Attendance data detection method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides an attendance data detection method and device, electronic equipment and a storage medium, and belongs to the technical field of machine learning. The method comprises the following steps: acquiring attendance voice data, biological detection data, attendance performance data and task completion data of a detection object in a preset attendance time period; and performing voice detection on the attendance voice data based on a preset voice detection model to obtain a voice detection index. And performing object pressure detection according to the biological detection data to obtain an object pressure index. And performing quantification processing on the attendance performance data to obtain an attendance performance score, and performing quantification processing on the task completion data to obtain a task completion score. And performing object attendance detection based on the voice detection index, the object pressure index, the attendance performance score and the task completion score to obtain an attendance score of the detected object. According to the embodiment of the invention, the accuracy of attendance data detection can be improved.

Description

Technical Field

[0001] The present application relates to the field of machine learning technology, and in particular to an attendance data detection method and device, an electronic device, and a storage medium. Background Art

[0002] In enterprise management, attendance data monitoring refers to the process of automated or semi-automated verification and analysis of employee attendance records through technical means, providing data support for enterprise management. Attendance data monitoring can help companies better manage attendance and optimize attendance management processes, thereby standardizing employee work hours and improving work efficiency.

[0003] Currently, related technologies typically use tools such as card swiping and fingerprint recognition to automatically record employee attendance information such as get off work and leave times, overtime, etc., and then directly manage employee attendance based on this attendance information. However, this method has low accuracy in detecting attendance data. Summary of the Invention

[0004] The main purpose of the embodiments of the present application is to provide an attendance data detection method and device, an electronic device and a storage medium, which can improve the accuracy of attendance data detection.

[0005] To achieve the above objectives, a first aspect of an embodiment of the present application provides an attendance data detection method, the method comprising:

[0006] Obtaining the test subject's attendance voice data, biological test data, attendance performance data, and task completion data during the preset attendance time period;

[0007] Performing voice detection on the attendance voice data based on a preset voice detection model to obtain a voice detection index, where the voice detection index is used to indicate a quantitative value of the emotion of the detection subject during the preset attendance time period;

[0008] Performing a stress test on the subject based on the biological test data to obtain a stress index for the subject, wherein the stress index is used to indicate a quantitative stress value of the subject during the preset attendance time period;

[0009] Quantifying the attendance performance data to obtain an attendance performance score, and quantifying the task completion data to obtain a task completion score;

[0010] The subject's attendance is detected based on the voice detection index, the subject's stress index, the attendance performance score, and the task completion score to obtain the attendance score of the detected subject.

[0011] In some embodiments, performing subject attendance detection based on the voice detection index, the subject stress index, the attendance performance score, and the task completion score to obtain the attendance score of the detected subject includes:

[0012] determining an emotional stress score of the detection subject based on the speech detection index and the subject stress index;

[0013] The subject's attendance is detected based on the emotional stress score, the attendance performance score, and the task completion score to obtain the attendance score of the detected subject.

[0014] In some embodiments, the attendance voice data includes at least two attendance voice sub-data, the voice detection index includes a voice detection sub-score corresponding to each attendance voice sub-data, and performing subject attendance detection based on the emotional stress score, the attendance performance score, and the task completion score to obtain the attendance score of the detected subject includes:

[0015] determining a maximum speech score and a minimum speech score based on at least two of the speech detection sub-scores;

[0016] Determining a voice score difference based on the maximum voice score and the minimum voice score, wherein the voice score difference is used to indicate a quantitative value of the degree of emotion change of the detection subject during the preset attendance time period;

[0017] The emotional stress score, the voice score difference, the attendance performance score and the task completion score are weightedly calculated to obtain the attendance score of the detection subject.

[0018] In some embodiments, performing subject attendance detection based on the voice detection index, the subject stress index, the attendance performance score, and the task completion score to obtain the attendance score of the detected subject includes:

[0019] Obtaining the effective working time and post deviation time of the detection subject in the preset attendance time period;

[0020] Calculate the ratio of the effective working hours to the job deviation hours to obtain the effective working percentage;

[0021] Determine the penalty score of the detection object based on the comparison result of the effective work ratio and the preset time ratio;

[0022] The subject's attendance is detected based on the voice detection index, the subject's stress index, the attendance performance score, the task completion score, and the penalty score to obtain the attendance score of the detected subject.

[0023] In some embodiments, performing stress detection on the subject based on the biological detection data to obtain a stress index of the subject includes:

[0024] extracting a target detection data sequence from the biological detection data;

[0025] Calculating a target power spectrum density based on the target detection data sequence, and determining low-frequency power data and high-frequency power data of the target detection data sequence according to the target power spectrum density;

[0026] A ratio calculation is performed on the low-frequency power data and the high-frequency power data to obtain an object pressure index.

[0027] In some embodiments, the quantifying the task completion data to obtain a task completion score includes:

[0028] Obtaining the object position type of the detection object;

[0029] When the position type of the object is the first position type, obtaining the effective working time of the detection object in the preset attendance time period;

[0030] The task completion score is determined based on the effective working time and the task completion data.

[0031] In some embodiments, the quantifying the task completion data to obtain a task completion score further includes:

[0032] When the position type of the object is the second position type, obtaining the task allocation data of the detection object in the preset attendance time period;

[0033] The task completion score is determined based on the task assignment data and the task completion data.

[0034] To achieve the above-mentioned purpose, a second aspect of an embodiment of the present application provides an attendance data detection device, the device comprising:

[0035] A data acquisition module is used to obtain the attendance voice data, biological test data, attendance performance data and task completion data of the test subject during the preset attendance time period;

[0036] a voice detection module, configured to perform voice detection on the attendance voice data based on a preset voice detection model to obtain a voice detection index, wherein the voice detection index is used to indicate a quantitative value of the emotion of the detection subject during the preset attendance time period;

[0037] A stress detection module, configured to perform stress detection on the subject according to the biological detection data to obtain a stress index of the subject, wherein the stress index of the subject is used to indicate a quantitative stress value of the detected subject during the preset attendance time period;

[0038] a performance quantification module, configured to quantify the attendance performance data to obtain an attendance performance score, and quantify the task completion data to obtain a task completion score;

[0039] The attendance scoring module is used to perform subject attendance detection based on the voice detection index, the subject stress index, the attendance performance score and the task completion score to obtain the attendance score of the detected subject.

[0040] To achieve the above-mentioned purpose, the third aspect of an embodiment of the present application proposes an electronic device, which includes a memory and a processor, wherein the memory stores a computer program, and the processor implements the method described in the first aspect when executing the computer program.

[0041] To achieve the above-mentioned purpose, the fourth aspect of the embodiments of the present application proposes a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the method described in the first aspect.

[0042] The attendance data detection method and device, electronic device and storage medium proposed in the present application obtain the attendance voice data, biological detection data, attendance performance data and task completion data of the detection object in a preset attendance time period. Furthermore, based on the preset voice detection model, voice detection is performed on the attendance voice data to obtain a voice detection index, which is used to indicate the emotional quantification value of the detection object in the preset attendance time period. Furthermore, based on the biological detection data, the object stress detection is performed to obtain the object stress index, which is used to indicate the stress quantification value of the detection object in the preset attendance time period. Furthermore, the attendance performance data and task completion data are quantified and processed respectively to obtain the attendance performance score and the task completion score. Finally, based on the voice detection index, the object stress index, the attendance performance score and the task completion score, the object attendance detection is performed to obtain the attendance score of the detection object.

[0043] When determining the attendance score of the test subject, this application conducts multi-dimensional attendance detection by combining the test subject's attendance performance, task completion, emotional state and stress state, which can more comprehensively evaluate the test subject's attendance during the attendance time period, so as to improve the accuracy of attendance data detection, thereby improving the accuracy of the test subject's attendance score. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1is a flow chart of the attendance data detection method provided in an embodiment of the present application;

[0045] Figure 2 yes Figure 1 Flowchart of step S103 in FIG.

[0046] Figure 3 yes Figure 1 Flowchart of step S104 in FIG.

[0047] Figure 4 yes Figure 1 Another flow chart of step S104 in FIG.

[0048] Figure 5 yes Figure 1 Flowchart of step S105 in FIG.

[0049] Figure 6 yes Figure 5 Flowchart of step S502 in FIG.

[0050] Figure 7 yes Figure 1 Another flow chart of step S105 in ;

[0051] Figure 8 Schematic diagram of the structure of the attendance data detection device provided in an embodiment of the present application;

[0052] Figure 9 This is a schematic diagram of the hardware structure of the electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0054] It should be noted that although the device schematics illustrate functional module divisions and the flowcharts illustrate logical sequences, in certain circumstances, the steps shown or described may be performed in a sequence that differs from the module divisions in the device or the sequence in the flowcharts. The terms "first," "second," and so on, in the specification, claims, and drawings, are used to distinguish similar items and are not necessarily used to describe a specific sequence or precedence.

[0055] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application pertains. The terms used herein are for the purpose of describing the embodiments of this application only and are not intended to limit this application.

[0056] First, let’s analyze some of the terms used in this application:

[0057] Hidden Markov Model (HMM) is a statistical model used to infer the emotional state of the detected object through observable speech data.

[0058] A deep neural network (DNN) is a multi-layer neural network model that generates a speech detection index by learning features from speech data to evaluate the emotional state of the subject.

[0059] Fast Fourier Transform (FFT): is a data processing method used to convert target detection data sequences into power distributions at different frequencies to reflect the frequency domain characteristics of the data sequences.

[0060] An autoregressive model (AR) is a statistical model used to predict future values based on past values of a target detection data series. By fitting the past and future values of the target detection data series, the target power spectral density corresponding to the target detection data series is calculated.

[0061] In enterprise management, attendance data verification refers to the process of automated or semi-automated verification and analysis of employee attendance records through technical means, providing data support for enterprise management. Attendance data verification can help companies better manage attendance and optimize attendance management processes, thereby standardizing employee work hours and optimizing work efficiency. Currently, relevant technologies propose installing fingerprint time clocks at company entrances. Employees clock in and out daily by pressing their fingerprints, and the fingerprint time clocks automatically record attendance information such as their arrival time, arrival time, and overtime. However, this method poses issues such as clocking in by proxy or missed operations, resulting in reduced accuracy of the generated attendance data. Alternatively, relevant technologies propose installing high-definition cameras at designated locations. Employees clock in and out using facial recognition technology, and the cameras automatically record attendance information such as their arrival time, arrival time, and overtime. However, the attendance data generated by this method does not reflect employees' actual work status within the company.

[0062] Based on this, embodiments of the present application provide an attendance data detection method and device, an electronic device, and a storage medium, which can improve the accuracy of attendance data detection.

[0063] The attendance data detection method provided in the embodiment of the present application relates to the field of machine learning technology. The attendance data detection method provided in the embodiment of the present application can be applied to a terminal, can be applied to a server side, or can be software running in a terminal or a server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc.; the server side can be configured as an independent physical server, or as a server cluster or distributed system composed of multiple physical servers, or as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application that implements the attendance data detection method, etc., but is not limited to the above forms.

[0064] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and the like. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, and the like that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments in which tasks are performed by remote processing devices connected via a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media, including storage devices.

[0065] It should be noted that in each specific embodiment of the present application, when it comes to the need to perform relevant processing on data related to the identity or characteristics of the detection object based on detection object information, object voice data, object biological detection data, and detection object historical data detection, the permission or consent of the detection object will be obtained first, and the collection, use, and processing of these data will comply with relevant laws, regulations, and standards. In addition, when the embodiment of the present application needs to obtain sensitive personal information of the detection object, the separate permission or separate consent of the detection object will be obtained by means of a pop-up window or by jumping to a confirmation page. After clearly obtaining the separate permission or separate consent of the detection object, the necessary detection object-related data for enabling the normal operation of the embodiment of the present application will be obtained.

[0066] Figure 1 This is an optional flowchart of the attendance data detection method provided in the embodiment of the present application. Figure 1The method may include but is not limited to steps S101 to S105.

[0067] Step S101, obtaining the attendance voice data, biological test data, attendance performance data and task completion data of the detection subject during the preset attendance time period;

[0068] Step S102: performing voice detection on the attendance voice data based on a preset voice detection model to obtain a voice detection index;

[0069] Step S103, performing a stress test on the subject based on the biological test data to obtain a stress index of the subject;

[0070] Step S104: quantify the attendance performance data to obtain an attendance performance score, and quantify the task completion data to obtain a task completion score;

[0071] Step S105 , performing subject attendance detection based on the voice detection index, the subject's stress index, the attendance performance score, and the task completion score to obtain the subject's attendance score.

[0072] In step S101 of some embodiments, the detection subject indicates an individual within an enterprise or organization whose attendance data needs to be detected. For example, this could be an employee within a company or a member within an organization. The preset attendance time period indicates the attendance time range pre-set by the enterprise or organization. For example, a company may specify a preset attendance time period for employees from 9:00 AM to 6:00 PM daily for a month; or an organization may specify a preset attendance time period for members from 8:00 AM to 5:00 PM for two weeks. The preset attendance time period can be freely set based on actual needs. Attendance voice data indicates the voice information generated by the detection subject in specific work scenarios during the attendance time period. Specific work scenarios include customer service calls, conference speeches, team communication, online training, and remote collaboration. For example, during the preset attendance time period, the attendance voice data may be derived from voice recordings of employees communicating with customers over the phone; alternatively, the attendance voice data may be derived from voice data of the detection subject speaking in team meetings.

[0073] Biological test data is used to indicate the physiological data of the test subject during a specific task within the attendance time period, collected through wearable devices or sensors. Specific task periods include high-pressure situations such as participating in important projects, attending meetings, and communicating with customers. For example, during the preset attendance time period, biological test data can be the heart rate change data of employees during online training collected through a smart bracelet; or, biological test data can also be the blood pressure change data of employees while speaking in a meeting collected through a blood pressure monitoring device. Attendance performance data is used to indicate the attendance status of the test subject during the preset attendance time period. For example, during the preset attendance time period, the attendance status of employees in the company can be full attendance, lateness, early departure, or absence. Task completion data is used to indicate the number of tasks completed by the test subject during the attendance time period. For example, during the attendance time period, the employee completed 4 tasks or 5.5 tasks.

[0074] It should be noted that the number of tasks for the test subject is calculated by summing up the test subject's contribution ratio for each task. The contribution ratio refers to the ratio of the actual workload completed by the test subject in a task to the total workload. For example, if an employee participated in completing three tasks, with a contribution ratio of 50% for each task, the number of tasks is 1.5 (number of tasks = 1 × 50% + 1 × 50% + 1 × 50%). Alternatively, if an employee participated in four tasks, with a contribution ratio of 100% for each task, the number of tasks is 4.

[0075] In step S102 of some embodiments, the preset voice detection model is a deep learning model, such as a hidden Markov model or a deep neural network, for analyzing emotional features in attendance voice data. The voice detection index is an emotional quantification value derived from analyzing the attendance voice data using the preset voice detection model. It is used to represent the emotional state of the detected subject during the preset attendance time period. For example, the voice detection index can be a value between 0 and 100, with higher values indicating more negative emotions and lower values indicating more positive emotions.

[0076] In step S103 of some embodiments, the subject stress index is a stress quantification value obtained by analyzing the biological test data, and is used to represent the stress level of the test subject during a preset attendance time period. For example, the subject stress index can be a value between 0 and 100, with lower values indicating lower stress levels and higher values indicating higher stress levels.

[0077] See also Figure 2 In some embodiments, step S103 may include but is not limited to steps S201 to S203:

[0078] Step S201, extracting a target detection data sequence from biological detection data;

[0079] Step S202: Calculate the target power spectrum density based on the target detection data sequence, and determine the low-frequency power data and high-frequency power data of the target detection data sequence according to the target power spectrum density;

[0080] Step S203 , calculating the ratio of the low-frequency power data to the high-frequency power data to obtain the object pressure index.

[0081] In step S201 of some embodiments, the target detection data sequence is a data sequence for a specific time period extracted from the biological detection data. For example, if the biological detection data is heart rate variability data, the target detection data sequence may be the heart rate data between two consecutive heartbeats (denoted as RR intervals) recorded by the detection subject while in a meeting; or, if the biological detection data is blood pressure variability data, the target detection data sequence may be the blood pressure data recorded every 30 seconds by the detection subject while communicating with a client.

[0082] In step S202 of some embodiments, the target power spectrum density is used to indicate the power distribution of the target detection data sequence at different frequencies, and is used to reflect the frequency domain characteristics of the data sequence. The low-frequency power data is the power data of the low-frequency band in the target power spectrum density, and the high-frequency power data is the power data of the high-frequency band in the target power spectrum density. For example, if the frequency range of the target power spectrum density is 0.04 Hz to 0.4 Hz, the low-frequency power data is the power data of the target power spectrum density with a frequency range of 0.04 Hz to 0.15 Hz, and the high-frequency power data is the power data of the target power spectrum density with a frequency range of 0.15 Hz to 0.4 Hz.

[0083] It should be noted that the target power spectral density can be calculated by fast Fourier transform on the target detection data sequence, or by using an autoregressive model. The specific calculation method of the target power spectral density can be freely set according to actual needs.

[0084] In step S203 of some embodiments, the object pressure index is obtained by calculating the ratio of the low-frequency power data to the high-frequency power data, and the calculation formula is shown as follows (1):

[0085] P=LF / HF (1)

[0086] Where P is the object pressure index, LF is the low-frequency power data, and HF is the high-frequency power data.

[0087] When the biological detection data is electrocardiogram data, the embodiment of the present application can first extract the data sequence of RR intervals from the electrocardiogram data to form a non-uniformly sampled time series. Furthermore, the non-uniformly sampled time series is transformed into a uniformly sampled time series RR(n) by an interpolation method. Furthermore, an autoregressive model of RR(n) is established, and its calculation formula is shown as follows (2):

[0088]

[0089] Where RR(n) represents the data sequence of the RR interval at the nth time point (i.e., the target detection data sequence); p is the model order, which is the number of past values used to predict the current value; a k is a model parameter, which represents the weight of the kth past value; e(n) is a noise term, which represents the random error that cannot be explained by the autoregressive model; k is the index of the past value; and n is the index of the current time point.

[0090] Furthermore, the a corresponding to each detection object is calculated by the autoregressive model of RR(n) k , and then a k Substitute the following formula (3) to calculate the corresponding target power spectrum density:

[0091]

[0092] Among them, σ 2 is the variance of the noise term e(n); j is the imaginary unit; e -j2πfk is the complex exponential term used to represent the frequency component; e is the base of the natural exponential function; and f is the frequency in Hz.

[0093] Then, the low-frequency power data and high-frequency power data of the target detection data sequence are determined by the target power spectrum density. If the frequency range of the target power spectrum density is 0.04Hz to 0.5Hz, the calculation formula of the low-frequency power data is as follows (4):

[0094]

[0095] The calculation formula for high-frequency power data is shown below (5):

[0096]

[0097] Finally, the ratio of low-frequency power data to high-frequency power data is calculated to obtain the object pressure index P = LF / HF = P LF / P HF .

[0098] In step S104 of some embodiments, the attendance performance score is a score obtained by quantifying the attendance of the subject according to the preset attendance mapping rules. The preset attendance mapping rules can be set as follows:

[0099] As shown in Table 1:

[0100] Attendance Corresponding scores Perfect attendance 10 points (full score) Being late once 2 points deduction Leave early once 2 points deduction One absence 4 points deduction

[0101] Table 1

[0102] Please refer to Table 1. If the subject's attendance during the preset attendance period is perfect, the corresponding attendance performance score is 10 points. If the subject is late once or leaves early once during the preset attendance period, 2 points will be deducted from the attendance performance score. If the subject is absent once during the preset attendance period, 4 points will be deducted from the attendance performance score. For example, if an employee is late twice, leaves early once, and is absent once in a month, their attendance performance score is: 10-2 × 2-2-4 = 0 points. Alternatively, if an employee is late once and leaves early once in half a month, their attendance performance score is: 10-2-2 = 6 points.

[0103] It should be noted that the corresponding score for perfect attendance in the preset attendance mapping rules and the penalty rules for lateness, early departure, and absence can be freely set according to actual needs. For example, an enterprise can set the corresponding score for perfect attendance to other values (such as 20 points or 100 points) based on its own management needs and adjust the penalty rules for lateness, early departure, and absence accordingly.

[0104] The task completion score is a score obtained by quantifying the number of tasks completed by the test object according to the preset task quantity mapping rules. The preset task quantity mapping rules can be set as shown in Table 2 below:

[0105] Number of tasks Corresponding scores Complete 10 or more tasks 10 points (full score) For each task not completed 1 point deduction

[0106] Table 2

[0107] Please refer to Table 2. If the test subject completes 10 or more tasks within the preset attendance period, the task completion score is 10 points. For each task not completed within the preset attendance period, 1 point will be deducted. For example, if an employee completes 15 tasks in a month, their task completion score is 10 points; or if an employee completes 5 tasks in a month, their task completion score is 10 - 1 × 5 = 5 points.

[0108] It should be noted that the full score for the number of tasks in the preset task quantity mapping rules and the deduction rules for each task not completed can be freely set according to actual needs. For example, an enterprise can set the full score for the number of completed tasks to other values (such as 20 points or 100 points) according to its own management needs, and adjust the deduction rules for each task not completed accordingly. In addition, the number of tasks corresponding to the full score can also be adjusted according to actual needs. For example, an enterprise can set the full score for completing 20 or more tasks according to its own management needs.

[0109] See also Figure 3 In some embodiments, step S104 may include but is not limited to steps S301 to S303:

[0110] Step S301, obtaining the object position type of the detection object;

[0111] Step S302: When the target job type is the first job type, obtain the effective working time of the detected target in the preset attendance time period;

[0112] Step S303: Determine the task completion score based on the effective working time and the task completion data.

[0113] In step S301 of some embodiments, the object position type refers to the job category of the detection object in the enterprise or organization. For example, the object position type can be a development position, a sales position, a management position, etc.

[0114] In step S302 of some embodiments, the first position type is a development position. The effective working time refers to the time the detection subject actually spends working during the preset attendance time period. The calculation formula for the effective working time is shown as follows (6):

[0115] Tactual=Twork+Tmeeting-Tnonwork (6)

[0116] Among them, Tactual is the effective working time; Twork is the time spent at the workstation; Tmeeting is the time spent in meetings; and Tnonwork is the time spent visiting non-work-related websites during working hours.

[0117] For example, if an employee spends 7 hours at their workstation in a day, attends meetings for 1 hour, and visits non-work-related websites during work hours for 2 hours, their effective working hours are 7+1-2=6 hours. Alternatively, if an employee spends 140 hours at their workstation in a month, attends meetings for 20 hours, and visits non-work-related websites during work hours for 40 hours, their effective working hours are 140+20-40=120 hours.

[0118] In step S303 of some embodiments, the task completion score is calculated by combining the effective working time and the task completion data, and the calculation formula is shown as follows (7):

[0119] η=Ncompleted / Tactual (7)

[0120] Among them, η is the task completion score; Ncompleted is the task completion data; Tactual is the effective working time.

[0121] For example, if an employee's effective working hours in a day are 6 hours and the number of tasks completed is 1.5, the task completion score is 0.25 points; or if an employee's effective working hours in a month are 120 hours and the number of tasks completed is 24, the task completion score is 0.2 points.

[0122] The embodiment of the present application not only considers the number of tasks completed by employees for development positions, but also combines the actual input of employees during effective working time, thereby eliminating time differences caused by non-work-related activities, and accurately reflecting the actual work situation of employees within the company.

[0123] See also Figure 4 In some embodiments, step S104 may also include but is not limited to steps S401 to S402:

[0124] Step S401: When the target job type is the second job type, obtain the task allocation data of the detected target in the preset attendance time period;

[0125] Step S402: Determine a task completion score based on the task assignment data and the task completion data.

[0126] In step S401 of some embodiments, the second position type is a sales position. The task allocation data is used to indicate the number of tasks assigned to the detection subject within a preset attendance time period.

[0127] In step S402 of some embodiments, the task completion score is calculated by performing calculations on the task assignment data and the task completion data, and the calculation formula is shown as follows (8):

[0128] η=Ncompleted / Nassigned (8)

[0129] Among them, η is the task completion score; Ncompleted is the task completion data; Nassigned is the task assignment data.

[0130] For example, if an employee is assigned 2 tasks in a day and has 1 task completed, the task completion score is 0.5 points; or if an employee is assigned 20 tasks in a month and has 15 task completed, the task completion score is 0.75 points.

[0131] The embodiment of the present application not only considers the number of tasks completed by employees but also the number of tasks assigned to employees for the task completion scoring of sales positions, thereby eliminating unfair evaluations caused by uneven task distribution and motivating employees to improve their task completion rates.

[0132] In step S105 of some embodiments, the attendance score is a quantitative value that evaluates the attendance performance and work status of the test subject within a preset attendance time period, and its calculation formula is shown as follows (9):

[0133]

[0134] Among them, Sdev is the attendance score; Sattendance is the attendance performance score; η is the task completion score; E is the voice detection index, is the normalized emotional index; P is the object stress index, is the normalized pressure index; α1, β1, w E1 and w P1 are weight coefficients, and these weight coefficients can be freely set according to actual needs, but must satisfy α1+β1+w E1 +w P1 = 1. For example, if the weight coefficient α1 is 0.2, β1 is 0.2, w E1 is 0.3, w P1 is 0.3, Sattendance is 8, η is 0.5, E is 50, and P is 30, then Sdev=0.2×8+0.2×0.5+0.3×0.5+0.3×0.7=2.06.

[0135] See also Figure 5 In some embodiments, step S105 may include but is not limited to steps S501 to S502:

[0136] Step S501, determining the emotional stress score of the detection subject based on the voice detection index and the subject stress index;

[0137] Step S502 : performing attendance detection on the subject based on the emotional stress score, attendance performance score, and task completion score to obtain the attendance score of the detected subject.

[0138] In step S501 of some embodiments, the emotional stress score is used to evaluate the quantitative value of the emotional state and stress level of the detection subject during the preset attendance time period, and its calculation formula is shown as follows (10):

[0139]

[0140] Among them, EP is the emotional stress score; w E2 and w P2 are weight coefficients, and these weight coefficients can be freely set according to actual needs, but they must satisfy w E2 +w P2 =1.

[0141] In step S502 of some embodiments, the attendance score is calculated by using the emotional stress score, attendance performance score, and task completion score, and the calculation formula is shown as follows (11):

[0142] Sdev=α2×Sattendance+β2×η+γ2×EP (11)

[0143] Among them, α2, β2, and γ2 are weight coefficients, and these weight coefficients can be freely set according to actual needs, but must satisfy α2 + β2 + γ2 = 1. For example, if the weight coefficient α2 is 0.3, β2 is 0.3, γ2 is 0.4, Sattendance is 6, η is 0.4, and EP is 0.6, then Sdev = 0.3 × 6 + 0.3 × 0.4 + 0.4 × 0.6 = 2.16.

[0144] The embodiment of the present application comprehensively considers the voice detection index and the object stress index, which can provide richer information dimensions, thereby more comprehensively reflecting the emotional fluctuations and stress levels of employees at work, so as to help enterprises better understand the work status of employees.

[0145] See also Figure 6 In some embodiments, the attendance voice data includes at least two attendance voice sub-data, and the voice detection index includes a voice detection sub-score corresponding to each attendance voice sub-data. Step S502 may include, but is not limited to, steps S601 to S603:

[0146] Step S601, determining a maximum speech score and a minimum speech score based on at least two speech detection sub-scores;

[0147] Step S602, determining a speech score difference based on the maximum speech score and the minimum speech score;

[0148] Step S603 , performing weighted calculation on the emotional stress score, voice score difference, attendance performance score, and task completion score to obtain the attendance score of the detected subject.

[0149] In step S601 of some embodiments, the attendance voice sub-data is a voice data segment in the attendance voice data, which is used to represent the voice data of the detection object in a specific work scenario. For example, within a preset attendance time period, an employee may attend multiple meetings. The voice data in each meeting is an attendance voice sub-data, and these attendance voice sub-data together constitute the attendance voice data. The voice detection sub-score refers to the score obtained after emotion detection of the corresponding attendance voice sub-data. The maximum voice score is the highest score among the multiple voice detection sub-scores, and the minimum voice score is the lowest score among the multiple voice detection sub-scores.

[0150] In step S602 of some embodiments, the speech score difference is the difference between the maximum speech score and the minimum speech score, which is used to reflect the amplitude of emotional fluctuation. For example, if the maximum speech score is 85 and the minimum speech score is 70, the speech score difference is 15 points; or, if the maximum speech score is 90 and the minimum speech score is 85, the speech score difference is 5 points.

[0151] In step S603 of some embodiments, the attendance score is obtained by weighted calculation of the emotional stress score, the voice score difference, the attendance performance score, and the task completion score, and the calculation formula is shown as follows (12):

[0152]

[0153] Among them, α3, β3, γ3, ω, w E3 and w P3 are weight coefficients, and these weight coefficients can be freely set according to actual needs, but must satisfy α3+β3+γ3+ω=1, w E3 +w P3 =1; VF is the difference in speech score. For example, if the weight coefficient α3 is 0.3, β3 is 0.3, γ3 is 0.3, ω is 0.1, w E3 is 0.5, w P3 is 0.5, Sattendance is 7, η is 0.4, E is 80, P is 70, and VF is 5, then Sdev = 0.3×7+0.3×0.4+0.3×(0.5×0.8+0.5×0.3)-0.1×5=1.745.

[0154] The embodiment of the present application quantifies the emotional fluctuations of employees in different work scenarios by introducing voice score differences, which not only enriches the evaluation dimensions of attendance scores, but also enables attendance scores to more comprehensively reflect employees' work status and emotional management capabilities, thereby improving the accuracy of attendance scores.

[0155] See also Figure 7In some embodiments, step S105 includes but is not limited to steps S701 to S704:

[0156] Step S701: Obtain the effective working time and post deviation time of the detection subject in the preset attendance time period;

[0157] Step S702: Calculate the ratio of effective working hours to post deviation hours to obtain the effective working ratio.

[0158] Step S703, determining a penalty score for the detection object based on a comparison result of the effective work ratio and the preset duration ratio;

[0159] Step S704 , performing subject attendance detection based on the voice detection index, subject stress index, attendance performance score, task completion score, and penalty score to obtain the subject's attendance score.

[0160] In step S701 of some embodiments, the duration of job deviation refers to the duration of time the subject is engaged in non-job duties or non-work-related activities during a preset attendance period. For example, this may include the time an employee spends browsing social media, handling personal matters, or engaging in non-work-related activities during a preset attendance period.

[0161] In step S702 of some embodiments, the effective work ratio refers to the ratio of effective work time to total attendance time, and its calculation formula is shown as follows (13):

[0162]

[0163] Among them, W r is the percentage of effective work; Tactual is the effective working time; Tnotwork is the time of job deviation.

[0164] In step S703 of some embodiments, the preset duration ratio is a pre-set threshold value used to measure the minimum effective work ratio that the detection subject should achieve within the preset attendance time period. The penalty score is a score determined based on the comparison result of the effective work ratio and the preset duration ratio, which is used to quantify the degree to which the detection subject deviates from the post within the preset attendance time period and adjust the attendance score. The penalty score corresponding to the comparison result is shown in Table 3 below:

[0165] Comparison results Penalty score The effective work ratio is less than or equal to the preset duration ratio 0.5 points The effective work ratio is greater than the preset duration ratio 0 points

[0166] Table 3

[0167] Please refer to Table 3. If the preset time ratio is 0.8 and the effective work ratio of an employee is 0.75, the penalty score is 0.5 points; or if the preset time ratio is 0.85 and the effective work ratio of an employee is 0.9, the penalty score is 0 points.

[0168] It should be noted that enterprises or organizations can set different penalty scoring rules based on actual needs. For example, an enterprise can set the maximum score for the penalty score to other values (such as 0.1 points or 1 point).

[0169] In step S704 of some embodiments, the attendance score is calculated by using the voice detection index, the subject stress index, the attendance performance score, the task completion score, and the penalty score, and the calculation formula is shown as follows (14):

[0170]

[0171] Among them, Sattendance is the attendance performance score; η is the task completion score; E is the voice detection index, is the normalized emotional index; P is the object stress index, is the normalized pressure index; α4, β4, w E4 and w P4 are weight coefficients, and these weight coefficients can be freely set according to actual needs, but must satisfy α4+β4+w E4 +w P4 =1; For example, if the weight coefficient α4 is 0.3, β4 is 0.3, w E4 is 0.2, w P4 is 0.2, Sattendance is 8, η is 0.5, E is 50, P is 70, is 0.5, then Sdev=0.3×8+0.3×0.5+0.2×0.5+0.2×0.3-0.5=2.21.

[0172] The embodiment of the present application introduces penalty scoring to quantify the extent to which employees deviate from their posts during working hours, which not only improves the accuracy of attendance scoring but also motivates employees to reduce non-work-related activities, thereby improving overall work efficiency.

[0173] It should be noted that this application calculates the time difference between the employee's clock-in time and the time of entering the company through face recognition. The calculation formula is as follows (15):

[0174] Tthresholdin=|Trecordin-Tin| (15)

[0175] Where Tthresholdin is the entry time difference; Trecordin is the clock-in time; and Tin is the entry time determined by facial recognition. For example, if an employee clocks in at 9:00 and enters at 9:15 using facial recognition, then Tthresholdin = |9:00 - 9:15| = 15 minutes.

[0176] Furthermore, this application calculates the time difference between the employee's clock-out time and the time of leaving the company determined by face recognition. The calculation formula is as follows (16):

[0177] thresholdout=|Trecordout-Tout| (16)

[0178] Where Tthresholdout is the time difference between the clock-in and clock-out times; Trecordout is the clock-in time; and Tout is the time of entry as determined by facial recognition. For example, if an employee clocks out at 18:00 and leaves the office at 18:05 as determined by facial recognition, then Tthresholdout = |18:00 - 18:05| = 5 minutes.

[0179] Furthermore, the comparison results are determined by comparing the entry time difference and the exit time difference with the time difference threshold, and judging whether there is a punch-in behavior based on the comparison results. The corresponding relationship between the comparison results and whether there is a punch-in behavior is shown in Table 4 below:

[0180] Comparison results Is there any behavior of punching in for others? The time difference is less than or equal to the time difference threshold no The time difference is greater than the time difference threshold yes The time difference is less than or equal to the time difference threshold no The time difference is greater than the time difference threshold yes

[0181] Table 4

[0182] Please refer to Table 4. If the entry time difference or the exit time difference is greater than the time difference threshold, it is considered that there is a proxy punching behavior, and a sub-penalty score is set for the proxy punching behavior. The number of proxy punching behaviors within the preset attendance time period is counted, and the abnormal behavior penalty score within the preset attendance time period is calculated based on the number of proxy punching behaviors and the corresponding set sub-penalty score. For example, if an employee has 3 abnormal behaviors within the preset attendance time period, and the sub-penalty score is set to 1 point, the final abnormal behavior penalty score is 3 points. Finally, the attendance score is adjusted according to the abnormal behavior penalty score, and the calculation principle of adjusting the attendance score by the abnormal behavior penalty score is consistent with the penalty score.

[0183] By identifying the behavior of punching in for others and setting sub-penalty scores, the embodiment of the present application can more accurately quantify the attendance of employees, thereby effectively improving the accuracy of attendance scores, and then enhancing the self-discipline of employees through standardized constraints, so as to achieve coordinated optimization of management efficiency and work efficiency.

[0184] See also Figure 8The present application also provides an attendance data detection device that can implement the above-mentioned attendance data detection method. The device includes:

[0185] The data acquisition module 801 is used to obtain the attendance voice data, biological test data, attendance performance data and task completion data of the detection subject during the preset attendance time period;

[0186] The voice detection module 802 is used to perform voice detection on the attendance voice data based on a preset voice detection model to obtain a voice detection index, which is used to indicate a quantitative value of the emotion of the detected object during the preset attendance time period;

[0187] A stress detection module 803 is configured to perform stress detection on the subject based on the biological detection data to obtain a stress index of the subject, where the stress index indicates a quantitative value of stress of the detected subject during a preset attendance period.

[0188] Performance quantification module 804, for quantifying attendance performance data to obtain attendance performance scores, and quantifying task completion data to obtain task completion scores;

[0189] The attendance scoring module 805 is used to perform attendance detection on the subject based on the voice detection index, the subject's stress index, the attendance performance score and the task completion score to obtain the attendance score of the detected subject.

[0190] The specific implementation of the attendance data detection device is substantially the same as the specific embodiment of the attendance data detection method described above, and will not be described in detail herein.

[0191] The present application also provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the attendance data detection method when executing the computer program. The electronic device can be any smart terminal including a tablet computer, an in-vehicle computer, or the like.

[0192] See also Figure 9 , Figure 9 The hardware structure of an electronic device according to another embodiment is shown. The electronic device includes:

[0193] The processor 901 can be implemented as a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;

[0194] The memory 902 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 902 can store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 902 and is called by the processor 901 to execute the attendance data detection method of the embodiments of this application.

[0195] Input / output interface 903, used to implement information input and output;

[0196] Communication interface 904, used to implement communication interaction between this device and other devices, which can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WiFi, Bluetooth, etc.);

[0197] Bus 905 , which transmits information between various components of the device (e.g., processor 901 , memory 902 , input / output interface 903 , and communication interface 904 );

[0198] The processor 901 , the memory 902 , the input / output interface 903 and the communication interface 904 are connected to each other in communication within the device via a bus 905 .

[0199] An embodiment of the present application further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned attendance data detection method is implemented.

[0200] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely arranged relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0201] The embodiments described in the embodiments of this application are intended to more clearly illustrate the technical solutions of the embodiments of this application and do not constitute a limitation on the technical solutions provided by the embodiments of this application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0202] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0203] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, i.e., they may be located in one place or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of this embodiment.

[0204] Those skilled in the art will appreciate that all or some of the steps in the methods, systems, and functional modules / units in the devices disclosed above may be implemented as software, firmware, hardware, or appropriate combinations thereof.

[0205] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0206] It should be understood that in this application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0207] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the above-mentioned units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0208] The units described above as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0209] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0210] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: various media that can store programs, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0211] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but are not intended to limit the scope of the present invention. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and essence of the present invention should be within the scope of the present invention.

Claims

1. A method for detecting attendance data, characterized in that: The method comprises: Obtaining the test subject's attendance voice data, biological test data, attendance performance data, and task completion data during the preset attendance time period; Performing voice detection on the attendance voice data based on a preset voice detection model to obtain a voice detection index, where the voice detection index is used to indicate a quantitative value of the emotion of the detection subject during the preset attendance time period; Performing a stress test on the subject based on the biological test data to obtain a stress index for the subject, wherein the stress index is used to indicate a quantitative stress value of the subject during the preset attendance time period; Quantifying the attendance performance data to obtain an attendance performance score, and quantifying the task completion data to obtain a task completion score; The subject's attendance is detected based on the voice detection index, the subject's stress index, the attendance performance score, and the task completion score to obtain the attendance score of the detected subject.

2. The method according to claim 1, characterized in that The subject attendance detection is performed based on the voice detection index, the subject stress index, the attendance performance score, and the task completion score to obtain the attendance score of the detected subject, including: determining an emotional stress score of the detection subject based on the speech detection index and the subject stress index; The subject's attendance is detected based on the emotional stress score, the attendance performance score, and the task completion score to obtain the attendance score of the detected subject.

3. The method according to claim 2, characterized in that The attendance voice data includes at least two attendance voice sub-data, the voice detection index includes a voice detection sub-score corresponding to each attendance voice sub-data, and the subject attendance detection based on the emotional stress score, the attendance performance score, and the task completion score to obtain the attendance score of the detected subject includes: determining a maximum speech score and a minimum speech score based on at least two of the speech detection sub-scores; Determining a voice score difference based on the maximum voice score and the minimum voice score, wherein the voice score difference is used to indicate a quantitative value of the degree of emotion change of the detection subject during the preset attendance time period; The emotional stress score, the voice score difference, the attendance performance score and the task completion score are weightedly calculated to obtain the attendance score of the detection subject.

4. The method according to claim 1, wherein The subject attendance detection is performed based on the voice detection index, the subject stress index, the attendance performance score, and the task completion score to obtain the attendance score of the detected subject, including: Obtaining the effective working time and post deviation time of the detection subject in the preset attendance time period; Calculate the ratio of the effective working hours to the job deviation hours to obtain the effective working percentage; Determine the penalty score of the detection object based on the comparison result of the effective work ratio and the preset time ratio; The subject's attendance is detected based on the voice detection index, the subject's stress index, the attendance performance score, the task completion score, and the penalty score to obtain the attendance score of the detected subject.

5. The method according to claim 1, wherein The step of performing stress detection on the subject based on the biological detection data to obtain a stress index of the subject includes: extracting a target detection data sequence from the biological detection data; Calculating a target power spectrum density based on the target detection data sequence, and determining low-frequency power data and high-frequency power data of the target detection data sequence according to the target power spectrum density; A ratio calculation is performed on the low-frequency power data and the high-frequency power data to obtain an object pressure index.

6. The method according to claim 1, characterized in that The quantifying of the task completion data to obtain a task completion score includes: Obtaining the object position type of the detection object; When the position type of the object is the first position type, obtaining the effective working time of the detection object in the preset attendance time period; The task completion score is determined based on the effective working time and the task completion data.

7. The method according to claim 6, characterized in that The quantifying of the task completion data to obtain a task completion score further includes: When the position type of the object is the second position type, obtaining the task allocation data of the detection object in the preset attendance time period; The task completion score is determined based on the task assignment data and the task completion data.

8. An attendance data detection device, characterized in that: The device comprises: A data acquisition module is used to obtain the attendance voice data, biological test data, attendance performance data and task completion data of the test subject during the preset attendance time period; a voice detection module, configured to perform voice detection on the attendance voice data based on a preset voice detection model to obtain a voice detection index, wherein the voice detection index is used to indicate a quantitative value of the emotion of the detection subject during the preset attendance time period; A stress detection module, configured to perform stress detection on the subject according to the biological detection data to obtain a stress index of the subject, wherein the stress index of the subject is used to indicate a quantitative stress value of the detected subject during the preset attendance time period; a performance quantification module, configured to quantify the attendance performance data to obtain an attendance performance score, and quantify the task completion data to obtain a task completion score; The attendance scoring module is used to perform subject attendance detection based on the voice detection index, the subject stress index, the attendance performance score and the task completion score to obtain the attendance score of the detected subject.

9. An electronic device, characterized in that: The electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images