Device control method and apparatus, electronic device and storage medium

Abstract

The present application relates to the technical field of communication and provides a device control method and apparatus, an electronic device and a storage medium, which includes the steps of: acquiring (101) system information of the first system and system information of the second system recorded in the device when an access of the device to a first system is detected; inputting (102) the system information of the first system and the system information of the second system into a pre-trained learning model to acquire a result indicating whether the first system and the second system are the same system; and controlling (103) the device to lock the output if the first system and the second system are not the same system, where the second system is a system that the device has accessed before accessing the first system, and the system information includes information of N categories (N is an integer greater than 1).

Description

[Technical Field]

[0001] This application claims priority from a Chinese patent application bearing application number "202110994389.6" and filed on August 27, 2021, the entire contents of which are incorporated herein by reference.

[0002] The present application relates to the technical field of communications, and in particular to a device control method and apparatus, an electronic device, and a storage medium. [Background technology]

[0003] As communication power supply technology develops, the prices of communication power supply devices such as batteries, power cables, and rectifiers continue to rise, and communication operators around the world are now faced with a new and very serious problem: device theft.

[0004] The basic concept of engineers to solve the device theft problem is usually to lock the output and make the device unavailable when theft of the device is detected, thereby reducing the value of theft and thus mitigating the device theft problem. A concept proposed so far for detecting device theft is to provide a GPS positioning system within the device, set its initial geographic location when the device is first started up, and control the device to determine that the device has been stolen and lock the output when a change in the current geographic location is detected. Summary of the Invention [Problem to be solved by the invention]

[0005] However, installing a GPS positioning system inside a device would significantly increase the hardware cost of the device, and installing a GPS positioning system inside a device such as a rectifier would be technically quite difficult, and it would be necessary to consider, for example, the influence between the electromagnetic body and the air passage, the installation of the antenna, etc. [Means for solving the problem]

[0006] An embodiment of the present application provides a device control method, which includes the steps of: when access of a device to a first system is detected, obtaining system information of the first system and system information of a second system recorded in the device; inputting the system information of the first system and the system information of the second system into a pre-trained learning model to obtain a result indicating whether the first system and the second system are the same system; and if the first system and the second system are not the same system, controlling the device to lock the output, wherein the second system is a system that the device has accessed before accessing the first system, and the system information includes information of N categories (N is an integer greater than 1).

[0007] An embodiment of the present application further provides a device control device, comprising: an acquisition module for acquiring system information of the first system and system information of a second system recorded in the device when access of the device to a first system is detected; an input module for inputting the system information of the first system and the system information of the second system into a pre-trained learning model to obtain a result indicating whether the first system and the second system are the same system; and a control module for controlling the device to lock the output if the first system and the second system are not the same system, wherein the second system is a system that the device has accessed before accessing the first system, and the system information includes information of N categories (N is an integer greater than 1).

[0008] An embodiment of the present application further provides an electronic device comprising at least one processor and a memory communicatively connected to the at least one processor, wherein the memory stores commands executable by the at least one processor, and execution of the commands by the at least one processor enables the at least one processor to perform the device control method described above.

[0009] An embodiment of the present application further provides a computer-readable storage medium having stored thereon a computer program that, when executed by a processor, realizes the above device control method. [Brief explanation of the drawings]

[0010] [Figure 1] 1 is a specific flowchart 1 of a device control method according to an embodiment of the present application. [Figure 2] 2 is a specific flowchart 2 of a device control method according to an embodiment of the present application. [Figure 3] 1 is a schematic block diagram of a power supply system according to an embodiment of the present application; [Figure 4] FIG. 1 is a schematic block diagram of a configuration model according to an embodiment of the present application. [Figure 5] FIG. 1 is a schematic block diagram of a structural model of an embodiment of the present application. [Figure 6] FIG. 1 is a schematic block diagram of a transition model according to an embodiment of the present application. [Figure 7] FIG. 1 is a schematic block diagram of a basic configuration model according to an embodiment of the present application; [Figure 8] FIG. 2 is a schematic block diagram of a version model according to an embodiment of the present application; [Figure 9] FIG. 1 is a schematic block diagram of an integrated model according to an embodiment of the present application. [Figure 10] 1 is a specific flowchart of building and training a learning model according to an embodiment of the present application. [Figure 11] 3 is a specific flowchart 3 of a device control method according to an embodiment of the present application. [Figure 12] FIG. 1 is a schematic block diagram of a device control device according to an embodiment of the present application. [Figure 13] 1 is a schematic block diagram of an electronic device according to an embodiment of the present application; DETAILED DESCRIPTION OF THE INVENTION

[0011] The main objective of the embodiments of the present invention is to provide a device control method and apparatus, an electronic device and a storage medium, and to provide a method for detecting device theft by identifying changes in status, without requiring the installation of additional hardware and overcoming the technical difficulties associated with installing hardware.

[0012] In order to clarify the objectives, technical means, and advantages of the embodiments of the present application, the following detailed description of each embodiment will be given with reference to the drawings. Although many technical details are described in each embodiment of the present application to facilitate understanding of the present application, those skilled in the art will understand that the technical means claimed in the present application can be realized without these technical details and various modifications based on the following embodiments. The division of the following embodiments is for the convenience of explanation and does not limit the specific implementation of the present application. The embodiments can be combined and referenced with each other as long as they are not inconsistent.

[0013] One embodiment of the present application relates to a device control method for identifying whether a device is currently stolen by identifying whether a first system currently being accessed by the device matches a second system that the device initially accessed, and controlling the device to lock the output if it is determined that the device has been stolen, thereby reducing the value of theft and further mitigating the problem of device theft.

[0014] FIG. 1 shows a specific procedure of the device control method of this embodiment.

[0015] In step 101, if an access of a device to a first system is detected, the system information of the first system and the system information of a second system recorded in the device are obtained.

[0016] In step 102, the system information of the first system and the system information of the second system are input into a pre-trained learning model to obtain a result indicating whether the first system and the second system are the same system.

[0017] In step 103, if the first system and the second system are not the same system, the device is controlled to lock the output.

[0018] In this embodiment, the device has accessed the second system before accessing the first system, so the device records system information for the second system. The first system stores system information for the first system. The system information includes multiple categories of information. When access to the first system by the device is detected, the system information for the first system and the system information for the second system are input into a pre-trained learning model, and a comprehensive determination is made based on the multiple categories of information to determine whether the first system and the second system are the same system. If it is determined that the first system and the second system are not the same system, the device is determined to be stolen. In this case, the device is controlled to lock its output, preventing normal use of the device, reducing its value as a theft target and ultimately mitigating the problem of device theft. In an embodiment of the present application, software comprehensively determines whether a change has occurred in the system currently accessed by the device based solely on the system information of the accessed system. If a change has occurred in the system currently accessed, the device is controlled to lock its output. Compared to incorporating a GPS positioning system into the device, this eliminates the need for additional hardware to detect device theft, significantly reducing the hardware cost of the device. Furthermore, software is easier to implement than hardware, so it can overcome the technical difficulties that existed with traditional hardware.

[0019] In one embodiment, the first system and the second system are both power supply systems, and the device is one of a rectifier, an inverter, an uninterruptible power supply, and a DC / DC system.

[0020] To solve the device theft problem, an example of this application assumes a scenario from everyday life. Suppose a student who has been absent from school returns to school and, while passing by a classroom, notices that all the teachers and students inside are unfamiliar faces. In this case, it can be determined that there is a high probability that this student does not belong to this group. This is an example of social psychology, similar to the change that occurred in the power supply system (the situation changed) after the rectifier was stolen.

[0021] Based on this example of social psychology, one possible way to mitigate the problem of device theft is to use machine learning or other methods to have the device automatically identify changes in its location, and if it determines that a change has occurred, lock it to prevent it from being used, thereby reducing its value as a theft target.

[0022] In group theory, groups, as a subject of social psychological research, have the following basic characteristics and parameters:

[0023] 1) Group composition: The situation of the members who make up the group.

[0024] 2) Group structure: communication structure, power structure (e.g., leader-subordinate relationship), tendency structure, emotion structure, interpersonal relationship structure, etc. When a group is viewed as an entity engaged in a common activity, it also includes the group's activity structure, i.e., the state of role division among group members in the common activity.

[0025] 3) Group transitions: various transition events that occur in a group, that is, dynamic expressions of human relationships within the group.

[0026] 4) Group values ​​and norms, such as standards and rules of behavior that are recognized as being adhered to by the group and its members, and may further include a group sanctions regime to ensure that group norms are observed and enforced by all group members.

[0027] 5) The level of group development.

[0028] In one embodiment, social psychology typically analyzes and considers groups based on the five points above. Based on this, this embodiment identifies changes in device location status and, ultimately, determines device theft, building a model by referencing these five basic characteristics and parameters. Because the operational status is identified through software, there is no need to install additional hardware to detect device theft, significantly reducing the hardware cost of the device. Furthermore, because software is easier to implement than hardware, it overcomes the technical difficulties inherent in conventional hardware.

[0029] Hereinafter, a case will be described in which the first system and the second system are both power supply systems and the device is a rectifier.

[0030] When the rectifier first accesses the second system, the monitoring unit of the second system acquires and records the basic characteristics and parameter information of the second system as system information of the second system. Specifically, this system information may be stored in a non-volatile memory such as EEPROM / FLASH, and the various types of information stored therein may be transmitted to each component in the system being accessed via a communication protocol. The rectifier receives and records this information.

[0031] During the operation of the second system, if a change occurs in the basic characteristics and parameter information of the second system, or if a change occurs in the characteristic parameters of the second system, for example, the battery capacity changes from 100 Ah to 150 Ah, or if a major event such as component replacement, version upgrade, safety accident, etc. occurs in the second system, or if a major incident occurs in the second system, for example, rectifier replacement, AC power distribution software update, or fire, theft, etc., the monitoring unit in the second system updates the stored system information of the second system and at the same time notifies each rectifier it is accessing to synchronously update and store the records.

[0032] When a rectifier accesses a first system, the first system obtains system information for the first system and system information for the second system recorded in the rectifier. The system information for the second system indicates the status of the second system, and the system information for the first system indicates the status of the first system. The system information typically includes N categories of information. To comprehensively determine whether the first system is the second system, in an embodiment of the present application, the system information for the first system and the system information for the second system are input into a pre-trained learning model to obtain a result indicating whether the first system and the second system are the same system. If it is determined that the first system and the second system are not the same system, the rectifier is determined to have been stolen and the rectifier is controlled to lock its output. The rectifier may also be configured to issue an alarm signal.

[0033] In one embodiment, the learning model includes N category models and one integrated model, and the N category models correspond one-to-one to the N categories. Referring to Figure 2, steps 201 and 203 are almost the same as steps 101 and 103, and will not be repeated here. However, step 202 differs in that it includes sub-steps 2021 and 2022.

[0034] In sub-step 2021, the system information of the first system and the system information of the corresponding category of the second system are input to the N category models, respectively, to obtain N determination results.

[0035] In sub-step 2022, the N determination results are input to the integrated model to obtain a result indicating whether the first system and the second system are the same system.

[0036] Referring to FIG. 3 , taking a power supply system as an example, the core components of the power supply system include a communication center supervision unit (CSU), a smart rectifier, a lithium battery pack, etc. Optionally, the power supply system may further include an AC power distribution unit, a DC power distribution unit, an AC / DC electricity meter, and other environmental detection units. Data is exchanged between each component via a communication network. Specifically, a field supervision unit (FSU) in the computer room monitors data between each system and exchanges data with the CSU via the communication network. The CSU also exchanges data with devices such as the rectifier, battery pack, AC power distribution unit, DC power distribution unit, AC electricity meter, and DC electricity meter via the communication network.

[0037] In one embodiment, referring to FIG. 3, the N category models may include any one or any combination of a configuration model, a structure model, a transition model, a base setting model, and a version model.

[0038] The layout configuration model acquires, as a determination result, a result indicating whether the layout configuration of the first system and the layout configuration of the second system are compatible, based on the layout configuration of each component in the system information.

[0039] Taking the case where both the first and second systems are power supply systems as an example, referring to the input / output diagram of the layout configuration model in Figure 4, the input parameters of the layout configuration model include the number and compatibility of rectifiers, batteries, and each component among the system information. The system information includes system information of the first system and system information of the second system. The judgment result is a layout configuration status value, where "0" indicates no change and "1" indicates a change.

[0040] The structural model obtains a judgment result indicating whether the southbound / northbound targets of the first system are compatible with the southbound / northbound targets of the second system based on the southbound and northbound targets of each component in the system information.

[0041] Taking the case where both the first and second systems are power supply systems as an example, referring to the input / output diagram of the structural model in Figure 5, the input parameters of the structural model include the rectifier, battery, monitoring unit, and the south / north orientation of each component among the system information. The system information includes the system information of the first system and the system information of the second system. The judgment result is the state value of the group structure, where "0" indicates no change and "1" indicates a change.

[0042] The transition model obtains, as a determination result, a result indicating whether or not the event set of the first system and the event set of the second system are compatible, based on the event set that occurred in each component in the system information.

[0043] Taking the case where the first and second systems are both power supply systems as an example, referring to the input / output diagram of the transition model in Figure 6, the input parameters of the transition model include the number of replacement records and the number of conformances, the number of version upgrades and the number of conformances, and the number of safety incidents and the number of conformances among the system information. The system information includes the system information of the first system and the system information of the second system. The judgment result is the state value of the transition of the population, where "0" indicates no change and "1" indicates a change.

[0044] The basic setting model acquires, as a determination result, a result indicating whether or not the basic setting parameters of the first system and the basic setting parameters of the second system are compatible, based on the basic setting parameters of each component in the system information.

[0045] Taking the case where the first system and the second system are both power supply systems as an example, referring to the input / output schematic diagram of the basic setting model in Figure 7, the input parameters of the basic setting model include the operating mode / battery capacity / load disconnection voltage and other parameter values ​​that need to be referenced from the system information. The system information includes the system information of the first system and the system information of the second system. The judgment result is the normative state value of the group, where "0" indicates no change and "1" indicates a change.

[0046] The version model acquires, as a determination result, a result indicating whether or not the version parameters of the first system and the version parameters of the second system are compatible, based on the version parameters of each component in the system information.

[0047] Taking the case where the first and second systems are both power supply systems as an example, referring to the input / output diagram of the version model in Figure 8, the input parameters of the version model include the version number and compatibility number of the rectifier / battery and each component among the system information. The system information includes the system information of the first system and the system information of the second system. The judgment result is a state value at the population level, where "0" indicates no change and "1" indicates a change.

[0048] After obtaining the judgment results output from N category models, these judgment results are integrated. Model The integration in Figure 9 Model Referring to the input / output diagram, the input parameters of the integrated model include the judgment results output from the N models. In one embodiment, the judgment results are the state value of the configuration, the state value of the group structure, the state value of the group transition, the state value of the group norm, and the state value of the group level, respectively. The output parameters are results indicating whether the first system and the second system are the same system, with "0" indicating no change and "1" indicating a change.

[0049] In this embodiment, N category models are specifically defined, and the information judged by the N category models is information from different dimensions of the system. The more category models are installed, the more accurate the results obtained by comprehensive judgment. The configuration of each component refers to the current connection number, description number, and compatibility number of each component. The south / north orientation of each component refers to the connection relationship between each component. The set of events occurring in each component includes a set of events that occurred in each component in the system, such as component replacement, version upgrade, and safety accident. The basic setting parameters of each component include the operating mode, battery capacity, overheat protection point, overvoltage protection point, etc. of each component in the system. The version parameters of each component include the version status of each component in the system.

[0050] In one embodiment, before inputting the system information of the first system and the second system into the pre-trained learning model, a learning model needs to be constructed and trained. Specifically, the learning model may be a machine learning model or a deep learning model. In one embodiment, a machine learning model is used as the learning model. A machine learning model consumes fewer resources than a deep learning model, thereby broadening the scope of application of the device control method.

[0051] Specifically, the configuration model, the structure model, the transition model, the basic configuration model, the version model, and the integrated model may be constructed and trained in advance, and the trained configuration model, the structure model, the transition model, the basic configuration model, the version model, and the integrated model may be used as the learning model. The learning model may be constructed and trained in a device, for example, a rectifier, but if the device has insufficient resources, the learning model may be constructed and trained in the monitoring systems of the first and second systems, respectively.

[0052] The steps of constructing and training a learning model in the first system are specifically shown in the flowchart of Figure 10. The method of constructing and training a learning model in the second system or rectifier is similar, so it will not be described again below.

[0053] In step 301, the basic characteristics and parameters of a large amount of communication power supply systems are collected as sample data.

[0054] The engineer must first build and train each learning model in the monitoring system of the first system. Specifically, the engineer collects sample data representing the basic characteristics and parameters of a large number of communication power supply systems. This sample data includes sample data for all application scenarios in which rectifiers can be deployed, such as the core network power supply in a DC computer room, the base frame of a macro base station, embedded power supplies, embedded power supplies in a micro base station, and wall-mounted power supplies. This sample data can be generated quickly and automatically by specifically configuring the tool software.

[0055] The sample data of the group configuration will be explained as an example. In the situation where the communication power supply system is applied to a 100A wall-mounted power supply, the rectifier, battery, monitoring unit, AC power distribution unit and DC power distribution unitIf the numbers of arrangements are 2, 1, 1, 0, and 0, respectively, the actual number of operations may be 2, 1, 1, 0, and 0. If the numbers of arrangements are 6, 2, 1, 0, and 0, respectively, when the communication power supply system is applied to a 300A embedded power supply, the actual number of operations may be 5, 2, 1, 0, and 0, or 4, 2, 1, 0, and 0. If the numbers of arrangements are 40, 4, 2, 1, and 1, respectively, when the communication power supply system is applied to a 2000A core network power supply, the actual number of operations may be 30 to 40, 2 to 4, 2, 1, and 1. In this way, as long as the data matches sample data that can theoretically actually occur, it can be used, and therefore sample data can be generated automatically, in large quantities, and quickly by the tool software.

[0056] In step 302, the sample data is tagged.

[0057] Specifically, two types of tags may be set: a tag "0" indicating no change in the situation, and a tag "1" indicating a change in the situation. These sample data may be tagged manually, or may be tagged automatically by tool software according to predetermined rules.

[0058] In step 303, the sample data is processed.

[0059] Specifically, sample data may be normalized using a formula to place all processed data between (0, 1). Here, Xreal is the true value of the actual sample, and X * is the data after normalization, Xmax is the maximum or upper limit value of the corresponding type of data sample, and Xmin is the minimum or lower limit value of the corresponding type of data sample.

[0060] For example, if the current number of rectifier connections is 11 and the range of the current number of rectifier connections is assumed to be 0 to 100, the current number of rectifier connections, 11, is normalized to 0.11. unit , and DC power distribution unit For southbound / northbound targets of equal components, one may simply define a single ID value between (0,1), e.g., Field Monitoring Unit FSU = 1.0, Monitoring Unit = 0.9, DC Distribution = 0.8, Battery = 0.7, Rectifier = 0.6. If the northbound target of a monitoring unit is an FSU, the northbound target may be denoted as {1.0}. If the southbound target is a battery and rectifier, the southbound target may be denoted as {0.7,0.6}.

[0061] In step 304, a training set, a validation set, and a test set are created.

[0062] Specifically, the training set, validation set, and test set may be created in a ratio of 6:2:2. Since the model must first be trained using the training set, a large amount of sample data is required. After training the model using the training set, the trained model may be validated using a validation set with a relatively small amount of data, and then the trained model may be tested and corrected using a test set with a relatively small amount of data.

[0063] In step 305, a configuration model is constructed and trained.

[0064] Specifically, a population configuration model is constructed and trained corresponding to the first point (population configuration) in the population theory. The input parameters of the configuration model include the configuration of each component in the first system and the second system, and the output parameters are whether the configuration changes or not. The configuration model is trained using training data including a training set, a validation set, and a test set.

[0065] In step 306, a structural model is built and trained.

[0066] Specifically, a population structural model is constructed and trained in accordance with the second point (population structure) in the population theory. The input parameters of the structural model include the south-facing / north-facing target of each component in the first system and the second system, and the output parameters are whether the south-facing / north-facing target is unchanged or changed. The structural model is trained using training data including a training set, a validation set, and a test set.

[0067] In step 307, a transition model is constructed and trained.

[0068] Specifically, a population transition model is constructed and trained in response to the third point (population transition) in the population theory. The input parameters of the transition model include a set of events that occurred in each component in the first and second systems, such as part replacement, version upgrade, and safety accident, and the output parameters are whether the set of events has changed or not. The transition model is trained using training data including a training set, a validation set, and a test set.

[0069] In step 308, a baseline model is constructed and trained.

[0070] Specifically, a population norm model is constructed and trained in response to the fourth point (population values ​​and norms) in the population theory. The input parameters of the basic setting model include the basic setting parameters of each component in the first system and the second system, such as the operating mode, battery capacity, overheat protection point, and overvoltage protection point, and the output parameters are the basic setting parameters that are unchanged or changed. The basic setting model is trained using training data including a training set, a validation set, and a test set.

[0071] In step 309, a version model is constructed and trained.

[0072] Specifically, in response to the fifth point in the above group theory (group development level), Version A model is constructed and trained. The input parameters of the version model include the version parameters of each component in the first and second systems, and the output parameters are: Version A version model is trained using training data with unchanged or changed parameters and including a training set, a validation set, and a test set.

[0073] It should be noted that there is no limitation on the order of steps 305 to 309. In order to improve installation efficiency, some of the version models may be simultaneously constructed and trained from the layout configuration model.

[0074] In step 310, a joint model is constructed and trained.

[0075] Specifically, referring to the input / output schematic diagram of the integrated model in Figure 9, the input parameters of the integrated model are the determination results output from each of the configuration model to the version model. The output parameters are results indicating whether the first system and the second system are the same system, and may be understood as results indicating whether the device has ever belonged to the first system. Furthermore, the integrated model is trained using training data including a training set, a validation set, and a test set.

[0076] In one embodiment, one or more of the above six learning models may be selected and set according to the actual situation.

[0077] When N+1 trained learning models are constructed and installed and all of the learning models are installed in the device, the device control method is applicable to the device. When all of the learning models are set in the first system, the device control method is applicable to the first system. When learning models are installed in both the device and the first system, the method may be executed by the device or the first system.

[0078] In one embodiment, referring to the flowchart of FIG. 11, steps 402 and 102 are substantially similar and will not be repeated here.

[0079] In sub-step 4011, if access to the first system of the device is detected, it is determined whether a pre-trained learning model is installed on the device, and if YES, proceed to sub-step 4012, and if NO, proceed to sub-step 4013.

[0080] In sub-step 4012, system information of the first system transmitted from the first system is received, and system information of the second system stored in the device is obtained.

[0081] In sub-step 4013, the system information of the second system is sent to the first system so that the first system receives the system information of the second system and obtains the system information of the first system stored in the first system.

[0082] In step 403, if the first system and the second system are not the same system, an enable signal is output to the theft processing unit in the device to enable the theft processing unit and control the device to lock the output.

[0083] Specifically, after accessing the first system, the device maintains normal output for a short period of time, for example, five minutes, during which time the device determines whether a pre-trained learning model is installed on the device. If a pre-trained learning model is installed on the device, the device acquires system information about the first system from the first system, and inputs the acquired system information about both the first and second systems into the learning model to make a comprehensive judgment. If a pre-trained learning model is not installed on the device, the device determines that a learning model is installed on the first system. In this case, the device transmits system information about the second system to the first system, and the first system inputs the acquired system information about the second system and the system information about the first system into the learning model to make a comprehensive judgment.

[0084] Figure 3 shows an example in which a trained learning model is installed in the monitoring unit of the first system. The monitoring unit obtains the system information of the second system recorded in the rectifier, inputs the system information of the first and second systems into the configuration model, structure model, transition model, basic installation model, and version model, respectively, and inputs the judgment results obtained from the five models into the integrated model to obtain a result indicating whether the rectifier has ever belonged to the first system. The result is then input into the rectifier's theft processing unit. If the rectifier has ever belonged to the first system, the rectifier's normal output is maintained. If the rectifier has never belonged to the first system, it is determined that the rectifier has been stolen, and the theft processing unit controls the rectifier to lock its output.

[0085] In one embodiment, different information is input into the trained layout configuration model, structure model, transition model, basic installation model, and version model. For example, the layout configuration of each component of the first system from the current system information and the layout configuration of each component of the second system from the described system information are input into the layout configuration model. The south-facing / north-facing target of each component of the first system from the current system information and the south-facing / north-facing target of each component of the second system from the described system information are input into the structure model. A set of events that have occurred in each component of the first system from the current system information and a set of events that have occurred in each component of the second system from the described system information are input into the transition model. The basic setting parameters of each component of the first system from the current system information and the basic setting parameters of each component of the second system from the described system information are input into the basic setting model. The version parameters of each component of the first system from the current system information and the version parameters of each component of the second system from the described system information are input into the version model. The determination results output from the configuration model, structure model, transition model, basic setting model, and version model are input into an integrated model to comprehensively determine whether the first system and the second system are the same system. This may also be understood as comprehensively determining whether the device has ever belonged to the first system. If it is determined that the device has ever belonged to the first system, the device is maintained in its normal operating state. If it is determined that the device has never belonged to the first system, the device is determined to have been stolen, and the output is locked. Furthermore, the rectifier may be configured to issue an alarm signal.

[0086] Obviously, the more complex the first and second systems are, the more sub-components they contain, such as rectifiers, batteries, AC / DC power distribution devices, etc., and the more and more significant the basic features and parameters of the group are, which can effectively improve the accuracy of rectifier feature identification and scene identification.

[0087] Because devices such as rectifiers are typically fragile, telecommunications carriers typically purchase a large number of spare parts such as rectifiers in order to ensure the safety of power supply by quickly replacing them. Obviously, these spare parts are also at risk of being stolen.

[0088] In one embodiment, when a station's communications power supply is started, all standby rectifiers are inserted one by one into slots with the lowest usage probability (e.g., the last slot), and the above-described operation of allowing devices to access the second system is performed sequentially, causing all standby rectifiers to record and store basic characteristic parameter information of the currently accessed power supply system. The standby rectifiers may then be removed from the currently accessed power supply system. If these standby rectifiers are resold, inserted into other power supply systems, or powered on by a competing manufacturer, the rectifiers can automatically identify the change in status and further lock their outputs, thereby reducing their value for theft and ultimately mitigating the problem of device theft.

[0089] One embodiment of the present application relates to a device control device, and referring to FIG. 12, the device control device comprises an acquisition module 1, an input module 2, and a control module 3, where the acquisition module 1 is connected to the input module 2, and the input module 2 is connected to the control module 3.

[0090] When an acquisition module 1 detects that a device is accessing a first system, it acquires system information of the first system and system information of a second system recorded on the device. The second system is a system that the device has accessed before accessing the first system. The input module 2 inputs the system information of the first system and the system information of the second system into a pre-trained learning model and obtains a result indicating whether the first system and the second system are the same system. The system information includes information of N categories, where N is an integer greater than 1. When a control module 3 determines that the first system and the second system are not the same system, it controls the device to lock the output.

[0091] Obviously, this embodiment is an apparatus embodiment corresponding to the above method embodiment, and this embodiment can be implemented in combination with the above method embodiment. The relevant technical details described in the above method embodiment are also valid for this embodiment, and will not be repeated here to avoid redundancy. Therefore, the relevant technical details described in this embodiment can also be applied to the above method embodiment.

[0092] Note that each module described in this embodiment is a logical module, and in actual operation, one logical unit may be one physical unit, a part of one physical unit, or may be realized by a combination of multiple physical units. Also, in order to highlight the innovativeness of this application, units that are less relevant to solving the technical problem presented by this application are not described in this embodiment, but this does not mean that other units do not exist in this embodiment.

[0093] One embodiment of the present application relates to a device, and as shown in Fig. 13, the device includes at least one processor 501 and a memory 502 communicatively connected to the at least one processor 501. The memory 502 stores commands executable by the at least one processor 501. Execution of the commands by the at least one processor 501 enables the at least one processor 501 to execute the device control method.

[0094] The memory and the processor are also connected by a bus. The bus may include any number of interconnected buses and bridges. The bus connects various circuits of one or more processors and memories. The bus may also connect various other circuits, such as peripheral devices, voltage regulators, power management circuits, etc., as is well known in the art and will not be described in further detail here. The bus interface serves as an interface between the bus and a transceiver. The transceiver may be a single element or multiple elements, including, for example, multiple receivers and transmitters, and serves as a unit for communication with other devices over a transmission medium. Data processed by the processor is transmitted over a wireless medium via an antenna. The antenna also receives data and transmits it to the processor.

[0095] The processor manages the bus and normal processing, and provides various functions including timers, interfacing with peripheral devices, voltage regulation, power management and other control functions. Memory is also used to store data used by the processor when performing operations.

[0096] One embodiment of the present application relates to a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the method embodiments described above.

[0097] That is, as can be understood by those skilled in the art, all or some of the steps in the methods of the above embodiments can be performed by instructing relevant hardware through a program. The program is stored in a storage medium and includes a plurality of commands for causing a device (which may be a single-chip microcomputer, a chip, etc.) or a processor to execute all or some of the steps of the methods described in each embodiment of the present application. The storage medium includes various media capable of storing program code, such as a U disk, a mobile hard disk, a ROM (Read-Only Memory), a RAM (Random Access Memory), a magnetic disk, an optical disk, etc.

[0098] As will be understood by those skilled in the art, the above embodiments are specific examples for realizing the present application, and various changes in form and details may be made in actual practice without departing from the spirit and scope of the present application.

Claims

1. 1. A device control method, executed by a device, comprising: When an access of the device to a first system is detected, acquiring system information of the first system and system information of a second system recorded in the device; inputting system information of the first system and system information of the second system into a learning model and obtaining a result indicating whether the first system and the second system are the same system; and controlling the device to lock an output if the first system and the second system are not the same system; the second system is a system that the device has accessed before accessing the first system; The system information includes information of N categories (N is an integer greater than 1), said locking an output includes making said device unavailable; the learning model includes N category models corresponding one-to-one to the N categories and one integrated model; The N category models are an arrangement configuration model for acquiring, as a determination result, a result indicating whether or not the arrangement configuration of the first system and the arrangement configuration of the second system are compatible, based on the arrangement configuration of each component in the system information; a structural model for acquiring, as a determination result, a result indicating whether the south-facing / north-facing target of the first system and the south-facing / north-facing target of the second system are compatible, based on the south-facing / north-facing target of each component in the system information; a transition model for acquiring, as a determination result, a result indicating whether or not an event set of the first system and an event set of the second system match, based on an event set that has occurred in each component among the system information; a basic setting model for obtaining a result indicating whether or not the basic setting parameters of the first system and the basic setting parameters of the second system are compatible as a determination result based on the basic setting parameters of each component in the system information; a version model for acquiring, as a determination result, a result indicating whether or not the version parameters of the first system and the version parameters of the second system are compatible, based on the version parameters of each component in the system information; Device control methods.

2. The step of inputting system information of the first system and system information of the second system into a learning model and obtaining a result indicating whether the first system and the second system are the same system comprises: inputting system information of the first system and system information of the corresponding category of the second system into the N category models, respectively, to obtain N judgment results; inputting the N determination results into the integrated model to obtain a result indicating whether the first system and the second system are the same system; The device control method according to claim 1 .

3. applied to the device, The step of acquiring system information of the first system and system information of the second system recorded in the device includes: receiving system information of the first system transmitted from the first system and acquiring system information of the second system stored in the device; The device control method according to claim 1 or 2.

4. applied to a monitoring unit in the first system, The step of acquiring system information of the first system and system information of the second system recorded in the device includes: receiving system information of the second system transmitted from the device and acquiring system information of the first system stored in the first system; The step of controlling the device to lock the output comprises: outputting an enable signal to a theft processing unit in the device to enable the theft processing unit and control the device to lock its output; The device control method according to claim 1 .

5. The learning model is a machine learning model. The device control method according to claim 1 .

6. The first system and the second system are both power supply systems, and the device is any one of a rectifier, an inverter, an uninterruptible power supply, and a DC / DC system. The device control method according to claim 1 .

7. an acquisition module for acquiring system information of the first system and system information of the second system recorded in the device when access of the device to the first system is detected; an input module for inputting system information of the first system and system information of the second system into a learning model and obtaining a result indicating whether the first system and the second system are the same system; a control module for controlling the device to lock an output if the first system and the second system are not the same system; the second system is a system that the device has accessed before accessing the first system; The system information includes information of N categories (N is an integer greater than 1), said locking an output includes making said device unavailable; the learning model includes N category models corresponding one-to-one to the N categories and one integrated model; The N category models are an arrangement configuration model for acquiring, as a determination result, a result indicating whether or not the arrangement configuration of the first system and the arrangement configuration of the second system are compatible, based on the arrangement configuration of each component in the system information; a structural model for acquiring, as a determination result, a result indicating whether the south-facing / north-facing target of the first system and the south-facing / north-facing target of the second system are compatible, based on the south-facing / north-facing target of each component in the system information; a transition model for acquiring, as a determination result, a result indicating whether or not an event set of the first system and an event set of the second system match, based on an event set that has occurred in each component among the system information; a basic setting model for obtaining a result indicating whether or not the basic setting parameters of the first system and the basic setting parameters of the second system are compatible as a determination result based on the basic setting parameters of each component in the system information; a version model for acquiring, as a determination result, a result indicating whether or not the version parameters of the first system and the version parameters of the second system are compatible, based on the version parameters of each component in the system information; Device control device.

8. at least one processor; a memory communicatively connected to the at least one processor; The memory stores commands executable by the at least one processor, and the at least one processor is enabled to execute the device control method according to claim 1 by executing the commands. Electronic devices.

9. A computer program is stored in the device control device, the computer program being configured to implement the device control method according to claim 1 when executed by a processor. A computer-readable storage medium.

Images