A file management system using intelligent robots

Abstract

The present invention discloses an archive management system using an intelligent robot, which relates to the field of robot archive management, and includes: a coordinate modeling module, which is used to establish a three-dimensional coordinate system model according to the actual situation of the archive room; an archive classification module, which is used to classify and identify archives, and establish a classification identification list; an archive access module, which is used to extract and confirm the accessed archive information based on a decision tree model; a guiding robot module, which is used to guide the intelligent robot to reach the location of the archive cabinet to be accessed according to the digital three-dimensional coordinate system model, and to make an abnormal prompt; a platform processing module, which is used to establish a visualization platform, which is used to display and record the access information and abnormal prompt information of the archive. The advantages of the present invention are: the intelligent robot is used to realize automatic access to archives and identification of abnormal access, thereby effectively improving the efficiency, safety and intelligence of archive management.

Description

Technical Field

[0001] The present invention relates to the field of robot file management, and in particular to a file management system using an intelligent robot. Background Art

[0002] Archives are authentic records of history and important carriers of cultural heritage, involving all aspects of the country, society and individuals. Protecting the integrity and authenticity of archives is of great significance, and archive management is an important means to ensure the long-term preservation of archival information. With the rapid development of intelligent robot technology, the use of intelligent robots to replace traditional manual management has gradually received widespread attention. The use of intelligent robots can effectively improve the management capabilities of archive management in data collection, efficiency improvement, security, and standardization and intelligence of archive access.

[0003] Existing technologies mainly use robotic devices to organize and clean archives, or provide guidance through human-computer interaction interfaces, but these technologies require human participation in the storage and access of archives, making the recording of archive access data, the search of archives, and the security of archives complicated and difficult. The lack of a systematic, standardized, and intelligent archive management process leads to low efficiency in archive management, high labor costs, and low security, which is not conducive to the long-term development and storage of archive management. Summary of the invention

[0004] In order to solve the above-mentioned technical problems, an archive management system using an intelligent robot is provided. The technical solution solves the problem that the technologies proposed in the above-mentioned background technologies require human participation in the access of archives, making the recording of archive access data, the search of archives and the security of archives complicated and difficult. There is a lack of systematic, standardized and intelligent archive management processes, resulting in low efficiency of archive management, high labor costs and low security, which is not conducive to the long-term development and storage of archive management.

[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is:

[0006] A file management system using an intelligent robot, comprising:

[0007] A coordinate modeling module, which is used to establish a three-dimensional coordinate system model according to the actual situation of the archive room;

[0008] An archive classification module, which is used to classify and identify archives according to archive classification requirements and to establish a classification identification list;

[0009] An archive access module, which is used to extract and confirm the accessed archive information based on a decision tree model;

[0010] A guiding robot module, which is used to guide the intelligent robot to reach the location of the file cabinet to be accessed according to the digital three-dimensional coordinate system model, and to give a prompt whether there is any abnormality;

[0011] The platform processing module is used to establish a visualization platform for displaying and recording file access information and abnormal prompt information.

[0012] Preferably, the step of establishing a three-dimensional coordinate system model according to the actual situation of the archive room specifically includes:

[0013] Obtain spatial information of the archive room, including length, width, height, placement information of filing cabinets and other items;

[0014] Get the information of the filing cabinet, including length, height, width and file placement information;

[0015] Get aisle information, including aisle spacing and number of aisles;

[0016] Based on UWB positioning method, obtain the location information of the intelligent robot;

[0017] A three-dimensional coordinate system model is established based on the spatial information of the archive room, the filing cabinet information, the aisle information and the position information of the robot;

[0018] According to the corresponding proportional relationship between the model's three-dimensional coordinate system and the actual position, the model is digitized for robot recognition;

[0019] The UWB positioning method is expressed as: ; In the formula, v is the propagation speed of the pulse signal measured by the UWB base station, which is a fixed value, and t is the total round-trip propagation time of the pulse signal measured by the UWB base station. They are the fixed position information of the UWB base station in three directions. The intersection of the circular radii of the pulse signals measured in three directions is the actual position information of the intelligent robot.

[0020] Preferably, the archive access module specifically includes:

[0021] A sample set unit, the sample set unit is used to prepare a file classification training sample set of a decision tree according to a file classification information database, wherein the file classification information category is used as a feature item and the number is used as a result item;

[0022] A Gini index determination unit is used to calculate the Gini indexes of different categories under the same archive category based on the archive classification training sample set and the Gini index algorithm; based on the Gini indexes of different categories under the same archive category, calculate the Gini index under a certain category respectively;

[0023] A screening numbering unit, which is used to establish a decision tree model based on the Gini index algorithm, and screen out the most suitable file number by inputting corresponding feature items according to the learning and training of the file classification training sample set in the early stage of the model;

[0024] A new file classification unit is used to filter out the storage location information of the filing cabinet that is closest to the new file information that has not been entered through a decision tree model.

[0025] Preferably, the expression for calculating the Gini index of different categories under the same archive category specifically includes:

[0026] ; In the formula, is the Gini index of different classifications under the same file category and the training sample set D, is the number of sample groups of the kth classification in the training sample set D, D is the number of sample groups in the training sample set, n is the number of different classifications under the same file category in the training sample set, and k is the number of different classifications under the same file category in the training sample set;

[0027] The Gini index expression calculated under a certain classification is:

[0028] ; In the formula, is the Gini index of category i under archive category A, i is the i-th category under archive category A, is the number of sample groups of the ith classification, is the total number of remaining sample groups after removing the i-th classification sample group, is the Gini index of the ith category under archive category A, It is the total Gini index of the remaining categories under archive category A excluding the i-th category.

[0029] Preferably, the guiding robot module specifically includes:

[0030] A file location confirmation unit, which is used to guide the intelligent robot to reach the location of the file cabinet to be accessed by querying the location information of the file number in the digital three-dimensional coordinate system model based on the file number information obtained by the decision tree model;

[0031] The access position abnormality unit is used to compare the number information of the file to be accessed with the RFID tag that has arrived at the designated file cabinet position to determine whether the information is the same. If so, it means that the file and the position are accurate. If not, it means that there is an abnormality and an abnormality alarm is issued;

[0032] A new file positioning unit is used to screen out the storage location information of the closest filing cabinet to the new file through a decision tree model, and guide the intelligent robot to store the file and record the file storage information based on the vacant location information of the filing cabinet that is not marked in the digital three-dimensional coordinate system model.

[0033] Preferably, the establishment of a visualization platform for displaying and recording archive access information and abnormal prompt information specifically includes:

[0034] Establish a visualization platform to list the coordinates of the archive access information and abnormal prompt information in the form of charts;

[0035] Based on the visualization platform, it is used to display the three-dimensional coordinate system model of the archive room and the marking status in the coordinate system;

[0036] Based on the visualization platform, the storage information of new archives is received and recorded, and the archive classification training sample set in the decision tree model is updated in a timely manner.

[0037] Compared with the prior art, the present invention has the following beneficial effects:

[0038] Based on the analysis of the spatial information of the archive room, the filing cabinet information, the aisle information and the real-time position information of the intelligent robot, a three-dimensional coordinate system model is established. The coordinate point location information of each file is marked through the model to facilitate the intelligent robot to confirm the location of each file and accurately access the files. Secondly, through the decision tree model, the most appropriate file number is screened out according to the input file identification, and the specific location of the accessed file is confirmed through the number and the position information of the three-dimensional coordinate system, thereby realizing automatic access to the files, improving the efficiency of file management and the security of the files, and ensuring the standardization and intelligence of file access. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 This is a flow chart of an archive management system using an intelligent robot according to the present invention;

[0040] Figure 2 The present invention is a flow chart for establishing a three-dimensional coordinate system model according to the actual situation of the archive room;

[0041] Figure 3 A flow chart of extracting and confirming the accessed archive information based on the decision tree model of the present invention;

[0042] Figure 4 The present invention guides the intelligent robot to reach the location of the filing cabinet to be accessed based on the digital three-dimensional coordinate system model and makes a flowchart to indicate whether there is any abnormality. DETAILED DESCRIPTION

[0043] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0044] Reference Figure 1 As shown, a file management system using an intelligent robot includes:

[0045] A coordinate modeling module, which is used to establish a three-dimensional coordinate system model according to the actual situation of the archive room;

[0046] An archive classification module, which is used to classify and identify archives according to archive classification requirements and to establish a classification identification list;

[0047] An archive access module, which is used to extract and confirm the accessed archive information based on a decision tree model;

[0048] A guiding robot module, which is used to guide the intelligent robot to reach the location of the file cabinet to be accessed according to the digital three-dimensional coordinate system model, and to give a prompt whether there is any abnormality;

[0049] The platform processing module is used to establish a visualization platform for displaying and recording file access information and abnormal prompt information.

[0050] Reference Figure 1 As shown, the file access module specifically includes:

[0051] A sample set unit, the sample set unit is used to prepare a file classification training sample set of a decision tree according to a file classification information database, wherein the file classification information category is used as a feature item and the number is used as a result item;

[0052] A Gini index determination unit is used to calculate the Gini indexes of different categories under the same archive category based on the archive classification training sample set and the Gini index algorithm; based on the Gini indexes of different categories under the same archive category, calculate the Gini index under a certain category respectively;

[0053] A screening numbering unit, which is used to establish a decision tree model based on the Gini index algorithm, and screen out the most suitable file number by inputting corresponding feature items according to the learning and training of the file classification training sample set in the early stage of the model;

[0054] A new file classification unit is used to filter out the storage location information of the filing cabinet that is closest to the new file information that has not been entered through a decision tree model.

[0055] Reference Figure 1 As shown, the guiding robot module specifically includes:

[0056] A file location confirmation unit, which is used to guide the intelligent robot to reach the location of the file cabinet to be accessed by querying the location information of the file number in the digital three-dimensional coordinate system model based on the file number information obtained by the decision tree model;

[0057] The access position abnormality unit is used to compare the number information of the file to be accessed with the RFID tag that has arrived at the designated file cabinet position to determine whether the information is the same. If so, it means that the file and the position are accurate. If not, it means that there is an abnormality and an abnormality alarm is issued;

[0058] A new file positioning unit is used to screen out the storage location information of the closest filing cabinet to the new file through a decision tree model, and guide the intelligent robot to store the file and record the file storage information based on the vacant location information of the filing cabinet that is not marked in the digital three-dimensional coordinate system model.

[0059] It can be explained that this solution establishes a three-dimensional coordinate system model by analyzing the spatial information of the archive room, the filing cabinet information and the aisle information, and marks the coordinate point location information of each file through the model, so as to facilitate the intelligent robot to confirm the location of each file and accurately access the files. Secondly, through the decision tree model, the most appropriate file number is screened out according to the input file identification, and the specific location of the accessed file is confirmed through the number and the location information of the three-dimensional coordinate system, thereby realizing automatic access to the files.

[0060] Reference Figure 2 As shown, the establishment of a three-dimensional coordinate system model according to the actual situation of the archive room specifically includes:

[0061] Obtain the spatial information of the archive room, including length, width, height, placement information of filing cabinets and other items;

[0062] Get the information of the filing cabinet, including length, height, width and file placement information;

[0063] Get aisle information, including aisle spacing and number of aisles;

[0064] Based on UWB positioning method, obtain the location information of the intelligent robot;

[0065] A three-dimensional coordinate system model is established based on the spatial information of the archive room, the filing cabinet information, the aisle information and the position information of the robot;

[0066] According to the corresponding proportional relationship between the model's three-dimensional coordinate system and the actual position, the model is digitized for robot recognition;

[0067] The UWB positioning method is expressed as: ; In the formula, v is the propagation speed of the pulse signal measured by the UWB base station, which is a fixed value, and t is the total round-trip propagation time of the pulse signal measured by the UWB base station. They are the fixed position information of the UWB base station in three directions. The intersection of the circular radii of the pulse signals measured in three directions is the actual position information of the intelligent robot.

[0068] It can be explained that the actual archive room space information, archive cabinet information, aisle information and robot position information are mapped into the three-dimensional coordinate system model using the three-dimensional coordinate system. The two-dimensional plane coordinate information of the axis can guide the direction and distance of the intelligent robot's walking on the ground. The specific location of each file cabinet is marked in the digital three-dimensional coordinate system model, and the file location information on the z-axis is mapped to The robot is guided to reach the axis in the two-dimensional plane through the digital three-dimensional coordinate system model. The UWB positioning method is to establish three fixed base stations in different directions, use the base station to measure the time spent by the pulse signal in the round trip, calculate the relative propagation distance of the measured pulse signal, and make a circular trajectory with the relative propagation distance as the radius to find the intersection of the three running trajectories, and this intersection is the position information of the intelligent robot. This method can improve the stability and accuracy of the indoor positioning of the intelligent robot, has a certain anti-interference ability, and can ensure that the intelligent robot accurately reaches the designated position.

[0069] Reference Figure 3 As shown, the extraction and confirmation of the accessed archive information based on the decision tree model specifically includes:

[0070] According to the archive classification information database, a sample set of archive classification training for the decision tree is prepared, wherein the archive classification information category is used as a feature item and the number is used as a result item;

[0071] According to the archive classification training sample set, based on the damping index algorithm, the Gini index of different classifications under the same archive category is calculated;

[0072] Based on the Gini index of different classifications under the same archive category, calculate the Gini index under a certain classification respectively;

[0073] Based on the Gini index algorithm, a decision tree model is established. According to the model's previous learning and training of the archive classification training sample set, the most suitable archive number is screened out by inputting the corresponding feature items;

[0074] For new file information that has not been entered, the decision tree model is used to filter out the storage location information of the filing cabinet that is closest to it.

[0075] The expression for calculating the Gini index of different categories under the same archive category specifically includes:

[0076] ; In the formula, is the Gini index of different classifications under the same file category and the training sample set D, is the number of sample groups of the kth classification in the training sample set D, D is the number of sample groups in the training sample set, n is the number of different classifications under the same file category in the training sample set, and k is the number of different classifications under the same file category in the training sample set;

[0077] The Gini index expression calculated under a certain classification is:

[0078] ; In the formula, is the Gini index of category i under archive category A, i is the i-th category under archive category A, is the number of sample groups of the ith classification, is the total number of remaining sample groups after removing the i-th classification sample group, is the Gini index of the ith category under archive category A, It is the total Gini index of the remaining categories under archive category A excluding the i-th category.

[0079] It can be explained that by extracting archive classification identification information, the archive classification training sample set of the decision tree is established to train the decision tree model. Since it is necessary to ensure the accuracy of the corresponding archive information and the stability of archive access, the training sample set needs to be trained in an all-round way. Secondly, compared with information gain, the binary tree classification method of the Gini index is more suitable for the decision tree model. The binary tree branch of the Gini index divides the archive category classification into one category and all classification sets except this category. This method is more suitable and more effective for classification with fixed archive classification identification.

[0080] Reference Figure 4 As shown, the method of guiding the intelligent robot to reach the location of the file cabinet to be accessed based on the digital three-dimensional coordinate system model and providing a prompt whether there is an abnormality specifically includes:

[0081] According to the file number information obtained by the decision tree model, the intelligent robot is guided to the location of the file cabinet to be accessed by querying the location information of the number in the digital three-dimensional coordinate system model;

[0082] Compare the serial number information of the file to be accessed with the RFID tag that has arrived at the designated filing cabinet location to determine whether the information is the same. If so, it means that the file and location are accurate. If not, it means that there is an abnormality and an abnormality alarm is issued;

[0083] For new archives, the decision tree model is used to screen out the storage location information of the filing cabinet that is closest to it, and based on the vacant location information of the filing cabinet that is not marked in the digital three-dimensional coordinate system model, the intelligent robot is guided to store the archives and record the archive storage information.

[0084] It can be explained that the principle of the intelligent robot to store and locate archives is to establish a digital three-dimensional coordinate system model, determine the robot's movement distance and direction according to the robot's walking speed and walking time through the proportional relationship between the digital three-dimensional coordinate system model and the actual archive room space distance, and thus guide the robot to reach the location coordinates corresponding to the archive to be accessed. Among them, the walking of the intelligent robot is a uniform speed process. Secondly, through RFID tag technology, when the intelligent robot reaches the archive location, When the two-dimensional plane position of the axis is detected, the file information in the z-axis direction is received, thereby realizing the intelligent robot's access to the files in the three-dimensional direction. Among them, the RFID tag technology is composed of coupling elements and chips. Each tag has a unique electronic code and a storage space that can be written by the user. When the RFID tag enters the radio frequency field of the intelligent robot reader, the tag antenna will receive the radio frequency signal and generate an induced current, thereby activating the tag chip, so that the file information recorded in the chip is received by the reader to realize the identification of the file information.

[0085] In summary, the advantages of the present invention are: by analyzing the spatial information, filing cabinet information and aisle information of the archive room, a three-dimensional coordinate system model is established, and the coordinate point position information of each file is marked through the model, so as to facilitate the intelligent robot to confirm the position of each file and accurately access the files. Secondly, through the decision tree model, the most appropriate file number is screened out according to the input file identification, and the specific location of the accessed file is confirmed through the number and the position information of the three-dimensional coordinate system, thereby realizing automatic access to the files, improving the efficiency of file management and the security of the files, and ensuring the standardization and intelligence of file access.

[0086] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

Claims

1. A file management system using an intelligent robot, characterized in that: include: A coordinate modeling module, which is used to establish a three-dimensional coordinate system model according to the actual situation of the archive room; An archive classification module, which is used to classify and identify archives according to archive classification requirements and to establish a classification identification list; An archive access module, which is used to extract and confirm the accessed archive information based on a decision tree model; A guiding robot module, which is used to guide the intelligent robot to reach the location of the file cabinet to be accessed according to the digital three-dimensional coordinate system model, and to give a prompt whether there is any abnormality; A platform processing module, which is used to establish a visualization platform for displaying and recording file access information and abnormal prompt information; The file access module specifically includes: A sample set unit, the sample set unit is used to prepare a file classification training sample set of a decision tree according to a file classification information database, wherein the file classification information category is used as a feature item and the number is used as a result item; A Gini index determination unit is used to calculate the Gini indexes of different categories under the same archive category based on the archive classification training sample set and the Gini index algorithm; based on the Gini indexes of different categories under the same archive category, calculate the Gini index under a certain category respectively; A screening numbering unit, which is used to establish a decision tree model based on the Gini index algorithm, and screen out the most suitable file number by inputting corresponding feature items according to the learning and training of the file classification training sample set in the early stage of the model; A new file classification unit, which is used to filter out the storage location information of the closest filing cabinet to the new file information that has not been entered through a decision tree model; The expression for calculating the Gini index of different categories under the same archive category specifically includes: In the formula, For the training sample set and the Gini index of different classifications under the same file category, For the Classification in the training sample set The number of sample groups in is the number of sample groups in the training sample set, is the number of different classifications under the same file category in the training sample set, Different classifications of the same file category in the training sample set; The Gini index expression calculated under a certain classification is: In the formula, For the archive category Category under The Gini index, For the archive category The next categories, For the The number of sample groups for each classification, To remove the The total number of remaining sample groups of classified sample groups, For the archive category The next The Gini index of the categories is For the archive category Remove the following The total Gini index of the remaining categories.

2. The file management system using an intelligent robot according to claim 1, characterized in that: According to the actual situation of the archive room, establishing a three-dimensional coordinate system model specifically includes: Obtain spatial information of the archive room, including length, width, height, placement information of filing cabinets and other items; Get the information of the filing cabinet, including length, height, width and file placement information; Get aisle information, including aisle spacing and number of aisles; Based on UWB positioning method, obtain the location information of the intelligent robot; A three-dimensional coordinate system model is established based on the spatial information of the archive room, the filing cabinet information, the aisle information and the position information of the robot; According to the corresponding proportional relationship between the model's three-dimensional coordinate system and the actual position, the model is digitized for robot recognition; The UWB positioning method is expressed as: In the formula, The propagation speed of the pulse signal measured for the UWB base station is a fixed value. , , They are the fixed position information of the UWB base station in three directions. The intersection of the circular radii of the pulse signals measured in three directions is the actual position information of the intelligent robot.

3. The file management system using an intelligent robot according to claim 2, characterized in that: According to the requirements for archive classification, archives are classified and marked, and an archive classification list is established, which specifically includes: According to the requirements of archive classification, archives are classified and the classified archives are marked and recorded through RFID tag technology; Collect classified information of archives, number the classified and marked archives, and establish an archive classification information database; Based on the digital three-dimensional coordinate system model, the placement information of the marked files in the filing cabinet is marked in the three-dimensional coordinate system model by one-to-one correspondence with the coordinate points in the coordinate system.

4. The file management system using an intelligent robot according to claim 3, characterized in that: The guiding robot module specifically includes: A file location confirmation unit, which is used to guide the intelligent robot to reach the location of the file cabinet to be accessed by querying the location information of the file number in the digital three-dimensional coordinate system model based on the file number information obtained by the decision tree model; The access position abnormality unit is used to compare the number information of the file to be accessed with the RFID tag that has arrived at the designated file cabinet position to determine whether the information is the same. If so, it means that the file and the position are accurate. If not, it means that there is an abnormality and an abnormality alarm is issued; A new file positioning unit is used to screen out the storage location information of the closest filing cabinet to the new file through a decision tree model, and guide the intelligent robot to store the file and record the file storage information based on the vacant location information of the filing cabinet that is not marked in the digital three-dimensional coordinate system model.

5. The file management system using an intelligent robot according to claim 4, characterized in that: The establishment of a visualization platform for displaying and recording archive access information and abnormal prompt information specifically includes: Establish a visualization platform to list the coordinates of the archive access information and abnormal prompt information in the form of charts; Based on the visualization platform, it is used to display the three-dimensional coordinate system model of the archive room and the marking status in the coordinate system; Based on the visualization platform, the storage information of new archives is received and recorded, and the archive classification training sample set in the decision tree model is updated in a timely manner.

Images