Intelligent assessment data processing method

Abstract

The invention provides an intelligent assessment data processing method, and the method comprises the steps: receiving a station template graph, configured by a management end, of a target enterprise, the station template graph comprises a plurality of recognition regions, and the recognition regions are provided with corresponding assessment ends; receiving assessment data uploaded by each assessment end, and processing the corresponding identification area in the station template graph based on the assessment data to obtain a theoretical assessment graph; acquiring a station image acquired by an acquisition device, identifying the station image based on an assessment identification strategy and the station template graph to obtain update data of the assessment end, and updating the corresponding identification area based on the update data to obtain an actual assessment graph; and carrying out selection processing on the plurality of station images in a preset time period based on a video frame selection strategy to obtain an assessment backtracking video of each assessment end, and sending the actual assessment graph and the assessment backtracking video to a management end.

Description

Technical Field

[0001] The present invention relates to data processing technology, and in particular to an intelligent assessment data processing method. Background Art

[0002] Intelligent assessment data processing is the process by which enterprises use computer hardware and software technologies to effectively collect, store, process and apply data. Enterprise data can be diverse, for example, the internal management of attendance and clock-in data.

[0003] In the existing technology, companies usually use electronic software to clock in and out for attendance, and automatically generate attendance forms based on the clock-in data. The employee's attendance information is displayed through the employee's clock-in time in the attendance form, but the employee's real attendance information cannot be displayed intuitively. At the same time, when errors occur in the attendance clock-in information, for example, an employee clocks in at work within the specified clock-in time, but leaves the office after the clock-in, the company cannot conduct a retrospective review and lacks real clock-in information.

[0004] Therefore, how to visualize enterprise data to facilitate personnel viewing and ensure the accuracy of data has become an urgent problem that needs to be solved. Summary of the Invention

[0005] The embodiment of the present invention provides an intelligent assessment data processing method, which can record the real attendance information of enterprise employees and display it intuitively in the form of pictures, while retaining relevant data information to make an assessment review video for feedback viewing, thereby improving the intuitiveness and authenticity of the attendance information.

[0006] A first aspect of an embodiment of the present invention provides an intelligent assessment data processing method, comprising:

[0007] Receiving a workstation template diagram of a target enterprise configured by a management terminal, wherein the workstation template diagram includes a plurality of identification areas, each of which has a corresponding assessment terminal;

[0008] Receiving the assessment data uploaded by each assessment terminal, and processing the corresponding identification area in the workstation template diagram based on the assessment data to obtain a theoretical assessment diagram;

[0009] Acquire a workstation image acquired by an acquisition device, identify the workstation image based on an assessment recognition strategy and a workstation template map, obtain updated data of the assessment end, and update a corresponding identification area in the theoretical assessment map based on the updated data to obtain an actual assessment map;

[0010] Based on the video frame selection strategy, multiple workstation images within a preset time period are selected and processed to obtain the assessment review video of each assessment end, and the actual assessment image and the assessment review video are sent to the management end.

[0011] Optionally, in a possible implementation of the first aspect, the receiving the assessment data uploaded by each assessment terminal, and processing the corresponding identification area in the workstation template map based on the assessment data to obtain a theoretical assessment map includes:

[0012] receiving assessment data uploaded by each assessment terminal, the assessment data including attendance data and absence data, determining a first pixel value according to the attendance data, and determining a second pixel value according to the absence data;

[0013] Based on the first pixel value or the second pixel value, the border of the corresponding identification area in the workstation template image is updated by the assessment end to obtain a theoretical assessment image.

[0014] Optionally, in a possible implementation of the first aspect, acquiring the workstation image captured by the acquisition device, identifying the workstation image based on the assessment recognition strategy and the workstation template map to obtain updated data of the assessment end, and updating the corresponding identification area in the theoretical assessment map based on the updated data to obtain the actual assessment map, includes:

[0015] Retrieving the recognition template corresponding to the acquisition device in the workstation template map, using the recognition area in the recognition template as the judgment area, and obtaining the workstation image acquired by the acquisition device;

[0016] The identification template is superimposed on the workstation image, and personnel identification is performed on the image of the judgment area in the identification template to obtain updated data. Based on the updated data, the corresponding identification area in the theoretical assessment map is updated to obtain the actual assessment map.

[0017] Optionally, in a possible implementation of the first aspect, performing personnel recognition on the image in the judgment area in the recognition template to obtain update data, and updating the corresponding recognition area in the theoretical assessment map based on the update data to obtain the actual assessment map includes:

[0018] Identify the number of workstation images of personnel on the assessment terminals corresponding to each judgment area in the recognition template as the assessment judgment number;

[0019] If it is determined that the assessment judgment quantity is greater than or equal to the preset quantity, the current data of the corresponding assessment terminal is determined to be attendance data;

[0020] If it is determined that the assessment judgment number is less than the preset number, the current data of the corresponding assessment terminal is determined to be absence data;

[0021] If the current data of the assessment end is inconsistent with the assessment data, the third pixel value is retrieved as update data, and the identification area of ​​the corresponding assessment end in the theoretical assessment map is used as the update area;

[0022] The border of the update area is updated based on the update data to obtain an actual assessment map.

[0023] Optionally, in a possible implementation of the first aspect, the method further includes:

[0024] Retrieving the position attributes in the judgment area of ​​the recognition template, wherein the position attributes include R&D attributes and communication attributes;

[0025] Based on the R&D attribute, the corresponding judgment area is used as the R&D area, and based on the communication attribute, the corresponding judgment area is used as the communication area;

[0026] Conducting continuous focus assessment on the R&D areas to obtain the R&D focus of each R&D area;

[0027] Intermittent concentration determination is performed on the communication areas to obtain the communication concentration of each communication area.

[0028] Optionally, in a possible implementation of the first aspect, the performing continuous focus determination on the R&D areas to obtain the R&D focus of each R&D area includes:

[0029] Retrieving the device orientation of the display device in each R&D area, identifying the facial orientation of people in the R&D area, and recording the time period when the device orientation is opposite to the facial orientation as the first conditional time period of each R&D area;

[0030] The time period when personnel in each R&D area trigger the input device is counted as the second condition time period of each R&D area;

[0031] Obtaining a condition superposition period for each R&D area based on the intersection of the first condition period and the second condition period for each R&D area;

[0032] Select an image of each R&D area at any time during the condition superposition period as a reference image, and use images at two times adjacent to the reference image as comparison images;

[0033] Selecting the pixel point at the same position in the reference image and the comparison image as the coordinate origin, and performing coordinate processing on the reference image and the comparison image based on the coordinate origin;

[0034] Determine pixel points with different pixel values ​​in the reference image and the comparison image at the same coordinates as changed pixel points, and obtain the changed number of the changed pixel points and the total number of pixels in the reference image;

[0035] A change ratio is obtained based on the ratio of the number of changes to the total number, and when it is determined that the change ratio is less than a preset change ratio, the moment of the corresponding baseline image is used as the R&D focus moment;

[0036] The R&D focus moments are counted to obtain the R&D focus duration, and the R&D focus level of each R&D area is obtained based on the ratio of the R&D focus duration to the preset working hours;

[0037] Optionally, in a possible implementation of the first aspect, performing intermittent concentration determination on the communication areas to obtain the communication concentration of each communication area includes:

[0038] Identifying a back contour of a communication device in the communication area and a hand contour of a person in the communication area, and obtaining a time period in which the hand contour and the back contour intersect as a first judgment time period;

[0039] Identifying the head outline of the person in the communication area, and obtaining the time period during which the back outline is within the head outline as a second judgment time period;

[0040] The communication focus duration of each communication zone is obtained according to the intersection of the first judgment period and the second judgment period, and the communication focus degree of each communication zone is obtained based on the ratio of the communication focus duration to the preset working duration.

[0041] Optionally, in a possible implementation of the first aspect, selecting and processing the plurality of workstation images within a preset time period based on a video frame selection strategy to obtain an assessment review video of each assessment terminal includes:

[0042] Obtaining the identification area corresponding to the assessment end in the actual assessment map as the display area, and using the remaining identification areas as the cover area;

[0043] Determining the corresponding judgment area in the recognition template as a reserved area based on the corresponding assessment terminal, and setting the remaining judgment areas as hidden areas;

[0044] Determining that the current data of the assessment terminal is attendance data, and selecting any one of the workstation images within a first preset time period, which has a person in the reserved area, as a starting image;

[0045] selecting any one of the workstation images of personnel in the reserved area within the second preset time period as the termination image;

[0046] Determining that the current data of the assessment terminal is absence data, and selecting any image of a workstation in the reserved area without personnel within a first preset time period as a starting image;

[0047] selecting any one of the workstation images in the reserved area without personnel within a second preset time period as a termination image, wherein the preset time period includes a first preset time period and a second preset time period;

[0048] The assessment review video of each assessment terminal is obtained according to the actual assessment diagram within the preset time period, the starting diagram and the ending diagram.

[0049] Optionally, in a possible implementation of the first aspect, obtaining the assessment retrospective video of each assessment terminal according to the actual assessment graph, the start graph, and the end graph within a preset time period includes:

[0050] Retrieving a preset mask layer to mask the mask area in the actual assessment image to obtain a status frame;

[0051] Recalling a preset mask layer to mask the image corresponding to the hidden area in the recognition template above the starting image to obtain a starting frame;

[0052] Retrieving a preset mask layer to mask the image corresponding to the hidden area in the recognition template above the termination image to obtain a termination frame;

[0053] All status frames, start frames and end frames of each assessment end within a preset time period are counted to obtain the assessment retrospective video of each assessment end.

[0054] A second aspect of an embodiment of the present invention provides an intelligent assessment data processing system, comprising:

[0055] A receiving module, configured to receive a workstation template diagram of a target enterprise configured by a management terminal, wherein the workstation template diagram includes a plurality of identification areas, each of which has a corresponding assessment terminal;

[0056] A processing module, configured to receive the assessment data uploaded by each assessment terminal, and process the corresponding identification area in the workstation template diagram based on the assessment data to obtain a theoretical assessment diagram;

[0057] an identification module for acquiring a workstation image acquired by the acquisition device, identifying the workstation image based on the assessment identification strategy and the workstation template map, obtaining updated data of the assessment end, and updating the corresponding identification area in the theoretical assessment map based on the updated data to obtain an actual assessment map;

[0058] The sending module is used to select and process multiple workstation images within a preset time period based on a video frame selection strategy, obtain the assessment review video of each assessment end, and send the actual assessment image and the assessment review video to the management end.

[0059] The beneficial effects of the present invention are as follows:

[0060] 1. The present invention intuitively displays the assessment data of the enterprise in the form of pictures, making the attendance data results more real and intuitive. At the same time, the assessment data within a preset time period is obtained to generate an assessment review video, thereby improving the efficiency of the later assessment data review. On the one hand, the present invention corresponds the assessment end to the identification area in the workstation template map, processes the corresponding identification area according to the received assessment data, and obtains a theoretical assessment map. Then, the collected workstation image is identified through the assessment identification strategy and the workstation template map to obtain updated data, thereby updating the identification area corresponding to the updated data to obtain an actual assessment map, so that the displayed employee attendance results are more intuitive and easy to view. On the other hand, multiple workstation images within a preset time period are selected and processed according to the video frame selection strategy to obtain the assessment review video of each assessment end. Attendance data within a preset time period can be reviewed through the assessment review video, reducing employees' objections to the attendance results and improving the authenticity of the attendance data.

[0061] 2. The present invention updates the color of the corresponding identification area border in the theoretical assessment map based on the assessment data uploaded by the employees and the updated data obtained through identification and judgment to obtain an actual assessment map, so that the displayed attendance results are clearer and more intuitive. First, through the assessment data uploaded by each assessment terminal, the first pixel value corresponding to the attendance data and the second pixel value corresponding to the absence data are used to update the color of the corresponding identification area border in the workstation template map to obtain a theoretical assessment map. Secondly, according to the range collected by the acquisition device, the corresponding identification template is located in the workstation template map, and the judgment area in the identification template is determined. The identification template is then superimposed on the acquired workstation image, and the image in the judgment area is identified. When the number of acquired assessment judgments, that is, the number of workstation images of personnel at the assessment terminal corresponding to the judgment area, is greater than or equal to the preset number, the current data obtained at the assessment terminal is attendance data, otherwise, absence data is obtained. Finally, when it is determined that the current data at the assessment end is inconsistent with the assessment data, the third pixel value is used to update the color of the identification area border in the theoretical assessment image corresponding to the assessment end to obtain the actual assessment image, realize the calibration function of the assessment data, and make the assessment data intuitively displayed. After the workstation image recognition and verification, the actual assessment image is obtained, which improves the authenticity and intuitiveness of the attendance data.

[0062] 3. The present invention selects and processes multiple workstation images based on a video frame selection strategy to obtain an assessment review video that can view the assessment data of each assessment end on any date, thereby avoiding disputes caused by employees raising objections to attendance data and improving the efficiency of attendance data review. First, a preset masking layer is used to retain the display area in the actual assessment image corresponding to the corresponding assessment end, and the remaining masking areas are covered to obtain a status frame. The preset masking layer is used to cover the image corresponding to the hidden area in the recognition template above the obtained starting image to obtain a starting frame. The same method is used to obtain the ending frame corresponding to the ending image. All the status frames, starting frames, and ending frames of each assessment end within a preset time length are statistically combined to generate an assessment review video. Among them, the use of a preset masking layer can protect the attendance information of other enterprise employees from being leaked. Secondly, when an employee has objections to the received assessment data, he or she can submit an appeal request through the assessment end. From the appeal request, the collected workstation video can be retrieved as the appeal video based on the appeal date to determine the employee's actual attendance situation and to update and modify the assessment review video accordingly. Specifically, based on the appeal date, the first edit frame and the second edit frame corresponding to the start frame and the end frame in the assessment review video are replaced with the first replacement frame and the second replacement frame extracted from the appeal video. At the same time, the third edit frame corresponding to the status frame is highlighted to indicate that the assessment data has been updated. Finally, the updated assessment review video is sent to the management end. The generated assessment review video can be used to retrieve the assessment data in a timely manner for review, or to efficiently process the inconsistency of attendance data, update the relevant information, and improve the authenticity and reliability of the attendance data. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 This is a schematic diagram of an application scenario provided by an embodiment of the present invention;

[0064] Figure 2 This is a flow chart of an intelligent assessment data processing method provided by the present invention;

[0065] Figure 3 This is a structural diagram of an intelligent assessment data processing system provided by the present invention;

[0066] Figure 4 A schematic diagram of the hardware structure of an electronic device provided by the present invention. DETAILED DESCRIPTION

[0067] The following specific embodiments are used to describe the technical solution of the present invention in detail. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0068] like Figure 1The figure shows an application scenario diagram provided by an embodiment of the present invention. The present invention extracts a workstation template diagram based on an internal office scene of an enterprise, and by making the assessment end correspond to the identification area in the workstation template diagram, the corresponding identification area is processed according to the received assessment data to obtain a theoretical assessment diagram, and then the workstation image collected by the camera is identified through the assessment identification strategy and the workstation template diagram, and it is judged whether there is a person at the current workstation to obtain updated data, thereby updating the identification area corresponding to the updated data to obtain an actual assessment diagram. Therefore, the assessment data can be displayed in the form of a picture. At the same time, the collected workstation image is selected and processed according to the video frame selection strategy to obtain the assessment review video of each assessment end, and the obtained actual assessment diagram and assessment review video are sent to the management end to realize the storage of real attendance information and improve the authenticity of attendance data. There is no limit on the number of office employees in the enterprise.

[0069] like Figure 2 As shown, a first aspect of an embodiment of the present invention provides an intelligent assessment data processing method, including S1-S4:

[0070] S1, receiving a workstation template map of a target enterprise configured by a management terminal, wherein the workstation template map includes a plurality of identification areas, and each identification area has a corresponding assessment terminal.

[0071] In actual applications, the punch-in time is displayed through a spreadsheet, which makes the assessment data display not intuitive. Therefore, it is necessary to first receive the workstation template map of the target enterprise configured by the management end. The received workstation template map contains multiple identification areas. At the same time, each identification area also has a corresponding assessment end.

[0072] Among them, the workstation template map is a template map of the working location of the enterprise employees. For example, it is a template map obtained by dividing the employee workstations in the enterprise office area. The identification area is the area for identifying personnel. The identification area can be the position area corresponding to the employee workstation in the workstation template map. For example, corresponding identification areas are set for multiple different workstation position areas. Employee A's workstation corresponds to identification area No. 1 in the workstation template map, employee B's workstation corresponds to identification area No. 2 in the workstation template map, and employee C's workstation corresponds to identification area No. 3 in the workstation template map. The assessment terminal can be the mobile terminal corresponding to the employee. The assessment terminal corresponds to the identification area one-to-one. For example, it can be a mobile phone, tablet, etc. Among them, assessment terminal No. 1 corresponds to identification area No. 1, assessment terminal No. 2 corresponds to identification area No. 2, and assessment terminal No. 3 corresponds to identification area No. 3.

[0073] The present invention makes one-to-one correspondence between the identification area of ​​the workstation template map and the assessment end, making it convenient for subsequent personnel to update the corresponding identification area when uploading assessment data on the assessment end. At the same time, the obtained workstation template map is also the basis for subsequent workstation image recognition and judgment.

[0074] S2, receiving the assessment data uploaded by each assessment terminal, and processing the corresponding identification area in the workstation template diagram based on the assessment data to obtain a theoretical assessment diagram.

[0075] In actual applications, it is necessary to process the corresponding identification areas in the workstation template diagram based on the assessment data uploaded by the employees on the assessment terminal to obtain a theoretical assessment diagram.

[0076] Among them, the assessment data is the assessment data of employee attendance, and the theoretical assessment image is the assessment image obtained after the identification area is processed by the assessment data. For example, the identification area corresponding to the corresponding attendance data in the workstation template image is marked green, and the identification area corresponding to the absence data is marked red. The image obtained after marking is the theoretical assessment image.

[0077] In some embodiments, step S2 (receiving the assessment data uploaded by each assessment terminal, and processing the corresponding identification area in the workstation template map based on the assessment data to obtain a theoretical assessment map) includes S21-S22:

[0078] S21, receiving assessment data uploaded by each assessment terminal, wherein the assessment data includes attendance data and absence data, determining a first pixel value according to the attendance data, and determining a second pixel value according to the absence data.

[0079] It can be understood that the assessment data of the corresponding identification area can be obtained by uploading the attendance data and absence data to the assessment terminal. In order to display and distinguish the identification areas corresponding to attendance and absence, it is determined that the attendance data corresponds to the first pixel value and the absence data corresponds to the second pixel value.

[0080] Among them, the first pixel value is the pixel value corresponding to the attendance data, and the second pixel value is the pixel value corresponding to the absence data. For example, the first pixel value corresponding to the attendance data can be green, and the second pixel value corresponding to the absence data can be red, which is not limited here.

[0081] The present invention uses the first pixel value and the second pixel value to distinguish and display the attendance data and the absence data, so that the attendance data displayed in the picture is more intuitive and clear.

[0082] S22, based on the assessment end, updating the border of the corresponding identification area in the workstation template image with the first pixel value or the second pixel value to obtain a theoretical assessment image.

[0083] It can be understood that after receiving the assessment data uploaded by the assessment end, the border of the identification area in the work station template corresponding to the attendance data is updated with the first pixel through the identification area and assessment data corresponding to the assessment end, and the border of the identification area in the work station template corresponding to the absence data is updated with the second pixel.

[0084] For example, employee A uploads attendance data on mobile phone No. 1, employee B uploads absence data on mobile phone No. 2, and employee C uploads attendance data on mobile phone No. 3. Employee A's workstation corresponds to identification area No. 1 in the workstation template diagram, employee B's workstation corresponds to identification area No. 2 in the workstation template diagram, and employee C's workstation corresponds to identification area No. 3 in the workstation template diagram. The first pixel value corresponding to the attendance data can be green, and the second pixel value corresponding to the absence data can be red. Therefore, the border of identification area No. 1 is updated and displayed in green, the border of identification area No. 2 is updated and displayed in red, and the border of identification area No. 3 is updated and displayed in green, and an updated theoretical assessment diagram is obtained.

[0085] S3, obtaining the workstation image collected by the collection device, identifying the workstation image based on the assessment identification strategy and the workstation template map, obtaining updated data of the assessment end, and updating the corresponding identification area in the theoretical assessment map based on the updated data to obtain an actual assessment map.

[0086] In actual applications, since there is a phenomenon that people leave immediately after clocking in, in order to calibrate the assessment data, the workstation image can be collected by the acquisition device, and the collected workstation image can be identified according to the assessment recognition strategy and the workstation template map. After identification, updated data is obtained and sent to the assessment end. At the same time, the corresponding identification area in the theoretical assessment map is updated according to the updated data to obtain the actual assessment map.

[0087] It can be understood that the collection area of ​​the collection device is fixed, so the target area can contain multiple collection devices, where the collection device can be a camera, the update data is the data for updating the recognition area, and the actual assessment image is the assessment image obtained after the recognition area is updated with the updated data.

[0088] In some embodiments, step S3 (obtaining a workstation image acquired by an acquisition device, identifying the workstation image based on an assessment recognition strategy and a workstation template map, obtaining updated data of the assessment end, and updating a corresponding identification area in the theoretical assessment map based on the updated data to obtain an actual assessment map) includes S31-S32:

[0089] S31, retrieve the recognition template corresponding to the acquisition device in the workstation template map, use the recognition area in the recognition template as the judgment area, and obtain the workstation image acquired by the acquisition device.

[0090] It is understood that in order to facilitate the recognition and processing of the collected workstation image, the recognition template corresponding to the acquisition device in the workstation template map is located, and a position area in the recognition template corresponding to the recognition area in the workstation template map is obtained. This area in the recognition template is used as the judgment area, and the recognition area and the judgment area are one-to-one corresponding. At the same time, the workstation image is obtained through the acquisition device. For example, the acquisition area of ​​the acquisition device is fixed, so the workstation template map can be intercepted through the fixed acquisition area to obtain the recognition template. Then, the judgment area No. 1 in the recognition template corresponds to the recognition area No. 1 in the workstation template map, and the judgment area No. 2 in the recognition template corresponds to the recognition area No. 2 in the workstation template map. At the same time, the workstation image is captured by the camera.

[0091] Among them, the corresponding recognition template is positioned in the workstation template map according to the range collected by the collection device, and the workstation image is the image collected by the collection device.

[0092] S32, superimposing the recognition template on top of the workstation image, performing personnel recognition on the image of the judgment area in the recognition template to obtain updated data, and updating the corresponding recognition area in the theoretical assessment map based on the updated data to obtain the actual assessment map.

[0093] It can be understood that to identify the collected workstation image, it is necessary to superimpose the identification template on top of the workstation image, and obtain updated data by performing personnel identification on the image of the judgment area in the identification template. Based on the updated data, the corresponding identification area in the theoretical assessment map is updated to obtain the actual assessment map.

[0094] For example, the assessment data uploaded by the employee corresponding to identification area No. 1 on the assessment end is attendance, the assessment data uploaded by the employee corresponding to identification area No. 2 on the assessment end is absence, and the assessment data uploaded by the employee corresponding to identification area No. 3 on the assessment end is attendance. By identifying the workstation image, it is found that identification area No. 1 corresponds to employee attendance, identification area No. 2 corresponds to employee attendance, and identification area No. 3 corresponds to employee absence. Since the uploaded assessment data corresponding to identification areas No. 2 and No. 3 are inconsistent with the identified results, the updated data corresponding to identification areas No. 2 and No. 3 are obtained, and the colors of the borders of the identification areas No. 2 and No. 3 are updated to obtain the actual assessment picture.

[0095] In some embodiments, step S32 (performing personnel recognition on the image in the judgment area of ​​the recognition template to obtain updated data, and updating the corresponding recognition area in the theoretical assessment map based on the updated data to obtain the actual assessment map) includes S321-S325:

[0096] S321, identifying the number of workstation images of personnel on the assessment end corresponding to each judgment area in the recognition template as the assessment judgment number.

[0097] In actual applications, workstation images will be collected multiple times during working hours, and personnel identification will be performed in the corresponding judgment areas in order to obtain more accurate assessment data. Personnel identification in images can be achieved through existing technologies, such as static headcount, etc., which are existing technologies and will not be elaborated here.

[0098] The number of workstation images of personnel captured by the assessment end is used as the assessment judgment quantity. For example, when acquiring workstation images, each image is taken at an interval of one hour, resulting in eight images being obtained in a day. Of these eight images, eight contain images of personnel in the workstation images corresponding to judgment area 1, and six contain images of personnel in the workstation images corresponding to judgment area 2. Therefore, the assessment judgment quantity corresponding to judgment area 1 is 8, and the assessment judgment quantity corresponding to judgment area 2 is 6. This is the number of images collected to determine whether a workstation is occupied. If the number is greater than the preset number, it indicates that the person is present and working. If the person is absent from their seat for a long time, the corresponding number is smaller.

[0099] S322: If it is determined that the assessment judgment quantity is greater than or equal to a preset quantity, the current data of the corresponding assessment terminal is determined to be attendance data.

[0100] It is understandable that company employees may leave their workstations for short periods of time due to meetings, getting water, etc., and some workstation images in which people cannot be identified will appear in the collected workstation images. Therefore, the number of workstation images in which people can be identified is preset to obtain a preset number.

[0101] When the number of assessment judgments is greater than or equal to the preset number, the current data of the corresponding assessment terminal is determined to be attendance data. For example, if the preset number is 5, the assessment judgment number corresponding to judgment area 1 is 8, and the assessment judgment number corresponding to judgment area 2 is 6. Since 8>5 and 6>5, the current data of assessment terminal 1 is attendance data, and the current data of assessment terminal 2 is also attendance data.

[0102] S323: If it is determined that the assessment judgment number is less than a preset number, the current data of the corresponding assessment terminal is determined to be absence data.

[0103] It is understood that when the number of assessment judgments is less than the preset number, the current data of the corresponding assessment terminal is determined to be absence data. For example, if the preset number is 5, the assessment judgment number corresponding to the judgment area 3 is identified as 4. Since 4<5, the current data of the assessment terminal 3 is absence data.

[0104] S324: If the current data of the assessment end is inconsistent with the assessment data, retrieve the third pixel value as update data, and use the identification area of ​​the corresponding assessment end in the theoretical assessment diagram as the update area.

[0105] It can be understood that when the current data of the assessment end obtained through identification and judgment is inconsistent with the uploaded assessment data, the third pixel value can be called as the update data. At the same time, the identification area corresponding to the assessment end in the theoretical assessment map is used as the update area.

[0106] Among them, the third pixel value is a pixel value that distinguishes the first pixel value from the second pixel value, and can be yellow, purple, etc. For example: Employee B uploads the corresponding assessment data of identification area No. 2 on assessment terminal No. 2 as absence data, and employee C uploads the corresponding assessment data of identification area No. 3 on assessment terminal No. 3 as attendance data. Due to changes in the situation, employee B works on that day, and then the current data of assessment terminal No. 2 is determined to be attendance data based on personnel recognition of the workstation image. Because employee C is not present in the corresponding identification area No. 3 in the extracted workstation image, the current data of assessment terminal No. 3 is determined to be absence data based on personnel recognition of the workstation image. Because the assessment data corresponding to No. 2 and No. 3 are inconsistent with the current data, the updated data of identification area No. 2 and No. 3 are determined, wherein the third pixel value of the border of No. 2 is yellow, and the third pixel value of the border of identification area No. 3 is purple. At the same time, identification areas No. 2 and No. 3 in the theoretical assessment map are updated areas.

[0107] S325, updating the border of the update area based on the update data to obtain an actual assessment diagram.

[0108] It can be understood that the actual assessment image is obtained by using the third pixel value to update the border of the update area. For example, if the third pixel value of the border of identification area 2 is determined to be yellow, and the third pixel value of the border of identification area 3 is determined to be purple, the red corresponding to the border of identification area 2 in the obtained theoretical assessment image is updated to yellow, and the green corresponding to the border of identification area 3 is updated to purple, thereby obtaining the actual assessment image.

[0109] In some embodiments, it further includes:

[0110] A1, retrieve the position attributes in the judgment area of ​​the recognition template, wherein the position attributes include R&D attributes and communication attributes.

[0111] It should be noted that since the job attributes of the personnel corresponding to different workstations are different, for example, some R&D personnel need to use the keyboard for a long time to work, while some personnel may need to use tools such as mobile phones to communicate at work. Therefore, the work conditions of different judgment areas can be identified and judged according to different job attributes in order to obtain the work concentration of the personnel.

[0112] Among them, the position attributes are the work function attributes of the personnel corresponding to the judgment area, including R&D attributes and communication attributes. The R&D attributes are the functional attributes corresponding to the R&D personnel, such as the personnel corresponding to the judgment area are R&D personnel. The communication attributes are the attributes of the personnel corresponding to the judgment area who need to communicate at work, such as the functional attributes corresponding to human resources, customer service, sales, etc.

[0113] Through the above implementation, the job attributes corresponding to each judgment area can be determined, so that the work concentration of personnel in different areas can be identified and judged according to the job attributes.

[0114] A2: Based on the R&D attribute, the corresponding judgment area is used as the R&D area, and based on the communication attribute, the corresponding judgment area is used as the communication area.

[0115] It can be understood that the R&D area is a judgment area corresponding to the R&D attribute, and the communication area is a judgment area corresponding to the communication attribute.

[0116] A3, performing a continuous focus judgment on the R&D areas to obtain the R&D focus of each R&D area.

[0117] It is understandable that since the nature of the work corresponding to R&D requires personnel to concentrate for a long time, such as long-term execution of code input or modification, the R&D area can be continuously identified and judged to obtain R&D concentration.

[0118] Among them, R&D focus refers to the degree of focus of the corresponding personnel in the R&D area.

[0119] In some embodiments, step A3 (determining the continuity of the R&D areas to obtain the R&D focus of each R&D area) includes:

[0120] A31, retrieve the device orientation of the display device in each R&D area, identify the facial orientation of the people in the R&D area, and record the time period when the device orientation is opposite to the facial orientation as the first conditional time period of each R&D area.

[0121] It is understandable that when people are concentrating on their work, they need to face the display device at the corresponding workstation. Therefore, the first conditional time period can be determined based on the device orientation and facial orientation.

[0122] Among them, the display device is the device that displays work content in the R&D area, such as a computer, the device orientation is the screen orientation of the display device, such as towards the personnel, the face orientation is the face orientation of the personnel in the R&D area, and the first conditional period is the time period when the personnel are facing the display device.

[0123] It is not difficult to understand that when the preliminary condition for judging whether a person is working is that the person needs to face the computer, therefore, when it is recognized that the device orientation is opposite to the face orientation, it can be said that the person is facing the computer, which can be preliminarily indicated that the person is working. Therefore, the time period when the device orientation is opposite to the face orientation can be used as the first conditional time period for each R&D area.

[0124] A32, counting the time period when personnel in each R&D area trigger the input device as the second condition time period of each R&D area.

[0125] It should be noted that when personnel are concentrating on their work, they will continuously trigger the input devices in the R&D area, such as triggering the keyboard or mouse for a long time, so that the corresponding period can be used as the second condition period.

[0126] The input device is a device for inputting work content, such as a keyboard, a mouse, etc., and the second condition period is a time period when a person triggers the input device.

[0127] Through the above implementation, the present invention can obtain the second conditional period so as to subsequently determine the corresponding R&D focus.

[0128] A33: Obtain a conditional superposition period for each R&D area according to the intersection of the first conditional period and the second conditional period for each R&D area.

[0129] It can be understood that the conditional superposition period is the intersection period of the first conditional period and the second conditional period.

[0130] A34, selecting an image of each R&D area at any time during the condition superposition period as a reference image, and using images at two times adjacent to the reference image as comparison images.

[0131] It is understandable that when the personnel's concentration is higher, the amplitude of the action change within a certain period of time is smaller. Therefore, images can be selected within the conditional superposition period to compare the action positions, thereby obtaining the corresponding R&D concentration.

[0132] The reference image is an image used to compare the amplitude of motion changes, that is, an image within the conditional superposition period; the comparison image is an image for motion comparison with the reference image, that is, an image at two adjacent moments to the reference image.

[0133] A35, selects the pixel point at the same position in the reference image and the comparison image as the coordinate origin, and performs coordinate processing on the reference image and the comparison image based on the coordinate origin.

[0134] It can be understood that in order to compare the positions of the reference image and the comparison image, the pixel points at the same position will be selected as the coordinate origin. Generally, the reference image and the comparison image will be coordinate-processed to facilitate the subsequent position comparison of the reference image and the comparison image in order to obtain R&D focus.

[0135] A36, determining pixel points with different pixel values ​​in the reference image and the comparison image at the same coordinates as changed pixel points, obtaining the changed number of the changed pixel points, and the total number of pixel points in the reference image.

[0136] It is understandable that when the pixel values ​​at the same position in two images are inconsistent, it means that the corresponding personnel have moved at the corresponding parts at adjacent moments. Therefore, the pixel points at the corresponding positions can be used as changed pixel points to count the number of changed pixel points and obtain the number of changes, which is convenient for subsequent determination of R&D focus.

[0137] The changed pixels are pixels at the same position but with different pixel values, the changed number is the number of changed pixels, and the total number is the total number of corresponding pixels in the reference image.

[0138] A37, according to the ratio of the said change quantity and the total quantity, obtains the change ratio, and when it is determined that the change ratio is less than the preset change ratio, uses the moment of the corresponding reference image as the R&D focus moment.

[0139] It can be understood that the change ratio is the ratio of the number of changes to the total number, and the preset change ratio is the preset position change ratio.

[0140] It is not difficult to understand that when the calculated proportion is smaller than the preset change proportion, it means that the number of pixel offsets between the selected comparison image and the reference image is small, that is, the amplitude of the person's movement is small, which can indicate that the person is concentrating on work. Therefore, the moment corresponding to the reference image can be used as the R&D concentration moment.

[0141] Among them, R&D focus moments are the moments when R&D personnel focus on their work.

[0142] A38, counting the R&D focus moments to obtain R&D focus duration, and based on the ratio of the R&D focus duration to the preset working hours, obtaining the R&D focus of each R&D area.

[0143] It is understandable that the R&D focus time is the time during which R&D personnel focus on their work, and the preset working time is the pre-set working time, such as 8 hours.

[0144] It is not difficult to understand that the reference images are selected in turn in the conditional superposition period, and the adjacent images are selected as comparison images, so as to determine the R&D focus moment, and the R&D focus moment is counted to obtain the R&D focus duration.

[0145] A4, performing intermittent concentration determination on the communication area to obtain the communication concentration of each communication area.

[0146] It is understandable that, since the nature of the work corresponding to the communication attribute requires personnel to communicate by phone from time to time, the communication area can be intermittently identified and judged in order to obtain the communication concentration.

[0147] Among them, communication concentration refers to the degree of concentration of the work of the corresponding personnel in the communication area.

[0148] In some embodiments, step A4 (determining the intermittent concentration of the communication zones to obtain the communication concentration of each communication zone) includes:

[0149] A41, identifying the back contour of the communication device in the communication area and the hand contour of the person in the communication area, and obtaining a time period in which the hand contour and the back contour have an intersection as a first judgment time period.

[0150] It can be understood that in order to identify whether the people in the communication area are communicating normally, the intersection of the contours of the people holding the phone and answering the phone at the ear in the communication area can be identified. When the people are communicating normally, they will hold the phone. Therefore, the time period when the hand contour and the back contour have an intersection can be used as the first judgment period.

[0151] Among them, the communication device is a device for work communication, such as a telephone, the back contour is the device contour corresponding to the back of the communication device, the hand contour is the contour of the hand of the person in the communication area, and the first judgment period is the time period when the hand contour and the back contour have an intersection.

[0152] A42, identifying the head outline of the person in the communication area, and obtaining a time period during which the back outline is within the head outline as a second judgment time period.

[0153] It can be understood that the head outline is the outline of the head of the person in the communication area, and the second judgment period is the period when the face outline is within the head outline.

[0154] A43: Obtain a communication focus duration of each communication zone based on the intersection of the first judgment period and the second judgment period, and obtain a communication focus degree of each communication zone based on a ratio of the communication focus duration to the preset working time.

[0155] It can be understood that the longer the period when the back contour is in the head contour, the longer the person spends on work communication. Then, based on the intersection of the first judgment period and the second judgment period, the communication concentration time corresponding to the communication area can be obtained, so as to calculate the ratio with the preset working time and obtain the communication concentration.

[0156] Among them, the communication focus time is the working time that people in the communication area focus on communication, and the communication concentration level is the degree of concentration of people in the communication area on the corresponding work.

[0157] S4, based on the video frame selection strategy, multiple workstation images within a preset time period are selected and processed to obtain the assessment review video of each assessment end, and the actual assessment image and the assessment review video are sent to the management end.

[0158] In actual applications, in order to facilitate personnel to review the assessment data, the relevant assessment data will be collected, retained and sent to the management end.

[0159] Therefore, the obtained workstation images are selected and processed according to the video frame selection strategy to obtain the assessment review video of each assessment terminal. The obtained actual assessment image and assessment review video are sent to the management terminal. The preset time period is a pre-set time period for selecting workstation images, for example, 8:00-17:00 in a day, which means that the workstation images selected for processing are those within the preset time period.

[0160] The assessment review video is a video that can review the assessment data. For example, multiple selected assessment data images are combined into a video.

[0161] In some embodiments, step S4 (selecting and processing the plurality of workstation images within a preset time period based on a video frame selection strategy to obtain an assessment review video of each assessment terminal) includes S41-S47:

[0162] S41, obtaining the identification area corresponding to the assessment end in the actual assessment map as the display area, and using the remaining identification areas as the cover area.

[0163] In actual applications, the collection device will capture the private information of other employees. Therefore, the following masking scheme is used to distinguish the attendance data of each assessment end and obtain a separate assessment review video for each assessment end.

[0164] It is understood that when obtaining attendance data for each assessment terminal, the identification area corresponding to the corresponding assessment terminal in the actual assessment image is used as the display area, and the remaining identification areas are used as masked areas. For example, when selecting and processing the assessment data corresponding to assessment terminal No. 1 and obtaining the assessment review video for assessment terminal No. 1, the identification area No. 1 in the actual assessment image corresponding to assessment terminal No. 1 is used as the display area, and the remaining identification areas No. 2, No. 3, etc. are used as masked areas.

[0165] The present invention subsequently distinguishes the assessment data of each assessment end by using a preset mask layer, thereby protecting the attendance information of each enterprise employee.

[0166] S42: determining the corresponding judgment area in the recognition template as a reserved area based on the corresponding assessment terminal, and setting the remaining judgment areas as hidden areas.

[0167] It is understood that when acquiring attendance data for each assessment terminal, the judgment area corresponding to the corresponding assessment terminal in the identification template is reserved as the reserved area, and the remaining judgment areas are hidden areas. For example, the judgment area 1 in the identification template corresponding to assessment terminal 1 is reserved as the reserved area, and the remaining judgment areas such as 2 and 3 are hidden areas.

[0168] S43, determining that the current data of the assessment terminal is attendance data, and selecting any one of the workstation images within a first preset time period, which has personnel in the reserved area, as a starting image.

[0169] It can be understood that when the current data of the assessment end is determined to be attendance data after processing, a workstation image with personnel in the reserved area corresponding to the assessment end is selected from the workstation images obtained within the first preset time period, and this workstation image is used as the starting image.

[0170] The first preset time period is a time period determined in advance by humans, for example, 8:00-12:00 in the morning.

[0171] For example: determine that the No. 1 assessment terminal corresponding to the No. 1 identification area is the attendance data, select an image of a workstation with someone in the No. 1 reserved area between 8:00 am and 12:00 pm, and select this selected workstation image as the starting image.

[0172] S44, selecting any one of the workstation images of personnel in the reserved area within the second preset time period as the termination image.

[0173] It can be understood that when the current data of the assessment end is determined to be attendance data after processing, a workstation image with personnel in the reserved area corresponding to the assessment end is selected from the workstation images obtained within the second preset time period, and this workstation image is used as the termination image.

[0174] The second preset time period is a time period determined in advance, for example, 14:00-17:00.

[0175] For example: determine that the No. 1 assessment terminal corresponding to the No. 1 identification area is the attendance data, select a workstation image with someone sitting in the No. 1 reserved area between 14:00-17:00, and the selected workstation image is the termination image.

[0176] S45, determining that the current data of the assessment terminal is absence data, and selecting any workstation image in which no personnel are present in the reserved area within a first preset time period as a starting image.

[0177] It can be understood that when it is determined that the current data of the assessment end is absence data after processing, a workstation image without personnel in the reserved area corresponding to the assessment end is selected from the workstation images obtained within the first preset time period, and this workstation image is used as the starting image.

[0178] For example: determine that the No. 3 assessment terminal corresponding to the No. 3 identification area is absent data, select a workstation image with no one sitting in the No. 3 reserved area between 8:00 am and 12:00 pm, and use the selected workstation image as the starting image.

[0179] S46 , selecting any one of the workstation images in the reserved area without personnel within a second preset time period as a termination image, wherein the preset time period includes a first preset time period and a second preset time period.

[0180] It can be understood that when it is determined that the current data of the assessment end is absence data after processing, a workstation image without personnel in the reserved area corresponding to the assessment end is selected from the workstation images obtained within the second preset time period, and this workstation image is used as the termination image.

[0181] For example: determine that the No. 3 assessment terminal corresponding to the No. 3 identification area is absent data, select a workstation image with no one sitting in the No. 3 reserved area between 14:00-17:00 in the morning, and the selected workstation image is the termination image.

[0182] S47, obtaining an assessment retrospective video of each assessment terminal according to the actual assessment graph within a preset time period, the starting graph and the ending graph.

[0183] It can be understood that the assessment review video is a video composed of the actual assessment picture, starting picture, and ending picture within a preset time length.

[0184] The preset duration is manually set, such as one month. The assessment review video corresponding to each assessment terminal includes all actual assessment images, starting images, and ending images within the preset duration. For example, the assessment review video corresponding to assessment terminal No. 1 is a video consisting of the actual assessment images, starting images, and ending images corresponding to identification zone No. 1 for each day within a continuous month.

[0185] In some embodiments, step S47 (obtaining the assessment retrospective video of each assessment terminal according to the actual assessment graph, the start graph, and the end graph within the preset time period) includes S471-S474:

[0186] S471, calling a preset mask layer to mask the mask area in the actual assessment image to obtain a status frame.

[0187] It is understandable that in order to protect the assessment data of corporate employees in the actual assessment chart from being leaked, only the display area information in the actual assessment chart is displayed, that is, only the assessment data of the corresponding assessment end is displayed, and the masked area is masked. Therefore, it is necessary to call the preset mask layer, wherein the preset mask layer is a layer preset artificially for masking, such as a mosaic layer, etc. The masked area in the actual assessment chart is masked to obtain a status frame. For example: in the actual assessment chart, identification area No. 1 is the display area, and the masked area in the actual assessment chart is masked using the preset mask layer, and the masked actual assessment chart is used as the status frame.

[0188] S472, calling a preset mask layer to mask the image corresponding to the hidden area in the recognition template above the starting image to obtain a starting frame.

[0189] It can be understood that the preset mask layer is called to cover the recognition template above the starting image, the image corresponding to the reserved area in the corresponding recognition template in the starting image is retained, and the image corresponding to the hidden area in the recognition template above the starting image is covered. The masked starting image obtained is the starting frame.

[0190] For example: get the starting image corresponding to workstation No. 1, place the recognition template on this starting image, get judgment area No. 1 as the reserved area, and the remaining judgment areas No. 2, No. 3, etc. as the hidden area, use the preset mask layer to mask the corresponding image in the mask area through the recognition template, and get the masked starting image as the starting frame.

[0191] S473, calling a preset mask layer to mask the image corresponding to the hidden area in the recognition template above the termination image to obtain a termination frame.

[0192] It can be understood that the preset mask layer is called to cover the recognition template above the termination image, the image corresponding to the reserved area in the recognition template corresponding to the termination image is retained, and the image corresponding to the hidden area in the recognition template above the termination image is covered. The obtained covered termination image is the termination frame.

[0193] For example: get the termination image corresponding to workstation No. 1, place the recognition template on this termination image, get judgment area No. 1 as the reserved area, and the remaining judgment areas No. 2, No. 3, etc. as the hidden area, use the preset mask layer to mask the corresponding image in the mask area through the recognition template, and the masked termination image is the termination frame.

[0194] S474, counting all status frames, start frames and end frames of each assessment terminal within a preset time period to obtain the assessment retrospective video of each assessment terminal.

[0195] It can be understood that the assessment review video is composed of all status frames, start frames and end frames of each assessment end within a preset time length.

[0196] The assessment review video corresponding to each assessment endpoint is a video consisting of the actual assessment image, start image, and end image within the preset duration, masked to obtain the corresponding status frames, start frames, and end frames. For example, starting from October 1st, the status frames, start frames, and end frames of each assessment endpoint are counted daily, and these daily status frames, start frames, and end frames are combined into a daily assessment review video. For a month, the status frames, start frames, and end frames of each assessment endpoint are counted continuously, and the daily assessment review videos are combined into a monthly assessment review video.

[0197] Based on the above embodiment, the present invention also includes B1-B2:

[0198] B1, binding the assessment data uploaded by the assessment terminal with the corresponding identification area in the actual assessment map.

[0199] It can be understood that there is a one-to-one correspondence between the assessment end and the identification area in the actual assessment map, so the assessment data uploaded by the assessment end can be bound one-to-one with the corresponding identification area in the actual assessment map.

[0200] B2, determining that the management end triggers any one of the identification areas in the actual assessment map, and retrieves the assessment data corresponding to the corresponding identification area for display.

[0201] It is understood that the management terminal can view the assessment data corresponding to any identification area. Therefore, when the management terminal triggers any identification area in the actual assessment map, the assessment data corresponding to the corresponding identification area will be retrieved and displayed. For example, if the attendance data uploaded by employee No. 1 is processed and the current data is determined to be attendance data, the border of identification area No. 1 in the actual assessment map is green. If the management terminal needs to view the assessment data corresponding to employee No. 1, the management terminal clicks on identification area No. 1 in the actual assessment map to trigger it, and the attendance data of identification area No. 1 will be displayed.

[0202] On the basis of the above embodiments, the present invention also includes C1-C3:

[0203] C1, receiving the appeal request from the assessment end, parsing the appeal request to obtain the appeal date, and using the corresponding assessment end as the appeal end, and using the identification area corresponding to the appeal end as the appeal area.

[0204] In real-world scenarios, occasional situations can arise, such as employees attending meetings or getting water. This can lead to deviations in the current data obtained from the recognition and judgment of workstation images extracted within a preset time period. To protect the accuracy of employee assessment data, employees are given the right to appeal on the assessment end. For example, eight workstation images are captured hourly throughout the day, but an employee is absent due to a meeting or getting water during the capture. This results in only four images of the employee's workstation, less than the preset number of five. Consequently, the current data in the corresponding identification area in the actual assessment image will be judged as absent. Therefore, if an employee disagrees with the assessment data, they can submit an appeal request on the assessment end.

[0205] It's understandable that the appeal request can be parsed to the appeal date, where the appeal date is the date corresponding to the inconsistency in the assessment data. The assessment terminal that submitted the appeal request is designated as the appeal terminal, and the identification area corresponding to the appeal terminal is designated as the appeal area. For example, Assessment Terminal 3 receives the assessment data and finds that the border of Identification Area 3 in the actual assessment image for October 4th is purple, indicating that the uploaded data is attendance data. However, it identifies the data as absence data, which Employee C objects to. Therefore, Employee C submits an appeal request, making Assessment Terminal 3 the appeal terminal and Identification Area 3 in the actual assessment image the appeal area.

[0206] C2: Determine a corresponding collection device as the complaint device based on the complaint area, and obtain the workstation video collected by the complaint device as the complaint video according to the complaint date.

[0207] It is understood that the complaint area has a corresponding collection device. The corresponding collection device will be determined as the complaint device, and the workstation video captured by the complaint device will be obtained as the complaint video based on the complaint date. For example, if camera A captured workstation 3, the video captured by camera A at workstations 10 and 4 will be used as the complaint video.

[0208] C3, updating the assessment review video of the appeal end according to the appeal video, and sending the updated assessment review video to the management end.

[0209] It is understandable that the assessment review video corresponding to the appeal end is updated through the appeal video, and the updated assessment review video is sent to the management end.

[0210] In some embodiments, step C3 (updating the assessment review video of the appeal terminal according to the appeal video, and sending the updated assessment review video to the management terminal) includes C31-C35:

[0211] C31, locating the corresponding start frame in the assessment review video of the appeal end according to the appeal date as the first editing frame, the corresponding end frame as the second editing frame, and the corresponding status frame as the third editing frame.

[0212] It is understandable that the appeal date can be used to locate the start frame, end frame, and status frame corresponding to the appeal date in the assessment review video corresponding to the appeal end, and the corresponding start frame can be used as the first editing frame, the end frame as the second editing frame, and the status frame as the third editing frame. For example, if the appeal date is October 4, the start frame of October 4 in the assessment review video corresponding to the appeal end No. 3 can be used as the first editing frame, the end frame as the second editing frame, and the status frame as the third editing frame.

[0213] C32, highlighting the display area in the third editing frame.

[0214] It is understandable that, in order to facilitate subsequent viewing by the administrator, the display area in the third editing frame is highlighted.

[0215] C33 : Based on the first preset time period, extract the image of the workstation with personnel in the complaint area in the complaint video as a first replacement frame.

[0216] It can be understood that, within the first preset time period in the complaint video, an image of a workstation with personnel in the complaint area is extracted as the first replacement frame.

[0217] The first replacement frame is an image that replaces the first edited frame. For example, in the workstation video obtained on October 4, a workstation image of a person at workstation 3 is extracted between 8:00 AM and 12:00 PM. This workstation image is the first replacement frame.

[0218] C34. Based on the second preset time period, extract the image of the workstation with personnel in the complaint area in the complaint video as a second replacement frame.

[0219] It can be understood that, within the second preset time period in the complaint video, an image of a workstation with personnel in the complaint area is extracted as the second replacement frame.

[0220] The second replacement frame is an image that replaces the second edited frame. For example, in the workstation video of October 4, an image of a person at workstation 3 is extracted between 14:00 and 17:00, and the obtained image is the second replacement frame.

[0221] C35, replace and update the first edit frame according to the first replacement frame, and replace and update the second edit frame according to the second replacement frame, and send the updated assessment review video to the management end.

[0222] It is understood that the first edited frame in the assessment review video is replaced with the first replacement frame, and the second edited frame is replaced with the second replacement frame, and the updated assessment review video is sent to the management terminal. For example, the image without personnel in the assessment review video of 10.4 corresponding to the assessment terminal 3 is replaced with an image with personnel, and the updated assessment review video is then sent to the management terminal for storage.

[0223] In order to better implement the intelligent assessment data processing method provided by the present invention, the present invention also provides an intelligent assessment data processing system, such as Figure 3 Shown, including:

[0224] The receiving module is used to receive a workstation template of a target enterprise configured by a management terminal, wherein the workstation template includes a plurality of identification areas, each of which has a corresponding assessment terminal.

[0225] The processing module is used to receive the assessment data uploaded by each assessment terminal, and process the corresponding identification area in the workstation template diagram based on the assessment data to obtain a theoretical assessment diagram.

[0226] The recognition module is used to obtain the workstation image collected by the acquisition device, identify the workstation image based on the assessment recognition strategy and the workstation template map, obtain the updated data of the assessment end, and update the corresponding identification area in the theoretical assessment map based on the updated data to obtain the actual assessment map.

[0227] The sending module is used to select and process multiple workstation images within a preset time period based on a video frame selection strategy, obtain the assessment review video of each assessment end, and send the actual assessment image and the assessment review video to the management end.

[0228] like Figure 4 FIG. 4 is a schematic diagram of the hardware structure of an electronic device provided by an embodiment of the present invention. The electronic device 40 includes: a processor 41, a memory 42 and a computer program;

[0229] The memory 42 is used to store the computer program, which may also be a flash memory. The computer program is, for example, an application program or a functional module for implementing the above method.

[0230] The processor 41 is configured to execute the computer program stored in the memory to implement the various steps performed by the device in the above method. For details, please refer to the relevant description in the above method embodiment.

[0231] Optionally, the memory 42 may be independent or integrated with the processor 41 .

[0232] When the memory 42 is a device independent of the processor 41, the device may further include:

[0233] The bus 43 is used to connect the memory 42 and the processor 41 .

[0234] The present invention also provides a readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, it is used to implement the methods provided in the various embodiments described above.

[0235] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. An intelligent assessment data processing method, characterized in that: include: Receiving a workstation template diagram of a target enterprise configured by a management terminal, wherein the workstation template diagram includes a plurality of identification areas, each of which has a corresponding assessment terminal; Receiving the assessment data uploaded by each assessment terminal, and processing the corresponding identification area in the workstation template diagram based on the assessment data to obtain a theoretical assessment diagram; Acquire a workstation image acquired by an acquisition device, identify the workstation image based on an assessment recognition strategy and a workstation template map, obtain updated data of the assessment end, and update a corresponding identification area in the theoretical assessment map based on the updated data to obtain an actual assessment map; Based on the video frame selection strategy, multiple workstation images within a preset time period are selected and processed to obtain the assessment review video of each assessment end, and the actual assessment image and the assessment review video are sent to the management end.

2. The method according to claim 1, characterized in that The receiving of the assessment data uploaded by each assessment terminal, and processing the corresponding identification area in the workstation template diagram based on the assessment data to obtain a theoretical assessment diagram, includes: receiving assessment data uploaded by each assessment terminal, the assessment data including attendance data and absence data, determining a first pixel value according to the attendance data, and determining a second pixel value according to the absence data; Based on the first pixel value or the second pixel value, the border of the corresponding identification area in the workstation template image is updated by the assessment end to obtain a theoretical assessment image.

3. The method according to claim 2, characterized in that The method includes: obtaining a workstation image collected by the acquisition device, identifying the workstation image based on the assessment recognition strategy and the workstation template map, obtaining updated data of the assessment end, and updating the corresponding identification area in the theoretical assessment map based on the updated data to obtain an actual assessment map, including: Retrieving the recognition template corresponding to the acquisition device in the workstation template map, using the recognition area in the recognition template as the judgment area, and obtaining the workstation image acquired by the acquisition device; The identification template is superimposed on the workstation image, and personnel identification is performed on the image of the judgment area in the identification template to obtain updated data. Based on the updated data, the corresponding identification area in the theoretical assessment map is updated to obtain the actual assessment map.

4. The method according to claim 3, characterized in that The step of performing personnel recognition on the image in the judgment area of ​​the recognition template to obtain updated data, and updating the corresponding recognition area in the theoretical assessment map based on the updated data to obtain the actual assessment map, includes: Identify the number of workstation images of personnel on the assessment terminals corresponding to each judgment area in the recognition template as the assessment judgment number; If it is determined that the assessment judgment quantity is greater than or equal to the preset quantity, the current data of the corresponding assessment terminal is determined to be attendance data; If it is determined that the assessment judgment number is less than the preset number, the current data of the corresponding assessment terminal is determined to be absence data; If the current data of the assessment end is inconsistent with the assessment data, the third pixel value is retrieved as update data, and the identification area of ​​the corresponding assessment end in the theoretical assessment map is used as the update area; The border of the update area is updated based on the update data to obtain an actual assessment map.

5. The method according to claim 3, characterized in that Also includes: Retrieving the position attributes in the judgment area of ​​the recognition template, wherein the position attributes include R&D attributes and communication attributes; Based on the R&D attribute, the corresponding judgment area is used as the R&D area, and based on the communication attribute, the corresponding judgment area is used as the communication area; Conducting continuous focus assessment on the R&D areas to obtain the R&D focus of each R&D area; Intermittent concentration determination is performed on the communication areas to obtain the communication concentration of each communication area.

6. The method according to claim 5, characterized in that The continuous focus determination of the R&D areas to obtain the R&D focus of each R&D area includes: Retrieving the device orientation of the display device in each R&D area, identifying the facial orientation of people in the R&D area, and recording the time period when the device orientation is opposite to the facial orientation as the first conditional time period of each R&D area; The time period when personnel in each R&D area trigger the input device is counted as the second condition time period of each R&D area; Obtaining a condition superposition period for each R&D area based on the intersection of the first condition period and the second condition period for each R&D area; Select an image of each R&D area at any time during the condition superposition period as a reference image, and use images at two times adjacent to the reference image as comparison images; Selecting the pixel point at the same position in the reference image and the comparison image as the coordinate origin, and performing coordinate processing on the reference image and the comparison image based on the coordinate origin; Determine pixel points with different pixel values ​​in the reference image and the comparison image at the same coordinates as changed pixel points, and obtain the changed number of the changed pixel points and the total number of pixels in the reference image; A change ratio is obtained based on the ratio of the number of changes to the total number, and when it is determined that the change ratio is less than a preset change ratio, the moment of the corresponding baseline image is used as the R&D focus moment; The R&D focus moments are counted to obtain the R&D focus duration, and based on the ratio of the R&D focus duration to the preset working hours, the R&D focus of each R&D area is obtained.

7. The method according to claim 5, characterized in that The intermittent concentration determination of the communication areas to obtain the communication concentration of each communication area includes: Identifying a back contour of a communication device in the communication area and a hand contour of a person in the communication area, and obtaining a time period in which the hand contour and the back contour intersect as a first judgment time period; Identifying the head outline of the person in the communication area, and obtaining the time period during which the back outline is within the head outline as a second judgment time period; The communication focus duration of each communication zone is obtained according to the intersection of the first judgment period and the second judgment period, and the communication focus degree of each communication zone is obtained based on the ratio of the communication focus duration to the preset working duration.

8. The method according to claim 4, characterized in that The plurality of workstation images within a preset time period are selected and processed based on the video frame selection strategy to obtain the assessment review video of each assessment terminal, including: Obtaining the identification area corresponding to the assessment end in the actual assessment map as the display area, and using the remaining identification areas as the cover area; Determining the corresponding judgment area in the recognition template as a reserved area based on the corresponding assessment terminal, and setting the remaining judgment areas as hidden areas; Determining that the current data of the assessment terminal is attendance data, and selecting any one of the workstation images within a first preset time period, which has a person in the reserved area, as a starting image; selecting any one of the workstation images of personnel in the reserved area within the second preset time period as the termination image; Determining that the current data of the assessment terminal is absence data, and selecting any image of a workstation in the reserved area without personnel within a first preset time period as a starting image; selecting any one of the workstation images in the reserved area without personnel within a second preset time period as a termination image, wherein the preset time period includes a first preset time period and a second preset time period; The assessment review video of each assessment terminal is obtained according to the actual assessment diagram within the preset time period, the starting diagram and the ending diagram.

9. The method according to claim 8, characterized in that The step of obtaining the assessment retrospective video of each assessment terminal according to the actual assessment graph, the start graph, and the end graph within the preset time period includes: Retrieving a preset mask layer to mask the mask area in the actual assessment image to obtain a status frame; Recalling a preset mask layer to mask the image corresponding to the hidden area in the recognition template above the starting image to obtain a starting frame; Retrieving a preset mask layer to mask the image corresponding to the hidden area in the recognition template above the termination image to obtain a termination frame; All status frames, start frames and end frames of each assessment end within a preset time period are counted to obtain the assessment retrospective video of each assessment end.

10. An intelligent assessment data processing system, characterized in that: include: A receiving module, configured to receive a workstation template diagram of a target enterprise configured by a management terminal, wherein the workstation template diagram includes a plurality of identification areas, each of which has a corresponding assessment terminal; A processing module, configured to receive the assessment data uploaded by each assessment terminal, and process the corresponding identification area in the workstation template diagram based on the assessment data to obtain a theoretical assessment diagram; an identification module for acquiring a workstation image acquired by the acquisition device, identifying the workstation image based on the assessment identification strategy and the workstation template map, obtaining updated data of the assessment end, and updating the corresponding identification area in the theoretical assessment map based on the updated data to obtain an actual assessment map; The sending module is used to select and process multiple workstation images within a preset time period based on a video frame selection strategy, obtain the assessment review video of each assessment end, and send the actual assessment image and the assessment review video to the management end.

Images