Security level determination method, electronic equipment, storage medium and program product

Abstract

The embodiment of the invention provides a security level determination method, electronic equipment, a storage medium and a program product. The method comprises the following steps: receiving object information of a data object; determining an object type and feature information corresponding to the data object according to the object information; analyzing and processing the object information, the object type and the feature information to obtain a classification text corresponding to the data object; and performing text processing on the object type and the feature information to obtain a prompt text corresponding to the data object. And determining a target security level corresponding to the data object according to the classification text and the prompt text. The method improves the accuracy of determining the security level.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a method for determining a security level, an electronic device, a storage medium, and a program product. Background Art

[0002] Data objects can be divided into different security levels according to certain standards and specifications to ensure that appropriate security measures and controls can be implemented to protect sensitive data objects from unauthorized access and attacks.

[0003] In the prior art, the rule engine can analyze, process or make decisions on the input data objects through a predefined set of rules to obtain the security level corresponding to the data objects. The rule engine directly classifies the security level of the data objects according to the object information of the data objects. The same feature fields may appear in different object information, and the differences of the same feature fields in different data objects are ignored, resulting in low accuracy in determining the security level. Summary of the invention

[0004] The embodiments of the present application provide a method for determining a security level, an electronic device, a storage medium, and a program product, so as to achieve the effect of improving the accuracy of determining the security level.

[0005] In a first aspect, an embodiment of the present application provides a method for determining a security level, including:

[0006] receiving object information of a data object;

[0007] Determine, according to the object information, the object type and characteristic information corresponding to the data object;

[0008] Analyze and process the object information, the object type and the feature information to obtain a classification text corresponding to the data object;

[0009] Performing text processing on the object type and the characteristic information to obtain a prompt text corresponding to the data object;

[0010] A target security level corresponding to the data object is determined based on the classification text and the prompt text.

[0011] In a possible implementation, determining a target security level corresponding to the data object according to the classification text and the prompt text includes:

[0012] Performing a first classification process on the classified text through a target classification model to obtain a first weight of a security level corresponding to the data object;

[0013] Based on the first large model of the rule set, the prompt text is subjected to a second classification process to obtain a second weight corresponding to the security level of the data object;

[0014] A target security level corresponding to the data object is determined according to the first weight and the second weight.

[0015] In a possible implementation manner, determining a target security level corresponding to the data object according to the first weight and the second weight includes:

[0016] determining a level difference between the first weight and the second weight;

[0017] If the level difference is less than or equal to a preset difference, the first weight and the second weight are fused to obtain a target weight;

[0018] A target security level corresponding to the data object is determined according to the target weight.

[0019] In a possible implementation, analyzing and processing the object information, the object type, and the feature information to obtain a classification text corresponding to the data object includes:

[0020] Generating an object description text of the data object according to the object information;

[0021] The object type, the feature information and the object description text are concatenated to obtain a classification text corresponding to the data object.

[0022] In a possible implementation manner, generating an object description text of the data object according to the object information includes:

[0023] Extracting features from the object information to obtain multiple feature words;

[0024] The plurality of characteristic words are analyzed and processed by the second largest model to obtain the object description text.

[0025] In a possible implementation, text processing is performed on the object type and the characteristic information to obtain a prompt text corresponding to the data object, including:

[0026] Get the prompt template corresponding to the first largest model;

[0027] The prompt text is determined according to the object type, the feature information and the prompt template.

[0028] In a possible implementation, determining the prompt text according to the object type, feature information, and prompt template includes:

[0029] Performing text recognition processing on the prompt template to determine a first replacement field corresponding to the object type and a second replacement field corresponding to the feature information;

[0030] The first replacement field is replaced by the object type, and the second replacement field is replaced by the feature information to obtain the prompt text.

[0031] In a second aspect, an embodiment of the present application provides a device for determining a security level, including a receiving module, a first determining module, an analyzing and processing module, a text processing module, and a second determining module:

[0032] The receiving module is used to receive object information of a data object;

[0033] The first determination module is used to determine the object type and feature information corresponding to the data object according to the object information;

[0034] The analysis and processing module is used to analyze and process the object information, the object type and the feature information to obtain the classification text corresponding to the data object;

[0035] The text processing module is used to perform text processing on the object type and the feature information to obtain a prompt text corresponding to the data object;

[0036] The second determination module is used to determine the target security level corresponding to the data object according to the classification text and the prompt text.

[0037] In a possible implementation manner, the second determining module is specifically configured to:

[0038] Performing a first classification process on the classified text through a target classification model to obtain a first weight of a security level corresponding to the data object;

[0039] Based on the first large model of the rule set, the prompt text is subjected to a second classification process to obtain a second weight corresponding to the security level of the data object;

[0040] A target security level corresponding to the data object is determined according to the first weight and the second weight.

[0041] In a possible implementation manner, the second determining module is specifically configured to:

[0042] determining a level difference between the first weight and the second weight;

[0043] If the level difference is less than or equal to a preset difference, the first weight and the second weight are fused to obtain a target weight;

[0044] A target security level corresponding to the data object is determined according to the target weight.

[0045] In a possible implementation manner, the analysis and processing module is specifically used to:

[0046] Generating an object description text of the data object according to the object information;

[0047] The object type, the feature information and the object description text are concatenated to obtain a classification text corresponding to the data object.

[0048] In a possible implementation manner, the analysis and processing module is specifically used to:

[0049] Extracting features from the object information to obtain multiple feature words;

[0050] The plurality of characteristic words are analyzed and processed by the second largest model to obtain the object description text.

[0051] In a possible implementation, the text processing module is specifically used to:

[0052] Get the prompt template corresponding to the first largest model;

[0053] The prompt text is determined according to the object type, the feature information and the prompt template.

[0054] In a possible implementation, the text processing module is specifically used to:

[0055] Performing text recognition processing on the prompt template to determine a first replacement field corresponding to the object type and a second replacement field corresponding to the feature information;

[0056] The first replacement field is replaced by the object type, and the second replacement field is replaced by the feature information to obtain the prompt text.

[0057] In a third aspect, an embodiment of the present application provides an electronic device, including: a memory, a processor;

[0058] The memory stores computer-executable instructions;

[0059] 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.

[0060] 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.

[0061] 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.

[0062] The security level determination method, electronic device, storage medium and program product provided in the embodiments of the present application can determine the object type and characteristic information corresponding to the data object, determine the classification text and prompt text based on the object information, object type and characteristic information of the data object, divide the target security level of the data object according to the classification text and prompt text, and distinguish the characteristic information of the data object through the data object, which can improve the accuracy of determining the security level. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] 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.

[0064] Figure 1 A schematic diagram of an application scenario provided by an embodiment of the present application;

[0065] Figure 2 A flowchart of a method for determining a security level provided in an embodiment of the present application;

[0066] Figure 3 A flowchart of another method for determining a security level provided in an embodiment of the present application;

[0067] Figure 4 A schematic diagram of the architecture of a method for determining a security level provided in an embodiment of the present application;

[0068] Figure 5 A schematic diagram of the structure of a device for determining a security level provided in an embodiment of the present application;

[0069] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0070] 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

[0071] 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.

[0072] First, the terms involved in this application are explained:

[0073] Security level: Security level refers to the assessment of the security protection level of information or system. Information or system is usually divided into different security levels according to certain standards and specifications to ensure that appropriate security measures and controls are implemented to protect sensitive data from unauthorized access and attacks.

[0074] Classification model: A classification model is a model in machine learning that is used to classify input data into predefined categories. By learning from the training data, the classification model is able to make predictions about new data based on features.

[0075] Large models: Large models usually refer to machine learning models with a large number of parameters and complex structures, especially in the field of deep learning. These models are trained on massive amounts of data to learn rich features and patterns, and are suitable for tasks such as image recognition and natural language processing. Large models usually perform well when processing complex tasks, but they also require large computing resources and data support.

[0076] Prompted learning: Prompted learning is a machine learning method, especially in the field of natural language processing, that guides large models to produce specific outputs by designing and optimizing "prompts" or "input instructions". It allows users to improve the performance of the model through simplified input styles without comprehensive fine-tuning, so that it can better adapt and perform in a specific task.

[0077] Figure 1 A schematic diagram of an application scenario provided by an embodiment of the present application. Figure 1 , terminal device 101 and server 102. The business system can be installed in the terminal device 101, and the user can select the data object on the interface of the business system through the input device of the terminal device 101, and click the button to generate the target security level corresponding to the data object, and the terminal device 101 can send the object information of the data object to the server. The terminal device 101 can be a mobile phone, a desktop computer, a laptop computer, a wearable terminal, etc.

[0078] The server 102 may receive object information of the data object, and determine the object type and feature information corresponding to the data object according to the object information. The object information, object type and feature information may be analyzed and processed to obtain the classification text corresponding to the data object, and the object type and feature information may be text processed to obtain the prompt text corresponding to the data object. The server 102 may determine the target security level corresponding to the data object according to the classification text and the prompt text.

[0079] In the prior art, the rule engine can analyze, process or make decisions on the input data objects through a predefined set of rules to obtain the security level corresponding to the data objects. The rule engine directly classifies the security level of the data objects according to the object information of the data objects. The same feature fields may appear in different object information, and the differences of the same feature fields in different data objects are ignored, resulting in low accuracy in determining the security level.

[0080] The method for determining the security level provided in the present application can determine the object type and characteristic information corresponding to the data object, determine the classification text and prompt text based on the object information, object type and characteristic information of the data object, divide the target security level of the data object according to the classification text and prompt text, and distinguish the characteristic information of the data object through the data object, thereby improving the accuracy of determining the security level.

[0081] 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.

[0082] Figure 2 A flowchart of a method for determining a security level provided in an embodiment of the present application. Figure 2 , the method may include:

[0083] S201. Receive object information of a data object.

[0084] The execution subject of the embodiment of the present application may be a server, or a security level determination device set in the server. The security level determination device may be implemented by software, or by a combination of software and hardware.

[0085] A data object may be used to indicate an identifier of a data set that is considered to be valuable in an organization or enterprise, and the object information of the data object may be structured metadata.

[0086] Metadata provides information or description about other data, making the organization, search and use of data more efficient. For example, data object information can be the table in which the data object is stored in the database.

[0087] Object information may include the field name, data type, and purpose of the data object.

[0088] S202: Determine the object type and feature information corresponding to the data object according to the object information.

[0089] Object types may include cash objects, current objects, non-current objects, financial objects, physical objects, etc.

[0090] The characteristic information may be used to indicate the specific characteristic content of the data object. For example, assuming that the object type of the data object is a cash object, the characteristic information may be the object balance.

[0091] In some possible embodiments, the field name in the object information may be determined, and the object type of the data object may be determined according to the field name. The object type corresponding to each field name may be stored in a database or other storage.

[0092] S203: Analyze and process the object information, object type and feature information to obtain the classification text corresponding to the data object.

[0093] Classification text can be used to indicate multiple levels of field information of a data object. The classification text can include multiple levels of fields. For example, the first level field of the classification text can be the object type, the second level field can be the object description text, and the third level field can be feature information.

[0094] Building a classified text of multi-layer field information of data objects can improve the accuracy of data object analysis. In addition, as the business changes dynamically, the object description text can be updated in real time to help maintain the timeliness of information and ensure that relevant personnel can obtain the latest business information.

[0095] S204: Perform text processing on the object type and feature information to obtain a prompt text corresponding to the data object.

[0096] The prompt text can be used as input information of the first large model to determine the security level corresponding to the data object.

[0097] The prompt text may be a clear instruction, for example: "Please combine the rule set you have learned, as well as the object type and feature information, to output the security level of the field."

[0098] The first large model may be a large model obtained by prompt learning and training based on a rule set, wherein the rule set may include expert rules, custom rules, and grading specifications, etc.

[0099] S205: Determine the target security level corresponding to the data object according to the classification text and the prompt text.

[0100] The target security level can be used to indicate the security importance of the data object. The higher the target security level, the higher the level of security measures for protecting the data object.

[0101] Specifically, the target security level can be determined in the following way: through the target classification model, the classified text is subjected to a first classification process to obtain a first weight of the security level corresponding to the data object; based on the first large model of the rule set, the prompt text is subjected to a second classification process to obtain a second weight of the security level corresponding to the data object; based on the first weight and the second weight, the target security level corresponding to the data object is determined.

[0102] The target classification model may be obtained by training a preset model through a training set, and the preset model may be a neural network model, a support vector machine, a decision tree, etc.

[0103] The first large model may be a large language model (LLM), which may be a deep learning model trained using a large amount of text data and may be capable of generating natural language text or understanding the meaning of language text.

[0104] The method for determining the security level provided in the embodiment of the present application can determine the object type and characteristic information corresponding to the data object, determine the classification text and prompt text based on the object information, object type and characteristic information of the data object, divide the target security level of the data object according to the classification text and prompt text, and distinguish the characteristic information of the data object through the data object, thereby improving the accuracy of determining the security level.

[0105] Figure 3 A flowchart of another method for determining a security level provided in an embodiment of the present application. Figure 3 , the method may include:

[0106] S301: Receive object information of a data object.

[0107] S302: Determine the object type and feature information corresponding to the data object according to the object information.

[0108] The execution process of S301-S302 can refer to the execution process of S201-S202, which will not be repeated here.

[0109] S303: Generate an object description text of the data object according to the object information.

[0110] The object description text may be used to describe the purpose of the data object. For example, the object description text may be "cash used for working capital".

[0111] In some possible embodiments, feature extraction may be performed on object information to obtain a plurality of feature words; the plurality of feature words may be analyzed and processed by the second largest model to obtain an object description text.

[0112] The second largest model may be an LLM model. A plurality of feature words may be input into the second largest model. The second largest model may generate an object description text of the data object according to the plurality of feature words.

[0113] If the object information of a data object changes, the object description text of the data object will also be dynamically updated, which can ensure the consistency and timeliness of the information and improve the flexibility of determining the target security level.

[0114] Automatically generating object description text reduces the time and cost of manual writing, can quickly respond to changes in business needs, and improve processing efficiency.

[0115] Object information is metadata. Using the metadata of data objects as the input of the second largest model can ensure that the generated object description text is consistent with the actual situation of the data object, reducing the risk of inaccurate information.

[0116] When training the initial LLM model corresponding to the second largest model, an audit mechanism can be established to allow domain experts to evaluate and correct the generated descriptions to ensure that they meet actual needs.

[0117] S304: concatenate the object type, feature information and object description text to obtain the classification text corresponding to the data object.

[0118] The object type, feature information and object description text can be concatenated in a preset order to obtain the classification text corresponding to the data object.

[0119] For example, assuming the preset order is: object type + object description text + characteristic information, assuming the object type is cash type, the characteristic information is cash used for working capital, and the characteristic information is object balance, then the classification text is "cash type + cash used for working capital + object balance".

[0120] S305: Obtain a prompt template corresponding to the first largest model.

[0121] A prompt template can include multiple replacement fields and fixed fields.

[0122] Replacement fields in the prompt template can be replaced with information from the data object.

[0123] S306: Determine the prompt text according to the object type, feature information and prompt template.

[0124] Perform text recognition processing on the prompt template to determine a first replacement field corresponding to the object type and a second replacement field corresponding to the feature information; replace the first replacement field with the object type and replace the second replacement field with the feature information to obtain a prompt text.

[0125] For example, assuming that the prompt module can be "Please combine the rule set you have learned, as well as the first replacement field and the second replacement field, to output the security level of the field", the first replacement field and the second replacement field can be replaced, and the prompt text obtained is "Please combine the rule set you have learned, as well as the object type and feature information, to output the security level of the field."

[0126] S307: Perform a first classification process on the classified text through the target classification model to obtain a first weight of the security level corresponding to the data object.

[0127] In some possible embodiments, the format of the classified text may be converted to obtain the converted classified text, and the converted classified text may be input into a target classification model to obtain a first weight.

[0128] For example, assuming that the classified text is in a text format, the converted classified text is in a coding format, and the coding format may include a binary coding format, a Huffman coding format, a word embedding format, and the like.

[0129] S308. Based on the first large model of the rule set, perform a second classification process on the prompt text to obtain a second weight corresponding to the security level of the data object.

[0130] We can collect and organize relevant data security classification rules such as national standards, industry standards and banking and insurance regulatory standards to form a comprehensive rule set, which can ensure that data security classification decisions follow unified standards and improve the consistency and reliability of decisions. At the same time, embedding the rule set into the first large model will help ensure that data security classification complies with the latest laws, regulations and industry standards, and can reduce compliance risks.

[0131] As standards and regulations change, the No. 1 model can adapt to new requirements by updating the rule set, keeping decisions timely and relevant.

[0132] By means of prompt learning, expert rules are embedded in the first model, enabling it to simulate the expert's decision-making process, making it more professional in data security classification and reducing the risk of relying on manual judgment. At the same time, it reduces the time for manual review and decision-making, improves the efficiency of data processing, and enables enterprises to respond to compliance requirements more quickly.

[0133] S309: Determine a target security level corresponding to the data object according to the first weight and the second weight.

[0134] In some possible embodiments, the level difference between the first weight and the second weight can be determined; if the level difference is less than a preset difference, the first weight and the second weight are fused to obtain a target weight; and based on the target weight, a target security level corresponding to the data object is determined.

[0135] The first weight can be used to describe the weight of the security level corresponding to the data object determined based on machine learning. The second weight can be used to describe the weight of the security level corresponding to the data object determined based on the large model.

[0136] If the level difference between the first weight and the second weight is less than or equal to the preset difference, that is, the difference between the two decision results is small, the first weight and the second weight can be fused to obtain the target weight; if the level difference between the first weight and the second weight is greater than the preset difference, that is, the difference between the two decision results is large, a prompt message can be entered, and the final target safety level can be output after manual verification.

[0137] The target security level corresponding to the target weight may be determined in the following manner: obtaining security levels corresponding to a plurality of weight intervals, determining a target weight interval corresponding to the target weight among the plurality of weight intervals, and determining the security level corresponding to the target weight interval as the target security level.

[0138] For example, assuming there are three weight intervals, namely weight intervals 1-3, each weight interval and the security level corresponding to each weight interval are shown in Table 1. Assuming the target weight is 0.7, the target security level can be determined to be security level 2, among which security level 1 has the lowest security importance and security level 3 has the highest security importance.

[0139] Table 1

[0140]

[0141] Combining the weights of the first model and the target classification model to determine the target safety level can reduce the risk of misjudgment and improve the accuracy of decision-making.

[0142] The method for determining the security level provided in the embodiment of the present application can determine the classification text and prompt text corresponding to the data object, process the classification text through the target classification model to obtain the first weight, process the prompt text through the first large model to obtain the second weight, and if the level difference is less than or equal to the preset difference, the first weight and the second weight can be fused to obtain the target weight; according to the target weight, the target security level corresponding to the data object is determined. Through different decision paths, the model can output richer security levels, which can improve the accuracy of determining the security level.

[0143] Figure 4 This is a schematic diagram of the architecture of a method for determining a security level provided in an embodiment of the present application. Figure 4 After receiving the object information of the data object, the object type and characteristic information corresponding to the data object can be determined according to the object information.

[0144] The second largest model can be used to analyze and process multiple feature words in the object information to obtain the object description text, and the object type, feature information and object description text can be spliced ​​to obtain the classification text corresponding to the data object. The target classification model can be used to perform the first classification on the classification text to obtain the first weight of the security level corresponding to the data object.

[0145] The prompt template corresponding to the first large model can be obtained, and the prompt text can be determined according to the object type, feature information and the prompt template. The prompt text can be subjected to a second classification process based on the first large model of the rule set to obtain a second weight of the security level corresponding to the data object.

[0146] Determine the level difference between the first weight and the second weight; if the level difference is less than or equal to the preset difference, fuse the first weight and the second weight to obtain the target weight; determine the target security level corresponding to the data object according to the target weight.

[0147] Figure 5 This is a schematic diagram of a security level determination device provided in an embodiment of the present application. Figure 5 The security level determination device 10 may include a receiving module 11, a first determination module 12, an analysis and processing module 13, a text processing module 14 and a second determination module 15:

[0148] The receiving module 11 is used to receive object information of a data object;

[0149] The first determination module 12 is used to determine the object type and feature information corresponding to the data object according to the object information;

[0150] The analysis and processing module 13 is used to analyze and process the object information, object type and feature information to obtain the classification text corresponding to the data object;

[0151] The text processing module 14 is used to perform text processing on the object type and feature information to obtain a prompt text corresponding to the data object.

[0152] The second determination module 15 is used to determine the target security level corresponding to the data object according to the classification text and the prompt text.

[0153] The full-level determination device provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and this embodiment will not be described in detail here.

[0154] In a possible implementation manner, the second determining module 15 is specifically configured to:

[0155] Through the target classification model, the classified text is first classified to obtain the first weight of the security level corresponding to the data object;

[0156] Based on the first model of the rule set, the prompt text is subjected to a second classification process to obtain a second weight corresponding to the security level of the data object;

[0157] A target security level corresponding to the data object is determined according to the first weight and the second weight.

[0158] In a possible implementation manner, the second determining module 15 is specifically configured to:

[0159] Determine a difference in rank between the first weight and the second weight;

[0160] If the level difference is less than or equal to the preset difference, the first weight and the second weight are fused to obtain the target weight;

[0161] According to the target weight, determine the target security level corresponding to the data object.

[0162] In a possible implementation manner, the analysis and processing module 13 is specifically used for:

[0163] Generate object description text of data object according to object information;

[0164] The object type, feature information and object description text are concatenated to obtain the classification text corresponding to the data object.

[0165] In a possible implementation manner, the analysis and processing module 13 is specifically used for:

[0166] Extract features from object information to obtain multiple feature words;

[0167] The second largest model is used to analyze and process multiple feature words to obtain object description text.

[0168] In a possible implementation, the text processing module 14 is specifically used for:

[0169] Get the prompt template corresponding to the first largest model;

[0170] Determine the prompt text based on the object type, feature information and prompt template.

[0171] In a possible implementation, the text processing module 14 is specifically used for:

[0172] Performing text recognition processing on the prompt template to determine a first replacement field corresponding to the object type and a second replacement field corresponding to the feature information;

[0173] The object type is replaced in the first replacement field, and the characteristic information is replaced in the second replacement field to obtain the prompt text.

[0174] The full-level determination device provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and this embodiment will not be described in detail here.

[0175] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 6 The electronic device 20 may include a processor 21 and a memory 22. Exemplarily, the processor 21 and the memory 22 are interconnected via a bus 23.

[0176] The memory 22 stores computer executable instructions;

[0177] The processor 21 executes the computer-executable instructions stored in the memory 22, so that the processor 21 executes the method for determining the security level as shown in the above method embodiment.

[0178] Accordingly, 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 method for determining the security level of the above method embodiment.

[0179] Accordingly, an embodiment of the present application may also provide a computer program product, including a computer program, which, when executed by a processor, can implement the method for determining the security level shown in the above method embodiment.

[0180] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0181] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0182] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0183] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0184] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0185] Memory may include non-permanent storage in a computer-readable medium, in the form of random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0186] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0187] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0188] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for determining a security level, characterized in that: include: receiving object information of a data object; Determine, according to the object information, the object type and characteristic information corresponding to the data object; Analyze and process the object information, the object type and the feature information to obtain a classification text corresponding to the data object; Performing text processing on the object type and the characteristic information to obtain a prompt text corresponding to the data object; A target security level corresponding to the data object is determined based on the classification text and the prompt text.

2. The method according to claim 1, characterized in that: Determining a target security level corresponding to the data object according to the classification text and the prompt text includes: Performing a first classification process on the classified text through a target classification model to obtain a first weight of a security level corresponding to the data object; Based on the first large model of the rule set, the prompt text is subjected to a second classification process to obtain a second weight corresponding to the security level of the data object; A target security level corresponding to the data object is determined according to the first weight and the second weight.

3. The method according to claim 2, characterized in that Determining a target security level corresponding to the data object according to the first weight and the second weight includes: determining a level difference between the first weight and the second weight; If the level difference is less than or equal to a preset difference, the first weight and the second weight are fused to obtain a target weight; A target security level corresponding to the data object is determined according to the target weight.

4. The method according to any one of claims 1 to 3, characterized in that: Analyzing and processing the object information, the object type and the feature information to obtain the classification text corresponding to the data object includes: Generating an object description text of the data object according to the object information; The object type, the feature information and the object description text are concatenated to obtain a classification text corresponding to the data object.

5. The method according to claim 4, characterized in that Generating an object description text of the data object according to the object information, including: Extracting features from the object information to obtain multiple feature words; The plurality of characteristic words are analyzed and processed by the second largest model to obtain the object description text.

6. The method according to any one of claims 1 to 5, characterized in that: Performing text processing on the object type and the characteristic information to obtain a prompt text corresponding to the data object includes: Get the prompt template corresponding to the first largest model; The prompt text is determined according to the object type, the feature information and the prompt template.

7. The method according to claim 6, characterized in that Determining the prompt text according to the object type, feature information and prompt template includes: Performing text recognition processing on the prompt template to determine a first replacement field corresponding to the object type and a second replacement field corresponding to the feature information; The first replacement field is replaced by the object type, and the second replacement field is replaced by the feature information to obtain the prompt text.

8. A device for determining a security level, characterized in that: It includes a receiving module, a first determining module, an analyzing and processing module, a text processing module and a second determining module: The receiving module is used to receive object information of a data object; The first determination module is used to determine the object type and feature information corresponding to the data object according to the object information; The analysis and processing module is used to analyze and process the object information, the object type and the feature information to obtain the classification text corresponding to the data object; The text processing module is used to perform text processing on the object type and the feature information to obtain a prompt text corresponding to the data object; The second determination module is used to determine the target security level corresponding to the data object according to the classification text and the prompt text.

9. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 7.

10. 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 7 when executed by a processor.

Images