File data management system of law enforcement recorder

Abstract

The invention belongs to the technical field of data transmission, and discloses a file data management system of a law enforcement recorder. Comprising a data acquisition module used for acquiring law enforcement record data; the priority division module is used for performing priority division on the law enforcement record data; the data compression module is used for carrying out compression processing on the law enforcement record data to obtain law enforcement compressed data and carrying out data transmission based on the corresponding priority; the data collection module is used for collecting network characteristic data in real time during data transmission; the efficiency adjusting module is used for dynamically adjusting the data transmission efficiency according to the network characteristic data; the breakpoint transmission continuing module is used for storing the transmission progress when the data transmission is interrupted and continuing the data transmission when the data transmission is recovered; according to the invention, the transmission efficiency and reliability of the law enforcement record data can be obviously improved, so that the effectiveness and credibility of law enforcement activities are ensured, and efficient and stable technical guarantee is provided for data management of the law enforcement recorder.

Description

Technical Field

[0001] The present invention relates to the technical field of data transmission, and more specifically, to a file data management system for a law enforcement recorder. Background Art

[0002] In modern law enforcement activities, law enforcement recorders are an important tool for law enforcement personnel to perform their duties and are widely used to record audio and video data during the law enforcement process. These data are not only of great significance in the evidence collection and review of law enforcement behavior, but can also be used in judicial proceedings, case analysis and law enforcement supervision. However, with the frequent law enforcement activities, file data management also faces many challenges, such as the sharp increase in data volume, low data transmission efficiency, data loss and other issues. Therefore, how to efficiently manage these data has become a problem that needs to be solved.

[0003] The patent with publication number CN107196992A discloses a file data management system for law enforcement recorders; it includes: a data acquisition module, a storage management module and a comprehensive information management module, the storage management module is used to receive and distribute the file data, generate file index information according to the file data, send the file index information to the comprehensive information management module, and also respond to user requests and status information requests sent by the comprehensive information management module; this invention implements centralized and comprehensive management of law enforcement recorder data, supports parallel import of data from multiple recorders, shortens data import time; distributes file data to reduce storage costs of massive data; efficiently retrieves file data stored in the system, and realizes data sharing among different information systems;

[0004] However, the above technology does not effectively optimize the data transmission process. When processing large-scale audio and video data, there are still problems such as low network utilization efficiency, data transmission interruption, and data loss, which leads to low overall data transmission efficiency and insufficient reliability, thereby affecting the effectiveness and credibility of law enforcement recorders at critical moments.

[0005] In view of this, the present invention proposes a file data management system for law enforcement recorders to solve the above problems. Summary of the invention

[0006] In order to overcome the above-mentioned defects of the prior art and to achieve the above-mentioned purpose, the present invention provides the following technical solution: a file data management system for a law enforcement recorder, comprising:

[0007] Data collection module, used to collect law enforcement record data;

[0008] A prioritization module for prioritizing law enforcement record data;

[0009] A data compression module is used to compress law enforcement record data, obtain law enforcement compressed data, and transmit data based on corresponding priorities;

[0010] A data collection module, used to collect network characteristic data in real time during data transmission;

[0011] The efficiency adjustment module dynamically adjusts the data transmission efficiency according to the network characteristic data;

[0012] The breakpoint resume module is used to save the transmission progress when the data transmission is interrupted, and when the data transmission is resumed, the data transmission is continued according to the transmission progress.

[0013] Further, the law enforcement record data includes audio data and video data;

[0014] The method for prioritizing law enforcement record data includes:

[0015] Mark the collected law enforcement record data as the current record data; obtain the law enforcement coordinates corresponding to the current record data, the law enforcement coordinates are the coordinates corresponding to the law enforcement recorder that collects the law enforcement record data; obtain the incident coordinates, the incident coordinates are the coordinates of the location where the law enforcement task occurs; calculate the law enforcement distance corresponding to the current record data based on the law enforcement coordinates and the incident coordinates, and mark it as the current distance; the expression of the current distance is: ; In the formula, is the current distance, is the radius of the Earth, is the latitude of the enforcement coordinates, is the latitude of the coordinates of the incident, is the longitude of the enforcement coordinates, is the longitude of the coordinates of the incident;

[0016] Obtain the remaining distances, which include multiple law enforcement distances, each of which corresponds to a law enforcement record data, and the law enforcement record data corresponding to each law enforcement distance in the remaining distances corresponds to the same law enforcement task as the current record data;

[0017] Sort the real-time distance and other distances from small to large to generate a sorting table. The positive order of the sorting table is the priority of the law enforcement record data corresponding to each law enforcement distance.

[0018] Furthermore, the method for obtaining law enforcement compressed data includes:

[0019] Compressing the audio data in the law enforcement record data to obtain audio compression data; compressing the video data in the law enforcement record data to obtain video compression data; using the audio compression data and the video compression data as law enforcement compression data;

[0020] The method for obtaining audio compression data comprises:

[0021] The audio data is divided into blocks according to the preset block size, each block contains Audio sample values, is an integer greater than 1; calculating the average sampling value corresponding to each block; subtracting the corresponding average sampling value from the audio sampling value in each block to obtain the sampling difference value corresponding to each audio sampling value; replacing the audio sampling value in each block with the corresponding sampling difference value;

[0022] Preset prediction order ; The first The first sampling difference is marked as the sample value, and the remaining sampling difference is marked as the value to be predicted; according to the sample value in each block, the predicted value corresponding to the first value to be predicted in each block is predicted; the first sample value corresponding to each block is replaced with the first value to be predicted, and the predicted value corresponding to the second value to be predicted in each block is predicted; and so on, the predicted value corresponding to each value to be predicted in each block is predicted, that is, the predicted value corresponding to each value to be predicted is based on the previous The sampling difference is used for prediction and acquisition;

[0023] Subtract the corresponding prediction value from each value to be predicted to obtain the prediction error corresponding to each value to be predicted; replace the value to be predicted in each block with the corresponding prediction error; quantize the prediction error in each block and calculate the quantization value corresponding to each prediction error; replace the prediction error in each block with the corresponding quantization value; perform entropy coding on the quantization value in each block to obtain the code corresponding to each quantization value; replace the quantization value in each block with the corresponding code, and the codes in all blocks constitute audio compression data.

[0024] Furthermore, the expression of the average sampling value is: ; In the formula, is the average sampling value, For the block Audio sample values, ;

[0025] The expression of the predicted value is: ; In the formula, For the block The predicted value corresponding to the value to be predicted, is the sample value The prediction coefficient corresponding to the sampling difference is For the block The sampling difference, , ;

[0026] The expression of the quantized value is: ; In the formula, For the block A quantitative value, For the block prediction error, To quantify the accuracy, is the floor function.

[0027] Furthermore, the method for obtaining video compression data includes:

[0028] Process the video data by framing and obtain image frames, is an integer greater than 1; intra-frame compression is performed on each image frame to obtain an intra-frame compressed image corresponding to each image frame, wherein the intra-frame compression includes discrete cosine transform, quantization and entropy coding; inter-frame compression is performed on every two adjacent intra-frame compressed images, wherein the inter-frame compression includes motion estimation and differential coding; motion vectors and residual data corresponding to every two adjacent intra-frame compressed images are obtained; the motion vector is the pixel displacement between the two adjacent intra-frame compressed images, and the residual data is the pixel value change between the two adjacent intra-frame compressed images; all the intra-frame compressed images and the motion vectors and residual data corresponding to every two adjacent intra-frame compressed images are used as video compression data.

[0029] Furthermore, the network characteristic data includes network bandwidth, network delay, packet loss rate and jitter;

[0030] The step of dynamically adjusting the data transmission efficiency comprises:

[0031] Step 1: Define the population size m, iteration threshold T and step factor ;

[0032] Step 2: Build the population , population The position of each individual in the population is defined in a one-dimensional search space. The range of the one-dimensional search space is the efficiency range, which is the range of data transmission efficiency. The individual position corresponds to the value in the efficiency range one by one. The corresponding number of iterations t is 0;

[0033] Step 3: Determine the stability function;

[0034] Step 4: Population Divide into subpopulations, each of which includes Individuals, ;

[0035] Step 5: Determine the optimal individuals in each subpopulation and the population The best individual in

[0036] Step 6: Calculate the moving speed of each individual and update the position of each individual;

[0037] Step 7: Determine whether each individual has undergone subpopulation replacement, and re-update the corresponding position of the individual that has undergone subpopulation replacement;

[0038] Step 8: Update the best individuals in each subpopulation and the population The best individual in

[0039] Step 9: Determine whether the number of iterations t is less than the iteration threshold If so, then let , and return to step 6, if not, go to step 10;

[0040] Step 10: According to the population The value corresponding to the optimal individual in the data is used to dynamically adjust the data transmission efficiency.

[0041] Furthermore, in step 2, the population , is the mth individual; The expression for each individual position in is: ; In the formula, is the position of the ith individual, is the random coefficient of the ith individual, , ;

[0042] In step 3, the expression of the stability function is: ; In the formula, For stability, To predict bandwidth utilization, To predict network latency, To predict the packet loss rate, To predict jitter, , , , All are preset weight coefficients; predicted bandwidth utilization is the predicted bandwidth utilization after adjustment for data transmission efficiency; predicted network delay is the predicted network delay after adjustment for data transmission efficiency; predicted packet loss rate is the predicted packet loss rate after adjustment for data transmission efficiency; predicted jitter is the predicted jitter after adjustment for data transmission efficiency;

[0043] The predicted bandwidth utilization, predicted network delay, predicted packet loss rate, and predicted jitter are used as prediction data. The method for obtaining the prediction data includes:

[0044] The numerical values ​​corresponding to the network characteristic data and the individual positions are used as analysis data, and the analysis data is input into the trained network prediction model to predict the corresponding data label. The data label is the digital label corresponding to the predicted data. The predicted data and the digital label correspond one to one, and the corresponding predicted data is obtained according to the data label. The training process of the network prediction model includes:

[0045] Collect q groups of analysis data in advance, set corresponding data labels for the q groups of analysis data, q is an integer greater than 1, and convert the analysis data and the corresponding data labels into a corresponding set of feature vectors; use each set of feature vectors as the input of a network prediction model, the network prediction model uses a set of predicted data labels corresponding to each group of analysis data as output, and uses the actual data labels corresponding to each group of analysis data as prediction targets, the actual data labels are the pre-set data labels corresponding to the analysis data; minimize the sum of prediction errors of all analysis data as a training target; the network prediction model is a deep neural network model.

[0046] Furthermore, in step 4, the population Divide into Methods for subpopulations include:

[0047] Calculate population The stability of each individual in the , and sort them from large to small; set an increasing serial number for each individual in the positive order of sorting, and the serial number range is ;according to sub-populations, perform a modulo operation on the sequence number of each individual to obtain the corresponding sub-sequence number; the expression of the sub-sequence number is: ; In the formula, is the sub-sequence number, is the serial number, is the modulo function; if the sub-sequence number is not 0, the corresponding individual is assigned to the subpopulations; if the subsequence number is 0, the corresponding individual is assigned to the subpopulation;

[0048] In step 5, the optimal individuals and populations in each subpopulation are determined. The method for finding the optimal individual in is as follows: calculate the stability corresponding to each individual, take the individual with the greatest stability in each subpopulation as the optimal individual of the corresponding subpopulation, and mark it as ; The most stable individual among all individuals is regarded as the population The best individual is marked as ;

[0049] In step 6, the method for calculating the moving speed corresponding to each individual includes:

[0050] If the individual is not the optimal individual corresponding to the subpopulation, the expression of the corresponding moving speed is: ; In the formula, is the moving speed of the ith individual, is the position of the best individual in the subpopulation corresponding to the i-th individual, is the position of the ith individual, ;

[0051] If the individual is the optimal individual corresponding to the subpopulation, the expression of the corresponding moving speed is: ; In the formula, For population The position of the best individual in ;

[0052] Methods for updating the location of each individual include:

[0053] If the individual is not the optimal individual corresponding to the subpopulation, the expression of the individual position after update is: ; In the formula, is the position of the i-th individual after update, ;

[0054] If the individual is the optimal individual corresponding to the subpopulation, the expression of the updated individual position is: .

[0055] Furthermore, in step 7, the method for determining whether each individual undergoes subpopulation replacement includes:

[0056] Calculate the stability of each individual after the position update; mark the individuals that are not the best individuals as ordinary individuals, subtract the stability of the best individual in the corresponding subpopulation from the stability of each ordinary individual, and obtain the stability difference corresponding to each ordinary individual; preset the difference threshold, and compare each stability difference with the difference threshold; if the stability difference is less than or equal to the difference threshold, mark the corresponding ordinary individual as a replacement individual; if the stability difference is greater than the difference threshold, do not mark the corresponding ordinary individual;

[0057] Sort the stability of each optimal individual from large to small to generate a stability sorting table; add the stability of each replacement individual to the stability sorting table, obtain the two stabilities before the stability of each replacement individual, and mark them as replacement stability; replace each replacement individual to the subpopulation corresponding to the corresponding replacement stability; if the number of stabilities before the stability of the replacement individual is less than 2, do not replace the subpopulation for the corresponding replacement individual;

[0058] Methods for re-updating the corresponding positions of individuals replaced in the subpopulation include:

[0059] ;

[0060] In the formula, is the position of the i-th individual after re-updating, ;

[0061] In step 8, the optimal individuals and populations in each subpopulation are updated. The method of determining the best individual in each subpopulation and the population in step 5 is the same as The method for the optimal individual in is consistent.

[0062] Furthermore, the grouping time is preset, and the law enforcement compressed data is grouped according to the grouping time to obtain Group law enforcement group data, is an integer greater than 1, and the time length corresponding to each group of law enforcement group data is the group duration; a verification algorithm is used to generate a corresponding verification value for each group of law enforcement group data, and it is marked as a first verification value; each group of law enforcement group data is marked as incomplete, and each group of law enforcement group data marked as incomplete is transmitted in chronological order; when a group of law enforcement group data is transmitted, the corresponding verification value is recalculated and marked as a second verification value; if the first verification value is consistent with the second verification value, the corresponding law enforcement group data is marked as completed; if the first verification value is inconsistent with the second verification value, the corresponding law enforcement group data is still marked as incomplete, and the corresponding law enforcement group data is retransmitted; when data transmission is resumed after interruption, the law enforcement group data marked as incomplete continues to be transmitted.

[0063] Technical effects and advantages of the file data management system of a law enforcement recorder of the present invention:

[0064] By prioritizing law enforcement record data, data transmission can be achieved in a hierarchical manner; high-efficiency audio and video compression technology is used to effectively compress law enforcement record data; swarm intelligence algorithms are used to dynamically adjust data transmission efficiency, and breakpoint-resumption mechanisms are comprehensively applied; key issues such as low network utilization efficiency, data transmission interruptions, and data loss during data transmission are effectively resolved, significantly improving the transmission efficiency and reliability of law enforcement record data, thereby ensuring the effectiveness and credibility of law enforcement activities, and providing efficient and stable technical support for law enforcement recorder data management. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 This is a schematic diagram of a file data management system for a law enforcement recorder according to Embodiment 1 of the present invention;

[0066] Figure 2 This is a flow chart of a method for dynamically adjusting data transmission efficiency according to Embodiment 1 of the present invention. DETAILED DESCRIPTION

[0067] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0068] Example 1

[0069] See also Figure 1 As shown, the file data management system of a law enforcement recorder described in this embodiment includes a data acquisition module, a priority division module, a data compression module, a data collection module, an efficiency adjustment module and a breakpoint continuation module; each module is connected by wired and / or wireless means to realize data transmission between modules.

[0070] Data collection module, used to collect law enforcement record data.

[0071] Law enforcement record data includes audio data and video data; law enforcement record data is the audio and video of the law enforcement scene recorded in real time during the law enforcement process; the audio data is used to record the conversation between law enforcement officers and the parties (including inquiries, questions and answers, and other communication content) and the background sounds at the law enforcement scene (such as traffic sounds, crowd sounds, etc.); video data is used to record the on-site images of law enforcement officers during the law enforcement process, including the entire process of law enforcement; law enforcement record data is obtained through law enforcement recorders; law enforcement record data is not only used for evidence collection and review, but can also play a key role in judicial proceedings, case analysis and law enforcement supervision.

[0072] A prioritization module is used to prioritize law enforcement record data.

[0073] Methods for prioritizing law enforcement record data include:

[0074] Mark the collected law enforcement record data as the current record data; obtain the law enforcement coordinates corresponding to the current record data, the law enforcement coordinates are the coordinates corresponding to the law enforcement recorder that collects the law enforcement record data, and the law enforcement coordinates are obtained through the built-in GPS positioning device of the law enforcement recorder; obtain the coordinates of the incident, the coordinates of the incident are the coordinates of the location where the law enforcement task occurs; the location where the law enforcement task occurs is determined by the law enforcement personnel before performing the law enforcement task, and the coordinates of the incident are obtained by the law enforcement personnel entering the location where the law enforcement task occurs into the map software (such as Google Maps, Amap, etc.); according to the law enforcement coordinates and the coordinates of the incident, calculate the law enforcement distance corresponding to the current record data and mark it as the current distance; the expression of the current distance is: ; In the formula, is the current distance, is the radius of the earth, and this embodiment preferably is 6371 kilometers, is the latitude of the enforcement coordinates, is the latitude of the coordinates of the incident, is the longitude of the enforcement coordinates, is the longitude of the coordinates of the incident;

[0075] Obtain the remaining distances, which include multiple law enforcement distances, each of which corresponds to a law enforcement record data, and the law enforcement record data corresponding to each law enforcement distance in the remaining distances corresponds to the same law enforcement task as the current record data, that is, the law enforcement recorders that collect the law enforcement record data corresponding to each law enforcement distance in the remaining distances are used together with the law enforcement recorder that collects the current record data in the same law enforcement task; it should be noted that the law enforcement recorders used in the same law enforcement task share data, that is, the law enforcement recorder can receive the law enforcement distances calculated by the other law enforcement recorders used in the same law enforcement task;

[0076] Sort the real-time distance and other distances from small to large to generate a sorting table. The positive order of the sorting table is the priority of the law enforcement record data corresponding to each law enforcement distance.

[0077] It should be understood that in some law enforcement tasks (such as multi-department joint law enforcement actions, criminal case investigations, etc.), multiple law enforcement recorders are required to collect law enforcement record data at the same time, and the collected multiple law enforcement record data all need to be transmitted. However, due to bandwidth limitations, when multiple law enforcement recorders transmit law enforcement record data at the same time, network resources will be shared, resulting in data transmission network delays or even data loss. Therefore, it is necessary to prioritize the law enforcement record data and transmit it in stages according to the corresponding priority to ensure the reliable transmission of the law enforcement record data.

[0078] The data compression module is used to compress the law enforcement record data, obtain the law enforcement compressed data, and transmit the data based on the corresponding priority.

[0079] Methods for obtaining law enforcement compressed data include:

[0080] The audio data in the law enforcement record data is compressed to obtain audio compressed data; the video data in the law enforcement record data is compressed to obtain video compressed data; and the audio compressed data and the video compressed data are used as law enforcement compressed data.

[0081] Methods for obtaining audio compression data include:

[0082] The audio data is divided into blocks according to the preset block size, each block contains Audio sample values, is an integer greater than 1, and the block size is preset by those skilled in the art according to actual conditions; the average sampling value corresponding to each block is calculated, and the expression of the average sampling value is: ; In the formula, is the average sampling value, For the block Audio sample values, ; Subtract the corresponding average sampling value from the audio sampling value in each block to obtain the sampling difference value corresponding to each audio sampling value; Replace the audio sampling value in each block with the corresponding sampling difference value.

[0083] Preset prediction order The prediction order is preset by those skilled in the art according to the actual situation; The sampling difference values ​​are marked as sample values, and the remaining sampling difference values ​​are marked as values ​​to be predicted; according to the sample values ​​in each block, the first value to be predicted (i.e., the first value to be predicted) in each block is predicted. The predicted value corresponding to the first sample value (i.e., the first sampling difference value) of each block is replaced by the first value to be predicted, and the second value to be predicted in each block (i.e., the first sampling difference value) is predicted. The predicted value corresponding to each value to be predicted in each block is predicted by analogy, that is, the predicted value corresponding to each value to be predicted is calculated based on the previous The prediction is obtained by sampling difference; the expression of the predicted value is: ; In the formula, For the block The predicted value corresponding to the value to be predicted, is the sample value The prediction coefficient corresponding to the sampling difference is For the block The sampling difference, , The prediction coefficient corresponding to each sampling difference is determined by technicians in this field during the compression process of historical law enforcement record data by minimizing the mean square error.

[0084] Subtract the corresponding prediction value from each value to be predicted to obtain the prediction error corresponding to each value to be predicted; replace the value to be predicted in each block with the corresponding prediction error; quantize the prediction error in each block and calculate the quantized value corresponding to each prediction error; the expression of the quantized value is: ; In the formula, For the block A quantitative value, For the block prediction error, The quantization accuracy is preset by technicians in this field according to the actual situation. To round down the function, ensure that the prediction error after quantization is an integer, so as to facilitate the subsequent entropy coding; replace the prediction error in each block with the corresponding quantization value; perform entropy coding (such as Huffman coding, arithmetic coding, etc.) on the quantization value in each block to obtain the code corresponding to each quantization value; replace the quantization value in each block with the corresponding code, and the codes in all blocks constitute the audio compression data.

[0085] The method of obtaining video compression data includes:

[0086] Process the video data by framing and obtain image frames, is an integer greater than 1; intra-frame compression is performed on each image frame to obtain an intra-frame compressed image corresponding to each image frame, the intra-frame compression includes discrete cosine transform, quantization and entropy coding; inter-frame compression is performed on every two adjacent intra-frame compressed images, and the inter-frame compression includes motion estimation and differential coding; motion vectors and residual data corresponding to every two adjacent intra-frame compressed images are obtained; the motion vector is the pixel displacement between two adjacent intra-frame compressed images, and the residual data is the pixel value change between two adjacent intra-frame compressed images; all intra-frame compressed images and the motion vectors and residual data corresponding to every two adjacent intra-frame compressed images are used as video compression data; it should be noted that discrete cosine transform, quantization, entropy coding, motion estimation and differential coding are all existing technologies and will not be described in detail here.

[0087] The data collection module is used to collect network characteristic data in real time during data transmission.

[0088] Network characteristic data includes network bandwidth, network delay, packet loss rate and jitter.

[0089] Network bandwidth refers to the amount of data that can be transmitted over the network per unit time. Network bandwidth is collected and monitored in real time through SNMP (Simple Network Management Protocol), NetFlow or sFlow on network devices (such as routers and switches). Network bandwidth determines the rate of data transmission. The larger the network bandwidth, the more data can be transmitted per unit time, and vice versa. Therefore, network bandwidth is dynamically monitored to adjust the data transmission rate and avoid network congestion.

[0090] Network delay is the time it takes for law enforcement compressed data to be transmitted from the law enforcement recorder to the data storage server. Network delay is obtained by periodically sending ping commands from the law enforcement recorder to the data storage server and calculating the time difference between the sending time and the receiving time. Network delay directly affects the data transmission response time. The higher the network delay, the slower the data transmission efficiency, which will have a significant impact in real-time applications (such as video streaming, VoIP, etc.). The impact of network delay can be reduced by dynamically adjusting the data transmission efficiency.

[0091] The packet loss rate is the ratio of the data packets lost during the data transmission of law enforcement compressed data to the total transmitted data packets. When the law enforcement recorder sends a ping command regularly, the packet loss rate is obtained by counting the number of lost data packets in the sent data packets and dividing the number of lost data packets by the number of sent data packets. Packet loss will lead to a decrease in data transmission efficiency and cause transmission retries or data integrity problems. Therefore, it is necessary to dynamically adjust the data transmission efficiency to reduce the packet loss rate.

[0092] Jitter is the standard deviation of network delay. When the law enforcement recorder sends a ping command regularly, the standard deviation of all network delays is calculated to obtain the jitter. The greater the jitter, the more unstable the data transmission time will be, affecting the quality of streaming media and real-time applications. Therefore, it is necessary to dynamically adjust the data transmission efficiency to reduce jitter and stabilize the network delay.

[0093] The efficiency adjustment module dynamically adjusts the data transmission efficiency according to the network characteristic data.

[0094] like Figure 2 As shown, the steps of dynamically adjusting the data transmission efficiency include:

[0095] Step 1: Define the population size m, iteration threshold T and step factor ;

[0096] Step 2: Build the population , population The position of each individual in the population is defined in a one-dimensional search space. The range of the one-dimensional search space is the efficiency range, which is the range of data transmission efficiency. The individual position corresponds to the value in the efficiency range one by one. The corresponding number of iterations t is 0;

[0097] Step 3: Determine the stability function;

[0098] Step 4: Population Divide into subpopulations, each of which includes Individuals, ;

[0099] Step 5: Determine the optimal individuals in each subpopulation and the population The best individual in

[0100] Step 6: Calculate the moving speed of each individual and update the position of each individual;

[0101] Step 7: Determine whether each individual has undergone subpopulation replacement, and re-update the corresponding position of the individual that has undergone subpopulation replacement;

[0102] Step 8: Update the best individuals in each subpopulation and the population The best individual in

[0103] Step 9: Determine whether the number of iterations t is less than the iteration threshold If so, then let , and return to step 6, if not, go to step 10;

[0104] Step 10: According to the population The value corresponding to the optimal individual in the data is used to dynamically adjust the data transmission efficiency.

[0105] In step 1 above, the population size m, iteration threshold T and step factor A technician in this field collects multiple sets of different network characteristic data in the process of historically dynamically adjusting the data transmission efficiency; multiple sets of different definition parameters are set for each set of network characteristic data, and the definition parameters are the population size m, the iteration threshold T and the step size factor. ; For the same group of network characteristic data corresponding to different groups of definition parameters, the corresponding data transmission efficiency is obtained through the swarm intelligence algorithm of steps 1 to 10, and the corresponding stability is calculated, and the definition parameters corresponding to the data transmission efficiency with the maximum stability are used as the definition parameters corresponding to the corresponding network characteristic data; and the definition parameters corresponding to multiple groups of different network characteristic data are obtained by analogy; the means of multiple groups of definition parameters (i.e., the population size mean, the iteration threshold mean, and the step factor mean) are used as the population size m, the iteration threshold T, and the step factor defined in step 1 .

[0106] In step 2 above, the population , is the mth individual; The expression for each individual position in is: ; In the formula, is the position of the ith individual, is the random coefficient of the ith individual, , ; The efficiency range is measured and obtained by technicians in this field through network monitoring tools.

[0107] In step 3 above, the expression of the stability function is: ; In the formula, For stability, To predict bandwidth utilization, To predict network latency, To predict the packet loss rate, To predict jitter, , , , are all preset weight coefficients; the specific values ​​of the weight coefficients can be set according to actual conditions, and the weight coefficients reflect the importance of predicted bandwidth utilization, predicted network delay, predicted packet loss rate and predicted jitter to stability in the data transmission process. Technical personnel in this field can preset corresponding weight coefficients according to the actual importance of predicted bandwidth utilization, predicted network delay, predicted packet loss rate and predicted jitter to stability in the data transmission process, so as to accurately evaluate the stability in the data transmission process; the predicted bandwidth utilization is the predicted bandwidth utilization after the data transmission efficiency is adjusted; the predicted network delay is the predicted network delay after the data transmission efficiency is adjusted; the predicted packet loss rate is the predicted packet loss rate after the data transmission efficiency is adjusted; the predicted jitter is the predicted jitter after the data transmission efficiency is adjusted.

[0108] The predicted bandwidth utilization, predicted network delay, predicted packet loss rate, and predicted jitter are used as prediction data. The method for obtaining the prediction data includes:

[0109] The numerical values ​​corresponding to the network characteristic data and the individual positions are used as analysis data, and the analysis data is input into the trained network prediction model to predict the corresponding data labels. The data labels are the digital labels corresponding to the predicted data. The predicted data and the digital labels correspond one to one, and the corresponding predicted data are obtained according to the data labels.

[0110] The training process of the network prediction model includes:

[0111] Collect q groups of analysis data in advance, set corresponding data labels for the q groups of analysis data, q is an integer greater than 1, and convert the analysis data and the corresponding data labels into a corresponding set of feature vectors; the data labels corresponding to the analysis data are determined by a technician in the field of historical dynamic adjustment of data transmission efficiency, collect q groups of analysis data, and adjust the data transmission efficiency according to the data corresponding to the individual position in each group of analysis data under the condition of network characteristic data in each group of analysis data, and perform data transmission, respectively collect prediction data in the data transmission process, and use the corresponding data labels as the data labels of the corresponding analysis data, and sequentially set corresponding data labels for the p groups of analysis data;

[0112] Each set of feature vectors is used as the input of the network prediction model. The network prediction model uses a set of predicted data labels corresponding to each set of analysis data as output, and uses the actual data labels corresponding to each set of analysis data as the prediction target. The actual data labels are pre-set data labels corresponding to the analysis data. The training goal is to minimize the sum of the prediction errors of all analysis data. The calculation formula of the prediction error is: ,in is the prediction error, q is the group number of the eigenvector corresponding to the analysis data, is the predicted data label corresponding to the qth group of analyzed data, is the actual data label corresponding to the qth group of analyzed data; the network prediction model is trained until the sum of the prediction errors reaches convergence and the training is stopped.

[0113] The above network prediction model is specifically a deep neural network model; it includes an input layer, a hidden layer and an output layer; each hidden layer includes multiple neurons, each neuron is connected to the neurons in the next layer, and the connection contains weights, which determine the importance and influence of data transmission in the neural network; an activation function is applied to each neuron between the hidden layer and the output layer, and the activation function introduces nonlinearity, allowing the network to learn more complex patterns and features.

[0114] In step 4 above, the population Divide into Methods for subpopulations include:

[0115] Calculate population The stability of each individual in the , and sort them from large to small; set an increasing serial number for each individual in the positive order of sorting, and the serial number range is ;according to sub-populations, perform a modulo operation on the sequence number of each individual to obtain the corresponding sub-sequence number; the expression of the sub-sequence number is: ; In the formula, is the sub-sequence number, is the serial number, is the modulo function; if the sub-sequence number is not 0, the corresponding individual is assigned to the subpopulations; if the subsequence number is 0, the corresponding individual is assigned to the Subpopulation.

[0116] For example, population Including 3 individuals, divided into 3 sub-populations, due to , so the first individual is assigned to the first subpopulation, because , so the second individual is assigned to the second subpopulation, , so the third individual is assigned to the third subpopulation.

[0117] In step 5 above, determine the optimal individual and population in each subpopulation The method for finding the optimal individual in is as follows: calculate the stability corresponding to each individual, take the individual with the greatest stability in each subpopulation as the optimal individual of the corresponding subpopulation, and mark it as ; The most stable individual among all individuals is regarded as the population The best individual is marked as .

[0118] In the above step 6, the method for calculating the moving speed corresponding to each individual includes:

[0119] If the individual is not the optimal individual corresponding to the subpopulation, the expression of the corresponding moving speed is: ; In the formula, is the moving speed of the ith individual, is the position of the best individual in the subpopulation corresponding to the i-th individual, is the position of the ith individual, ;

[0120] If the individual is the optimal individual corresponding to the subpopulation, the expression of the corresponding moving speed is: ; In the formula, For population The position of the best individual in .

[0121] Methods for updating the location of each individual include:

[0122] If the individual is not the optimal individual corresponding to the subpopulation, the expression of the individual position after update is: ; In the formula, is the position of the i-th individual after update, ;

[0123] If the individual is the optimal individual corresponding to the subpopulation, the expression of the updated individual position is: .

[0124] In the above step 7, the method for determining whether each individual undergoes subpopulation replacement includes:

[0125] Calculate the stability of each individual after the position update; mark the individuals that are not the best individuals as ordinary individuals, subtract the stability of the best individual in the corresponding subpopulation from the stability of each ordinary individual, and obtain the stability difference corresponding to each ordinary individual; preset the difference threshold, which is preset by a person skilled in the art according to actual conditions; compare each stability difference with the difference threshold; if the stability difference is less than or equal to the difference threshold, mark the corresponding ordinary individual as a replacement individual; if the stability difference is greater than the difference threshold, do not mark the corresponding ordinary individual;

[0126] Sort the stability of each optimal individual from large to small to generate a stability sorting table; add the stability of each replacement individual to the stability sorting table, obtain the two stabilities before the stability of each replacement individual, and mark them as replacement stabilities; replace each replacement individual to the subpopulation corresponding to the replacement stability; if the number of stabilities before the stability of the replacement individual is less than 2, do not replace the subpopulation for the corresponding replacement individual.

[0127] Methods for re-updating the corresponding positions of individuals replaced in the subpopulation include:

[0128] ;

[0129] In the formula, is the position of the i-th individual after re-updating, .

[0130] In step 8 above, update the optimal individual in each subpopulation and the population The method of determining the best individual in each subpopulation and the population in step 5 above is the same as The method of the optimal individual in is consistent.

[0131] It should be understood that dynamic adjustment of data transmission efficiency can not only optimize data transmission performance, but also adapt to complex network environments, thereby ensuring the real-time, integrity and security of law enforcement compressed data, and providing strong technical support for law enforcement work.

[0132] The breakpoint resume module is used to save the transmission progress when the data transmission is interrupted, and when the data transmission is resumed, the data transmission is continued according to the transmission progress.

[0133] Preset grouping time, the grouping time is pre-set by technical personnel in the field according to actual conditions; group the law enforcement compressed data according to the grouping time, and obtain Group law enforcement group data, is an integer greater than 1, and the time length corresponding to each group of law enforcement packet data is the group duration; a check algorithm (such as MD5, CRC32, etc.) is used to generate a corresponding check value for each group of law enforcement packet data, and it is marked as the first check value; each group of law enforcement packet data is marked as incomplete, and each group of law enforcement packet data marked as incomplete is transmitted in chronological order; when a group of law enforcement packet data is transmitted, the corresponding check value is recalculated and marked as the second check value; if the first check value is consistent with the second check value, the corresponding law enforcement packet data is marked as completed, indicating that the corresponding law enforcement packet data has not been tampered with or damaged; if the first check value is inconsistent with the second check value, the corresponding law enforcement packet data is still marked as incomplete, and the corresponding law enforcement packet data is retransmitted, indicating that the corresponding law enforcement packet data is erroneous or incomplete and needs to be retransmitted; when data transmission is resumed after interruption, the law enforcement packet data marked as incomplete continues to be transmitted.

[0134] This embodiment realizes data hierarchical transmission by prioritizing law enforcement record data; adopts high-efficiency audio and video compression technology to effectively compress law enforcement record data; uses swarm intelligence algorithm to dynamically adjust data transmission efficiency, and comprehensively applies breakpoint resumption mechanism; effectively solves key problems such as low network utilization efficiency, data transmission interruption, and data loss during data transmission, significantly improves the transmission efficiency and reliability of law enforcement record data, thereby ensuring the effectiveness and credibility of law enforcement activities, and providing efficient and stable technical guarantee for law enforcement recorder data management.

[0135] Example 2

[0136] The present application also provides an electronic device. The electronic device may include one or more processors and one or more memories. The memories store computer-readable codes, and when the computer-readable codes are executed by the one or more processors, the file data management system of the law enforcement recorder as described above may be executed.

[0137] The method or system according to the implementation mode of the present application can also be implemented with the help of the architecture of the electronic device shown in the present application. The electronic device may include a bus, one or more CPUs, ROM, RAM, a communication port connected to a network, input / output, a hard disk, etc. A storage device in the electronic device, such as a ROM or a hard disk, can store a file data management system of a law enforcement recorder provided in the present application. Furthermore, the electronic device may also include a user interface. Of course, the architecture shown in the present application is only exemplary. When implementing different devices, one or more components in the electronic device shown in the present application may be omitted according to actual needs.

[0138] Example 3

[0139] One embodiment of the present application discloses a computer-readable storage medium. Computer-readable instructions are stored on the computer-readable storage medium. When the computer-readable instructions are executed by a processor, a file data management system of a law enforcement recorder according to an embodiment of the present application described with reference to the above figures can be executed. The storage medium includes, but is not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory (cache). Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.

[0140] In addition, according to the implementation of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the present application provides a non-transitory machine-readable storage medium, which stores machine-readable instructions, and the machine-readable instructions can be executed by a processor to execute instructions corresponding to the method steps provided by the present application, for example: a file data management system for law enforcement recorders. When the computer program is executed by a central processing unit (CPU), the above functions defined in the method of the present application are executed.

[0141] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0142] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A file data management system for law enforcement recorders, characterized in that: include: Data collection module, used to collect law enforcement record data; A prioritization module for prioritizing law enforcement record data; A data compression module is used to compress law enforcement record data, obtain law enforcement compressed data, and transmit data based on corresponding priorities; A data collection module, used to collect network characteristic data in real time during data transmission; The efficiency adjustment module dynamically adjusts the data transmission efficiency according to the network characteristic data; The breakpoint resume module is used to save the transmission progress when the data transmission is interrupted, and when the data transmission is resumed, the data transmission is continued according to the transmission progress.

2. According to the file data management system of the law enforcement recorder of claim 1, it is characterized in that: The law enforcement record data includes audio data and video data; The method for prioritizing law enforcement record data includes: Mark the collected law enforcement record data as current record data; Get the law enforcement coordinates corresponding to the current recorded data. The law enforcement coordinates are the coordinates corresponding to the law enforcement recorder that collects the law enforcement record data. Get the incident coordinates. The incident coordinates are the coordinates of the location where the law enforcement task occurred. According to the law enforcement coordinates and the incident coordinates, calculate the law enforcement distance corresponding to the current recorded data and mark it as the current distance. The expression of the current distance is: ; In the formula, is the current distance, is the radius of the Earth, is the latitude of the enforcement coordinates, is the latitude of the coordinates of the incident, is the longitude of the enforcement coordinates, is the longitude of the coordinates of the incident; Obtain the remaining distances, which include multiple law enforcement distances, each of which corresponds to a law enforcement record data, and the law enforcement record data corresponding to each law enforcement distance in the remaining distances corresponds to the same law enforcement task as the current record data; Sort the real-time distance and other distances from small to large to generate a sorting table. The positive order of the sorting table is the priority of the law enforcement record data corresponding to each law enforcement distance.

3. The file data management system of a law enforcement recorder according to claim 2, characterized in that: The method for obtaining law enforcement compressed data comprises: Compressing the audio data in the law enforcement record data to obtain audio compression data; compressing the video data in the law enforcement record data to obtain video compression data; using the audio compression data and the video compression data as law enforcement compression data; The method for obtaining audio compression data comprises: The audio data is divided into blocks according to the preset block size, each block contains Audio sample values, is an integer greater than 1; calculating the average sampling value corresponding to each block; subtracting the corresponding average sampling value from the audio sampling value in each block to obtain the sampling difference value corresponding to each audio sampling value; replacing the audio sampling value in each block with the corresponding sampling difference value; Preset prediction order ; The first The first sampling difference is marked as the sample value, and the remaining sampling difference is marked as the value to be predicted; according to the sample value in each block, the predicted value corresponding to the first value to be predicted in each block is predicted; the first sample value corresponding to each block is replaced with the first value to be predicted, and the predicted value corresponding to the second value to be predicted in each block is predicted; and so on, the predicted value corresponding to each value to be predicted in each block is predicted, that is, the predicted value corresponding to each value to be predicted is based on the previous The sampling difference is used to predict and obtain; Subtract the corresponding prediction value from each value to be predicted to obtain the prediction error corresponding to each value to be predicted; replace the value to be predicted in each block with the corresponding prediction error; quantize the prediction error in each block and calculate the quantization value corresponding to each prediction error; replace the prediction error in each block with the corresponding quantization value; perform entropy coding on the quantization value in each block to obtain the code corresponding to each quantization value; replace the quantization value in each block with the corresponding code, and the codes in all blocks constitute audio compression data.

4. According to the file data management system of the law enforcement recorder of claim 3, it is characterized in that: The expression for the average sample value is: ; In the formula, is the average sampling value, For the block Audio sample values, ; The expression of the predicted value is: ; In the formula, For the block The predicted value corresponding to the value to be predicted, is the sample value The prediction coefficient corresponding to the sampling difference is For the block The sampling difference, , ; The expression of the quantized value is: ; In the formula, For the block A quantitative value, For the block prediction error, To quantify the accuracy, is the floor function.

5. The file data management system of the law enforcement recorder according to claim 4 is characterized in that: The method for obtaining video compression data comprises: Process the video data by framing and obtain image frames, is an integer greater than 1; intra-frame compression is performed on each image frame to obtain an intra-frame compressed image corresponding to each image frame, wherein the intra-frame compression includes discrete cosine transform, quantization and entropy coding; inter-frame compression is performed on every two adjacent intra-frame compressed images, wherein the inter-frame compression includes motion estimation and differential coding; motion vectors and residual data corresponding to every two adjacent intra-frame compressed images are obtained; the motion vector is the pixel displacement between the two adjacent intra-frame compressed images, and the residual data is the pixel value change between the two adjacent intra-frame compressed images; all the intra-frame compressed images and the motion vectors and residual data corresponding to every two adjacent intra-frame compressed images are used as video compression data.

6. A file data management system for law enforcement recorders according to claim 5, characterized in that: The network characteristic data includes network bandwidth, network delay, packet loss rate and jitter; The step of dynamically adjusting the data transmission efficiency comprises: Step 1: Define the population size m, iteration threshold T and step factor ; Step 2: Build the population , population The position of each individual in the population is defined in a one-dimensional search space. The range of the one-dimensional search space is the efficiency range, which is the range of data transmission efficiency. The individual position corresponds to the value in the efficiency range one by one. The corresponding number of iterations t is 0; Step 3: Determine the stability function; Step 4: Population Divide into subpopulations, each of which includes Individuals, ; Step 5: Determine the optimal individuals in each subpopulation and the population The best individual in Step 6: Calculate the moving speed of each individual and update the position of each individual; Step 7: Determine whether each individual has undergone subpopulation replacement, and re-update the corresponding position of the individual that has undergone subpopulation replacement; Step 8: Update the best individuals in each subpopulation and the population The best individual in Step 9: Determine whether the number of iterations t is less than the iteration threshold If so, then let , and return to step 6, if not, go to step 10; Step 10: According to the population The value corresponding to the optimal individual in the data is used to dynamically adjust the data transmission efficiency.

7. A file data management system for law enforcement recorders according to claim 6, characterized in that: In step 2, the population , is the mth individual; The expression for each individual position in is: ; In the formula, is the position of the ith individual, is the random coefficient of the ith individual, , ; In step 3, the expression of the stability function is: ; In the formula, For stability, To predict bandwidth utilization, To predict network latency, To predict the packet loss rate, To predict jitter, , , , All are preset weight coefficients; predicted bandwidth utilization is the predicted bandwidth utilization after adjustment for data transmission efficiency; predicted network delay is the predicted network delay after adjustment for data transmission efficiency; predicted packet loss rate is the predicted packet loss rate after adjustment for data transmission efficiency; predicted jitter is the predicted jitter after adjustment for data transmission efficiency; The predicted bandwidth utilization, predicted network delay, predicted packet loss rate, and predicted jitter are used as prediction data. The method for obtaining the prediction data includes: The numerical values ​​corresponding to the network characteristic data and the individual positions are used as analysis data, and the analysis data is input into the trained network prediction model to predict the corresponding data label. The data label is the digital label corresponding to the predicted data. The predicted data and the digital label correspond one to one, and the corresponding predicted data is obtained according to the data label. The training process of the network prediction model includes: Collect q groups of analysis data in advance, set corresponding data labels for the q groups of analysis data, q is an integer greater than 1, and convert the analysis data and the corresponding data labels into a corresponding set of feature vectors; use each set of feature vectors as the input of a network prediction model, the network prediction model uses a set of predicted data labels corresponding to each group of analysis data as output, and uses the actual data labels corresponding to each group of analysis data as prediction targets, the actual data labels are the pre-set data labels corresponding to the analysis data; minimize the sum of prediction errors of all analysis data as a training target; the network prediction model is a deep neural network model.

8. The file data management system of the law enforcement recorder according to claim 7, characterized in that: In step 4, the population Divide into Methods for subpopulations include: Calculate population The stability of each individual in the , and sort them from large to small; set an increasing serial number for each individual in the positive order of sorting, and the serial number range is ;according to sub-populations, perform a modulo operation on the sequence number of each individual to obtain the corresponding sub-sequence number; the expression of the sub-sequence number is: ; In the formula, is the sub-sequence number, is the serial number, is the modulo function; if the sub-sequence number is not 0, the corresponding individual is assigned to the subpopulations; if the subsequence number is 0, the corresponding individual is assigned to the subpopulation; In step 5, the optimal individuals and populations in each subpopulation are determined. The method for finding the optimal individual in is as follows: calculate the stability corresponding to each individual, take the individual with the greatest stability in each subpopulation as the optimal individual of the corresponding subpopulation, and mark it as ; The most stable individual among all individuals is regarded as the population The best individual is marked as ; In step 6, the method for calculating the moving speed corresponding to each individual includes: If the individual is not the optimal individual corresponding to the subpopulation, the expression of the corresponding moving speed is: ; In the formula, is the moving speed of the ith individual, is the position of the best individual in the subpopulation corresponding to the i-th individual, is the position of the ith individual, ; If the individual is the optimal individual corresponding to the subpopulation, the expression of the corresponding moving speed is: ; In the formula, For population The position of the best individual in ; Methods for updating the location of each individual include: If the individual is not the optimal individual corresponding to the subpopulation, the expression of the individual position after update is: ; In the formula, is the position of the i-th individual after update, ; If the individual is the optimal individual corresponding to the subpopulation, the expression of the updated individual position is: .

9. A file data management system for law enforcement recorders according to claim 8, characterized in that: In step 7, the method for determining whether each individual undergoes subpopulation replacement includes: Calculate the stability of each individual after the position update; mark the individuals that are not the best individuals as ordinary individuals, subtract the stability of the best individual in the corresponding subpopulation from the stability of each ordinary individual, and obtain the stability difference corresponding to each ordinary individual; preset the difference threshold, and compare each stability difference with the difference threshold; if the stability difference is less than or equal to the difference threshold, mark the corresponding ordinary individual as a replacement individual; if the stability difference is greater than the difference threshold, do not mark the corresponding ordinary individual; Sort the stability of each optimal individual from large to small to generate a stability sorting table; add the stability of each replacement individual to the stability sorting table, obtain the two stabilities before the stability of each replacement individual, and mark them as replacement stability; replace each replacement individual to the subpopulation corresponding to the corresponding replacement stability; if the number of stabilities before the stability of the replacement individual is less than 2, do not replace the subpopulation for the corresponding replacement individual; Methods for re-updating the corresponding positions of individuals replaced in the subpopulation include: ； In the formula, is the position of the i-th individual after re-updating, ; In step 8, the optimal individuals and populations in each subpopulation are updated. The method of determining the best individual in each subpopulation and the population in step 5 is the same as The method of the optimal individual in is consistent.

10. A file data management system for law enforcement recorders according to claim 9, characterized in that: Preset grouping time, group law enforcement compressed data according to grouping time, and obtain Group law enforcement group data, is an integer greater than 1, and the time length corresponding to each group of law enforcement group data is the group duration; a corresponding check value is generated for each group of law enforcement group data using a check algorithm, and is marked as a first check value; each group of law enforcement group data is marked as incomplete, and each group of law enforcement group data marked as incomplete is transmitted in sequence according to the time sequence; when a group of law enforcement group data is transmitted, the corresponding check value is recalculated and marked as a second check value; If the first check value is consistent with the second check value, the corresponding law enforcement group data is marked as completed; If the first check value is inconsistent with the second check value, the corresponding law enforcement group data is still marked as incomplete, and the corresponding law enforcement group data is retransmitted; when data transmission is resumed after interruption, the law enforcement group data marked as incomplete continues to be transmitted.

Images