CN111242602A - Control method and device of payment equipment, computer readable storage medium and equipment - Google Patents
Control method and device of payment equipment, computer readable storage medium and equipment Download PDFInfo
- Publication number
- CN111242602A CN111242602A CN202010058072.7A CN202010058072A CN111242602A CN 111242602 A CN111242602 A CN 111242602A CN 202010058072 A CN202010058072 A CN 202010058072A CN 111242602 A CN111242602 A CN 111242602A
- Authority
- CN
- China
- Prior art keywords
- payment
- time period
- target time
- information
- training
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 53
- 238000012549 training Methods 0.000 claims abstract description 123
- 238000003062 neural network model Methods 0.000 claims abstract description 38
- 230000006870 function Effects 0.000 claims description 20
- 238000004590 computer program Methods 0.000 claims description 12
- 230000001131 transforming effect Effects 0.000 claims description 10
- 230000002618 waking effect Effects 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 4
- 230000007958 sleep Effects 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 18
- 230000008569 process Effects 0.000 description 7
- 238000012545 processing Methods 0.000 description 7
- 239000011159 matrix material Substances 0.000 description 4
- 230000002035 prolonged effect Effects 0.000 description 4
- 230000032683 aging Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000006266 hibernation Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
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
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/22—Payment schemes or models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/38—Payment protocols; Details thereof
- G06Q20/40—Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
- G06Q20/405—Establishing or using transaction specific rules
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Computer Security & Cryptography (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Finance (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to a control method, a device, a computer readable storage medium and a device of a payment device, wherein the method comprises the following steps: acquiring a target time period, current weather information and holiday information; obtaining the predicted payment times of the payment equipment in the target time period according to the target time period, the weather information and the holiday information through a payment prediction model; the payment prediction model is obtained by training an initial neural network model by using a plurality of training samples, each training sample in the plurality of training samples comprises real payment times, weather information and holiday information when payment occurs, and each time period is any one of a plurality of time periods divided into one day; and when the predicted payment times are less than a preset threshold value, controlling the payment device to enter a dormant state in a target time period. The scheme provided by the application can save the operation resources of the payment equipment and prolong the service life of the payment equipment.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a method and an apparatus for controlling a payment device, a computer-readable storage medium, and a computer device.
Background
With the rapid development of computer technology, intelligent payment devices appear in the market, such as self-help payment machines appearing in various shopping malls or convenience stores, and the like, the intelligent payment devices gradually replace the traditional manual cash-receiving mode, help people to perform self-help payment after shopping is finished, and bring great convenience to the life of people.
At present, most of intelligent payment equipment carries out payment in a mode of scanning payment codes or face recognition, so that the intelligent payment equipment needs to scan the payment codes or face information in real time, a scanning function is in an activated state for a long time, great resource waste is caused, and the intelligent payment equipment is high in loss.
Disclosure of Invention
Based on this, it is necessary to provide a control method and apparatus for a payment device, a computer-readable storage medium, and a computer device, for solving the technical problem that resources are wasted due to the fact that a payment code or face information needs to be scanned in real time in the current intelligent payment device.
A method of controlling a payment device, comprising:
acquiring a target time period, current weather information and holiday information;
obtaining the predicted payment times of the payment equipment in the target time period according to the target time period, the weather information and the holiday information through a payment prediction model;
the payment prediction model is a model obtained by training an initial neural network model by using a plurality of training samples, each training sample in the plurality of training samples comprises real payment times, weather information and holiday information when payment occurs, and each time period is any one of a plurality of time periods divided from one day;
and when the predicted payment times are smaller than a preset threshold value, controlling the payment equipment to enter a dormant state in the target time period.
A control apparatus of a payment device, the apparatus comprising:
the acquisition module is used for acquiring target time periods, weather information and holiday information;
the prediction module is used for obtaining the predicted payment times of the payment equipment in the target time period according to the target time period, the weather information and the holiday information through a payment prediction model; the payment prediction model is a model obtained by training an initial neural network model by using a plurality of training samples, each training sample in the plurality of training samples comprises real payment times, weather information and holiday information when payment occurs, and each time period is any one of a plurality of time periods divided from one day;
and the control module is used for controlling the payment equipment to enter a dormant state in the target time period when the predicted payment times are smaller than a preset threshold value.
A computer-readable storage medium, in which a computer program is stored which, when executed by a processor, causes the processor to carry out the steps of the method of controlling a payment device as described above.
A computer device comprising a memory and a processor, the memory storing a computer program which, when executed by the processor, causes the processor to carry out the steps of the above-mentioned control method of a payment device.
On one hand, the payment prediction model is used for predicting the predicted payment times of the payment equipment in the target time period, and when the predicted payment times is smaller than the preset threshold value, the payment equipment is controlled to enter the dormant state in the target time period, so that the working state of the payment equipment can be correspondingly adjusted according to the predicted payment times, the running resources of the payment equipment are saved, and the service life of the payment equipment is prolonged. On the other hand, the payment prediction model is obtained by training the initial neural network model through the historical payment data of the payment equipment in advance, and the payment rule information carried by the historical payment data is fully mined, so that the prediction result of the payment prediction model is more accurate.
Drawings
FIG. 1 is a diagram of an application environment of a control method of a payment device in one embodiment;
FIG. 2 is a schematic flow chart diagram of a method of controlling a payment device in one embodiment;
FIG. 3 is a schematic diagram of an interface for prompting messages displayed by the payment device in one embodiment;
FIG. 4 is a diagram illustrating a mapping between time periods and time sequence numbers in one embodiment;
FIG. 5 is a flow diagram illustrating a process for obtaining a predicted number of payments made by a payment prediction model for a payment device over a target time period, under an embodiment;
FIG. 6 is a schematic diagram of a network architecture of a payment prediction model in one embodiment;
FIG. 7 is a schematic flow chart diagram illustrating the training steps of the payment prediction model in one embodiment;
FIG. 8A is a schematic illustration of payment data collected in one embodiment;
FIG. 8B is a diagram of a training sample in one embodiment;
FIG. 9 is a schematic flow chart diagram illustrating a method for controlling a payment device in accordance with one particular embodiment;
FIG. 10 is a block diagram showing the construction of a control device of the payment apparatus in one embodiment;
FIG. 11 is a block diagram of a computer device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
Fig. 1 is an application environment diagram of a control method of a payment apparatus in one embodiment. Referring to fig. 1, the control method of the payment apparatus is applied to a control system of the payment apparatus, which includes a payment apparatus 110 and a database 120, and the payment apparatus 110 and the database 120 may be connected through a network. The payment device 110 may specifically be a self-checkout machine, a self-service cash register, or the like. The payment apparatus 110 may include a payment information collecting device 1102, where the payment information collecting device 1102 is configured to collect payment information of a user, such as a payment code or face information provided by the user, and the payment information collecting device 1102 may be a camera, and the camera may be at least one of a color camera or a depth camera. The database 120 is used to store payment data collected by the payment device 110, and the historical payment data of the payment device 110 can be used to train an initial neural network model to obtain a payment prediction model for predicting the payment times of the payment device 110 in a certain time period.
In one embodiment, the payment device 110 may obtain a target time period, current weather information, and holiday information; obtaining the predicted payment times of the payment equipment in the target time period according to the target time period, the weather information and the holiday information through a payment prediction model; the payment prediction model is obtained by training an initial neural network model by using a plurality of training samples, each training sample in the plurality of training samples comprises real payment times, weather information and holiday information when payment occurs, and each time period is any one of a plurality of time periods divided into one day; and when the predicted payment times are less than a preset threshold value, controlling the payment device to enter a dormant state in a target time period. The payment apparatus 110 includes a payment information collecting device, and when the predicted payment number is less than a preset threshold, the payment apparatus 110 may control the payment information collecting device to enter a sleep state within a target time period.
As shown in fig. 2, in one embodiment, a method of controlling a payment device is provided. The present embodiment is mainly illustrated by applying the method to the payment device 110 in fig. 1. Referring to fig. 2, the control method of the payment device specifically includes the following steps:
s202, acquiring a target time period, current weather information and holiday information.
Wherein the target time period is a time range in which the number of payments made by the payment device is predicted, for example, 12:00-12: 30. The current weather information is whether the weather conditions within the target time period are suitable for the weather category for out shopping. The holiday information is that the today to which the target time period belongs is a workday or holiday.
In this embodiment, the number of payments made by the payment device in each target time period in a day is predicted, and whether a transaction will occur is determined, that is, the payment made by the payment device is greatly related to the weather condition in the current target time period and whether the current day is a holiday or not, so that the payment device needs to acquire the current weather information and holiday information in prediction.
In one embodiment, the payment device may divide each day into a plurality of time periods, each of which is a target time period. The payment device can predict the payment times in each target time period at one time so as to determine whether a transaction occurs in each target time period, and when the current system time of the payment device is included in the target time period, the working state of the payment device in each target time period in the day is controlled according to the prediction result, wherein the working state comprises one of a dormant state and an active state. For example, the payment times in each target time period of the day can be predicted once every morning at 0:00, and the working state of the payment device in each target time period can be controlled according to the prediction result of each target time period.
Alternatively, the payment device may divide each day into a plurality of target time periods evenly according to a preset interval, and the preset interval may be set according to actual needs, for example, the preset interval may be divided every half hour, so that each day is divided into 48 target time periods, or may be divided every hour, so that each day is divided into 24 target time periods. Of course, each day can be divided into a plurality of target time periods with different durations according to the operation condition of the working environment where the user is located. It will be appreciated that the shorter the duration of each target time period, the greater the number of times the operating state of the payment device is intervened.
In one embodiment, the payment device may divide each day into a plurality of time periods, and determine a time period including the current system time as the target time period according to the current system time of the payment device. The payment device may predict the number of payments made by the payment device in a new target time period when the current system time belongs to the new target time period.
The target time period is any time period in a day, and it can be understood that the weather information of each target time period in the day is generally the same. The weather information can be divided according to whether the weather information is suitable for shopping outdoors, for example, the weather information is not suitable for shopping outdoors under the weather conditions of rain, snow, strong wind, haze and the like, the weather information can be classified as "1" when the weather information is suitable for shopping outdoors, such as sunny days and cloudy days, and the weather information can be classified as "0" when the weather information is suitable for shopping outdoors. The payment device may obtain the corresponding weather information after inquiring the weather condition through a network, or the payment device may obtain the corresponding weather information after inquiring the current weather condition according to a local weather inquiry service.
The holiday information is that today to which the target time period belongs is a workday or holiday. The payment device may classify today as a holiday by "1" and today as a weekday by "0".
S204, obtaining the predicted payment times of the payment equipment in the target time period according to the target time period, the weather information and the holiday information through a payment prediction model; the payment prediction model is obtained by training an initial neural network model by using a plurality of training samples, each training sample in the plurality of training samples comprises real payment times, weather information and holiday information when payment occurs, and each time period is any one of a plurality of time periods divided into one day.
The payment prediction model is a neural network model with the ability to predict the number of payments made by the payment device over a target time period. The payment device can set a model structure based on the neural network in advance to obtain an initial neural network model, and then train the initial neural network model through a plurality of training samples to obtain model parameters of the payment prediction model. Each training sample comprises real payment times paid by the payment device in a time period, weather information when payment occurs and holiday information, and a model obtained by training the training samples has the capability of predicting the payment times of the payment device in a target time period. When the payment times of the payment equipment in each target time period need to be predicted, the trained model parameters can be obtained, and then the model parameters are imported into the initial neural network model to obtain a payment prediction model.
Specifically, when the payment times of the payment device in the target time period are predicted, the obtained target time period, the weather information and the holiday information can be input into a payment prediction model trained in advance, and then prediction is performed based on the information through the payment prediction model, so that the predicted payment times of the payment device in the target time period can be obtained.
And S206, when the predicted payment times are less than the preset threshold value, controlling the payment device to enter a dormant state in the target time period.
Specifically, the predicted payment times output by the payment prediction model are compared with a preset threshold, and when the predicted payment times are smaller than the preset threshold, the possibility that the payment behavior occurs on the payment equipment in the target time period is smaller, and the payment equipment can automatically enter a dormant state. Conversely, in one embodiment, the method further comprises: when the predicted payment times are larger than the preset threshold value, the payment device is controlled to enter the activated state in the target time period, namely, when the predicted payment times are larger than the preset threshold value, the possibility that payment behaviors occur through the payment device in the target time period is high, and the payment device can be in the activated state.
In an embodiment, the preset threshold may be set as needed, for example, may be 0, so when the predicted payment number is greater than 0, it indicates that there is a high possibility that the user pays through the payment device in the target time period next, to ensure the shopping experience of the user, the payment device may enter an active state, and when the predicted payment number is less than 0, it indicates that there is a high possibility that the user does not pay through the payment device in the target time period next, to save resources, reduce the loss of the payment device, and may control the payment device to enter a dormant state. Particularly, as the aging and the service life of the photosensitive devices such as the camera are related, the continuous use can accelerate the aging and reduce the service life, so that the camera on the payment equipment can be controlled to enter a dormant state, the turn-on time of the camera is reduced, and the service life of the camera is prolonged.
In one embodiment, after the step of controlling the payment device to enter the hibernation state for the target period of time, the method further comprises: displaying prompt information for waking up the payment device; when a wake-up trigger event for the payment device is detected, the payment device is controlled to enter an active state.
It is understood that the payment prediction model is obtained by training a training sample generated based on historical payment data of the payment device, and therefore, the prediction result of the payment prediction model for predicting the payment times in the current target time period may not be completely accurate. In order to ensure the shopping experience of the user in payment by using the payment device, the payment device can display prompt information for waking up the payment device after entering a dormant state, so as to prompt the user that the payment device is currently in the dormant state and cannot collect the payment information provided by the user, and if the payment device needs to pay, the user needs to manually trigger the waking up. Further, when the payment device detects a wake-up trigger event for the payment device, the activation state is automatically entered, and the payment device may collect payment information provided by the user.
Fig. 3 is a schematic interface diagram of prompt messages displayed by the payment device in different operating states according to an embodiment. Referring to the left side of fig. 3, the payment device is in an activated state, prompting the user to "scan code in alignment with the camera" to pay by scanning the pay code, or prompting the user to "swipe face" by clicking "to pay by means of face recognition. Referring to the right side of fig. 3, the payment device is in a dormant state, and prompts the user that "the camera is dormant, the screen is clicked to pay" and "the face is swiped," and when the user clicks the screen, the payment device is woken up, for example, the payment device may be switched to an interface on the left side of fig. 3, and enters an active state, and at this time, the user may pay through the payment device.
According to the control method of the payment equipment, on one hand, the predicted payment times of the payment equipment in the target time period are predicted through the payment prediction model, the payment equipment is controlled to enter the dormant state in the target time period when the predicted payment times are smaller than the preset threshold value, and the working state of the payment equipment can be correspondingly adjusted according to the predicted payment times, so that the running resources of the payment equipment are saved, and the service life of the payment equipment is prolonged. On the other hand, the payment prediction model is obtained by training the initial neural network model through the historical payment data of the payment equipment in advance, and the payment rule information carried by the historical payment data is fully mined, so that the prediction result of the payment prediction model is more accurate.
In one embodiment, the payment device may divide each day into a plurality of time periods, with one-to-one mapping between each of the plurality of time periods and the time sequence number. As shown in fig. 4, the payment device will divide each day evenly by half an hour, divide each day into 48 target time periods, and map each target time period with a corresponding time sequence number, i.e., identify each target time period with a time sequence number. Further, referring to fig. 5, step S204, obtaining the predicted payment times of the payment device in the target time period according to the target time period, the weather information and the holiday information through the payment prediction model, includes the following steps S502-S508:
and S502, determining a time sequence number corresponding to the target time period.
Specifically, the payment device may determine a time serial number corresponding to the target time period according to a mapping relationship between the time period and the time serial number.
And S504, inputting the time serial number, the weather information and the information of the holidays into the payment prediction model.
For example, the target time period is 12:00-12:30, the corresponding time sequence number is 24, the current weather condition is a weather condition suitable for out-of-home shopping, the weather information is "0", the current day is holiday, the holiday information is "1", and the data input to the payment prediction model may be a vector with dimension 3, i.e., (24,0, 1). And the payment equipment inputs the acquired time serial number, weather information and holiday information into an input layer of the payment prediction model, and transmits the information into the payment prediction model through the input layer for subsequent processing.
S506, transforming the time sequence number, the weather information and the holiday information by paying the first connection weight between the input layer and the hidden layer of the prediction model to obtain the hidden layer characteristics.
And S508, transforming and fusing the characteristics of the hidden layers through a second connection weight between the hidden layer and the output layer of the payment prediction model to obtain the predicted payment times of the payment equipment in the target time period corresponding to the time sequence number.
The payment prediction model comprises an input layer, a hidden layer and an output layer, wherein the input layer is connected with the hidden layer in a full-connection mode, the hidden layer is connected with the output layer in a full-connection mode, the input layer is connected with the hidden layer in a first connection weight mode, and the hidden layer is connected with the output layer in a second connection weight mode. And performing matrix multiplication processing on the information acquired by the input layer and the first connection weight to obtain corresponding hidden layer characteristics, performing matrix multiplication processing on the hidden layer characteristics and the second connection weight, and fusing to obtain the predicted payment times of the payment equipment in a target time period.
Fig. 6 is a schematic diagram of a network structure of the payment prediction model in one embodiment. Referring to FIG. 6, the payment prediction model is based on 3 × 2 × 1 error inversionThe multi-layer feedforward neural network is obtained by training a propagation algorithm, an input layer of a payment prediction model comprises 3 nodes, a hidden layer comprises 2 nodes, and an output layer comprises 1 node. The 3 nodes of the input layer are respectively used for acquiring a time serial number x1, current weather information x2 and holiday information x3 corresponding to the target time period, and the first connection weight between the ith node of the input layer and the jth node of the hidden layer can be used
Representing where i e (1,2,3), j e (1,2), by weighting the first connection between the input layer and the hidden layer
Performing matrix multiplication processing on the information of the 3 nodes of the input layer to obtain hidden layer characteristics z1 and z2 of the 2 nodes of the hidden layer, wherein the second connection weight between the jth node of the hidden layer and the kth node of the output layer can be used
Representing j e (1,2), k e (1), by weighting the second connection between the hidden layer and the output layer
And performing matrix multiplication processing on the k node and 2 hidden layer characteristics of the hidden layer, and adding the k node and the hidden layer characteristics to obtain an output result of the k node of the output layer, wherein when the output layer only has 1 node, the output of the node is the predicted payment times of the payment equipment in the target time period.
In the embodiment, compared with the manual mode for controlling the working state of the payment device, the possibility that the user conducts the transaction through the payment device in the target time period is mined out from the weather information and the holiday information corresponding to the target time period through the payment prediction model trained in advance, so that the automatic prediction is realized, and the accuracy is high.
In one embodiment, the method for obtaining the payment prediction model by the payment device may train a model according to historical payment data corresponding to the payment performed by the payment device, and specifically includes: acquiring a training sample, and inputting the training sample to the initial neural network model; obtaining the predicted payment times of the payment equipment in a corresponding time period according to the time serial number, the weather information and the holiday information in the training sample based on the current model parameters through the initial neural network model; constructing an error function according to the real payment times and the predicted payment times; minimizing the error function and determining updated model parameters; and after updating the initial neural network model according to the updated model parameters, returning to the step of obtaining the training sample to continue training until the training end condition is met, and obtaining a payment prediction model for predicting payment times.
As shown in fig. 7, the training step of the payment prediction model includes:
s702, acquiring a training sample, wherein the training sample comprises real payment times of the payment equipment in a time period, weather information and holiday information when payment occurs, and the time period corresponds to the time sequence number.
The training samples are training data required for model training, each training sample includes real payment times of the payment device in a time period, weather information and holiday information when payment occurs, and the number of the training samples may be multiple, for example, multiple training samples may be generated according to historical payment data corresponding to payment performed on the payment device in a week. It should be noted that, because the working environments of each payment device are different, the training sample is generated according to the payment devices in the same working environment or the historical payment data of the same payment device, so that the payment prediction model obtained according to the training sample can be used for predicting the payment times of the payment devices in the same working environment or the same payment device in the target time period in the future.
In one embodiment, obtaining training samples comprises: collecting payment data generated on payment equipment, wherein the payment data comprises payment generation time, weather information and holiday information when payment occurs; counting the payment times of the payment equipment in each time period according to the payment occurrence time; and generating a training sample according to the payment times of the payment equipment in each time period, the weather information when the payment occurs and the holiday information.
Specifically, the payment device may store payment data corresponding to each payment action in a database, each piece of the payment data including a time when the secondary payment occurs, weather information when the payment occurs, and holiday information. Considering that payment does not always occur at every moment, and if the model needs to predict whether payment occurs at every moment or not, the problem of waste of operating resources is solved, the payment times in every time period can be counted according to the payment occurrence time, for example, the payment times in every half hour can be counted, a training sample is generated according to the payment times in every time period, the weather information when payment occurs and holiday information, and the model trained according to the training sample has the capability of predicting the payment times in every half hour. FIG. 8A is a diagram illustrating payment data collected in one embodiment. As shown in fig. 8B, a schematic diagram of each training sample obtained by processing historical payment data of the payment device in one embodiment is shown.
S704, inputting the training sample into the initial neural network model.
Specifically, the training sample comprises input data and reference data of the model, the input data is time sequence number, weather information and holiday information, the reference data is real payment times, the input layer transmits the input data to the inside of the payment prediction model for subsequent processing, namely the training sample is input into the initial neural network model for model training, and in the training process, model parameters are continuously adjusted according to the difference between the predicted payment times and the real payment times output by the model.
S706, transforming the time sequence number, the weather information and the holiday information through the current first connection weight between the input layer and the hidden layer of the initial neural network model to obtain the characteristics of the hidden layer; and transforming and fusing the characteristics of the hidden layers through the current second connection weight between the hidden layer and the output layer of the initial neural network model to obtain the predicted payment times of the payment equipment in a time period.
The built initial neural network model comprises an input layer, a hidden layer and an output layer, wherein the input layer is connected with the hidden layer in a full-connection mode, the connection weight is a first connection weight, the hidden layer is connected with the output layer in a full-connection mode, and the connection weight is a second connection weight. In the training process, for each training sample, the predicted payment times are obtained after calculation is carried out on the basis of the current first connection weight and the current second connection weight of the model, the predicted payment times are determined on the basis of the current model parameters, the difference between the predicted payment times and the real payment times is large before the training is completed, but the difference between the predicted payment times and the real payment times of the training samples is gradually reduced along with the continuous adjustment of the model parameters in the training process.
And S708, constructing an error function according to the real payment times and the predicted payment times.
The error function is used for evaluating the difference degree between the predicted payment times and the real payment times output by the model according to the current training sample, and the adjustment directions of model parameters, namely the first connection weight and the second connection weight, can be determined based on the constructed difference function.
In one embodiment, the error function constructed for each training sample may be obtained by the following equation:
wherein i represents the ith training sample, ti is the real payment times of the ith training sample, Oi is the predicted payment times obtained by predicting the ith training sample by the current network, the error function is a function related to the model parameters, and the model parameters are continuously adjusted to make the error function E extremely small in the training process.
S710, minimizing an error function, and determining an updated first connection weight and an updated second connection weight; and after updating the initial neural network model according to the updated first connection weight and the updated second connection weight, returning to the step of obtaining the training sample to continue training until the training end condition is met, and obtaining a payment prediction model for predicting payment times.
Specifically, for the error function corresponding to each training sample, the model parameter obtained when the loss is minimum is taken as the updated model parameter, then the next training sample is predicted on the basis of the updated model parameter so as to continue training the model parameter, and the training is ended until the obtained model parameter enables the model to be stable or the training frequency reaches the preset frequency.
In the embodiment, the model is trained through the training sample generated by the historical payment data acquired by the payment equipment, so that the obtained payment prediction model can be directly used for predicting the payment times of the payment equipment in each time period, and the method has high accuracy and strong reference.
As shown in fig. 9, in a specific embodiment, the method for controlling the payment device specifically includes the following steps:
s902, collecting payment data generated on payment equipment, wherein the payment data comprises payment generation time, weather information and holiday information when the payment occurs;
s904, counting the payment times of the payment equipment in each time period according to the payment occurrence time;
s906, generating a training sample according to the payment times of the payment equipment in each time period, the weather information when the payment occurs and the holiday information, wherein the training sample comprises the real payment times of the payment equipment in a time period, the weather information when the payment occurs and the holiday information, and one time period corresponds to the time sequence number;
s908, inputting the training sample into the initial neural network model;
s910, obtaining the predicted payment times of the payment equipment in a corresponding time period according to the time sequence number, the weather information and the holiday information based on the current model parameters through the initial neural network model;
s912, constructing an error function according to the real payment times and the predicted payment times;
s914, minimizing the error function, and determining updated model parameters;
s916, after the initial neural network model is updated according to the updated model parameters, returning to the step of obtaining the training sample to continue training until the training end condition is met, and obtaining a payment prediction model for predicting payment times;
s918, acquiring a plurality of time periods obtained after dividing each day according to preset time intervals;
s920, determining a target time period containing the current time according to the current time of the payment equipment;
s922, determining a time sequence number corresponding to the target time period, and acquiring current weather information and holiday information;
s924, inputting the time sequence number, the weather information and the information of the holidays into a payment prediction model;
s926, transforming the time sequence number, the weather information and the holiday information by paying the first connection weight between the input layer and the hidden layer of the prediction model to obtain the characteristics of the hidden layer;
and S928, transforming and fusing the characteristics of the hidden layers through a second connection weight between the hidden layer and the output layer of the payment prediction model to obtain the predicted payment times of the payment equipment in the target time period corresponding to the time sequence number.
S930, when the predicted payment times are smaller than a preset threshold value, controlling the payment equipment to enter a dormant state in a target time period, and displaying prompt information for awakening the payment equipment; when a wake-up trigger event for the payment device is detected, the payment device is controlled to enter an active state.
And S932, controlling the payment device to enter an activated state in the target time period when the predicted payment times is larger than a preset threshold value.
According to the control method of the payment equipment, on one hand, the predicted payment times of the payment equipment in the target time period are predicted through the payment prediction model, the payment equipment is controlled to enter the dormant state in the target time period when the predicted payment times are smaller than the preset threshold value, and the working state of the payment equipment can be correspondingly adjusted according to the predicted payment times, so that the running resources of the payment equipment are saved, and the service life of the payment equipment is prolonged. On the other hand, the payment prediction model is obtained by training the initial neural network model through the historical payment data of the payment equipment in advance, and the payment rule information carried by the historical payment data is fully mined, so that the prediction result of the payment prediction model is more accurate.
Fig. 9 is a flowchart illustrating a control method of the payment apparatus in one embodiment. It should be understood that, although the steps in the flowchart of fig. 9 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a portion of the steps in fig. 9 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
In one embodiment, as shown in fig. 10, there is provided a control apparatus 1000 of a payment device, which may be implemented by software, hardware or a combination of both as all or a part of the payment device. The apparatus comprises an acquisition module 1002, a prediction module 1004, and a control module 1006, wherein:
an obtaining module 1002, configured to obtain a target time period, weather information, and holiday information;
the prediction module 1004 is used for obtaining the predicted payment times of the payment device in the target time period according to the target time period, the weather information and the holiday information through the payment prediction model; the payment prediction model is obtained by training an initial neural network model by using a plurality of training samples, each training sample in the plurality of training samples comprises real payment times, weather information and holiday information when payment occurs, and each time period is any one of a plurality of time periods divided into one day;
the control module 1006 is configured to control the payment device to enter a sleep state within a target time period when the predicted payment times is less than a preset threshold.
In one embodiment, the obtaining module 1002 is further configured to obtain a plurality of time periods obtained after dividing each day according to a preset time interval; and determining a target time period containing the current time according to the current time of the payment device.
In one embodiment, each of the plurality of time periods is mapped to a time sequence number, and the prediction module 1004 is further configured to determine a time sequence number corresponding to the target time period; inputting the time sequence number, the weather information and the information of the holidays into a payment prediction model; transforming the time sequence number, the weather information and the holiday information by paying a first connection weight between an input layer and a hidden layer of the prediction model to obtain the characteristics of the hidden layer; and transforming and fusing the characteristics of the hidden layers through a second connection weight between the hidden layer and the output layer of the payment prediction model to obtain the predicted payment times of the payment equipment in a target time period corresponding to the time sequence number.
In an embodiment, the control apparatus 1000 of the payment device further includes a display module, configured to display a prompt message for waking up the payment device; the control module 1006 is further configured to control the payment device to enter an active state when a wake trigger event for the payment device is detected.
In one embodiment, the control module 1006 is further configured to control the payment device to enter an active state for a target time period when the predicted number of payments is greater than a preset threshold.
In an embodiment, the control apparatus 1000 of the payment device further includes a training module, configured to obtain a training sample, where the training sample includes real payment times, weather information and holiday information of the payment device in a time period, and the time period corresponds to the time sequence number; inputting the training sample to an initial neural network model; obtaining the predicted payment times of the payment equipment in a corresponding time period according to the time sequence number, the weather information and the holiday information on the basis of the current model parameters through the initial neural network model; constructing an error function according to the real payment times and the predicted payment times; minimizing the error function and determining updated model parameters; and after updating the initial neural network model according to the updated model parameters, returning to the step of obtaining the training sample to continue training until the training end condition is met, and obtaining a payment prediction model for predicting payment times.
In one embodiment, the training module is further configured to collect payment data occurring on the payment device, the payment data including a time at which the payment occurred, weather information when the payment occurred, and holiday information; counting the payment times of the payment equipment in each time period according to the payment occurrence time; and generating a training sample according to the payment times of the payment equipment in each time period, the weather information when the payment occurs and the holiday information.
On one hand, the control device 1000 of the payment device predicts the predicted payment times of the payment device in the target time period through the payment prediction model, and controls the payment device to enter the dormant state in the target time period when the predicted payment times are smaller than the preset threshold, so that the working state of the payment device can be correspondingly adjusted according to the predicted payment times, thereby saving the operation resources of the payment device and prolonging the service life of the payment device. On the other hand, the payment prediction model is obtained by training the initial neural network model through the historical payment data of the payment equipment in advance, and the payment rule information carried by the historical payment data is fully mined, so that the prediction result of the payment prediction model is more accurate.
FIG. 11 is a diagram illustrating an internal structure of a computer device in one embodiment. The computer device may specifically be the payment device 110 in fig. 1. As shown in fig. 11, the computer device includes a processor, a memory, a network interface, a payment information collecting device, and a display screen, which are connected through a system bus. Wherein the memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system and may also store a computer program which, when executed by the processor, causes the processor to implement a method of controlling a payment device. The internal memory may also have stored therein a computer program that, when executed by the processor, causes the processor to perform a method of controlling a payment device. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, the input device of the computer equipment can be a touch layer covered on the display screen, and the payment information acquisition device of the computer equipment can be a depth camera or a color camera.
Those skilled in the art will appreciate that the architecture shown in fig. 11 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, the control device 1000 of the payment apparatus provided in the present application may be implemented in a form of a computer program, and the computer program may be run on a computer apparatus as shown in fig. 11. The memory of the computer device may store various program modules constituting the control means 1000 of the payment device, such as the acquisition module 1002, the prediction module 1004 and the control module 1006 shown in fig. 10. The respective program modules constitute computer programs that cause the processor to execute the steps in the control method of the payment apparatus of the respective embodiments of the present application described in the present specification.
For example, the computer device shown in fig. 11 may execute step S202 by the obtaining module 1002 in the control apparatus 1000 of the payment device shown in fig. 10. The computer device may perform step S204 through the prediction module 1004. The computer device may perform step S206 through the control module 1006.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory storing a computer program which, when executed by the processor, causes the processor to perform the steps of the above-described control method of a payment device. Here, the steps of the control method of the payment apparatus may be the steps in the control method of the payment apparatus of the above-described respective embodiments.
In one embodiment, a computer readable storage medium is provided, storing a computer program which, when executed by a processor, causes the processor to perform the steps of the above-described control method of a payment device. Here, the steps of the control method of the payment apparatus may be the steps in the control method of the payment apparatus of the above-described respective embodiments.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a non-volatile computer-readable storage medium, and can include the processes of the embodiments of the methods described above when the program is executed. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (15)
1. A method of controlling a payment device, comprising:
acquiring a target time period, current weather information and holiday information;
obtaining the predicted payment times of the payment equipment in the target time period according to the target time period, the weather information and the holiday information through a payment prediction model;
the payment prediction model is a model obtained by training an initial neural network model by using a plurality of training samples, each training sample in the plurality of training samples comprises real payment times, weather information and holiday information when payment occurs, and each time period is any one of a plurality of time periods divided from one day;
and when the predicted payment times are smaller than a preset threshold value, controlling the payment equipment to enter a dormant state in the target time period.
2. The method of claim 1, wherein obtaining the target time period comprises:
acquiring a plurality of time periods obtained after dividing each day according to preset time intervals;
and determining a target time period containing the current time according to the current time of the payment equipment.
3. The method of claim 2, wherein a one-to-one mapping between each of the plurality of time periods and a time sequence number, and wherein obtaining, by a payment prediction model, a predicted number of payments by a payment device within the target time period based on the target time period, the weather information, and the holiday information comprises:
determining a time sequence number corresponding to the target time period;
inputting the time serial number, the weather information and the holiday information into a payment prediction model;
converting the time sequence number, the weather information and the holiday information through a first connection weight between an input layer and a hidden layer of the payment prediction model to obtain hidden layer characteristics;
and transforming and fusing the characteristics of the hidden layers through a second connection weight between the hidden layer and the output layer of the payment prediction model to obtain the predicted payment times of the payment equipment in the target time period corresponding to the time serial number.
4. The method of claim 1, wherein after the step of controlling the payment device to enter a sleep state for the target period of time, the method further comprises:
displaying a prompt message for waking up the payment device;
when a wake-up trigger event for the payment device is detected, then
Controlling the payment device to enter an active state.
5. The method of claim 1, further comprising:
and when the predicted payment times are larger than a preset threshold value, controlling the payment device to enter an activated state in the target time period.
6. The method according to any one of claims 1 to 5, wherein the training step of the payment prediction model comprises:
acquiring a training sample, wherein the training sample comprises real payment times of payment equipment in a time period, weather information and holiday information when payment occurs, and the time period corresponds to a time sequence number;
inputting the training samples to an initial neural network model;
obtaining the predicted payment times of the payment equipment in the corresponding time period according to the time sequence number, the weather information and the holiday information on the basis of the current model parameters through the initial neural network model;
constructing an error function according to the real payment times and the predicted payment times;
minimizing the error function and determining updated model parameters;
and after updating the initial neural network model according to the updated model parameters, returning to the step of obtaining the training samples to continue training until a training end condition is met, and obtaining a payment prediction model for predicting payment times.
7. The method of claim 6, wherein the obtaining training samples comprises:
collecting payment data occurring on the payment device, wherein the payment data comprises payment occurrence time, weather information and holiday information when payment occurs;
counting the payment times of the payment equipment in each time period according to the payment occurrence time;
and generating a training sample according to the payment times of the payment equipment in each time period, the weather information when the payment occurs and the holiday information.
8. A control apparatus of a payment device, the apparatus comprising:
the acquisition module is used for acquiring target time periods, weather information and holiday information;
the prediction module is used for obtaining the predicted payment times of the payment equipment in the target time period according to the target time period, the weather information and the holiday information through a payment prediction model; the payment prediction model is a model obtained by training an initial neural network model by using a plurality of training samples, each training sample in the plurality of training samples comprises real payment times, weather information and holiday information when payment occurs, and each time period is any one of a plurality of time periods divided from one day;
and the control module is used for controlling the payment equipment to enter a dormant state in the target time period when the predicted payment times are smaller than a preset threshold value.
9. The apparatus of claim 8, wherein the obtaining module is further configured to divide each day into a plurality of time periods according to a preset time interval; and determining a target time period containing the current time according to the current time of the payment equipment.
10. The apparatus of claim 9, wherein each of the plurality of time periods is mapped to a time sequence number; the prediction module is further configured to determine a time sequence number corresponding to the target time period; inputting the time serial number, the weather information and the holiday information into a payment prediction model; converting the time sequence number, the weather information and the holiday information through a first connection weight between an input layer and a hidden layer of the payment prediction model to obtain hidden layer characteristics; and transforming and fusing the characteristics of the hidden layers through a second connection weight between the hidden layer and the output layer of the payment prediction model to obtain the predicted payment times of the payment equipment in the target time period corresponding to the time serial number.
11. The apparatus of claim 8, further comprising a display module configured to display a prompt for waking up the payment device when the payment device enters a sleep state within the target time period; the control module is further configured to control the payment device to enter an active state when a wake-up trigger event for the payment device is detected.
12. The apparatus of claim 8, wherein the control module is further configured to control the payment device to enter an active state for the target time period when the predicted payment number is greater than a preset threshold.
13. The apparatus according to any one of claims 8 to 12, further comprising a training module for obtaining a training sample, wherein the training sample comprises a real payment number of the payment device in a time period, weather information when payment occurs, and holiday information, and the time period corresponds to a time sequence number; inputting the training samples to an initial neural network model; obtaining the predicted payment times of the payment equipment in the corresponding time period according to the time sequence number, the weather information and the holiday information on the basis of the current model parameters through the initial neural network model; constructing an error function according to the real payment times and the predicted payment times; minimizing the error function and determining updated model parameters; and after updating the initial neural network model according to the updated model parameters, returning to the step of obtaining the training samples to continue training until a training end condition is met, and obtaining a payment prediction model for predicting payment times.
14. A computer-readable storage medium, storing a computer program which, when executed by a processor, causes the processor to carry out the steps of the method according to any one of claims 1 to 7.
15. A computer device comprising a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the steps of the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010058072.7A CN111242602B (en) | 2020-01-19 | 2020-01-19 | Control method, device, computer readable storage medium and apparatus for payment apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010058072.7A CN111242602B (en) | 2020-01-19 | 2020-01-19 | Control method, device, computer readable storage medium and apparatus for payment apparatus |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111242602A true CN111242602A (en) | 2020-06-05 |
| CN111242602B CN111242602B (en) | 2023-12-26 |
Family
ID=70880951
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010058072.7A Active CN111242602B (en) | 2020-01-19 | 2020-01-19 | Control method, device, computer readable storage medium and apparatus for payment apparatus |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111242602B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112258172A (en) * | 2020-10-16 | 2021-01-22 | 多点(深圳)数字科技有限公司 | Payment automatic degradation method based on machine learning |
| CN113343893A (en) * | 2021-06-24 | 2021-09-03 | 武汉虹信技术服务有限责任公司 | Equipment face recognition control method based on personnel passing rule and application thereof |
| CN114419797A (en) * | 2022-01-24 | 2022-04-29 | 上海蜜罐科技有限公司 | Energy-saving method and system for outdoor express cabinet |
| CN114548523A (en) * | 2022-01-26 | 2022-05-27 | 深圳市傲天科技股份有限公司 | User viewing information prediction method, device, equipment and storage medium |
| CN117880861A (en) * | 2024-03-13 | 2024-04-12 | 季华实验室 | Signal intensity optimization method of NB-IOT equipment and related equipment |
| CN117880861B (en) * | 2024-03-13 | 2024-05-28 | 季华实验室 | Signal intensity optimization method of NB-IOT equipment and related equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20010032176A1 (en) * | 1999-12-29 | 2001-10-18 | Starkman Hartley C. | Methods and systems for a collections model for loans |
| CN104298336A (en) * | 2013-07-19 | 2015-01-21 | 贝壳网际（北京）安全技术有限公司 | Mobile terminal and control method and device of application program of mobile terminal |
| CN107093096A (en) * | 2016-12-15 | 2017-08-25 | 口碑控股有限公司 | A kind of Traffic prediction method and device |
| CN109447598A (en) * | 2018-09-25 | 2019-03-08 | 平安科技（深圳）有限公司 | Payment data processing method, device, computer equipment and storage medium |
| CN110363571A (en) * | 2019-06-24 | 2019-10-22 | 阿里巴巴集团控股有限公司 | The sensed in advance method and apparatus of trade user |
-
2020
- 2020-01-19 CN CN202010058072.7A patent/CN111242602B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20010032176A1 (en) * | 1999-12-29 | 2001-10-18 | Starkman Hartley C. | Methods and systems for a collections model for loans |
| CN104298336A (en) * | 2013-07-19 | 2015-01-21 | 贝壳网际（北京）安全技术有限公司 | Mobile terminal and control method and device of application program of mobile terminal |
| CN107093096A (en) * | 2016-12-15 | 2017-08-25 | 口碑控股有限公司 | A kind of Traffic prediction method and device |
| CN109447598A (en) * | 2018-09-25 | 2019-03-08 | 平安科技（深圳）有限公司 | Payment data processing method, device, computer equipment and storage medium |
| CN110363571A (en) * | 2019-06-24 | 2019-10-22 | 阿里巴巴集团控股有限公司 | The sensed in advance method and apparatus of trade user |
Non-Patent Citations (1)
| Title |
|---|
| 牛东晓等编著: "电力负荷预测技术及其应用", 北京：中国电力出版社, pages: 202 - 204 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112258172A (en) * | 2020-10-16 | 2021-01-22 | 多点(深圳)数字科技有限公司 | Payment automatic degradation method based on machine learning |
| CN113343893A (en) * | 2021-06-24 | 2021-09-03 | 武汉虹信技术服务有限责任公司 | Equipment face recognition control method based on personnel passing rule and application thereof |
| CN113343893B (en) * | 2021-06-24 | 2022-08-05 | 武汉虹信技术服务有限责任公司 | Equipment face recognition control method based on personnel passing rule and application thereof |
| CN114419797A (en) * | 2022-01-24 | 2022-04-29 | 上海蜜罐科技有限公司 | Energy-saving method and system for outdoor express cabinet |
| CN114548523A (en) * | 2022-01-26 | 2022-05-27 | 深圳市傲天科技股份有限公司 | User viewing information prediction method, device, equipment and storage medium |
| CN114548523B (en) * | 2022-01-26 | 2023-11-07 | 深圳市傲天科技股份有限公司 | User viewing information prediction method, device, equipment and storage medium |
| CN117880861A (en) * | 2024-03-13 | 2024-04-12 | 季华实验室 | Signal intensity optimization method of NB-IOT equipment and related equipment |
| CN117880861B (en) * | 2024-03-13 | 2024-05-28 | 季华实验室 | Signal intensity optimization method of NB-IOT equipment and related equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111242602B (en) | 2023-12-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111242602B (en) | Control method, device, computer readable storage medium and apparatus for payment apparatus | |
| Hong et al. | Probabilistic electric load forecasting: A tutorial review | |
| CN105787582A (en) | Stock risk prediction method and apparatus | |
| Antoniadis et al. | A prediction interval for a function-valued forecast model: Application to load forecasting | |
| Guo et al. | Parking spaces repurchase strategy design via simulation optimization | |
| CN111210056A (en) | Electricity price scheme determination method and device, computer equipment and storage medium | |
| CN111260156A (en) | Construction method of cash flow prediction model and cash flow prediction method and device | |
| CN105243098A (en) | Face image clustering method and apparatus | |
| CN110880127A (en) | Consumption level prediction method and device, electronic equipment and storage medium | |
| CN111951045A (en) | Electricity charge accounting method and device based on big data | |
| CN112785089A (en) | Agent service configuration method and device, electronic equipment and storage medium | |
| Edington et al. | A time-evolving digital twin tool for engineering dynamics applications | |
| Tomar et al. | Deep learning neural network prediction system enhanced with best window size in sliding window algorithm for predicting domestic power consumption in a residential building | |
| CN111210260A (en) | Electricity price data processing method and device, computer equipment and storage medium | |
| CN117217380A (en) | Parking lot vacant parking space prediction method and device, electronic equipment and storage medium | |
| CN117332898A (en) | New energy small time scale power time sequence rolling prediction method based on machine learning | |
| Jiang et al. | NSDAR: A neural network-based model for similar day screening and electric load forecasting | |
| CN111242423A (en) | Active demand response potential analysis method, device, equipment and storage medium | |
| CN113537631B (en) | Medicine demand prediction method, device, electronic equipment and storage medium | |
| CN115169731A (en) | Smart campus energy consumption prediction method, device, equipment and medium | |
| JP2009251742A (en) | Demand predicting device, demand predicting method and demand predicting program | |
| CN114841451A (en) | Driver travel subsidy method and device and storage medium | |
| WO2022005403A1 (en) | Communications apparatus and method for estimating potential demand for improved forecasting and resource management | |
| JP3268520B2 (en) | How to forecast gas demand | |
| CN114417190A (en) | Website recommendation method and device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 40023548 Country of ref document: HK |
|
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |