement of the present application, step S8, in which the lighting function and the water function of the landscape are turned on in the future time period of the medium flow interval, includes:

[0042] Step S10, when the future time period begins to occur, counting the power consumption of the light source of the lighting function, the power consumption of the moving water function and the water consumption;

[0043] Step S20, sending the light source power consumption, the dynamic water power consumption, and the water consumption to an external monitoring terminal.

[0044] As a further improvement of the present application, step S9, in which the lighting function, the water movement function, and the water pressure function of the landscape are turned on in the future time period of the high flow interval, then includes:

[0045] Step S100, when the future occurrence time period begins to occur, counting the light source power consumption of the lighting function, the dynamic water power consumption of the dynamic water function, the pressure water power consumption of the pressure water function, and the total water consumption of the dynamic water function and the pressure water function;

[0046] Step S200, sending the light source power consumption, the dynamic water power consumption, the pressurized water power consumption, and the total water consumption to an external monitoring terminal.

[0047] To achieve the above objectives, this application also provides the following technical solutions:

[0048] A waterscape configuration device, the configuration device is applied to the configuration method as described above, the configuration device comprises:

[0049] A landscape passenger flow acquisition module, used to acquire the historical minimum passenger flow and the historical maximum passenger flow of the landscape;

[0050] A passenger flow interval division module, used to divide the interval between the historical lowest passenger flow and the historical highest passenger flow into three continuous sub-intervals in ascending order of value;

[0051] A historical occurrence time period acquisition module is used to respectively acquire the historical occurrence time period of each sub-interval;

[0052] An occurrence time period prediction model acquisition module is used to learn and train the historical occurrence time period of each sub-interval through a machine learning machine, and obtain an occurrence time period prediction model after completing the training;

[0053] A future occurrence time period acquisition module, used for predicting the future occurrence time period of each sub-interval based on a preset natural day step number through the occurrence time period prediction model;

[0054] A passenger flow sub-interval definition module is used to define three consecutive sub-intervals as a low flow interval, a medium flow interval, and a high flow interval in sequence;

[0055] A low passenger flow landscape control module is used to turn on the lighting function of the landscape during a future period of low passenger flow;

[0056] A medium passenger flow landscape control module, used to activate the lighting function and water function of the landscape in the future time period of the medium flow interval;

[0057] The high passenger flow landscape control module is used to activate the lighting function, water movement function and water pressure function of the landscape during the future time period of the high passenger flow interval.

[0058] To achieve the above objectives, this application also provides the following technical solutions:

[0059] An electronic device comprises a processor and a memory coupled to the processor, wherein the memory stores program instructions executable by the processor; when the processor executes the program instructions stored in the memory, the configuration method as described above is implemented.

[0060] To achieve the above objectives, this application also provides the following technical solutions:

[0061] A storage medium stores program instructions, and when the program instructions are executed by a processor, the above configuration method can be implemented.

[0062] The present application obtains the historical minimum passenger flow and the historical maximum passenger flow of the landscape; divides the interval between the historical minimum passenger flow and the historical maximum passenger flow into three consecutive sub-intervals in ascending order; obtains the historical occurrence time period of each sub-interval respectively; learns and trains the historical occurrence time period of each sub-interval through a machine learning machine, and obtains an occurrence time period prediction model after the training is completed; predicts the future occurrence time period of each sub-interval based on a preset natural daily step number through the occurrence time period prediction model; defines the three consecutive sub-intervals as a low-flow interval, a medium-flow interval, and a high-flow interval in turn; turns on the lighting function of the landscape in the future occurrence time period of the low-flow interval; turns on the lighting function and the water movement function of the landscape in the future occurrence time period of the medium-flow interval; turns on the lighting function, the water movement function, and the water pressure function of the landscape in the future occurrence time period of the high-flow interval. The present application divides the full-time passenger flow of the landscape into intervals and activates corresponding functions at corresponding passenger flows. There is no need for manual opening and closing or opening and closing according to a plan, so that the landscape can be opened and closed based on real-time passenger flow. In order to rely on real-time passenger flow, the present application also uses prediction technology to predict the upcoming passenger flow or real-time passenger flow. Compared with the prior art, the waterscape control of the present application can significantly improve the utilization efficiency of crystals, while also avoiding subjective errors and mistakes caused by manual opening and closing. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 A schematic diagram of the steps of an embodiment of a method for configuring a waterscape of the present application;

[0064] Figure 2 This is a functional module diagram of an embodiment of a waterscape configuration device of the present application;

[0065] Figure 3 This is a schematic diagram of the structure of an embodiment of the electronic device of the present application;

[0066] Figure 4 This is a schematic diagram of the structure of an embodiment of the storage medium of the present application. DETAILED DESCRIPTION

[0067] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0068] The terms "first", "second" and "third" in this application are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features. Thus, the features defined as "first", "second" and "third" can explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "multiple" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined. All directional indications in the embodiments of the present application (such as up, down, left, right, front, back...) are only used to explain the relative position relationship, movement, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication also changes accordingly. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally also includes steps or units that are not listed, or optionally also includes other steps or units inherent to these processes, methods, products or devices.

[0069] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0070] like Figure 1 As shown, this embodiment provides an embodiment of a method for configuring a waterscape. In this embodiment, the waterscape includes a landscape with at least two water-using functions.

[0071] Preferably, the landscape of this embodiment includes at least two functions of still water function, dynamic water function and pressure water function. For the convenience of subsequent description, the landscape of this embodiment includes still water function, dynamic water function and pressure water function at the same time.

[0072] It is worth noting that the landscape with static water function, dynamic water function and pressure water function is a mature existing technology. The landscape in this embodiment is a conventional application of the aforementioned existing technology and no structural improvement has been made to the existing technology. This embodiment will no longer repeat the detailed structure of the aforementioned landscape.

[0073] Specifically, the configuration method includes the following steps:

[0074] Step S1, obtaining the historical minimum passenger flow and the historical maximum passenger flow of the landscape.

[0075] Preferably, the historical lowest passenger flow and the historical highest passenger flow of the landscape in at least one natural year in the past may be used as selection criteria.

[0076] Step S2: divide the interval between the historical lowest passenger flow and the historical highest passenger flow into three consecutive sub-intervals in ascending order of value.

[0077] Preferably, the three consecutive sub-intervals are the low flow interval, the medium flow interval, and the high flow interval in step S6.

[0078] Step S3, respectively obtain the historical occurrence time period of each sub-interval.

[0079] To give a non-limiting example, the fluctuation range of several historical time periods of the high-flow interval is between 8:00 p.m. and 10:00 p.m. on weekdays and between 1:00 p.m. and 10:00 p.m. on holidays; the fluctuation range of several historical time periods of the medium-flow interval is between 5:00 p.m. and 7:00 p.m. on weekdays and between 10:00 a.m. and noon on holidays; the fluctuation range of the low-flow interval is within the rest of the time of the high-flow interval and the medium-flow interval.

[0080] It can be seen that a time period has a starting time point and an ending time point, and the numbers correspond one to one. The specific training process of this embodiment will be carried out with the time points as training data.

[0081] Step S4, learning and training the historical occurrence time period of each sub-interval through a machine learning machine, and obtaining an occurrence time period prediction model after completing the training.

[0082] Step S5, predicting the future occurrence time period of each sub-interval based on the preset natural daily step number through the occurrence time period prediction model.

[0083] Preferably, the preset natural day step count can be set to one natural day.

[0084] Step S6, defining three consecutive sub-intervals as a low flow interval, a medium flow interval, and a high flow interval in sequence.

[0085] Step S7, turning on the landscape lighting function during the future low traffic interval.

[0086] Step S8, turning on the lighting function and water function of the landscape in the future time period of the medium flow interval.

[0087] Step S9, turning on the lighting function, water movement function, and water pressure function of the landscape during the future time period of the high flow interval.

[0088] Furthermore, in step S4, the historical occurrence time period of each sub-interval is learned and trained by a machine learning machine, and an occurrence time period prediction model is obtained after the training is completed, including:

[0089] Step S41, obtaining a plurality of historical occurrence time periods of each sub-interval based on a preset time period.

[0090] Preferably, the preset time period can be set in the same manner as the preset number of steps per natural day, such as one natural day.

[0091] Step S42: Pack all historical occurrence time periods of the same sub-interval into one data set.

[0092] Step S43, performing standard normalization on the data set of the current sub-interval to obtain a normalized data set.

[0093] Preferably, the standard normalization of this embodiment is zero-mean normalization (Z-score normalization), which gives the mean and standard deviation of the original data to standardize the data, and the processed data conforms to the standard normal distribution, that is, the mean is 0 and the standard deviation is 1. For the normalization method, this embodiment can also use batch normalization. Compared with simple normalization, in the previous neural network training, only the input layer data is normalized, but not in the middle layer. Although the data set of the input node is normalized, the data distribution of the input data after matrix multiplication is likely to change greatly, and as the number of hidden layer network layers continues to deepen, the change in data distribution will become greater and greater. Therefore, the normalization processing performed by batch normalization in the middle layer of the neural network makes the training effect better.

[0094] Step S44, dividing the normalized data set of the current sub-interval into a training set and a validation set according to a preset ratio.

[0095] Preferably, the preset ratio is usually 80%:20% to divide the image data into a training set and a validation set, that is, 80% of the data is the training set and 20% of the data is the validation set.

[0096] Step S45, defining a neural network model having an input layer, a hidden layer, and an output layer that are sequentially signal-connected.

[0097] Step S46, outputting the training set of the current sub-interval to the input layer, and performing a preset number of trainings through the neural network model.

[0098] Step S47, based on each training, obtain the root mean square error between the verification set and the current training result.

[0099] Step S48, obtaining the minimum value of the root mean square error among all training results, and obtaining the training result corresponding to the minimum value as the occurrence time period prediction model of the current sub-interval.

[0100] Furthermore, in step S43, the data set of the current sub-interval is subjected to standard normalization to obtain a normalized data set, including:

[0101] Step S431, obtaining the historical start time and the historical end time of each historical occurrence time period in the current sub-interval.

[0102] Step S432, converting the historical start time of the current historical occurrence time period into the historical start seconds.

[0103] For example, the time of 8 a.m. on that day converted into seconds is 8×60×60=28800 seconds, which is the 28800th second of the day, and the same applies below.

[0104] Step S433, convert the historical end time of the current historical occurrence time period into historical end seconds.

[0105] Step S434, standardize the historical start seconds and the historical end seconds of the current historical occurrence time period respectively by formula (1):

[0106]

[0107] Among them, t j ' ,start is the normalized historical starting data obtained by normalizing the jth historical starting second of the current historical time period, t j,start is the jth historical starting second of the current historical time period, is the average of all historical starting seconds in the current historical period, δ start is the standard deviation of all historical starting seconds in the current historical period, t j ' ,end The normalized historical end data obtained by normalizing the j-th historical end seconds of the current historical time period, t j,end is the jth historical end second of the current historical time period, is the average of all historical end seconds in the current historical period, δ end It is the standard deviation of all historical end seconds in the current historical period.

[0108] Furthermore, the neural network model is represented by formula (2):

[0109]

[0110] Among them, y is the neural network model; x n is the nth input node of the input layer, each input node corresponds to a normalized data set in the training set, is the weight from the mth input node of the input layer to the nth input node of the hidden layer; is the bias of the nth input node connected to the hidden layer; is the bias of the output layer; tanh(·) is the activation function; the numbers in the brackets of the symbol subscripts are the number of layers, the subscript (1) is the first layer, that is, the input layer, the subscript (1, 2) is the first layer to the second layer, that is, the input layer to the hidden layer, and the subscript (3) is the third layer, that is, the output layer.

[0111] Preferably, training model training a neural network usually requires providing a large amount of data, namely a data set; the data set is generally divided into three categories, namely the above-mentioned training set, validation set and test set.

[0112] Among them, one epoch is the process of training once with all the samples in the training set. The so-called training once refers to one forward pass and one back pass. When the number of samples in an epoch (i.e., training set) is too large, training once may consume too much time, and it is not necessary to use all the data in the training set for each training. In this case, the entire training set needs to be divided into multiple small blocks, that is, divided into multiple batches for training. An epoch consists of one or more batches, where a batch is a part of the training set. Each training process only uses a part of the data, i.e., a batch. The process of training a batch is an iteration.

[0113] Preferably, the neural network training specifically includes a perceptron, which is composed of two layers of neurons. The input layer receives external input signals and transmits them to the output layer. The output layer is MP neurons, and the step function is y=f(∑w·x-β).

[0114] Preferably, given a training data set, the weight w and the training bias β can be obtained by learning, and β can be understood as a fixed value with an input of -1,0.

[0115] It should be noted that the above formula is not interchangeable with the symbolic meaning of other formulas in the embodiment, and this step function is only used for principle explanation and does not participate in the calculation of other formulas.

[0116] Preferably, in this embodiment, the number of neural network training times can be set to 1000 times.

[0117] Preferably, the learning rate from the 1st to the 500th epoch can be set to 0.01, the learning rate from the 501st to the 750th epoch can be set to 0.001, and the learning rate from the 751st to the 1000th epoch can be set to 0.0001.

[0118] It can be understood that the neural network training of this embodiment mainly includes the following ideas:

[0119] ① Initialize the weights and bias items in the network.

[0120] Initializing parameter values ​​(output unit weights, bias terms and hidden unit weights, bias terms are all model parameters) is to activate forward propagation, obtain the output value of each layer element, and then obtain the value of the loss function.

[0121] ②Activate forward propagation to obtain the output value of each layer and the expected value of the loss function of each layer.

[0122] ③According to the loss function, calculate the error term of the output unit and the error term of the hidden unit.

[0123] Calculate various errors, calculate the gradient of the parameters with respect to the loss function, or calculate partial derivatives according to the chain rule of calculus. For partial derivatives of vectors or matrices in a composite function, the partial derivative of the function inside the composite function is always multiplied on the left; for partial derivatives of scalars in a composite function, the partial derivative of the function inside the composite function can be multiplied on the left or on the right.

[0124] ④Update the weights and bias items in the neural network.

[0125] ⑤ Repeat ② to ④ until the loss function is less than the preset bias or the number of iterations is used up, and the parameters output at this time are the current optimal parameters.

[0126] Furthermore, step S5 predicts the future occurrence time period of each sub-interval based on the preset natural day step number through the occurrence time period prediction model, including:

[0127] Step S51, obtaining normalized future start data and normalized future end data based on a preset natural day step number through calculation using an occurrence time period prediction model.

[0128] Step S52, substituting the normalized future start data and the normalized future end data into formula (1) to obtain the future start seconds and the future end seconds based on the preset natural day step number.

[0129] Preferably, at this time, the left side of equation (1) becomes a known quantity, and the true value becomes an unknown quantity.

[0130] Step S53, converting the future start seconds and the future end seconds into the future start time and the future end time respectively.

[0131] Step S54, defining the duration from the future start time to the future end time as the future occurrence time period.

[0132] Further, step S8, turning on the lighting function and water function of the landscape in the future time period of the medium flow interval, and then including:

[0133] Step S10, when the future time period begins to occur, counting the light source power consumption of the lighting function, the moving water power consumption and the water consumption of the moving water function.

[0134] Step S20, sending the light source power consumption, dynamic water power consumption, and water consumption to an external monitoring terminal.

[0135] Further, step S9, in the future occurrence time period of the high flow interval, the lighting function, the water movement function, and the water pressure function of the landscape are turned on, and then, the following steps are included:

[0136] Step S100, when the future time period begins, count the light source power consumption of the lighting function, the dynamic water power consumption of the dynamic water function, the pressure water power consumption of the pressure water function, and the total water consumption of the dynamic water function and the pressure water function.

[0137] Step S200, sending the light source power consumption, dynamic water power consumption, pressurized water power consumption, and total water consumption to an external monitoring terminal.

[0138] Preferably, the design intention of step S10 to step S20 and step S100 to step S200 is to monitor whether the water feature has any faults, such as water outage, power outage, short circuit, etc.

[0139] This embodiment obtains the historical minimum passenger flow and the historical maximum passenger flow of the landscape; divides the interval between the historical minimum passenger flow and the historical maximum passenger flow into three consecutive sub-intervals in ascending order; obtains the historical occurrence time period of each sub-interval respectively; learns and trains the historical occurrence time period of each sub-interval through a machine learning machine, and obtains an occurrence time period prediction model after the training is completed; predicts the future occurrence time period of each sub-interval based on a preset natural daily step number through the occurrence time period prediction model; defines the three consecutive sub-intervals as a low-flow interval, a medium-flow interval, and a high-flow interval in turn; turns on the lighting function of the landscape in the future occurrence time period of the low-flow interval; turns on the lighting function and the water movement function of the landscape in the future occurrence time period of the medium-flow interval; turns on the lighting function, the water movement function, and the water pressure function of the landscape in the future occurrence time period of the high-flow interval. This embodiment divides the full-time passenger flow of the landscape into intervals and activates corresponding functions at corresponding passenger flows. There is no need for manual opening and closing or opening and closing according to a plan, so that the landscape can be opened and closed based on real-time passenger flow. In order to rely on real-time passenger flow, this embodiment also uses prediction technology to predict the upcoming passenger flow or real-time passenger flow. Compared with the prior art, the waterscape control of this embodiment can significantly improve the utilization efficiency of crystals, while also avoiding subjective errors and mistakes caused by manual opening and closing.

[0140] like Figure 2 As shown, this embodiment provides an embodiment of a waterscape configuration device. In this embodiment, the configuration device is applied to the configuration method in the above embodiment.

[0141] Specifically, the configuration device includes a landscape passenger flow acquisition module 1, a passenger flow interval division module 2, a historical occurrence time period acquisition module 3, an occurrence time period prediction model acquisition module 4, a future occurrence time period acquisition module 5, a passenger flow sub-interval definition module 6, a low passenger flow landscape control module 7, a medium passenger flow landscape control module 8, and a high passenger flow landscape control module 9, which are electrically connected in sequence.

[0142] Among them, the landscape passenger flow acquisition module 1 is used to obtain the historical minimum passenger flow and the historical maximum passenger flow of the landscape; the passenger flow interval division module 2 is used to divide the interval between the historical minimum passenger flow and the historical maximum passenger flow into three continuous sub-intervals in ascending order; the historical occurrence time period acquisition module 3 is used to obtain the historical occurrence time period of each sub-interval respectively; the occurrence time period prediction model acquisition module 4 is used to learn and train the historical occurrence time period of each sub-interval through a machine learning machine, and obtain the occurrence time period prediction model after the training is completed; the future occurrence time period acquisition module 5 is used to predict the future occurrence time period of each sub-interval based on the preset natural day step number through the occurrence time period prediction model; the passenger flow sub-interval definition module 6 is used to define three continuous sub-intervals as a low flow interval, a medium flow interval, and a high flow interval in turn; the low passenger flow landscape control module 7 is used to turn on the landscape lighting function in the future occurrence time period of the low flow interval; the medium passenger flow landscape control module 8 is used to turn on the landscape lighting function and water movement function in the future occurrence time period of the medium flow interval; the high passenger flow landscape control module 9 is used to turn on the landscape lighting function, water movement function, and water pressure function in the future occurrence time period of the high flow interval.

[0143] Furthermore, the occurrence time period prediction model acquisition module 4 specifically includes a first occurrence time period prediction model acquisition submodule, a second occurrence time period prediction model acquisition submodule, a third occurrence time period prediction model acquisition submodule, a fourth occurrence time period prediction model acquisition submodule, a fifth occurrence time period prediction model acquisition submodule, a sixth occurrence time period prediction model acquisition submodule, a seventh occurrence time period prediction model acquisition submodule, and an eighth occurrence time period prediction model acquisition submodule, which are electrically connected in sequence; the first occurrence time period prediction model acquisition submodule is electrically connected to the historical occurrence time period acquisition module 3, and the eighth occurrence time period prediction model acquisition submodule is electrically connected to the future occurrence time period acquisition module 5.

[0144] Among them, the first occurrence time period prediction model acquisition submodule is used to obtain several historical occurrence time periods of each sub-interval based on a preset time period; the second occurrence time period prediction model acquisition submodule is used to package all historical occurrence time periods of the same sub-interval into a data set; the third occurrence time period prediction model acquisition submodule is used to perform standard normalization on the data set of the current sub-interval to obtain a normalized data set; the fourth occurrence time period prediction model acquisition submodule is used to divide the normalized data set of the current sub-interval into a training set and a verification set according to a preset ratio; the fifth occurrence time period prediction model acquisition submodule is used to define a neural network model having an input layer, a hidden layer, and an output layer that are signal-connected in sequence; the sixth occurrence time period prediction model acquisition submodule is used to output the training set of the current sub-interval to the input layer, and perform a preset number of trainings through the neural network model; the seventh occurrence time period prediction model acquisition submodule is used to obtain the root mean square error between the verification set and the current training result based on each training; the eighth occurrence time period prediction model acquisition submodule is used to obtain the minimum value of the root mean square error among all training results, and obtain the training result corresponding to the minimum value as the occurrence time period prediction model of the current sub-interval.

[0145] Furthermore, the third occurrence time period prediction model acquisition submodule specifically includes a first occurrence time period prediction model acquisition unit, a second occurrence time period prediction model acquisition unit, a third occurrence time period prediction model acquisition unit, and a fourth occurrence time period prediction model acquisition unit, which are electrically connected in sequence; the first occurrence time period prediction model acquisition unit is electrically connected to the second occurrence time period prediction model acquisition submodule, and the fourth occurrence time period prediction model acquisition unit is electrically connected to the fourth occurrence time period prediction model acquisition submodule.

[0146] The first occurrence time period prediction model acquisition unit is used to acquire the historical start time and the historical end time of each historical occurrence time period in the current sub-interval.

[0147] The second occurrence time period prediction model acquisition unit is used to convert the historical start time of the current historical occurrence time period into the historical start seconds.

[0148] The third occurrence time period prediction model acquisition unit is used to convert the historical end time of the current historical occurrence time period into the historical end seconds.

[0149] The fourth occurrence time period prediction model acquisition unit is used to standardize the historical start seconds and the historical end seconds of the current historical occurrence time period respectively by formula (1):

[0150]

[0151] Among them, t j ' ,startis the normalized historical starting data obtained by normalizing the jth historical starting second of the current historical time period, t j,start is the jth historical starting second of the current historical time period, is the average of all historical starting seconds in the current historical period, δ start is the standard deviation of all historical starting seconds in the current historical period, t j ' ,end The normalized historical end data obtained by normalizing the j-th historical end seconds of the current historical time period, t j,end is the jth historical end second of the current historical time period, is the average of all historical end seconds in the current historical period, δ end It is the standard deviation of all historical end seconds in the current historical period.

[0152] Furthermore, the fifth occurrence time period prediction model acquisition submodule is a neural network model represented by formula (2):

[0153]

[0154] Among them, y is the neural network model; x n is the nth input node of the input layer, each input node corresponds to a normalized data set in the training set, is the weight from the mth input node of the input layer to the nth input node of the hidden layer; is the bias of the nth input node connected to the hidden layer; is the bias of the output layer; tanh(·) is the activation function; the numbers in the brackets of the symbol subscripts are the number of layers, the subscript (1) is the first layer, that is, the input layer, the subscript (1, 2) is the first layer to the second layer, that is, the input layer to the hidden layer, and the subscript (3) is the third layer, that is, the output layer.

[0155] Furthermore, the future occurrence time period acquisition module 5 includes a first future occurrence time period acquisition sub-module, a second future occurrence time period acquisition sub-module, a third future occurrence time period acquisition sub-module, and a fourth future occurrence time period acquisition sub-module, which are electrically connected in sequence; the first future occurrence time period acquisition sub-module is electrically connected to the occurrence time period prediction model acquisition module 4, and the fourth future occurrence time period acquisition sub-module is electrically connected to the passenger flow sub-interval definition module 6.

[0156] Among them, the first future occurrence time period acquisition submodule is used to calculate the normalized future start data and the normalized future end data based on the preset natural day step number through the occurrence time period prediction model; the second future occurrence time period acquisition submodule is used to substitute the normalized future start data and the normalized future end data into formula (1) to obtain the future start seconds and the future end seconds based on the preset natural day step number; the third future occurrence time period acquisition submodule is used to convert the future start seconds and the future end seconds into the future start time and the future end time respectively; the fourth future occurrence time period acquisition submodule is used to define the time from the future start time to the future end time as the future occurrence time period.

[0157] Furthermore, the configuration device also includes a first consumption statistics module and a first consumption sending module which are electrically connected in sequence, and the first consumption statistics module is electrically connected to the passenger flow landscape control module 8.

[0158] Among them, the first consumption statistics module is used to count the light source power consumption of the lighting function, the moving water power consumption of the moving water function and the water consumption when the future time period begins; the first consumption sending module is used to send the light source power consumption, moving water power consumption and water consumption to the external monitoring end.

[0159] Furthermore, the configuration device also includes a second consumption statistics module and a second consumption sending module which are electrically connected in sequence; the second consumption statistics module is electrically connected to the high passenger flow landscape control module 9.

[0160] Among them, the second consumption statistics module is used to count the light source power consumption of the lighting function, the dynamic water consumption of the dynamic water function, the water pressure consumption of the water pressure function, and the total water consumption of the dynamic water function and the water pressure function when the future time period begins; the second consumption sending module is used to send the light source power consumption, dynamic water consumption, water pressure consumption, and total water consumption to the external monitoring end.

[0161] It should be noted that this embodiment is a functional module embodiment based on the above method embodiment. The optimization, expansion, limitation, example, and principle description of this embodiment can be referred to the above embodiment, and this embodiment will not be repeated.

[0162] This embodiment obtains the historical minimum passenger flow and the historical maximum passenger flow of the landscape; divides the interval between the historical minimum passenger flow and the historical maximum passenger flow into three consecutive sub-intervals in ascending order; obtains the historical occurrence time period of each sub-interval respectively; learns and trains the historical occurrence time period of each sub-interval through a machine learning machine, and obtains an occurrence time period prediction model after the training is completed; predicts the future occurrence time period of each sub-interval based on a preset natural daily step number through the occurrence time period prediction model; defines the three consecutive sub-intervals as a low-flow interval, a medium-flow interval, and a high-flow interval in turn; turns on the lighting function of the landscape in the future occurrence time period of the low-flow interval; turns on the lighting function and the water movement function of the landscape in the future occurrence time period of the medium-flow interval; turns on the lighting function, the water movement function, and the water pressure function of the landscape in the future occurrence time period of the high-flow interval. This embodiment divides the full-time passenger flow of the landscape into intervals and activates corresponding functions at corresponding passenger flows. There is no need for manual opening and closing or opening and closing according to a plan, so that the landscape can be opened and closed based on real-time passenger flow. In order to rely on real-time passenger flow, this embodiment also uses prediction technology to predict the upcoming passenger flow or real-time passenger flow. Compared with the prior art, the waterscape control of this embodiment can significantly improve the utilization efficiency of crystals, while also avoiding subjective errors and mistakes caused by manual opening and closing.

[0163] Figure 3 Schematic diagram of the structure of an electronic device according to an embodiment of the present application. Figure 3 As shown, the electronic device 10 includes a processor 101 and a memory 102 coupled to the processor 101 .

[0164] The memory 102 stores program instructions for implementing a method for configuring a waterscape in any of the above embodiments.

[0165] The processor 101 is used to execute program instructions stored in the memory 102 to configure the water landscape.

[0166] The processor 101 may also be referred to as a CPU (Central Processing Unit). The processor 101 may be an integrated circuit chip having a signal processing capability. The processor 101 may also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0167] Further, Figure 4 This is a schematic diagram of the structure of a storage medium according to an embodiment of the present application. Figure 4 The storage medium 11 of the embodiment of the present application stores program instructions 111 that can implement all the above methods, wherein the program instructions 111 can be stored in the above storage medium in the form of a software product, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) or a processor to execute all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or terminal devices such as a computer, a server, a mobile phone, and a tablet.

[0168] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0169] In addition, each functional unit in each embodiment of the present application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of software functional units. The above is only an implementation method of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the specification and drawings of this application, or directly or indirectly used in other related technical fields, is also included in the patent protection scope of the present application.

Claims

1. A method for configuring a water-using landscape, wherein the water landscape comprises a landscape having at least two water-using functions, characterized in that: The configuration method comprises: Step S1, obtaining the historical minimum passenger flow and the historical maximum passenger flow of the landscape; Step S2, dividing the interval between the historical lowest passenger flow and the historical highest passenger flow into three consecutive sub-intervals in ascending order of value; Step S3, respectively obtaining the historical occurrence time period of each sub-interval; Step S4, learning and training the historical occurrence time period of each sub-interval through a machine learning machine, and obtaining an occurrence time period prediction model after completing the training; Step S5, predicting the future occurrence time period of each sub-interval based on a preset natural day step number by using the occurrence time period prediction model; Step S6, defining three consecutive sub-intervals as a low flow interval, a medium flow interval, and a high flow interval in sequence; Step S7, turning on the lighting function of the landscape in the future time period of the low traffic interval; Step S8, turning on the lighting function and the water function of the landscape in the future time period of the medium flow interval; Step S9, turning on the lighting function, water movement function, and water pressure function of the landscape during the future time period of the high flow interval.

2. The configuration method according to claim 1, characterized in that: Step S4, learning and training the historical occurrence time period of each sub-interval by a machine learning machine, and obtaining an occurrence time period prediction model after the training is completed, including: Step S41, obtaining several historical occurrence time periods of each sub-interval based on a preset time period; Step S42, packing all historical occurrence time periods of the same sub-interval into a data set; Step S43, performing standard normalization on the data set of the current sub-interval to obtain a normalized data set; Step S44, dividing the normalized data set of the current sub-interval into a training set and a validation set according to a preset ratio; Step S45, defining a neural network model having an input layer, a hidden layer, and an output layer that are sequentially signal-connected; Step S46, outputting the training set of the current sub-interval to the input layer, and performing a preset number of trainings through the neural network model; Step S47, obtaining a root mean square error between the verification set and the current training result based on each training; Step S48, obtaining the minimum value of the root mean square error among all training results, and obtaining the training result corresponding to the minimum value as the occurrence time period prediction model of the current sub-interval.

3. The configuration method according to claim 2, characterized in that: Step S43, performing standard normalization on the data set of the current sub-interval to obtain a normalized data set, including: Step S431, obtaining the historical start time and the historical end time of each historical occurrence time period in the current sub-interval; Step S432, converting the historical start time of the current historical occurrence time period into the historical start seconds; Step S433, converting the historical end time of the current historical occurrence time period into the historical end seconds; Step S434, standardize the historical start seconds and the historical end seconds of the current historical occurrence time period respectively by formula (1): Among them, t j ' ,start is the normalized historical starting data obtained by normalizing the jth historical starting second of the current historical time period, t j,start is the jth historical starting second of the current historical time period, is the average of all historical starting seconds in the current historical period, δ start is the standard deviation of all historical starting seconds in the current historical period, t j ' ,end The normalized historical end data obtained by normalizing the j-th historical end seconds of the current historical time period, t j,end is the jth historical end second of the current historical time period, is the average of all historical end seconds in the current historical period, δ end It is the standard deviation of all historical end seconds in the current historical period.

4. The configuration method according to claim 2, characterized in that: The neural network model is represented by formula (2): Wherein, y is the neural network model; x n is the nth input node of the input layer, each input node corresponds to a normalized data set in the training set, is the weight from the mth input node of the input layer to the nth input node of the hidden layer; is the bias of the nth input node connected to the hidden layer; is the bias of the output layer; tanh(·) is the activation function; the numbers in the brackets of the symbol subscripts are the number of layers, the subscript (1) is the first layer, that is, the input layer, the subscript (1, 2) is the first layer to the second layer, that is, the input layer to the hidden layer, and the subscript (3) is the third layer, that is, the output layer.

5. The configuration method according to claim 3, characterized in that: Step S5, predicting the future occurrence time period of each sub-interval based on the preset natural day step number through the occurrence time period prediction model, including: Step S51, calculating the normalized future start data and the normalized future end data based on the preset natural day step number through the occurrence time period prediction model; Step S52, substituting the normalized future start data and the normalized future end data into formula (1) to obtain the future start seconds and the future end seconds based on the preset natural day step number; Step S53, converting the future start seconds and the future end seconds into the future start time and the future end time respectively; Step S54, defining the duration from the future start time to the future end time as the future occurrence time period.

6. The configuration method according to claim 1, characterized in that: Step S8, turning on the lighting function and the water function of the landscape in the future time period of the medium flow interval, and then comprising: Step S10, when the future time period begins to occur, counting the power consumption of the light source of the lighting function, the power consumption of the moving water function and the water consumption; Step S20, sending the light source power consumption, the dynamic water power consumption, and the water consumption to an external monitoring terminal.

7. The configuration method according to claim 1, characterized in that: Step S9, turning on the lighting function, water movement function, and water pressure function of the landscape in the future time period of the high flow interval, and then including: Step S100, when the future occurrence time period begins to occur, counting the light source power consumption of the lighting function, the dynamic water power consumption of the dynamic water function, the pressure water power consumption of the pressure water function, and the total water consumption of the dynamic water function and the pressure water function; Step S200, sending the light source power consumption, the dynamic water power consumption, the pressurized water power consumption, and the total water consumption to an external monitoring terminal.

8. A waterscape configuration device, the configuration device being applied to the configuration method according to any one of claims 1 to 7, characterized in that: The configuration device comprises: A landscape passenger flow acquisition module, used to acquire the historical minimum passenger flow and the historical maximum passenger flow of the landscape; A passenger flow interval division module, used to divide the interval between the historical lowest passenger flow and the historical highest passenger flow into three continuous sub-intervals in ascending order of value; A historical occurrence time period acquisition module is used to respectively acquire the historical occurrence time period of each sub-interval; An occurrence time period prediction model acquisition module is used to learn and train the historical occurrence time period of each sub-interval through a machine learning machine, and obtain an occurrence time period prediction model after completing the training; A future occurrence time period acquisition module, used for predicting the future occurrence time period of each sub-interval based on a preset natural day step number through the occurrence time period prediction model; A passenger flow sub-interval definition module is used to define three consecutive sub-intervals as a low flow interval, a medium flow interval, and a high flow interval in sequence; A low passenger flow landscape control module is used to turn on the lighting function of the landscape during a future period of low passenger flow; A medium passenger flow landscape control module, used to activate the lighting function and water function of the landscape in the future time period of the medium flow interval; The high passenger flow landscape control module is used to activate the lighting function, water movement function and water pressure function of the landscape during the future time period of the high passenger flow interval.

9. An electronic device, characterized in that: It comprises a processor and a memory coupled to the processor, wherein the memory stores program instructions executable by the processor; when the processor executes the program instructions stored in the memory, the configuration method according to any one of claims 1 to 7 is implemented.

10. A storage medium, characterized in that: The storage medium stores program instructions, and when the program instructions are executed by the processor, the configuration method according to any one of claims 1 to 7 can be implemented.

Images