A discontinuous receiving method and apparatus

By setting timers and artificial intelligence models in the intelligent network, collecting node energy consumption and updating the model periodically, the problems of large data volume and high energy consumption in traditional networks are solved, achieving efficient information transmission and network intelligence.

CN116963317BActive Publication Date: 2026-11-10BEIJING UNIV OF POSTS & TELECOMM
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202210393428.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-04-15
Publication Date
2026-11-10
Estimated Expiration
2042-04-15

AI Technical Summary

Technical Problem

In intelligent networks, traditional network service capabilities are difficult to match with high-dimensional information spaces, resulting in excessively large amounts of data transmitted through communication. Information service systems cannot continuously meet the needs of complex and intelligent information transmission, and the energy consumption of updating node models is high, making frequent updates impossible.

Method used

By setting timers in the network to respond to model version number updates, collecting node energy consumption, calculating energy consumption thresholds, and starting timers to make energy-intensive nodes receive and update the model intermittently, information transmission compression and model slice transmission are performed using artificial intelligence models to reduce unnecessary reception and updates.

Benefits of technology

It achieves reduced node energy consumption, improved information transmission efficiency, reduced resource waste, and enhanced network intelligence while meeting the requirement that the model cannot be updated frequently.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN116963317B_ABST
    Figure CN116963317B_ABST
Patent Text Reader

Abstract

This disclosure provides a method and apparatus for non-interrupted reception, relating to the field of communication technology. The specific implementation scheme is as follows: when the model version number on the network is updated, energy consumption data of the nodes is collected, and a timer in the node with high energy consumption is started to enable the node's model reception capability. This allows the node with high energy consumption to receive and update the model in the node according to the target model corresponding to the current version number. This disclosure achieves interval updates of the model on the node with high energy consumption and meets the requirement that the model should not be updated frequently.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This disclosure relates to the field of communication technology, and more particularly to a discontinuous reception method and apparatus. Background Technology

[0002] In the future Internet of Everything, network nodes are trending towards intelligence. This intelligence leads to a rapid expansion of the information space, even resulting in a dimensional disaster. This exacerbates the difficulty of representing the information carrying space, making it difficult for traditional network service capabilities to match the high-dimensional information space. The excessive amount of data transmitted in communications makes information service systems unable to continuously meet people's complex, diverse, and intelligent information transmission needs. However, using artificial intelligence models to encode, propagate, and decode business information can significantly reduce the amount of data transmitted in communication services, greatly improving information transmission efficiency. These models are relatively stable and possess reusability and propagation capabilities. The propagation and reuse of these models will help enhance network intelligence while reducing overhead and resource waste, forming a highly intelligent and simplified network.

[0003] Discontinuous Reception (DRX) refers to packet-based data streams that are typically bursty, with data transmission occurring for a period of time followed by a longer period of inactivity. During periods of no data transmission, power consumption can be reduced and battery life extended by stopping PDCCH (Physical Downlink Control Channel) reception (which halts PDCCH blind detection).

[0004] To conserve power, the model cannot be updated very frequently. Therefore, even if the version number updates rapidly on the network, nodes with poor energy consumption need to be updated with version numbers at intervals. Summary of the Invention

[0005] This disclosure provides a discontinuous reception method and apparatus.

[0006] According to a first aspect of this disclosure, a discontinuous reception method is provided, wherein it is applied in a network, the network including multiple nodes, each node storing a model and a timer, the timer being used to enable or disable the node's reception model capability;

[0007] Each node is configured with a corresponding standard energy consumption range;

[0008] Discontinuous reception methods include:

[0009] In response to model version number updates in the network, the current version number is obtained, the energy consumption of the node to be updated is collected, and the update energy consumption estimate of the node to be updated using the target model corresponding to the current version number is calculated. The target model corresponding to the current version number is the model required by the node to be updated.

[0010] The updated energy consumption threshold is calculated based on the standard energy consumption range and the energy consumed.

[0011] In response to an updated energy consumption estimate being less than or equal to an updated energy consumption threshold, a timer is started, enabling the node to be updated to receive and update its model according to the target model.

[0012] According to a second aspect of this disclosure, a discontinuous receiving device is provided, which is applied in a network including multiple nodes, each node storing a model and a timer, the timer being used to enable or disable the receiving model capability of the node.

[0013] Each node is configured with a corresponding standard energy consumption range;

[0014] include:

[0015] The acquisition unit responds to the model version number update in the network by obtaining the current version number, collecting the energy consumption of the node to be updated, and calculating the estimated update energy consumption of the node to be updated using the target model corresponding to the current version number. The target model corresponding to the current version number is the model required by the node to be updated.

[0016] The calculation unit calculates the updated energy consumption threshold based on the standard energy consumption range and the energy consumed;

[0017] The update unit, in response to the updated energy consumption estimate being less than or equal to the updated energy consumption threshold, starts a timer so that the node to be updated receives and updates the model according to the target model.

[0018] According to a third aspect of this disclosure, an electronic device is provided, comprising:

[0019] At least one processor; and

[0020] A memory that is communicatively connected to at least one processor; wherein,

[0021] The memory stores instructions that can be executed by at least one processor, such that at least one processor can perform the methods described above.

[0022] According to a fourth aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are used to cause a computer to perform the methods described above.

[0023] The beneficial effects of the technical solution provided in this disclosure are:

[0024] The solution provided in this disclosure triggers energy consumption collection of nodes when the model version number on the network is updated, starts a timer in the node with excessive energy consumption, and updates the model in the node according to the target model corresponding to the current version number, thereby realizing the interval update of the model on the node with excessive energy consumption and meeting the requirement that the model should not be updated frequently.

[0025] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0026] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0027] Figure 1 This is a flowchart illustrating the discontinuous reception method provided according to Embodiment 1 of this disclosure;

[0028] Figure 2 This is a schematic diagram of the structure of a discontinuous receiving device according to Embodiment 2 of this disclosure;

[0029] Figure 3 This is a block diagram of an electronic device according to an embodiment of the present disclosure. Detailed Implementation

[0030] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0031] In the intelligent and simplified network, business information is primarily disseminated through artificial intelligence (AI) models. By using AI models to compress the initial business information into a second business information related to the AI ​​model, the data communication volume in the network is significantly reduced, with compression efficiency surpassing traditional compression algorithms. Specifically, the sending device uses a pre-configured first model to extract the initial business information and obtain the second business information to be transmitted; the sending device then transmits the second business information to the receiving device. The receiving device receives the second business information and uses the pre-configured second model to reconstruct it into a third business information. The third business information reconstructed by the second model has slight quality differences compared to the original first business information, but the content is identical, providing a virtually indistinguishable user experience. Before the sending device transmits the second business information to the receiving device, an update module determines whether the receiving device needs to update the second model. If an update is required, the module transmits the pre-configured third model to the receiving device, which then uses the third model to update the second model. By processing business information through a pre-trained AI model, the data transmission volume in communication services can be significantly reduced, greatly improving information transmission efficiency. These models are relatively stable and possess reusability and propagation capabilities. Model propagation and reuse help enhance network intelligence while reducing overhead and resource waste. A model can be divided into several model slices according to different segmentation rules. These model slices can also be transferred between different network nodes, and the slices can be assembled into a model. Model slices can be stored distributed across multiple network nodes. When a network node discovers that it is missing or needs to update a certain model or model slice, it can request it from nearby nodes that may possess that slice.

[0032] The transmission of service information and models both occur within the communication network, based on network protocols. The network nodes traversed along the transmission paths include intelligent routers. The functions of intelligent routers include, but are not limited to, service information transmission, model transmission, model self-updating, and security protection. The transmission function of intelligent routers involves transmitting service information or models from source nodes to destination nodes, with multiple paths existing between them. The model transmission function of intelligent routers can transmit model slices, improving transmission speed by strategically arranging model slices to travel along multiple paths.

[0033] Example 1

[0034] Figure 1 This illustration shows a discontinuous reception method provided by an embodiment of the present disclosure, applied in a network, the network including multiple nodes, each node storing a model and a timer, the timer being used to enable or disable the node's reception model capability;

[0035] Each node is configured with a corresponding standard energy consumption range;

[0036] Discontinuous reception methods include:

[0037] Step S101: In response to the model version number update in the network, obtain the current version number, collect the energy consumption of the node to be updated, and calculate the update energy consumption estimate of the node to be updated using the target model corresponding to the current version number, wherein the target model corresponding to the current version number is the model required by the node to be updated.

[0038] Step S102: Calculate the updated energy consumption threshold based on the standard energy consumption range and the consumed energy.

[0039] Step S103: In response to the updated energy consumption estimate being less than or equal to the updated energy consumption threshold, a timer is started, so that the node to be updated receives and updates the model according to the target model.

[0040] This disclosure triggers energy consumption data collection on nodes when the model version number is updated on the network, starts a timer in the node with high energy consumption to enable the node to receive the model, so that the node with high energy consumption receives and updates the model in the node according to the target model corresponding to the current version number, thereby realizing the interval update of the model on the node with high energy consumption and meeting the requirement that the model should not be updated frequently.

[0041] Specifically, in response to the model version number update in the network, the nodes in the network obtain the current version number, and the nodes determine whether the target model corresponding to the current version number is the required model;

[0042] If so, set that node as the node to be updated;

[0043] If not, do not process the node;

[0044] Collect the energy consumption of the node to be updated. Here, the energy consumption refers to the energy consumption value that the node to be updated has consumed before this update.

[0045] Calculate the estimated update energy consumption of the node to be updated by using the target model corresponding to the current version number for model update;

[0046] The updated energy consumption threshold is calculated based on the standard energy consumption range and the energy consumption already consumed, where the updated energy consumption threshold can be the difference between the standard energy consumption range and the energy consumption already consumed.

[0047] Determine whether the above updated energy consumption estimate is less than or equal to the updated energy consumption threshold;

[0048] If so, then the node update consumes a lot of energy and the model in the node needs to be updated. Therefore, the timer in the node to be updated is started, thereby enabling the node to receive the model. That is, the node to be updated changes from OFF state to ON state, so that the node to be updated receives the target model corresponding to the current version number and updates the model to be updated according to the target model.

[0049] If not, the node consumes too little power and there is no need to update the model in the node. Therefore, there is no need to start the timer in the node to be updated. In other words, the ability of the node to receive the model is still in the OFF state.

[0050] For example, the network includes a first node A1, a second node A2, a third node A3, a fourth node A4, and a fifth node A5, and the network has version number 1.4, which is now updated to version 1.5;

[0051] First, all nodes in the network obtain the current version number 1.5, and each node determines whether the target model corresponding to the current version number 1.5 is the model that the node needs. If so, the node is set as a node to be updated.

[0052] For example, the target model corresponding to the current version number 1.5 is the model required for the first node A1, the third node A3, and the fifth node A5;

[0053] The target model corresponding to the current version number 1.5 is the model that is not needed for the second node A2 and the fourth node A4;

[0054] Therefore, the first node A1, the third node A3, and the fifth node A5 are nodes to be updated.

[0055] Next, the energy consumption of the nodes to be updated (first node A1, third node A3 and fifth node A5) is collected, and the energy consumption of updating the nodes to be updated (first node A1, third node A3 and fifth node A5) using the target model corresponding to the current version number is estimated.

[0056] And the updated energy consumption threshold is calculated based on the standard energy consumption range and the energy consumed;

[0057] Then, it is determined whether the updated energy consumption estimate is less than or equal to the updated energy consumption threshold;

[0058] If so, start the timer, and the node to be updated changes from the OFF state to the ON state. In the ON state, the node to be updated can receive the target model corresponding to the current version number in the network, so that the node to be updated can update the model to be updated according to the target model.

[0059] If not, the timer will not be started, meaning the timer will remain off and the node to be updated will remain in the OFF state, meaning the model in the node to be updated will not be updated.

[0060] For example, the first node A1 is set with a standard energy consumption range, denoted as B1;

[0061] The third node A3 has a standard energy consumption range, denoted as B3;

[0062] The fifth node is set as the fifth standard energy consumption range, denoted as B5;

[0063] Collect the energy consumed by the first node A1 and record it as C1;

[0064] Collect the energy consumed by the third node A3, and record it as C3;

[0065] Collect the energy consumed by the fifth node and record it as C5;

[0066] The update energy consumption thresholds for the first node A1, the third node A3, and the fifth node A5 are calculated and denoted as D1, D3, and D5, respectively. The update energy consumption threshold is the maximum energy consumption that the current node can use.

[0067] Subsequently, the update energy consumption threshold of the first node A1 is calculated and denoted as E1, where E1 = B1 - C1;

[0068] The energy consumption threshold for updating the third node A3 is calculated and denoted as E3, where E3 = B3 - C3;

[0069] The update energy consumption threshold of the fifth node A5 is calculated and denoted as E5, where E5 = B5 - C5. At this time, the estimated update energy consumption of the first node A1 is less than or equal to the update energy consumption threshold of the first node A1, i.e., D1 ≤ E1. Therefore, the timer in the first node A1 is started, the first node A1 changes from OFF state to ON state, the first node A1 receives the target model corresponding to the current version number, and the first node A1 updates the model to be updated in the first node A1 according to the target model.

[0070] At this time, the estimated update energy consumption of the third node A3 is less than or equal to the update energy consumption threshold of the third node A3, i.e., D3≤E3. Therefore, the timer in the third node A3 is started, the third node A3 changes from OFF state to ON state, the third node A3 receives the target model corresponding to the current version number, and the third node A3 updates the model to be updated in the third node A3 according to the target model.

[0071] At this point, the energy consumption threshold for updating the fifth node A5 is greater than that for the fifth node A5, i.e., D5 > E5. Therefore, the timer in the fifth node A5 is not started, meaning that the timer in the fifth node A5 remains in the off state. Thus, the fifth node A5 remains in the OFF state, and the model in the fifth node A5 is not updated.

[0072] It should be noted that the steps of the corresponding methods are not necessarily performed in the order shown and described in this specification in other embodiments. In some other embodiments, the methods may include more or fewer steps than those described in this specification. Furthermore, a single step described in this disclosure may be broken down into multiple steps in other embodiments; and multiple steps described in this specification may be combined into a single step in other embodiments.

[0073] This disclosure provides a possible implementation in which the model type of the model required by the node to be updated is the same as the model type of the model to be updated stored in the node to be updated.

[0074] Specifically, the model type required by the node to be updated is the same as the model type of the model to be updated stored in the node to be updated. Therefore, the model type of the target model corresponding to the current version number is the same as the model type of the model to be updated stored in the node to be updated.

[0075] For example, each node in the network obtains the current version number 1.5, and each node determines whether the model type of the target model corresponding to the current version number 1.5 is the same as the model type of the model stored locally on the node. If so, the node is set as a node to be updated.

[0076] For example, the model types stored in the first node A1, the third node A3, and the fifth node A5 are the same as the model types corresponding to the current version number 1.5;

[0077] The model types stored in the second node A2 and the fourth node A4 are different from the model types corresponding to the current version number 1.5;

[0078] Therefore, the first node A1, the third node A3, and the fifth node A5 are nodes to be updated.

[0079] This disclosure provides a possible implementation, wherein step S103 specifically includes the following steps:

[0080] Step S1031: Calculate the estimated performance improvement of the node to be updated by using the target model for model update;

[0081] Step S1032: Obtain the preset expected value;

[0082] Step S1033: In response to the updated energy consumption estimate being less than or equal to the updated energy consumption threshold, and in response to the performance improvement estimate being greater than or equal to the preset expected value, a timer is started.

[0083] This disclosure provides a possible implementation method in which the timer is non-periodic and needs to be triggered by specific conditions;

[0084] Step S103 specifically includes the following steps:

[0085] In response to the updated energy consumption estimate being less than or equal to the updated energy consumption threshold, update data between the target model and the model to be updated in the node to be updated is obtained, and the performance improvement estimate of the target model compared to the model to be updated is calculated based on the updated data.

[0086] A timer is started in response to a performance improvement estimate that is greater than or equal to a preset expected value.

[0087] Specifically, the above implementation provides one way to trigger a timer:

[0088] The timer can only be started when both of the above conditions are met simultaneously, so that the node to be updated can update the model to be updated according to the target model corresponding to the current version number. This ensures that the timer is started only when the target model corresponding to the current version number can significantly improve the performance of the node to be updated and the energy consumption loss during the update is small, thereby improving the update efficiency and reducing energy consumption. It also allows for the interval version number update of poorly performing nodes with insignificant performance improvement and large energy consumption loss during the update.

[0089] Specifically, the current version number includes the updates compared to the previous version, and the update data between the target model and the model to be updated can be obtained based on the updates of each version.

[0090] For example, if there is a version number 1.4 on the internet that has been updated to version 1.5, then version 1.5 includes the update content 1.5 compared to version 1.4, and so on. Version 1.4 includes the update content 1.4 compared to version 1.3, and so on. Version 1.2 includes the update content 1.2 compared to version 1.1.

[0091] If the existing model in the first node A1 is the model corresponding to version 1.1, then the update data between the target model and the model corresponding to version 1.1 includes: update content 1.2, update content 1.3, update content 1.4, and update content 1.5;

[0092] If the existing model in the third node A3 is the model corresponding to version 1.3, then the update data between the target model and the model corresponding to version 1.3 includes: update content 1.4 and update content 1.5.

[0093] Specifically, updated data can also be obtained directly based on the differences between the target model and the model to be updated.

[0094] Of course, obtaining updated data is not limited to the two methods mentioned above, and will not be elaborated here.

[0095] For example, the network includes a first node A1, a second node A2, a third node A3, a fourth node A4, and a fifth node A5, and the network has version number 1.4, which is now updated to version 1.5;

[0096] Among them, the current energy consumption of the first node A1 and the third node A3 exceeds the first standard energy consumption range, so it is necessary to start the timers in the first node A1 and the third node A.

[0097] The first step is to obtain the update data between the target model and the model to be updated in the first node A1 based on the model data of the current version number, and record it as the first update data;

[0098] Based on the model data of the current version number, obtain the update data between the target model and the model to be updated in the third node A3, and record it as the third update data;

[0099] The second step is to calculate the estimated performance improvement of the target model compared to the model to be updated in the first node A1 based on the first updated data, and denoted as the first performance improvement estimate.

[0100] The estimated performance improvement of the target model compared to the model to be updated in the third node A3 is calculated based on the third updated data, and is denoted as the third performance improvement estimate.

[0101] The third step is to determine whether the estimated first performance improvement is greater than or equal to the preset expected value set in the first node A1.

[0102] At this point, the estimated first performance improvement is greater than or equal to the preset expected value set in the first node A1, and the fourth step is executed;

[0103] Determine whether the estimated value of the third performance improvement is greater than or equal to the preset expected value set in the third node A3;

[0104] At this point, the estimated performance improvement value is less than the preset expected value set in the third node A3, so the subsequent processing of the third node A3 ends, that is, the timer in the third node A3 is not started.

[0105] The fourth step is to calculate the estimated update energy consumption of the target model when simulating the update of the model to be updated in the first node A1, and denoted as the first update energy consumption estimate.

[0106] The fifth step is to determine whether the estimated energy consumption of the first update is less than or equal to the preset update energy consumption threshold of the first node A1.

[0107] At this point, if the first update energy consumption estimate is less than or equal to the update energy consumption threshold of the first node A1, the timer in the first node A1 is started, so that the first node A1 updates the model to be updated in the first node A1 according to the target model corresponding to the current version number.

[0108] This disclosure provides a possible implementation method in which the timer is non-periodic and needs to be triggered by specific conditions;

[0109] Step S103 specifically includes the following steps:

[0110] In response to an updated energy consumption estimate being less than or equal to the standard energy consumption range, the number of version updates between the target model and the model to be updated is obtained.

[0111] A timer is started in response to a version update count that is greater than or equal to the version update threshold.

[0112] Specifically, the above implementation provides another way to trigger the timer: only nodes to be updated whose calculated number of version updates is greater than or equal to the version update threshold can start the timer, so that the nodes to be updated update the model to be updated according to the target model corresponding to the current version number. Since the longer the interval between triggering the update, the lower the energy consumption will be, thus reducing energy consumption, and realizing the interval version update of the model by the node.

[0113] Each node can be configured with a corresponding version update threshold.

[0114] For example, the network includes a first node A1, a second node A2, a third node A3, a fourth node A4, and a fifth node A5. The network has a current version number of 1.5. The version numbers of the model are 1.1, 1.2, 1.3, 1.4, and 1.5. The version update threshold is set to 2.

[0115] Among them, the current energy consumption of the first node A1 and the third node A3 exceeds the first standard energy consumption range, so it is necessary to start the timers in the first node A1 and the third node A.

[0116] If the existing model in the first node A1 is the model corresponding to version 1.1, then the number of version updates between the target model and the model corresponding to version 1.1 is 4, which is greater than the version update threshold, and the timer in the first node A1 is started.

[0117] If the existing model in the third node A3 is the model corresponding to version 1.3, then the number of version updates between the target model and the model corresponding to version 1.3 is 2, which is equal to the version update threshold, and the timer in the third node A3 is started.

[0118] This disclosure provides a possible implementation, wherein calculating the updated energy consumption estimate includes:

[0119] Receive test instructions and perform energy consumption tests on the node to be updated according to the test instructions, and collect the estimated update energy consumption value of the node to be updated.

[0120] Specifically, step S101 includes the following steps:

[0121] Step S1011: In response to the model version number update in the network, the node obtains the current version number and determines whether the target model is the required model.

[0122] If so, set the node as the node to be updated;

[0123] Step S1012: Receive the test command and perform energy consumption test on the node to be updated according to the test command, and collect the estimated update energy consumption value of the node to be updated.

[0124] This disclosure provides a possible implementation in which a node is connected to an energy consumption data acquisition device, and the energy consumption acquisition device performs energy consumption testing on the node and collects the current energy consumption.

[0125] Specifically, in response to a model version number update in the network, a node obtains the current version number, determines that the target model is the required model, and sets the node as the node to be updated.

[0126] The network receives the test command, obtains the preset test process in the test command, and obtains the control commands corresponding to each test step in the test process; according to the test process, the control commands are sent sequentially to the node under test and the energy consumption data acquisition device connected to it, so that the node under test and the energy consumption data acquisition device connected to it can respond to the received control commands.

[0127] When a test command is received, the energy consumption data acquisition device tests the energy consumption of the node to be updated, collects the current energy consumption of the node after the test, and then feeds back the collected current energy consumption.

[0128] This disclosure provides a possible implementation in which a model launch receiver stored in the same node is activated in response to a timer start in the node.

[0129] Specifically, each node stores a corresponding model and a timer. The node listens to the network and starts the timer when requirements are met. At this time, the model is allocated an "ON" period. During this period, the model starts its receiver and updates the model once based on the target model corresponding to the current version on the network. During other times (OFF), the model will turn off its receiver to save power.

[0130] This disclosure provides a possible implementation in which a receiver is used to receive the target model corresponding to the current version number.

[0131] Specifically, the node where the model is located during other times (OFF) simply does not receive version number updates on the network, but it can still receive other data, and the model is still supported or controlled by the corresponding protocol for propagation, thus retaining its propagation and reusability.

[0132] This disclosure provides a possible implementation method in which model propagation employs a model propagation dynamics algorithm protocol.

[0133] Specifically, since the model dynamics algorithm is not the core technology of this disclosure, it will not be described in detail here.

[0134] The above describes a discontinuous reception method. The following describes a discontinuous reception device.

[0135] Example 2

[0136] Figure 2 This illustration shows a discontinuous receiving device provided in an embodiment of the present disclosure, applied in a network, the network including multiple nodes, each node storing a model and a timer, the timer being used to enable or disable the node's receiving model capability;

[0137] Each node is configured with a corresponding standard energy consumption range;

[0138] include:

[0139] The acquisition unit 201 responds to the model version number update in the network by acquiring the current version number, acquiring the energy consumption consumed by the node to be updated, and calculating the estimated update energy consumption of the node to be updated using the target model corresponding to the current version number, wherein the target model corresponding to the current version number is the model required by the node to be updated.

[0140] The calculation unit 202 calculates the updated energy consumption threshold based on the standard energy consumption range and the consumed energy.

[0141] Update unit 203, in response to the updated energy consumption estimate being less than or equal to the updated energy consumption threshold, starts a timer so that the node to be updated receives and updates the model according to the target model.

[0142] This disclosure triggers energy consumption data collection on nodes when the model version number is updated on the network, starts a timer in the node with high energy consumption to enable the node to receive the model, so that the node with high energy consumption receives and updates the model in the node according to the target model corresponding to the current version number, thereby realizing the interval update of the model on the node with high energy consumption and meeting the requirement that the model should not be updated frequently.

[0143] This disclosure provides a possible implementation in which the model type of the model required by the node to be updated is the same as the model type of the model to be updated stored in the node to be updated.

[0144] This disclosure provides a possible implementation method in which model propagation employs a model propagation dynamics algorithm protocol.

[0145] The beneficial effects achieved by the embodiments of this disclosure are the same as those of the discontinuous reception method embodiments described above, and will not be repeated here.

[0146] The acquisition, storage, and application of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0147] According to embodiments of this disclosure, this disclosure also provides an electronic device and a readable storage medium.

[0148] The electronic device includes:

[0149] At least one processor; and

[0150] A memory that is communicatively connected to at least one processor; wherein,

[0151] The memory stores instructions that can be executed by at least one processor, such that at least one processor can perform the methods described above.

[0152] The electronic device triggers energy consumption collection of nodes when the model version number on the network is updated, starts timers in nodes with high energy consumption to enable the nodes to receive models, so that the nodes with high energy consumption receive and update the models in the nodes according to the target model corresponding to the current version number, thereby realizing the interval update of models on nodes with high energy consumption and meeting the requirement that models should not be updated frequently.

[0153] The non-transitory computer-readable storage medium stores computer instructions for causing a computer to perform the methods provided in embodiments of this disclosure.

[0154] When the model version number on the network is updated, the readable storage medium triggers the energy consumption collection of the nodes, starts the timer in the nodes with high energy consumption to enable the nodes to receive models, so that the nodes with high energy consumption receive and update the models in the nodes according to the target model corresponding to the current version number, thereby realizing the interval update of the models on the nodes with high energy consumption and meeting the requirement that the models should not be updated frequently.

[0155] Figure 3 A schematic block diagram of an example electronic device 300 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0156] like Figure 3 As shown, device 300 includes a computing unit 301, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 302 or a computer program loaded from storage unit 308 into random access memory (RAM) 303. The RAM 303 may also store various programs and data required for the operation of device 300. The computing unit 301, ROM 302, and RAM 303 are interconnected via bus 304. Input / output (I / O) interface 307 is also connected to bus 304.

[0157] Multiple components in device 300 are connected to I / O interface 305, including: input unit 306, such as keyboard, mouse, etc.; output unit 307, such as various types of monitors, speakers, etc.; storage unit 308, such as disk, optical disk, etc.; and communication unit 309, such as network card, modem, wireless transceiver, etc. Communication unit 309 allows device 300 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0158] The computing unit 301 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 301 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 301 performs the various methods and processes described above, such as a discontinuous reception method. For example, in some embodiments, a discontinuous reception method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 307. In some embodiments, part or all of the computer program may be loaded and / or installed on device 300 via ROM 302 and / or communication unit 309. When the computer program is loaded into RAM 303 and executed by the computing unit 301, one or more steps of a discontinuous reception method described above may be performed. Alternatively, in other embodiments, the computing unit 301 may be configured to perform a discontinuous reception method by any other suitable means (e.g., by means of firmware).

[0159] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0160] Program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on the machine, partially on the machine, as a standalone software package partially on the machine and partially on the process machine, or entirely on the process machine or server.

[0161] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0162] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0163] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0164] Computer systems can include clients and servers. Clients and servers are generally separate from each other and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, distributed system servers, or servers incorporating blockchain technology.

[0165] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0166] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A discontinuous reception method, characterized in that, In a network, the network consists of multiple nodes, each of which stores a model and a timer. The timer is used to enable or disable the node's ability to receive models. Each node is configured with a corresponding standard energy consumption range; The discontinuous reception method includes: In response to a model version number update in the network, the current version number is obtained, the energy consumption of the node to be updated is collected, and the update energy consumption estimate of the node to be updated using the target model corresponding to the current version number is calculated, wherein the target model corresponding to the current version number is the model required by the node to be updated. The updated energy consumption threshold is calculated based on the standard energy consumption range and the consumed energy. In response to the updated energy consumption estimate being less than or equal to the updated energy consumption threshold, the timer is started, causing the node to be updated to receive and update the model according to the target model; The step of starting the timer includes the following steps: Obtain the update data between the target model and the model to be updated in the node to be updated, and calculate the estimated performance improvement of the target model compared to the model to be updated based on the update data; Obtain the preset expected value; The timer is started in response to the estimated performance improvement being greater than or equal to the preset expected value.

2. The discontinuous reception method as described in claim 1, wherein, Starting the timer includes the following steps: In response to the updated energy consumption estimate being less than or equal to the standard energy consumption range, the number of version updates between the target model and the model to be updated is obtained; The timer is started in response to a version update count being greater than or equal to the version update threshold.

3. The discontinuous reception method as described in claim 1, wherein, Calculating the updated energy consumption estimate includes: Receive test instructions and perform energy consumption tests on the node to be updated according to the test instructions, and collect the estimated update energy consumption value of the node to be updated.

4. The discontinuous reception method as described in claim 1 or 3, wherein, The node is connected to an energy consumption data acquisition device, which performs energy consumption tests on the node.

5. The discontinuous reception method as described in claim 1, wherein, In response to the start of the timer in the node, a model start receiver stored in the same node.

6. The discontinuous reception method as described in claim 5, wherein, The receiver is used to receive the target model corresponding to the current version number.

7. The discontinuous reception method as described in claim 1, wherein, The model type required by the node to be updated is the same as the model type of the model to be updated stored in the node to be updated.

8. The discontinuous reception method as described in claim 1, wherein, The update of the model in the node to be updated according to the target model specifically includes: Obtain the parameters of the target model and update the target model's parameters into the model to be updated.

9. A discontinuous receiving device, characterized in that, In a network, the network consists of multiple nodes, each of which stores a model and a timer. The timer is used to enable or disable the node's ability to receive models. Each node is configured with a corresponding standard energy consumption range; include: The acquisition unit, in response to the model version number update in the network, acquires the current version number, acquires the energy consumption of the node to be updated, and calculates the estimated update energy consumption of the node to be updated using the target model corresponding to the current version number, wherein the target model corresponding to the current version number is the model required by the node to be updated. The calculation unit calculates the updated energy consumption threshold based on the standard energy consumption range and the consumed energy. The update unit, in response to the updated energy consumption estimate being less than or equal to the updated energy consumption threshold, starts the timer, causing the node to be updated to receive and update its model according to the target model. Specifically, the update unit is used to: obtain update data between the target model and the model to be updated in the node to be updated; calculate the performance improvement estimate of the target model compared to the model to be updated based on the update data; obtain a preset expected value; and start the timer in response to the performance improvement estimate being greater than or equal to the preset expected value.

10. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-8.

11. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-8.