WO2021217943A1 - 企业整改监管方法、装置、设备及计算机可读存储介质 - Google Patents
企业整改监管方法、装置、设备及计算机可读存储介质 Download PDFInfo
- Publication number
- WO2021217943A1 WO2021217943A1 PCT/CN2020/106069 CN2020106069W WO2021217943A1 WO 2021217943 A1 WO2021217943 A1 WO 2021217943A1 CN 2020106069 W CN2020106069 W CN 2020106069W WO 2021217943 A1 WO2021217943 A1 WO 2021217943A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- rectification
- video
- picture
- rectified
- enterprise
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000004458 analytical method Methods 0.000 claims abstract description 62
- 238000012937 correction Methods 0.000 claims abstract description 10
- 230000007613 environmental effect Effects 0.000 claims description 61
- 239000011159 matrix material Substances 0.000 claims description 55
- 230000003068 static effect Effects 0.000 claims description 49
- 239000000284 extract Substances 0.000 claims description 29
- 238000000605 extraction Methods 0.000 claims description 11
- 238000007689 inspection Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 7
- 230000001105 regulatory effect Effects 0.000 description 6
- 238000012552 review Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 241001674044 Blattodea Species 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000003252 repetitive effect Effects 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 241000700159 Rattus Species 0.000 description 1
- 230000000739 chaotic effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/12—Hotels or restaurants
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C1/00—Registering, indicating or recording the time of events or elapsed time, e.g. time-recorders for work people
- G07C1/20—Checking timed patrols, e.g. of watchman
Definitions
- This application relates to the field of data processing technology, and in particular to an enterprise rectification supervision method, device, equipment and computer-readable storage medium.
- catering companies have developed vigorously, but currently some catering companies have sanitary problems in the back kitchens, which affect the health of consumers. Therefore, the supervision and inspection of the back kitchens of catering companies is particularly important.
- the supervision department usually conducts supervision and inspection on the back kitchens of catering companies through video inspections. Once they find that there is a need for rectification in violation of regulations, they will issue rectification requirements within a time limit to the catering companies.
- the catering unit needs to complete the rectification of the back kitchen before the prescribed time limit and report it to the supervisory department.
- the inventor realizes that under the traditional supervision method, the supervisor will review the effect of the rectification after receiving the feedback of the completion of the rectification of the restaurant enterprise. Once the review determines that the rectification is not in place and requires a second rectification, the supervisor shall conduct a second review after the second rectification is completed.
- the entire supervisory inspection process consumes a lot of time for supervisors, high labor costs, and low supervisory inspection efficiency.
- the main purpose of this application is to provide an enterprise rectification supervision method, device, equipment and computer-readable storage medium, aiming to solve the technical problems of high labor cost and low efficiency in the supervision and inspection of the back kitchen of catering enterprises in the prior art.
- the embodiment of the present application provides an enterprise rectification supervision method, and the enterprise rectification supervision method includes the following steps:
- the rectification video is analyzed, an analysis result is generated, and the rectification of the enterprise to be rectified is supervised according to the analysis result.
- this application also provides an enterprise rectification supervision device, and the enterprise rectification supervision device includes:
- the extraction module is used to obtain the initial video before the rectification and the rectification video after the rectification of the enterprise to be rectified, and extract the first picture and the second picture at the same time point from the initial video and the rectification video respectively;
- a judging module configured to judge whether the rectification environment corresponding to the rectification video is valid according to the first picture and the second picture;
- An obtaining module configured to obtain a rectification task list corresponding to the initial video if the rectification environment is effective
- the supervision module is configured to analyze the rectification video according to the rectification task list, generate analysis results, and supervise the rectification of the enterprise to be rectified according to the analysis results.
- this application also provides an enterprise rectification supervision device
- the enterprise rectification supervision device includes a memory, a processor, and an enterprise rectification supervision program stored on the memory and running on the processor, When the enterprise rectification supervision program is executed by the processor, the following steps are implemented:
- the rectification video is analyzed, an analysis result is generated, and the rectification of the enterprise to be rectified is supervised according to the analysis result.
- the present application also provides a computer-readable storage medium on which an enterprise rectification supervision program is stored, and when the enterprise rectification supervision program is executed by a processor, the following steps are implemented:
- the rectification video is analyzed, an analysis result is generated, and the rectification of the enterprise to be rectified is supervised according to the analysis result.
- This application provides a method, device, equipment, and computer-readable storage medium for supervision of enterprise rectification.
- the time is extracted from the initial video and the rectification video respectively Click the same first picture and second picture; and based on the first picture and second picture, determine whether the rectification environment corresponding to the rectification video is valid; if the rectification environment is valid, obtain the rectification task list corresponding to the initial video;
- the rectification task list is analyzed, the rectification video is analyzed, and the analysis result is generated, so as to supervise the rectification of the enterprise to be rectified based on the analysis result.
- the rectification video is a real video
- the regulatory environment represented by the first picture and the second picture is the same, so that according to the first picture and the first picture 2.
- the effectiveness of the rectification environment judged by the picture is more true and accurate.
- the rectification video is analyzed to realize the supervision of the rectification of the enterprise to be rectified, avoid frequent review by supervisors, save labor costs, and improve the authenticity of the rectification environment. Regulatory efficiency.
- FIG. 1 is a schematic diagram of the structure of the enterprise rectification supervision equipment of the hardware operating environment involved in the scheme of the embodiment of the application;
- Figure 2 is a schematic flow chart of the first embodiment of the method for rectification and supervision of the applicant enterprise
- Fig. 3 is a schematic diagram of functional modules of a preferred embodiment of the enterprise rectification supervision device of the applicant.
- FIG. 1 is a schematic diagram of the structure of the enterprise rectification supervision equipment of the hardware operating environment involved in the solution of the embodiment of the present application.
- the enterprise rectification supervision device in the embodiment of the present application may be a PC, or a portable terminal device such as a tablet computer and a portable computer.
- the enterprise rectification supervision device may include: a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, and a communication bus 1002.
- the communication bus 1002 is used to implement connection and communication between these components.
- the user interface 1003 may include a display screen (Display) and an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface.
- the network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface).
- the memory 1005 may be a high-speed RAM memory, or a non-volatile memory (non-volatile memory), such as a magnetic disk memory.
- the memory 1005 may also be a storage device independent of the aforementioned processor 1001.
- the structure of the enterprise rectification supervision equipment shown in Figure 1 does not constitute a limitation on the enterprise rectification supervision equipment, and may include more or less components than shown in the figure, or a combination of certain components, or different The layout of the components.
- the memory 1005 which is a computer-readable storage medium, may include an operating system, a network communication module, a user interface module, and a detection program.
- the network interface 1004 is mainly used to connect to the back-end server and communicate with the back-end server;
- the user interface 1003 is mainly used to connect to the client (user side) and communicate with the client;
- the processor 1001 can be used to call the detection program stored in the memory 1005 and perform the following operations:
- the rectification video is analyzed, an analysis result is generated, and the rectification of the enterprise to be rectified is supervised according to the analysis result.
- the step of judging whether the rectification environment corresponding to the rectification video is effective according to the first picture and the second picture includes:
- the step of extracting the first environmental feature points in the first picture and forming each of the first environmental feature points into a first feature matrix includes:
- the step of obtaining a rectification task list corresponding to the initial video includes:
- the step of analyzing the rectification video according to the rectification task list to generate an analysis result includes:
- the preset time interval is adjusted, and the step of analyzing and decimating the frames of the corrected video is performed according to the adjusted preset time interval.
- the step of supervising the rectification of the enterprise to be rectified according to the analysis result includes:
- the processor 1001 may be used to call the detection program stored in the memory 1005 and execute the following operate:
- the specific implementation method of the enterprise rectification supervision equipment of the application is basically the same as the following embodiments of the enterprise rectification supervision method, and will not be repeated here.
- the first embodiment of the present application provides a schematic flow chart of an enterprise rectification supervision method.
- the enterprise rectification supervision method includes the following steps:
- Step S10 Obtain the initial video before the rectification and the rectification video after the rectification of the enterprise to be rectified, and extract the first picture and the second picture at the same time point from the initial video and the rectification video respectively;
- the enterprise rectification supervision method in this embodiment is applied to the server, and is suitable for monitoring the rectification of the enterprise through the server.
- the enterprise may be various units that need to carry out environmental rectification and behavior rectification, and this embodiment preferably uses the back kitchen of a catering enterprise for illustration. That is, the rectification of the dirty, chaotic, and poor environment in the back kitchen of catering enterprises, and the behavior of catering service personnel not wearing work hats, work gloves, etc. shall be supervised.
- the server is in communication connection with a camera capable of shooting video, so that the camera can transmit the captured video to the server for processing.
- the camera can be installed in a fixed position and can be rotated at a fixed position.
- the angle of rotation includes the range of the back kitchen of the catering company to take pictures of the back kitchen and ensure that the environment captured in each rotation cycle is consistent.
- the camera can also exist in the form of video inspection, and the inspection is carried out at a fixed speed and a fixed route to ensure the consistency of the shooting environment.
- the camera transmits the captured video information to the server according to the preset inspection period.
- the server determines whether there is content that needs to be rectified. If there is content that needs to be rectified, then The enterprise is regarded as the enterprise to be rectified, and the video information is used as the initial video before the rectification of the enterprise to be rectified. Different rectification deadlines are set in the server according to the degree of difficulty of the content to be rectified in advance. According to the content that needs to be rectified in the initial video, the corresponding rectification deadline can be determined, and the content and the rectification deadline will be notified. Send the form to the enterprise to be rectified.
- the server After the server receives the video information uploaded by the enterprise to be rectified again, it obtains the video information as the rectified video after the rectification, and obtains the previously stored initial video from the storage unit to supervise the pending video through the initial video and the rectified video. Whether the rectification of the rectification enterprise is in place.
- the initial video and the rectification video are shot in the same scene, that is, to ensure that the rectification environment corresponding to the rectification video is the environment that actually needs rectification in the enterprise to be rectified.
- the first picture and the second picture at the same time point are respectively extracted from the video. Because the initial picture and the rectification picture are taken by the camera, and the camera rotates at a fixed position to shoot or patrol and shoot at a fixed speed and a fixed route, the initial video and the rectification video capture the same scene at the same time point.
- the first picture and the second picture extracted from the same time point should have the same scene. Therefore, it is possible to detect whether the initial video and the rectification video are for the same scene according to the scenes shown in the first picture and the second picture.
- multiple identical time points can be set. Bring up multiple first and second pictures; such as the first and second pictures at 1 minute, the first and second pictures at 2 minutes, the first and second pictures at 3 minutes Wait.
- the rectification of the enterprise to be rectified needs to be completed within the rectification period.
- the rectification video needs to be used to determine the rectification period.
- the step of respectively extracting the first picture and the second picture at the same time point from the initial video and the rectification video includes:
- Step a1 Extract the first generation time of the initial video and the second generation time of the rectification video, and determine whether the rectification video is in the preset rectification based on the first generation time and the second generation time Generated within the time limit;
- the initial video carries a time characterizing its recording date, and this time is extracted as the first generation time of the initial video.
- the rectification video also carries a time characterizing its recording date, and this time is extracted as the second generation time of the rectification video.
- the preset rectification time limit is the above-mentioned rectification time limit determined based on the content that needs to be rectified in the initial video.
- the preset rectification period is one month
- the first generation time is January 1st of a certain year
- the second generation time is January 25th of the same year
- the time difference between the two is within the preset rectification period. It is determined that the rectification video is generated within the preset rectification period, that is, the rectification of the enterprise to be rectified is completed within the required rectification period.
- Step a2 if it is generated within the preset rectification period, execute the step of extracting the first picture and the second picture at the same time point from the initial video and the rectification video respectively;
- the rectification video is generated within the preset rectification period, it means that the generated rectification video is valid.
- the first picture and the second picture at the same time point can be extracted from the initial video and the rectification video, respectively, to pass The first picture and the second picture are used to determine whether the initial video and the rectification video are shot for the same scene, and whether the rectification environment corresponding to the rectification video is an environment that actually needs rectification in the enterprise to be rectified, that is, to determine whether the rectification environment corresponding to the rectification video is effective.
- step a3 if it is not within the preset rectification period, output a prompt message indicating that the rectification is invalid.
- the rectification video is not generated within the preset rectification period, it means that the rectification of the enterprise to be rectified has not been completed within the required rectification period, and the rectification of the enterprise to be rectified is invalid, and a prompt message indicating that the rectification is invalid is output.
- Step S20 judging whether the rectification environment corresponding to the rectification video is valid according to the first picture and the second picture;
- the first picture is extracted from the initial video
- the second picture at the same time point is extracted from the rectification video
- it can be based on the scene environment represented in the first picture and the scene represented in the second picture.
- the rectification environment corresponding to the rectification video is effective, that is, whether the environment taken by the rectification video is the real environment of the enterprise to be rectified after the rectification.
- dynamic characters may be captured.
- the dynamic characters have dynamic characteristics, so that the scenes in the first picture and the second picture at the same time point are not exactly the same.
- the first picture contains a certain staff member. , There are no staff, etc. in the second picture.
- a recognition mechanism of the dynamic character may be set in this embodiment. Train the initial model through a large number of dynamic character samples in advance to obtain the dynamic character recognition model, and transfer the extracted first picture and second picture to the dynamic character recognition model, and the dynamic character recognition model recognizes the first picture and the second picture Whether dynamic characters are included, if dynamic characters are included, the dynamic characters will be eliminated, and the scene environment represented by the first picture and the second picture after the dynamic characters have been eliminated is judged whether the scene environment represented by the first picture and the second picture are consistent, so as to avoid the consistency of the dynamic characters on the scene environment Judgment.
- the rectification environment corresponding to the rectification video is effective, and the environment captured by the rectification video is the real environment of the enterprise to be rectified after the rectification. If they are inconsistent, it means that the rectification environment corresponding to the rectification video is invalid, and the environment taken by the rectification video is not the real environment of the enterprise to be rectified after the rectification, and false rectification may exist.
- the overall similarity is greater than the preset threshold, it means that the similarity between multiple first pictures and second pictures is high, and it can be determined that the scene environment represented by the initial video and the rectification video are consistent, and the rectification environment corresponding to the rectification video Effective, the environment taken by the rectification video is the real environment of the enterprise to be rectified after the rectification. On the contrary, it means that the scene environment represented by the initial video and the rectification video are inconsistent, and the environment where the rectification video is shot is not the real environment of the enterprise to be rectified after the rectification, and there may be false rectification situations.
- Step S30 if the rectification environment is effective, obtain a rectification task list corresponding to the initial video;
- the rectification task list corresponding to the initial video is obtained to characterize the rectification required by the enterprise to be rectified Content.
- the rectification task list may be pre-generated and stored in the storage unit of the server, and carries an identifier representing the initial video.
- the server reads the rectification task list from the storage unit through the identifier to obtain the rectification task list corresponding to the initial video.
- the rectification task list can also be generated by real-time detection of whether the initial video contains rectification items through preset rectification items, that is, real-time identification of the rectification items included in the initial video to generate a rectification task list.
- Step S40 Analyze the rectification video according to the rectification task sheet, generate an analysis result, and supervise the rectification of the enterprise to be rectified according to the analysis result.
- the content that needs to be rectified contained in the rectification task list is regarded as the content to be rectified, and the rectification video is analyzed according to the content to be rectified to obtain multiple rectified pictures containing all the content to be rectified, and the multiple The picture has been rectified as the analysis result.
- the rectification of the enterprises to be rectified is supervised.
- the steps to supervise the rectification of the enterprise to be rectified include:
- Step S41 Obtain the rectification requirements in the rectification task sheet, and determine whether the analysis result matches the rectification requirements;
- the corresponding rectification requirements are set for all pre-set rectification items. Regardless of whether the rectification task list is generated in advance or in real time, the rectification requirements corresponding to the content to be rectified that need to be rectified in the rectification task list are set. Set it in the rectification task list.
- the server obtains the rectification requirements corresponding to the content to be rectified from the rectification task list, and finds the rectified pictures corresponding to the content to be rectified among the multiple rectified pictures of the analysis results, and then bases the rectified pictures corresponding to the content to be rectified.
- the rectification requirements corresponding to the contents to be rectified are identified, and the rectified pictures corresponding to the contents to be rectified are judged whether they meet the respective rectification requirements, so as to realize the judgment of whether the analysis results match the rectification requirements.
- Step S42 if it matches the rectification requirements, complete the rectification supervision of the enterprise to be rectified;
- Step S43 if it does not match the rectification requirement, output a prompt message for continuing the rectification.
- the prompt information includes the content that needs to be rectified and the time limit for rectification. After that, when the rectification video is received again, it is also judged whether the re-received rectification video is valid.
- the content that has not been rectified in place is obtained to generate a new rectification task list, and the new rectification task list is used to correct the received rectification
- the video is analyzed, and based on the analysis results, the rectification of the enterprises to be rectified is supervised until all the contents to be rectified in the enterprises to be rectified are rectified in place.
- the first picture and the second picture at the same time point are extracted from the initial video and the rectification video respectively; According to the first picture and the second picture, judge whether the rectification environment corresponding to the rectification video is effective; if the rectification environment is effective, obtain the rectification task list corresponding to the initial video; then analyze the rectification video according to the rectification task list, and generate the analysis result , In order to supervise the rectification of enterprises to be rectified based on the analysis results.
- the rectification video is a real video
- the regulatory environment represented by the first picture and the second picture is the same, so that according to the first picture and the first picture 2.
- the effectiveness of the rectification environment judged by the picture is more true and accurate.
- the rectification video is analyzed to realize the supervision of the rectification of the enterprise to be rectified, avoid frequent review by supervisors, save labor costs, and improve the authenticity of the rectification environment. Regulatory efficiency.
- a second embodiment of the enterprise rectification supervision method of the application is proposed.
- the judgment is made based on the first picture and the second picture.
- the steps for whether the rectification environment corresponding to the rectification video is effective include:
- Step S21 extracting first environmental feature points in the first picture, and forming each of the first environmental feature points into a first feature matrix
- the first environmental feature point is extracted from the first picture, where the first environmental feature point is the feature information of the static object contained in the first picture. Thereafter, the feature information of each static object is formed into a first feature matrix, so as to characterize all the features of the static objects contained in the first picture through the first feature matrix.
- the step of extracting the first environmental feature points in the first picture and forming each first environmental feature point into a first feature matrix includes:
- Step S211 identifying static objects in the first picture, and detecting attribute information of each of the static objects, where the attribute information includes at least a name, color, size, and coordinates;
- the initial model is trained in advance by using pictures of solid objects such as dining tables, chairs, pots, stoves, etc. commonly used in catering companies as training samples to obtain a recognition model for recognizing solid objects in the environment.
- the server calls the recognition model to recognize static objects in the first picture, and then detects the number of static objects and attribute information of each static object.
- the attribute information includes at least the name, color, size, coordinates, etc. of the static object.
- the name tags of each training sample can be used to identify the name of each static object; at the same time, the color of the static object can be recognized through OpenCV image processing technology, and the preset coordinate system can be set. The position of the object in the preset coordinate system determines the size and position coordinates.
- Step S212 forming the attribute information of each of the static objects into an attribute sequence, and using each of the attribute sequences as a first environmental feature point in the first picture;
- each static object is formed as an attribute sequence of each static object, and each attribute sequence is used as the first environmental feature point in the first picture. If the static object A in the first picture is identified, its name, color, size and coordinates are: table, black, 1m*1m, (20, 30), then the attribute sequence formed for it is [table, black , 1m*1m, (20, 30)]. In addition, the attribute sequence is used as a first environmental feature point in the first picture to represent various features of the static object "table" in the first picture.
- Step S213 Arrange each of the first environmental feature points to form a first feature matrix.
- each first environmental feature point is formed as the first Feature matrix
- each row in the first feature matrix represents various features of a static object
- each column represents the performance of each static object on a certain feature, such as
- Step S22 extracting second environmental feature points in the second picture, and forming each of the second environmental feature points into a second feature matrix
- the second environmental feature point is extracted from the second picture, and the second environmental feature point is the feature information of the static object contained in the second picture. Thereafter, the feature information of each static object is formed into a second feature matrix, so as to characterize all the features of the static objects contained in the second picture through the second feature matrix.
- the method of extracting the second environmental feature points to form the second feature matrix is the same as the method of extracting the first environmental feature points to form the first feature matrix.
- the attribute information includes at least the name, color, size, and coordinates; the attribute information of each static object is formed into an attribute sequence, and Each attribute sequence is used as the second environmental feature point in the second picture; the second environmental feature points are arranged to form a second feature matrix.
- the specific implementation is the same as that of forming the first feature matrix described above, and will not be repeated here.
- Step S23 Determine the similarity parameter between the first feature matrix and the second feature matrix, and determine whether the rectification environment corresponding to the rectified video is effective according to the similarity parameter.
- a matrix operation is performed between the first feature matrix and the second feature matrix to obtain a similarity parameter that characterizes the degree of similarity between the two.
- a similarity threshold representing the level of similarity is preset in the server, and the obtained similarity parameter is compared with the similarity threshold to determine whether the similarity parameter is greater than the similarity threshold. If the similarity parameter is greater than the similarity threshold, the feature that characterizes the static object in the first picture is more similar to the feature of the static object in the second picture, and the environment for the rectification is the environment of the enterprise to be rectified, so as to determine which corresponds to the entire video The rectification environment is effective.
- the similarity parameter is not greater than the similarity threshold, the feature that characterizes the static object in the first picture has a low degree of similarity with the feature of the static object in the second picture, and the environment targeted for rectification is not the environment of the enterprise to be rectified, and there may be falsehoods. In the case of rectification, it was determined that the rectification environment corresponding to the entire video was invalid.
- the first characteristic matrix and the second characteristic matrix are formed to characterize the characteristics of all the static objects contained in the first picture and the second picture. Furthermore, the similarity parameter between the first feature matrix and the second feature matrix is used to determine whether the rectification environment targeted by the rectification video is effective. Because the first feature matrix contains the features of all static objects in the first picture, and the second feature matrix contains the features of all static objects in the second picture, the effectiveness of the correction environment determined by the similarity parameters of the two is more effective. To be true and accurate.
- a third embodiment of the enterprise rectification supervision method of the present application is proposed.
- the acquisition of the rectification corresponding to the initial video The steps of the task list include:
- Step S31 parse the initial video, and extract frames of the parsed initial video according to a preset time interval to obtain multiple video frames;
- the rectification task list corresponding to the initial video is preferably generated based on the pre-set rectification items, and the rectification items included in the initial video are detected in real time.
- the initial video is first analyzed by ffmpeng, and frames are extracted from the analyzed initial video according to a preset preset time interval to obtain multiple video frames.
- the preset time interval represents the time span of decimating frames of the parsed initial video. For example, the preset time interval is 5 seconds, after the frame is decimated from the 0th second of the initial video, the frame is decimated again at the 5th second, until the initial The end time of the video. The smaller the preset time interval, the more the number of frames drawn, and the more accurate the rectification task list will be.
- Step S32 Identify whether there is content to be rectified in the plurality of video frames, and if there is content to be rectified, generate the content to be rectified as a rectification task list corresponding to the initial video.
- the contents that need to be rectified include but are not limited to staff not wearing work caps, cockroaches and rats in the back kitchen, dirty kitchen, etc. If there is content to be rectified, add the content to be rectified to the template of the rectification task list to form a rectification task list corresponding to the initial video, and use the content to be rectified in the rectification task list to characterize the needs of the enterprise to be rectified The content of the rectification.
- the step of analyzing the rectification video according to the rectification task list to generate the analysis result includes:
- Step S44 Analyze and extract frames of the rectified video according to the preset time interval to obtain multiple rectified pictures
- ffmpeng analyzes and extracts frames to obtain multiple rectified pictures. Use multiple rectification pictures to reflect the rectification situation of the enterprise to be rectified, whether all the contents that need rectification have been rectified in place, etc.
- Step S45 It is judged whether the plurality of rectified pictures include all the contents to be rectified in the rectification task list, and if all the contents to be rectified are included, then the plurality of rectified pictures are generated as the analysis result ;
- the rectified pictures in order to make the rectified pictures fully reflect the rectification situation of the enterprise to be rectified, it is necessary to ensure that multiple rectified pictures include all the contents to be rectified in the rectification task list. If the content to be rectified in the rectification task list includes the staff not wearing a work cap and cockroaches in the back kitchen, the multiple rectified pictures in the selected frame include at least one staff member and at least the back kitchen environment. Therefore, after obtaining multiple rectified pictures, judge the multiple rectified pictures according to the rectification task list, and judge whether the multiple rectified pictures include all the content to be rectified in the rectification task list. If it contains all the content to be rectified, it means that the rectified video is framed, and the multiple rectified pictures obtained meet the requirements, and they are generated as analysis results.
- Step S46 If all the content to be corrected are not included, adjust the preset time interval, and execute the step of analyzing and extracting frames of the corrected video according to the adjusted preset time interval.
- the preset time interval is adjusted , Adjust the preset time interval to a smaller time span. Thereafter, based on the adjusted preset time span, the rectification video is re-drawn frames to extract more rectified pictures until all the content to be rectified in the rectification task list is included, and the analysis result is generated. It should be noted that if multiple rectified pictures contain multiple repetitive content to be rectified, it means that too many rectified pictures have been extracted.
- the preset time interval can be adjusted to a larger time span for frame extraction to avoid Too many repetitive rectified pictures are generated as analysis results, which leads to an increase in the amount of data processed by the server on the analysis results and reduces processing efficiency.
- a rectification task list is formed from the initial video analysis frame, and the rectification video is analyzed and extracted according to the rectification task list to form a rectified picture.
- the rectified picture forms the analysis result to reflect the company's Rectification situation.
- this application also provides an enterprise rectification supervision device.
- Fig. 3 is a schematic diagram of the functional modules of the first embodiment of the enterprise rectification supervision device of the application.
- the said enterprise rectification supervision device includes:
- the extraction module 10 is used to obtain the initial video before the rectification and the rectification video after the rectification of the enterprise to be rectified, and extract the first picture and the second picture at the same time point from the initial video and the rectification video respectively;
- the judging module 20 is configured to judge whether the rectification environment corresponding to the rectification video is valid according to the first picture and the second picture;
- the obtaining module 30 is configured to obtain a rectification task list corresponding to the initial video if the rectification environment is effective;
- the supervision module 40 is configured to analyze the rectification video according to the rectification task list, generate analysis results, and supervise the rectification of the enterprise to be rectified according to the analysis results.
- the extraction module 10 obtains the initial video before the rectification and the rectification video after the rectification of the enterprise to be rectified, it extracts the first picture and the first picture at the same time point from the initial video and the rectification video, respectively.
- Two pictures; and the judging module 20 determines whether the rectification environment corresponding to the rectification video is valid according to the first picture and the second picture; if the rectification environment is valid, the acquisition module 30 obtains the rectification task list corresponding to the initial video;
- the supervision module 40 analyzes the rectification video according to the rectification task list, and generates the analysis result, so as to supervise the rectification of the enterprise to be rectified based on the analysis result.
- the rectification video is a real video
- the regulatory environment represented by the first picture and the second picture is the same, so that according to the first picture and the first picture 2.
- the effectiveness of the rectification environment judged by the picture is more true and accurate.
- the rectification video is analyzed to realize the supervision of the rectification of the enterprise to be rectified, avoid frequent review by supervisors, save labor costs, and improve the authenticity of the rectification environment. Regulatory efficiency.
- judgment module 20 includes:
- a first extraction unit configured to extract first environmental feature points in the first picture, and form each of the first environmental feature points into a first feature matrix
- a second extraction unit configured to extract second environmental feature points in the second picture, and form each of the second environmental feature points into a second feature matrix
- the judging unit is configured to determine the similarity parameter between the first feature matrix and the second feature matrix, and determine whether the rectification environment corresponding to the rectified video is effective according to the similarity parameter.
- first extraction unit is further configured to include:
- the step of extracting the first environmental feature points in the first picture and forming each of the first environmental feature points into a first feature matrix includes:
- the acquisition module 30 further includes:
- the parsing unit is configured to analyze the initial video, and extract frames from the analyzed initial video according to a preset time interval to obtain multiple video frames;
- the identification unit is configured to identify whether there is content to be corrected in the plurality of video frames, and if there is content to be corrected, generate the content to be corrected into a correction task list corresponding to the initial video.
- monitoring module 40 further includes:
- the frame extraction unit is configured to analyze and extract frames of the rectified video according to the preset time interval to obtain multiple rectified pictures
- the adjustment unit is configured to adjust the preset time interval if not all the content to be rectified is included, and execute the step of analyzing and extracting frames of the rectified video according to the adjusted preset time interval.
- monitoring module 40 further includes:
- An obtaining unit configured to obtain the rectification requirements in the rectification task list, and determine whether the analysis result matches the rectification requirements
- the completion unit is used to complete the rectification supervision of the enterprise to be rectified if it matches the rectification requirements;
- the first output unit is configured to output prompt information for continuing the rectification if it does not match the rectification requirements.
- the extraction module 10 includes:
- the third extraction unit is configured to extract the first generation time of the initial video and the second generation time of the rectification video, and determine whether the rectification video is based on the first generation time and the second generation time Generated within the preset rectification period;
- the execution unit is configured to perform the step of extracting the first picture and the second picture at the same time point from the initial video and the rectification video, if it is generated within the preset rectification time limit;
- the second output unit is configured to output a prompt message indicating that the rectification is invalid if it is not within the preset rectification period.
- the specific implementation of the enterprise rectification supervision device of this application is basically the same as the above embodiments of the enterprise rectification supervision method, and will not be repeated here.
- the embodiment of the present application also proposes a computer-readable storage medium.
- the computer-readable storage medium may be non-volatile or volatile.
- the computer-readable storage medium stores an enterprise rectification supervision program, and when the enterprise rectification supervision program is executed by a processor, the steps of the above-mentioned enterprise rectification supervision method are realized.
- the technical solution of this application essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product is stored in a computer-readable storage medium as described above (such as The ROM/RAM, magnetic disk, optical disk) includes several instructions to make a terminal device (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) execute the methods described in the various embodiments of the present application.
- a terminal device which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Evolutionary Biology (AREA)
- Operations Research (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Multimedia (AREA)
- Quality & Reliability (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Testing, Inspecting, Measuring Of Stereoscopic Televisions And Televisions (AREA)
- Image Analysis (AREA)
Abstract
一种企业整改监管方法、装置、设备及计算机可读存储介质，所述方法包括：获取待整改企业整改前的初始视频和整改后的整改视频，并从初始视频和整改视频中分别提取出时间点相同的第一图片和第二图片（S10）；根据第一图片和第二图片，判断与整改视频对应的整改环境是否有效（S20）；若整改环境有效，则获取与初始视频对应的整改任务单（S30）；根据整改任务单，解析整改视频，生成解析结果，并根据解析结果，对待整改企业的整改进行监管（S40）。
Description
优先权信息
本申请要求于2020年4月30日提交中国专利局、申请号为202010369989.9，发明名称为“企业整改监管方法、装置、设备及计算机可读存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
本申请涉及数据处理技术领域，尤其涉及一种企业整改监管方法、装置、设备及计算机可读存储介质。
随着生活水平的提高，餐饮企业得到了蓬勃发展，但是当前部分餐饮企业的后厨存在卫生问题，而影响消费者的健康，因而对餐饮企业后厨的监管检查则显得尤为重要。
当前，监管部门通常通过视频巡查的方式对餐饮企业的后厨进行监管检查，一旦发现违规需要整改的事项，便会给餐饮企业下发限期整改要求。餐饮单位需要在规定的期限之前完成后厨的整改，上报监管部门。发明人意识到，在传统的监管方式下，监管员接收到餐企整改完毕的反馈后，对其整改效果进行复查。一旦经复查判定此次整改不到位需二次整改的情况下，监管员需在二次整改完毕后，再一次进行二次复查工作。整个监管检查过程需消耗监管人员大量的时间，人力成本高，监管检查效率低。
发明内容
本申请的主要目的在于提供一种企业整改监管方法、装置、设备及计算机可读存储介质，旨在解决现有技术中对餐饮企业后厨的监管检查人力成本高、效率低的技术问题。
为实现上述目的，本申请实施例提供一种企业整改监管方法，所述企业整改监管方法包括以下步骤：
获取待整改企业整改前的初始视频和整改后的整改视频，并从所述初始视频和整改视频中分别提取出时间点相同的第一图片和第二图片；
根据所述第一图片和所述第二图片，判断与所述整改视频对应的整改环境是否有效；
若所述整改环境有效，则获取与所述初始视频对应的整改任务单；
根据所述整改任务单，解析所述整改视频，生成解析结果，并根据所述解析结果，对所述待整改企业的整改进行监管。
为实现上述目的，本申请还提供一种企业整改监管装置，所述企业整改监管装置包括：
提取模块，用于获取待整改企业整改前的初始视频和整改后的整改视频，并从所述初始视频和整改视频中分别提取出时间点相同的第一图片和第二图片；
判断模块，用于根据所述第一图片和所述第二图片，判断与所述整改视频对应的整改环境是否有效；
获取模块，用于若所述整改环境有效，则获取与所述初始视频对应的整改任务单；
监管模块，用于根据所述整改任务单，解析所述整改视频，生成解析结果，并根据所述解析结果，对所述待整改企业的整改进行监管。
进一步地，为实现上述目的，本申请还提供企业整改监管设备，所述企业整改监管设备包括存储器、处理器以及存储在所述存储器上并可在所述处理器上运行的企业整改监管程序，所述企业整改监管程序被所述处理器执行时实现如下步骤：
获取待整改企业整改前的初始视频和整改后的整改视频，并从所述初始视频和整改视频中分别提取出时间点相同的第一图片和第二图片；
根据所述第一图片和所述第二图片，判断与所述整改视频对应的整改环境是否有效；
若所述整改环境有效，则获取与所述初始视频对应的整改任务单；
根据所述整改任务单，解析所述整改视频，生成解析结果，并根据所述解析结果，对所述待整改企业的整改进行监管。
此外，为实现上述目的，本申请还提供一种计算机可读存储介质，所述计算机可读存储介质上存储有企业整改监管程序，所述企业整改监管程序被处理器执行时实现如下步骤：
获取待整改企业整改前的初始视频和整改后的整改视频，并从所述初始视频和整改视频中分别提取出时间点相同的第一图片和第二图片；
根据所述第一图片和所述第二图片，判断与所述整改视频对应的整改环境是否有效；
若所述整改环境有效，则获取与所述初始视频对应的整改任务单；
根据所述整改任务单，解析所述整改视频，生成解析结果，并根据所述解析结果，对所述待整改企业的整改进行监管。
本申请提供一种企业整改监管方法、装置、设备及计算机可读存储介质，在获取到待整改企业整改前的初始视频和整改后的整改视频后，从初始视频和整改视频中分别提取出时间点相同的第一图片和第二图片；并根据第一图片和第二图片，判断与整改视频对应的整改环境是否有效；若整改环境有效，则获取与初始视频对应的整改任务单；进而根据整改任务单，解析整改视频，生成解析结果，以根据解析结果，对待整改企业的整改进行监管。因第一图片和第二图片来源于初始视频和整改视频中相同的时间点，若整改视频为真实视频，则第一图片和第二图片所表征的监管环境相同，使得依据第一图片和第二图片判定的整改环境的有效性更为真实准确。在此基础上，依据初始视频对应的整改任务单，对整改视频进行解析，实现对待整改企业的整改进行监管，避免监管人员频繁复查，节省了 人力成本，在确保整改环境真实性的同时提高了监管效率。
图1为本申请实施例方案涉及的硬件运行环境的企业整改监管设备结构示意图；
图2为本申请企业整改监管方法第一实施例的流程示意图；
图3为本申请企业整改监管装置较佳实施例的功能模块示意图。
应当理解，此处所描述的具体实施例仅仅用以解释本申请，并不用于限定本申请。
如图1所示，图1是本申请实施例方案涉及的硬件运行环境的企业整改监管设备结构示意图。
在后续的描述中，使用用于表示元件的诸如“模块”、“部件”或“单元”的后缀仅为了有利于本申请的说明，其本身没有特定的意义。因此，“模块”、“部件”或“单元”可以混合地使用。
本申请实施例企业整改监管设备可以是PC，也可以是平板电脑、便携计算机等可移动式终端设备。
如图1所示，该企业整改监管设备可以包括：处理器1001，例如CPU，网络接口1004，用户接口1003，存储器1005，通信总线1002。其中，通信总线1002用于实现这些组件之间的连接通信。用户接口1003可以包括显示屏(Display)、输入单元比如键盘(Keyboard)，可选用户接口1003还可以包括标准的有线接口、无线接口。网络接口1004可选的可以包括标准的有线接口、无线接口(如WI-FI接口)。存储器1005可以是高速RAM存储器，也可以是稳定的存储器(non-volatile memory)，例如磁盘存储器。存储器1005可选的还可以是独立于前述处理器1001的存储装置。
本领域技术人员可以理解，图1中示出的企业整改监管设备结构并不构成对企业整改监管设备的限定，可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件布置。
如图1所示，作为一种计算机可读存储介质的存储器1005中可以包括操作系统、网络通信模块、用户接口模块以及检测程序。
在图1所示的设备中，网络接口1004主要用于连接后台服务器，与后台服务器进行数据通信；用户接口1003主要用于连接客户端(用户端)，与客户端进行数据通信；而处理器1001可以用于调用存储器1005中存储的检测程序，并执行以下操作：
获取待整改企业整改前的初始视频和整改后的整改视频，并从所述初始视频和整改视频中分别提取出时间点相同的第一图片和第二图片；
根据所述第一图片和所述第二图片，判断与所述整改视频对应的整改环境是否有效；
若所述整改环境有效，则获取与所述初始视频对应的整改任务单；
根据所述整改任务单，解析所述整改视频，生成解析结果，并根据所述解析结果，对所述待整改企业的整改进行监管。
进一步地，所述根据所述第一图片和所述第二图片，判断与所述整改视频对应的整改环境是否有效的步骤包括：
提取所述第一图片中的第一环境特征点，并将各所述第一环境特征点形成为第一特征矩阵；
提取所述第二图片中的第二环境特征点，并将各所述第二环境特征点形成为第二特征矩阵；
确定所述第一特征矩阵和所述第二特征矩阵之间的相似度参数，并根据所述相似度参数，判断与所整改视频对应的整改环境是否有效。
进一步地，所述提取所述第一图片中的第一环境特征点，并将各所述第一环境特征点形成为第一特征矩阵的步骤包括：
识别所述第一图片中的静态物体，并检测各所述静态物体的属性信息，其中所述属性信息至少包括名称、颜色、尺寸、坐标；
将每一所述静态物体的属性信息形成为属性序列，并将各所述属性序列作为所述第一图片中的第一环境特征点；
将各所述第一环境特征点进行排列，形成为第一特征矩阵。
进一步地，所述获取与所述初始视频对应的整改任务单的步骤包括：
对所述初始视频进行解析，并根据预设时间间隔，对解析的所述初始视频进行抽帧，得到多个视频帧；
识别多个所述视频帧中是否存在待整改内容，若存在待整改内容，则将所述待整改内容生成为与所述初始视频对应的整改任务单。
进一步地，所述根据所述整改任务单，解析所述整改视频，生成解析结果的步骤包括：
根据所述预设时间间隔，对所述整改视频进行解析抽帧，得到多张已整改图片；
判断多张所述已整改图片是否包含所述整改任务单中全部的待整改内容，若包含全部的所述待整改内容，则将多张所述已整改图片生成为所述解析结果；
若未包含全部的所述待整改内容，则调整所述预设时间间隔，并根据调整后的所述预设时间间隔，执行对所述整改视频进行解析抽帧的步骤。
进一步地，所述根据所述解析结果，对所述待整改企业的整改进行监管的步骤包括：
获取所述整改任务单中的整改要求，并判断所述解析结果是否与所述整改要求匹配；
若与所述整改要求匹配，则完成对所述待整改企业的整改监管；
若与所述整改要求不匹配，则输出继续整改的提示信息。
进一步地，所述从所述初始视频和整改视频中分别提取出时间点相同的第一图片和第二图片的步骤之前，处理器1001可以用于调用存储器1005中存储的检测程序，并执行以 下操作：
提取所述初始视频的第一生成时间和所述整改视频的第二生成时间，并根据所述第一生成时间和所述第二生成时间，判断所述整改视频是否在预设整改期限内生成；
若在预设整改期限内生成，则执行从所述初始视频和整改视频中分别提取出时间点相同的第一图片和第二图片的步骤；
若不在预设整改期限内，则输出整改无效的提示信息。
本申请企业整改监管设备的具体实施方式与下述企业整改监管方法各实施例基本相同，在此不再赘述。
为了更好的理解上述技术方案，下面将参照附图更详细地描述本公开的示例性实施例。虽然附图中显示了本公开的示例性实施例，然而应当理解，可以以各种形式实现本公开而不应被这里阐述的实施例所限制。相反，提供这些实施例是为了能够更透彻地理解本公开，并且能够将本公开的范围完整的传达给本领域的技术人员。
为了更好的理解上述技术方案，下面将结合说明书附图以及具体的实施方式对上述技术方案进行详细的说明。
参照图2，本申请第一实施例提供一种企业整改监管方法的流程示意图。该实施例中，所述企业整改监管方法包括以下步骤：
步骤S10，获取待整改企业整改前的初始视频和整改后的整改视频，并从所述初始视频和整改视频中分别提取出时间点相同的第一图片和第二图片；
本实施例中的企业整改监管方法应用于服务器，适用于通过服务器对企业的整改进行监管。其中，企业可以是需要进行环境整改和行为整改的各类单位，本实施例优选以餐饮企业的后厨进行说明。即对于餐饮企业后厨中存在脏、乱、差环境，以及餐饮服务人员未佩戴工作帽、工作手套等行为的整改进行监管。
进一步地，服务器与可拍摄视频的摄像头通信连接，以便于摄像头将拍摄的视频传输到服务器进行处理。其中，摄像头可以安装在固定位置，且可在固定位置转动，转动的角度包含了餐饮企业的后厨范围，以对后厨进行拍摄，并确保每个旋转周期所拍摄的环境一致。此外，摄像头也可以以视频巡查的形式存在，且以固定的速度和固定的路线进行巡查，以确保所拍摄环境的一致性。
更进一步地，摄像头按照预先设定的检查周期将拍摄的视频信息传输到服务器，对于某一餐饮企业初次上传的视频信息，服务器判断其中是否存在需要整改的内容，若存在需要整改的内容，则将该企业作为待整改企业，并将该视频信息作为待整改企业整改前的初始视频。服务器中预先针对所需要整改内容的难易程度设定有不同的整改期限，根据初始视频中所需要整改的内容，即可确定其对应的整改期限，将所需要整改的内容和整改期限以通知的形式发送到待整改企业。此后服务器在接收到待整改企业再次上传的视频信息后，将该视频信息作为整改后的整改视频进行获取，并从存储单元中获取此前存储的初始视频，以通过初始视频和整改视频来监管待整改企业的整改是否到位。
进一步地，为了确保初始视频和整改视频针对同一场景进行拍摄，即确保整改视频对应的整改环境为待整改企业内真实需要整改的环境，在获取到初始视频和整改视频之后，从初始视频和整改视频中分别提取出时间点相同的第一图片和第二图片。因初始图片和整改图片通过摄像头拍摄得到，而摄像头以固定位置转动进行拍摄或者以固定的速度和固定的路线进行巡查拍摄，使得初始视频和整改视频在相同时间点所拍摄的场景相同。若整改视频对应的整改环境为待整改企业内真实需要整改的环境，则从相同时间点提取的第一图片和第二图片应当具有相同的场景。从而可依据第一图片和第二图片所展示的场景来检测初始视频和整改视频是否针对同一场景，其中，为了对初始视频和整改视频的判定更为准确，可设定多个相同时间点，提起多张第一图片和第二图片；如在视频时长1分钟时的第一图片和第二图片，2分钟时的第一图片和第二图片，3分钟时的第一图片和第二图片等。
可理解地，待整改企业的整改需要在整改期限内完成，为了确保待整改企业的整改在整改期限内完成，在获取到整改视频后，需要通过该整改视频来确定整改期限。具体地，从初始视频和整改视频中分别提取出时间点相同的第一图片和第二图片的步骤之前包括：
步骤a1，提取所述初始视频的第一生成时间和所述整改视频的第二生成时间，并根据所述第一生成时间和所述第二生成时间，判断所述整改视频是否在预设整改期限内生成；
可理解地，初始视频携带有表征其录制日期的时间，提取该时间作为初始视频的第一生成时间。同样地，整改视频也携带有表征其录制日期的时间，提取该时间作为整改视频的第二生成时间。根据第一生成时间和第二时间所表征的时间差值，判断整改视频是否在预设整改期限内生成，即判断待整改企业的整改是否在要求的整改期限内完成。其中，预设整改期限为上述依据初始视频中所需要整改的内容确定的整改期限。如预设整改期限为一个月，第一生成时间为某年1月1号，第二生成时间为同年1月25号，则因两者之间的时间差值在预设整改期限内，可判定整改视频在预设整改期限内生成，即待整改企业的整改在要求的整改期限内完成。
步骤a2，若在预设整改期限内生成，则执行从所述初始视频和整改视频中分别提取出时间点相同的第一图片和第二图片的步骤；
进一步地，若经确定整改视频在预设整改期限内生成，则说明所生成的整改视频有效，可从初始视频和整改视频中分别提取出时间点相同的第一图片和第二图片，以通过第一图片和第二图片来判断初始视频和整改视频是否针对同一场景进行拍摄，整改视频对应的整改环境是否为待整改企业内真实需要整改的环境，即判断整改视频对应的整改环境是否有效。
步骤a3，若不在预设整改期限内，则输出整改无效的提示信息。
更进一步地，若经确定整改视频不在预设整改期限内生成，则说明待整改企业的整改未在要求的整改期限内完成，待整改企业的整改无效，从而输出整改无效的提示信息。
步骤S20，根据所述第一图片和所述第二图片，判断与所述整改视频对应的整改环境 是否有效；
更进一步地，在从初始视频中提取出第一图片，并且从整改视频中提取出相同时间点的第二图片后，即可依据第一图片中所表征的场景环境和第二图片中所表征的场景环境的一致性，来判断与整改视频对应的整改环境是否有效，即整改视频所拍摄的环境是否为待整改企业经整改后的真实环境。需要说明的是，视频拍摄过程可能拍摄到动态人物，动态人物具有动的特性，使得时间点相同的第一图片和第二图片中的场景不完全一样，如第一图片中包含某一工作人员，则第二图片中不存在工作人员等。因此，为了避免动态人物对第一图片和第二图片所表征场景环境一致性的影响，本实施例可设置动态人物的识别机制。预先通过大量动态人物样本对初始模型进行训练，得到动态人物识别模型，将提取的第一图片和第二图片传输到动态人物识别模型中，由动态人物识别模型识别第一图片和第二图片中是否包含有动态人物，若包含有动态人物，则将动态人物剔除，并判断经剔除动态人物后第一图片和第二图片所表征的场景环境是否一致，以此避免动态人物对场景环境一致性的判断。若一致，则说明与整改视频对应的整改环境有效，整改视频所拍摄的环境为待整改企业经整改后的真实环境。若不一致，则说明与整改视频对应的整改环境无效，整改视频所拍摄的环境非待整改企业经整改后的真实环境，可能存在虚假整改情况。
此外，也可以通过从各个相同时间点所提取的第一图片和第二图片之间的相似度来进行一致性判定，检测每个相同时间点所提取的第一图片和第二图片之间的相似性，进而在各个相似性之间做均值运算，得到多个第一图片和第二图片之间的整体相似度。若该整体相似度大于预设阈值，则说明多张第一图片和第二图片之间的相似性较高，可判定初始视频和整改视频所表征的场景环境一致，与整改视频对应的整改环境有效，整改视频所拍摄的环境为待整改企业经整改后的真实环境。反之，则说明初始视频和整改视频所表征的场景环境不一致，整改视频所拍摄的环境非待整改企业经整改后的真实环境，可能存在虚假整改情况。
步骤S30，若所述整改环境有效，则获取与所述初始视频对应的整改任务单；
进一步地，若经第一图片和第二图片判定出整改环境有效，整改视频是针对整改后的待整改企业进行拍摄，则获取与初始视频对应的整改任务单，以表征待整改企业所需要整改的内容。其中，整改任务单可预先生成并存储在于服务器的存储单元中，并携带表征初始视频的标识，服务器通过该标识从存储单元中读取整改任务单来获取与初始视频对应的整改任务单。此外，整改任务单还可通过预先设定的整改项，实时检测初始视频中是否包含有整改项来生成，即实时识别初始视频中包含的整改项生成为整改任务单。
步骤S40，根据所述整改任务单，解析所述整改视频，生成解析结果，并根据所述解析结果，对所述待整改企业的整改进行监管。
更进一步地，将整改任务单种包含的需要整改的内容作为待整改内容，并根据待整改内容，对整改视频进行解析，得到包含所有待整改内容的多张已整改图片，并将该多张已整改图片作为解析结果。此后，通过判断作为解析结果的多张已整改图片中所有待整改内 容是否均已整改到位，来对待整改企业的整改进行监管。具体地，根据解析结果，对待整改企业的整改进行监管的步骤包括：
步骤S41，获取所述整改任务单中的整改要求，并判断所述解析结果是否与所述整改要求匹配；
进一步地，针对预先设定的所有整改项均设定各自对应的整改要求，无论整改任务单是预先生成还是实时生成，均将整改任务单中所需要整改的待整改内容所对应的整改要求设定到整改任务单中。服务器从整改任务单中获取各待整改内容对应的整改要求，并查找解析结果的多张已整改图片中与各待整改内容对应的已整改图片，进而将各待整改内容对应的已整改图片依据各待整改内容对应的整改要求进行识别，判断各待整改内容对应的已整改图片是否符合各自的整改要求，以此，实现对解析结果是否与整改要求匹配的判断。
步骤S42，若与所述整改要求匹配，则完成对所述待整改企业的整改监管；
更进一步地，若判断出各待整改内容对应的已整改图片均符合各自的整改要求，则说明解析结果与整改要求匹配，待整改企业中所需要整改的内容均已整改到位，则完成对待整改企业的整改监管。需要说明的是，到下一个监管周期，重新获取该企业的初始视频判断其是否需要整改，若需要整改则重新按照上述方式进行整改监管，直到整改到位。
步骤S43，若与所述整改要求不匹配，则输出继续整改的提示信息。
进一步地，若判断出各待整改内容对应的已整改图片中存在任意一项不符合其对应的整改要求，则说明待整改企业中至少存在一项需要整改的内容尚未整改到位，此时输出继续整改的提示信息。其中，提示信息包含需要继续整改的内容以及整改期限。此后，当再次接收到整改视频时，同样判断该再次接收的整改视频是否有效，若有效则获取尚未整改到位的内容生成新的整改任务单，并根据新的整改任务单，对再次接收的整改视频进行解析，并根据解析结果，对待整改企业的整改进行监管，直到待整改企业中所有待整改内容均整改到位。
本实施例的企业整改监管方法，在获取到待整改企业整改前的初始视频和整改后的整改视频后，从初始视频和整改视频中分别提取出时间点相同的第一图片和第二图片；并根据第一图片和第二图片，判断与整改视频对应的整改环境是否有效；若整改环境有效，则获取与初始视频对应的整改任务单；进而根据整改任务单，解析整改视频，生成解析结果，以根据解析结果，对待整改企业的整改进行监管。因第一图片和第二图片来源于初始视频和整改视频中相同的时间点，若整改视频为真实视频，则第一图片和第二图片所表征的监管环境相同，使得依据第一图片和第二图片判定的整改环境的有效性更为真实准确。在此基础上，依据初始视频对应的整改任务单，对整改视频进行解析，实现对待整改企业的整改进行监管，避免监管人员频繁复查，节省了人力成本，在确保整改环境真实性的同时提高了监管效率。
进一步的，基于本申请企业整改监管方法第一实施例，提出本申请企业整改监管方法第二实施例，在第二实施例中，所述根据所述第一图片和所述第二图片，判断与所述整改 视频对应的整改环境是否有效的步骤包括：
步骤S21，提取所述第一图片中的第一环境特征点，并将各所述第一环境特征点形成为第一特征矩阵；
本实施例依据第一图片和第二图片，判断整改视频所针对的整改环境是否有效，通过第一图片和第二图片之间所表征场景的相似性实现，两者之间所表征场景的相似性越高，说明初始视频和整改视频针对同一场景的可能性越大，即整改视频有效，反之整改视频无效。具体地，从第一图片中提取出第一环境特征点，其中第一环境特征点为第一图片中包含的静态物体的特征信息。此后，将各个静态物体的特征信息形成为第一特征矩阵，以通过第一特征矩阵来表征第一图片中包含的所有静态物体特征。其中，提取第一图片中的第一环境特征点，并将各第一环境特征点形成为第一特征矩阵的步骤包括：
步骤S211，识别所述第一图片中的静态物体，并检测各所述静态物体的属性信息，其中所述属性信息至少包括名称、颜色、尺寸、坐标；
进一步地，预先通过餐饮企业中常用的诸如餐桌、椅子、锅、炉子等固态物体图片作为训练样本对初始模型进行训练，得到用于识别环境中固态物体的识别模型。服务器调用该识别模型识别第一图片中具有的静态物体，再检测静态物体的数量和各静态物体的属性信息，属性信息至少包括静态物体的名称、颜色、尺寸、坐标等。具体地，可通过初始模型训练过程中，将各训练样本的名称标签来识别各静态物体的名称；同时通过OpenCV图像处理技术来识别静态物体的颜色，并设定预设坐标系，通过检测静态物体在该预设坐标系中的位置来确定尺寸大小，以及位置坐标。
步骤S212，将每一所述静态物体的属性信息形成为属性序列，并将各所述属性序列作为所述第一图片中的第一环境特征点；
更进一步地，将每个静态物体所具有的属性信息形成为各静态物体的属性序列，并将各属性序列作为第一图片中的第一环境特征点。如识别出第一图片中的静态物体A，其名称、颜色、尺寸和坐标分别为：桌子、黑色、1m*1m、(20，30)，则对其所形成的属性序列为[桌子、黑色、1m*1m、(20，30)]。并且，将该属性序列作为第一图片中的一个第一环境特征点，表征第一图片中静态物体“桌子”的各项特征。
步骤S213，将各所述第一环境特征点进行排列，形成为第一特征矩阵。
进一步地，在将各静态物体的属性信息均形成为属性序列，即得到表征第一图片中各静态物体特征的各项第一环境特征点后，将各项第一环境特征点形成为第一特征矩阵，第一特征矩阵中每一行表示一个静态物体的各类特征，每一列表示每个静态物体在某项特征上的表现，如
步骤S22，提取所述第二图片中的第二环境特征点，并将各所述第二环境特征点形成 为第二特征矩阵；
同样地，从第二图片中提取出第二环境特征点，第二环境特征点为第二图片中包含的静态物体的特征信息。此后，将各个静态物体的特征信息形成为第二特征矩阵，以通过第二特征矩阵来表征第二图片中包含的所有静态物体特征。其中，提取第二环境特征点形成第二特征矩阵的方式与提取第一环境特征点形成第一特征矩阵的方式相同。即，识别第二图片中的静态物体，并检测各所述静态物体的属性信息，其中属性信息至少包括名称、颜色、尺寸、坐标；将每一静态物体的属性信息形成为属性序列，并将各属性序列作为第二图片中的第二环境特征点；将各第二环境特征点进行排列，形成为第二特征矩阵。其具体实施方式和上述形成第一特征矩阵相同，在此不做赘述。
步骤S23，确定所述第一特征矩阵和所述第二特征矩阵之间的相似度参数，并根据所述相似度参数，判断与所整改视频对应的整改环境是否有效。
更进一步地，在第一特征矩阵和第二特征矩阵之间进行矩阵运算，得到表征两者之间相似程度高低的相似度参数。此外，服务器中预先设置有表征相似程度高低的相似度阈值，将得到的相似度参数和该相似度阈值对比，判断相似度参数是否大于相似度阈值。若相似度参数大于相似度阈值，则表征第一图片中静态物体的特征与第二图片中静态物体的特征越相似，整改所针对的环境为待整改企业的环境，从而判定与整个视频对应的整改环境有效。反之，若相似度参数不大于相似度阈值，则表征第一图片中静态物体的特征与第二图片中静态物体的特征相似程度低，整改所针对的环境不是待整改企业的环境，可能存在虚假整改的情况，故而判定与整个视频对应的整改环境无效。
本实施例通过从第一图片和第二图片中提取出各自静态物体的特征点，形成第一特征矩阵和第二特征矩阵来表征第一图片和第二图片中包含的所有静态物体的特征，进而通过第一特征矩阵和第二特征矩阵之间的相似度参数，来判断整改视频针对的整改环境是否有效。因第一特征矩阵包含了第一图片中所有静态物体的特征，第二特征矩阵包含了第二图片中所有静态物体的特征，使得通过两者的相似度参数所判定的整改环境的有效性更为真实准确。
进一步的，基于本申请企业整改监管方法第一实施例或第二实施例，提出本申请企业整改监管方法第三实施例，在第三实施例中，所述获取与所述初始视频对应的整改任务单的步骤包括：
步骤S31，对所述初始视频进行解析，并根据预设时间间隔，对解析的所述初始视频进行抽帧，得到多个视频帧；
在本实施例中，与初始视频对应的整改任务单优选为依据预先设定的整改项，实时检测初始视频中包含的整改项生成。具体地，先通过ffmpeng对初始视频进行解析，并按照预先设定的预设时间间隔，对解析的初始视频进行抽帧，得到多个视频帧。其中预设时间间隔表征对解析的初始视频进行抽帧的时间跨度，如预设时间间隔5为秒，则从初始视频的第0秒进行抽帧后，到第5秒再次抽帧，直到初始视频的结束时间。预设时间间隔越小， 所抽帧的数量越多，以此所形成的整改任务单越准确。
步骤S32，识别多个所述视频帧中是否存在待整改内容，若存在待整改内容，则将所述待整改内容生成为与所述初始视频对应的整改任务单。
进一步地，根据预先设定的整改项，对多个视频站进行识别，识别各视频帧中是否存在需要整改的内容，即是否存在待整改内容。其中，需要整改的内容包括但不限于工作人员未佩戴工作帽、后厨有蟑螂老鼠、厨房脏乱等。若存在待整改内容，则将各项待整改内容添加到整改任务单的模板中，形成与初始视频对应的整改任务单，通过整改任务单中的各项待整改内容来表征待整改企业所需要整改的内容。
更进一步地，所述根据所述整改任务单，解析所述整改视频，生成解析结果的步骤包括：
步骤S44，根据所述预设时间间隔，对所述整改视频进行解析抽帧，得到多张已整改图片；
进一步地，对于待整改企业整改后的整改视频，同样根据预设时间间隔，通过ffmpeng进行解析抽帧，得到多张已整改图片。通过多张已整改图片，来反映待整改企业的整改情况，各项需要整改的内容是否均已整改到位等。
步骤S45，判断多张所述已整改图片是否包含所述整改任务单中全部的待整改内容，若包含全部的所述待整改内容，则将多张所述已整改图片生成为所述解析结果；
可理解地，为了使得已整改图片完整的反映待整改企业的整改情况，需要确保多张已整改图片包括整改任务单中所有的待整改内容。如整改任务单中的待整改内容包括工作人员未佩戴工作帽和后厨有蟑螂，则抽帧的多张已整改图片中至少包含一个工作人员，且至少包含后厨环境。因而，在得到多张已整改图片后，根据整改任务单，对多张已整改图片进行判断，判断多张已整改图片是否包含整改任务单中全部的待整改内容。若包含全部的待整改内容，则说明对整改视频抽帧，得到的多张已整改图片符合要求，而将其生成为解析结果。
步骤S46，若未包含全部的所述待整改内容，则调整所述预设时间间隔，并根据调整后的所述预设时间间隔，执行对所述整改视频进行解析抽帧的步骤。
进一步地，若经判定多张已整改图片未包括整改任务单中全部的待整改内容，即多张已整改图片缺少待整改任务单中任意一项待整改内容，则对预设时间间隔进行调整，将预设时间间隔调整为更小的时间跨度。此后，基于调整的预设时间时间跨度，对整改视频重新进行抽帧，以抽取更多的已整改图片，直到包含整改任务单中全部的待整改内容，生成解析结果。需要说明的是，若多张已整改图片中包含多张重复的待整改内容，说明抽取的已整改图片过多，可将预设时间间隔调整为更大的时间跨度进行抽帧，以避免将过多重复的已整改图片生成为解析结果，导致服务器对解析结果处理数据量的增加，降低了处理效率。
本实施例依据预设时间间隔，对初始视频解析抽帧形成整改任务单，并根据整改任务 单对整改视频进行解析抽帧形成已整改图片，由已整改图片形成解析结果来反映待整改企业的整改情况。通过将预设时间间隔设定为可调整的特性，来确保所抽取的已整改图片包括整改任务单中全部的待整改内容，使得根据已整改图片所形成的解析结果，对待整改企业整改所进行监管更为准确。
进一步地，本申请还提供一种企业整改监管装置。
参照图3，图3为本申请企业整改监管装置第一实施例的功能模块示意图。所述企业整改监管装置包括：
提取模块10，用于获取待整改企业整改前的初始视频和整改后的整改视频，并从所述初始视频和整改视频中分别提取出时间点相同的第一图片和第二图片；
判断模块20，用于根据所述第一图片和所述第二图片，判断与所述整改视频对应的整改环境是否有效；
获取模块30，用于若所述整改环境有效，则获取与所述初始视频对应的整改任务单；
监管模块40，用于根据所述整改任务单，解析所述整改视频，生成解析结果，并根据所述解析结果，对所述待整改企业的整改进行监管。
本实施例的企业整改监管装置，提取模块10在获取到待整改企业整改前的初始视频和整改后的整改视频后，从初始视频和整改视频中分别提取出时间点相同的第一图片和第二图片；并由判断模块20根据第一图片和第二图片，判断与整改视频对应的整改环境是否有效；若整改环境有效，则由获取模块30获取与初始视频对应的整改任务单；进而由监管模块40根据整改任务单，解析整改视频，生成解析结果，以根据解析结果，对待整改企业的整改进行监管。因第一图片和第二图片来源于初始视频和整改视频中相同的时间点，若整改视频为真实视频，则第一图片和第二图片所表征的监管环境相同，使得依据第一图片和第二图片判定的整改环境的有效性更为真实准确。在此基础上，依据初始视频对应的整改任务单，对整改视频进行解析，实现对待整改企业的整改进行监管，避免监管人员频繁复查，节省了人力成本，在确保整改环境真实性的同时提高了监管效率。
进一步地，所述判断模块20包括：
第一提取单元，用于提取所述第一图片中的第一环境特征点，并将各所述第一环境特征点形成为第一特征矩阵；
第二提取单元，用于提取所述第二图片中的第二环境特征点，并将各所述第二环境特征点形成为第二特征矩阵；
判断单元，用于确定所述第一特征矩阵和所述第二特征矩阵之间的相似度参数，并根据所述相似度参数，判断与所整改视频对应的整改环境是否有效。
进一步地，所述第一提取单元还用于包括：
所述提取所述第一图片中的第一环境特征点，并将各所述第一环境特征点形成为第一特征矩阵的步骤包括：
识别所述第一图片中的静态物体，并检测各所述静态物体的属性信息，其中所述属性 信息至少包括名称、颜色、尺寸、坐标；
将每一所述静态物体的属性信息形成为属性序列，并将各所述属性序列作为所述第一图片中的第一环境特征点；
将各所述第一环境特征点进行排列，形成为第一特征矩阵。
进一步地，所述获取模块30还包括：
解析单元，用于对所述初始视频进行解析，并根据预设时间间隔，对解析的所述初始视频进行抽帧，得到多个视频帧；
识别单元，用于识别多个所述视频帧中是否存在待整改内容，若存在待整改内容，则将所述待整改内容生成为与所述初始视频对应的整改任务单。
进一步地，所述监管模块40还包括：
抽帧单元，用于根据所述预设时间间隔，对所述整改视频进行解析抽帧，得到多张已整改图片；
生成单元，用于判断多张所述已整改图片是否包含所述整改任务单中全部的待整改内容，若包含全部的所述待整改内容，则将多张所述已整改图片生成为所述解析结果；
调整单元，用于若未包含全部的所述待整改内容，则调整所述预设时间间隔，并根据调整后的所述预设时间间隔，执行对所述整改视频进行解析抽帧的步骤。
进一步地，所述监管模块40还包括：
获取单元，用于获取所述整改任务单中的整改要求，并判断所述解析结果是否与所述整改要求匹配；
完成单元，用于若与所述整改要求匹配，则完成对所述待整改企业的整改监管；
第一输出单元，用于若与所述整改要求不匹配，则输出继续整改的提示信息。
进一步地，所述提取模块10包括：
第三提取单元，用于提取所述初始视频的第一生成时间和所述整改视频的第二生成时间，并根据所述第一生成时间和所述第二生成时间，判断所述整改视频是否在预设整改期限内生成；
执行单元，用于若在预设整改期限内生成，则执行从所述初始视频和整改视频中分别提取出时间点相同的第一图片和第二图片的步骤；
第二输出单元，用于若不在预设整改期限内，则输出整改无效的提示信息。
本申请企业整改监管装置具体实施方式与上述企业整改监管方法各实施例基本相同，在此不再赘述。
此外，本申请实施例还提出一种计算机可读存储介质，所述计算机可读存储介质可以是非易失性的，也可以是易失性的。
计算机可读存储介质上存储有企业整改监管程序，企业整改监管程序被处理器执行时实现如上所述的企业整改监管方法的步骤。
本申请计算机可读存储介质的具体实施方式与上述企业整改监管方法各实施例基本 相同，在此不再赘述。
需要说明的是，在本文中，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者系统不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者系统所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括该要素的过程、方法、物品或者系统中还存在另外的相同要素。
上述本申请实施例序号仅仅为了描述，不代表实施例的优劣。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件，但很多情况下前者是更佳的实施方式。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品存储在如上所述的一个计算机可读存储介质(如ROM/RAM、磁碟、光盘)中，包括若干指令用以使得一台终端设备(可以是手机，计算机，服务器，空调器，或者网络设备等)执行本申请各个实施例所述的方法。
以上仅为本申请的优选实施例，并非因此限制本申请的专利范围，凡是利用本申请说明书及附图内容所作的等效结构或等效流程变换，或直接或间接运用在其他相关的技术领域，均同理包括在本申请的专利保护范围内。
Claims (20)
- 一种企业整改监管方法，其中，所述企业整改监管方法包括以下步骤：获取待整改企业整改前的初始视频和整改后的整改视频，并从所述初始视频和整改视频中分别提取出时间点相同的第一图片和第二图片；根据所述第一图片和所述第二图片，判断与所述整改视频对应的整改环境是否有效；若所述整改环境有效，则获取与所述初始视频对应的整改任务单；根据所述整改任务单，解析所述整改视频，生成解析结果，并根据所述解析结果，对所述待整改企业的整改进行监管。
- 如权利要求1所述的企业整改监管方法，其中，所述根据所述第一图片和所述第二图片，判断与所述整改视频对应的整改环境是否有效的步骤包括：提取所述第一图片中的第一环境特征点，并将各所述第一环境特征点形成为第一特征矩阵；提取所述第二图片中的第二环境特征点，并将各所述第二环境特征点形成为第二特征矩阵；确定所述第一特征矩阵和所述第二特征矩阵之间的相似度参数，并根据所述相似度参数，判断与所整改视频对应的整改环境是否有效。
- 如权利要求2所述的企业整改监管方法，其中，所述提取所述第一图片中的第一环境特征点，并将各所述第一环境特征点形成为第一特征矩阵的步骤包括：识别所述第一图片中的静态物体，并检测各所述静态物体的属性信息，其中所述属性信息至少包括名称、颜色、尺寸、坐标；将每一所述静态物体的属性信息形成为属性序列，并将各所述属性序列作为所述第一图片中的第一环境特征点；将各所述第一环境特征点进行排列，形成为第一特征矩阵。
- 如权利要求1所述的企业整改监管方法，其中，所述获取与所述初始视频对应的整改任务单的步骤包括：对所述初始视频进行解析，并根据预设时间间隔，对解析的所述初始视频进行抽帧，得到多个视频帧；识别多个所述视频帧中是否存在待整改内容，若存在待整改内容，则将所述待整改内容生成为与所述初始视频对应的整改任务单。
- 如权利要求4所述的企业整改监管方法，其中，所述根据所述整改任务单，解析所述整改视频，生成解析结果的步骤包括：根据所述预设时间间隔，对所述整改视频进行解析抽帧，得到多张已整改图片；判断多张所述已整改图片是否包含所述整改任务单中全部的待整改内容，若包含全部的所述待整改内容，则将多张所述已整改图片生成为所述解析结果；若未包含全部的所述待整改内容，则调整所述预设时间间隔，并根据调整后的所述预设时间间隔，执行对所述整改视频进行解析抽帧的步骤。
- 如权利要求1-5任一项所述的企业整改监管方法，其中，所述根据所述解析结果，对所述待整改企业的整改进行监管的步骤包括：获取所述整改任务单中的整改要求，并判断所述解析结果是否与所述整改要求匹配；若与所述整改要求匹配，则完成对所述待整改企业的整改监管；若与所述整改要求不匹配，则输出继续整改的提示信息。
- 如权利要求1-5任一项所述的企业整改监管方法，其中，所述从所述初始视频和整改视频中分别提取出时间点相同的第一图片和第二图片的步骤之前包括：提取所述初始视频的第一生成时间和所述整改视频的第二生成时间，并根据所述第一生成时间和所述第二生成时间，判断所述整改视频是否在预设整改期限内生成；若在预设整改期限内生成，则执行从所述初始视频和整改视频中分别提取出时间点相同的第一图片和第二图片的步骤；若不在预设整改期限内，则输出整改无效的提示信息。
- 一种企业整改监管装置，其中，所述企业整改监管装置包括：提取模块，用于获取待整改企业整改前的初始视频和整改后的整改视频，并从所述初始视频和整改视频中分别提取出时间点相同的第一图片和第二图片；判断模块，用于根据所述第一图片和所述第二图片，判断与所述整改视频对应的整改环境是否有效；获取模块，用于若所述整改环境有效，则获取与所述初始视频对应的整改任务单；监管模块，用于根据所述整改任务单，解析所述整改视频，生成解析结果，并根据所述解析结果，对所述待整改企业的整改进行监管。
- 一种企业整改监管设备，其中，所述企业整改监管设备包括存储器、处理器以及存储在所述存储器上并可在所述处理器上运行的企业整改监管程序，所述企业整改监管程序被所述处理器执行时实现如下步骤：获取待整改企业整改前的初始视频和整改后的整改视频，并从所述初始视频和整改视频中分别提取出时间点相同的第一图片和第二图片；根据所述第一图片和所述第二图片，判断与所述整改视频对应的整改环境是否有效；若所述整改环境有效，则获取与所述初始视频对应的整改任务单；根据所述整改任务单，解析所述整改视频，生成解析结果，并根据所述解析结果，对所述待整改企业的整改进行监管。
- 如权利要求9所述的企业整改监管设备，其中，所述根据所述第一图片和所述第二图片，判断与所述整改视频对应的整改环境是否有效的步骤包括：提取所述第一图片中的第一环境特征点，并将各所述第一环境特征点形成为第一特征矩阵；提取所述第二图片中的第二环境特征点，并将各所述第二环境特征点形成为第二特征矩阵；确定所述第一特征矩阵和所述第二特征矩阵之间的相似度参数，并根据所述相似度参数，判断与所整改视频对应的整改环境是否有效。
- 如权利要求10所述的企业整改监管设备，其中，所述提取所述第一图片中的第一环境特征点，并将各所述第一环境特征点形成为第一特征矩阵的步骤包括：识别所述第一图片中的静态物体，并检测各所述静态物体的属性信息，其中所述属性信息至少包括名称、颜色、尺寸、坐标；将每一所述静态物体的属性信息形成为属性序列，并将各所述属性序列作为所述第一图片中的第一环境特征点；将各所述第一环境特征点进行排列，形成为第一特征矩阵。
- 如权利要求9所述的企业整改监管设备，其中，所述获取与所述初始视频对应的整改任务单的步骤包括：对所述初始视频进行解析，并根据预设时间间隔，对解析的所述初始视频进行抽帧，得到多个视频帧；识别多个所述视频帧中是否存在待整改内容，若存在待整改内容，则将所述待整改内容生成为与所述初始视频对应的整改任务单。
- 如权利要求12所述的企业整改监管设备，其中，所述根据所述整改任务单，解析所述整改视频，生成解析结果的步骤包括：根据所述预设时间间隔，对所述整改视频进行解析抽帧，得到多张已整改图片；判断多张所述已整改图片是否包含所述整改任务单中全部的待整改内容，若包含全部的所述待整改内容，则将多张所述已整改图片生成为所述解析结果；若未包含全部的所述待整改内容，则调整所述预设时间间隔，并根据调整后的所述预设时间间隔，执行对所述整改视频进行解析抽帧的步骤。
- 如权利要求9-13任一项所述的企业整改监管设备，其中，所述根据所述解析结果，对所述待整改企业的整改进行监管的步骤包括：获取所述整改任务单中的整改要求，并判断所述解析结果是否与所述整改要求匹配；若与所述整改要求匹配，则完成对所述待整改企业的整改监管；若与所述整改要求不匹配，则输出继续整改的提示信息。
- 如权利要求9-13任一项所述的企业整改监管设备，其中，所述从所述初始视频和整改视频中分别提取出时间点相同的第一图片和第二图片的步骤之前包括：提取所述初始视频的第一生成时间和所述整改视频的第二生成时间，并根据所述第一生成时间和所述第二生成时间，判断所述整改视频是否在预设整改期限内生成；若在预设整改期限内生成，则执行从所述初始视频和整改视频中分别提取出时间点相同的第一图片和第二图片的步骤；若不在预设整改期限内，则输出整改无效的提示信息。
- 一种计算机可读存储介质，其中，所述计算机可读存储介质上存储有企业整改监管程序，所述企业整改监管程序被处理器执行时实现如下步骤：获取待整改企业整改前的初始视频和整改后的整改视频，并从所述初始视频和整改视频中分别提取出时间点相同的第一图片和第二图片；根据所述第一图片和所述第二图片，判断与所述整改视频对应的整改环境是否有效；若所述整改环境有效，则获取与所述初始视频对应的整改任务单；根据所述整改任务单，解析所述整改视频，生成解析结果，并根据所述解析结果，对所述待整改企业的整改进行监管。
- 如权利要求16所述的计算机可读存储介质，其中，所述根据所述第一图片和所述第二图片，判断与所述整改视频对应的整改环境是否有效的步骤包括：提取所述第一图片中的第一环境特征点，并将各所述第一环境特征点形成为第一特征矩阵；提取所述第二图片中的第二环境特征点，并将各所述第二环境特征点形成为第二特征矩阵；确定所述第一特征矩阵和所述第二特征矩阵之间的相似度参数，并根据所述相似度参数，判断与所整改视频对应的整改环境是否有效。
- 如权利要求17所述的计算机可读存储介质，其中，所述提取所述第一图片中的第一环境特征点，并将各所述第一环境特征点形成为第一特征矩阵的步骤包括：识别所述第一图片中的静态物体，并检测各所述静态物体的属性信息，其中所述属性信息至少包括名称、颜色、尺寸、坐标；将每一所述静态物体的属性信息形成为属性序列，并将各所述属性序列作为所述第一图片中的第一环境特征点；将各所述第一环境特征点进行排列，形成为第一特征矩阵。
- 如权利要求16所述的计算机可读存储介质，其中，所述获取与所述初始视频对应的整改任务单的步骤包括：对所述初始视频进行解析，并根据预设时间间隔，对解析的所述初始视频进行抽帧，得到多个视频帧；识别多个所述视频帧中是否存在待整改内容，若存在待整改内容，则将所述待整改内容生成为与所述初始视频对应的整改任务单。
- 如权利要求19所述的计算机可读存储介质，其中，所述根据所述整改任务单，解析所述整改视频，生成解析结果的步骤包括：根据所述预设时间间隔，对所述整改视频进行解析抽帧，得到多张已整改图片；判断多张所述已整改图片是否包含所述整改任务单中全部的待整改内容，若包含全部的所述待整改内容，则将多张所述已整改图片生成为所述解析结果；若未包含全部的所述待整改内容，则调整所述预设时间间隔，并根据调整后的所述预设时间间隔，执行对所述整改视频进行解析抽帧的步骤。
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010369989.9 | 2020-04-30 | ||
| CN202010369989.9A CN111563726A (zh) | 2020-04-30 | 2020-04-30 | 企业整改监管方法、装置、设备及计算机可读存储介质 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2021217943A1 true WO2021217943A1 (zh) | 2021-11-04 |
Family
ID=72074448
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2020/106069 WO2021217943A1 (zh) | 2020-04-30 | 2020-07-31 | 企业整改监管方法、装置、设备及计算机可读存储介质 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN111563726A (zh) |
| WO (1) | WO2021217943A1 (zh) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114339145A (zh) * | 2021-12-06 | 2022-04-12 | 浪潮软件股份有限公司 | 一种基于智能可视化的企业经营闭环监管方法及系统 |
| CN114666478B (zh) * | 2022-03-26 | 2024-04-30 | 武汉晟天元智能科技有限公司 | 一种企业整改监管装置及方法 |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170364515A1 (en) * | 2013-11-26 | 2017-12-21 | Viscovery Pte. Ltd. | Mobile device capable of offline and online synchronous image identifying, an image identifying system, and a storage medium for the same |
| CN108229780A (zh) * | 2016-12-22 | 2018-06-29 | 中国科学院沈阳自动化研究所 | 一种基于平板电脑的车间管理系统和方法 |
| CN109040781A (zh) * | 2018-08-27 | 2018-12-18 | 北京京东尚科信息技术有限公司 | 视频认证方法、装置、系统、电子设备及可读介质 |
| CN110381293A (zh) * | 2019-06-18 | 2019-10-25 | 平安国际智慧城市科技股份有限公司 | 视频监控方法、装置及计算机可读存储介质 |
| CN110472922A (zh) * | 2018-05-09 | 2019-11-19 | 洛阳华清天木生物科技有限公司 | 一种基于智慧实验室安全检查的管理系统 |
Family Cites Families (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4595759B2 (ja) * | 2005-09-09 | 2010-12-08 | 株式会社デンソー | 環境認識装置 |
| US20170076176A1 (en) * | 2015-09-16 | 2017-03-16 | Le Holdings (Beijing) Co., Ltd. | Method and system for displaying item related information in video streaming |
| CN106686404B (zh) * | 2016-12-16 | 2021-02-02 | 中兴通讯股份有限公司 | 一种视频分析平台、匹配方法、精准投放广告方法及系统 |
| CN108830501A (zh) * | 2018-06-28 | 2018-11-16 | 林冠眉 | 一种基于企业微信公众平台的问题库管理方法与系统 |
| CN109063612A (zh) * | 2018-07-19 | 2018-12-21 | 中智城信息技术有限公司 | 城市智能红线管理方法及机器可读存储介质 |
| CN109583771A (zh) * | 2018-12-04 | 2019-04-05 | 北京诺士诚国际工程项目管理有限公司 | 一种工程督办方法及装置 |
| CN110008832A (zh) * | 2019-02-27 | 2019-07-12 | 西安电子科技大学 | 基于深度学习人物图像自动分割方法、信息数据处理终端 |
| CN110136021A (zh) * | 2019-06-06 | 2019-08-16 | 天津智橙物联科技有限公司 | 一种车间管理的系统 |
| CN110516656A (zh) * | 2019-09-04 | 2019-11-29 | 上海眼控科技股份有限公司 | 视频监控方法、装置、计算机设备和可读存储介质 |
| CN110532988B (zh) * | 2019-09-04 | 2021-01-05 | 上海眼控科技股份有限公司 | 行为监控方法、装置、计算机设备和可读存储介质 |
| CN110795595B (zh) * | 2019-09-10 | 2024-03-05 | 安徽南瑞继远电网技术有限公司 | 基于边缘计算的视频结构化存储方法、装置、设备及介质 |
| CN110728270A (zh) * | 2019-12-17 | 2020-01-24 | 北京影谱科技股份有限公司 | 视频人物的去除方法、装置及设备及计算机可读存储介质 |
-
2020
- 2020-04-30 CN CN202010369989.9A patent/CN111563726A/zh active Pending
- 2020-07-31 WO PCT/CN2020/106069 patent/WO2021217943A1/zh active Application Filing
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170364515A1 (en) * | 2013-11-26 | 2017-12-21 | Viscovery Pte. Ltd. | Mobile device capable of offline and online synchronous image identifying, an image identifying system, and a storage medium for the same |
| CN108229780A (zh) * | 2016-12-22 | 2018-06-29 | 中国科学院沈阳自动化研究所 | 一种基于平板电脑的车间管理系统和方法 |
| CN110472922A (zh) * | 2018-05-09 | 2019-11-19 | 洛阳华清天木生物科技有限公司 | 一种基于智慧实验室安全检查的管理系统 |
| CN109040781A (zh) * | 2018-08-27 | 2018-12-18 | 北京京东尚科信息技术有限公司 | 视频认证方法、装置、系统、电子设备及可读介质 |
| CN110381293A (zh) * | 2019-06-18 | 2019-10-25 | 平安国际智慧城市科技股份有限公司 | 视频监控方法、装置及计算机可读存储介质 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111563726A (zh) | 2020-08-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105303632B (zh) | 一种移动监控签到系统及工作方法 | |
| WO2021217943A1 (zh) | 企业整改监管方法、装置、设备及计算机可读存储介质 | |
| CN110569874A (zh) | 一种垃圾分类方法、装置、智能终端及存储介质 | |
| KR20200098875A (ko) | 3ｄ 얼굴인식 시스템 및 방법 | |
| WO2018090641A1 (zh) | 识别保险单号码的方法、装置、设备及计算机可读存储介质 | |
| CN110781805B (zh) | 一种目标物体检测方法、装置、计算设备和介质 | |
| WO2019056503A1 (zh) | 门店监控评价方法、装置及存储介质 | |
| CN109658040A (zh) | 会议管理的方法、装置、设备及计算机存储介质 | |
| CN109873979A (zh) | 一种基于摄像头的静态图像差异比对方法及装置 | |
| CN110096606B (zh) | 一种外籍人员管理方法、装置和电子设备 | |
| CN110288755A (zh) | 基于文本识别的发票检验方法、服务器及存储介质 | |
| CN109558792B (zh) | 一种基于样本和特征检测互联网徽标内容的方法和系统 | |
| TW201448585A (zh) | 利用行動電話及雲端可視化搜尋引擎之即時物體掃描 | |
| CN111368808A (zh) | 答题数据的采集方法、装置、系统和教学设备 | |
| WO2018149322A1 (zh) | 图像识别方法、装置、设备及存储介质 | |
| CN113689070B (zh) | 食品安全在线监管方法及装置、存储介质、计算机设备 | |
| CN111047147A (zh) | 一种业务流程自动采集方法及智能终端 | |
| CN113568934A (zh) | 一种数据查询方法、装置、电子设备和存储介质 | |
| CN111199172A (zh) | 基于终端录屏的处理方法及装置、存储介质 | |
| CN111680653A (zh) | 座位信息生成方法、装置、设备及存储介质 | |
| CN111047731A (zh) | 一种基于ar技术的电信机房巡检方法及系统 | |
| CN108334602B (zh) | 数据标注方法和装置、电子设备、计算机存储介质 | |
| JP6567638B2 (ja) | 鼻紋照合システム、鼻紋照合方法及び鼻紋照合プログラム | |
| CN111339939B (zh) | 基于图像识别的考勤方法及装置 | |
| CN106097403B (zh) | 一种基于图像曲线推算的网络受保护指数数据的获取方法 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 20933545 Country of ref document: EP Kind code of ref document: A1 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 32PN | Ep: public notification in the ep bulletin as address of the adressee cannot be established |
Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 15/03/2023) |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 20933545 Country of ref document: EP Kind code of ref document: A1 |