Terminal low-power-consumption data processing method and system, electronic equipment and storage medium

Abstract

The invention discloses a terminal low-power-consumption data processing method and system, electronic equipment and a storage medium, and the method comprises the steps: inputting collected first collection data of a terminal at a previous collection moment into a prediction model, and obtaining second collection data of the terminal at a current collection moment; acquiring third acquisition data of the terminal at the current acquisition moment; the third acquisition data is a real result corresponding to the second acquisition data; and determining the prediction accuracy according to the second collection data and the third collection data, and adjusting the data reporting frequency of the terminal according to the prediction accuracy. According to the embodiment of the application, the data reporting frequency of the terminal is adjusted by comparing the second acquisition data predicted at the current acquisition moment with the actually acquired third acquisition data, so that the power consumption of data transmission can be reduced and the operation cost of the system can be reduced on the premise of not reducing the data acquisition frequency and accuracy. The method can be widely applied to the technical field of Internet of Things.

Description

Technical Field

[0001] The present application relates to the technical field of Internet of Things, and in particular to a low-power consumption data processing method, system, electronic device and storage medium for a terminal. Background Art

[0002] Base wine is an important raw material for wine companies, and it is also an important fixed asset and collateral for companies when applying for financial loans. Before the finished wine is produced, it needs to be strictly sealed and protected. In related technologies, base wine data is usually collected at regular intervals, and the collected data is uploaded to the cloud for storage. The data collection and uploading process is very power-consuming, resulting in a short battery life and high operating costs for the entire system. Summary of the invention

[0003] The main purpose of the embodiments of the present application is to provide a low-power data processing method, system, electronic device and storage medium for a terminal.

[0004] To achieve the above-mentioned purpose, one aspect of an embodiment of the present application proposes a low-power data processing method for a terminal, the method comprising: inputting the first collected data of the terminal at the previous collection moment into a prediction model to obtain the second collected data of the terminal at the current collection moment; obtaining the third collected data of the terminal at the current collection moment; the third collected data is the real result corresponding to the second collected data; according to the second collected data and the third collected data, the prediction accuracy is determined, and according to the prediction accuracy, the data reporting frequency of the terminal is adjusted. By comparing the second collected data predicted at the current collection moment with the third collected data actually collected, the embodiment of the present application adjusts the data reporting frequency of the terminal, which can reduce the power consumption of data transmission and reduce the operating cost of the system without reducing the frequency and accuracy of data collection.

[0005] In some embodiments, the method provided in the embodiments of the present application, adjusting the data reporting frequency of the terminal according to the prediction accuracy, includes:

[0006] If the prediction accuracy is greater than or equal to a first threshold, reducing the acquisition frequency;

[0007] Alternatively, if the prediction accuracy is less than the first threshold, the acquisition frequency is maintained.

[0008] In some embodiments, the method provided by the embodiments of the present application, if the prediction accuracy is greater than or equal to a first threshold, reducing the acquisition frequency includes:

[0009] Determining a first ratio according to a difference between the prediction accuracy and the first threshold;

[0010] The acquisition frequency is updated according to the first ratio to obtain the adjusted acquisition frequency.

[0011] In some embodiments, the method provided by the embodiments of the present application, wherein the first collected data of the terminal at the previous collection time is input into the prediction model to obtain the second collected data of the terminal at the current collection time, comprises:

[0012] Processing the first collected data through an input layer to obtain a first feature;

[0013] Input the first feature into the first convolution layer and the second convolution layer respectively to obtain the third feature and the fourth feature; the number of convolution kernels of the first convolution layer is 32, and the number of convolution kernels of the second convolution layer is 64;

[0014] Inputting the third feature and the fourth feature into a pooling layer to obtain a fifth feature;

[0015] The fifth feature is processed through a fully connected layer and an output layer to obtain second collected data.

[0016] In some embodiments, the method provided by the embodiments of the present application further includes:

[0017] Get the accumulated duration;

[0018] If the cumulative duration is greater than or equal to the preset duration, the second collected data and the third collected data obtained within the current cumulative duration are used as training data, the prediction model is trained based on the adaptive moment estimation optimizer and stochastic gradient descent, the parameters of the prediction model are updated, the trained prediction model is obtained, and the accumulated duration is returned; the accumulated duration is the duration elapsed from the time the parameters of the prediction model are updated, and the preset duration is the period for updating the prediction model.

[0019] In some embodiments, the method provided by the embodiments of the present application further includes:

[0020] If the prediction accuracy is greater than or equal to a second threshold, extending the preset time duration;

[0021] Alternatively, if the prediction accuracy is less than the second threshold, the preset time duration is shortened.

[0022] In some embodiments, in the method provided by the embodiment of the present application, the collected data includes several collected parameters, and the determining of the prediction accuracy according to the second collected data and the third collected data includes:

[0023] Determining first accuracy of a plurality of field values ​​according to the second collected data and the third collected data; the second collected data includes a plurality of field values, and the field values ​​correspond to the collection parameters;

[0024] The prediction accuracy is determined according to the first accuracy and the corresponding weight.

[0025] To achieve the above object, another aspect of an embodiment of the present application provides a low-power data processing system for a terminal, the system comprising:

[0026] The first module is used to input the first collected data of the terminal at the previous collection time into the prediction model to obtain the second collected data of the terminal at the current collection time;

[0027] The second module is used to obtain the third collected data of the terminal at the current collection time; the third collected data is the real result corresponding to the second collected data;

[0028] The third module is used to determine the prediction accuracy according to the second collected data and the third collected data, and adjust the data reporting frequency of the terminal according to the prediction accuracy.

[0029] To achieve the above objective, another aspect of an embodiment of the present application provides an electronic device, the electronic device comprising a memory and a processor, the memory storing a computer program, and the processor implementing the above method when executing the computer program.

[0030] To achieve the above objective, another aspect of an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program implements the above method when executed by a processor.

[0031] The embodiments of the present application include at least the following beneficial effects: The method provided by the embodiments of the present application includes: inputting the first collected data of the terminal at the previous collection time into the prediction model to obtain the second collected data of the terminal at the current collection time; obtaining the third collected data of the terminal at the current collection time; the third collected data is the real result corresponding to the second collected data; according to the second collected data and the third collected data, the prediction accuracy is determined, and according to the prediction accuracy, the data reporting frequency of the terminal is adjusted. The embodiments of the present application adjust the data reporting frequency of the terminal by comparing the second collected data predicted at the current collection time with the third collected data actually collected, which can reduce the power consumption of data transmission and reduce the operating cost of the system without reducing the frequency and accuracy of data collection. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1A comparative schematic diagram of various embodiments of the data collection process provided in the related art;

[0033] Figure 2 A comparison diagram of advantages of an embodiment of the data collection process provided by the present application;

[0034] Figure 3 A schematic diagram showing the power consumption comparison during data collection and transmission provided by this application;

[0035] Figure 4 It is a flowchart of an embodiment of a low-power data processing method for a terminal provided by the present application;

[0036] Figure 5 It is a structural schematic diagram of an embodiment of the prediction model provided by the present application;

[0037] Figure 6 is a flowchart of an embodiment of a model updating process provided by the present application;

[0038] Figure 7 is a flowchart of another embodiment of the low-power data processing method for a terminal provided by the present application;

[0039] Figure 8 is a curve diagram of an embodiment of the accuracy of the prediction model provided by the present application;

[0040] Fig. 9 It is a structural diagram of a low-power data processing system for a terminal provided in an embodiment of the present application;

[0041] Fig.10 It is a schematic diagram of the hardware structure of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0042] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is further described in detail below in conjunction with the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the embodiments of the present application. They are only examples of devices and methods consistent with some aspects of the embodiments of the present application as detailed in the attached claims.

[0043] It is understood that the terms "first", "second", etc. used in this application can be used to describe various concepts in this article, but unless otherwise specified, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another concept. For example, without departing from the scope of the embodiment of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the words "if" and "if" as used herein can be interpreted as "at the time of" or "when" or "in response to determination".

[0044] The terms "at least one", "multiple", "each", "any", etc. used in this application, at least one includes one, two or more, multiple includes two or more, each refers to each of the corresponding multiple, and any refers to any one of the multiple.

[0045] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0046] Base wine is an important raw material for wine companies, and is also an important fixed asset and collateral for companies to obtain financial loans. Before the production of finished wine, it needs to be strictly sealed and protected. Figure 1 As shown, in the related art, the collector can be powered by strong electricity to collect and upload the base wine data. However, this solution is difficult to install and deploy, has high cost, and consumes a lot of power. In another embodiment, the collector can be powered by a battery to collect and upload data. In this solution, the battery needs to be replaced frequently, and there is also a problem of high power consumption.

[0047] Based on the above background, the present invention is based on a data acquisition terminal, a wireless data transceiver module, and a cloud system. The data acquisition terminal is responsible for collecting various data indicators of the base wine, including but not limited to the base wine liquid level, alcohol content, density, temperature, battery voltage, etc., and then handed over to the wireless data transceiver module to send it to the cloud system. The cloud system realizes the storage, analysis and processing of the base wine data. The average power consumption of the data acquisition terminal for each collection is about 15uA, while the average power consumption of the wireless data transceiver module for uploading data once is 130uA, which is about 8 times that of data collection. The present invention adopts a method to predict the next measurement value through AI algorithm learning, and then dynamically adjusts the data reporting frequency of the terminal according to the accuracy of the prediction, which greatly reduces the overall power consumption. Refer to Figure 2 As shown, for a system in which the collector is powered by a battery, the collection method provided by this application greatly reduces power consumption, achieving simple system installation and deployment, low power consumption, and low operation and maintenance costs.

[0048] It can be understood that this method improves the traditional scheme according to the characteristics of base wine data collection to reduce the cost of data collection.

[0049] See below for a specific embodiment:

[0050] 1. The collection of base wine storage data has the following multiple data values:

[0051] {"ID":"17120962131223","time":2024-09-10 12:00:00,"wine":11.1,"ru":83.2,"weight":889.7,"tmp":26.5,"high":1112.1,"voltage":3.2}.

[0052] 2. After multiple terminal data collection tests, the results show that the average power consumption of the terminal for one collection is about 15uA, and the average power consumption for sending to the cloud is about 130uA. Figure 3 shown.

[0053] 3. The traditional method collects data once and sends it once. If data is collected once every hour, the total power consumption for one month is about: 30*24*(15+130)=104.4mA. The power of a standard CR2032 battery is 240mA. Under this method, the battery needs to be replaced every 2 months, and the operation and maintenance cost of the terminal is high.

[0054] This system aims to solve the problem of data collection of base wine during storage. Using the improved solution of this method to collect base wine data can greatly extend the battery life of the collection equipment and reduce the operation and maintenance cost of base wine data collection.

[0055] The terminal low-power data processing method provided in the embodiment of the present application relates to the field of Internet of Things technology. The terminal low-power data processing method provided in the embodiment of the present application can be applied to the terminal, can also be applied to the server, and can also be software running in the terminal or the server. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, and a car terminal, etc., but is not limited to this; the server side can be configured as an independent physical server, or it can be configured as a server cluster or distributed system composed of multiple physical servers, and can also be configured to provide cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms and other basic cloud computing services. The cloud server, the server can also be a node server in the blockchain network; the software can be an application of a data processing method for realizing terminal low power consumption, etc., but is not limited to the above forms.

[0056] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0057] It should be noted that in each specific implementation of the present application, when it comes to the need to perform relevant processing based on data related to user identity or characteristics such as user information, user behavior data, user historical data, and user location information, the user's permission or consent will be obtained first, and the collection, use, and processing of these data will comply with relevant laws, regulations, and standards. In addition, when the embodiment of the present application needs to obtain the user's sensitive personal information, the user's separate permission or consent will be obtained through a pop-up window or by jumping to a confirmation page. After clearly obtaining the user's separate permission or consent, the necessary user-related data for the normal operation of the embodiment of the present application will be obtained.

[0058] Figure 4 This is an optional flowchart of the low-power data processing method for a terminal provided in an embodiment of the present application; Figure 4 The method may include but is not limited to steps S100 to S300.

[0059] Step S100, inputting the first collected data of the terminal at the previous collection time into the prediction model to obtain the second collected data of the terminal at the current collection time;

[0060] Step S200, obtaining the third collected data of the terminal at the current collection time; the third collected data is the real result corresponding to the second collected data;

[0061] Step S300: determining prediction accuracy according to the second collected data and the third collected data, and adjusting the data reporting frequency of the terminal according to the prediction accuracy.

[0062] In the embodiment of the present application, the second collected data is the predicted data based on the current moment. It is understandable that, for the base wine data, the cloud needs to obtain the collected data of the terminal at intervals, or the terminal uploads the collected data to the cloud. In the present application, the second collected data (predicted result) at the current collection moment is predicted by the first collected data (real result) at the previous collection moment, and the second collected data is compared and analyzed with the third collected data (real result) collected at the current collection moment, and the reporting frequency is adjusted according to the comparison and analysis results. It is understandable that the present application adjusts the data reporting frequency of the terminal after data collection. It is understandable that, according to relevant experience, the power consumption of data collection is not high, mainly because the power consumption is high when the data is reported and transmitted. Therefore, in the embodiment of the present application, the collection frequency is not reduced, and the collection is performed regularly and normally according to the business requirements, but it is not necessarily reported every time the collection is completed. It is dynamically adjusted according to the accuracy of the prediction model. For example, it can be adjusted to report 1 data per day, and the reported data includes the data results collected throughout the day. In this regard, the embodiment of the present application can adjust the reporting frequency according to the prediction accuracy of the collected data. In some embodiments, the embodiments of the present application can lower the reporting frequency, reduce the number of reports, and thereby reduce the energy consumption caused by data reporting.

[0063] In some embodiments, the method provided in the embodiments of the present application adjusts the data reporting frequency of the terminal according to the prediction accuracy, including:

[0064] If the prediction accuracy is greater than or equal to the first threshold, reduce the data reporting frequency;

[0065] Alternatively, if the prediction accuracy is less than the first threshold, the data reporting frequency is maintained.

[0066] In some possible implementations, the first threshold is an acceptable prediction accuracy. Exemplarily, the first threshold can be 90% or 92%, and the present application does not limit the specific value of the first threshold. If the prediction accuracy is greater than the first threshold, the collected data from the previous collection moment to the current collection moment can be predicted to a certain extent by the collected data at the previous collection moment, and the performance of the base wine can be evaluated by the predicted collected data to prevent abnormal / accidental situations; at the same time, the data is continuously collected and recorded. Therefore, at this time, the reporting frequency can be reduced, the reporting interval can be lengthened, and the number of reports can be reduced. In another embodiment, if the prediction accuracy is greater than the first threshold, the current reporting frequency can be maintained. Of course, the current reporting frequency can also be increased, and those skilled in the art can adjust it according to actual needs. The present application does not make specific limitations.

[0067] In some embodiments, the method provided in the embodiments of the present application, if the prediction accuracy is greater than or equal to the first threshold, reduces the data reporting frequency, including:

[0068] Determining a first ratio according to a difference between the prediction accuracy and a first threshold;

[0069] The data reporting frequency is updated according to the first ratio to obtain an adjusted data reporting frequency.

[0070] In some possible implementations, the adjustment strategy for the data reporting frequency in the embodiments of the present application can be formulated according to actual needs. In some embodiments, the first ratio can be determined based on the difference between the prediction accuracy and the first threshold. The first ratio can characterize the percentage by which the adjusted data reporting frequency is reduced compared to the current data reporting frequency. Of course, it is understandable that a comparison table of the difference and the data reporting frequency can also be set, and the adjusted data reporting frequency can be determined by table comparison. A functional relationship between the difference and the data reporting frequency can also be set, and the adjusted data reporting frequency can be determined by mathematical calculation.

[0071] In some embodiments, the method provided in the embodiments of the present application refers to Figure 5 As shown, the first collected data of the terminal at the previous collection time is input into the prediction model to obtain the second collected data of the terminal at the current collection time, including:

[0072] Processing the first collected data through the input layer to obtain a first feature;

[0073] The first feature is input into the first convolution layer and the second convolution layer respectively to obtain the third feature and the fourth feature; the number of convolution kernels in the first convolution layer is 32, and the number of convolution kernels in the second convolution layer is 64;

[0074] Input the third feature and the fourth feature into the pooling layer to obtain the fifth feature;

[0075] The fifth feature is processed through the fully connected layer and the output layer to obtain the second collected data.

[0076] In some embodiments, reference Figure 6 As shown, the method provided in the embodiment of the present application further includes:

[0077] Step S400, obtaining the accumulated duration;

[0078] Step S500, if the cumulative duration is greater than or equal to the preset duration, the second collected data and the third collected data obtained within the current cumulative duration are used as training data, the prediction model is trained based on the adaptive moment estimation optimizer and the stochastic gradient descent, the parameters of the prediction model are updated, the trained prediction model is obtained, and the cumulative duration is returned; the cumulative duration is the duration elapsed from the time the parameters of the prediction model are updated, and the preset duration is the period for updating the prediction model.

[0079] In some possible implementations, the embodiments of the present application may retrain the prediction model at regular intervals (ie, cumulative duration) to optimize the parameters of the prediction model.

[0080] In some embodiments, the method provided by the embodiments of the present application further includes:

[0081] If the prediction accuracy is greater than or equal to the second threshold, extend the preset time;

[0082] Alternatively, if the prediction accuracy is less than the second threshold, the preset time duration is shortened.

[0083] In some possible implementations, the second threshold value may also represent an expected value for the prediction accuracy of the prediction model. In the embodiments of the present application, the first threshold value and the second threshold value are not substantially related in magnitude. In some embodiments, the first threshold value may be the same as the second threshold value, and in other embodiments, the first threshold value may be different from the second threshold value. This application does not make specific limitations.

[0084] In some embodiments, the method provided in the embodiments of the present application, the collected data includes several collected parameters, and the prediction accuracy is determined according to the second collected data and the third collected data, including:

[0085] Determining first accuracy of a plurality of field values ​​according to the second collected data and the third collected data; the second collected data includes a plurality of field values, and the field values ​​correspond to the collection parameters;

[0086] The prediction accuracy is determined according to the first accuracy and the corresponding weight.

[0087] Below, refer to Figure 7 As shown, in combination with specific application examples, the scheme of the embodiment of the present invention is described in detail and explained:

[0088] First, a convolutional neural network (CNN) machine learning algorithm environment is established in the cloud system. The collected data of the terminal is then input into CNN as input to obtain a predicted value, which is then compared with the subsequently collected data to obtain the overall accuracy. Finally, the data transmission frequency of the terminal is dynamically adjusted according to the accuracy value to reduce the number of transmissions and achieve the purpose of reducing terminal power consumption.

[0089] Specific implementation process:

[0090] (1) Establish a convolutional neural network (CNN) machine learning algorithm environment in the cloud system. The specific implementation process is as follows:

[0091] (2) The algorithm structure is set to: input layer, two convolutional layers, one pooling layer, two fully connected layers and output layer.

[0092] (3) The convolution kernel size is set to 3×3, and the number is 32 and 64 respectively.

[0093] (4) The pooling layer uses maximum pooling with a window size of 2×2 to improve computational efficiency.

[0094] (5) ReLU is selected as the activation function to increase the nonlinear expression ability of CNN.

[0095] (6) The training algorithm uses stochastic gradient descent, and the optimizer selects Adam to update the weights and biases of CNN.

[0096] (7) Based on the collected experimental data set, the algorithm is trained through the experimental data set, and finally an algorithm model with an accuracy rate greater than 90% is obtained.

[0097] (8) Apply the algorithm model to the actual production environment to predict production data.

[0098] (9) Input the collected data from the Nth terminal into the CNN as input. These collected data may include but are not limited to base wine liquid level, alcohol content, density, temperature, battery voltage, etc. The data may be preprocessed before input, such as normalization, denoising, etc., to improve the accuracy of the algorithm.

[0099] (10) The data collected by the terminal for the N+1th time is used as the result, and compared with the data collected for the Nth time after being predicted by the algorithm model. The accuracy of each field value is calculated separately first, and then aggregated to obtain the overall accuracy A, which is as follows:

[0100] a k =C k / S k ×100%

[0101]

[0102] Among them, a k represents the accuracy of the kth field, C k represents the predicted value of the kth field, S k represents the actual value of the kth field, f(x) represents the overall accuracy A, p k represents the weight of the kth field, and N represents the total number of fields.

[0103] (11) Dynamically adjust the data transmission frequency of the terminal according to the value of the accuracy rate A. When the overall accuracy rate is greater than 90%, increase the interval of the data transmission frequency, reduce the number of transmissions by 10%, and increase the accuracy rate by 1% each time. The transmission frequency is reduced by 10% on the original basis. That is, when the accuracy rate is greater than 99%, the transmission frequency is reduced to 99% of the original frequency, and the minimum is once a day, thereby achieving the purpose of reducing the power consumption of the terminal. Figure 8 As shown in FIG. 1 , the relationship between the prediction accuracy of the prediction model and the number of data reports is that when the prediction accuracy is high, the number of reports can be appropriately reduced.

[0104] This system helps liquor companies collect data on base liquor at a lower cost. The embodiments of this application can be applied to the following scenarios: liquor industry scenarios, such as base liquor storage, etc.; other brewing industries. Of course, the method provided in this application can also be used in other scenarios in other industries, by adjusting the frequency of data collection to reduce power consumption. This application does not limit the application industries and scenarios in detail.

[0105] See also Fig. 9 The embodiment of the present application also provides a low-power data processing system for a terminal, which can implement the above-mentioned low-power data processing method for a terminal, and the system includes:

[0106] The first module 610 is used to input the first collected data of the terminal at the previous collection time into the prediction model to obtain the second collected data of the terminal at the current collection time;

[0107] The second module 620 is used to obtain the third collected data of the terminal at the current collection time; the third collected data is the real result corresponding to the second collected data;

[0108] The third module 630 is used to determine the prediction accuracy according to the second collected data and the third collected data, and adjust the data reporting frequency of the terminal according to the prediction accuracy.

[0109] In some embodiments, the system provided by the embodiments of the present application further includes a fourth module for:

[0110] Get the accumulated duration;

[0111] If the cumulative duration is greater than or equal to the preset duration, the second collected data and the third collected data obtained within the current cumulative duration are used as training data, and the prediction model is trained based on the adaptive moment estimation optimizer and stochastic gradient descent, and the parameters of the prediction model are updated to obtain the trained prediction model, and the cumulative duration is returned; the cumulative duration is the time elapsed after the parameters of the prediction model are updated, and the preset duration is the period for updating the prediction model.

[0112] It can be understood that the contents of the above method embodiments are all applicable to the present system embodiments, the functions specifically implemented by the present system embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0113] The embodiment of the present application also provides an electronic device, the electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the above-mentioned terminal low-power data processing method when executing the computer program. The electronic device can be any intelligent terminal including a tablet computer, a car computer, etc.

[0114] It can be understood that the contents of the above method embodiments are all applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0115] See also Fig.10 , Fig.10 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:

[0116] The processor 901 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;

[0117] The memory 902 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 902 can store an operating system and other applications. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 902, and the processor 901 calls and executes the terminal low-power data processing method of the embodiment of this application;

[0118] Input / output interface 903, used to implement information input and output;

[0119] Communication interface 904, used to realize communication interaction between the device and other devices, which can be realized by wired mode (such as USB, network cable, etc.) or wireless mode (such as mobile network, WIFI, Bluetooth, etc.);

[0120] A bus 905 that transmits information between various components of the device (e.g., the processor 901, the memory 902, the input / output interface 903, and the communication interface 904);

[0121] The processor 901 , the memory 902 , the input / output interface 903 and the communication interface 904 are connected to each other in communication within the device via a bus 905 .

[0122] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the low-power data processing method for the terminal is implemented.

[0123] It can be understood that the contents of the above method embodiments are all applicable to the present storage medium embodiments, the functions specifically implemented by the present storage medium embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0124] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0125] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0126] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0127] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0128] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0129] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0130] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0131] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0132] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0133] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0134] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.

[0135] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.

Claims

1. A low-power terminal data processing method, characterized in that: The method comprises: Inputting the first collected data of the terminal at the previous collection time into the prediction model to obtain the second collected data of the terminal at the current collection time; Acquire third collected data of the terminal at the current collection time; the third collected data is a true result corresponding to the second collected data; The prediction accuracy is determined according to the second collected data and the third collected data, and the data reporting frequency of the terminal is adjusted according to the prediction accuracy.

2. The method according to claim 1, characterized in that The adjusting the data reporting frequency of the terminal according to the prediction accuracy includes: If the prediction accuracy is greater than or equal to a first threshold, reducing the data reporting frequency; Alternatively, if the prediction accuracy is less than the first threshold, the data reporting frequency is maintained.

3. The method according to claim 2, characterized in that If the prediction accuracy is greater than or equal to a first threshold, reducing the data reporting frequency includes: Determining a first ratio according to a difference between the prediction accuracy and the first threshold; The data reporting frequency is updated according to the first ratio to obtain the adjusted data reporting frequency.

4. The method according to claim 1, characterized in that The step of inputting the first collected data of the terminal at the previous collection time into the prediction model to obtain the second collected data of the terminal at the current collection time includes: Processing the first collected data through an input layer to obtain a first feature; Input the first feature into the first convolution layer and the second convolution layer respectively to obtain the third feature and the fourth feature; the number of convolution kernels of the first convolution layer is 32, and the number of convolution kernels of the second convolution layer is 64; Inputting the third feature and the fourth feature into a pooling layer to obtain a fifth feature; The fifth feature is processed through a fully connected layer and an output layer to obtain second collected data.

5. The method according to claim 1, characterized in that: The method further comprises: Get the accumulated duration; If the cumulative duration is greater than or equal to the preset duration, the second collected data and the third collected data obtained within the current cumulative duration are used as training data, the prediction model is trained based on the adaptive moment estimation optimizer and stochastic gradient descent, the parameters of the prediction model are updated, the trained prediction model is obtained, and the accumulated duration is returned; the accumulated duration is the duration elapsed from the time the parameters of the prediction model are updated, and the preset duration is the period for updating the prediction model.

6. The method according to claim 5, characterized in that The method further comprises: If the prediction accuracy is greater than or equal to a second threshold, extending the preset time duration; Alternatively, if the prediction accuracy is less than the second threshold, the preset time duration is shortened.

7. The method according to claim 1, characterized in that The collected data includes several collected parameters, and the step of determining the prediction accuracy according to the second collected data and the third collected data includes: Determining first accuracy of a plurality of field values ​​according to the second collected data and the third collected data; the second collected data includes a plurality of field values, and the field values ​​correspond to the collection parameters; The prediction accuracy is determined according to the first accuracy and the corresponding weight.

8. A low-power terminal data processing system, characterized in that: The system comprises: The first module is used to input the first collected data of the terminal at the previous collection time into the prediction model to obtain the second collected data of the terminal at the current collection time; The second module is used to obtain the third collected data of the terminal at the current collection time; the third collected data is the real result corresponding to the second collected data; The third module is used to determine the prediction accuracy according to the second collected data and the third collected data, and adjust the data reporting frequency of the terminal according to the prediction accuracy.

9. An electronic device, characterized in that: The electronic device comprises a memory and a processor, the memory stores a computer program, and the processor implements the method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images