An Internet of Things (IoT) device control system, method, and storage medium

Abstract

This invention discloses an IoT device control system, method, and storage medium. The invention pre-stores several commonly used target command data on an offline server. When user query data is received, it is first matched against the target command data stored on the offline server. If a match is successful, the query data can be processed solely by the offline server. If a match fails, the query data is sent to an online server for processing via network connectivity. Existing central servers rely solely on online servers to process user voice commands, while this invention uses both offline and online servers to process query data. Therefore, this invention reduces the dependence of IoT device control on the network, thereby reducing the computational burden on the online server. It solves the problems of existing IoT systems being easily affected by network conditions and the high computational overhead of online servers.

Description

Technical Field

[0001] This invention relates to the field of equipment control, and more particularly to an Internet of Things (IoT) device control system, method, and storage medium. Background Technology

[0002] Smart home technology embodies the Internet of Things (IoT) under the influence of the internet. It connects various devices in the home through IoT technology, providing functions such as appliance control, lighting control, remote telephone control, indoor and outdoor remote control, and burglar alarms. Currently, most smart home control processes voice commands on a central (cloud) server connected to the internet. If the central server malfunctions or needs updating, it may affect the control of the smart home. Furthermore, relying solely on a central server to process voice commands results in high computational overhead.

[0003] Therefore, existing technologies still need improvement and development. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide an Internet of Things (IoT) device control system, method and storage medium to address the above-mentioned deficiencies of the prior art, and to solve the problems that existing IoT systems are easily affected by network conditions and that online servers have high computational overhead.

[0005] The technical solution adopted by this invention to solve the problem is as follows:

[0006] In a first aspect, embodiments of the present invention provide an Internet of Things (IoT) device control system, wherein the system includes an offline server and an online server;

[0007] The offline server is used to obtain query data and match the query data with several pre-stored target command data.

[0008] When a match is successful, the IoT device is controlled according to the target command data of the successful match.

[0009] When a match fails, the query data is sent to the online server;

[0010] The online server is used to match the query data with cloud command data, and control the IoT device based on the successfully matched cloud command data.

[0011] In one implementation, the method for determining each of the target command data includes:

[0012] Obtain the usage frequency and preset frequency threshold corresponding to several command data points;

[0013] The command data whose usage frequency is greater than a frequency threshold is used as the target command data.

[0014] In one embodiment, the system further includes a monitoring module;

[0015] The monitoring module is used to acquire the query data and send the query data to the offline server;

[0016] When the offline server is successfully matched, the target command data that was successfully matched sent by the offline server is obtained, and a device operation instruction is generated based on the target command data;

[0017] The device operation command is sent to the corresponding IoT device.

[0018] In one implementation, the monitoring module is further configured to:

[0019] When the offline server fails to match, the query data is sent to the online server to obtain the cloud command data that has been successfully matched by the online server, and the device operation instruction is generated based on the cloud command data.

[0020] In one implementation, the monitoring module is further configured to:

[0021] The successfully matched cloud command data is sent to the offline server.

[0022] In one implementation, the offline server is further used for:

[0023] The new target command data is determined based on the cloud command data.

[0024] In one implementation, the offline server is further used for:

[0025] Obtain the number of times each of the target commands is used within a preset time period;

[0026] Based on the number of times it is used, the target command data to be deleted is determined.

[0027] In one implementation, the preset time period is a future time period, and the step of obtaining the usage counts of each of the target command data within the preset time period includes:

[0028] Obtain the historical usage counts of each target command data within a historical time period;

[0029] Based on the historical usage counts corresponding to each of the target command data, predict the usage counts corresponding to each of the target command data in the future time period.

[0030] In one implementation, determining the target command data to be deleted based on the number of uses includes:

[0031] Sort the target command data according to the number of times it is used;

[0032] Based on the sorting results, the target command data to be deleted is determined.

[0033] In one implementation, determining the target command data to be deleted based on the number of uses includes:

[0034] Get the preset threshold number of times;

[0035] The target command data whose usage frequency is less than the threshold frequency is designated as the target command data to be deleted.

[0036] In one implementation, determining the target command data to be deleted based on the number of uses includes:

[0037] Obtain a preset frequency range, and select the target command data whose usage frequency is outside the frequency range as the target command data to be deleted;

[0038] Sort the target command data whose usage frequency falls within the specified frequency range;

[0039] The target command data to be deleted is determined based on the sorting results and is located within the specified frequency range.

[0040] In one implementation, the offline server is further used for:

[0041] Obtain the environmental information corresponding to the target user;

[0042] Based on the environmental information, new target command data is determined.

[0043] In one implementation, the method for determining the query data includes:

[0044] Acquire the voice data of the target user, and determine the text data based on the voice data;

[0045] The query data is determined based on the text data.

[0046] Secondly, embodiments of the present invention also provide an Internet of Things (IoT) device control method, wherein the method includes:

[0047] Obtain query data and send the query data to an offline server, wherein the offline server has pre-stored several target command data;

[0048] When the offline server is successfully matched, the target command data that is successfully matched with the query data is obtained, and the IoT device is controlled according to the successfully matched target command data;

[0049] When the offline server fails to match, the query data is sent to the online server;

[0050] Obtain cloud command data that successfully matches the query data, and control the IoT device based on the successfully matched cloud command data.

[0051] Thirdly, embodiments of the present invention also provide a computer-readable storage medium storing a plurality of instructions, wherein the instructions are adapted to be loaded and executed by a processor to implement the steps of an Internet of Things (IoT) device control method, the method comprising:

[0052] Obtain query data and send the query data to an offline server, wherein the offline server has pre-stored several target command data;

[0053] When the offline server is successfully matched, the target command data that is successfully matched with the query data is obtained, and the IoT device is controlled according to the successfully matched target command data;

[0054] When the offline server fails to match, the query data is sent to the online server;

[0055] Obtain cloud command data that successfully matches the query data, and control the IoT device based on the successfully matched cloud command data.

[0056] The beneficial effects of this invention are as follows: In this embodiment, several commonly used target command data are pre-stored on an offline server. When user query data is obtained, it is first matched against the target command data stored on the offline server. If a match is successful, the query data can be processed solely by the offline server. If a match fails, the query data is sent to an online server for processing via network connectivity. Existing central servers rely solely on online servers to process user voice commands, while this invention uses both offline and online servers to process query data. Therefore, this invention reduces the dependence of IoT devices on the network during control, thereby reducing the computational burden on the online server. It solves the problems of existing IoT systems being easily affected by network conditions and the high computational overhead of online servers. Attached Figure Description

[0057] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0058] Figure 1 This is a schematic diagram of the modules of the Internet of Things (IoT) device control system provided in an embodiment of the present invention.

[0059] Figure 2 This is a schematic diagram showing the connection between the monitoring module and the offline server and online server provided in an embodiment of the present invention.

[0060] Figure 3 This is a schematic diagram of the workflow of the monitoring module provided in an embodiment of the present invention.

[0061] Figure 4 This is a schematic diagram illustrating the process of updating an offline server using an online server, as provided in an embodiment of the present invention.

[0062] Figure 5 This is a schematic diagram illustrating the interaction between the monitoring module and the offline and online servers provided in this embodiment of the invention.

[0063] Figure 6 This is a schematic diagram of the command mining and updating process on an offline server provided in an embodiment of the present invention.

[0064] Figure 7 This is a flowchart illustrating the IoT device control method provided in an embodiment of the present invention.

[0065] Figure 8 This is a schematic diagram of the terminal provided in the embodiment of the present invention. Detailed Implementation

[0066] This invention discloses a control system, method, and storage medium for Internet of Things (IoT) devices. To make the objectives, technical solutions, and effects of this invention clearer and more explicit, the invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only for explaining the invention and are not intended to limit the invention.

[0067] Those skilled in the art will understand that, unless specifically stated otherwise, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the term “comprising” as used in this specification means the presence of the stated features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. It should be understood that when we say an element is “connected” or “coupled” to another element, it can be directly connected or coupled to the other element, or there may be intermediate elements. Furthermore, “connected” or “coupled” as used herein can include wireless connections or wireless coupling. The term “and / or” as used herein includes all or any units and all combinations of one or more associated listed items.

[0068] It will be understood by those skilled in the art that, unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. It should also be understood that terms such as those defined in general dictionaries should be understood to have the same meaning as in the context of the prior art, and should not be interpreted in an idealized or overly formal sense unless specifically defined as herein.

[0069] Smart home technology embodies the Internet of Things (IoT) under the influence of the internet. It connects various devices in the home through IoT technology, providing functions such as appliance control, lighting control, remote telephone control, indoor and outdoor remote control, and burglar alarms. Currently, most smart home control processes voice commands on a central (cloud) server connected to the internet. If the central server malfunctions or needs updating, it may affect the control of the smart home. Furthermore, relying solely on a central server to process voice commands results in high computational overhead.

[0070] To address the aforementioned deficiencies in existing technologies, this invention discloses an IoT device control system. The system includes an offline server and an online server. The offline server acquires query data and matches it with pre-stored target command data. When a match is successful, the IoT device is controlled according to the matched target command data. When a match fails, the query data is sent to the online server. The online server matches the query data with cloud command data and controls the IoT device according to the matched cloud command data. Existing central servers rely solely on the online server to process user voice commands. This invention, however, uses both an offline server and an online server to process query data, thus reducing the IoT device's dependence on the network during control and lowering the computational burden on the online server. This solves the problems of existing IoT systems being easily affected by network conditions and the high computational overhead of online servers.

[0071] like Figure 1 As shown, the system includes an offline server 01 and an online server 02;

[0072] The offline server 01 is used to obtain query data and match the query data with several pre-stored target command data.

[0073] When a match is successful, the IoT device is controlled according to the target command data of the successful match.

[0074] When a match fails, the query data is sent to the online server;

[0075] The online server 02 is used to match the query data with cloud command data, and control the IoT device based on the successfully matched cloud command data.

[0076] Specifically, the query data can be voice data issued by the user of the IoT device, such as the query to turn on the air conditioner or the dehumidifier. To reduce the dependence of the IoT device on the network during control, this embodiment pre-stores several commonly used target command data on an offline server. When the user's query data is obtained, it is first matched with the target command data stored on the offline server. If the match is successful, it means that the query data can be processed solely by the offline server. If the match fails, the query data is then sent to the online server for processing via the network. This embodiment, by using both the offline and online servers to process query data, reduces the dependence of the IoT device on the network during control, thereby reducing the computational burden on the offline server.

[0077] In one implementation, the method for determining the query data includes:

[0078] Acquire the voice data of the target user, and determine the text data based on the voice data;

[0079] The query data is determined based on the text data.

[0080] Specifically, the IoT device in this embodiment is voice-controlled. The system first acquires the target user's voice data. To facilitate matching, the voice data needs to be converted into text data, and finally, the text data is used as query data, thereby improving matching efficiency. In one implementation, the text data is a text string, and the text string is a regular expression.

[0081] In one implementation, the method for determining each of the target command data includes:

[0082] Obtain the usage frequency and preset frequency threshold corresponding to several command data points;

[0083] The command data whose usage frequency is greater than a frequency threshold is used as the target command data.

[0084] Specifically, this embodiment requires periodically calculating the usage frequency of each command data point. For each command data point, if its usage frequency exceeds a preset frequency threshold, it indicates that the command data point is a frequently used command by the target user, and thus it is considered as target command data. This embodiment pre-sets a frequency threshold, and by comparing numerical values, it can quickly determine which command data points are frequently used commands by the target user.

[0085] like Figure 2 As shown, the system also includes a monitoring module 03:

[0086] The monitoring module 03 is used to acquire the query data and send the query data to the offline server;

[0087] When the offline server is successfully matched, the target command data that was successfully matched sent by the offline server is obtained, and a device operation instruction is generated based on the target command data;

[0088] When the offline server fails to match, the query data is sent to the online server to obtain the cloud command data that has been successfully matched by the online server, and the device operation instruction is generated based on the cloud command data.

[0089] The device operation command is sent to the corresponding IoT device.

[0090] Specifically, such as Figure 3As shown, the monitoring module first acquires the user's query data and then sends it to an offline server for processing. If the query data fails to match on the offline server, it indicates that the query data is not a command frequently used by the target user, and the offline server cannot process it. The monitoring module then sends the query data to an online server. The online server is connected to the internet, so it can identify and process query data that failed to match on the offline server. The monitoring module generates corresponding device operation instructions based on the data that successfully matches on either the offline or online server, and then controls the corresponding IoT device to perform the appropriate operation through these instructions. In this embodiment, the monitoring module connects to both the offline and online servers, thus allowing it to manage both servers simultaneously and make timely decisions regarding the distribution of query data.

[0091] In one implementation, both the offline server and the online server are servers with Natural Language Processing Unit (NLU) capabilities, which can identify the domain, intent, and action corresponding to the query data using stored target command data or cloud command data.

[0092] In one implementation, the monitoring module 03 is further configured to:

[0093] The successfully matched cloud command data is sent to the offline server;

[0094] The offline server 01 is also used for:

[0095] The new target command data is determined based on the cloud command data.

[0096] Specifically, such as Figure 4 As shown, when query data needs to be sent to the online server for processing, it means that the offline server does not store the target command data corresponding to the query data. Therefore, the monitoring module can send the successfully matched cloud command data returned by the online server to the offline server, so that the offline server can update the target command data based on the cloud command data for future use by the offline server.

[0097] Because offline servers have limited memory, and new scenarios and devices will generate a continuous stream of commonly used user command data, it is necessary to continuously update and mine the stored target command data in order to optimize the memory utilization, speed and performance of offline servers.

[0098] In one implementation, the offline server is further used for:

[0099] Obtain the number of times each of the target commands is used within a preset time period;

[0100] Based on the number of times it is used, the target command data to be deleted is determined.

[0101] Specifically, the offline server needs to periodically calculate the number of times each target command data is used within a preset time period, and then delete the target command data that is used less frequently, thereby saving memory to store command data that will be used more frequently in the future.

[0102] In one implementation, the preset time period is a future time period, and the step of obtaining the usage counts of each of the target command data within the preset time period includes:

[0103] Obtain the historical usage counts of each target command data within a historical time period;

[0104] Based on the historical usage counts corresponding to each of the target command data, predict the usage counts corresponding to each of the target command data in the future time period.

[0105] Specifically, this embodiment predicts the future usage of target command data by analyzing its historical usage frequency over a historical time period. Based on the prediction results, the command data stored on the offline server can be adjusted in a timely manner, enabling the offline server to better handle user queries in the future. For example, for each target command data, the offline server checks its usage frequency within 24 hours to predict its usage frequency over 2-3 weeks. For instance, if the usage frequency within 24 hours is 3-7 times, the predicted usage frequency over 2-3 weeks might be 100 times.

[0106] In one implementation, determining the target command data to be deleted based on the number of uses includes:

[0107] Sort the target command data according to the number of times it is used;

[0108] Based on the sorting results, the target command data to be deleted is determined.

[0109] Specifically, in this embodiment, target command data can be sorted according to the frequency of use of each target command. The sorting order can be from most to least frequent or from least to most frequent. Based on the sorting results, target command data that is not frequently used by the user is determined. For example, if the sorting order is from most to least frequent, then several target command data from the last few positions in the sorting results are deleted to save memory.

[0110] In another implementation, determining the target command data to be deleted based on the number of uses includes:

[0111] Obtain a preset frequency range, and select the target command data whose usage frequency is outside the frequency range as the target command data to be deleted;

[0112] Sort the target command data whose usage frequency falls within the specified frequency range;

[0113] The target command data to be deleted is determined based on the sorting results and is located within the specified frequency range.

[0114] For example, assuming the usage range is set to 80-120 times, target command data with usage outside this range will be discarded. The remaining target command data will be sorted, and then the target command data with higher usage will be retained, while the target command data with lower usage will be filtered out to save memory for storing new target command data.

[0115] In one implementation, the function used to sort the target command data is shown below:

[0116] [Sorted Top 500 FrequentQueries] = Sort top500 (Q t >threshold)

[0117] Among them, Sort top500 It is a query Q t The sorting function. t = 1, ..., t represents the number of queries; in practice, t can be 1500. threshold represents the threshold value, i.e., a pre-defined range of 80-120 queries.

[0118] In another implementation, determining the target command data to be deleted based on the number of uses includes:

[0119] Get the preset threshold number of times;

[0120] The target command data whose usage frequency is less than the threshold frequency is designated as the target command data to be deleted.

[0121] Specifically, a usage threshold can be set as a standard to assess whether target command data is used frequently. For each target command data, if the number of times it is used is less than the threshold, it means that the user uses the target command data infrequently, and it is deleted. At the same time, target command data with a usage frequency higher than the threshold is retained.

[0122] In one implementation, such as Figure 5As shown, the monitoring module first sends the query data to the offline server for identification / matching. If the offline server fails to identify / match, the query data is then sent to the online server for identification / matching. Based on the identification / matching results from the online server, the system updates the command data stored in the offline server and the counts (i.e., usage counts) of each command. Furthermore, after a preset interval (e.g., 2-3 weeks), the system automatically performs target command data mining to identify frequently used commands and update the offline server accordingly.

[0123] In one implementation, such as Figure 6 As shown, after the system completes the mining of the target command data, it filters the command data stored on the offline server using a counting threshold to obtain the top few (e.g., the top 500) command data with the highest count values, and deletes other command data. Then, the filtered command data is used to update the list of frequently used command data stored on the offline server. The system will continue to update the command data stored on the offline server and the count of each command data item.

[0124] In one implementation, the offline server is further used for:

[0125] Obtain the environmental information corresponding to the target user;

[0126] Based on the environmental information, new target command data is determined.

[0127] Specifically, the offline server can also automatically update target command data based on current environmental information. For example, if a user frequently turns on the air conditioner in summer and the hot water system frequently in winter, then the command data for turning on the air conditioner can be used as the target command data in summer, and the command data for turning on the hot water system can be used as the target command data in winter. This invention predicts the IoT device operations that the target user might perform by analyzing the environment in which the user is located, and adjusts the command data stored in the offline server in a timely manner based on the prediction results, so that the command data stored in the offline server better matches the target user's current operations.

[0128] The advantages of this invention are:

[0129] 1. This invention can be applied to smart home, smart building management, and smart city scenarios. Through a simple design architecture, it enables more reliable and precise control of IoT devices. If the online server fails to connect to the internet, the offline server can still take over control of all devices.

[0130] 2. This invention improves system reliability, allowing offline and online servers to work in parallel and support each other. Even with poor network conditions, the offline server can process user queries locally, effectively reducing the usage time and load on the online server / online IoT server. 60-70% of commands can be processed locally on the offline server, significantly reducing the IoT system's dependence on the online server.

[0131] 3. This invention updates the target command data stored on the offline server using data fed back from the online server, essentially functioning as a teacher-student learning model. It can be extended to other scenarios or to implement other new functions without consuming significant resources.

[0132] Based on the above embodiments, the present invention also provides an Internet of Things (IoT) device control method, such as... Figure 7 As shown, the method includes:

[0133] Step S100: Obtain query data and send the query data to an offline server, wherein the offline server has pre-stored several target command data;

[0134] Step S200: When the offline server is successfully matched, the target command data that is successfully matched with the query data is obtained, and the IoT device is controlled according to the successfully matched target command data;

[0135] Step S300: When the offline server fails to match, the query data is sent to the online server;

[0136] Step S400: Obtain cloud command data that successfully matches the query data, and control the IoT device according to the successfully matched cloud command data.

[0137] Based on the above embodiments, the present invention also provides a terminal, the principle block diagram of which can be as follows: Figure 8 As shown, the terminal includes a processor, memory, network interface, and display screen connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface is used to communicate with external terminals via a network connection. When the computer program is executed by the processor, it implements an IoT device control method. The display screen can be an LCD screen or an e-ink screen.

[0138] Those skilled in the art will understand that Figure 8The schematic diagram shown is merely a partial structural diagram related to the present invention and does not constitute a limitation on the terminal to which the present invention is applied. A specific terminal may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0139] In one implementation, the terminal's memory stores one or more programs, and these programs are configured to be executed by one or more processors, and include instructions for performing IoT device control methods.

[0140] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided by this invention can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0141] In summary, this invention discloses an IoT device control system, method, and storage medium. The system includes an offline server and an online server. The offline server acquires query data and matches it with pre-stored target command data. When a match is successful, the IoT device is controlled according to the matched target command data. When a match fails, the query data is sent to the online server. The online server matches the query data with cloud command data and controls the IoT device according to the matched cloud command data. Existing central servers rely solely on the online server to process user voice commands, while this invention uses both offline and online servers to process query data. Therefore, this invention reduces the dependence of IoT device control on the network, thereby reducing the computational burden on the online server. It solves the problems of existing IoT systems being easily affected by network conditions and the high computational overhead of online servers.

[0142] It should be understood that the application of the present invention is not limited to the examples above. Those skilled in the art can make improvements or modifications based on the above description, and all such improvements and modifications should fall within the protection scope of the appended claims.

Claims

1. A control system for Internet of Things (IoT) devices, characterized in that, The system includes offline servers and online servers; The offline server is used to obtain query data and match the query data with several pre-stored target command data. The method for determining each of the target command data includes: obtaining the usage frequency and a preset frequency threshold corresponding to several command data respectively; and taking the command data whose usage frequency is greater than the frequency threshold as the target command data. When a match is successful, the IoT device is controlled according to the target command data of the successful match. When a match fails, the query data is sent to the online server; The online server is used to match the query data with cloud command data, and control the IoT device according to the successfully matched cloud command data; The offline server is further configured to: obtain the historical usage counts of each target command data in a historical time period; predict the usage counts of each target command data in a future time period based on the historical usage counts of each target command data; and determine the target command data to be deleted based on the usage counts. After a preset interval is reached, the system automatically performs target command data mining to identify frequently used command data and update the offline server. After the system completes the target command data mining, it filters the command data stored in the offline server using a counting threshold to obtain the top few command data with the highest count values ​​and deletes other command data. The filtered command data is then used to update the list of frequently used command data stored in the offline server.

2. The IoT device control system according to claim 1, characterized in that, The system also includes a monitoring module; The monitoring module is used to acquire the query data and send the query data to the offline server; When the offline server is successfully matched, the target command data that was successfully matched sent by the offline server is obtained, and a device operation instruction is generated based on the target command data; The device operation command is sent to the corresponding IoT device.

3. The IoT device control system according to claim 2, characterized in that, The monitoring module is also used for: When the offline server fails to match, the query data is sent to the online server to obtain the cloud command data that has been successfully matched by the online server, and the device operation instruction is generated based on the cloud command data.

4. The IoT device control system according to claim 3, characterized in that, The monitoring module is also used for: The successfully matched cloud command data is sent to the offline server.

5. The IoT device control system according to claim 4, characterized in that, The offline server is also used for: The new target command data is determined based on the cloud command data.

6. The IoT device control system according to claim 1, characterized in that, The step of determining the target command data to be deleted based on the number of uses includes: Sort the target command data according to the number of times it is used; Based on the sorting results, the target command data to be deleted is determined.

7. The IoT device control system according to claim 1, characterized in that, The step of determining the target command data to be deleted based on the number of uses includes: Get the preset threshold number of times; The target command data whose usage frequency is less than the threshold frequency is designated as the target command data to be deleted.

8. The IoT device control system according to claim 1, characterized in that, The step of determining the target command data to be deleted based on the number of uses includes: Obtain a preset frequency range, and select the target command data whose usage frequency is outside the frequency range as the target command data to be deleted; Sort the target command data whose usage frequency falls within the specified frequency range; The target command data to be deleted is determined based on the sorting results and is located within the specified frequency range.

9. The IoT device control system according to claim 1, characterized in that, The offline server is also used for: Obtain the environmental information corresponding to the target user; Based on the environmental information, new target command data is determined.

10. The Internet of Things (IoT) device control system according to claim 1, characterized in that, The method for determining the query data includes: Acquire the target user's voice data, and determine the text data based on the voice data; The query data is determined based on the text data.

11. A method for controlling an Internet of Things (IoT) device, characterized in that, The method includes: The query data is obtained and sent to an offline server, wherein the offline server pre-stores a number of target command data; the method for determining each target command data includes: obtaining the usage frequency and a preset frequency threshold corresponding to the number of command data respectively; and taking the command data whose usage frequency is greater than the frequency threshold as the target command data. When the offline server is successfully matched, the target command data that is successfully matched with the query data is obtained, and the IoT device is controlled according to the successfully matched target command data; When the offline server fails to match, the query data is sent to the online server; Obtain cloud command data that successfully matches the query data, and control the IoT device based on the successfully matched cloud command data; The offline server is used to obtain the historical usage counts of each target command data in a historical time period; based on the historical usage counts of each target command data, the usage counts of each target command data in a future time period are predicted; based on the usage counts, the target command data to be deleted are determined. After a preset interval is reached, the system automatically performs target command data mining to identify frequently used command data and update the offline server. After the system completes the target command data mining, it filters the command data stored in the offline server using a counting threshold to obtain the top few command data with the highest count values ​​and deletes other command data. The filtered command data is then used to update the list of frequently used command data stored in the offline server.

12. A computer-readable storage medium storing a plurality of instructions, characterized in that, The instructions are applicable to steps loaded and executed by a processor to implement an Internet of Things (IoT) device control method, the method comprising: The query data is obtained and sent to an offline server, wherein the offline server pre-stores a number of target command data; the method for determining each target command data includes: obtaining the usage frequency and a preset frequency threshold corresponding to the number of command data respectively; and taking the command data whose usage frequency is greater than the frequency threshold as the target command data. When the offline server is successfully matched, the target command data that is successfully matched with the query data is obtained, and the IoT device is controlled according to the successfully matched target command data; When the offline server fails to match, the query data is sent to the online server; Obtain cloud command data that successfully matches the query data, and control the IoT device based on the successfully matched cloud command data; The offline server is used to obtain the historical usage counts of each target command data in a historical time period; based on the historical usage counts of each target command data, the usage counts of each target command data in a future time period are predicted; based on the usage counts, the target command data to be deleted are determined. After a preset interval is reached, the system automatically performs target command data mining to identify frequently used command data and update the offline server. After the system completes the target command data mining, it filters the command data stored in the offline server using a counting threshold to obtain the top few command data with the highest count values ​​and deletes other command data. The filtered command data is then used to update the list of frequently used command data stored in the offline server.

Images