A smart conference system

Abstract

The present invention discloses a smart conference system, which relates to the field of data encryption and is used to solve the problem that in a scenario of frequent modification and multi-person collaboration, there are traces of simultaneous modification or supplementation of document content by multiple people, which will lead to inconsistent keys or version conflicts, and the document is inaccessible or lost. File feature information and conference feature information are collected, a data analysis model is established, a merging evaluation coefficient is obtained, and the difference of each merging evaluation coefficient is obtained, and trend analysis and calculation are performed to obtain the overall trend of the document key, and the difference is compared with a merging threshold to obtain a comparison result, and the merging degree of the document key is limited based on the comparison result, and based on the limited result, a key security prediction analysis is performed through a time series model to obtain security performance data, and a key merging scheme is dynamically adjusted to avoid key conflicts and data loss, so as to ensure the long-term security of document data.

Description

Technical Field

[0001] The present invention relates to the field of data encryption, and more specifically, to a smart conference system. Background Art

[0002] Traditional conference systems usually use paper materials to transmit and record information, which is not only inefficient but also prone to information leakage. Existing electronic conference systems have gradually achieved paperless, and in terms of information security and encryption, strict security measures need to be taken to ensure the confidentiality and integrity of conference information.

[0003] The prior art has the following deficiencies:

[0004] At present, in the field of data encryption, document encryption methods used in electronic conference systems usually use symmetric encryption algorithms or asymmetric encryption algorithms. However, this method does not take into account the authority of conference participants. With the development of technology, the system has built-in document review permissions to further enhance the security of documents. However, meetings are in scenarios where there are frequent modifications and multi-person collaboration. There are traces of multiple people modifying or supplementing the document content at the same time, which will lead to inconsistent keys or version conflicts, resulting in the risk of inaccessibility or loss of documents. Therefore, a smart conference system is proposed.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0006] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a smart conference system, which solves the problems raised in the above-mentioned background technology by using different product inspection methods.

[0007] To achieve the above object, the present invention provides the following technical solution: a smart conference system, including a data acquisition module, a data processing module, a merging analysis module and a security prediction module; the modules are connected by signals;

[0008] The data collection module is used to collect file feature information and meeting feature information, obtain the file history modification frequency, the proportion of unmodifiable content, the history modification frequency of authorized personnel, and the history modification content length of authorized personnel through data processing, and send the file feature information and meeting feature information to the data processing module;

[0009] The data processing module is used to receive the file feature information and the meeting feature information, establish a data analysis model, obtain the combined evaluation coefficient, and send the combined evaluation coefficient to the combined analysis module;

[0010] The merge analysis module is used to obtain the merge evaluation coefficient of each time period, and compare and calculate the merge evaluation coefficients of each time period to obtain the difference of each merge evaluation coefficient, perform trend analysis and calculation on the difference of each merge evaluation coefficient to obtain the overall trend of the document key, and compare the overall trend of the document key with the merge threshold to obtain the comparison result, and limit the degree of merging of the document key this time according to the comparison result, and send the limit result to the security prediction module;

[0011] The security prediction module is used to receive the qualification results, detect, evaluate and collect the document editing status in real time, and perform key security prediction analysis on the qualification results through a time series model to further refine and optimize the key merging solution.

[0012] In a preferred embodiment, the file characteristic information includes the file historical modification frequency and the proportion of unmodifiable content, and the meeting characteristic information includes the historical modification frequency of authorized personnel and the length of historical modification content of authorized personnel;

[0013] The data processing includes:

[0014] By defining a time period, collecting and counting all modification records of the document within the time period, the file history modification frequency is obtained by the ratio of the number of modifications in the modification record to the time period. ; Where i is the i-th time period; the i-th time period corresponds to the i-th meeting;

[0015] Based on the set document content, after the system automatically counts the size of the unmodifiable portion of the document, the ratio of the unmodifiable portion size to the total document size is calculated to obtain the unmodifiable content ratio. ;

[0016] The system automatically identifies the current meeting participants and their permissions, determines whether the meeting participants have the permission to modify the document, collects the sum of the modification records of the document by the participants within the permission of the current meeting, and compares it with the corresponding time period to obtain the historical modification frequency of the personnel within the permission. ;

[0017] By collecting the current meeting participants and their modification records, the accumulated historical modification length of the current meeting participants is calculated, and the accumulated modification length of all participants within the authority is added up to obtain the historical modification length of the personnel within the authority. .

[0018] In a preferred embodiment, the file feature information and the meeting feature information are obtained, a data analysis model is established, and a combined evaluation coefficient is generated. , the specific formula is:

[0019]

[0020] In the formula, is the combined evaluation coefficient, , , as well as The preset ratio coefficients are the file's historical modification frequency, the proportion of unmodifiable content, the historical modification frequency of authorized personnel, and the length of historical modification content of authorized personnel, and , , as well as Both are greater than 0.

[0021] In a preferred embodiment, the combined evaluation coefficient of each time period is obtained. , and compare and calculate the combined evaluation coefficients of each time period. The operation logic is: , and obtain the difference of each combined evaluation coefficient , where g is the g-th comparison;

[0022] The difference of the combined evaluation coefficient greater than 0 is defined as a combined upward trend, and the difference of the combined evaluation coefficient less than 0 is defined as a combined downward trend.

[0023] In a preferred embodiment, the differences of the combined evaluation coefficients are added together, and the operation logic is as follows: , get the overall trend of document keys and compare it with the merge threshold;

[0024] If the total trend of the document key is greater than or equal to the merge threshold, the key attributes of the document in the current meeting are merged into the preset first range as the document key, and a security signal is generated;

[0025] If the overall trend of the document key is less than the merge threshold, the key attributes of the document in the current meeting are merged into the preset second range as the document key, and a modification signal is generated.

[0026] In a preferred embodiment, the limiting result includes a document key for generating a modification signal and a document key for generating a security signal, and a key security prediction analysis is performed through a time series model to determine an optimized key merging scheme;

[0027] Identify the personnel with authority in the current meeting. The mobile devices of the personnel with authority have ID authentication set. Count the number of mobile devices that currently have authority and are editing the document to obtain the number of mobile devices currently editing the document.

[0028] In a preferred embodiment, the time series model adopts an ARIMAX model. The specific steps of performing key security prediction analysis using the time series model are as follows:

[0029] Step A1, obtaining prediction data;

[0030] Step A2, establishing an ARIMAX model;

[0031] Step A3, using the maximum likelihood estimation (MLE) method to estimate the ARIMAX model parameters;

[0032] Step A4, verify the effect of the fitting model and check the goodness of fit of the model by residual analysis;

[0033] Step A5, using the fitted model to predict the future allocation plan, and taking the maximum value of the prediction result as the highest risk point for key security in the future time period.

[0034] In a preferred embodiment, the ARIMAX model formula is:

[0035]

[0036] In the formula, is the safety performance of the current time period, is a constant term, is the i-th order autoregressive parameter, is the order of the autoregressive term, is the j-th order moving average parameter, is the predicted target value at lag i, is the order of the moving average term, is the white noise term with lag j, is a white noise term, representing random error, is an exogenous variable The coefficient of is the lag order of the exogenous variable, is an exogenous variable lagged by k periods.

[0037] In a preferred embodiment, in step A3, , , , , It is calculated by the maximum likelihood estimation method.

[0038] Technical effects and advantages of the present invention:

[0039] 1. The present invention collects file feature information and conference feature information, establishes a data analysis model, obtains a merge evaluation coefficient, compares and calculates the difference between the merge evaluation coefficients, performs trend analysis and calculations on the difference, obtains the overall trend of the document key, and compares the difference with the merge threshold to obtain a comparison result, and limits the degree of merging the document key based on the comparison result, thereby solving the problem that the document cannot be opened normally due to low key coordination performance caused by frequent document modifications, and enhances the key modifiability.

[0040] 2. The present invention receives the limiting results, detects, evaluates and collects the document editing status in real time for the document key that generates the modification signal, and performs key security prediction and analysis through a time series model to obtain security performance data and dynamically adjust the key merging scheme to meet the requirements of multiple people collaborating in a meeting to modify the document while ensuring that the document has a certain degree of security, avoiding key conflicts and data loss, and at the same time looking forward to the security performance of the document key to ensure the long-term security of the document. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 This is a module schematic diagram of a smart conference system of the present invention. DETAILED DESCRIPTION

[0042] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0043] The present invention avoids the disadvantage of fixed keys in traditional symmetric encryption algorithms by combining the content-associated key algorithm with the traditional symmetric encryption algorithm. It is understandable that due to the fixed keys, the ciphertext structures of different documents may have similarities, and attackers may infer the keys or decrypt documents by analyzing these similarities, thereby greatly reducing the security of document encryption. The algorithm used in combination with the document content makes the document key dynamic and has a certain degree of security. The degree of merging of key data is evaluated by parameters such as the frequency of file history modification and the proportion of unmodifiable content, thereby obtaining the document key.

[0044] Among them, the implementation steps of combining the content-associated key algorithm with the traditional symmetric encryption algorithm are: extract key attributes twice as keys, first extract the attribute part of the document, then extract the data part of the document, and finally merge the data extracted from the first two times to obtain the file key.

[0045] Example 1

[0046] The present invention discloses a smart conference system. Figure 1 As shown, it includes a data acquisition module, a data processing module, a merging analysis module and a safety prediction module; and the modules are connected by signals.

[0047] The data collection module is used to collect file feature information and meeting feature information. Through data processing, the historical file modification frequency, the proportion of unmodifiable content, the historical modification frequency of authorized personnel, and the historical modification content length of authorized personnel are obtained, and the file feature information and meeting feature information are sent to the data processing module.

[0048] Among them, file feature information includes the historical modification frequency of the file and the proportion of unmodifiable content, and meeting feature information includes the historical modification frequency of authorized personnel and the length of historical modification content of authorized personnel.

[0049] The file history modification frequency refers to the number of times or frequency that a document is modified within a certain period of time. Specifically, the file history modification frequency can be used to obtain the frequency of editing, updating or changing a document within a certain period of time, that is, the number of times the document is modified within a specified time range. The acquisition logic is to define the time period first, and collect and count all modification records of the document within the defined time period, and obtain the file history modification frequency through the ratio of the number of modifications to the time period. ; where i is the i-th time period; the i-th time period corresponds to the i-th meeting.

[0050] It should be noted that the definition of a limited time period is that the time period corresponds to the interval between meetings. It is understandable that the personnel with authority and personnel attributes of each meeting are different, so the number of modifications to the same document in each meeting is also different, that is, the modifiable content in each meeting is also different. Therefore, the set time period is not a fixed period, but is set according to the length of the meeting interval.

[0051] The proportion of unmodifiable content refers to the proportion of content that cannot be modified by users or the system in a document to the entire document content. The unmodifiable nature is set by the meeting initiator or team. Specifically, when editing or creating a document, modification permissions are set for different content parts. After input from the input end, the unmodifiable parts are identified by the system's built-in text tags or marks (for example, XML, HTML tags or other formatting symbols).

[0052] The logic for obtaining the percentage of unmodifiable content is to calculate the percentage of unmodifiable content after the system detection is completed. Specifically, the system automatically counts the size of the portion of the document marked as unmodifiable (for example, measured by metrics such as the number of characters, bytes, and pages), according to the formula:

[0053]

[0054] In the formula, For the unmodifiable part size, is the total size of the document, It is the proportion of unmodifiable content. It can be understood that the higher the proportion of unmodifiable content, the higher the security of the document.

[0055] From the above, we can see that the historical modification frequency of personnel within the authority refers to the frequency of modifications to the same document by the personnel with the authority during the time period between different meetings. Therefore, this frequency will change with the interval between meetings. Specifically, the participants and their authority in different meetings are different, resulting in different numbers of modifications to the same document in different meetings.

[0056] The logic for obtaining the historical modification frequency of personnel within the authority is to automatically identify the current meeting participants and their authority through the system, determine whether the meeting participants have the authority to modify the document, collect the sum of the modification records of the document by the participants within the authority of this meeting, and compare it with the corresponding time period to obtain the historical modification frequency of personnel within the authority. .

[0057] Among them, there are multiple authorized persons in this meeting, and their personal historical modification frequency is m. However, the starting point of the present invention is to analyze the merging of the generated document keys. It is necessary to add the historical modification frequencies of multiple authorized persons to obtain the historical modification frequencies of authorized persons. It can be understood that if At the same time, because the multiple authorized persons in the meeting of the previous time period may not be consistent with the persons in this time period, the one-sided influence of individual historical modification frequency on the document key is abandoned, and the historical modification frequency of authorized persons in the meeting is used as the basis for consideration.

[0058] The length of historical modifications made by authorized personnel refers to the total length of modifications made to the document by personnel with modification authority within a specified time period, where the length can be measured in a variety of ways, such as the number of characters, bytes, paragraphs, or actual pages of the document.

[0059] The logic for obtaining the length of historical modifications of authorized personnel is to identify authorized personnel through the defined time period, collect their modification records, calculate their cumulative historical modification length, add up the cumulative modification lengths of all authorized personnel, and obtain the length of historical modifications of authorized personnel. .

[0060] The data processing module is used for file feature information and conference feature information, establishes a data analysis model, obtains a combined evaluation coefficient, and sends it to the combined analysis module.

[0061] Obtain file feature information and meeting feature information, including the file's historical modification frequency, the proportion of unmodifiable content, the historical modification frequency of authorized personnel, and the length of historical modification content by authorized personnel, establish a data analysis model, and generate a combined evaluation coefficient , the specific formula is:

[0062]

[0063] In the formula, is the combined evaluation coefficient, , , as well as The preset ratio coefficients are the file's historical modification frequency, the proportion of unmodifiable content, the historical modification frequency of authorized personnel, and the length of historical modification content of authorized personnel, and , , as well as Both are greater than 0.

[0064] Among them, the frequency of historical file modifications, the proportion of unmodifiable content, the frequency of historical modifications by authorized personnel, and the length of historical modifications by authorized personnel are all data-based manifestations of the current degree of key merging. Specifically, the more key attributes are merged, the higher the security, but the lower the modifiability. Repeated modifications to the key architecture can easily cause system freezes or even documents to fail to open normally. The fewer key attributes are merged, the higher the modifiability, but the security is threatened.

[0065] It can be seen from the above formula that when the frequency of historical file modifications, the frequency of historical modifications by authorized personnel, and the length of historical modifications by authorized personnel are greater, the merge evaluation coefficient is greater, which means that the current key attributes of the merge are fewer, in order to meet the needs of multiple modifications to the document during the meeting process; conversely, if the proportion of unmodifiable content is larger, the merge evaluation coefficient is smaller.

[0066] The merge analysis module is used to obtain the merge evaluation coefficients of each time period, and compare and calculate them to obtain the differences in each merge evaluation coefficient, perform trend analysis and calculation on them to obtain the overall trend of the document key, and compare it with the merge threshold to obtain the comparison result, and limit the degree of merging of the document key based on it, and send the limited result to the security prediction module.

[0067] Get the combined evaluation coefficients for each time period and get , and compare and calculate the combined evaluation coefficients of each time period. The operation logic is: , and obtain the difference of each combined evaluation coefficient , where g is the g-th comparison.

[0068] The difference of the combined evaluation coefficient greater than 0 is defined as a combined upward trend, and the difference of the combined evaluation coefficient less than 0 is defined as a combined downward trend.

[0069] Among them, the merge rising trend and the merge falling trend both express that the amount of data merged by the document key presents an upward or downward trend, that is, the more merges there are, the more security the document is inclined to, and conversely, the fewer merges there are, the more modifiable the document is inclined to.

[0070] The differences of each combined evaluation coefficient are added together, and the operation logic is as follows: , get the overall trend of document keys and compare it with the merge threshold.

[0071] The logic for obtaining the merge threshold is to collect a distribution sample set of the historical merge key information library, divide the data set into a training set and a test set, set the evaluation index and clustering algorithm, and in each round of cross-validation, train the model on the training set and evaluate the model performance on the test set. Then, adjust the merge threshold based on the performance of the validation set. Therefore, the merge threshold is constantly iteratively updated.

[0072] In the present invention, clustering algorithm is a type of unsupervised learning algorithm, which is used to divide the data points in the data set into groups or clusters with similarities; a common one is K-means clustering, which divides the data points in the data set into K clusters, so that the distance between the data point of each curve and the center point (centroid) of its cluster is minimized, and finally the effect of the adjusted merging threshold is measured by the Euclidean distance, so as to set the merging threshold.

[0073] After obtaining the overall trend of the document key, it will be compared and analyzed with the continuously iterated merge threshold.

[0074] If the total trend of the document key is greater than or equal to the merge threshold, the key attributes of the document in the current meeting are merged into a preset first range as the document key, and a security signal is generated.

[0075] If the overall trend of the document key is less than the merge threshold, the key attributes of the document in the current meeting are merged into the preset second range as the document key, and a modification signal is generated.

[0076] The generated security signal and modification signal are sent to the security prediction module; the document key for generating the security signal is brought into the hash tree or challenger game for security testing, and the document key for generating the security signal has a certain degree of security; and the document key for generating the modification signal has a certain degree of modifiability, and relatively fewer key attributes are merged to ensure document security, and an end signal is generated for the document key for generating the modification signal.

[0077] It should be noted that the settings within the preset first and second ranges can be adjusted according to actual conditions. For example, although this embodiment takes the merging within the preset first and second ranges as an example, in fact, the experimenter can set multiple preset ranges according to actual conditions to fine-tune the degree of merging of document keys, so as to facilitate better precise adjustment according to different information.

[0078] The degree of merging is implemented by the experimenter according to the actual situation. For example, the first range is set to 80% of the merged key attributes, etc., and is not limited here.

[0079] The present invention collects file feature information and conference feature information, establishes a data analysis model, obtains a merge evaluation coefficient, compares and calculates the difference between the merge evaluation coefficients, performs trend analysis and calculation on the difference, obtains the overall trend of the document key, compares the difference with the merge threshold, obtains the comparison result, and limits the degree of merging the document key based on the comparison result, solves the problem that the document cannot be opened normally due to low key coordination performance caused by frequent document modifications, and enhances the key modifiability.

[0080] Example 2

[0081] Embodiment 1 of the present invention focuses on examples of collecting file feature information and conference feature information, establishing a data analysis model, obtaining a merge evaluation coefficient, and comparing and calculating the coefficients to obtain differences in the merge evaluation coefficients, performing trend analysis and calculations to obtain a total trend of the document key, and comparing the comparison result with the merge threshold to obtain a comparison result, and based on which an operation strategy is defined for the degree of merging the document key. However, in Embodiment 1, only the modifiability of the document is considered, while the original intention of document security and data encryption is ignored. Obviously, if only one person is allowed to modify the document alone during the meeting, the above-mentioned key merging method can be applicable, but in actual application scenarios, there is the possibility of multiple people collaborating to modify the document content, and the document security cannot be further met. In response to the above problems, Embodiment 2 of the present invention is further refined.

[0082] The security prediction module is used to receive the restricted results, detect and evaluate the document editing status in real time for the document key that generates the modification signal, and perform key security prediction analysis through the time series model to further refine and optimize the key merging solution.

[0083] The limiting result includes a document key for generating a modification signal and a document key for generating a security signal. As can be seen from the above-mentioned embodiment 1, the document key for generating a security signal is more secure.

[0084] Among them, the document editing status refers to whether the current document is in an editable state. If the document is in an editable state on multiple mobile terminals (that is, the number of mobile terminals of the editable document is greater than 1), the number of mobile terminals currently editing the document is collected, and key security prediction analysis is performed through a time series model.

[0085] The logic for obtaining the number of mobile terminals currently editing the document is to identify the personnel with authority in the current meeting, whose mobile devices have ID authentication set, count the number of mobile devices that currently have authority and are editing the document, and obtain the number of mobile terminals currently editing the document.

[0086] It should be noted that the time series model used in this embodiment is the ARIMAX model. Refining and optimizing the key merging scheme means that after determining the document key that currently generates the modification signal, through further analysis and adjustment, the key merging scheme is made more scientific and reasonable, thereby enhancing the security of the document key.

[0087] Furthermore, the specific steps for key security prediction analysis using a time series model are as follows:

[0088] Step A1, obtaining prediction data;

[0089] Step A2, establishing an ARIMAX model;

[0090] Step A3, using the maximum likelihood estimation (MLE) method to estimate the ARIMAX model parameters;

[0091] Step A4, verify the effect of the fitting model and check the goodness of fit of the model by residual analysis;

[0092] Step A5, using the fitted model to predict future generation plans, and taking the maximum value of the prediction result as the highest risk point for key security in the future time period.

[0093] Specifically, the prediction data include the file history modification frequency corresponding to each time period, the proportion of unmodifiable content, the historical modification frequency of personnel with authority, the length of historical modification content by personnel with authority, the number of mobile terminals currently editing the document, and security performance data; among them, the file history modification frequency corresponding to each time point, the proportion of unmodifiable content, the historical modification frequency of personnel with authority, and the length of historical modification content by personnel with authority have been exemplified in Example 1 and will not be repeated here.

[0094] Safety performance data refers to historical safety performance data, and its data serves as the main variable of the time series.

[0095] Furthermore, the basic form of the ARIMAX model is:

[0096]

[0097] In the formula, is the safety performance of the current time period, is a constant term, is the i-th order autoregressive parameter, is the order of the autoregressive term, is the j-th order moving average parameter, is the predicted target value at lag i, is the order of the moving average term, is the white noise term with lag j, is a white noise term, representing random error, is an exogenous variable The coefficient of is the lag order of the exogenous variable, is an exogenous variable lagged by k periods.

[0098] It should be noted that the exogenous variable part can integrate the impact of other relevant variables (such as the frequency of historical file modifications, the proportion of unmodifiable content, the frequency of historical modifications by authorized personnel, the length of historical modifications by authorized personnel, and the number of mobile terminals currently editing documents) on security performance.

[0099] It should be noted that in step A3, , , , , It is calculated by the maximum likelihood estimation (MLE) method. The specific steps are as follows:

[0100] Error term Normal distribution , then the likelihood function is:

[0101]

[0102] Taking the logarithm of the likelihood function gives the log-likelihood function:

[0103]

[0104] By maximizing the log-likelihood function, we can obtain the parameter estimates , , , , .

[0105] The key merging scheme is dynamically adjusted by predicting the maximum and average values ​​of the results.

[0106] This embodiment exemplifies as follows:

[0107] The maximum value of the predicted result It represents the highest risk point for key security in the future period. A risk period merging strategy is formulated. At the time point of the document, 30% more key attributes are added for merging or 40% of authorized personnel who are editing are reduced to ensure document information security and the reliability of encryption algorithms;

[0108] According to the average of the predicted results , formulate a balance period merging strategy, and complete the reintegration of document keys through existing technologies (such as key negotiation mechanism, etc.) during the time period when the security performance is close to the average value.

[0109] The risk period and balance period are set based on the specific divisions implemented by the experimenters, and the boundaries of this division are not limited.

[0110] The present invention receives the limiting result, detects, evaluates and collects the document editing status in real time for the document key that generates the modification signal, performs key security prediction and analysis through a time series model, obtains security performance data, and dynamically adjusts the key merging solution to meet the requirements of multiple people collaborating to modify the document in a meeting while ensuring that the document has a certain level of security, avoids key conflicts and data loss, and at the same time, looks forward to the security performance of the document key to ensure the long-term security of the document.

[0111] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0112] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0113] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0114] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0115] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0116] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0117] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0118] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0119] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0120] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A smart conference system, characterized by: It includes data acquisition module, data processing module, combined analysis module and safety prediction module; signal connection between each module; The data collection module is used to collect file feature information and meeting feature information, obtain the file history modification frequency, the proportion of unmodifiable content, the history modification frequency of authorized personnel, and the history modification content length of authorized personnel through data processing, and send the file feature information and meeting feature information to the data processing module; The data processing module is used to receive the file feature information and the meeting feature information, establish a data analysis model, obtain the combined evaluation coefficient, and send the combined evaluation coefficient to the combined analysis module; The merge analysis module is used to obtain the merge evaluation coefficient of each time period, and compare and calculate the merge evaluation coefficients of each time period to obtain the difference of each merge evaluation coefficient, perform trend analysis and calculation on the difference of each merge evaluation coefficient to obtain the overall trend of the document key, and compare the overall trend of the document key with the merge threshold to obtain the comparison result, and limit the degree of merging of the document key this time according to the comparison result, and send the limit result to the security prediction module; The security prediction module is used to receive the qualification results, detect and evaluate and collect the document editing status in real time, and perform key security prediction analysis on the qualification results through the time series model to further refine and optimize the key merging solution; File feature information includes the file's historical modification frequency and the percentage of unmodifiable content. Meeting feature information includes the historical modification frequency of authorized personnel and the length of authorized personnel's historical modification content. The data processing includes: By defining a time period, collecting and counting all modification records of the document within the time period, the file history modification frequency is obtained by the ratio of the number of modifications in the modification record to the time period. ; Where i is the i-th time period; the i-th time period corresponds to the i-th meeting; Based on the set document content, after the system automatically counts the size of the unmodifiable portion of the document, the ratio of the unmodifiable portion size to the total document size is calculated to obtain the unmodifiable content ratio. ; The system automatically identifies the current meeting participants and their permissions, determines whether the meeting participants have the permission to modify the document, collects the sum of the modification records of the document by the participants within the permission of the current meeting, and compares it with the corresponding time period to obtain the historical modification frequency of the personnel within the permission. ; By collecting the current meeting participants and their modification records, the accumulated historical modification length of the current meeting participants is calculated, and the accumulated modification length of all participants within the authority is added up to obtain the historical modification length of the personnel within the authority. ; Obtain file feature information and meeting feature information, establish a data analysis model, and generate a combined evaluation coefficient , the specific formula is: In the formula, is the combined evaluation coefficient, , , as well as The preset ratio coefficients are the file's historical modification frequency, the proportion of unmodifiable content, the historical modification frequency of authorized personnel, and the length of historical modification content of authorized personnel, and , , as well as Both are greater than 0.

2. The intelligent conference system according to claim 1, characterized in that: Get the combined evaluation coefficients for each time period and get , and compare and calculate the combined evaluation coefficients of each time period. The operation logic is: , and obtain the difference of each combined evaluation coefficient , where g is the g-th comparison; The difference of the combined evaluation coefficient greater than 0 is defined as a combined upward trend, and the difference of the combined evaluation coefficient less than 0 is defined as a combined downward trend.

3. The intelligent conference system according to claim 2, characterized in that: The differences of each combined evaluation coefficient are added together, and the operation logic is as follows: , get the overall trend of document keys and compare it with the merge threshold; If the total trend of the document key is greater than or equal to the merge threshold, the key attributes of the document in the current meeting are merged into the preset first range as the document key, and a security signal is generated; If the overall trend of the document key is less than the merge threshold, the key attributes of the document in the current meeting are merged into the preset second range as the document key, and a modification signal is generated.

4. The intelligent conference system according to claim 3, characterized in that: The limited results include the document key for generating the modification signal and the document key for generating the security signal, and the key security prediction analysis is performed through the time series model to determine the optimization and adjustment of the key merging scheme; Identify the personnel with authority in the current meeting. The mobile devices of the personnel with authority have ID authentication set. Count the number of mobile devices that currently have authority and are editing the document to obtain the number of mobile devices currently editing the document.

5. The intelligent conference system according to claim 4, characterized in that: The time series model uses the ARIMAX model. The specific steps for key security prediction analysis using the time series model are as follows: Step A1, obtaining prediction data; Step A2, establishing an ARIMAX model; Step A3, using the maximum likelihood estimation (MLE) method to estimate the ARIMAX model parameters; Step A4, verify the effect of the fitting model and check the goodness of fit of the model by residual analysis; Step A5, using the fitted model to predict the future allocation plan, and taking the maximum value of the prediction result as the highest risk point for key security in the future time period.

6. The intelligent conference system according to claim 5, characterized in that: The ARIMAX model formula is: In the formula, is the safety performance of the current time period, is a constant term, is the i-th order autoregressive parameter, is the order of the autoregressive term, is the j-th order moving average parameter, is the predicted target value at lag i, is the order of the moving average term, is the white noise term with lag j, is a white noise term, representing random error, is an exogenous variable The coefficient of is the lag order of the exogenous variable, is an exogenous variable lagged by k periods.

7. The intelligent conference system according to claim 6, characterized in that: In step A3, , , , , It is calculated by the maximum likelihood estimation method.

Images