Big data analysis early warning system based on video and audio of chest card recorder

Abstract

The invention discloses a big data analysis and early warning system based on video and audio of a chest card recorder, and belongs to the technical field of data analysis and early warning, and the system comprises a data collection module which is used for collecting video and audio data obtained by the chest card recorder and recorded position information; the data transmission module is used for transmitting the acquired data and information to a data server; the data server is used for processing and analyzing the acquired data and information, analyzing and judging the working condition of the worker in combination with the information in the big database and generating alarm information, and meanwhile, the data server can also judge the working quality of the worker according to the acquired data information; and the user interface module is used for providing an interface for interaction between a user and the system. According to the invention, the working condition and quality of the worker can be judged according to the acquired data information, and the condition of the worker during work order processing can be known more clearly, so that corresponding measures are taken, and the high working efficiency is ensured.

Description

Technical Field

[0001] The present invention belongs to the technical field of data analysis and early warning, and in particular relates to a big data analysis and early warning system based on video and audio of a badge recorder. Background Art

[0002] With the continuous improvement of enterprise management and security monitoring needs, traditional monitoring methods can no longer meet the requirements of modern enterprises for employee behavior management, work efficiency improvement, safety assurance, etc. Especially in some industries that require employees to go out for work or inspection, such as logistics, electricity, transportation, etc., it is particularly important to conduct real-time monitoring and data analysis of employee behavior trajectories and work status.

[0003] At present, although there are some portable monitoring devices on the market, such as law enforcement recorders and badge cameras, these devices can only provide basic recording functions, and cannot achieve in-depth analysis of video data and intelligent early warning, and cannot make early warning judgments on the working conditions of staff. In addition, these devices are not convenient enough in terms of video playback and trajectory tracking, and cannot meet the needs of enterprises for data visualization and rapid response. Summary of the invention

[0004] The purpose of the present invention is to provide a big data analysis and early warning system based on the video and audio of a badge recorder to solve the problems faced by the above-mentioned background technology.

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] A big data analysis and early warning system based on video and audio data of a badge recorder, the system comprising:

[0007] A data collection module, the data collection module is used to collect the audio and video data obtained by the badge recorder and the recorded location information;

[0008] A data transmission module, which is used to transmit the acquired data and information to a data server;

[0009] Data server, which is used to process and analyze the acquired data and information, analyze and judge the work status of the staff in combination with the information in the big database, and generate alarm information in a timely manner. At the same time, the data server can also judge the work quality of the staff based on the acquired data information;

[0010] A user interface module, which is used to provide an interface for users to interact with the system;

[0011] Mini Program side: The mini program side is used to provide data input and work order management functions on the mobile side.

[0012] Furthermore, a map display unit is provided in the user interface module, and the data server packages the obtained location information and the audio and video data corresponding to the location information, uploads them to the geographical location corresponding to the map display unit, and generates a corresponding viewing track on the map according to the staff's driving track.

[0013] Furthermore, the data input into the mini program includes photos, videos and text descriptions taken by the staff, which are then uploaded to the data server. The data server searches for the corresponding work order problem description in the system based on the uploaded data, thereby automatically generating a processing work order and sending it to the corresponding relevant personnel for processing.

[0014] Furthermore, the method for the data server to generate warning information is:

[0015] Obtain the location points of the work orders that the staff needs to process and the dispatch points of the work orders, so as to generate multiple work paths and the ideal arrival time T of each work path th ;

[0016] Generate the employee's allowed activity range based on the generated work path. When the employee's location exceeds the employee's allowed activity range, an alarm message is generated.

[0017] By formula T t =T p *(1-β) gives the theoretical arrival time T of the staff t ;

[0018] If T t >T th , then generate an alarm message;

[0019] Among them, T p is the actual arrival time of the staff, and β is the influence coefficient.

[0020] Furthermore, the method for obtaining the influence coefficient β is:

[0021] Get the traffic flow value B on the selected working path from the big database m And the mean traffic flow B on the working path in the same historical time period v ;

[0022] Obtain the rainfall amount rain, fog level fog and snow accumulation snow on the selected work path from the big database;

[0023] By formula The influence coefficient is obtained, where τ1 and τ2 are preset coefficients.

[0024] Furthermore, the method for generating alarm information by the data server further includes:

[0025] The data server converts the acquired audio data into text information using language conversion technology, inputs it into a model library based on neural network model training, extracts the corresponding abnormal sentence keywords, and generates an alarm message if the number of abnormal sentence keywords exceeds the preset threshold;

[0026] At the same time, the data server automatically generates the corresponding problem description based on the generated abnormal keyword information through AI technology and sends it to the terminal manager.

[0027] Furthermore, the method by which the data server evaluates the work quality of the staff is:

[0028] The data server extracts multiple sets of work order processing information from the database at regular intervals, including the time HT taken to process each work order. i , the number of warning messages that appear each time a work order is processed is X j ;

[0029] By formula The evaluation value A is obtained;

[0030] If A∈(0, A1), the staff member’s work quality is judged to be excellent;

[0031] If A∈[A1, A2], the work quality of the staff is judged to be good;

[0032] If A∈(A2, +∞), the staff member’s work quality is judged to be poor;

[0033] Where n is the average number of work orders processed within a cycle. The standard time required to process each work order. is the threshold number of times that an alarm message appears each time a work order is processed, i∈[1,n], j∈[1,n], A1 and A1 are the preset evaluation thresholds.

[0034] Beneficial effects of the present invention:

[0035] The present invention obtains audio and video data and location information in work order processing through a badge recorder and uploads it to a data server. The data server can package the obtained location information and the audio and video data of the corresponding location information, upload them to the geographical location corresponding to the map display unit, and generate a corresponding viewing trajectory on the map according to the staff's driving trajectory. In this way, terminal personnel can monitor the staff's behavior trajectory in real time through the user interface module. When viewing the trajectory, functions such as video trajectory playback and audio trajectory playback can also be realized, so that the staff's work location and situation can be obtained more accurately, thereby improving the company's management efficiency of employee behavior.

[0036] The present invention can also judge the work status and work quality of the staff according to the acquired data information, so that the situation of the staff when processing the work order can be more clearly understood, so as to take corresponding measures to ensure high work efficiency.

[0037] The present invention can conduct a comprehensive analysis based on the number of times the staff handles work orders, the number of alarms generated, and the processing time within a predetermined period to obtain the work quality of the staff, thereby better facilitating the enterprise to monitor the work quality of employees and providing a strong guarantee for the development of the enterprise.

[0038] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for describing the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0040] Figure 1 It is a system block diagram of the present invention. DETAILED DESCRIPTION

[0041] 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.

[0042] In one embodiment, a big data analysis and early warning system based on the video and audio of a badge recorder is disclosed. Figure 1 As shown, the system includes:

[0043] A data acquisition module, which is used to collect the video and audio data acquired by the badge recorder and the recorded location information;

[0044] A data transmission module, which is used to transmit the acquired data and information to a data server;

[0045] Data server: The data server is used to process and analyze the acquired data and information, and analyze and judge the work status of the staff in combination with the information in the big database, and generate alarm information in a timely manner. At the same time, the data server can also judge the work quality of the staff based on the acquired data information;

[0046] User interface module, which is used to provide an interface for users to interact with the system;

[0047] Mini Program side: The Mini Program side is used to provide data input and work order management functions on the mobile side.

[0048] Through the above technical solution, the present application obtains the audio and video data and location information in the work order processing through the badge recorder, and uploads it to the data server. The data server can package the obtained location information and the audio and video data of the corresponding location information, upload it to the corresponding geographical location of the map display unit, and generate a corresponding viewing track on the map according to the staff's driving track. In this way, the terminal personnel can monitor the staff's behavior track in real time through the user interface module. When viewing the track, the video track playback, audio track playback and other functions can also be realized, and the work location and situation of the staff can be obtained more accurately, thereby improving the company's management efficiency of employee behavior. The present application can also judge the work situation and work quality of the staff based on the acquired data information, so that the situation of the staff when processing the work order can be more clearly understood, so as to take corresponding measures to ensure high work efficiency.

[0049] As an embodiment of the present invention, a map display unit is provided in the user interface module. The data server packages the obtained location information and the audio and video data corresponding to the location information, uploads them to the geographical location corresponding to the map display unit, and generates a corresponding viewing track on the map according to the staff's driving track.

[0050] The user enters the map display unit through the user interface module and can view the real-time position of the staff on the map. At the same time, the corresponding viewing track can be generated according to the staff's driving track. The viewing track contains the location information uploaded by the data server and the audio and video data of the corresponding location information. In this way, the user can drag the timeline on the map or click a certain location point, and the system will play the audio and video data corresponding to the time or location point. At the same time, when the user drags the track on the map, the video will also be played synchronously to the video clip corresponding to the track point; conversely, when the user drags or pauses the video on the video interface, the track on the map will also be highlighted or paused accordingly. In this way, the status of the staff can be clearly known, thereby improving the efficiency of the company's management of employee behavior.

[0051] As an implementation mode of the present invention, the data input into the mini program end includes photos, videos and text descriptions taken by the staff, which are then uploaded to the data server. The data server searches for the corresponding work order problem description in the system based on the uploaded data, thereby automatically generating a processing work order and sending it to the corresponding relevant personnel for processing.

[0052] When employees encounter urgent matters that need to be handled, they can use the badge recorder through the mini program to take photos or record short videos, and fill in the corresponding work order information (such as problem description, processing requirements, etc.). The mini program sends this information to the data server, which will automatically generate a processing work order after receiving it and notify relevant personnel to handle it. At the same time, this information will also be recorded in the system for subsequent analysis and query. This can improve the efficiency of work order generation and provide strong protection for the development of the enterprise.

[0053] As an implementation mode of the present invention, the method for the data server to generate alarm information is:

[0054] Obtain the location points of the work orders that the staff needs to process and the dispatch points of the work orders, so as to generate multiple work paths and the ideal arrival time T of each work path th ;

[0055] Generate the employee's allowed activity range based on the generated work path. When the employee's location exceeds the employee's allowed activity range, an alarm message is generated.

[0056] By formula T t =T p *(1-β) gives the theoretical arrival time T of the staff t ;

[0057] If T t >T th , then generate an alarm message;

[0058] Among them, T p is the actual arrival time of the staff, β is the influence coefficient;

[0059] The method for obtaining the influence coefficient β is: obtain the vehicle flow value B on the selected working path from the large database m And the mean traffic flow value B on the working path in the same historical time period v ;

[0060] Obtain the rainfall amount rain, fog level fog and snow accumulation snow on the selected work path from the big database;

[0061] By formula The influence coefficient is obtained, where τ1 and τ2 are preset coefficients.

[0062] Through the above technical solution, this embodiment provides a method for the server to generate alarm information. Since the staff will be out of the company's monitoring when they are working outside, they may deal with some things that are not related to work, resulting in low processing efficiency. Therefore, this embodiment obtains the location point of the processing work order that the staff needs to process and the dispatch point of the processing work order, thereby generating multiple work paths and the ideal arrival time T of each work path. th ; After the staff selects the corresponding work path, the employee's allowed activity range is generated. For example, the activity range can be within a certain position around the work path as the center. When the employee's position exceeds the employee's allowed activity range, it means that the employee has left the work range, and an alarm message is generated to promptly reflect the employee's return to the corresponding position to ensure work efficiency; In addition, affected by environmental factors such as rainy and snowy weather, or traffic congestion, the time when the employee arrives at the location point for processing the work order may be different from the ideal time, which will lead to judgment errors, so the traffic flow value B on the selected work path is obtained from the big database m And the mean traffic flow B on the working path in the same historical time period v , and obtain the rainfall rain, fog level fog and snow accumulation snow on the selected working path from the big database, and then use the formula The influence coefficient is obtained. From the formula, it can be seen that the actual traffic flow value and the historical traffic flow average are comprehensively analyzed to predict the traffic condition value of this section. The larger the value, the greater the actual impact on travel. Similarly, when the rainfall is greater, the fog level is higher, or the amount of snow is more, the actual impact on travel is also greater. Therefore, the influence coefficient is obtained by combining these factors for comprehensive analysis, and the formula T is used to calculate the influence coefficient. t =T p *(1-β) gives the theoretical arrival time T of the staff t ; From the formula, we can see that the larger the impact coefficient is, the more time is delayed in actual arrival. When comparing the theoretical arrival time with the ideal arrival time, if T t >T th , it can be considered that the staff is likely to be handling tasks other than work on the road, and an alarm message is generated to notify the corresponding terminal manager. In this way, the status of the staff when processing the work order can be obtained, so that the terminal manager can more accurately judge whether the staff is handling work tasks, which is conducive to improving management efficiency.

[0063] In the above technical solution, the preset coefficients τ1 and τ2 can be determined based on empirical data.

[0064] As an implementation mode of the present invention, the method for generating alarm information by the data server further includes:

[0065] The data server converts the acquired audio data into text information using language conversion technology, inputs it into a model library based on neural network model training, extracts the corresponding abnormal sentence keywords, and generates an alarm message if the number of abnormal sentence keywords exceeds the preset threshold;

[0066] At the same time, the data server automatically generates the corresponding problem description based on the generated abnormal keyword information through AI technology and sends it to the terminal manager.

[0067] The data server can convert the acquired audio data into text information using language conversion technology, and input it into a model library based on neural network model training. The model library is equipped with enough abnormal sentence keywords, so that it can be known whether the staff has abnormal sentence keywords when processing the work order. When the number of abnormal sentence keywords exceeds the preset threshold, it means that there are many problems when processing the work order, and an alarm message is generated to remind the terminal manager. At the same time, the data server automatically generates the corresponding problem description based on the generated abnormal keyword information through AI technology, and sends it to the terminal manager. In this way, the terminal personnel can find the corresponding processing method based on the generated problem description in time and feedback it to the staff, thereby improving processing efficiency.

[0068] As an implementation mode of the present invention, the method for the data server to evaluate the work quality of the staff is:

[0069] The data server extracts multiple sets of work order processing information from the database at regular intervals, including the time HT taken to process each work order. i , the number of warning messages that appear each time a work order is processed is X j ;

[0070] By formula The evaluation value A is obtained;

[0071] If A∈(0, A1), the staff member’s work quality is judged to be excellent;

[0072] If A∈[A1, A2], the work quality of the staff is judged to be good;

[0073] If A∈(A2, +∞), the staff member’s work quality is judged to be poor;

[0074] Where n is the average number of work orders processed within a cycle. The standard time required to process each work order. is the threshold number of times the alarm information appears each time a work order is processed, i∈[1,n], j∈[1,n], A1 and A1 are the preset evaluation thresholds.

[0075] Through the above technical solution, this embodiment provides a method for the data server to evaluate the work quality of the staff, specifically: the data server extracts multiple sets of work order processing information from the database at intervals, and the cycle can be determined manually, such as a month, including the time HT used for each work order processing. i , the number of warning messages that appear each time a work order is processed is X j , so that through the formula The evaluation value A is obtained, the formula It represents the ratio of the time taken to process each work order to the standard time. It can be seen that the larger the ratio is within the cycle, the longer it takes, and the worse the work quality is. The formula It indicates the ratio of the number of alarms that occur each time a work order is processed to the number of threshold alarms. It can be seen that the larger the ratio is within a period, the more alarms occur, indicating that the work quality is worse. If the staff processes fewer work orders within the period, it means that their work quality is also poor. Therefore, when the evaluation value A is larger, the staff's work quality is worse. Therefore, when A∈(0, A1), the staff's work quality is judged to be excellent, when A∈[A1, A2], the staff's work quality is judged to be good, and when A∈(A2, +∞), the staff's work quality is judged to be poor. In this way, a comprehensive analysis can be conducted based on the number of times the staff processes work orders, the number of alarms generated, and the processing time within a predetermined period to obtain the staff's work quality, which can better facilitate the company to monitor the quality of employees' work.

[0076] In the above technical solution, the preset evaluation threshold A1 and A1, the standard time for processing each work order The threshold number of times an alarm message appears each time a work order is processed All of these can be determined based on historical experience data, so I will not elaborate on them here.

[0077] The present invention obtains the audio-visual data and location information in the work order processing through the badge recorder, and uploads it to the data server. The data server can package the obtained location information and the audio-visual data of the corresponding location information, upload it to the corresponding geographical location of the map display unit, and generate the corresponding viewing trajectory on the map according to the staff's driving trajectory, so that the terminal personnel can monitor the staff's behavior trajectory in real time through the user interface module. When viewing the trajectory, the functions of video trajectory playback and audio trajectory playback can also be realized, and the working position and situation of the staff can be obtained more accurately, thereby improving the management efficiency of the enterprise to the employee's behavior. The present invention can also judge the work situation and work quality of the staff according to the acquired data information, so that the situation of the staff when processing the work order can be more clearly understood, so as to take corresponding measures to ensure the high efficiency of work efficiency. The present invention can make a comprehensive analysis based on the number of times the staff processes the work order, the number of alarms generated, and the processing time within a predetermined period to obtain the work quality of the staff, so as to better facilitate the enterprise to monitor the work quality of the employees and provide a strong guarantee for the development of the enterprise.

[0078] The above contents are merely examples and explanations of the concept of the present invention. The technicians in this technical field may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined by the claims, they should all fall within the protection scope of the present invention.

Claims

1. A big data analysis and early warning system based on the video and audio of badge recorders, characterized in that: The system comprises: A data collection module, the data collection module is used to collect the audio and video data obtained by the badge recorder and the recorded location information; A data transmission module, which is used to transmit the acquired data and information to a data server; Data server, which is used to process and analyze the acquired data and information, analyze and judge the work status of the staff in combination with the information in the big database, and generate alarm information in a timely manner. At the same time, the data server can also judge the work quality of the staff based on the acquired data information; A user interface module, which is used to provide an interface for users to interact with the system; Mini program side, the mini program side is used to provide data input and work order management functions for the mobile terminal.

2. The big data analysis and early warning system based on the video and audio of the badge recorder according to claim 1 is characterized in that: The user interface module is provided with a map display unit. The data server packages the obtained location information and the audio and video data corresponding to the location information, uploads them to the geographical location corresponding to the map display unit, and generates a corresponding viewing track on the map according to the staff's driving track.

3. The big data analysis and early warning system based on the video and audio of the badge recorder according to claim 1 is characterized in that: The data input on the mini program end includes photos, videos and text descriptions taken by the staff, which are then uploaded to the data server. The data server searches for the corresponding work order problem description in the system based on the uploaded data, and automatically generates a processing work order, which is then sent to the corresponding relevant personnel for processing.

4. The big data analysis and early warning system based on the video and audio of the badge recorder according to claim 1 is characterized in that: The method for the data server to generate alarm information is: Obtain the location points of the work orders that the staff needs to process and the dispatch points of the work orders, so as to generate multiple work paths and the ideal arrival time T of each work path th ; Generate the employee's allowed activity range based on the generated work path. When the employee's location exceeds the employee's allowed activity range, an alarm message is generated. By formula T t =T p *(1-β) gives the theoretical arrival time T of the staff t ; If T t >T th , then generate an alarm message; Among them, T p is the actual arrival time of the staff, and β is the influence coefficient.

5. The big data analysis and early warning system based on the video and audio data of the badge recorder according to claim 4 is characterized in that: The method for obtaining the influence coefficient β is: Get the traffic flow value B on the selected working path from the big database m And the mean traffic flow B on the working path in the same historical time period v ; Obtain the rainfall amount rain, fog level fog and snow accumulation snow on the selected work path from the big database; By formula The influence coefficient is obtained, where τ1 and τ2 are preset coefficients.

6. The big data analysis and early warning system based on the video and audio data of the badge recorder according to claim 4 is characterized in that: The method for generating alarm information by the data server also includes: The data server converts the acquired audio data into text information using language conversion technology, inputs it into a model library based on neural network model training, extracts the corresponding abnormal sentence keywords, and generates an alarm message if the number of abnormal sentence keywords exceeds the preset threshold; At the same time, the data server automatically generates the corresponding problem description based on the generated abnormal keyword information through AI technology and sends it to the terminal manager.

7. The big data analysis and early warning system based on the video and audio data of the badge recorder according to claim 6 is characterized in that: The method by which the data server judges the work quality of the staff is: The data server extracts multiple sets of work order processing information from the database at regular intervals, including the time HT taken to process each work order. i , the number of warning messages that appear each time a work order is processed is X j ; By formula The evaluation value A is obtained; If A∈(0, A1), the staff member’s work quality is judged to be excellent; If A∈[A1, A2], the work quality of the staff is judged to be good; If A∈(A2, +∞), the staff member’s work quality is judged to be poor; Where n is the average number of work orders processed within a cycle. The standard time required to process each work order. is the threshold number of times the alarm information appears each time a work order is processed, i∈[1,n], j∈[1,n], A1 and A1 are the preset evaluation thresholds.

Images