State adjustment strategy determination method and device, equipment and computer storage medium

Abstract

The invention discloses a state adjustment strategy determination method and device, equipment and a computer storage medium. The method comprises the following steps: acquiring communication feature information of target equipment in a target time period, preset communication feature information and a power consumption value corresponding to the preset communication feature information; a first preset number of target communication feature information is selected from the preset communication feature information, and the similarity between the target communication feature information and the communication feature information of the target device in the target time period is larger than a target value; determining an average value of power consumption values corresponding to the target communication feature information as a predicted power consumption value of the target equipment; and determining a state adjustment strategy of the target equipment within the target time period as a target state adjustment strategy corresponding to the predicted power consumption value according to a relationship between the preset power consumption value and a preset state adjustment strategy. According to the invention, the transformed state adjustment strategy is set through the transformed power consumption value, the communication requirement of the equipment can be flexibly adapted, the energy waste can be reduced, and the communication requirement of the equipment can be met in time.

Description

Technical Field

[0001] The present application belongs to the technical field of Internet of Things, and in particular, relates to a method, device, equipment and computer storage medium for determining a state adjustment strategy. Background Art

[0002] For equipment installation environments without power supply, batteries are needed to power the equipment. In order to meet the demand for the longest possible battery life, the Narrow Band-Internet of Things (NB-IoT) introduces enhanced discontinuous reception (eDRX) and power saving mode (PSM). The eDRX and PSM technologies greatly reduce the power consumption of the terminal.

[0003] eDRX and PSM are based on fixed time intervals and predetermined rules, so that the terminal network alternates between awake and dormant states. The terminal network can receive data when it is awake, but cannot receive data when it is dormant. Although eDRX and PSM reduce the power consumption of the terminal to a certain extent, in the case of sudden communication needs or environmental changes, eDRX and PSM will lead to energy waste or fail to meet the communication needs of the device in a timely manner. Summary of the invention

[0004] The embodiments of the present application provide a method, apparatus, device and computer storage medium for determining a state adjustment strategy. By setting a transformed state adjustment strategy according to a transformed power consumption value, the communication needs of the device can be flexibly adapted, which can reduce energy waste and meet the communication needs of the device in a timely manner.

[0005] In a first aspect, an embodiment of the present application provides a method for determining a state adjustment strategy, including:

[0006] Obtaining communication characteristic information, preset communication characteristic information, and power consumption value corresponding to the preset communication characteristic information of a target device within a target time period;

[0007] Selecting a first preset number of target communication characteristic information from the preset communication characteristic information, wherein the similarity between the target communication characteristic information and the communication characteristic information of the target device within the target time period is greater than a target value;

[0008] Determine an average value of the power consumption values ​​corresponding to the target communication characteristic information as the predicted power consumption value of the target device;

[0009] According to the relationship between the preset power consumption value and the preset state adjustment strategy, the state adjustment strategy of the target device in the target time period is determined to be the target state adjustment strategy corresponding to the predicted power consumption value, the preset power consumption value includes the predicted power consumption value, and the preset state adjustment strategy includes the target state adjustment strategy.

[0010] In a possible implementation, the preset communication characteristic information includes first sub-preset communication characteristic information and second sub-preset communication characteristic information; before obtaining the preset communication characteristic information of the target device within the target time period and the power consumption value corresponding to the preset communication characteristic information, the method further includes:

[0011] Obtain historical communication feature information of the target device within the target time period;

[0012] Dividing the historical communication characteristic information into first historical communication characteristic information and second historical communication characteristic information according to a preset ratio;

[0013] Inputting the first historical communication feature information and the second historical communication feature information into an initial power consumption classification model, and classifying the first historical communication feature information using the initial power consumption classification model to obtain a predicted category of the first historical communication feature information;

[0014] For each target historical communication feature information in the second historical communication feature information, a first preset number of third historical communication feature information is selected from the first historical communication feature information, and the target prediction category with the most prediction categories of the first preset number of third historical communication feature information is determined as the prediction category of the target historical communication feature information, and the similarity between the third historical communication feature information and the corresponding target historical communication feature information is greater than the target value;

[0015] According to the prediction category of the historical communication characteristic information, the historical communication characteristic information is divided into first sub-preset communication characteristic information and second sub-preset communication characteristic information;

[0016] The predicted categories of historical communication characteristic information include a first category and a second category, the power consumption value corresponding to the historical communication characteristic information of the first category is greater than a first threshold, and the power consumption value corresponding to the historical communication characteristic information of the second category is not greater than the first threshold.

[0017] In a possible implementation, the historical communication feature information is divided into first sub-preset communication feature information and second sub-preset communication feature information according to the category of the historical communication feature information, including:

[0018] Obtaining a power consumption value corresponding to the second historical communication characteristic information;

[0019] determining, according to the power consumption value, an actual category of the second historical communication characteristic information;

[0020] Determine an error value of an initial power consumption classification model according to the actual category and the predicted category;

[0021] When the error value does not meet the model training stop condition, update the parameters of the initial power consumption classification model to obtain an updated initial power consumption classification model, use the updated initial power consumption classification model to classify the first historical communication feature information and the second historical communication feature information, and update the predicted category of the historical communication feature information until the error value meets the model training stop condition to obtain the target predicted category of the historical communication feature information, wherein the parameters of the initial power consumption classification model include a first preset number;

[0022] The target prediction category of the historical communication feature information is used to divide the historical communication feature information into first sub-preset communication feature information and second sub-preset communication feature information.

[0023] In a possible implementation, selecting a first preset amount of target communication characteristic information from preset communication characteristic information includes:

[0024] A second preset number of target communication characteristic information is selected from the preset communication characteristic information, where the second preset number is the updated preset number.

[0025] In a possible implementation, after determining the average value of the power consumption values ​​corresponding to the target communication characteristic information as the predicted power consumption value of the target device, the method further includes:

[0026] Get the actual power consumption value of the target device within the target time period;

[0027] When the difference between the actual power consumption value and the predicted power consumption value is greater than the second threshold, the target prompt information is displayed.

[0028] In a possible embodiment, the communication characteristic information includes at least the activity level, communication frequency, and activity duration.

[0029] In a second aspect, an embodiment of the present application provides a device for determining a state adjustment strategy, including:

[0030] An acquisition module, used to acquire communication characteristic information of a target device within a target time period, preset communication characteristic information, and a power consumption value corresponding to the preset communication characteristic information;

[0031] A selection module, configured to select a first preset number of target communication characteristic information from preset communication characteristic information, wherein the similarity between the target communication characteristic information and the communication characteristic information of the target device within the target time period is greater than a target value;

[0032] A determination module, used to determine an average value of power consumption values ​​corresponding to target communication characteristic information as a predicted power consumption value of the target device;

[0033] The determination module is also used to determine that the state adjustment strategy of the target device in the target time period is the target state adjustment strategy corresponding to the predicted power consumption value based on the relationship between the preset power consumption value and the preset state adjustment strategy, the preset power consumption value includes the predicted power consumption value, and the preset state adjustment strategy includes the target state adjustment strategy.

[0034] In a third aspect, an embodiment of the present application provides an electronic device, the device comprising:

[0035] a processor and a memory storing computer program instructions;

[0036] A method for determining a state adjustment strategy for implementing any of the above items when a processor executes computer program instructions.

[0037] In a fourth aspect, an embodiment of the present application provides a computer storage medium, on which computer program instructions are stored. When the computer program instructions are executed by a processor, a method for determining any of the above-mentioned state adjustment strategies is implemented.

[0038] In a fifth aspect, an embodiment of the present application provides a computer program product, characterized in that when the instructions in the computer program product are executed by a processor of an electronic device, the electronic device is enabled to execute any one of the above-mentioned methods for determining a state adjustment strategy.

[0039] The method, apparatus, device and computer storage medium for determining a state adjustment strategy of an embodiment of the present application include: obtaining communication characteristic information, preset communication characteristic information and power consumption values ​​corresponding to the preset communication characteristic information of a target device within a target time period; selecting a first preset number of target communication characteristic information from the preset communication characteristic information, wherein the similarity between the target communication characteristic information and the communication characteristic information of the target device within the target time period is greater than the target value; determining an average value of the power consumption values ​​corresponding to the target communication characteristic information as the predicted power consumption value of the target device; and determining, based on a relationship between the preset power consumption value and the preset state adjustment strategy, that the state adjustment strategy of the target device within the target time period is a target state adjustment strategy corresponding to the predicted power consumption value, wherein the preset power consumption value includes the predicted power consumption value, and the preset state adjustment strategy includes the target state adjustment strategy.

[0040] In this way, the communication characteristic information of the target device is obtained in real time, multiple target communication characteristic information that is close to the communication characteristic information of the target device is determined from the preset communication characteristic information, the power consumption value of the target device is predicted according to the power consumption values ​​corresponding to the multiple target communication characteristic information, and the state adjustment strategy of the target device is determined based on the predicted power consumption value of the target device. That is, the state adjustment strategy is set according to the transformed power consumption value, which can flexibly adapt to the communication needs of the device, reduce energy waste, and meet the communication needs of the device in a timely manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solution of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0042] Figure 1 It is a flowchart of a method for determining a state adjustment strategy provided by an embodiment of the present application;

[0043] Figure 2 is a flowchart of a method for determining a state adjustment strategy provided by another embodiment of the present application;

[0044] Figure 3 is a flowchart of a method for determining a state adjustment strategy provided by another embodiment of the present application;

[0045] Figure 4 is a flowchart of a method for determining a state adjustment strategy provided by yet another embodiment of the present application;

[0046] Figure 5 is a flowchart of a method for determining a state adjustment strategy provided by yet another embodiment of the present application;

[0047] Figure 6 is a structural diagram of a device for determining a state adjustment strategy provided in yet another embodiment of the present application;

[0048] Figure 7 It is a structural diagram of an electronic device provided in yet another embodiment of the present application. DETAILED DESCRIPTION

[0049] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by illustrating the examples of the present application.

[0050] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0051] For equipment installation environments without power supply, batteries are needed to power the equipment. In order to meet the demand for the longest possible battery life, the Narrow Band-Internet of Things (NB-IoT) introduces enhanced discontinuous reception (eDRX) and power saving mode (PSM). The eDRX and PSM technologies greatly reduce the power consumption of the terminal.

[0052] eDRX and PSM are based on fixed time intervals, predetermined rules and parameters, so that the terminal network alternates between awake state and dormant state. When the terminal network is in awake state, the terminal can receive data, and when it is in dormant state, the terminal cannot receive data. Although eDRX and PSM reduce the power consumption of the terminal to a certain extent, in the case of sudden communication needs or environmental changes, eDRX and PSM will lead to energy waste or fail to meet the communication needs of the device in time.

[0053] In order to solve the problems of the prior art, the embodiments of the present application provide a method, device, equipment and computer storage medium for determining a state adjustment strategy. The method for determining a state adjustment strategy provided by the embodiments of the present application obtains the communication characteristic information of the target device in real time, determines multiple target communication characteristic information that is closer to the communication characteristic information of the target device from the preset communication characteristic information, predicts the power consumption value of the target device according to the power consumption values ​​corresponding to the multiple target communication characteristic information, and determines the state adjustment strategy of the target device based on the predicted power consumption value of the target device. That is, by setting the transformed state adjustment strategy according to the transformed power consumption value, it can flexibly adapt to the communication needs of the device, which can not only reduce energy waste, but also meet the communication needs of the device in a timely manner.

[0054] The following first introduces the method for determining the state adjustment strategy provided in the embodiment of the present application. Figure 1A flow chart of a method for determining a state adjustment strategy provided by an embodiment of the present application is shown.

[0055] like Figure 1 As shown, the method for determining the state adjustment strategy provided in the embodiment of the present application includes the following steps.

[0056] S110. Obtain communication characteristic information, preset communication characteristic information, and power consumption value corresponding to the preset communication characteristic information of a target device within a target time period.

[0057] Here, the target device may be a narrowband cellular Internet of Things (NB-IoT) device. The communication characteristic information may include, but is not limited to, characteristic information related to power consumption level, such as active duration, active level, and communication frequency. The method for obtaining the communication characteristic information is not specifically limited here.

[0058] In some embodiments, real-time status data of the target device is collected. That is, sensors are used to monitor the status of the target device in real time, obtain real-time data of the current communication demand and the active time of the target device, monitor the communication mode and data transmission status of the target device, obtain the communication demand of the device in real time, and understand whether the device currently needs to communicate. Feature extraction is performed on the status data, including features such as device historical behavior, communication mode, task execution time, etc. Specifically, it can include, but is not limited to, feature information related to power consumption level, such as active duration, activity level, and communication frequency.

[0059] In some embodiments, a timestamp is used to record the start and end time of a task, determine the task execution time, and analyze the time when the device executes different tasks, including the start time and duration of the task. That is, a timestamp is used to mark the moment when the target device goes from sleep to wake up and then to sleep again, and the difference between the two timestamps is calculated, which is the active duration. The active duration calculation formula (1) is as follows:

[0060] A t = t end -t start (1)

[0061] Among them, t start The start timestamp of the target device waking up, t end A is the timestamp of the target device sleeping. t Active time.

[0062] Count the number of times the target device communicates with the network, and calculate the communication frequency within the target time period. The communication frequency calculation formula (2) is as follows:

[0063]

[0064] Where N is the number of communications within the target time period, T is the length of the target time period, and F C is the communication frequency.

[0065] In some embodiments, the activity level may be determined by the number of communications within the target time period, and the activity level within the target time period is determined according to a preset correspondence between the number of communications and the activity level.

[0066] In some embodiments, the mean and standard deviation can also be used to extract the statistical characteristics and frequency domain characteristics of the time series of the target device behavior in the target time period, and analyze the historical changes of the active mode and communication frequency of the target device in the target time period. The time series feature extraction formula (3) is as follows:

[0067]

[0068] Among them, x i is each data point in the time series, and N is the total number of data points. The data points here include the data communicated between the base station and the terminal.

[0069] In some embodiments, the time domain signal can be converted to the frequency domain by Fourier transform to obtain spectrum information. According to the spectrum information, the characteristics of the communication mode are extracted from the communication data to analyze whether the communication mode of the target device has periodic communication and the distribution of communication duration.

[0070] In some embodiments, the preset communication characteristic information is set in advance. It includes communication characteristic information corresponding to different power consumption values. The power consumption value corresponding to the preset communication characteristic information can be a high power consumption level or a low power consumption level. The preset communication characteristic information can be communication characteristic information classified by a K-nearest neighbor model based on the size of the power consumption value.

[0071] S120: Select a first preset number of target communication characteristic information from preset communication characteristic information, wherein the similarity between the target communication characteristic information and the communication characteristic information of the target device within the target time period is greater than a target value.

[0072] Here, the target value may be a value set in advance.

[0073] In some embodiments, the Euclidean distance between the vector corresponding to the preset communication feature information and the vector corresponding to the communication feature information is calculated, and the normalized Euclidean distance represents the similarity between the preset communication feature information and the communication feature information. The preset communication feature information is sorted in descending order of the Euclidean distance to obtain a preset communication feature information sequence. From the preset communication feature information sequence, a first preset number of target communication feature information is selected from the front to the back. The calculation formula (4) of the Euclidean distance is as follows:

[0074]

[0075] Where n is the number of features, x i and i They are respectively the communication feature information and the i-th feature of a communication feature information in the preset communication feature information.

[0076] In some embodiments, the Euclidean distance may be calculated using the vectorized preset communication feature information and the communication feature information.

[0077] S130. Determine an average value of the power consumption values ​​corresponding to the target communication characteristic information as the predicted power consumption value of the target device.

[0078] In some embodiments, if a weight value exists for a certain characteristic information among different target communication characteristic information, a weighted average value of the power consumption values ​​corresponding to the target communication characteristic information is determined as the predicted power consumption value of the target device.

[0079] As an example, the calculation formula (5) for predicting the power consumption value is as follows:

[0080]

[0081] Among them, Label i is the power consumption value of the target communication characteristic information of the i-th nearest neighbor, and K is the first preset number.

[0082] In some embodiments, in order to simplify and save computing resources, the power consumption level of the classified preset communication characteristic information may also be assigned a value, and when determining the predicted power consumption value, the average value of the power consumption level is used to determine it.

[0083] As an example, the power consumption level of the preset communication characteristic information of the high power consumption category is assigned a value of 1, and the power consumption level of the preset communication characteristic information of the low power consumption category is assigned a value of 0.

[0084] In some embodiments, the power consumption category of the target device in the target time period can also be determined by voting. The power consumption categories include high power consumption and low power consumption categories. The power consumption value corresponding to the communication characteristic information in the high power consumption category is greater than the first threshold, and the power consumption value corresponding to the communication characteristic information in the low power consumption category is not greater than the first threshold. Since the preset communication characteristic information is communication characteristic information classified by the K-nearest neighbor model based on the size of the power consumption value, it is possible to determine by voting which category of communication characteristic information has the largest number of the first preset number of target communication characteristic information, and this category is the power consumption category of the target device in the target time period.

[0085] S140. According to the relationship between the preset power consumption value and the preset state adjustment strategy, determine that the state adjustment strategy of the target device in the target time period is the target state adjustment strategy corresponding to the predicted power consumption value, the preset power consumption value includes the predicted power consumption value, and the preset state adjustment strategy includes the target state adjustment strategy.

[0086] In some embodiments, the adaptive sleep and wake-up strategy adjustment is performed based on the predicted power consumption value, evaluating the future power consumption level of the device and dynamically adjusting the sleep and wake-up strategy of the device.

[0087] Specifically, appropriate power consumption thresholds are set according to business requirements and device characteristics, and the predicted power consumption value is used to determine whether the device is in a high power consumption state. The sleep duration and wake-up timing are adjusted in real time according to the predicted power consumption value, so that the device wakes up in a high power consumption state and sleeps in a low power consumption state.

[0088] In this way, the communication characteristic information of the target device is obtained in real time, multiple target communication characteristic information that is close to the communication characteristic information of the target device is determined from the preset communication characteristic information, the power consumption value of the target device is predicted according to the power consumption values ​​corresponding to the multiple target communication characteristic information, and the state adjustment strategy of the target device is determined based on the predicted power consumption value of the target device. That is, the state adjustment strategy is set according to the transformed power consumption value, which can flexibly adapt to the communication needs of the device, reduce energy waste, and meet the communication needs of the device in a timely manner.

[0089] Based on this, in some embodiments, the preset communication characteristic information includes first sub-preset communication characteristic information and second sub-preset communication characteristic information; Figure 2 As shown, before S110, the method may further include:

[0090] S101, obtaining historical communication feature information of a target device within a target time period;

[0091] S102, dividing the historical communication characteristic information into first historical communication characteristic information and second historical communication characteristic information according to a preset ratio;

[0092] S103, inputting the first historical communication feature information and the second historical communication feature information into an initial power consumption classification model, and classifying the first historical communication feature information using the initial power consumption classification model to obtain a predicted category of the first historical communication feature information;

[0093] S104, for each target historical communication feature information in the second historical communication feature information, select a first preset number of third historical communication feature information from the first historical communication feature information, and determine the target prediction category with the most prediction categories of the first preset number of third historical communication feature information as the prediction category of the target historical communication feature information, and the similarity between the third historical communication feature information and the corresponding target historical communication feature information is greater than the target value;

[0094] S105, dividing the historical communication characteristic information into first sub-preset communication characteristic information and second sub-preset communication characteristic information according to the predicted category of the historical communication characteristic information;

[0095] The predicted categories of historical communication characteristic information include a first category and a second category, the power consumption value corresponding to the historical communication characteristic information of the first category is greater than a first threshold, and the power consumption value corresponding to the historical communication characteristic information of the second category is not greater than the first threshold.

[0096] Here, the historical communication feature information may include, but is not limited to, feature information related to power consumption level, such as active duration, active level, and communication frequency. The method for obtaining the communication feature information is not specifically limited here. The first historical communication feature information is used as training data, and the second historical communication feature information is used as test data. The power consumption classification model is a K-nearest neighbor model, that is, a model constructed by a K-nearest neighbor algorithm.

[0097] In some embodiments, the historical communication feature information is preprocessed, missing values ​​are processed, and standardized to ensure data consistency and availability. Missing values ​​in the historical communication feature information are identified and filled with the mean to avoid interference with subsequent analysis. missing The feature information is filled with the mean μ of the feature information using formula (6). Formula (6) is as follows:

[0098] X missing = μ (6)

[0099] The Z score (data normalization) method is used to identify and handle outliers in historical communication feature information to avoid negative impact on model training. The Z score of each feature in the historical communication feature information is calculated, and data points with a Z score greater than or less than a certain threshold are usually considered outliers. For each feature x i , use the following standardization formula to remove outliers and standardize the data to a distribution with a mean of 0 and a standard deviation of 1 to ensure that different features have the same scale. The data standardization formula (7) is as follows:

[0100]

[0101] Here, μ is the mean of the feature and σ is the standard deviation of the feature.

[0102] In some embodiments, the category of historical communication feature information is predicted by the K-nearest neighbor algorithm, and the preprocessed historical communication feature information is divided into a training set and a test set. Assuming the total data volume of the historical communication feature information is N, and the training set ratio is p, the training set size is N×p, and the test set size is N×(1-p). For example, 80% of the data is used for training and 20% for testing. The preprocessed historical communication feature information is used as the input of the K-nearest neighbor algorithm, and the predicted category is used as the label. Assuming the feature matrix is ​​X, containing m samples and n features, and the predicted category is y, the i-th row of the feature matrix X represents the features of the i-th sample, and the i-th row of y represents the predicted category of the i-th sample. The feature matrix X and category y are as follows:

[0103]

[0104] Use the training set to train the K-nearest neighbor algorithm and establish a relationship model between the device power consumption value and each feature. Calculate the Euclidean distance between the corresponding vector of the historical communication feature information to be predicted in the test set and the corresponding vector of all historical communication feature information in the training set. Select the K historical communication feature information with the closest Euclidean distance to the historical communication feature information to be predicted from the training set. Then, for the classification task, the voting method is used to determine the category of the historical communication feature information to be predicted based on the predicted category of the K nearest neighbors' historical communication feature information. The voting method for the classification task is described in formula (8), which is as follows:

[0105]

[0106] Among them, Class i is the predicted category of the i-th nearest neighbor, δ(Class i ) is an indicator function. If the predicted category of the historical communication feature information to be predicted is equal to Class i , then it is 1, otherwise it is 0.

[0107] The finally obtained Class is the predicted category of the historical communication feature information to be predicted. Class is the category with the largest number among the predicted categories of the historical communication feature information of the K nearest neighbors.

[0108] For the regression task, according to the power consumption values ​​of the historical communication characteristic information of the K nearest neighbors, an average value or a weighted average value is calculated as the predicted power consumption value of the historical communication characteristic information to be predicted.

[0109] It is understandable that the actual power consumption value of the historical communication feature information needs to be used to adjust the hyperparameters of the initial power consumption classification model so that the final power consumption classification model can classify the historical communication feature information into high power consumption and low power consumption categories.

[0110] In this way, the historical communication feature information is classified into two categories of high power consumption and low power consumption through the power consumption classification model, without the need for manual classification, thereby improving the efficiency and accuracy of classification.

[0111] Based on this, in some embodiments, such as Figure 3 As shown, the above S105 may specifically include:

[0112] S210, obtaining a power consumption value corresponding to the second historical communication characteristic information;

[0113] S220, determining an actual category of the second historical communication characteristic information according to the power consumption value;

[0114] S230, determining an error value of the initial power consumption classification model according to the actual category and the predicted category;

[0115] S240, when the error value does not meet the model training stop condition, update the parameters of the initial power consumption classification model to obtain an updated initial power consumption classification model, classify the first historical communication feature information and the second historical communication feature information using the updated initial power consumption classification model, update the predicted category of the historical communication feature information, until the error value meets the model training stop condition, obtain the target predicted category of the historical communication feature information, and the parameters of the initial power consumption classification model include a first preset number;

[0116] S250: Using the target prediction category of the historical communication feature information, the historical communication feature information is divided into first sub-preset communication feature information and second sub-preset communication feature information.

[0117] In some embodiments, the model is optimized according to the actual category of the second historical communication feature information. According to the actual category and the predicted category, the error value of the initial power consumption classification model is determined. When the error value does not meet the model training stop condition, the parameters of the initial power consumption classification model are updated, including the first preset number, and the first historical communication feature information and the second historical communication feature information are classified using the updated initial power consumption classification model, and the predicted category of the historical communication feature information is updated until the error value meets the model training stop condition, and the target predicted category of the historical communication feature information is obtained. Using the target predicted category of the historical communication feature information, the historical communication feature information is divided into the first sub-preset communication feature information and the second sub-preset communication feature information.

[0118] In some embodiments, the first preset number may be updated by a cross-validation method.

[0119] In this way, the parameters of the model are adjusted through the test set to determine the appropriate K value. When the K value is appropriate, the historical communication characteristic information is divided to obtain the first sub-preset communication characteristic information and the second sub-preset communication characteristic information, thereby improving the accuracy of the division of historical communication characteristic information of different categories, thereby improving the accuracy of the predicted power consumption value of the target device, and thereby improving the accuracy of determining the state adjustment strategy.

[0120] Based on this, in some embodiments, such as Figure 4 As shown, the above S120 may specifically include:

[0121] S121. Select a second preset number of target communication characteristic information from preset communication characteristic information, where the second preset number is an updated preset number.

[0122] In some embodiments, the parameters of the model are adjusted through a test set to determine a suitable K value, and the power consumption value of the target device is predicted using the suitable K value.

[0123] In this way, the parameters of the model are adjusted through the test set to determine the appropriate K value. When the K value is appropriate, the power consumption value of the target device is predicted more accurately, thereby improving the accuracy of determining the state adjustment strategy.

[0124] Based on this, in some embodiments, such as Figure 5 As shown, after the above S130, the method may further include:

[0125] S131, obtaining the actual power consumption value of the target device within the target time period;

[0126] S132: When the difference between the actual power consumption value and the predicted power consumption value is greater than a second threshold, display target prompt information.

[0127] In some embodiments, the actual monitored power consumption data is used to calculate evaluation indicators such as prediction error and root mean square error, and the predicted power consumption value is compared with the actual device power consumption value to evaluate the accuracy of the prediction. The root mean square error (RMSE) calculation formula (9) is as follows:

[0128]

[0129] Where n is the number of samples, y i is the actual power consumption value, is the predicted power consumption value.

[0130] In some embodiments, when the difference between the actual power consumption value and the predicted power consumption value is greater than a second threshold, target prompt information is displayed, and the target prompt information is used to remind the user to re-acquire preset communication feature information, including historical communication feature information used to construct a sample.

[0131] In this way, when the preset communication characteristic information used for predicting the power consumption value of the target device cannot adapt to the target device, the user is notified to intervene and the preset communication characteristic information is re-acquired, thereby improving the accuracy of determining the state adjustment strategy.

[0132] Based on this, in some embodiments, the communication characteristic information includes at least the activity level, communication frequency, and activity duration.

[0133] In this way, the power consumption value of the target device can be predicted more accurately through the features that most affect the power consumption of the target device, thereby improving the accuracy of determining the state adjustment strategy.

[0134] In the embodiment provided by the present application, the K-nearest neighbor algorithm is used for power consumption prediction, which can intelligently predict the power consumption level of the device according to the real-time data, so as to formulate an adaptive sleep and wake-up strategy, thereby achieving lower power consumption of the device and making data transmission more stable and timely, and there will be no problem that the terminal cannot receive data immediately due to fixed-cycle sleep for power saving. This solves the problem in the prior art that in order to achieve the purpose of power saving, the eDRX technology is used to put the terminal into periodic sleep, resulting in data being received when it is turned on, but not when it is stopped; it also solves the problem in the prior art that the PSM technology needs to wait for the terminal to actively upload data before sending data.

[0135] The method for determining the state adjustment strategy provided in the embodiment of the present application is to determine the adaptive low-power sleep and wake-up strategy of the NB-IoT device based on the K-nearest neighbor algorithm. The method includes the following seven main parts:

[0136] 1) Collect historical data of NB-IoT devices.

[0137] 2) Extract features from the collected data, including historical device behavior, communication mode, task execution time, and other features;

[0138] 3) Clean the collected data, handle missing values, and standardize them to ensure data consistency and availability;

[0139] 4) Divide the preprocessed data into a training set and a test set. Assume that the total data volume is N and the training set ratio is p. Then the training set size is N×p and the test set size is N×(1-p). For example, 80% of the data is used for training and 20% for testing.

[0140] 5) Use the training set to train the K-nearest neighbor algorithm and establish a relationship model between device power consumption and various features;

[0141] 6) Use sensors to monitor the device status in real time and obtain real-time data on current communication needs and device active time. Monitor the device's communication mode and data transmission status, obtain the device's communication needs in real time, and understand whether the device currently needs to communicate;

[0142] 7) Use the trained K-nearest neighbor model to make real-time predictions on the power consumption of the device in the future.

[0143] Based on the method for determining the state adjustment strategy provided in the above embodiment, the present application also provides a specific implementation of a device for determining the state adjustment strategy. Please refer to the following embodiment.

[0144] See first Figure 6 The state adjustment strategy determination device 300 provided in the embodiment of the present application includes:

[0145] An acquisition module 310 is used to acquire communication characteristic information, preset communication characteristic information, and power consumption value corresponding to the preset communication characteristic information of a target device within a target time period;

[0146] A selection module 320, configured to select a first preset number of target communication characteristic information from preset communication characteristic information, wherein the similarity between the target communication characteristic information and the communication characteristic information of the target device within the target time period is greater than a target value;

[0147] A determination module 330 is used to determine an average value of power consumption values ​​corresponding to target communication characteristic information as a predicted power consumption value of the target device;

[0148] The determination module 330 is also used to determine that the state adjustment strategy of the target device in the target time period is the target state adjustment strategy corresponding to the predicted power consumption value based on the relationship between the preset power consumption value and the preset state adjustment strategy, the preset power consumption value includes the predicted power consumption value, and the preset state adjustment strategy includes the target state adjustment strategy.

[0149] Based on this, in some embodiments, the preset communication characteristic information includes first sub-preset communication characteristic information and second sub-preset communication characteristic information; the apparatus 300 may further include:

[0150] The acquisition module 310 is further configured to acquire historical communication characteristic information of the target device within the target time period before acquiring the preset communication characteristic information of the target device within the target time period and the power consumption value corresponding to the preset communication characteristic information;

[0151] A division module, used to divide the historical communication characteristic information into first historical communication characteristic information and second historical communication characteristic information according to a preset ratio;

[0152] A classification module, used to input the first historical communication feature information and the second historical communication feature information into an initial power consumption classification model, and classify the first historical communication feature information using the initial power consumption classification model to obtain a predicted category of the first historical communication feature information;

[0153] The determination module 330 is further configured to select, for each target historical communication feature information in the second historical communication feature information, a first preset number of third historical communication feature information from the first historical communication feature information, and determine the target prediction category with the most prediction categories of the first preset number of third historical communication feature information as the prediction category of the target historical communication feature information, and the similarity between the third historical communication feature information and the corresponding target historical communication feature information is greater than a target value;

[0154] The division module is further used to divide the historical communication characteristic information into first sub-preset communication characteristic information and second sub-preset communication characteristic information according to the predicted category of the historical communication characteristic information;

[0155] The predicted categories of historical communication characteristic information include a first category and a second category, the power consumption value corresponding to the historical communication characteristic information of the first category is greater than a first threshold, and the power consumption value corresponding to the historical communication characteristic information of the second category is not greater than the first threshold.

[0156] Based on this, in some embodiments, the partitioning module can be specifically used for:

[0157] Obtaining a power consumption value corresponding to the second historical communication characteristic information;

[0158] determining, according to the power consumption value, an actual category of the second historical communication characteristic information;

[0159] Determine an error value of an initial power consumption classification model according to the actual category and the predicted category;

[0160] When the error value does not meet the model training stop condition, update the parameters of the initial power consumption classification model to obtain an updated initial power consumption classification model, use the updated initial power consumption classification model to classify the first historical communication feature information and the second historical communication feature information, and update the predicted category of the historical communication feature information until the error value meets the model training stop condition to obtain the target predicted category of the historical communication feature information, wherein the parameters of the initial power consumption classification model include a first preset number;

[0161] The target prediction category of the historical communication feature information is used to divide the historical communication feature information into first sub-preset communication feature information and second sub-preset communication feature information.

[0162] Based on this, in some embodiments, the selection module 320 can be specifically used to:

[0163] A second preset number of target communication characteristic information is selected from the preset communication characteristic information, where the second preset number is the updated preset number.

[0164] Based on this, in some embodiments, the apparatus 300 may further include:

[0165] The acquisition module 310 is further configured to acquire the actual power consumption value of the target device within the target time period after determining the average value of the power consumption value corresponding to the target communication characteristic information as the predicted power consumption value of the target device;

[0166] The display module is used to display target prompt information when the difference between the actual power consumption value and the predicted power consumption value is greater than a second threshold.

[0167] Based on this, in some embodiments, the communication characteristic information includes at least the activity level, communication frequency, and activity duration.

[0168] The various modules of the state adjustment strategy determination device provided in the embodiment of the present application can realize the functions of the various steps of the state adjustment strategy determination method provided above and achieve the corresponding technical effects, which will not be repeated here for the sake of concise description.

[0169] Based on the same inventive concept, an embodiment of the present application also provides an electronic device.

[0170] Figure 7 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application is shown.

[0171] The electronic device may include a processor 401 and a memory 402 storing computer program instructions.

[0172] Specifically, the processor 401 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0173] Memory 402 may include a large capacity memory for data or instructions. By way of example and not limitation, memory 402 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, memory 402 may include a removable or non-removable (or fixed) medium. In appropriate cases, memory 402 may be inside or outside of an integrated gateway disaster recovery device. In a specific embodiment, memory 402 is a non-volatile solid-state memory.

[0174] The memory may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk storage medium device, an optical storage medium device, a flash memory device, an electrical, optical or other physical / tangible memory storage device. Therefore, generally, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., a memory device) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to one aspect of the present disclosure.

[0175] The processor 401 implements any one of the state adjustment strategy determination methods in the above embodiments by reading and executing computer program instructions stored in the memory 402 .

[0176] In one example, the electronic device may further include a communication interface 403 and a bus 410. Figure 7 As shown, the processor 401, the memory 402, and the communication interface 403 are connected via a bus 410 and communicate with each other.

[0177] The communication interface 403 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0178] The bus 410 includes hardware, software or both, coupling the components of the electronic device to each other. For example, but not limitation, the bus may include an accelerated graphics port (Accelerated Graphics Port, AGP) or other graphics bus, an enhanced industry standard architecture (Extended Industry Standard Architecture, EISA) bus, a front side bus (Front Side Bus, FSB), a hypertransport (Hyper Transport, HT) interconnection, an industry standard architecture (Industry Standard Architecture, ISA) bus, an infinite bandwidth interconnection, a low pin count (Linear Predictive Coding, LPC) bus, a memory bus, a micro channel architecture (MicroChannel Architecture, MCA) bus, a peripheral component interconnect (Peripheral Component Interconnect, PCI) bus, a PCI-Express (Peripheral Component Interconnect-X, PCI-X) bus, a serial advanced technology attachment (Serial Advanced Technology Attachment, SATA) bus, a video electronics standard association local (VESA Local Bus, VLB) bus or other suitable buses or a combination of two or more of these. Where appropriate, the bus 410 may include one or more buses. Although the embodiments of the present application describe and illustrate a specific bus, the present application considers any suitable bus or interconnection. The electronic device can execute the state adjustment strategy determination method in the embodiments of the present invention, thereby implementing the above-mentioned state adjustment strategy determination method.

[0179] In addition, in combination with the method for determining the state adjustment strategy in the above embodiment, the embodiment of the present application can provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when the computer program instructions are executed by the processor, any one of the methods for determining the state adjustment strategy in the above embodiment is implemented.

[0180] The present application also provides a computer program product. When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes each process of an embodiment of a method for determining any one of the above-mentioned state adjustment strategies.

[0181] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.

[0182] The functional blocks shown in the structural block diagram described above can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), appropriate firmware, plug-in, function card, etc. When implemented in software, the elements of the present application are programs or code segments used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or communication link by a data signal carried in a carrier. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, read-only memory (Read-Only Memory, ROM), flash memory, erasable read-only memory (Erasable ReadOnly Memory, EROM), floppy disks, compact disc read-only memory (Compact Disc Read-Only Memory, CD-ROM), optical discs, hard disks, optical fiber media, radio frequency (Radio Frequency, RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0183] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.

[0184] Aspects of the present disclosure are described above with reference to the flowchart and / or block diagram of the method, device (system) and computer program product according to the embodiment of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the function / action specified in one or more boxes of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field programmable logic circuit. It can also be understood that each box in the block diagram and / or flowchart and the combination of boxes in the block diagram and / or flowchart can also be implemented by dedicated hardware that performs a specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0185] The above are only specific implementation methods of the present application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present application is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the protection scope of this application.

Claims

1. A method for determining a state adjustment strategy, characterized in that: include: Acquire communication characteristic information, preset communication characteristic information, and power consumption values ​​corresponding to the preset communication characteristic information of a target device within a target time period; Selecting a first preset number of target communication characteristic information from the preset communication characteristic information, wherein the similarity between the target communication characteristic information and the communication characteristic information of the target device within the target time period is greater than a target value; Determine an average value of the power consumption values ​​corresponding to the target communication characteristic information as the predicted power consumption value of the target device; According to the relationship between the preset power consumption value and the preset state adjustment strategy, the state adjustment strategy of the target device within the target time period is determined to be the target state adjustment strategy corresponding to the predicted power consumption value, the preset power consumption value includes the predicted power consumption value, and the preset state adjustment strategy includes the target state adjustment strategy.

2. The method for determining a state adjustment strategy according to claim 1, wherein: The preset communication characteristic information includes first sub-preset communication characteristic information and second sub-preset communication characteristic information; Before obtaining preset communication characteristic information of the target device within the target time period and the power consumption value corresponding to the preset communication characteristic information, the method further includes: Acquire historical communication feature information of the target device within the target time period; Dividing the historical communication feature information into first historical communication feature information and second historical communication feature information according to a preset ratio; inputting the first historical communication feature information and the second historical communication feature information into an initial power consumption classification model, and classifying the first historical communication feature information using the initial power consumption classification model to obtain a predicted category of the first historical communication feature information; For each target historical communication feature information in the second historical communication feature information, selecting a first preset number of third historical communication feature information from the first historical communication feature information, and determining the target prediction category with the largest number of prediction categories among the first preset number of third historical communication feature information as the prediction category of the target historical communication feature information, wherein the similarity between the third historical communication feature information and the corresponding target historical communication feature information is greater than the target value; According to the prediction category of the historical communication feature information, the historical communication feature information is divided into first sub-preset communication feature information and second sub-preset communication feature information; The predicted categories of the historical communication feature information include a first category and a second category. The power consumption value corresponding to the historical communication feature information of the first category is greater than a first threshold, and the power consumption value corresponding to the historical communication feature information of the second category is not greater than the first threshold.

3. The method for determining a state adjustment strategy according to claim 2, wherein: The dividing the historical communication feature information into first sub-preset communication feature information and second sub-preset communication feature information according to the category of the historical communication feature information includes: Obtaining a power consumption value corresponding to the second historical communication characteristic information; determining an actual category of the second historical communication feature information according to the power consumption value; determining an error value of the initial power consumption classification model according to the actual category and the predicted category; When the error value does not meet the model training stop condition, updating the parameters of the initial power consumption classification model to obtain an updated initial power consumption classification model, using the updated initial power consumption classification model to classify the first historical communication feature information and the second historical communication feature information, and updating the predicted category of the historical communication feature information until the error value meets the model training stop condition to obtain a target predicted category of the historical communication feature information, wherein the parameters of the initial power consumption classification model include the first preset number; The target prediction category of the historical communication feature information is used to divide the historical communication feature information into first sub-preset communication feature information and second sub-preset communication feature information.

4. The method for determining a state adjustment strategy according to claim 3, wherein: The selecting a first preset number of target communication feature information from the preset communication feature information includes: A second preset number of target communication feature information is selected from the preset communication feature information, where the second preset number is an updated preset number.

5. The method for determining a state adjustment strategy according to claim 1, wherein: After determining the average value of the power consumption values ​​corresponding to the target communication characteristic information as the predicted power consumption value of the target device, the method further includes: Obtaining an actual power consumption value of the target device within the target time period; When the difference between the actual power consumption value and the predicted power consumption value is greater than a second threshold, target prompt information is displayed.

6. The method for determining a state adjustment strategy according to claim 1, wherein: The communication characteristic information includes at least activity level, communication frequency, and activity duration.

7. A device for determining a state adjustment strategy, characterized in that: include: An acquisition module, configured to acquire communication characteristic information, preset communication characteristic information, and power consumption values ​​corresponding to the preset communication characteristic information of a target device within a target time period; a selection module, configured to select a first preset number of target communication characteristic information from the preset communication characteristic information, wherein the similarity between the target communication characteristic information and the communication characteristic information of the target device within the target time period is greater than a target value; a determination module, configured to determine an average value of the power consumption values ​​corresponding to the target communication characteristic information as the predicted power consumption value of the target device; The determination module is also used to determine, based on the relationship between the preset power consumption value and the preset state adjustment strategy, that the state adjustment strategy of the target device within the target time period is the target state adjustment strategy corresponding to the predicted power consumption value, the preset power consumption value includes the predicted power consumption value, and the preset state adjustment strategy includes the target state adjustment strategy.

8. An electronic device, characterized in that: The device includes: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, the method for determining the state adjustment strategy according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed by a processor, the method for determining a state adjustment strategy according to any one of claims 1 to 6 is implemented.

10. A computer program product, characterized in that When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device is enabled to execute the method for determining a state adjustment strategy according to any one of claims 1 to 6.

Images