Data fusion method oriented to visual platform and entity archive management system

Abstract

The invention relates to the technical field of data visualization management, in particular to a data fusion method for a visualization platform and an entity archive management system, which comprises the following steps of: firstly, analyzing the similarity between a path behavior when an archive is retrieved on an archive observation road section through historical data and a path behavior on the archive observation road section in each archive retrieval process; determining the gear shifting possibility of the gear shifting behavior; then, on the basis of the file shifting possibility, a path behavior coding sequence obtained through coding more accurately quantifies behavior information of each file calling process; the abnormal possibility of each file calling process is determined by combining the overall deviation between the file calling process and the historical data on the dimension of the file shifting habit; therefore, the archive calling abnormity process screened based on the abnormity possibility is more accurate, and the accuracy of the corresponding archive management information visualization processing is higher, so that the tracing efficiency when archive problems occur is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data visualization management, and in particular to a data fusion method for a visualization platform and an entity archive management system. Background Art

[0002] The physical archive management system is an information system specifically designed for managing and organizing physical archives. Its primary functions include recording, searching, and archiving physical archives, as well as providing related management capabilities. It utilizes RFID technology to achieve contactless collection, precise location, and dynamic path tracking of archives. It utilizes technologies such as space utilization algorithms and door scanning, and uses WebGL to construct a 3D warehouse model to display information such as archive storage location, borrowing status, and environmental conditions. Timeline playback is used to obtain information on borrowing frequency and inventory counts of physical archives over past time periods. Visualization technology is then used to convert this data into graphics and images, enabling comprehensive control over the archive's location within the warehouse and the retrieval of records.

[0003] Existing physical file management technology automatically constructs the storage location of each physical file, such as a specific rack, column, or layer, based on file classification, size, and space utilization algorithms. RFID access doors and high-frequency scanning devices then scan the file's RFID tag and determine the file's location based on the relative position of the file and the access door. The file's retrieval frequency and related data are then determined based on the release time of the corresponding RFID signal and the corresponding retrieval data. Visualization technology then displays this data, such as file retrieval frequency and importance, on a visualization platform.

[0004] When performing visual data fusion, the existing physical archive management system usually directly displays the fused data and retrieval records after the archive is retrieved, and displays the archive retrieval process of the wrong archive as an abnormal archive retrieval process separately on the visualization platform to trace back when archive problems occur; however, the existing technology starts analysis from the time when the archive leaves the corresponding position on the archive shelf, and does not take into account the possibility that some people may accidentally take the wrong archive due to forgetting the location of the archive. As a result, the accuracy of the existing technology directly treating the archive retrieval process of the wrong archive as an abnormal archive retrieval process is low, thereby affecting the accuracy of the visualization processing of archive management information and reducing the efficiency of tracing back when archive problems occur. Summary of the Invention

[0005] In order to solve the technical problem of low accuracy in the prior art of directly treating the retrieval process of the wrong file as an abnormal retrieval process, the purpose of this application is to provide a data fusion method for a visualization platform and a physical file management system. The technical solution adopted is as follows: The first aspect of the present application provides a data fusion method for a visualization platform and a physical archive management system, comprising: In the archive room bird's-eye view node diagram, the archive retrieval path corresponding to each archive retrieval process when each person retrieves the target archive in the archive room is collected; wherein the archive retrieval path includes at least two archive observation sections; On the file retrieval path corresponding to each file retrieval process, the corresponding file transfer possibility is determined based on the similarity of the travel behavior between each file observation section and the historical observation section when the historical data was retrieved on the corresponding file observation section; based on the path optimization of the file retrieval path and the file transfer possibility of each file observation section, the path behavior coding sequence of the file retrieval path is determined; Based on the similarity and overall deviation in the path behavior coding sequence between each personnel in each file retrieval process and each retrieval process in the historical data, the abnormal possibility of each file retrieval process is determined; the abnormal file retrieval process is screened out according to the abnormal possibility; and the file management information is visualized based on the abnormal file retrieval process.

[0006] Furthermore, the process of obtaining the possibility of file transfer includes: A rectangular coordinate system is constructed with the lower left corner of the thumbnail of the archive room viewed from above as the origin, the horizontal rightward direction as the x-axis direction, and the vertical upward direction as the y-axis direction; the rectangular coordinate system is converted into a polar coordinate system; in each archive retrieval process, on the corresponding archive retrieval path, the polar angles of each archive observation section in the polar coordinate system at all sampling moments are arranged in chronological order to obtain a corresponding travel polar angle sequence; the polar diameters of each archive observation section in the polar coordinate system at all sampling moments are arranged in chronological order to obtain a corresponding travel polar diameter sequence; Each file retrieval process when each person retrieves the target file is taken as the target retrieval process; each file observation section in the target retrieval process is taken as the target observation section; in the historical data of all personnel, all file retrieval processes for file retrieval operations on the section corresponding to the target observation section are taken as reference retrieval processes; Under the target observation section, determining a reference similarity between the target retrieval process and each reference retrieval process under the target observation section based on similarities between the target retrieval process and each reference retrieval process in corresponding travel polar angle sequences, travel polar diameter sequences, and travel time lengths; According to the numerical distribution of the reference similarity corresponding to the target retrieval process, the possibility of shifting gears on the target observation section corresponding to the target retrieval process is determined.

[0007] Furthermore, the process of obtaining the reference similarity includes: Based on the dynamic time warping algorithm, the DTW distance between the polar angle sequence of the target observation section in the target retrieval process and the corresponding polar angle sequence in the reference retrieval process is negatively correlated to obtain the corresponding polar angle sequence similarity; Performing a negative correlation mapping on the DTW distance between the travel path sequence of the target observation section in the target retrieval process and the corresponding travel path sequence in the reference retrieval process to obtain the corresponding path sequence similarity; The difference between the total number of sampling moments of the target observation section in the target retrieval process and the total number of sampling moments in the reference retrieval process is used to obtain the corresponding time length similarity; A corresponding reference similarity is determined according to a normalized value of an average value among the polar angle sequence similarity, the polar diameter sequence similarity, and the time length similarity.

[0008] Furthermore, the process of determining the possibility of shifting on the target observation section corresponding to the target retrieval process according to the numerical distribution of the reference similarity corresponding to the target retrieval process includes: The maximum value of the reference similarity corresponding to the target retrieval process is used as the possibility of file transfer on the target observation section on the file retrieval path corresponding to the target retrieval process.

[0009] Furthermore, the process of obtaining the path behavior coding sequence includes: Determine the optimal path for each person to retrieve the required files in each file retrieval process when retrieving the target files through a path search algorithm; The file observation section corresponding to the overlap between the file retrieval path and the optimal path in each file retrieval process of each person when retrieving the target file is used as the optimal travel section; the file observation section with a file retrieval probability greater than a preset probability threshold is used as the file retrieval section; the other file observation sections other than the optimal travel section and the file retrieval section are used as suspected detour sections; The section code of the optimal traveling section is set as the preset optimal section parameter; the section code of the file retrieval section is set as the preset file retrieval section parameter; the section code of the suspected detour section is set as the preset detour section parameter; The section codes of each archive observation section in the archive retrieval path corresponding to each archive retrieval process when each person retrieves the target archive in the archive room are arranged in path order to obtain a path behavior code sequence.

[0010] Furthermore, the process of obtaining the abnormal possibility includes: The DTW distance between the path behavior coding sequence corresponding to each file retrieval process of each person in the archive room and the path behavior coding sequence corresponding to each other file retrieval process is negatively correlated to determine the consistency of the corresponding retrieval process; Determine the behavioral contribution of each archive retrieval process based on the overall similarity of the retrieval process consistency between each archive retrieval process and other archive retrieval processes; The other file retrieval processes other than the corresponding target retrieval process when each person retrieves the target file in the archive room are used as comparative retrieval processes; the behavioral contribution of each person in each comparative retrieval process is calculated; the cumulative value of the behavioral contribution of each person in all comparative retrieval processes is used as the overall contribution of each person; The consistency of the retrieval process between the target retrieval process and each comparison retrieval process is used as the comparison consistency of each comparison retrieval process; the product of the behavioral contribution of each comparison retrieval process and the comparison consistency is used as the comparison contribution of each comparison retrieval process; the cumulative value of the comparison contribution of each person in all comparison retrieval processes is used as the reference contribution; The abnormal possibility of the target retrieval process corresponding to each person is determined according to the negative correlation mapping value of the ratio between the reference contribution and the overall contribution.

[0011] Furthermore, the process of obtaining the behavior contribution includes: The mean of all retrieval process consistencies corresponding to each file retrieval process when each person retrieves the target file in the archive room is taken as the corresponding average process consistency; The difference between the mean of the average process consistency of all file retrieval processes for each person and the average process consistency of each file retrieval process is used as the overall consistency deviation of each file retrieval process; the standard deviation of the average process consistency of all file retrieval processes for each person is used as the corresponding retrieval habit stability; the deviation score of each file retrieval process is determined based on the product of the retrieval habit stability and the overall consistency deviation; A negative correlation mapping is performed based on the ratio between the deviation score and the average process consistency of each archive retrieval process to determine the behavioral contribution of each archive retrieval process.

[0012] Furthermore, the acquisition process of the abnormal process of retrieving the archive includes: The file retrieval process with an abnormal probability greater than the preset abnormality threshold is regarded as an abnormal file retrieval process.

[0013] Furthermore, the process of visualizing archive management information according to the abnormal process of retrieving archives includes: The archive retrieval records of abnormal archive retrieval processes are displayed separately on the visualization page.

[0014] Furthermore, the path search algorithm adopts the A-star algorithm.

[0015] In a second aspect, the present application provides a data fusion system for a visualization platform and a physical archive management system, the system comprising: A data collection and preprocessing module is used to collect, from the archive room overhead node diagram, the archive retrieval path corresponding to each archive retrieval process when each person retrieves the target archive in the archive room; wherein the archive retrieval path includes at least two archive observation sections; A path behavior coding module is used to determine the corresponding file transfer possibility on the file retrieval path corresponding to each file retrieval process based on the similarity of the behavior between each file observation section and the historical observation section when the historical data was retrieved on the corresponding file observation section; and determine the path behavior coding sequence of the file retrieval path based on the path optimization status of the file retrieval path and the file transfer possibility of each file observation section; The archive management information visualization processing module is used to determine the abnormal possibility of each archive retrieval process based on the similarity and overall deviation between each personnel in each archive retrieval process and each archive retrieval process in historical data; screen out abnormal archive retrieval processes based on the abnormal possibility; and perform archive management information visualization processing based on abnormal archive retrieval processes.

[0016] In a third aspect, the present application provides a computer device comprising a memory and a processor. The memory is configured to store computer program code, and the processor is configured to call and execute the computer program code from the memory to perform the method of the first aspect or any embodiment of the first aspect of the present application.

[0017] In a fourth aspect, the present application provides a computer program product, comprising a computer program code. When the computer program code is executed, the method of the first aspect or any embodiment of the first aspect of the present application is performed.

[0018] In a fifth aspect, the present application provides a computer-readable storage medium, which stores computer program code. When the computer program code is executed, it performs the method of the first aspect of the present application or any embodiment of the first aspect.

[0019] This application has the following beneficial effects: This application first analyzes the path behavior of historical data when retrieving archives on the archive observation section and the similarity of the path behavior of each archive retrieval process on the archive observation section to determine the possibility of file transfer behavior; then, based on the file transfer possibility, the path behavior coding sequence obtained by encoding is used to more accurately quantify the behavioral information of each archive retrieval process; thereby, the overall deviation between the archive retrieval process and the historical data is combined with the dimension of file transfer habits to determine the abnormal possibility of each archive retrieval process; the abnormal process of retrieving archives screened out based on the abnormal possibility is more accurate, and the corresponding archive management information visualization processing is more accurate, thereby improving the efficiency of tracing when archive problems occur. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0021] Figure 1 A flow chart of a data fusion method for a visualization platform and a physical archive management system provided by one embodiment of the present invention; Figure 2 A schematic diagram of a top-down node diagram of an archive room provided by one embodiment of the present invention; Figure 3 A structural diagram of a data fusion system for a visualization platform and a physical archive management system provided by one embodiment of the present invention; Figure 4 The present invention provides a schematic diagram of a computer device structure according to an embodiment of the present invention. DETAILED DESCRIPTION

[0022] In order to further illustrate the technical means and effects adopted by the present invention to achieve the predetermined purpose of the invention, the following is a detailed description of a data fusion method for a visualization platform and a physical archive management system proposed by the present invention, its specific implementation method, structure, characteristics and effects, in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment, and the specific features, structures or characteristics in one or more embodiments may be combined in any suitable form. In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as implying or suggesting relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features.

[0023] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0024] The following describes in detail a specific solution of a data fusion method for a visualization platform and a physical archive management system provided by the present invention with reference to the accompanying drawings.

[0025] This application embodiment provides a data fusion method for a visualization platform and a physical archive management system. Figure 1 , which shows a flow chart of a data fusion method for a visualization platform and a physical archive management system provided by one embodiment of the present invention, the method comprising: Step S101: In the archive room bird's-eye view node diagram, collect the archive retrieval path corresponding to each archive retrieval process when each person retrieves the target archive in the archive room; wherein the archive retrieval path includes at least two archive observation sections.

[0026] On each side of the file rack, a four-channel RFID reader is installed and fixed every 1 meter, and the antenna is arranged in a 45-degree cross layout to ensure 360-degree recognition without blind spots; then based on the position of the file rack, the four-channel RFID reader is used as a node, and the connection distance is less than the preset connection distance. The connection line between the nodes does not pass through the file rack; in a specific implementation of the embodiment of the present invention, the preset connection distance is set to 1.2 meters to connect the four-channel RFID readers in adjacent positions as much as possible. It can be adjusted by itself, but it is necessary to ensure that the preset connection distance is greater than the distance between adjacent file racks, so that the nodes at the corresponding positions between the file racks are connected to each other. After the connection is completed, the overhead node diagram of the archive room required by the embodiment of the present invention is obtained, and the static data corresponding to the archive management is preliminarily integrated through the overhead node diagram of the archive room. Please refer to Figure 2 , which shows a schematic diagram of an overhead node diagram of an archive room provided by an embodiment of the present invention; in the overhead node diagram of the archive room, in order to make all nodes correspond to a whole, a four-channel RFID reader is installed on both sides of the two ends of the archive rack, so that the nodes between different archive racks are interconnected, thereby determining a more accurate archive retrieval path.

[0027] In addition, each person is equipped with an RFID work badge when retrieving files, which records personnel information and is detected in real time by a four-channel RFID reader. The real-time location information of each person is located by the detected RFID work badge, and the file retrieval path corresponding to each file retrieval process when each person retrieves the target file in the archive room is determined based on the real-time collected location information; that is, the dynamic data of the file management process is integrated here; the dynamic data and static data are subsequently combined for analysis, so as to more clearly visualize the file management information.

[0028] In a specific implementation of an embodiment of the present invention, the sampling frequency of the four-channel RFID reader is set to detect once every three seconds. The file retrieval process refers to the process from a person entering the file rack to leaving the file rack after retrieving the target file. In addition, on the file retrieval path, the file retrieval path is divided into various file observation sections with each four-channel RFID reader as an interval point. In other words, the file retrieval path in the embodiment of the present invention is composed of multiple file observation sections. Among them, the target file refers to the file that the person needs to retrieve, which is collected by registering the information before retrieving the file. In addition, the target file in the embodiment of the present invention refers to a specific file. In other words, the subsequent analysis process is based on the file specifically referred to by the target file.

[0029] It should be noted that there is only one file in the four-channel RFID reader-writer adjacent to the file rack channel, that is, there is at most one file in each file observation section, and the installation distance of the corresponding four-channel RFID reader-writer can be adjusted according to the specific implementation environment; and for the file observation section, as long as the four-channel RFID readers on both sides of the two file observation sections are the same, then the corresponding two file observation sections represent the same file observation section, and the sampling frequency of the four-channel RFID reader-writer can be adjusted according to the specific implementation environment.

[0030] In addition, it should be noted that since the archive observation section only represents the connection between adjacent four-channel RFID readers, the position of the personnel may not coincide with the connection line, for example, Figure 2 When a person is in the rectangular area of the four four-channel RFID readers that form a rectangle, it is impossible to determine which archive observation section he belongs to; therefore, the embodiment of the present invention takes the archive observation section closest to the person's position as the archive observation section of the corresponding position, so that the person can obtain the archive observation section he is in when he is at any position in the archive room's bird's-eye view node diagram.

[0031] Step S102: On the archive retrieval path corresponding to each archive retrieval process, determine the corresponding archive transfer possibility based on the similarity of the travel behavior between each archive observation section and the historical observation section when the historical data was retrieved on the corresponding archive observation section; determine the path behavior coding sequence of the archive retrieval path based on the path optimization situation of the archive retrieval path and the archive transfer possibility of each archive observation section.

[0032] Considering that the abnormal process of file retrieval judged only by whether the file retrieval is correct has high limitations, this application specifically analyzes the behavior of each person in the file retrieval process when obtaining the target file, and screens out more accurate abnormal file retrieval processes through behavioral anomalies. In each file retrieval process, in addition to the travel behavior corresponding to the trajectory, there may also be the user's file retrieval behavior or long-term file observation behavior; this behavior usually corresponds to the user's behavioral characteristics of forgetting the location of the target file or the user's intentional behavior of taking other files; therefore, in order to more accurately analyze the path behavior characteristics of each file retrieval process, it is necessary to further analyze the possible file retrieval behavior or observation behavior.

[0033] Preferably, in some possible implementations of the embodiments of the present invention, the process of obtaining the possibility of file shifting includes: A rectangular coordinate system is constructed with the lower left corner of the thumbnail image of the archive room as the origin, the horizontal rightward direction as the x-axis, and the vertical upward direction as the y-axis. This rectangular coordinate system is then converted to a polar coordinate system. This polar coordinate system makes it easier and more intuitive to quantify the similarity between trajectory information.

[0034] During each archive retrieval process, along the corresponding archive retrieval path, the polar angles of each archive observation section at all sampling moments in the polar coordinate system are arranged in chronological order to obtain the corresponding travel polar angle sequence. The polar diameters of each archive observation section at all sampling moments in the polar coordinate system are arranged in chronological order to obtain the corresponding travel polar diameter sequence. Both travel polar angles and travel polar diameters can represent the real-time location information of the person, allowing subsequent trajectory similarity analysis based on the travel polar angle sequence and travel polar diameter sequence to more accurately represent the similarity of path behavior.

[0035] Each file retrieval process when each person retrieves the target file is sequentially considered as the target retrieval process; each file observation section during the target retrieval process is considered as the target observation section; and all file retrieval processes performed on the section corresponding to the target observation section in the historical data of all personnel are considered as reference retrieval processes. Historical data is data acquired a priori, and the reference retrieval process is the file retrieval process that reflects the file retrieval behavior of the target observation section. Therefore, for the target retrieval process, the more similar its trajectory on the target observation section is to the trajectory of the reference retrieval process on the target observation section, the more likely the target retrieval process has generated real file retrieval behavior on the target observation section, or that long-term file observation has resulted in characteristics similar to file retrieval behavior. It should be noted that long-term file observation usually corresponds to the situation where a person may have forgotten the location of the target file they need to retrieve, resulting in the need to check whether other files are the target file, that is, the behavior of the person retrieving the corresponding file and then putting it back.

[0036] In the target observation section, based on the similarity between the target retrieval process and each reference retrieval process in the corresponding travel polar angle sequence, travel polar diameter sequence, and travel time length, a reference similarity between the target retrieval process and each reference retrieval process in the target observation section is determined; specifically, the reference similarity acquisition process includes: Based on the dynamic time warping algorithm, the DTW distances between the polar angle sequence of the target observation section during the target retrieval process and the corresponding polar angle sequence during the reference retrieval process are negatively correlated to obtain the corresponding polar angle sequence similarity; the DTW distances between the polar path sequence of the target observation section during the target retrieval process and the corresponding polar path sequence during the reference retrieval process are negatively correlated to obtain the corresponding polar path sequence similarity; the difference between the total number of sampling moments of the target observation section during the target retrieval process and the total number of sampling moments during the reference retrieval process is used to obtain the corresponding time length similarity; the corresponding reference similarity is determined based on the normalized value of the mean between the polar angle sequence similarity, polar path sequence similarity and time length similarity.

[0037] Based on the principle of the dynamic time warping algorithm, the greater the polar angle sequence similarity and the polar diameter sequence similarity, the more similar the trajectory behavior of the target observation section during the target retrieval process is to the trajectory behavior during the reference retrieval process, and the more likely the corresponding target observation section is to correspond to the archive retrieval behavior of the reference retrieval process. In addition, time length similarity characterizes the behavioral similarity between the target retrieval process and the reference retrieval process in the target observation section in the time dimension. The more similar the time spent by the corresponding target retrieval process on the target observation section is to the time spent by the reference retrieval process on the target observation section, that is, the more similar the total number of sampling moments is, the higher the corresponding trajectory behavior similarity is. Therefore, the reference similarity is finally characterized by combining the average values of the polar angle sequence similarity, the polar diameter sequence similarity, and the time length similarity.

[0038] In a specific implementation of an embodiment of the present invention, the method of negatively mapping the DTW distance uses the inverse of an exponential function with a natural constant as the base for negative correlation mapping. The method of negatively mapping the DTW distance in the subsequent process is the same as here, and can be adjusted according to the specific implementation environment. For example, after the DTW distance is linearly normalized, negative correlation mapping is performed by subtracting the DTW distance from the real number 1. No further details are given here. It should be noted that the difference in this application represents the absolute value of the difference, and the dynamic time warping algorithm is a technical means well known to those skilled in the art. According to the dynamic time warping algorithm, the smaller the DTW distance between the two sequences, the more similar the two sequences are as a whole. No further limitation or details are given here. The process of obtaining the reference similarity is expressed by the formula: ;in, Retrieve process for target Reference retrieval process Reference similarity between ; For the target observation section in the target retrieval process The traveling polar angle sequence in the reference retrieval process The DTW distance between the corresponding travel polar angle sequences in ; For the target observation section in the target retrieval process The traveling radius sequence in the reference retrieval process The DTW distance between the corresponding travel path sequences in ; is an exponential function with a natural constant as its base; Retrieve process for target Reference retrieval process The polar angle sequence similarity between them; Retrieve process for target Reference retrieval process The similarity of the polar sequence between ; For the target observation section in the target retrieval process The total number of sampling moments in ; Reference retrieval process The total number of sampling moments in ; is the absolute value symbol; Retrieve process for target Reference retrieval process The similarity of the time length between them; is a linear normalization function.

[0039] According to the numerical distribution of the reference similarities corresponding to the target retrieval process, the possibility of file transfer on the target observation section corresponding to the target retrieval process is determined; in a specific implementation method of an embodiment of the present invention, according to the numerical distribution of the reference similarities corresponding to the target retrieval process, the process of determining the possibility of file transfer on the target observation section corresponding to the target retrieval process includes: taking the maximum value of the reference similarities corresponding to the target retrieval process as the possibility of file transfer on the target observation section on the file retrieval path corresponding to the target retrieval process. Since each reference retrieval process is a process of performing a file retrieval operation on the section corresponding to the target observation section, the maximum value of the reference similarity can better reflect the proximity of the target retrieval process in the file retrieval operation, thereby avoiding the influence of accidental data.

[0040] Furthermore, the behavior of file transfer can be judged based on the possibility of file transfer on the file observation section; and in the behavior of file transfer, further division is required. Under normal circumstances, for the sake of efficiency, personnel who need to retrieve the target file usually proceed directly to the target file after entering the archive room. If there is a possible detour in the corresponding file retrieval path, it should be divided into possible detour behaviors for analysis. Therefore, when further digitizing the trajectory behavior of each file retrieval process, it is necessary to analyze the path optimization of the file retrieval path to specifically divide the file observation sections corresponding to possible detour behaviors and the file observation sections corresponding to no detour behaviors.

[0041] Preferably, in some possible implementations of the embodiments of the present invention, the process of obtaining the path behavior coding sequence includes: A path search algorithm is used to determine the optimal path for each person to take when retrieving the required files during each file retrieval process. In one specific implementation of an embodiment of the present invention, the path search algorithm uses the A-star algorithm. Specifically, starting from the archive room entrance and ending at the archive observation section where the target file is located, a path search is performed along the archive observation section to obtain the corresponding optimal path. It should be noted that the implementer can adjust the path search algorithm, such as the D-star algorithm, based on the specific implementation environment, and further description is not provided here.

[0042] The file observation section corresponding to the overlapping part between the file retrieval path and the optimal path in each file retrieval process of each person when retrieving the target file is used as the optimal travel section; the file observation section with a file transfer possibility greater than the preset possibility threshold is used as the file retrieval section; and other file observation sections outside the optimal travel section and the file retrieval section are used as suspected detour sections. The file transfer possibility characterizes the possibility of file transfer behavior or long-term observation of file behavior, so the threshold is used to screen out the file retrieval sections where file transfer or observation may occur; in a specific implementation method of an embodiment of the present invention, the preset possibility threshold is set to 0.6, which can be adjusted according to the specific implementation environment and will not be further elaborated here. Since the value range of the file transfer possibility is limited to 0 to 1, according to the principle of normalization, the closer the value of the file transfer possibility is to 1, the more likely it is to be a file retrieval section, so 0.6 is used as the threshold to screen out the file observation sections with higher file transfer possibility, that is, the sections where file transfer behavior or long-term observation of file behavior occurs.

[0043] The optimal path represents the optimal path that the corresponding personnel will take when retrieving the target file, and after retrieving the target file, the return path is usually the same as the optimal path; for each person, if the corresponding file retrieval path when retrieving the target file does not overlap with the optimal path, then the non-overlapping file observation section has the possibility of detour to a certain extent. In order to distinguish different path behaviors; further, the amplitudes of different section parameters are set for different behavior sections, specifically: the section code of the optimal travel section is set to the preset optimal section parameter; the section code of the file retrieval section is set to the preset file transfer section parameter; the section code of the suspected detour section is set to the preset detour section parameter; finally, the section codes of each file observation section in the file retrieval path corresponding to each file retrieval process when each person retrieves the target file in the archive room are arranged in path order to obtain a path behavior code sequence. In a specific implementation of an embodiment of the present invention, the preset optimal section parameter is set to 1, the preset gear adjustment section parameter is set to 2, and the preset detour section parameter is set to 0, which can be adjusted according to the specific implementation environment.

[0044] By using a path behavior coding sequence to digitize the path behavior of each archive retrieval process on the archive retrieval path, it is possible to combine the data for comparative analysis when subsequently introducing the behavioral habits of the archive retrieval process, thereby screening out more accurate abnormal archive retrieval processes. In addition, it should be noted that although the optimal path is different from the optimal path imagined by different people, the optimal path for retrieving the same target archive in this application is the same. Its role is to provide a path standard when determining the path behavior coding sequence, so that the resulting path behavior code is more discriminative for different archive retrieval processes, rather than simply screening abnormal archive retrieval processes based on the standard that does not meet the optimal path.

[0045] Step S103: Determine the abnormal possibility of each file retrieval process based on the similarity and overall deviation between each personnel's file retrieval process and each file retrieval process in the historical data; filter out abnormal file retrieval processes based on the abnormal possibility; and visualize the file management information based on the abnormal file retrieval processes.

[0046] For each person, they usually form a certain path behavior habit when selecting the same target file. If in a certain file retrieval process, the path behavior of the corresponding person's file retrieval process is greatly different from the path behavior of other file retrieval processes in the historical data, then it means that the corresponding file retrieval process may have certain problems, and the possibility of it being an abnormal file retrieval process is higher; and the path behavior habit is characterized by the consistency of the path behavior. Therefore, the abnormal possibility of each file retrieval process is further determined based on the similarity and overall deviation in the path behavior coding sequence between each person in each file retrieval process and each file retrieval process in the historical data.

[0047] Preferably, in some possible implementations of the embodiments of the present invention, the process of obtaining the abnormality possibility includes: The DTW distance between the path behavior coding sequence corresponding to each file retrieval process of each personnel in the archive room and the path behavior coding sequence corresponding to each other file retrieval process is negatively correlated to determine the consistency of the corresponding retrieval process; based on the overall similarity of the retrieval process consistency between each file retrieval process and other file retrieval processes, the behavioral contribution of each file retrieval process is determined; specifically, the process of obtaining the behavioral contribution includes: The mean of all retrieval process consistencies corresponding to each file retrieval process when each person retrieves the target file in the archives is taken as the corresponding average process consistency. For each file retrieval process, the larger the mean of the consistency between it and all other file retrieval processes, the more the corresponding file retrieval process conforms to the habit of the corresponding person in retrieving the target file, and the more this file retrieval process can reflect the path behavior habit of the corresponding person in retrieving the target file, the stronger the corresponding behavior contribution. In a specific implementation of an embodiment of the present invention, the process of obtaining the average process consistency is expressed by the formula: ;in, For personnel When retrieving the target file from the archives The average process consistency of the archive retrieval process; For personnel When retrieving the target file from the archives The corresponding path behavior coding sequence in the process of file retrieval and the other The DTW distance between the corresponding path behavior coding sequences in the process of file retrieval; is an exponential function with a natural constant as its base; For personnel When retrieving the target file from the archives The file retrieval process and other The consistency of the retrieval process between the individual file retrieval processes.

[0048] The difference between the mean of the average process consistency of all file retrieval processes of each person and the average process consistency of each file retrieval process is taken as the overall consistency deviation of each file retrieval process; the standard deviation of the average process consistency of all file retrieval processes of each person is taken as the corresponding retrieval habit stability; the deviation score of each file retrieval process is determined based on the product of the retrieval habit stability and the overall consistency deviation.

[0049] First, with regard to the stability of retrieval habits and the overall consistency deviation for obtaining deviation scores, if the average process consistency of the corresponding file retrieval process is closer to the mean of the average process consistency of all file retrieval processes of the person, and the standard deviation of the average process consistency of all file retrieval processes is smaller, then it means that the similarity of the file retrieval process and the retrieval processes in the historical data, that is, the behavioral habits are relatively similar, and the path behavioral characteristics of the file retrieval process of the corresponding person when retrieving the target file are highly similar. At this time, the behavioral habits represented by the corresponding file retrieval process are more accurate, and the corresponding behavioral contribution is greater; therefore, the larger the deviation score, the smaller the behavioral contribution.

[0050] Further, according to the correlation, negative correlation mapping is performed based on the ratio between the deviation score and the average process consistency of each file retrieval process to determine the behavioral contribution of each file retrieval process, and the negative correlation mapping method here is the same as the method of negative correlation mapping of the DTW distance in the embodiment of the present invention, and will not be further elaborated here. In addition, it should be noted that in order to ensure that the calculation results are meaningful, when the embodiment of the present invention performs fractional operations, when the denominator is 0, a parameter adjustment factor greater than 0 is added to the denominator to prevent the denominator from being 0. The value of the parameter adjustment factor is set by the implementer according to the actual situation, and this application does not impose any special restrictions.

[0051] In a specific implementation of the embodiment of the present invention, the process of obtaining the overall consistency deviation is expressed by the formula: ;in, For personnel When retrieving the target file from the archives The overall consistency deviation of the archive retrieval process; For personnel When retrieving the target file from the archives The average process consistency of the archive retrieval process; For personnel The mean of the average process consistency of all archive retrieval processes when retrieving the target archives in the archives room; is the absolute value symbol. The process of obtaining the behavior contribution is expressed as follows: ;in, For personnel When retrieving the target file from the archives The contribution of each behavior in the file retrieval process; For personnel The standard deviation of the average process consistency of all archive retrieval processes when retrieving the target archives in the archives room, that is, the stability of retrieval habits; For personnel When retrieving the target file from the archives The overall consistency deviation of the archive retrieval process; For personnel When retrieving the target file from the archives The average process consistency of the file retrieval process.

[0052] The other file retrieval processes other than the corresponding target retrieval process when each person retrieves the target file in the archive room are used as comparative retrieval processes; the behavioral contribution of each person in each comparative retrieval process is counted; the cumulative value of the behavioral contribution of each person in all comparative retrieval processes is used as the overall contribution of each person; the retrieval process consistency between the target retrieval process and each comparative retrieval process is used as the comparative consistency of each comparative retrieval process; the product of the behavioral contribution and the comparative consistency of each comparative retrieval process is used as the comparative contribution of each comparative retrieval process; the cumulative value of the comparative contribution of each person in all comparative retrieval processes is used as the reference contribution.

[0053] The overall contribution here serves as the denominator, and its role is only to limit the value of the reference contribution so that the value of the obtained abnormal possibility is more reasonable. Therefore, its calculation significance is not further analyzed. As for the reference contribution, the greater the comparative contribution of each comparative retrieval process, the greater the reference degree of the comparative retrieval process in reflecting the behavioral habits of retrieving the target file, that is, the higher the consistency between the target retrieval process and the comparative retrieval process, that is, the higher the credibility of the comparative consistency, the more consistent the retrieval operation of the corresponding target retrieval process is with the behavioral habits of the corresponding personnel in retrieving the target file. Finally, the comparative contribution of all comparative retrieval processes is combined by the cumulative method, so that the greater the reference contribution obtained, the more consistent the path behavior characteristics of the corresponding file retrieval process are with the behavioral habits of the corresponding personnel in retrieving the target file, and the smaller the abnormal possibility is. Therefore, finally, according to the negative correlation mapping value of the ratio between the reference contribution and the overall contribution, the abnormal possibility of the target retrieval process corresponding to each person is determined. The greater the abnormal possibility, the more abnormal the corresponding file retrieval process. In a specific implementation of the embodiment of the present invention, the method for obtaining the abnormality probability through negative correlation mapping is the same as the method for performing negative correlation mapping on the DTW distance in the embodiment of the present invention, and is not further described here.

[0054] In a specific implementation of the embodiment of the present invention, the process of obtaining the abnormality possibility is expressed by the formula: ;in, For personnel When retrieving the target file from the archives The possibility of abnormalities in the file retrieval process; For personnel When retrieving the target file from the archives The first file retrieval process corresponds to The behavioral contribution of each comparison retrieval process; For personnel When retrieving the target file from the archives The overall contribution of each archive retrieval process; For personnel When retrieving the target file from the archives The first file retrieval process corresponds to The consistency of the comparison process, that is, the personnel When retrieving the target file from the archives The file retrieval process and the corresponding The consistency of the retrieval process between the contrasting retrieval processes; For personnel When retrieving the target file from the archives The first file retrieval process corresponds to The comparative contribution of each comparative retrieval process; For personnel When retrieving the target file from the archives The reference contribution of each archive retrieval process; is an exponential function with a natural constant as its base.

[0055] After determining the abnormal possibility of the file retrieval process, further screening of abnormal file retrieval processes is performed. In a specific implementation of an embodiment of the present invention, the acquisition process of abnormal file retrieval processes includes: taking the file retrieval process with an abnormal possibility greater than a preset abnormal threshold as the abnormal file retrieval process; wherein the preset abnormal threshold is set to 0.7, which can be adjusted according to the specific implementation environment, and will not be further elaborated here. When the function performs negative correlation mapping, since the value of the negative correlation mapping must be greater than 0, the value range of the obtained abnormal possibility is limited to 0 to 1. The greater the abnormal possibility, the more abnormal the corresponding file retrieval process. Therefore, the threshold is set to 0.7, so that the abnormal degree of the screened abnormal file retrieval process is greater, making the obtained abnormal file retrieval process more accurate.

[0056] After screening out abnormal file retrieval processes, in order to make the visualization of file management information more intuitive, in a specific implementation method of an embodiment of the present invention, the file retrieval records of the abnormal file retrieval processes are separately displayed in the visualization page, so that the file administrator can respond in time when the abnormal file retrieval processes occur, thereby avoiding the problem of abnormal file retrieval.

[0057] In another specific implementation of the embodiment of the present invention, all abnormal processes of retrieving all files by all personnel in the archives room are counted; and the frequency of abnormal processes of retrieving files by each personnel in each month is counted, and a line graph is constructed for display to determine whether there are problem personnel. No further details will be given here.

[0058] In summary, a data fusion method for visualization platform and physical archive management system first analyzes the similarity between the path behavior of historical data when retrieving archives on the archive observation section and the path behavior of each archive retrieval process on the archive observation section to determine the possibility of file transfer behavior; then, based on the file transfer possibility, the path behavior coding sequence obtained by encoding is made to more accurately quantify the behavioral information of each archive retrieval process; thereby, the abnormal possibility of each archive retrieval process is determined in combination with the overall deviation between the archive retrieval process and historical data in the dimension of file transfer habits; the abnormal process of retrieval of archives screened out based on the abnormal possibility is more accurate, and the corresponding archive management information visualization processing is more accurate, thereby improving the efficiency of tracing when archive problems occur.

[0059] This application also provides a data fusion system for visualization platform and physical archive management system, please refer to Figure 3 , which shows a structural diagram of a data fusion system for a visualization platform and a physical archive management system provided by an embodiment of the present invention. The system includes: a data acquisition and preprocessing module 301, a path behavior encoding module 302 and an archive management information visualization processing module 303.

[0060] The data collection and preprocessing module 301 is used to collect the file retrieval path corresponding to each file retrieval process of each person in the file room when retrieving the target file in the file room from the top-view node diagram of the file room; wherein the file retrieval path includes at least two file observation sections; The path behavior coding module 302 is used to determine the corresponding file transfer possibility based on the similarity of the behavior between each file observation section and the historical observation section when the historical data was retrieved on the corresponding file observation section on the file retrieval path corresponding to each file retrieval process; and determine the path behavior coding sequence of the file retrieval path based on the path optimization status of the file retrieval path and the file transfer possibility of each file observation section; The archive management information visualization processing module 303 is used to determine the abnormal possibility of each archive retrieval process based on the similarity and overall deviation between each personnel in each archive retrieval process and each archive retrieval process in the historical data; screen out abnormal archive retrieval processes based on the abnormal possibility; and perform archive management information visualization processing based on the abnormal archive retrieval processes.

[0061] It should be noted that the system provided in the above embodiment is merely an example of the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device can be divided into different functional modules to complete all or part of the functions described above. In addition, the data fusion system for a visualization platform and a physical archive management system provided in the above embodiment and the data fusion method for a visualization platform and a physical archive management system provided in the above embodiment are based on the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0062] The present application also provides a computer device. Figure 4 , which shows a schematic diagram of the structure of a computer device provided by an embodiment of the present invention, the computer device includes a memory 401, a processor 402, and a computer program 403 stored in the memory 401 and running on the processor 402, wherein when the processor 402 executes the computer program 403, the computer device can execute any one of the data fusion methods for visualization platforms and physical archive management systems introduced above.

[0063] An embodiment of the present application also provides a computer program product. When the computer program product is run on a computer device, the computer device can execute any one of the data fusion methods for visualization platforms and physical archive management systems introduced above.

[0064] An embodiment of the present application also provides a computer-readable storage medium, which stores computer program code. When the computer program code runs on a computer device, the computer device can execute any of the data fusion methods for visualization platforms and physical archive management systems introduced above.

[0065] In the embodiments provided in the present application, it should be understood that the provided computer devices, computer program products and computer-readable storage media are all used to execute the corresponding methods provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the methods provided above and will not be repeated here.

[0066] It should be noted that the order in which the embodiments of the present invention are described above is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0067] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

Claims

1. A data fusion method for a visualization platform and a physical archive management system, characterized in that: The method comprises: In the archive room bird's-eye view node diagram, the archive retrieval path corresponding to each archive retrieval process when each person retrieves the target archive in the archive room is collected; wherein the archive retrieval path includes at least two archive observation sections; On the file retrieval path corresponding to each file retrieval process, the corresponding file transfer possibility is determined based on the similarity of the travel behavior between each file observation section and the historical observation section when the historical data was retrieved on the corresponding file observation section; based on the path optimization of the file retrieval path and the file transfer possibility of each file observation section, the path behavior coding sequence of the file retrieval path is determined; Based on the similarity and overall deviation in the path behavior coding sequence between each personnel in each file retrieval process and each retrieval process in the historical data, the abnormal possibility of each file retrieval process is determined; the abnormal file retrieval process is screened out according to the abnormal possibility; and the file management information is visualized based on the abnormal file retrieval process.

2. The data fusion method for a visualization platform and a physical archive management system according to claim 1, characterized in that: The process of obtaining the possibility of file transfer includes: A rectangular coordinate system is constructed with the lower left corner of the thumbnail of the archive room viewed from above as the origin, the horizontal rightward direction as the x-axis direction, and the vertical upward direction as the y-axis direction; the rectangular coordinate system is converted into a polar coordinate system; in each archive retrieval process, on the corresponding archive retrieval path, the polar angles of each archive observation section in the polar coordinate system at all sampling moments are arranged in chronological order to obtain a corresponding travel polar angle sequence; the polar diameters of each archive observation section in the polar coordinate system at all sampling moments are arranged in chronological order to obtain a corresponding travel polar diameter sequence; Each file retrieval process when each person retrieves the target file is taken as the target retrieval process; each file observation section in the target retrieval process is taken as the target observation section; in the historical data of all personnel, all file retrieval processes for file retrieval operations on the section corresponding to the target observation section are taken as reference retrieval processes; Under the target observation section, determining a reference similarity between the target retrieval process and each reference retrieval process under the target observation section based on similarities between the target retrieval process and each reference retrieval process in corresponding travel polar angle sequences, travel polar diameter sequences, and travel time lengths; According to the numerical distribution of the reference similarity corresponding to the target retrieval process, the possibility of shifting gears on the target observation section corresponding to the target retrieval process is determined.

3. The data fusion method for a visualization platform and a physical archive management system according to claim 2, characterized in that: The process of obtaining the reference similarity includes: Based on the dynamic time warping algorithm, the DTW distance between the polar angle sequence of the target observation section in the target retrieval process and the corresponding polar angle sequence in the reference retrieval process is negatively correlated to obtain the corresponding polar angle sequence similarity; Performing a negative correlation mapping on the DTW distance between the travel path sequence of the target observation section in the target retrieval process and the corresponding travel path sequence in the reference retrieval process to obtain the corresponding path sequence similarity; The difference between the total number of sampling moments of the target observation section in the target retrieval process and the total number of sampling moments in the reference retrieval process is used to obtain the corresponding time length similarity; A corresponding reference similarity is determined according to a normalized value of an average value among the polar angle sequence similarity, the polar diameter sequence similarity, and the time length similarity.

4. The data fusion method for a visualization platform and a physical archive management system according to claim 2, characterized in that: The process of determining the possibility of shifting on the target observation section corresponding to the target retrieval process according to the numerical distribution of the reference similarity corresponding to the target retrieval process includes: The maximum value of the reference similarity corresponding to the target retrieval process is used as the possibility of file transfer on the target observation section on the file retrieval path corresponding to the target retrieval process.

5. The data fusion method for a visualization platform and a physical archive management system according to claim 1, characterized in that: The process of obtaining the path behavior coding sequence includes: Determine the optimal path for each person to retrieve the required files in each file retrieval process when retrieving the target files through a path search algorithm; The file observation section corresponding to the overlap between the file retrieval path and the optimal path in each file retrieval process of each person when retrieving the target file is used as the optimal travel section; the file observation section with a file retrieval probability greater than a preset probability threshold is used as the file retrieval section; the other file observation sections other than the optimal travel section and the file retrieval section are used as suspected detour sections; The section code of the optimal traveling section is set as the preset optimal section parameter; the section code of the file retrieval section is set as the preset file retrieval section parameter; the section code of the suspected detour section is set as the preset detour section parameter; The section codes of each archive observation section in the archive retrieval path corresponding to each archive retrieval process when each person retrieves the target archive in the archive room are arranged in path order to obtain a path behavior code sequence.

6. The data fusion method for a visualization platform and a physical archive management system according to claim 2, characterized in that: The process of obtaining the abnormal possibility includes: The DTW distance between the path behavior coding sequence corresponding to each file retrieval process of each person in the archive room and the path behavior coding sequence corresponding to each other file retrieval process is negatively correlated to determine the consistency of the corresponding retrieval process; Determine the behavioral contribution of each archive retrieval process based on the overall similarity of the retrieval process consistency between each archive retrieval process and other archive retrieval processes; The other file retrieval processes other than the corresponding target retrieval process when each person retrieves the target file in the archive room are used as comparative retrieval processes; the behavioral contribution of each person in each comparative retrieval process is calculated; the cumulative value of the behavioral contribution of each person in all comparative retrieval processes is used as the overall contribution of each person; The consistency of the retrieval process between the target retrieval process and each comparison retrieval process is used as the comparison consistency of each comparison retrieval process; the product of the behavioral contribution of each comparison retrieval process and the comparison consistency is used as the comparison contribution of each comparison retrieval process; the cumulative value of the comparison contribution of each person in all comparison retrieval processes is used as the reference contribution; The abnormal possibility of the target retrieval process corresponding to each person is determined according to the negative correlation mapping value of the ratio between the reference contribution and the overall contribution.

7. The data fusion method for a visualization platform and a physical archive management system according to claim 6, characterized in that: The process of obtaining the behavior contribution includes: The mean of all retrieval process consistencies corresponding to each file retrieval process when each person retrieves the target file in the archive room is taken as the corresponding average process consistency; The difference between the mean of the average process consistency of all file retrieval processes for each person and the average process consistency of each file retrieval process is used as the overall consistency deviation of each file retrieval process; the standard deviation of the average process consistency of all file retrieval processes for each person is used as the corresponding retrieval habit stability; the deviation score of each file retrieval process is determined based on the product of the retrieval habit stability and the overall consistency deviation; A negative correlation mapping is performed based on the ratio between the deviation score and the average process consistency of each archive retrieval process to determine the behavioral contribution of each archive retrieval process.

8. The data fusion method for a visualization platform and a physical archive management system according to claim 1 is characterized in that: The acquisition process of the abnormal process of retrieving files includes: The file retrieval process with an abnormal probability greater than the preset abnormality threshold is regarded as an abnormal file retrieval process.

9. The data fusion method for a visualization platform and a physical archive management system according to claim 1, characterized in that: The process of visualizing archive management information according to the abnormal process of retrieving archives includes: The archive retrieval records of abnormal archive retrieval processes are displayed separately on the visualization page.

10. The data fusion method for visualization platform and entity archive management system according to claim 5, characterized in that: The path search algorithm adopts the A-star algorithm.

Images