Method and system for timely identification of computer information security risks

Through facial recognition and account security rules monitoring, the information security of computer equipment during the job handover process is ensured, the information security risks in traditional handover methods are solved, and an automated and efficient handover process is realized.

CN118862174BActive Publication Date: 2024-12-03SICHUAN WATER CONSERVANCY VOCATIONAL & TECH COLLEGE
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411335081.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-24
Publication Date
2024-12-03
Estimated Expiration
2044-09-24

AI Technical Summary

Technical Problem

During the handover of traditional positions, the information security risks of computer equipment are high. Relying on oral notifications and paper records can easily lead to contact or use by unauthorized personnel, resulting in data leakage and untimely change of permissions, increasing information security risks.

Method used

Face recognition technology is used to confirm the identity of the handover person and the handover person during shift handover, and monitor it according to the preset account security usage rules to ensure that only authorized personnel participate in the handover and use of work accounts, and prevent illegal access through sensitive data trap software.

Benefits of technology

The automation and intelligence of shift handover have been realized, the complexity of manual operation and error rate have been reduced, the handover has been ensured that only the correct personnel have completed the handover, the intervention of unauthorized personnel has been reduced, the level of information security has been improved, and potential security threats have been promptly discovered and dealt with.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118862174B_ABST
    Figure CN118862174B_ABST
Patent Text Reader

Abstract

The present application relates to the field of information security technology, and discloses a method and system for timely identifying computer information security risks, the method comprising: collecting image information of a designated shift handover area, and determining a face image in the image information; determining the identity information of a handover person and a handoveree of the current handover shift according to a preset shift handover table, and obtaining the face features of the handover person and the handoveree; performing feature recognition on the face image based on the face features of the handover person and the handoveree; if the designated shift handover area only includes the handover person and the handoveree, then changing the user information of the target position work account logged in in the enterprise computer device from the handover person to the handoveree, and in the process of the handoveree using the target position work account, performing security monitoring on the handoveree's usage information based on the preset account security usage rules; otherwise outputting a shift handover failure prompt message.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of information security technology, and in particular to a method and system for timely identifying computer information security risks. Background Art

[0002] With the rapid development of information technology, enterprises have an increasing demand for computer information security. In the daily operation of enterprises, computer equipment carries a large amount of sensitive information and key business data, and its security is directly related to the stable operation and core competitiveness of the enterprise. Especially in the scenario involving job handover, how to ensure that computer equipment and the work accounts in it are safely and smoothly transferred from one employee to another has become an information security issue that needs to be solved urgently.

[0003] In the traditional job handover process, verbal notification or simple paper records are often used to confirm the identities of both parties and the status of the work handover. This method is not only inefficient, but also prone to security risks. For example, undesignated handover personnel may access or use computer equipment without authorization, resulting in data leakage or misoperation; at the same time, the permission change of work accounts may not be completed in a timely and accurate manner due to human negligence or malicious operations, further exacerbating information security risks.

[0004] In order to overcome the above technical defects and improve the protection level of enterprise computer information security, there is an urgent need for an efficient and intelligent method for timely identification of computer information security risks. Summary of the invention

[0005] In view of this, the embodiments of the present application provide a method and system for timely identifying computer information security risks, which helps to ensure the security of account usage of enterprise computer equipment during and after shift handovers.

[0006] According to one aspect of the present application, a method for timely identifying computer information security risks is provided, which is applied to enterprise computer equipment, and the method includes:

[0007] In response to a shift handover contact signal of a target post, image information of a designated shift handover area is collected, and face recognition is performed on the image information to determine a face image in the image information;

[0008] According to the preset shift handover table, determine the identity information of the handover person and the identity information of the handover person of the current handover shift, and obtain the facial features of the handover person corresponding to the identity information of the handover person and the facial features of the handover person corresponding to the identity information of the handover person;

[0009] Performing feature recognition on the facial image based on the facial features of the handover person and the handover recipient, so as to identify whether the designated shift handover area only includes the handover person and the handover recipient;

[0010] If the designated shift handover area only includes the handover person and the handoveree, the user information of the target position work account logged in in the enterprise computer device is changed from the handover person to the handoveree, and during the handoveree's use of the target position work account, the handoveree's usage information is securely monitored based on the preset account security usage rules;

[0011] Otherwise, a shift handover failure prompt message will be output.

[0012] In an embodiment of the present application, optionally, the preset account security usage rule includes at least one preset sensitive data type, a preset reasonable access frequency and a preset reasonable access duration corresponding to each of the preset sensitive data types, and a preset reasonable total access frequency and a preset reasonable total access duration corresponding to the preset sensitive data type;

[0013] Based on the preset account security usage rules, the user's usage information is monitored securely, including:

[0014] Counting the actual access frequency and actual access duration of the sensitive data corresponding to each preset sensitive data type accessed by the handover person in the enterprise computer device, as well as the actual total access frequency and actual total access duration corresponding to various sensitive data;

[0015] If the actual access frequency of any type of sensitive data exceeds the corresponding preset reasonable access frequency, the actual access duration exceeds the corresponding preset reasonable access duration, the actual total access frequency exceeds the preset reasonable total access frequency, or the actual total access duration exceeds the preset reasonable total access duration, a security warning message will be sent to the alarm terminal corresponding to the enterprise computer equipment.

[0016] In the embodiment of the present application, optionally, after sending the security warning information to the alarm terminal corresponding to the enterprise computer device, the method further includes:

[0017] activating sensitive data trap software in computer equipment of the enterprise;

[0018] The sensitive data trap software monitors operations in the enterprise computer device, and when an access operation to a target sensitive data file corresponding to any preset sensitive data type is monitored, a sensitive data trap file matching the target sensitive data file is opened, wherein the data in the sensitive data trap file is erroneous data generated based on the sensitive data in the target sensitive data file.

[0019] In the embodiment of the present application, optionally, after monitoring the operation in the enterprise computer device through the sensitive data trap software, the method further includes:

[0020] If the authorization information returned by the alarm terminal is received, the sensitive data trap software is closed, and data update prompt information corresponding to the sensitive data trap file is generated according to the sensitive data trap file opened by the sensitive data trap software during the monitoring period, so as to prompt the handover person that the data in the target sensitive data file has been updated;

[0021] If interception information returned by the alarm terminal is received, the operation of the handover person on the enterprise computer device is intercepted, and if the handover person's usage information contains data modification information on the enterprise computer device, data modification rollback is performed based on the data modification information.

[0022] In the embodiment of the present application, optionally, otherwise outputting a shift handover failure prompt message includes:

[0023] If the designated shift handover area does not include the handover person and / or the handover recipient, determining the identity information of the unidentified shift handover personnel;

[0024] If the designated shift handover area contains an irrelevant person who is not a shift handover person, the image information is annotated with information of the irrelevant person based on the face image of the irrelevant person, wherein the shift handover person includes the handover person and the handoveree;

[0025] Outputting shift handover failure prompt information based on the unrecognized shift handover personnel identity information and the labeled image information.

[0026] In the embodiment of the present application, optionally, if the designated shift handover area only includes the handover person and the handoveree, then changing the user information of the target position work account logged in in the enterprise computer device from the handover person to the handoveree includes:

[0027] If the designated shift handover area only includes the handover person and the handover recipient, outputting content handover prompt information to prompt the handover person to hand over the work content to the handover recipient;

[0028] The voice information of the handover person is collected through a sound collecting device, and the voice information is converted into text information. According to the text information and the responsibility information of the target position, a handover file prompt information is constructed, and a large language model is called to generate the handover information of the current shift according to the handover file prompt information. Based on the handover information, a handover file template corresponding to the target position is filled to obtain a target handover file;

[0029] The target handover document is displayed, and based on the confirmation operation of the handover person and the handoveree on the target handover document or the modified target handover document, the user information of the target position work account logged in in the enterprise computer device is changed from the handover person to the handoveree.

[0030] In an embodiment of the present application, optionally, filling in a handover file template corresponding to the target position based on the handover information to obtain a target handover file includes:

[0031] According to the handover document template, determining whether the handover information includes all mandatory items corresponding to the handover document template, wherein the handover document template includes mandatory items and optional items;

[0032] If all required information is included, the handover document template corresponding to the target position is filled in based on the handover information to obtain the target handover document;

[0033] If at least one required item of information is missing, supplementary prompt information of the handover information is generated based on the missing required item, the supplementary prompt information of the handover information is output, and supplementary voice information of the handover person is collected through the sound collecting device, and the supplementary voice information is converted into supplementary text information, and supplementary handover file prompt information is constructed according to the supplementary text information, the missing required item and the responsibility information of the target position, and the large language model is called to generate supplementary handover information for the current shift according to the supplementary handover file prompt information until all required information is obtained, and the handover file template corresponding to the target position is filled in based on the handover information and the supplementary handover information to obtain the target handover file.

[0034] In the embodiment of the present application, optionally, constructing the handover document prompt information according to the text information and the responsibility information of the target position includes:

[0035] Constructing the handover file prompt information according to the text information, the responsibility information of the target position, all the mandatory items corresponding to the handover file target, and the preset first guiding information, wherein the preset first guiding information is used to guide the large language model to identify the handover information related to each of the mandatory items in the text information according to the responsibility information of the target position;

[0036] The supplementary handover document prompt information is constructed according to the supplementary text information, the missing mandatory items and the responsibility information of the target position, including:

[0037] The supplementary handover document prompt information is constructed based on the supplementary text information, the missing required item information, the responsibility information of the target position and the preset second guidance information, wherein the preset second guidance information is used to guide the large language model to identify the supplementary handover information related to each of the missing required items in the supplementary text information according to the responsibility information of the target position.

[0038] In the embodiment of the present application, optionally, the large language model is obtained by:

[0039] Obtaining a general large language model and a training sample set, wherein the training sample set includes a plurality of training samples corresponding to each position in at least one position, and each training sample includes each filling item in a handover text template of the corresponding position, responsibility information of the corresponding position, a text sample, and a filling item information sample corresponding to the text sample;

[0040] Dividing the training sample set into a first training set and a second training set;

[0041] Training the general large language model according to the first training set to obtain an intermediate large language model;

[0042] For each training sample in the second training set, training sample reasoning prompt information is constructed according to each fill-in item in the training sample, the responsibility information of the corresponding position, the text sample and the preset reasoning information, wherein the training sample reasoning prompt information is used to guide the intermediate large language model to identify the prediction handover information related to each of the fill-in items in the text sample according to the responsibility information of the corresponding position, and provide the reasoning basis for each prediction handover information; the intermediate large language model generates the fill-in item prediction information corresponding to the training sample and the reasoning basis corresponding to the fill-in item prediction information according to the training sample reasoning prompt information, determines whether the intermediate large language model correctly infers the text sample according to the fill-in item prediction information and the fill-in item information sample in the training sample, and adjusts the parameters of the intermediate large language model according to the reasoning basis when the reasoning is incorrect, so as to optimize the intermediate large language model to obtain the large language model.

[0043] According to another aspect of the present application, a system for timely identifying computer information security risks is provided, the system comprising:

[0044] An image acquisition module, for collecting image information of a designated shift handover area in response to a shift handover contact signal of a target post, and performing face recognition on the image information to determine a face image in the image information;

[0045] A feature acquisition module is used to determine the identity information of the handover person and the identity information of the handover person of the current handover shift according to the preset shift handover table, and obtain the facial features of the handover person corresponding to the identity information of the handover person and the facial features of the handover person corresponding to the identity information of the handover person;

[0046] A recognition module, used for performing feature recognition on the facial image based on the facial features of the handover person and the handover person, so as to identify whether the designated shift handover area only includes the handover person and the handover person;

[0047] A handover module, for changing the user information of the target position work account logged in in the enterprise computer device from the handover person to the handover person if the designated shift handover area only includes the handover person and the handoveree, and for performing security monitoring on the handoveree's usage information based on preset account security usage rules during the handoveree's use of the target position work account;

[0048] The output module is used to output the prompt information of shift handover failure.

[0049] In the embodiment of the present application, optionally, the output module is further used to:

[0050] If the designated shift handover area does not include the handover person and / or the handover recipient, determining the identity information of the unidentified shift handover personnel;

[0051] If the designated shift handover area contains an irrelevant person who is not a shift handover person, the image information is annotated with information of the irrelevant person based on the face image of the irrelevant person, wherein the shift handover person includes the handover person and the handoveree;

[0052] Outputting shift handover failure prompt information based on the unrecognized shift handover personnel identity information and the labeled image information.

[0053] In the embodiment of the present application, optionally, the handover module is further used to:

[0054] If the designated shift handover area only includes the handover person and the handover recipient, outputting content handover prompt information to prompt the handover person to hand over the work content to the handover recipient;

[0055] The voice information of the handover person is collected through a sound collecting device, and the voice information is converted into text information. According to the text information and the responsibility information of the target position, a handover file prompt information is constructed, and a large language model is called to generate the handover information of the current shift according to the handover file prompt information. Based on the handover information, a handover file template corresponding to the target position is filled to obtain a target handover file;

[0056] The target handover document is displayed, and based on the confirmation operation of the handover person and the handoveree on the target handover document or the modified target handover document, the user information of the target position work account logged in in the enterprise computer device is changed from the handover person to the handoveree.

[0057] In the embodiment of the present application, optionally, the handover module is further used to:

[0058] According to the handover document template, determining whether the handover information includes all mandatory items corresponding to the handover document template, wherein the handover document template includes mandatory items and optional items;

[0059] If all required information is included, the handover document template corresponding to the target position is filled in based on the handover information to obtain the target handover document;

[0060] If at least one required item of information is missing, supplementary prompt information of the handover information is generated based on the missing required item, the supplementary prompt information of the handover information is output, and supplementary voice information of the handover person is collected through the sound collecting device, and the supplementary voice information is converted into supplementary text information, and supplementary handover file prompt information is constructed according to the supplementary text information, the missing required item and the responsibility information of the target position, and the large language model is called to generate supplementary handover information for the current shift according to the supplementary handover file prompt information until all required information is obtained, and the handover file template corresponding to the target position is filled in based on the handover information and the supplementary handover information to obtain the target handover file.

[0061] In the embodiment of the present application, optionally, the handover module is further used to:

[0062] Constructing the handover file prompt information according to the text information, the responsibility information of the target position, all the mandatory items corresponding to the handover file target, and the preset first guiding information, wherein the preset first guiding information is used to guide the large language model to identify the handover information related to each of the mandatory items in the text information according to the responsibility information of the target position;

[0063] The supplementary handover document prompt information is constructed based on the supplementary text information, the missing required item information, the responsibility information of the target position and the preset second guidance information, wherein the preset second guidance information is used to guide the large language model to identify the supplementary handover information related to each of the missing required items in the supplementary text information according to the responsibility information of the target position.

[0064] In the embodiment of the present application, optionally, the large language model is obtained by:

[0065] Obtaining a general large language model and a training sample set, wherein the training sample set includes a plurality of training samples corresponding to each position in at least one position, and each training sample includes each filling item in a handover text template of the corresponding position, responsibility information of the corresponding position, a text sample, and a filling item information sample corresponding to the text sample;

[0066] Dividing the training sample set into a first training set and a second training set;

[0067] Training the general large language model according to the first training set to obtain an intermediate large language model;

[0068] For each training sample in the second training set, training sample reasoning prompt information is constructed according to each fill-in item in the training sample, the responsibility information of the corresponding position, the text sample and the preset reasoning information, wherein the training sample reasoning prompt information is used to guide the intermediate large language model to identify the prediction handover information related to each of the fill-in items in the text sample according to the responsibility information of the corresponding position, and provide the reasoning basis for each prediction handover information; the intermediate large language model generates the fill-in item prediction information corresponding to the training sample and the reasoning basis corresponding to the fill-in item prediction information according to the training sample reasoning prompt information, determines whether the intermediate large language model correctly infers the text sample according to the fill-in item prediction information and the fill-in item information sample in the training sample, and adjusts the parameters of the intermediate large language model according to the reasoning basis when the reasoning is incorrect, so as to optimize the intermediate large language model to obtain the large language model.

[0069] In an embodiment of the present application, optionally, the preset account security usage rule includes at least one preset sensitive data type, a preset reasonable access frequency and a preset reasonable access duration corresponding to each of the preset sensitive data types, and a preset reasonable total access frequency and a preset reasonable total access duration corresponding to the preset sensitive data type;

[0070] The handover module is also used for:

[0071] Counting the actual access frequency and actual access duration of the sensitive data corresponding to each preset sensitive data type accessed by the handover person in the enterprise computer device, as well as the actual total access frequency and actual total access duration corresponding to various sensitive data;

[0072] If the actual access frequency of any type of sensitive data exceeds the corresponding preset reasonable access frequency, the actual access duration exceeds the corresponding preset reasonable access duration, the actual total access frequency exceeds the preset reasonable total access frequency, or the actual total access duration exceeds the preset reasonable total access duration, a security warning message will be sent to the alarm terminal corresponding to the enterprise computer equipment.

[0073] In the embodiment of the present application, optionally, the handover module is further used to:

[0074] activating sensitive data trap software in computer equipment of the enterprise;

[0075] The sensitive data trap software monitors operations in the enterprise computer device, and when an access operation to a target sensitive data file corresponding to any preset sensitive data type is monitored, a sensitive data trap file matching the target sensitive data file is opened, wherein the data in the sensitive data trap file is erroneous data generated based on the sensitive data in the target sensitive data file.

[0076] In the embodiment of the present application, optionally, the handover module is further used to:

[0077] If the authorization information returned by the alarm terminal is received, the sensitive data trap software is closed, and data update prompt information corresponding to the sensitive data trap file is generated according to the sensitive data trap file opened by the sensitive data trap software during the monitoring period, so as to prompt the handover person that the data in the target sensitive data file has been updated;

[0078] If interception information returned by the alarm terminal is received, the operation of the handover person on the enterprise computer device is intercepted, and if the handover person's usage information contains data modification information on the enterprise computer device, data modification rollback is performed based on the data modification information.

[0079] According to another aspect of the present application, a storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the above-mentioned method for timely identifying computer information security risks is implemented.

[0080] According to another aspect of the present application, a computer device is provided, including a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, wherein the processor implements the above-mentioned method for timely identification of computer information security risks when executing the program.

[0081] By means of the above technical scheme, a computer information security risk timely identification method and system provided by the embodiment of the present application proposes a computer information security risk timely identification method, which helps to ensure the security of the account use of enterprise computer equipment during the shift handover process. When the time for shift handover arrives, the system automatically collects image information of the designated shift handover area, and determines the face image in the image through face recognition technology; according to the preset shift handover table, the system determines the identity information of the handover person and the handover person of the current shift, and obtains their facial features; the collected face image is compared with the facial features of the handover person and the handover person to confirm whether the handover area only contains the handover person and the handover person; if it is confirmed that the handover area only contains the handover person and the handover person, the user information of the target position work account logged in in the enterprise computer equipment is automatically changed from the handover person to the handover person, and in the process of the handover person using the account, the system performs security monitoring on the usage according to the preset account security usage rules; if it is not possible to identify only the handover person and the handover person, a shift handover failure prompt message is output. The embodiment of the present application realizes the automation and intelligence of shift handover, reduces the complexity and error rate of manual operation, ensures through face recognition technology that only the correct handover person and the handoveree can complete the handover process, reduces the risk of unauthorized personnel intervention, ensures that only authorized personnel can participate in the handover process and use work accounts, effectively prevents security risks such as data leakage, misoperation and unauthorized access, and further ensures the security of computer information by continuously performing security monitoring during the handoveree's use of corporate computer equipment, which helps to timely discover security risks, thereby significantly improving the company's computer information security level.

[0082] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0083] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0084] Figure 1 A schematic diagram of a process for timely identifying computer information security risks provided by an embodiment of the present application is shown;

[0085] Figure 2 A schematic diagram of a process for timely identifying computer information security risks provided by an embodiment of the present application is shown;

[0086] Figure 3 A schematic diagram of the structure of a computer information security risk timely identification system provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0087] The present application will be described in detail below with reference to the accompanying drawings and in combination with embodiments. It should be noted that the embodiments and features in the embodiments of the present application can be combined with each other without conflict.

[0088] In this embodiment, a method for timely identifying computer information security risks is provided. Figure 1 As shown, the method includes:

[0089] Step 101, in response to a shift handover contact signal of a target post, image information of a designated shift handover area is collected, and face recognition is performed on the image information to determine a face image in the image information.

[0090] Step 102, according to the preset shift handover table, determine the identity information of the handover person and the identity information of the handover recipient of the current handover shift, and obtain the handover person's facial features corresponding to the handover person's identity information and the handover recipient's facial features corresponding to the handover recipient's identity information.

[0091] Step 103 , performing feature recognition on the facial image based on the facial features of the handover person and the handover recipient, so as to identify whether the designated shift handover area only includes the handover person and the handover recipient.

[0092] Step 104: If the designated shift handover area only includes the handover person and the handoveree, the user information of the target position work account logged in in the enterprise computer device is changed from the handover person to the handoveree, and during the handoveree's use of the target position work account, the handoveree's usage information is securely monitored based on preset account security usage rules.

[0093] Step 105: Otherwise, output a prompt message indicating that the shift handover has failed.

[0094] In the above embodiment, first, when the time for shift handover arrives, the system receives the shift handover contact signal, and the camera installed in the designated handover area will automatically turn on to capture the image information in the designated handover area. Then the system will perform face recognition processing on these images and extract the face images therein. Secondly, the system will refer to the preset shift handover table to determine the identity information of the specific personnel who should be handed over in the current handover shift, that is, the identity information of the handover person and the identity information of the handover person, and obtain the face features of these personnel from the database. Through the pre-entered personnel information, it is ensured that the system can accurately identify the correct handover person and the handover person, thereby improving the safety and accuracy of the handover. Then, the face image is compared with the face features of the handover person and the handover person to confirm whether only these two persons are included in the image, so as to ensure that only the correct handover person and the handover person appear in the designated area through feature recognition, eliminating the possibility of interference from other people and improving the safety of the handover. Finally, once it is confirmed that the face image only contains the handover person and the handoveree, the system can automatically change the user information of the work account to the handoveree, transfer the use rights of the work account from the handover person to the handoveree, and conduct security monitoring of the handoveree's use process, thereby realizing the automatic and safe handover of the work account, avoiding untimely or erroneous changes in account permissions due to human negligence or malicious operations. At the same time, continuous security monitoring can timely detect and respond to potential security threats. If the system fails to identify the correct handover person and the handoveree, or if the image contains other unrelated persons, the system will output a prompt message indicating that the shift handover failed. This feedback mechanism ensures that the account transfer will only be carried out under the correct handover conditions, timely detects and prompts the intervention of unauthorized personnel, prevents potential security risks, and ensures the smooth progress of the handover process.

[0095] By applying the technical solution of this embodiment, a method for timely identifying computer information security risks is proposed, which helps to ensure the security of account usage of enterprise computer equipment during shift handover. When the time for shift handover arrives, the system automatically collects image information of the designated shift handover area, and determines the face image in the image through face recognition technology; according to the preset shift handover table, the system determines the identity information of the handover person and the handover person of the current shift, and obtains their facial features; the collected face image is compared with the facial features of the handover person and the handover person to confirm whether the handover area only contains the handover person and the handover person; if it is confirmed that the handover area only contains the handover person and the handover person, the user information of the target position work account logged in in the enterprise computer equipment is automatically changed from the handover person to the handover person, and during the handover person's use of the account, the system performs security monitoring on the usage according to the preset account security usage rules; if it is not possible to identify only the handover person and the handover person, a shift handover failure prompt message is output. The embodiment of the present application realizes the automation and intelligence of shift handover, reduces the complexity and error rate of manual operation, ensures through face recognition technology that only the correct handover person and the handoveree can complete the handover process, reduces the risk of unauthorized personnel intervention, ensures that only authorized personnel can participate in the handover process and use work accounts, effectively prevents security risks such as data leakage, misoperation and unauthorized access, and further ensures the security of computer information by continuously performing security monitoring during the handoveree's use of corporate computer equipment, which helps to timely discover security risks, thereby significantly improving the company's computer information security level.

[0096] In the embodiment of the present application, optionally, step 105 includes:

[0097] If the designated shift handover area does not include the handover person and / or the handover recipient, determining the identity information of the unidentified shift handover personnel;

[0098] If the designated shift handover area contains an irrelevant person who is not a shift handover person, the image information is annotated with information of the irrelevant person based on the face image of the irrelevant person, wherein the shift handover person includes the handover person and the handoveree;

[0099] Outputting shift handover failure prompt information based on the unrecognized shift handover personnel identity information and the labeled image information.

[0100] In this embodiment, when the system detects that the situation in the designated shift handover area is not as expected, the following operations may be performed: If the system finds that the handover area does not contain the handover person and / or the handoveree, that is, at least one party does not appear in the designated shift handover area, the system will determine the identity information of the unidentified shift handover personnel, which helps to quickly locate the problem and understand which employee failed to participate in the handover on time. If there are other unrelated persons in the handover area besides the shift handover personnel, the system will annotate the image information based on the facial images of these unrelated persons. This annotation not only records the existence of unrelated persons, but also includes their identity information (if the system can identify them), providing a basis for subsequent safety analysis and processing; Based on the above-mentioned unidentified shift handover personnel identity information and the annotated image information, a shift handover failure prompt message is output. This prompt message will inform the relevant personnel of the problems that occurred during the handover process, which may be the absence of the handover person or the handoveree, or the intervention of unrelated personnel, thereby prompting the relevant personnel to take timely measures to solve the problem. The above design makes this embodiment more flexible and effective in dealing with complex and changeable handover scenarios. Through automated recognition and labeling functions, the system can quickly identify abnormal situations in the handover process and guide relevant personnel to handle them through clear prompt information, thereby ensuring the security of corporate computer equipment and accounts and improving the efficiency and accuracy of the handover process.

[0101] In the embodiment of the present application, optionally, in step 104, if the designated shift handover area only includes the handover person and the handoveree, the user information of the target position work account logged in in the enterprise computer device is changed from the handover person to the handoveree, including:

[0102] Step 104 - 1 : If the designated shift handover area only includes the handover person and the handover recipient, output content handover prompt information to prompt the handover person to hand over the work content to the handover recipient.

[0103] Step 104-2, collect the voice information of the handover person through the sound collecting device, convert the voice information into text information, construct the handover file prompt information according to the text information and the responsibility information of the target position, call the large language model to generate the handover information of the current shift according to the handover file prompt information, and fill in the handover file template corresponding to the target position based on the handover information to obtain the target handover file.

[0104] Step 104-3, displays the target handover document, and based on the confirmation operation of the handover person and the handoveree on the target handover document or the modified target handover document, changes the user information of the target position work account logged in in the enterprise computer device from the handover person to the handoveree.

[0105] In the above embodiment, when the system confirms that the designated shift handover area only contains the handover person and the handoveree, the content handover prompt information is first output to remind the handover person to start handing over the specific work content to the handoveree, ensuring that the handoveree can fully understand the current work status and pending matters. Then, the voice information of the handover person is collected through a sound collection device (such as a microphone) and converted into text information, and the oral handover content is converted into an editable text form using speech recognition technology. Next, based on the converted text information and the responsibility information of the target position, the handover file prompt information is constructed, and the text generation capability of the large language model (such as GPT, BERT, etc.) is used to generate the handover information of the current shift based on the handover file prompt information, wherein the large language model can understand and generate complex natural language texts, thereby helping to generate a comprehensive and accurate handover file. Further, the generated handover information is filled into the handover file template corresponding to the target position to obtain the target handover file, and the handover file template contains a fixed format, title, paragraph, etc., which is used to standardize the format and content of the handover file. Finally, the generated target handover file is displayed on the screen for the handover person and the handoveree to view. Based on the confirmation operation of the handover person and the handoveree on the target handover file or the modified target handover file (such as clicking the "Confirm" button, signing, etc.), the system determines that the handover work has been completed. After confirming that the handover work is correct, the system changes the user information of the target position work account logged in in the enterprise computer equipment from the handover person to the handoveree, ensuring the smooth handover of the account authority and avoiding the security risks and operational confusion caused by the failure to change the authority in time. Through the above steps, the embodiment of the present application not only realizes the automated handover and recording of work content, but also ensures the timely and accurate change of account authority, thereby improving the efficiency and security of job handover.

[0106] In the embodiment of the present application, optionally, in step 104-2, filling in a handover file template corresponding to the target position based on the handover information to obtain a target handover file includes:

[0107] Step 104-2-1, based on the handover document template, determine whether the handover information contains all mandatory items corresponding to the handover document template, wherein the handover document template includes mandatory items and optional items.

[0108] Step 104-2-2: If all required information items are included, the handover document template corresponding to the target position is filled in based on the handover information to obtain the target handover document.

[0109] Step 104-2-3, if at least one required item is missing, generate supplementary prompt information of the handover information based on the missing required item, output the supplementary prompt information of the handover information, collect supplementary voice information of the handover person through the sound collecting device, convert the supplementary voice information into supplementary text information, construct supplementary handover file prompt information according to the supplementary text information, the missing required item and the responsibility information of the target position, call the large language model to generate supplementary handover information for the current shift according to the supplementary handover file prompt information, until all required information is obtained, fill in the handover file template corresponding to the target position based on the handover information and the supplementary handover information to obtain the target handover file.

[0110] In this embodiment, first, the received handover information is checked for integrity according to the mandatory items and optional items defined in the handover file template. The handover file template is a predefined document structure, which contains the information that must be filled in to complete the handover work (mandatory items) and the information that can be filled in (optional items). If the handover information contains all the mandatory information corresponding to the handover file template, the system will directly fill in the handover file template corresponding to the target position based on these handover information, thereby generating the target handover file. If at least one mandatory item of information is missing in the handover information, the system will take the following steps to supplement this information: based on the missing mandatory items, the system generates supplementary prompt information for the handover information, clearly informing the handover person what information needs to be supplemented, the system outputs the supplementary prompt information for the handover information to the handover person through voice or display, and collects the handover person's supplementary voice information through a sound receiving device (such as a microphone), and converts the collected supplementary voice information into text information for subsequent processing. Next, based on the supplementary text information, the missing mandatory items, and the responsibilities of the target position, the system constructs the supplementary handover file prompt information to ensure that the large language model can fully consider the context and job responsibilities when generating the supplementary handover information. Then, the large language model is called to generate the supplementary handover information for the current shift based on the supplementary handover file prompt information. If all the mandatory information is included after supplementation, the handover file target is filled based on the handover information and the supplementary handover information to obtain the target handover file. Otherwise, the above process is repeated until the handover information contains all the mandatory information corresponding to the handover file template, and then the handover file template corresponding to the target position is filled based on the complete handover information (including the original handover information and the supplementary handover information), and finally the target handover file is generated. In the above manner, the system can ensure that the generated handover file is complete and accurate and meets the responsibilities of the target position. At the same time, the efficiency and convenience of the handover work are improved through the automated voice acquisition, text conversion and information supplementation process.

[0111] In an embodiment of the present application, optionally, constructing the handover file prompt information according to the text information and the responsibility information of the target position includes: constructing the handover file prompt information according to the text information, the responsibility information of the target position, all the mandatory items corresponding to the handover file target, and the preset first guide information, wherein the preset first guide information is used to guide the large language model to identify the handover information related to each of the all mandatory items in the text information according to the responsibility information of the target position. Correspondingly, constructing the supplementary handover file prompt information according to the supplementary text information, the missing mandatory items, and the responsibility information of the target position includes: constructing the supplementary handover file prompt information according to the supplementary text information, the missing mandatory item information, the responsibility information of the target position, and the preset second guide information, wherein the preset second guide information is used to guide the large language model to identify the supplementary handover information related to each of the missing mandatory items in the supplementary text information according to the responsibility information of the target position.

[0112] In this embodiment, the handover file prompt information can be specifically constructed based on the text information, the responsibility information of the target position, all the mandatory items corresponding to the handover file target, and the preset first guide information. All the mandatory items corresponding to the handover file target are a list of items that must be filled in the handover file template to ensure the comprehensiveness and standardization of the handover content. The preset first guide information is used to guide the large language model on how to accurately identify the content related to each mandatory item in the text information according to the job responsibility information. The supplementary handover file prompt information is constructed by supplementing the text information, the missing mandatory items, and the responsibility information of the target position. Supplementary text information: After the handover file is initially constructed, missing or supplementary information may be found, and this part of the information is provided in a new text form. Missing mandatory information: This refers to the list of mandatory items that are not fully covered in the initially constructed handover file. In the above manner, the large language model can assist in completing the tedious handover document preparation work, which not only improves efficiency but also reduces human errors. At the same time, the preset guide information ensures the pertinence and accuracy of information extraction, making the handover file more in line with the actual needs of the position. This intelligent solution is of great significance to improving enterprise management level and employee work efficiency.

[0113] In the embodiment of the present application, optionally, the large language model is obtained by:

[0114] Obtaining a general large language model and a training sample set, wherein the training sample set includes a plurality of training samples corresponding to each position in at least one position, and each training sample includes each filling item in a handover text template of the corresponding position, responsibility information of the corresponding position, a text sample, and a filling item information sample corresponding to the text sample;

[0115] Dividing the training sample set into a first training set and a second training set;

[0116] Training the general large language model according to the first training set to obtain an intermediate large language model;

[0117] For each training sample in the second training set, training sample reasoning prompt information is constructed according to each fill-in item in the training sample, the responsibility information of the corresponding position, the text sample and the preset reasoning information, wherein the training sample reasoning prompt information is used to guide the intermediate large language model to identify the prediction handover information related to each of the fill-in items in the text sample according to the responsibility information of the corresponding position, and provide the reasoning basis for each prediction handover information; the intermediate large language model generates the fill-in item prediction information corresponding to the training sample and the reasoning basis corresponding to the fill-in item prediction information according to the training sample reasoning prompt information, determines whether the intermediate large language model correctly infers the text sample according to the fill-in item prediction information and the fill-in item information sample in the training sample, and adjusts the parameters of the intermediate large language model according to the reasoning basis when the reasoning is incorrect, so as to optimize the intermediate large language model to obtain the large language model.

[0118] In the above embodiment, a general large language model and a training sample set are obtained. The general large language model can be a model that has been pre-trained on large-scale text data and has extensive language understanding and generation capabilities. The training sample set is specially designed for the task of extracting work handover information, and contains handover text templates for multiple positions (at least one), responsibilities information of the corresponding positions, text samples, and fill-in information samples corresponding to these text samples. These samples should cover as many possible handover scenarios and fill-in items as possible to ensure the generalization ability of the model. The training sample set is divided into a first training set and a second training set, so that the general large language model can be preliminarily trained using the first training set, and then the second training set is used for enhanced training. Preliminary training: Use the first training set to preliminarily train the general large language model to obtain an intermediate large language model. This step is mainly to allow the model to have a basic understanding and perception of the handover text and job responsibilities. Strengthen training: For each training sample in the second training set, construct training sample reasoning prompt information. This information not only includes the filling items, job responsibility information and text samples, but also adds preset reasoning information to guide the intermediate large language model to not only predict the correct handover information during the reasoning process, but also provide reasoning basis. In addition, the responsibility information of a certain position, the text sample corresponding to the position, the handover information corresponding to the text sample, the filling items of the position and the example of reasoning basis can be added to the training sample reasoning prompt information for reference by the model. The reasoning basis can be based on what content in the text sample the handover information corresponding to each filling item is derived. The intermediate large language model generates the filling item prediction information and its reasoning basis according to the training sample reasoning prompt information. Then, these prediction information are compared with the real filling item information samples in the training samples to evaluate the reasoning correctness of the model. If the reasoning is incorrect, adjust the parameters of the intermediate large language model according to the reasoning basis. This process is iterative. By continuously optimizing the parameters of the model, it can more accurately identify the handover information related to the filling items from the text samples. After multiple iterative training, the intermediate large language model is gradually optimized into a large language model that can efficiently handle the task of extracting work handover information. This model can not only predict the correct handover information, but also provide a basis for reasoning, increasing its interpretability and reliability. The resulting large language model can be deployed in actual work scenarios to assist employees in completing the preparation of handover documents, thereby reducing the workload of manual input and review and improving handover efficiency and accuracy.

[0119] Further, as a refinement and expansion of step 104 of the above embodiment, in order to fully illustrate the specific implementation process of this embodiment, another method for timely identification of computer information security risks is provided, which aims to monitor and prevent illegal or abnormal access to sensitive data through preset account security usage rules, and take corresponding protective measures when potential risks are discovered. Among them, the preset account security usage rules include at least one preset sensitive data type, a preset reasonable access frequency and a preset reasonable access duration corresponding to each of the preset sensitive data types, and a preset reasonable access total frequency and a preset reasonable access total duration corresponding to the preset sensitive data type, such as Figure 2 As shown, the method includes:

[0120] Step 201, counting the actual access frequency and actual access duration of the sensitive data corresponding to each preset sensitive data type accessed by the handover person in the enterprise computer device, as well as the actual total access frequency and actual total access duration corresponding to various sensitive data.

[0121] Step 202: If the actual access frequency of any type of sensitive data exceeds the corresponding preset reasonable access frequency, the actual access duration exceeds the corresponding preset reasonable access duration, the actual total access frequency exceeds the preset reasonable total access frequency, or the actual total access duration exceeds the preset reasonable total access duration, a security warning message is sent to the alarm terminal corresponding to the enterprise computer equipment.

[0122] Step 203, start the sensitive data trap software in the enterprise computer device.

[0123] Step 204: monitor the operations in the enterprise computer device through the sensitive data trap software, and when an access operation to a target sensitive data file corresponding to any preset sensitive data type is monitored, open a sensitive data trap file matching the target sensitive data file, wherein the data in the sensitive data trap file is erroneous data generated based on the sensitive data in the target sensitive data file.

[0124] Step 205: If the authorization information returned by the alarm terminal is received, the sensitive data trap software is closed, and data update prompt information corresponding to the sensitive data trap file is generated according to the sensitive data trap file opened by the sensitive data trap software during the monitoring period, so as to prompt the handover person that the data in the target sensitive data file has been updated.

[0125] Step 206: If the interception information returned by the alarm terminal is received, the operation of the handover person on the enterprise computer device is intercepted, and if the handover person's usage information contains data modification information on the enterprise computer device, data modification rollback is performed based on the data modification information.

[0126] In this embodiment, first, the system needs to count the actual access frequency and duration of the handover person accessing various preset sensitive data types in the enterprise computer equipment, as well as the total access frequency and total duration of these sensitive data. This step is the basis of risk assessment. By comparing the actual data with the preset rules, it can be preliminarily determined whether there is abnormal behavior. If the statistical results show that the access frequency, duration or total frequency and total duration of any sensitive data exceeds the preset reasonable range, the system will automatically send a security warning message to the alarm terminal corresponding to the enterprise computer equipment, and promptly notify the relevant personnel so that they can take further investigation or protective measures. In addition, after discovering potential risks, the system will start the sensitive data trap software, which is an important protection tool for taking specific protective measures when detecting access to sensitive data. Specifically, the sensitive data trap software will monitor the operations in the enterprise computer equipment, especially the access operations for the preset sensitive data types. Once the access to the target sensitive data file is detected, the software will open the sensitive data trap file matching the file. The data in the sensitive data trap file is erroneous data generated based on the sensitive data in the target sensitive data file, and is used to mislead illegal visitors. The data in the sensitive data trap file may have the same or similar format as the data in the target sensitive data file, but the actual data is different.

[0127] Furthermore, if the alarm terminal returns authorization information, it means that the access is confirmed to be legal after investigation or other security measures have been taken. At this time, the sensitive data trap software will be closed, and a data update prompt will be generated based on the trap file opened during the monitoring period to notify the handover person that the data in the target sensitive data file has been updated. If the alarm terminal returns interception information, it means that the access is considered illegal or there is a security risk. The system will intercept the handover person's further operations in the enterprise computer equipment. If the handover person's usage information contains data modifications during the interception, the system will roll back the data modification based on these modification information to restore the data to the state before the modification to prevent data leakage or damage.

[0128] By applying the technical solution of this embodiment, by presetting account security usage rules, and real-time monitoring and statistics of sensitive data access, it is possible to timely discover and prevent potential illegal or abnormal access, thereby significantly enhancing the security of sensitive data in enterprise computer equipment. Once it is detected that the access frequency and duration of sensitive data exceed the preset reasonable range, the system will immediately send a security warning message to the alarm terminal to ensure that relevant personnel can quickly receive notifications and take corresponding treatment measures, shortening the risk response time. By using sensitive data trap software, intelligent data protection is realized. Through the setting of trap files, potential illegal access can be trapped and recorded without interfering with normal access, providing strong support for subsequent investigation and processing. According to the authorization information or interception information returned by the alarm terminal, the processing strategy can be flexibly adjusted. For legal access, data update prompts are provided to maintain user experience; for illegal access, interception and data rollback are performed to prevent data leakage or damage. Through automated monitoring, warning and protection processes, the workload of manual monitoring can be greatly reduced and work efficiency can be improved. At the same time, through timely data update prompts and interception processing, subsequent correction work caused by data errors or leakage is also avoided.

[0129] Further, as Figure 1 The specific implementation of the method, the embodiment of the present application provides a computer information security risk timely identification system, such as Figure 3 As shown, the system includes:

[0130] An image acquisition module, for collecting image information of a designated shift handover area in response to a shift handover contact signal of a target post, and performing face recognition on the image information to determine a face image in the image information;

[0131] A feature acquisition module is used to determine the identity information of the handover person and the identity information of the handover person of the current handover shift according to the preset shift handover table, and obtain the facial features of the handover person corresponding to the identity information of the handover person and the facial features of the handover person corresponding to the identity information of the handover person;

[0132] A recognition module, used for performing feature recognition on the facial image based on the facial features of the handover person and the handover person, so as to identify whether the designated shift handover area only includes the handover person and the handover person;

[0133] A handover module, for changing the user information of the target position work account logged in in the enterprise computer device from the handover person to the handover person if the designated shift handover area only includes the handover person and the handoveree, and for performing security monitoring on the handoveree's usage information based on preset account security usage rules during the handoveree's use of the target position work account;

[0134] The output module is used to output the prompt information of shift handover failure.

[0135] In the embodiment of the present application, optionally, the output module is further used to:

[0136] If the designated shift handover area does not include the handover person and / or the handover recipient, determining the identity information of the unidentified shift handover personnel;

[0137] If the designated shift handover area contains an irrelevant person who is not a shift handover person, the image information is annotated with information of the irrelevant person based on the face image of the irrelevant person, wherein the shift handover person includes the handover person and the handoveree;

[0138] Outputting shift handover failure prompt information based on the unrecognized shift handover personnel identity information and the labeled image information.

[0139] In the embodiment of the present application, optionally, the handover module is further used to:

[0140] If the designated shift handover area only includes the handover person and the handover recipient, outputting content handover prompt information to prompt the handover person to hand over the work content to the handover recipient;

[0141] The voice information of the handover person is collected through a sound collecting device, and the voice information is converted into text information. According to the text information and the responsibility information of the target position, a handover file prompt information is constructed, and a large language model is called to generate the handover information of the current shift according to the handover file prompt information. Based on the handover information, a handover file template corresponding to the target position is filled to obtain a target handover file;

[0142] The target handover document is displayed, and based on the confirmation operation of the handover person and the handoveree on the target handover document or the modified target handover document, the user information of the target position work account logged in in the enterprise computer device is changed from the handover person to the handoveree.

[0143] In the embodiment of the present application, optionally, the handover module is further used to:

[0144] According to the handover document template, determining whether the handover information includes all mandatory items corresponding to the handover document template, wherein the handover document template includes mandatory items and optional items;

[0145] If all required information is included, the handover document template corresponding to the target position is filled in based on the handover information to obtain the target handover document;

[0146] If at least one required item of information is missing, supplementary prompt information of the handover information is generated based on the missing required item, the supplementary prompt information of the handover information is output, and supplementary voice information of the handover person is collected through the sound collecting device, and the supplementary voice information is converted into supplementary text information, and supplementary handover file prompt information is constructed according to the supplementary text information, the missing required item and the responsibility information of the target position, and the large language model is called to generate supplementary handover information for the current shift according to the supplementary handover file prompt information until all required information is obtained, and the handover file template corresponding to the target position is filled in based on the handover information and the supplementary handover information to obtain the target handover file.

[0147] In the embodiment of the present application, optionally, the handover module is further used to:

[0148] Constructing the handover file prompt information according to the text information, the responsibility information of the target position, all the mandatory items corresponding to the handover file target, and the preset first guiding information, wherein the preset first guiding information is used to guide the large language model to identify the handover information related to each of the mandatory items in the text information according to the responsibility information of the target position;

[0149] The supplementary handover document prompt information is constructed based on the supplementary text information, the missing required item information, the responsibility information of the target position and the preset second guidance information, wherein the preset second guidance information is used to guide the large language model to identify the supplementary handover information related to each of the missing required items in the supplementary text information according to the responsibility information of the target position.

[0150] In the embodiment of the present application, optionally, the large language model is obtained by:

[0151] Obtaining a general large language model and a training sample set, wherein the training sample set includes a plurality of training samples corresponding to each position in at least one position, and each training sample includes each filling item in a handover text template of the corresponding position, responsibility information of the corresponding position, a text sample, and a filling item information sample corresponding to the text sample;

[0152] Dividing the training sample set into a first training set and a second training set;

[0153] Training the general large language model according to the first training set to obtain an intermediate large language model;

[0154] For each training sample in the second training set, training sample reasoning prompt information is constructed according to each fill-in item in the training sample, the responsibility information of the corresponding position, the text sample and the preset reasoning information, wherein the training sample reasoning prompt information is used to guide the intermediate large language model to identify the prediction handover information related to each of the fill-in items in the text sample according to the responsibility information of the corresponding position, and provide the reasoning basis for each prediction handover information; the intermediate large language model generates the fill-in item prediction information corresponding to the training sample and the reasoning basis corresponding to the fill-in item prediction information according to the training sample reasoning prompt information, determines whether the intermediate large language model correctly infers the text sample according to the fill-in item prediction information and the fill-in item information sample in the training sample, and adjusts the parameters of the intermediate large language model according to the reasoning basis when the reasoning is incorrect, so as to optimize the intermediate large language model to obtain the large language model.

[0155] In an embodiment of the present application, optionally, the preset account security usage rule includes at least one preset sensitive data type, a preset reasonable access frequency and a preset reasonable access duration corresponding to each of the preset sensitive data types, and a preset reasonable total access frequency and a preset reasonable total access duration corresponding to the preset sensitive data type;

[0156] The handover module is also used to: count the actual access frequency and actual access duration of the sensitive data corresponding to each preset sensitive data type in the enterprise computer device by the handoveree, as well as the actual total access frequency and actual total access duration corresponding to various sensitive data; if the actual access frequency of any sensitive data exceeds the corresponding preset reasonable access frequency, the actual access duration exceeds the corresponding preset reasonable access duration, the actual total access frequency exceeds the preset reasonable total access frequency, or the actual total access duration exceeds the preset reasonable total access duration, a security warning message is sent to the alarm terminal corresponding to the enterprise computer device.

[0157] In an embodiment of the present application, optionally, the handover module is also used to: start the sensitive data trap software in the enterprise computer device; monitor the operations in the enterprise computer device through the sensitive data trap software, and when an access operation to a target sensitive data file corresponding to any preset sensitive data type is monitored, open a sensitive data trap file that matches the target sensitive data file, wherein the data in the sensitive data trap file is erroneous data generated based on the sensitive data in the target sensitive data file.

[0158] In the embodiment of the present application, optionally, the handover module is further used to:

[0159] If the authorization information returned by the alarm terminal is received, the sensitive data trap software is closed, and data update prompt information corresponding to the sensitive data trap file is generated according to the sensitive data trap file opened by the sensitive data trap software during the monitoring period, so as to prompt the handover person that the data in the target sensitive data file has been updated;

[0160] If interception information returned by the alarm terminal is received, the operation of the handover person on the enterprise computer device is intercepted, and if the handover person's usage information contains data modification information on the enterprise computer device, data modification rollback is performed based on the data modification information.

[0161] It should be noted that for other corresponding descriptions of the functional units involved in the computer information security risk timely identification system provided in the embodiment of the present application, reference can be made to Figure 1 to Figure 2 The corresponding description in the method will not be repeated here.

[0162] The embodiment of the present application also provides a computer device, which can be a personal computer, a server, a network device, etc. The computer device includes a bus, a processor, a memory and a communication interface, and can also include an input and output interface and a display device. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store location information. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the steps in each method embodiment are implemented.

[0163] Those skilled in the art will appreciate that the structure of the above-mentioned computer device is only a partial structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components, or combine certain components, or have a different arrangement of components.

[0164] In one embodiment, a computer-readable storage medium is provided. The computer-readable storage medium may be non-volatile or volatile, and stores a computer program thereon. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0165] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0166] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0167] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0168] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0169] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for timely identifying computer information security risks, characterized in that: Applied to enterprise computer equipment, the method comprises: In response to a shift handover contact signal of a target post, image information of a designated shift handover area is collected, and face recognition is performed on the image information to determine a face image in the image information; According to the preset shift handover table, determine the identity information of the handover person and the identity information of the handover person of the current handover shift, and obtain the facial features of the handover person corresponding to the identity information of the handover person and the facial features of the handover person corresponding to the identity information of the handover person; Performing feature recognition on the facial image based on the facial features of the handover person and the handover recipient, so as to identify whether the designated shift handover area only includes the handover person and the handover recipient; If the designated shift handover area only includes the handover person and the handoveree, the user information of the target position work account logged in in the enterprise computer device is changed from the handover person to the handoveree, and during the handoveree's use of the target position work account, the handoveree's usage information is securely monitored based on the preset account security usage rules; Otherwise, a shift handover failure prompt message is output, including: if the designated shift handover area does not include the handover person and / or the handoveree, the identity information of the unidentified shift handover personnel is determined; if the designated shift handover area includes an irrelevant person who is not a shift handover personnel, the image information is annotated with the irrelevant person information based on the face image of the irrelevant person, wherein the shift handover personnel include the handover person and the handoveree; according to the identity information of the unidentified shift handover personnel and the annotated image information, a shift handover failure prompt message is output; The security monitoring of the user's usage information based on the preset account security usage rules includes: When the usage information of the handover person does not meet the preset account security usage rules, a security warning message is sent to the alarm terminal corresponding to the enterprise computer device, and the sensitive data trap software in the enterprise computer device is started; the operation in the enterprise computer device is monitored by the sensitive data trap software, and when an access operation to a target sensitive data file corresponding to any preset sensitive data type is monitored, a sensitive data trap file matching the target sensitive data file is opened, wherein the data in the sensitive data trap file is error data generated based on the sensitive data in the target sensitive data file; If the authorization information returned by the alarm terminal is received, the sensitive data trap software is closed, and data update prompt information corresponding to the sensitive data trap file is generated according to the sensitive data trap file opened by the sensitive data trap software during the monitoring period, so as to prompt the handover person that the data in the target sensitive data file has been updated; If interception information returned by the alarm terminal is received, the operation of the handover person on the enterprise computer device is intercepted, and if the handover person's usage information contains data modification information on the enterprise computer device, data modification rollback is performed based on the data modification information.

2. The method for timely identifying computer information security risks according to claim 1, characterized in that: The preset account security usage rules include at least one preset sensitive data type, a preset reasonable access frequency and a preset reasonable access duration corresponding to each of the preset sensitive data types, and a preset reasonable total access frequency and a preset reasonable total access duration corresponding to the preset sensitive data types; Based on the preset account security usage rules, the user's usage information is monitored securely, including: Counting the actual access frequency and actual access duration of the sensitive data corresponding to each preset sensitive data type accessed by the handover person in the enterprise computer device, as well as the actual total access frequency and actual total access duration corresponding to various sensitive data; If the actual access frequency of any type of sensitive data exceeds the corresponding preset reasonable access frequency, the actual access duration exceeds the corresponding preset reasonable access duration, the actual total access frequency exceeds the preset reasonable total access frequency, or the actual total access duration exceeds the preset reasonable total access duration, a security warning message will be sent to the alarm terminal corresponding to the enterprise computer equipment.

3. The method for timely identifying computer information security risks according to claim 1 or 2, characterized in that: If the designated shift handover area only includes the handover person and the handoveree, the user information of the target position work account logged in in the enterprise computer device is changed from the handover person to the handoveree, including: If the designated shift handover area only includes the handover person and the handover recipient, outputting content handover prompt information to prompt the handover person to hand over the work content to the handover recipient; The voice information of the handover person is collected through a sound collecting device, and the voice information is converted into text information. According to the text information and the responsibility information of the target position, a handover file prompt information is constructed, and a large language model is called to generate the handover information of the current shift according to the handover file prompt information. Based on the handover information, a handover file template corresponding to the target position is filled to obtain a target handover file; The target handover document is displayed, and based on the confirmation operation of the handover person and the handoveree on the target handover document or the modified target handover document, the user information of the target position work account logged in in the enterprise computer device is changed from the handover person to the handoveree.

4. The method for timely identifying computer information security risks according to claim 3, characterized in that: Filling the handover document template corresponding to the target position based on the handover information to obtain the target handover document includes: According to the handover document template, determining whether the handover information includes all mandatory items corresponding to the handover document template, wherein the handover document template includes mandatory items and optional items; If all required information is included, the handover document template corresponding to the target position is filled in based on the handover information to obtain the target handover document; If at least one required item of information is missing, supplementary prompt information of the handover information is generated based on the missing required item, the supplementary prompt information of the handover information is output, and supplementary voice information of the handover person is collected through the sound collecting device, and the supplementary voice information is converted into supplementary text information, and supplementary handover file prompt information is constructed according to the supplementary text information, the missing required item and the responsibility information of the target position, and the large language model is called to generate supplementary handover information for the current shift according to the supplementary handover file prompt information until all required information is obtained, and the handover file template corresponding to the target position is filled in based on the handover information and the supplementary handover information to obtain the target handover file.

5. The method for timely identifying computer information security risks according to claim 4, characterized in that: Constructing handover document prompt information according to the text information and the responsibility information of the target position, including: Constructing the handover file prompt information according to the text information, the responsibility information of the target position, all the mandatory items corresponding to the handover file target, and the preset first guiding information, wherein the preset first guiding information is used to guide the large language model to identify the handover information related to each of the mandatory items in the text information according to the responsibility information of the target position; The supplementary handover document prompt information is constructed according to the supplementary text information, the missing mandatory items and the responsibility information of the target position, including: The supplementary handover document prompt information is constructed based on the supplementary text information, the missing required item information, the responsibility information of the target position and the preset second guidance information, wherein the preset second guidance information is used to guide the large language model to identify the supplementary handover information related to each of the missing required items in the supplementary text information according to the responsibility information of the target position.

6. The method for timely identifying computer information security risks according to claim 4, characterized in that: The large language model is obtained in the following way: Obtaining a general large language model and a training sample set, wherein the training sample set includes a plurality of training samples corresponding to each position in at least one position, and each training sample includes each filling item in a handover text template of the corresponding position, responsibility information of the corresponding position, a text sample, and a filling item information sample corresponding to the text sample; Dividing the training sample set into a first training set and a second training set; Training the general large language model according to the first training set to obtain an intermediate large language model; For each training sample in the second training set, training sample reasoning prompt information is constructed according to each fill-in item in the training sample, the responsibility information of the corresponding position, the text sample and the preset reasoning information, wherein the training sample reasoning prompt information is used to guide the intermediate large language model to identify the prediction handover information related to each of the fill-in items in the text sample according to the responsibility information of the corresponding position, and provide the reasoning basis for each prediction handover information; the intermediate large language model generates the fill-in item prediction information corresponding to the training sample and the reasoning basis corresponding to the fill-in item prediction information according to the training sample reasoning prompt information, determines whether the intermediate large language model correctly infers the text sample according to the fill-in item prediction information and the fill-in item information sample in the training sample, and adjusts the parameters of the intermediate large language model according to the reasoning basis when the reasoning is incorrect, so as to optimize the intermediate large language model to obtain the large language model.

7. A computer information security risk timely identification system, characterized in that: The system comprises: An image acquisition module, for collecting image information of a designated shift handover area in response to a shift handover contact signal of a target post, and performing face recognition on the image information to determine a face image in the image information; A feature acquisition module is used to determine the identity information of the handover person and the identity information of the handover person of the current handover shift according to the preset shift handover table, and obtain the facial features of the handover person corresponding to the identity information of the handover person and the facial features of the handover person corresponding to the identity information of the handover person; A recognition module, used for performing feature recognition on the facial image based on the facial features of the handover person and the handover person, so as to identify whether the designated shift handover area only includes the handover person and the handover person; A handover module, for changing the user information of the target position work account logged in in the enterprise computer device from the handover person to the handover person if the designated shift handover area only includes the handover person and the handoveree, and for performing security monitoring on the handoveree's usage information based on preset account security usage rules during the handoveree's use of the target position work account; Output module, used to output the prompt message of shift handover failure; The handover module is also used for: When the usage information of the handover person does not meet the preset account security usage rules, a security warning message is sent to the alarm terminal corresponding to the enterprise computer device, and the sensitive data trap software in the enterprise computer device is started; the operation in the enterprise computer device is monitored by the sensitive data trap software, and when an access operation to a target sensitive data file corresponding to any preset sensitive data type is monitored, a sensitive data trap file matching the target sensitive data file is opened, wherein the data in the sensitive data trap file is error data generated based on the sensitive data in the target sensitive data file; If the authorization information returned by the alarm terminal is received, the sensitive data trap software is closed, and data update prompt information corresponding to the sensitive data trap file is generated according to the sensitive data trap file opened by the sensitive data trap software during the monitoring period, so as to prompt the handover person that the data in the target sensitive data file has been updated; If interception information returned by the alarm terminal is received, the operation of the handover person on the enterprise computer device is intercepted, and if the handover person's usage information contains data modification information on the enterprise computer device, data modification rollback is performed based on the data modification information; The output module is further used for: if the designated shift handover area does not include the handover person and / or the handover recipient, determining the identity information of the unidentified shift handover personnel; if the designated shift handover area includes an unrelated person who is not a shift handover personnel, annotating the image information with the unrelated person information based on the facial image of the unrelated person, wherein the shift handover personnel include the handover person and the handover recipient; and outputting a shift handover failure prompt message based on the unidentified shift handover personnel identity information and the annotated image information.