Internet of Things card risk type identification method and device, server and storage medium

Abstract

The invention provides an Internet of Things card risk type identification method and device, a server and a storage medium. The method comprises the following steps: acquiring Internet of Things card data from an Internet of Things data platform; inputting the Internet of Things card data into the adjusted large language model; the adjusted output layer of the large language model generates a plurality of terminal types to be pointed corresponding to each terminal type; inputting the plurality of to-be-pointed terminal types into a directional network module, so that the directional network module obtains a probability value corresponding to the to-be-pointed terminal type with the maximum comprehensive weight value from the plurality of to-be-pointed terminal types; acquiring the Internet of Things card data corresponding to the probability value from the Internet of Things card data to obtain the Internet of Things card data corresponding to each terminal type; and according to the Internet of Things card feature data of each terminal type and the data in the Internet of Things card risk type feature library, identifying the Internet of Things card risk type. According to the method provided by the invention, the accuracy of identifying the risk type of the Internet of Things card is improved.

Description

Technical Field

[0001] The present application relates to the technical field of Internet of Things, and in particular to a method, device, server and storage medium for identifying the risk type of an Internet of Things card. Background Art

[0002] The IoT card is a traffic card provided by operators to meet the IoT industry's management needs for device networking. It provides network connection services for IoT devices and cannot be used for personal devices such as mobile phones. Due to the simplification of the IoT card application process, many problems of illegal use of IoT cards have arisen.

[0003] At present, in the security monitoring process of IoT cards, it is found that due to the lack of semantic relationship between the terminal types of IoT cards, the large language model has a semantic hallucination problem, outputs the wrong risk type, and reduces the accuracy of identifying the risk type of IoT cards. Summary of the invention

[0004] The embodiments of the present application provide a method, device, server and storage medium for identifying the risk type of an Internet of Things card, so as to achieve the effect of improving the accuracy of identifying the risk type of an Internet of Things card.

[0005] In a first aspect, an embodiment of the present application provides a method for identifying risk types of an Internet of Things card, comprising: collecting Internet of Things card data from an Internet of Things data platform; wherein the Internet of Things card data includes multiple terminal types; inputting the Internet of Things card data into an adjusted large language model; wherein the adjusted large language model includes a directional network module; the output layer of the adjusted large language model generates multiple terminal types to be directed to corresponding to each terminal type; inputting the multiple terminal types to be directed to the directional network module, so that the directional network module obtains a probability value corresponding to the terminal type to be directed with the largest comprehensive weight value from the multiple terminal types to be directed; obtaining Internet of Things card data corresponding to the probability value from the Internet of Things card data to obtain Internet of Things card data corresponding to each terminal type; extracting features of the Internet of Things card data corresponding to each terminal type to obtain Internet of Things card feature data for each terminal type; identifying the Internet of Things card risk type of the Internet of Things card data corresponding to each terminal type according to the Internet of Things card feature data of each terminal type and data in a risk type feature library of the Internet of Things card.

[0006] In a possible implementation, multiple terminal types to be pointed to are input into a directional network module, so that the directional network module obtains a probability value corresponding to a terminal type to be pointed to having the largest comprehensive weight value from among the multiple terminal types to be pointed to, including: obtaining the comprehensive weight value of each terminal type to be pointed to; and according to the comprehensive weight value of each terminal type to be pointed to, obtaining a probability value corresponding to the terminal type to be pointed to having the largest comprehensive weight value from among the multiple terminal types to be pointed to.

[0007] In a possible implementation manner, the formula for obtaining the comprehensive weight value of each terminal type to be directed is:

[0008]

[0009] In the formula, represents the comprehensive weight value of the j terminal types to be pointed to, i represents the number of multiple terminal types to be pointed to, γ represents the initialization matrix weight, and Indicates two different characters in the type of the terminal to be pointed to by the jth terminal. express The weight of express The weight of .

[0010] In a possible implementation, according to the comprehensive weight value of each terminal type to be directed, a probability value corresponding to the terminal type to be directed with the largest comprehensive weight value is obtained from multiple terminal types to be directed, and the formula is:

[0011]

[0012] In the formula, Indicates the probability value corresponding to the terminal type to be pointed to with the largest comprehensive weight value, It indicates obtaining the maximum comprehensive weight value from the i terminal types to be pointed to, and γ indicates the initialization matrix weight.

[0013] In a possible implementation, before collecting IoT card data from the IoT data platform, it also includes: regularly collecting historical IoT card data from the IoT data platform; labeling the risk types involved in the historical IoT card data according to the risk type sample library to obtain an IoT card risk type library; and extracting features from historical IoT card data of different risk types in the IoT card risk type library to obtain an IoT card risk type feature library.

[0014] In a possible implementation, before collecting IoT card data from the IoT data platform, it also includes: shielding specific attention heads of the large language model to obtain an initial large language model; adding a directional network module to the output layer of the initial large language model to obtain an adjusted large language model.

[0015] In a second aspect, an embodiment of the present application provides a device for identifying a risk type of an Internet of Things card, including:

[0016] A data collection module is used to collect IoT card data from an IoT data platform; wherein the IoT card data includes multiple terminal types;

[0017] An input module, used for inputting IoT card data into an adjusted large language model; wherein the adjusted large language model includes a directional network module;

[0018] A generation module, used for the output layer of the adjusted large language model to generate multiple terminal types to be pointed to corresponding to each terminal type;

[0019] A first acquisition module, used for inputting a plurality of terminal types to be directed to a directional network module, so that the directional network module obtains a probability value corresponding to a terminal type to be directed with a maximum comprehensive weight value from among the plurality of terminal types to be directed;

[0020] A second acquisition module is used to acquire the IoT card data corresponding to the probability value from the IoT card data to obtain the IoT card data corresponding to each terminal type;

[0021] An extraction module is used to extract the characteristics of the IoT card data corresponding to each terminal type, and obtain the IoT card characteristic data of each terminal type;

[0022] The risk type identification module is used to identify the IoT card risk type of the IoT card data corresponding to each terminal type based on the IoT card feature data of each terminal type and the data in the IoT card risk type feature library.

[0023] In a third aspect, an embodiment of the present application provides a server, including: a memory, a processor;

[0024] The memory stores computer-executable instructions;

[0025] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the above first aspect and / or various possible implementations of the first aspect.

[0026] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the first aspect above and / or various possible implementations of the first aspect.

[0027] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the above first aspect and / or various possible implementation methods of the first aspect.

[0028] The method, device, server and storage medium for identifying the risk type of the Internet of Things card provided in the embodiment of the present application input the collected Internet of Things card data containing the terminal type into the adjusted large language model, and generate multiple terminal types to be pointed to corresponding to each terminal type in the output layer of the adjusted large language model; the directional network module obtains the probability value corresponding to the terminal type to be pointed to with the largest comprehensive weight value, and obtains the Internet of Things card data corresponding to the probability value from the Internet of Things card data. Through the directional network module, the terminal type in the Internet of Things card data can be pointed to from the collected Internet of Things card data, and the Internet of Things card data related to the terminal type can be output, so as to avoid the semantic hallucination problem in the large language model and provide data support for identifying the risk type of the Internet of Things card. The features of the Internet of Things card data are extracted, and the risk type is identified based on the data in the Internet of Things card feature data and the risk type feature library of the Internet of Things card. Thereby, the accuracy of identifying the risk type of the Internet of Things card is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0030] Figure 1 A schematic diagram of the structure of a server provided in an embodiment of the present application;

[0031] Figure 2 A schematic diagram of a process for identifying the risk type of an Internet of Things card provided in an embodiment of the present application;

[0032] Figure 3 A schematic diagram of the structure of a device for identifying risk types of Internet of Things cards provided in an embodiment of the present application;

[0033] Figure 4 A schematic diagram of the hardware structure of the server provided in an embodiment of the present application.

[0034] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0035] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0036] Figure 1 A schematic diagram of the structure of the server provided in the embodiment of the present application, such as Figure 1 As shown, the server provided in this embodiment includes: a receiving device 101, a processor 102 and a display device 103.

[0037] It is to be understood that the structure illustrated in the embodiment of the present application does not constitute a specific limitation on the method. In other feasible implementations of the present application, the above architecture may include more or fewer components than shown in the figure, or combine certain components, or split certain components, or arrange the components differently, which can be determined according to the actual application scenario and is not limited here. Figure 1 The components shown may be implemented in hardware, software, or a combination of software and hardware.

[0038] In the specific implementation process, the receiving device 101 can be an input / output interface or a communication interface, and can collect Internet of Things card data from the Internet of Things data platform.

[0039] The processor 102 can process the IoT card data collected from the IoT data platform to obtain the risk type of the IoT card.

[0040] The display device 103 can be used to display the risk type of the Internet of Things card.

[0041] It should be understood that the above-mentioned processor can be implemented by the processor reading instructions in the memory and executing the instructions, or it can be implemented by a chip circuit.

[0042] In addition, the network architecture and business scenarios described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Ordinary technicians in this field can know that with the evolution of network architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0043] The IoT card is a traffic card provided by operators to meet the IoT industry's management needs for device networking. It provides network connection services for IoT devices and cannot be used for personal devices such as mobile phones. Due to the simplification of the IoT card application process, many problems of illegal use of IoT cards have emerged. At present, in the security monitoring process of IoT cards, it is found that due to the lack of semantic relationship between the terminal types of IoT cards, the large language model has semantic hallucination problems, outputs the wrong risk type, and reduces the accuracy of identifying IoT card risk types.

[0044] In order to solve the above technical problems, the present application proposes the following technical ideas: Since there is no semantic relationship between the terminal types of the Internet of Things cards, the large language model has a semantic hallucination problem, outputs the wrong risk type, and reduces the accuracy of identifying the risk type of the Internet of Things card. The inventor thought of not outputting the risk type of the Internet of Things card through the large language model, but directly obtaining and outputting the data related to the terminal type from the collected Internet of Things card data. Add a directional network module to the output layer of the large language model. The directional network module can point to the terminal type in the Internet of Things card data and output the Internet of Things card data related to the terminal type, avoiding the semantic hallucination problem of the large language model and providing data support for identifying the risk type of the Internet of Things card. Extract the features of the Internet of Things card data, and identify the risk type based on the data in the Internet of Things card feature data and the risk type feature library of the Internet of Things card. Thereby improving the accuracy of identifying the risk type of the Internet of Things card.

[0045] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0046] Figure 2 A flow chart of a method for identifying the risk type of an IoT card provided in an embodiment of the present application is shown in FIG. Figure 2 As shown, the method includes:

[0047] S201: Collecting IoT card data from an IoT data platform; wherein the IoT card data includes multiple terminal types.

[0048] In this embodiment, the collected IoT card data includes real-time call bill data, traffic data, roaming data, Internet access logs, IoT card real-time billing information, cmp platform data and Jasper platform data.

[0049] In this embodiment, the IoT card data is processed under the same vectorization dimension.

[0050] S202: Inputting the IoT card data into the adjusted large language model; wherein the adjusted large language model includes a directional network module.

[0051] In this embodiment, a directional network module is added to the output layer of the large language model, wherein the directional network module is used to point to the terminal type in the IoT card data, and obtain and output the IoT card data corresponding to the terminal type from the IoT card data input to the adjusted large language model.

[0052] S203: The output layer of the adjusted large language model generates multiple terminal types to be pointed to corresponding to each terminal type.

[0053] S204: Inputting a plurality of terminal types to be directed to the directional network module, so that the directional network module obtains a probability value corresponding to a terminal type to be directed with a maximum comprehensive weight value from among the plurality of terminal types to be directed.

[0054] Specifically, a comprehensive weight value of each terminal type to be directed is obtained; and according to the comprehensive weight value of each terminal type to be directed, a probability value corresponding to the terminal type to be directed with the largest comprehensive weight value is obtained from multiple terminal types to be directed.

[0055] In this embodiment, the formula for obtaining the comprehensive weight value of each terminal type to be directed is:

[0056]

[0057] In the formula, represents the comprehensive weight value of the j terminal types to be pointed to, i represents the number of multiple terminal types to be pointed to, γ represents the initialization matrix weight, and Indicates two different characters in the type of the terminal to be pointed to by the jth terminal. express The weight of express The weight of .

[0058] In this embodiment, historical IoT card data is collected from the IoT data platform at regular intervals to form an IoT card basic database. The terminal types of all IoT cards in the basic database are marked, and a large weight is assigned to each character in the terminal type to ensure that the comprehensive weight value of the terminal type of the real IoT card is greater than the comprehensive weight values ​​of other terminal types to be pointed to.

[0059] In this embodiment, according to the comprehensive weight value of each terminal type to be directed, the probability value corresponding to the terminal type to be directed with the largest comprehensive weight value is obtained from multiple terminal types to be directed, and the formula is:

[0060]

[0061] In the formula, Indicates the probability value corresponding to the terminal type to be pointed to with the largest comprehensive weight value, It indicates obtaining the maximum comprehensive weight value from the i terminal types to be pointed to, and γ indicates the initialization matrix weight.

[0062] In this embodiment, a probability value corresponding to the maximum comprehensive weight value is obtained from a plurality of terminal types to be directed.

[0063] S205: Obtain the Internet of Things card data corresponding to the probability value from the Internet of Things card data to obtain the Internet of Things card data corresponding to each terminal type.

[0064] In this embodiment, the probability value corresponding to the maximum comprehensive weight value is also the largest. The IoT card data corresponding to the maximum probability value is the IoT card data corresponding to the terminal type of the real IoT card.

[0065] In this embodiment, since the terminal types do not have a semantic relationship, multiple terminal types to be pointed to will be generated in the output layer, and the directional network module will point to the terminal type of the real Internet of Things card to obtain the Internet of Things card data corresponding to the terminal type of the real Internet of Things card from the Internet of Things card data.

[0066] S206: Extract features of the Internet of Things card data corresponding to each terminal type to obtain feature data of the Internet of Things card for each terminal type.

[0067] S207: Identify the IoT card risk type of the IoT card data corresponding to each terminal type according to the IoT card feature data of each terminal type and the data in the IoT card risk type feature library.

[0068] In this embodiment, the IoT card risk types include high-frequency calling and receiving risk, device replacement risk, high-risk area roaming risk, abnormal traffic usage risk, and track break risk. The IoT card risk type feature library includes features of each risk type. The risk type is identified by comparing the IoT card feature data of each terminal type with the data in the IoT card risk type feature library.

[0069] In summary, the collected IoT card data containing terminal types are input into the adjusted large language model, and multiple terminal types to be pointed to corresponding to each terminal type are generated in the output layer of the adjusted large language model; the directional network module obtains the probability value corresponding to the terminal type to be pointed to with the largest comprehensive weight value, and obtains the IoT card data corresponding to the probability value from the IoT card data. Through the directional network module, the terminal type in the IoT card data can be pointed to from the collected IoT card data, and the IoT card data related to the terminal type can be output, avoiding the semantic hallucination problem of the large language model, and providing data support for identifying the risk type of the IoT card. The features of the IoT card data are extracted, and the risk type is identified based on the IoT card feature data and the data in the IoT card risk type feature library. This improves the accuracy of identifying the risk type of the IoT card.

[0070] Based on the above embodiment, in this embodiment, the process of obtaining the risk type feature library of the Internet of Things card is introduced, which is detailed as follows:

[0071] S301: Periodically collect historical IoT card data from the IoT data platform.

[0072] In this embodiment, historical IoT card data is collected regularly to ensure the continuity and regularity of IoT card data acquisition.

[0073] Optionally, historical IoT card data includes historical real-time call bill data, traffic data, roaming data, Internet access logs, IoT card real-time billing information, cmp platform data and Jasper platform data.

[0074] In this embodiment, historical IoT card data of different sources and types are stored by type and stored in HDFS to form an IoT card basic database.

[0075] Optionally, the terminal type of the IoT card is marked, the terminal type corresponding to each IoT card is clarified, and a large weight is assigned to each character in the terminal type.

[0076] Optionally, remove abnormal data in the IoT card basic database, such as data that is obviously erroneous or does not conform to normal usage logic; eliminate duplicate roaming records to avoid deviations in analysis results due to duplicate data and reduce unnecessary data redundancy.

[0077] S302: According to the risk type sample library, the risk types involved in the historical Internet of Things card data are marked to obtain the Internet of Things card risk type library.

[0078] Among them, the risk type sample library contains known risk behavior patterns and case data.

[0079] Among them, the risk types include high-frequency calling and calling risks, that is, the number of calls and calling parties is abnormally frequent in a short period of time; device replacement risk, such as the IoT card frequently changes the connected terminal device in a short period of time; high-risk area roaming risk, if the IoT card appears in a high-risk area for roaming activities; abnormal traffic usage risk, including a sudden and substantial increase in traffic usage or abnormal traffic usage pattern; and track breaking risk, such as the IoT card's usage track is abnormally interrupted or does not conform to normal business logic.

[0080] S303: Extract features from historical IoT card data of different risk types in the IoT card risk type library to obtain an IoT card risk type feature library.

[0081] In this embodiment, feature extraction is performed on different types of historical IoT card data to obtain feature data of each type of IoT card to form an IoT card risk type feature library.

[0082] In summary, through regular collection, a large amount of IoT card data in different time periods can be accumulated, covering multiple terminal types, providing a sample basis for subsequent risk identification; by marking the risk types involved in historical IoT card data, an IoT card risk type library is obtained. Through feature extraction, a feature database of IoT cards of different risk types is obtained, providing strong data support for the subsequent accurate identification of risk types of IoT cards.

[0083] Based on the above embodiment, in this embodiment, the process of obtaining the adjusted large language model is introduced, which is described in detail as follows:

[0084] S401: Shield specific attention heads of the large language model to obtain an initial large language model;

[0085] In this embodiment, when the large language model processes information, the attention mechanism is a key part in the architecture of the large language model, which helps the model decide which parts to focus on when processing input information. The attention head is a component of the attention mechanism, and each attention head can focus on different aspects or features of the input.

[0086] Optionally, the initial large language model after shielding a specific attention head (RH) is used to construct a directional network module using an end-to-end principle.

[0087] S402: Add a directional network module to the output layer of the initial large language model to obtain an adjusted large language model.

[0088] In this embodiment, the initial large language model after shielding the specific attention head (RH) adopts the end-to-end principle to construct a directional network module.

[0089] In summary, by shielding the specific attention heads of the large language model, the IoT card data corresponding to the terminal type can be directly obtained from the input IoT card data through the directional network module, avoiding the semantic hallucination problem of the large language model, and providing data support for identifying the risk types of IoT cards, thereby improving the accuracy of identifying the risk types of IoT cards.

[0090] Figure 3 A schematic diagram of the structure of a device for identifying the risk type of an Internet of Things card provided in an embodiment of the present application, such as Figure 3As shown, the device for identifying the risk type of an Internet of Things card provided in this embodiment includes: a data acquisition module 301, an input module 302, a generation module 303, a first acquisition module 304, a second acquisition module 305, an extraction module 306 and a risk type identification module 307.

[0091] The data collection module 301 is used to collect Internet of Things card data from the Internet of Things data platform; wherein the Internet of Things card data includes multiple terminal types.

[0092] The input module 302 is used to input the IoT card data into the adjusted large language model; wherein the adjusted large language model includes a directional network module.

[0093] The generating module 303 is used for the output layer of the adjusted large language model to generate a plurality of terminal types to be directed corresponding to each terminal type.

[0094] The first acquisition module 304 is used to input multiple terminal types to be directed to the directional network module, so that the directional network module obtains the probability value corresponding to the terminal type to be directed with the largest comprehensive weight value from the multiple terminal types to be directed.

[0095] The second acquisition module 305 is used to acquire the Internet of Things card data corresponding to the probability value from the Internet of Things card data, so as to obtain the Internet of Things card data corresponding to each terminal type.

[0096] The extraction module 306 is used to extract the characteristics of the Internet of Things card data corresponding to each terminal type, and obtain the characteristic data of the Internet of Things card of each terminal type.

[0097] The risk type identification module 307 is used to identify the IoT card risk type of the IoT card data corresponding to each terminal type according to the IoT card feature data of each terminal type and the data in the IoT card risk type feature library.

[0098] In a possible implementation, the first acquisition module 304 is specifically used to: obtain a comprehensive weight value of each terminal type to be pointed to; and according to the comprehensive weight value of each terminal type to be pointed to, obtain a probability value corresponding to the terminal type to be pointed to with the largest comprehensive weight value from multiple terminal types to be pointed to.

[0099] In a possible implementation, the first acquisition module 304 includes a comprehensive weight value calculation unit, and the formula of the comprehensive weight value calculation unit is:

[0100]

[0101] In the formula, represents the comprehensive weight value of the j terminal types to be pointed to, i represents the number of multiple terminal types to be pointed to, γ represents the initialization matrix weight, and Indicates two different characters in the type of the terminal to be pointed to by the jth terminal. express The weight of express The weight of .

[0102] In a possible implementation, the first acquisition module 304 includes a probability calculation unit, and the formula of the probability calculation unit is:

[0103]

[0104] In the formula, Indicates the probability value corresponding to the terminal type to be pointed to with the largest comprehensive weight value, It indicates obtaining the maximum comprehensive weight value from the i terminal types to be pointed to, and γ indicates the initialization matrix weight.

[0105] In a possible implementation, the device for identifying the risk type of an Internet of Things card also includes: a third acquisition module, used to periodically collect historical Internet of Things card data from an Internet of Things data platform; label the risk types involved in the historical Internet of Things card data according to the risk type sample library to obtain an Internet of Things card risk type library; perform feature extraction on the historical Internet of Things card data of different risk types in the Internet of Things card risk type library to obtain an Internet of Things card risk type feature library.

[0106] In a possible implementation, the device for identifying the risk type of an Internet of Things card also includes: a fourth acquisition module, which shields a specific attention head of the large language model to obtain an initial large language model; and adds a directional network module to the output layer of the initial large language model to obtain an adjusted large language model.

[0107] The device for identifying the risk type of an Internet of Things card provided in this embodiment can execute the method provided in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be described in detail here.

[0108] Figure 4 The hardware structure diagram of the server provided in the embodiment of the present application is shown in FIG. Figure 4 As shown, the server provided in this embodiment includes: at least one processor 401 and a memory 402. Optionally, the server also includes a communication component 403. The processor 401, the memory 402 and the communication component 403 are connected via a bus 404.

[0109] In a specific implementation process, at least one processor 401 executes the computer-executable instructions stored in the memory 402, so that at least one processor 401 executes the above method.

[0110] The specific implementation process of the processor 401 can be found in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be repeated here.

[0111] In the above embodiments, it should be understood that the processor can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the invention can be directly implemented as a hardware processor, or can be implemented by a combination of hardware and software modules in the processor.

[0112] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (NVM), such as at least one disk storage.

[0113] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of this application is not limited to only one bus or one type of bus.

[0114] The present application also provides a computer program product, including a computer program, which implements the above method when executed by a processor.

[0115] The present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the above method is implemented.

[0116] The above-mentioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special-purpose computer.

[0117] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (Application Specific Integrated Circuits, referred to as: ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.

[0118] The division of units is only a logical function division, and there may be other divisions in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0119] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0120] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0121] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0122] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0123] Finally, it should be noted that those skilled in the art will readily conceive of other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses or adaptations of the present invention, which follow the general principles of the present invention and include common knowledge or customary technical means in the art not disclosed by the present invention, are not limited to the precise structure described above and shown in the drawings, and may be modified and changed in various ways without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A method for identifying the risk type of an Internet of Things card, characterized in that: Applicable to servers, including: Collecting IoT card data from an IoT data platform; wherein the IoT card data includes multiple terminal types; Inputting the IoT card data into the adjusted large language model; wherein the adjusted large language model includes a directional network module; The output layer of the adjusted large language model generates a plurality of terminal types to be directed corresponding to each terminal type; Inputting a plurality of terminal types to be directed to a directional network module, so that the directional network module obtains a probability value corresponding to a terminal type to be directed with a maximum comprehensive weight value from the plurality of terminal types to be directed; Obtaining the IoT card data corresponding to the probability value from the IoT card data to obtain the IoT card data corresponding to each terminal type; Extracting the features of the Internet of Things card data corresponding to each terminal type to obtain feature data of the Internet of Things card for each terminal type; According to the Internet of Things card feature data of each terminal type and the data in the Internet of Things card risk type feature library, the Internet of Things card risk type of the Internet of Things card data corresponding to each terminal type is identified.

2. The method according to claim 1, characterized in that The step of inputting a plurality of terminal types to be directed to a directional network module so that the directional network module obtains a probability value corresponding to a terminal type to be directed having a maximum comprehensive weight value from among the plurality of terminal types to be directed, comprises: Obtaining a comprehensive weight value of each terminal type to be directed; According to the comprehensive weight value of each terminal type to be directed, a probability value corresponding to the terminal type to be directed having the largest comprehensive weight value is obtained from the multiple terminal types to be directed.

3. The method according to claim 2, characterized in that The formula for obtaining the comprehensive weight value of each terminal type to be directed is: In the formula, represents the comprehensive weight value of the j terminal types to be pointed to, i represents the number of multiple terminal types to be pointed to, γ represents the initialization matrix weight, and Indicates two different characters in the type of the terminal to be pointed to by the jth terminal. express The weight of express The weight of .

4. The method according to claim 3, characterized in that The formula for obtaining the probability value corresponding to the terminal type to be directed with the largest comprehensive weight value from the multiple terminal types to be directed according to the comprehensive weight value of each terminal type to be directed is: In the formula, Indicates the probability value corresponding to the terminal type to be pointed to with the largest comprehensive weight value, It indicates obtaining the maximum comprehensive weight value from the i terminal types to be pointed to, and γ indicates the initialization matrix weight.

5. The method according to any one of claims 1 to 4, characterized in that: Before collecting the IoT card data from the IoT data platform, the method further includes: Collect historical IoT card data from the IoT data platform at regular intervals; According to the risk type sample library, the risk types involved in the historical IoT card data are marked to obtain an IoT card risk type library; Feature extraction is performed on historical IoT card data of different risk types in the IoT card risk type library to obtain an IoT card risk type feature library.

6. The method according to any one of claims 1 to 4, characterized in that: Before collecting the IoT card data from the IoT data platform, the method further includes: Shield the specific attention heads of the large language model to obtain the initial large language model; A directional network module is added to the output layer of the initial large language model to obtain an adjusted large language model.

7. A device for identifying the risk type of an Internet of Things card, characterized in that: Applicable to servers, including: A data collection module, used to collect IoT card data from an IoT data platform; wherein the IoT card data includes multiple terminal types; An input module, used for inputting the IoT card data into the adjusted large language model; wherein the adjusted large language model includes a directional network module; A generation module, used for the output layer of the adjusted large language model to generate a plurality of terminal types to be pointed to corresponding to each terminal type; A first acquisition module, used for inputting a plurality of terminal types to be directed to a directional network module, so that the directional network module acquires a probability value corresponding to a terminal type to be directed with a maximum comprehensive weight value from the plurality of terminal types to be directed; A second acquisition module is used to acquire the Internet of Things card data corresponding to the probability value from the Internet of Things card data, so as to obtain the Internet of Things card data corresponding to each terminal type; An extraction module, used to extract the characteristics of the Internet of Things card data corresponding to each terminal type, and obtain characteristic data of the Internet of Things card for each terminal type; The risk type identification module is used to identify the Internet of Things card risk type of the Internet of Things card data corresponding to each terminal type according to the Internet of Things card feature data of each terminal type and the data in the Internet of Things card risk type feature library.

8. A server, characterized in that: include: Memory, processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor performs the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 6 when executed by a processor.

10. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 6 when being executed by a processor.

Images