Method and device for improving safety management system of iron and steel enterprise

Abstract

The invention relates to the technical field of steel safety management, and provides a method and a device for improving a safety management system of a steel enterprise. The method comprises the following steps: organizing an expert to determine at least one current problem point on site in advance according to a safety standard, and collecting a multi-view picture set of each current problem point; generating an initial report table according to the optimal view angle picture in the multi-view angle picture set; and obtaining to-be-rectified information of each current problem point filled in the initial report table by an expert according to the safety standard to obtain a target report table. On the basis of on-site investigation of the expert, the expert is assisted to complete the target report table by collecting the multi-view picture set and generating the initial report table according to the optimal view picture, and the problems that in the prior art, report table filling efficiency is low, the generated report table is inconvenient to read, and the report table cannot be read easily are solved. And the accident prevention and control effect level is influenced.

Description

Technical Field

[0001] The present invention relates to the technical field of steel safety management, and in particular to a method and device for improving the safety management system of a steel enterprise. Background Art

[0002] The steel industry is an important basic raw material industry for the national economy. However, the steel industry has the characteristics of multiple professions, long processes, complex equipment and operations, and continuous operations, which are dangerous and have high inherent safety risks. At present, in order to prevent and control safety accidents, on the one hand, the regulatory authorities have increased safety supervision, and on the other hand, the steel enterprises themselves have improved their safety management level.

[0003] Generally, after conducting a hidden danger inspection in accordance with safety standards, it is necessary to record relevant problem points and generate corresponding report forms. However, due to the lack of a reliable process, the efficiency of filling out the report form is often low, and it is very likely that the safety standards violated by the problem point will not be recorded in the report form, and the problem point may even be missed, making it difficult for relevant personnel to grasp the hidden danger inspection situation through the report form. They have to communicate and combine other materials to grasp the hidden danger inspection situation. The safety management efficiency is too low, which is not conducive to accident prevention and control. In addition, the generated report form is likely to have a chaotic distribution of content and is not easy to read, which further affects the understanding of the problem points by relevant personnel, and thus affects the effect of accident prevention and control.

[0004] In view of this, overcoming the defects of the prior art is an urgent problem to be solved in the field of this technology. Summary of the invention

[0005] The technical problem to be solved by the present invention is to provide a method and device for improving the safety management system of a steel enterprise, the purpose of which is to determine at least one current problem point on site, and generate an initial report form based on a multi-perspective image set of each current problem point and the optimal perspective image therein; organize experts to fill in corresponding information to be rectified in the initial report form according to safety standards, so as to timely and thoroughly identify the current problem points and form a target report form, thereby solving the problem that the efficiency of filling in report forms in the prior art is low, the generated report forms are not easy to read, and the level of accident prevention and control effects is affected.

[0006] The present invention adopts the following technical solution:

[0007] In a first aspect, the present invention provides a method for improving the safety management system of a steel enterprise, wherein experts are organized to determine at least one current problem point on site in advance according to safety standards, and to collect a multi-view picture set of each current problem point; then for the at least one current problem point, the method for improving the safety management system of a steel enterprise comprises:

[0008] Generate an initial report table according to the optimal viewing angle picture in the multi-view picture set;

[0009] Obtain the information to be rectified for each current problem point filled in by the expert in the initial report form according to the safety standard, and obtain a target report form, so as to rectify the at least one current problem point according to the target report form.

[0010] Further, before generating an initial report table according to the optimal view picture in the multi-view picture set, the method includes:

[0011] Pre-acquire a set of historical pictures of historical problem points; wherein the set of historical pictures includes at least three historical pictures with different viewing angles;

[0012] The priority mapping relationship between the historical display priority of the historical picture and the historical problem point is learned to obtain a priority model, so as to use the priority model to determine the optimal viewing angle picture.

[0013] Further, generating an initial report table according to the optimal view picture in the multi-view picture set includes:

[0014] Determine the problem sequence number of the at least one current problem point; store the multi-view picture set of the at least one current problem point respectively according to the corresponding problem sequence number; wherein the multi-view picture set includes at least three scene pictures of different perspectives;

[0015] Using the priority model, determining the current display priority of each live picture in the multi-view picture set; determining the live picture with the highest current display priority in the multi-view picture set as the optimal view picture;

[0016] A corresponding question frame is constructed for each current question point according to the question sequence number, and an optimal viewing angle picture corresponding to the question sequence number is displayed in the question frame to obtain an initial report form.

[0017] Furthermore, before obtaining the information on rectification of each current problem point filled in by the expert in the initial report form according to the safety standard to obtain the target report form, the method includes:

[0018] Obtain in advance the safety standards violated by the historical problem points, as well as the historical rectification information of the historical problem points;

[0019] The keyword mapping relationship between the historical keywords of the historical rectification information and the safety standards violated by the historical problem points is learned to obtain a keyword model so as to use the keyword model to prompt the expert with optional safety standards when the expert fills in the information to be rectified.

[0020] Furthermore, the acquisition expert fills in the information to be rectified for each of the current problem points in the initial report form according to the safety standard, and obtains the target report form including:

[0021] When the expert fills in the problem description of the information to be rectified in the initial report form, extracting at least one current keyword from the problem description;

[0022] Using the keyword model to match the current keyword to obtain at least one first candidate standard; and / or using the current keyword to match the security standard to obtain at least one second candidate standard;

[0023] Displaying the at least one first candidate standard and / or the at least one second candidate standard, so that the expert can refer to the at least one first candidate standard and / or the at least one second candidate standard, fill in the information to be rectified, and obtain an intermediate report form;

[0024] According to the information to be rectified and the multi-view picture set, other on-site pictures are selectively added to the intermediate report form, or other on-site pictures are not added to the intermediate report form to obtain a target report form.

[0025] Further, the selectively adding other on-site pictures to the intermediate report form, or not adding other on-site pictures to the intermediate report form, to obtain a target report form includes:

[0026] When the expert has completed filling in the information to be rectified, determining the height of the text box occupied by the information to be rectified in the intermediate report form;

[0027] When the height of the text box is less than or equal to the picture height occupied by the optimal viewing angle picture, no other on-site pictures are added to the intermediate report form to obtain a corresponding target report form;

[0028] When the height of the text box is greater than the picture height occupied by the optimal viewing angle picture, add a corresponding number of other on-site pictures to the intermediate report form according to the current display priority, and ensure that the height of the text box is greater than or equal to the picture height of all on-site pictures in the target report form to obtain the corresponding target report form.

[0029] Furthermore, the acquisition expert fills in the information to be rectified for each of the current problem points in the initial report form according to the safety standard, and obtains the target report form including:

[0030] When the expert completes filling in the information to be rectified of the current problem point in the initial report form, an intermediate report form is generated; wherein the intermediate report form includes a problem grid of the at least one current problem point, each of the problem grids includes a corresponding picture grid, and the picture grid is used to display the on-site picture added to the intermediate report form;

[0031] When the expert clicks on any on-site picture in the picture frame of the current problem point in the intermediate report form, a shadow interface pops up and is displayed in the form of an interface covering the intermediate report form; an optional picture window and a magnified window are displayed on the shadow interface;

[0032] Acquire a multi-view picture set corresponding to the scene picture clicked in the picture frame; display all the scene pictures in the multi-view picture set in the optional picture window; when the expert clicks on any scene picture in the optional picture window, display the corresponding scene picture in an enlarged form in the enlarged window;

[0033] When the expert selects any on-site picture in the optional picture window, the expert returns to the interface of the intermediate report form from the shadow interface, obtains the on-site picture selected in the optional picture window, and replaces the on-site picture clicked in the picture frame with the obtained on-site picture; and / or, when the expert selects any on-site picture in the optional picture window and drags it out of the range of the optional picture window, the expert returns to the interface of the intermediate report form from the shadow interface, obtains the dragged on-site picture, and adds the obtained on-site picture to the picture frame;

[0034] According to the height of the text frame occupied by the information to be rectified, the picture frame is adaptively adjusted to obtain a corresponding target report form.

[0035] Furthermore, the picture frame is adaptively adjusted according to the height of the text frame occupied by the information to be rectified, and the corresponding target report form is obtained, including:

[0036] Determine the height of the text box occupied by the information to be rectified in the intermediate report form;

[0037] According to the order of the on-site pictures in the intermediate report form, determining at least one on-site picture that can be accommodated by the height of the text box;

[0038] In the picture frame, only the at least one live picture that can be accommodated is displayed.

[0039] In a second aspect, the present invention further provides a steel enterprise safety management system improvement device, which is used to implement the steel enterprise safety management system improvement method described in the first aspect, and the steel enterprise safety management system improvement device comprises:

[0040] At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the processor to execute the method for improving the safety management system of a steel enterprise as described in the first aspect.

[0041] In a third aspect, the present invention further provides a non-volatile computer storage medium, wherein the computer storage medium stores computer executable instructions, which are executed by one or more processors to complete the method for improving the safety management system of a steel enterprise described in the first aspect.

[0042] In a fourth aspect, a chip is provided, comprising: a processor and an interface, for calling and running a computer program stored in a memory to execute the method for improving the safety management system of a steel enterprise as in the first aspect.

[0043] In a fifth aspect, a computer program product comprising instructions is provided, which, when executed on a computer or a processor, enables the computer or the processor to execute the method for improving the safety management system of a steel enterprise as described in the first to fourth aspects and any one of the aspects.

[0044] In the sixth aspect, a steel enterprise safety management system improvement system is provided, comprising a steel enterprise safety management system improvement device as in the second aspect, and using the steel enterprise safety management system improvement method as described in the first aspect to complete the interaction of the steel enterprise safety management system improvement device of the second aspect.

[0045] Different from the prior art, the present invention has at least the following beneficial effects:

[0046] The present invention organizes experts to determine at least one current problem point on site in advance according to safety standards, collects a multi-perspective picture set for each current problem point; generates an initial report form based on the optimal perspective picture in the multi-perspective picture set; obtains the information to be rectified for each current problem point filled in by experts in the initial report form according to the safety standards, and obtains a target report form. Based on the on-site investigation by experts, the present invention utilizes the method of collecting a multi-perspective picture set and generating an initial report form according to the optimal perspective picture to assist experts as much as possible to fill in the information to be rectified according to safety standards without omission, efficiently and with high quality, and generates an easy-to-read target report form, thereby enabling relevant personnel to grasp the hidden danger investigation situation through the report form, quickly understand the current problem point, and facilitate the subsequent rectification of the current problem point according to the target report form, so as to improve the efficiency of safety management, ensure the effect of accident prevention and control, and improve the safety management efficiency of steel enterprises by combining the safety management experience of experts. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments of the present invention. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0048] Figure 1 It is a flow chart of a method for improving a safety management system of a steel enterprise provided by an embodiment of the present invention;

[0049] Figure 2 is a schematic diagram of an initial report form provided by an embodiment of the present invention;

[0050] Figure 3 is a flow chart of step 10 provided in an embodiment of the present invention;

[0051] Figure 4 is another flowchart of step 10 provided in an embodiment of the present invention;

[0052] Figure 5 It is a schematic diagram of a column of information to be rectified in an initial report form provided by an embodiment of the present invention;

[0053] Figure 6 is a flowchart of the first step 20 provided in an embodiment of the present invention;

[0054] Figure 7 is a flow chart of the second step 20 provided in an embodiment of the present invention;

[0055] Figure 8 is a schematic diagram of a first intermediate report form provided by an embodiment of the present invention;

[0056] Fig. 9 is a schematic diagram of a page of an intermediate report form provided by an embodiment of the present invention;

[0057] Fig.10 is a schematic diagram of the next page of an intermediate report form provided by an embodiment of the present invention;

[0058] Fig.11 is a flow chart of step 204b provided in an embodiment of the present invention;

[0059] Fig.12 is a flowchart of the third step 20 provided in an embodiment of the present invention;

[0060] Fig.13 is a schematic diagram of a second intermediate report form provided by an embodiment of the present invention;

[0061] Fig.14 is a schematic diagram of a live picture displayed in a form of covering the current interface provided by an embodiment of the present invention;

[0062] Fig.15 is a schematic diagram of a third intermediate report form provided by an embodiment of the present invention;

[0063] Fig.16 is a schematic diagram of a fourth intermediate report form provided by an embodiment of the present invention;

[0064] Fig.17 is a flow chart of step 205c provided in an embodiment of the present invention;

[0065] Fig.18 is a schematic diagram of a fifth intermediate report form provided by an embodiment of the present invention;

[0066] Fig.19 is a schematic diagram of a target report form provided by an embodiment of the present invention;

[0067] Fig. 20 It is a schematic diagram of expanding a problem frame of a current problem point 1 in a target report form provided by an embodiment of the present invention;

[0068] Fig.21 is a schematic diagram of a third method for improving a safety management system of a steel enterprise provided by an embodiment of the present invention;

[0069] Fig. 22 It is a schematic diagram of the architecture of a steel enterprise safety management system improvement device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0070] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0071] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0072] Unless the context requires otherwise, throughout the specification and claims, the term "including" is to be interpreted as open inclusion, that is, "including, but not limited to". In the description of the specification, the terms "one embodiment", "some embodiments", "exemplary embodiments", "examples", "specific examples" or "some examples" and the like are intended to indicate that specific features, structures, materials or characteristics associated with the embodiment or example are included in at least one embodiment or example of the present disclosure. The schematic representation of the above terms does not necessarily refer to the same embodiment or example. In addition, the specific features, structures, materials or characteristics may be included in any one or more embodiments or examples in any appropriate manner, that is, although they may be carried in the embodiments or examples of the above terms due to reasons such as the order and position of appearance, it is not limited to that they can be carried in combination by one embodiment or example.

[0073] In the description of the present invention, it is necessary to understand that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present disclosure and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present disclosure.

[0074] In the description of the present invention, the terms "first" and "second" are used only for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of the present disclosure, unless otherwise specified, the meaning of "multiple" is two or more. In addition, for example, the same type of nouns may be described as two independent individuals by adding "A" and "B" at the end. In this case, the corresponding features defined as "A" and "B" are only used to distinguish the same type of individuals for description purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features.

[0075] When describing some embodiments, the expressions "coupling", "coupling" and "connection" and their derivatives may be used. For example, when describing some embodiments, the term "connection" may be used to indicate that two or more components are in direct physical or electrical contact with each other. For another example, when describing some embodiments, the term "coupling" may be used to indicate that two or more components are in direct physical or electrical contact. However, the terms "connection" or "coupling" may also refer to two or more components that are not in direct contact with each other, but still cooperate or interact with each other, such as "optical path coupling", "wireless connection", etc. The embodiments disclosed herein are not necessarily limited to the contents of the present invention.

[0076] In the description of the present invention, the expression "A and / or B" (where A and B are used to formally represent specific characteristic contents) will be involved, and the corresponding expressions include the following three combinations: only A, only B, and a combination of A and B.

[0077] As used herein, "about," "substantially," or "approximately" includes the stated value and an average value that is within an acceptable range of deviation from the particular value as determined by one of ordinary skill in the art taking into account the measurements in question and the errors associated with the measurement of the particular quantity (i.e., the limitations of the measurement system).

[0078] Embodiment 1:

[0079] In order to solve the above problems, Figure 1 As shown, an embodiment of the present invention provides a method for improving the safety management system of a steel enterprise, organizing experts to determine at least one current problem point on site in advance according to safety standards, and collecting a multi-view picture set of each current problem point; then for the at least one current problem point, the method for improving the safety management system of a steel enterprise includes:

[0080] Step 10: Generate an initial report table based on the optimal viewing angle picture in the multi-view picture set.

[0081] Based on the many years of safety management experience of regulatory authorities and steel enterprises, the embodiment of the present invention has established a comprehensive team of safety experts in the fields of metallurgical safety technology, production safety standardization management and intelligence; among them, the fields involved in metallurgical safety technology include sintering, coking, ironmaking, steelmaking, rolling, oxygen production and gas, etc.

[0082] The method for improving the safety management system of a steel enterprise according to an embodiment of the present invention provides a systematic and scientific safety management solution. First, a team of safety experts goes to the site where the safety management project is required, and the experts conduct on-site inspections of safety hazards in accordance with safety standards and combined with their own experience, and determine the current problem points that actually exist on site. Among them, safety standards include laws and regulations, technical standards, normative documents, and enterprise safety management standards. For example, the current problem point is that the inlet and outlet of the cooling water of the vacuum medium frequency furnace are not equipped with a flow difference alarm device; the safety standard violated by the current problem point is Article 4 of the "Standards for Determining Major Production Safety Accident Hazards in the Industrial and Trade Industry", and the cooling water system of the medium frequency furnace should be equipped with an inlet and outlet water flow detection alarm device.

[0083] When determining the current problem point, experts are also required to collect a set of multi-perspective pictures that can reflect the current problem point based on their experience; for example, take on-site pictures of the cooling water inlet and outlet of the vacuum medium frequency furnace from different perspectives. The multi-perspective picture set includes at least three single-perspective on-site pictures, each with a different perspective; in an optional embodiment, the multi-perspective picture set of each current problem point may include six single-perspective on-site pictures from different angles.

[0084] An embodiment of the present invention also provides a digital safety management platform for the metallurgical industry, which is used to receive a multi-perspective picture set of current problem points at the project site, generate an initial report form for experts to fill in the information to be rectified, and finally obtain a corresponding target report form.

[0085] After collecting the multi-view picture set, the multi-view picture set collected by the experts is stored in the corresponding database of the metallurgical industry digital safety management platform. Since the on-site pictures from different perspectives often have different reflections on the corresponding current problem points, the optimal perspective picture that can best reflect the current problem point in the multi-view picture set is first determined. Figure 2 The figure shows a specific example of an initial report form. The initial report form is constructed according to the problem sequence number of the current problem point, and the optimal viewing angle picture is displayed in the corresponding on-site picture column, so that experts can fill in the information to be rectified with reference to the optimal viewing angle picture.

[0086] Step 20: Obtain the information to be rectified for each current problem point filled in by the expert in the initial report form according to the safety standard, and obtain a target report form, so as to rectify the at least one current problem point according to the target report form.

[0087] Among them, the information to be rectified is the rectification suggestions put forward by experts for each current problem point based on safety standards.

[0088] After generating the initial report form, the method for improving the safety management system of a steel enterprise according to the embodiment of the present invention has the experts fill in the information to be rectified for each current problem point by comparing the on-site pictures and safety standards, so as to finally generate a target report form for the on-site safety hazard investigation of the project, so as to facilitate the relevant project personnel to rectify the current problem points according to the information to be rectified. The information to be rectified includes the problem description, cause analysis and rectification suggestions of the current problem point, and the specific content of the information to be rectified is selected by the technicians in this field according to the specific usage scenario and experience.

[0089] The present invention organizes experts to determine at least one current problem point on site in advance according to safety standards, collects a multi-perspective picture set for each current problem point; generates an initial report form based on the optimal perspective picture in the multi-perspective picture set; obtains the information to be rectified for each current problem point filled in by experts in the initial report form according to the safety standards, and obtains a target report form. Based on the on-site investigation by experts, the present invention utilizes the method of collecting a multi-perspective picture set and generating an initial report form according to the optimal perspective picture to assist experts as much as possible to fill in the information to be rectified according to safety standards without omission, efficiently and with high quality, and generates an easy-to-read target report form, thereby enabling relevant personnel to grasp the hidden danger investigation situation through the report form, quickly understand the current problem point, and facilitate the subsequent rectification of the current problem point according to the target report form, so as to improve the efficiency of safety management, ensure the effect of accident prevention and control, and improve the safety management efficiency of steel enterprises by combining the safety management experience of experts.

[0090] The embodiment of the present invention determines the optimal viewing angle image in combination with the historical report table. To illustrate the process, the following first describes the process of using the digital safety management platform for the metallurgical industry:

[0091] Before storing the multi-view image collection in the database, obtain the historical report table of other projects, the historical image collection of all historical problem points, and the historical display priority of each historical image in the historical image collection. Among them, the historical problem points are found by experts when they investigate the safety hazards on the site of the project, and the corresponding historical image collection is collected during the investigation.

[0092] In an optional embodiment, when storing a historical picture collection (i.e., the first use of the digital safety management platform for the metallurgical industry), the historical display priority of each historical picture is determined by an expert, and different historical display priorities reflect the corresponding historical problem points to varying degrees. For example, for a historical picture collection of a certain historical problem point, the six historical pictures from different perspectives are: Historical Picture 1, Historical Picture 2, Historical Picture 3, Historical Picture 4, Historical Picture 5, and Historical Picture 6; the historical display priority of Historical Picture 1 is fourth, the historical display priority of Historical Picture 2 is first, the historical display priority of Historical Picture 3 is third, the historical display priority of Historical Picture 4 is second, the historical display priority of Historical Picture 5 is fifth, and the historical display priority of Historical Picture 6 is sixth. The historical report form is ultimately generated by the expert after conducting a safety hazard inspection on the project site based on the historical picture collection, etc.

[0093] Before storing the multi-view image collection in the database, Figure 3 As shown, before step 10, the following steps are included:

[0094] Step 101a: pre-acquire a set of historical pictures of historical problem points; wherein the set of historical pictures includes at least three historical pictures with different viewing angles.

[0095] Step 102a: learning the priority mapping relationship between the historical display priority of the historical picture and the historical problem point, and obtaining a priority model, so as to use the priority model to determine the optimal viewing angle picture.

[0096] In an optional embodiment, since historical pictures from different perspectives in a historical picture collection often reflect historical problem points to different degrees, after the experts determine the corresponding historical display priorities, the embodiment of the present invention uses image recognition algorithms such as target detection to construct an untrained priority model, and uses historical problem points, historical picture collections of historical problem points, and historical display priorities corresponding to historical picture collections as input training samples to train the untrained priority model. During the training process, the priority mapping relationship between the historical display priorities determined by experts and the historical problem points is learned to obtain a trained priority model.

[0097] In order to explain the process of determining the optimal viewing angle image, Figure 4 As shown, the step 10 includes:

[0098] Step 101b: Determine the problem sequence number of the at least one current problem point; store the multi-perspective picture set of the at least one current problem point respectively according to the corresponding problem sequence number; wherein the multi-perspective picture set includes at least three on-site pictures from different perspectives.

[0099] In an optional embodiment, the multi-view image set can be stored in the database of the metallurgical industry digital security management platform; Figure 2 As shown, when storing, the problem numbers can be arranged in the storage order, and when the corresponding pictures are used later, the current problem points can be determined according to the naming rules of the problem numbers. The multi-view picture set of each current problem point can include 6 on-site pictures from different perspectives.

[0100] Step 102b: using the priority model, determining the current display priority of each live picture in the multi-view picture set; determining the live picture with the highest current display priority in the multi-view picture set as the optimal view picture.

[0101] The current problem point and the multi-view picture set of the current problem point are input into the trained priority model to obtain the current display priority of each scene picture in the multi-view picture set; for example, for scene picture 1, scene picture 2, scene picture 3, scene picture 4, scene picture 5 and scene picture 6 in the multi-view picture set, when the current display priority of scene picture 2 is the first, scene picture 2 is used as the optimal view picture of the current problem point.

[0102] Step 103b: construct a corresponding question frame for each current question point according to the question sequence number, display the optimal viewing angle image corresponding to the question sequence number in the question frame, and obtain an initial report form.

[0103] like Figure 2 As shown in the figure, the problem grids are constructed for the current problem points with problem numbers 1, 2 and 3, and each problem grid includes a problem number column, a column for information to be rectified and a column for on-site pictures. Each problem number is displayed in the problem number column of the corresponding problem grid, and the optimal perspective picture of each current problem point is displayed in the on-site picture column of the corresponding problem grid to obtain an initial report form, so that when experts fill in the information to be rectified in the column for information to be rectified, they can refer to the optimal perspective picture to fill in; on the one hand, as long as the current problem points for which on-site pictures have been collected will be presented in the initial report form to avoid missing the current problem points; on the other hand, the optimal perspective picture helps experts quickly recall the specific on-site conditions of the corresponding current problem points.

[0104] Furthermore, after the multi-view image collection is stored, in order to facilitate experts to fill in the information to be rectified, such as Figure 5As shown, when the expert fills in the information to be rectified, the embodiment of the present invention will prompt the expert with the safety standards that may be applicable to the current problem point by displaying it in the information column to be rectified; on the one hand, it can remind the expert to fill in the relevant safety standards violated by the current problem point to avoid the current problem point with irregular and incomplete safety standards in the target report form; on the other hand, it provides the expert with the safety standards that may be applicable, so that the expert does not need to remember all the relevant safety standards or consult the materials, and can select and fill them in completely and accurately, thereby improving the efficiency and convenience of the expert's filling. For example, when the expert fills in the problem description part of the information to be rectified, since the problem description contains current keywords such as "cooling water system of the up-drawing continuous casting machine", the safety standards that may be applicable are matched and displayed for it, such as "Article 7 of the "Standards for Determining Major Production Safety Accident Hazards in the Industry and Trade Industry" (2017 Edition of the Nonferrous Industry Section), the cooling water system of the up-drawing continuous casting machine should be equipped with an inlet and outlet water flow difference detection and alarm device"; in an optional embodiment, all possible applicable safety standards are displayed. If the expert determines that any of the regulations is applicable to the current problem point, the expert can directly refer to the regulations to fill in the information to be rectified without having to look up the relevant safety standards.

[0105] In order to implement the above process, the embodiment of the present invention refers to the historical report table and determines the current keyword from the problem description of the current problem point, such as Figure 6 As shown, before step 20, the following steps are included:

[0106] Step 201a: pre-acquire the safety standards violated by the historical problem points and the historical rectification information of the historical problem points.

[0107] When the digital safety management platform for the metallurgical industry is used for the first time, the safety standards violated by historical problem points are determined by experts based on their own experience; in an optional embodiment, the content contained in the historical rectification information (for example, problem description) can be consistent with the rectification information to be filled in for the current problem point.

[0108] Step 202a: Learn the keyword mapping relationship between the historical keywords of the historical rectification information and the safety standards violated by the historical problem points, and obtain a keyword model so as to use the keyword model to prompt the expert with optional safety standards when the expert fills in the information to be rectified.

[0109] In an optional embodiment, a natural language processing model can be used to construct an untrained keyword model, and historical problem points, historical keywords, and security standards violated by historical problem points are used as input training samples to train the untrained keyword model. During the training process, the keyword mapping relationship between historical keywords determined by experts and corresponding security standards is learned to obtain a trained keyword model.

[0110] To illustrate the process of generating a target report form, Figure 7 As shown, the step 20 includes:

[0111] Step 201b: When the expert fills in the problem description of the information to be rectified in the initial report form, at least one current keyword is extracted from the problem description.

[0112] In an optional embodiment, a named entity recognition algorithm in natural language processing may be used to extract at least one current keyword from the sentence in the problem description.

[0113] For each current problem point, since the experts usually fill in the problem description first when filling in the corresponding information to be rectified, when the experts start to fill in the problem description, the embodiment of the present invention immediately obtains the already filled in problem description content and extracts the current keywords from it. Figure 8 As shown, when the expert has filled in the “Problem description: cooling water inlet of vacuum medium frequency furnace”, the current keyword “cooling water of medium frequency furnace” can be extracted from it.

[0114] Step 202b: Use the keyword model to match the current keyword to obtain at least one first candidate standard; and / or use the current keyword to match the security standard to obtain at least one second candidate standard.

[0115] Among them, the first alternative standard and the second alternative standard are both security standards that may be applicable to the current keyword.

[0116] The embodiments of the present invention utilize a keyword model for fuzzy matching to determine safety standards that may be applicable. Specifically, there are the following methods: (1) Use the keyword model to match the current keyword to determine at least one first candidate standard. (2) Use the current keyword to match the safety standard to determine at least one second candidate standard. (3) Determine the safety standard that may be applicable by combining the first candidate standard and the second candidate standard. Among them, when using the keyword model to match the current keyword, the current problem point can be input into the trained keyword model to obtain the current keyword of the current problem point and the safety standard that is violated. In an optional embodiment, the corresponding category of safety standards can be obtained by matching from the database of hidden danger investigation and control standard clauses of the digital safety management platform for the metallurgical industry according to the type of the current keyword.

[0117] In the database, since the original statement of the safety standard is very likely to not contain the current keyword, it is likely to only involve words with similar meanings or equivalent substitutes. Directly using the current keyword to match the corresponding safety standard in the database may not find a matching result. In order to solve this problem, the embodiment of the present invention also combines historical problem points and historical keywords, etc., uses a keyword model in a computer big data learning manner, and matches based on keyword mapping relationships; and combines the two methods of directly matching safety standards and using keyword models to provide experts with as many possible applicable safety standards as possible, avoiding the need for experts to remember or search for safety standards on their own, and improving filling efficiency.

[0118] Step 203b: Display the at least one first alternative standard and / or the at least one second alternative standard, so that the expert can refer to the at least one first alternative standard and / or the at least one second alternative standard, fill in the information to be rectified, and obtain an intermediate report form.

[0119] It should be noted that at least one first alternative standard and / or at least one second alternative standard are merely possibly applicable safety standards automatically generated by the embodiments of the present invention, and only serve as an auxiliary for experts to fill in the information to be rectified. Experts may also fill in safety standards other than the alternative standards based on their own experience.

[0120] In the embodiment of the present invention, the expert is prompted with the possible applicable safety standards, and the expert fills in the problem description, cause analysis and rectification suggestions with reference to the corresponding prompts, which greatly improves the convenience of filling in the information to be rectified, and enables the expert to directly fill in the information to be rectified with reference to the prompts, thus avoiding the situation where the safety standards are filled in irregularly and incompletely as much as possible. Figure 8 As shown, after the expert fills in the information to be rectified, an intermediate report form is obtained; each problem box in the intermediate report form includes: problem number, information to be rectified and optimal viewing angle picture.

[0121] Step 204b: Based on the information to be rectified and the multi-view picture set, other on-site pictures are selectively added to the intermediate report form, or other on-site pictures are not added to the intermediate report form to obtain a target report form.

[0122] When experts fill in the information to be rectified, the height of the text box occupied by the information to be rectified in the information to be rectified column will increase with the increase in the amount of text filled in, and the height of the on-site pictures (i.e., the optimal viewing angle pictures) in the on-site pictures column will also remain consistent with the corresponding text box height; therefore, in the intermediate report form, there will often be a large number of areas without pictures in the on-site pictures column.

[0123] When the information to be rectified exceeds a whole page, the corresponding optimal viewing angle image will only be displayed on one page, for example, Fig. 9 As shown, the optimal viewing angle image a of the current problem point a is displayed on a certain page of the middle report table, such as Fig.10 As shown, in the corresponding next page, only the column for comments to be rectified has text content, while the column for on-site pictures is empty. If it is directly used as a target report form, when relevant personnel read the current problem point a in the target report form, they need to flip back and forth between the two pages to compare the optimal viewing angle picture a with the information to be rectified. In this case, it is very inconvenient to view the information to be rectified, and it is easy to cause negligence or mistakes by relevant personnel.

[0124] In order to solve this problem, after the expert fills in the information to be rectified, the embodiment of the present invention will also adaptively and automatically add pictures in the multi-view picture set to the on-site picture column. The specific process is as follows:

[0125] like Fig.11 As shown, step 204b includes:

[0126] Step 2041: When the expert has completed filling in the information to be rectified, the height of the text box occupied by the information to be rectified in the intermediate report form is determined.

[0127] Since each current problem point corresponds to only one on-site picture (i.e., the best viewing angle picture), the height of the text in the information column to be rectified can be selected as the text box height. Fig.10 As shown, the height of the text box occupied by the information to be rectified at the current problem point a+1 is x.

[0128] Step 2042: When the height of the text box is less than or equal to the picture height occupied by the optimal viewing angle picture, no other on-site pictures are added to the intermediate report form to obtain the corresponding target report form.

[0129] Among them, other on-site pictures refer to: on-site pictures other than the best-viewing-angle pictures in the multi-viewing-angle picture set of the current problem point.

[0130] For example, Fig.10 As shown, the image height occupied by the optimal viewing angle image a+1 of the current problem point a+1 is y; since x and y are equal, there is no need to add the on-site image to the on-site image column of the current problem point a+1, and the content and format of the problem frame can be directly used as the problem frame of the current problem point a+1 in the target report form.

[0131] Step 2043: When the height of the text box is greater than the picture height occupied by the optimal viewing angle picture, add a corresponding number of other on-site pictures to the intermediate report form according to the current display priority, and ensure that the height of the text box is greater than or equal to the picture height of all on-site pictures in the target report form to obtain the corresponding target report form.

[0132] For example, Fig. 9 and Fig.10 As shown, the text box height of the current problem point a is obviously greater than the picture height occupied by the optimal viewing angle picture a, so it is necessary to add live pictures to the live picture column of the current problem point a. The multi-view picture set of the current problem point a includes live picture 1, live picture 2, live picture 3, live picture 4, live picture 5 and live picture 6. When live picture 2 is the optimal viewing angle picture a, first obtain the current display priority of the remaining live pictures, specifically: the live display priority of live picture 1 is the fourth, the live display priority of live picture 3 is the third, the live display priority of live picture 4 is the second, the live display priority of live picture 5 is the fifth, and the live display priority of live picture 6 is the sixth; so the order of adding live pictures to the live picture column is: live picture 4, live picture 3, live picture 1, live picture 5 and live picture 6.

[0133] According to the order of addition, the number of the above scene pictures that can be accommodated in sequence by the height of the text box is calculated, and the scene pictures other than the optimal viewing angle picture a are added to the scene picture column. For example, the height 1 occupied by the optimal viewing angle picture a and scene picture 4 is calculated, the height 2 occupied by the optimal viewing angle picture a, scene picture 4 and scene picture 3 is calculated, the height 3 occupied by the optimal viewing angle picture a, scene picture 4, scene picture 3 and scene picture 1 is calculated, the height 4 occupied by the optimal viewing angle picture a, scene picture 4, scene picture 3, scene picture 1 and scene picture 5 is calculated, and the height 5 occupied by the optimal viewing angle picture a, scene picture 4, scene picture 3, scene picture 1, scene picture 5 and scene picture 6 is calculated; from height 1 to height 5, multiple scene pictures that are less than or equal to the text box height and closest to the text box height are determined, for example, when height 3 is less than or equal to the text box height, and height 4 is greater than the text box height, it is determined to display the optimal viewing angle picture a, scene picture 4, scene picture 3 and scene picture 1 in the scene picture column, so scene picture 4, scene picture 3 and scene picture 1 are added to the scene picture column. After adding, the corresponding target report table is obtained. Since the on-site pictures in the embodiment of the present invention are often of the same size, the number of on-site pictures that can be accommodated by the text box height can also be obtained by directly dividing the text box height by the height of the on-site picture.

[0134] The embodiment of the present invention adaptively adjusts the number of on-site pictures in the intermediate report form according to the height of the text frame, so that the area occupied by the content in the information column to be rectified and the on-site picture column in the target report form remains close, avoiding the need to flip back and forth between the two pages to compare and read the on-site pictures of the current problem points and the information to be rectified, thereby improving the efficiency of relevant personnel in reading the target report form and facilitating relevant personnel to grasp the current problem points.

[0135] In the process of obtaining the target report form, the embodiment of the present invention also provides a solution for the expert to actively adjust the scene picture, such as Fig.12 As shown, the step 20 includes:

[0136] Step 201c: When the expert has completed filling in the information to be rectified for the current problem point in the initial report form, an intermediate report form is generated; wherein the intermediate report form includes a problem frame for the at least one current problem point, each of the problem frames includes a corresponding picture frame, and the picture frame is used to display the on-site picture added to the intermediate report form.

[0137] It should be noted that the embodiment of the present invention can follow the steps above and adaptively and automatically add on-site pictures in the multi-perspective picture set to the on-site picture column when the expert fills in the information to be rectified; at the same time, the expert can also actively select on-site pictures to be displayed in the on-site picture column based on experience at any time point before obtaining the target report form; among them, since the optimal perspective picture is automatically generated by the embodiment of the present invention based on the historical report form, when the expert selects the on-site picture to be displayed in the on-site picture column, it is not necessary to select the corresponding optimal perspective picture, so the on-site picture column does not necessarily contain the optimal perspective picture of the current problem point.

[0138] like Fig.13 The shown example is a specific example of an intermediate report form, where the picture frame is the range used by the on-site picture in the on-site picture column. For example, the picture frame of the current problem point 1 is the range occupied by the on-site picture 1-1, the picture frame of the current problem point 2 is the range occupied by the on-site picture 2-1, and the picture frame of the current problem point 3 is the range occupied by the on-site picture 3-1.

[0139] Step 202c: When the expert clicks on any on-site picture in the picture frame of the current problem point in the intermediate report form, a shadow interface pops up and is displayed in the form of an interface covering the intermediate report form; an optional picture window and a magnified window are displayed on the shadow interface.

[0140] For example, when the expert clicks on the scene picture 1-1 in the intermediate report form, Fig.14As shown, the interface of the intermediate report table jumps to the shadow interface through the scene picture 1-1. The optional picture window on the shadow interface is used to display all the scene pictures in the multi-perspective picture set of the current problem point 1 to which the scene picture 1-1 belongs (i.e., scene picture 1-1 to scene picture 1-6). The enlarged window on the shadow interface is used to display an enlarged version of a scene picture in the multi-perspective picture set.

[0141] Step 203c: Obtain a multi-perspective picture set corresponding to the live picture clicked in the picture frame; display all live pictures in the multi-perspective picture set in the optional picture window; when the expert clicks on any live picture in the optional picture window, display the corresponding live picture in an enlarged form in the enlarged window.

[0142] In order to display the corresponding live pictures in the optional picture window and the enlarged window, first obtain all the live pictures in the multi-perspective picture set corresponding to the live picture 1-1; in an optional embodiment, the thumbnails of the acquired live pictures are displayed in the optional picture window in an up and down sliding manner, and the only live pictures visible on the current interface are Live Picture 1-1, Live Picture 1-2 and Live Picture 1-3. When the expert clicks the scroll bar on the right side of the optional picture window and drags it down to the bottom, the visible live pictures are Live Picture 1-4, Live Picture 1-5 and Live Picture 1-6.

[0143] When the expert does not click on any live picture in the optional picture window, the first live picture in the multi-perspective picture set can be displayed in the enlarged window by default; when the expert clicks on live picture 1-2 in the optional picture window, the live picture 1-2 will be displayed in the enlarged window in an enlarged form.

[0144] Step 204c: When the expert selects any on-site picture in the optional picture window, the expert returns to the interface of the intermediate report form from the shadow interface, obtains the on-site picture selected in the optional picture window, and replaces the on-site picture clicked in the picture frame with the obtained on-site picture; and / or, when the expert selects any on-site picture in the optional picture window and drags it out of the range of the optional picture window, the expert returns to the interface of the intermediate report form from the shadow interface, obtains the dragged on-site picture, and adds the obtained on-site picture to the picture frame.

[0145] In an optional embodiment, when the expert needs to replace the on-site picture in the picture frame, he can select the on-site picture by double-clicking a certain on-site picture in the optional picture window. For example, since the expert jumps to the shadow interface through the on-site picture 1-1, when the expert needs to replace the on-site picture 1-1, he can select the on-site picture 1-3 used to replace the on-site picture 1-1 by double-clicking in the optional picture window, and then the shadow interface of the embodiment of the present invention disappears, and returns to the interface of the intermediate report form, and at the same time obtains the on-site picture 1-1 (or obtains the index of the on-site picture 1-1, etc.), and then uses the on-site picture 1-3 to replace the on-site picture 1-1 in the intermediate report form, and adaptively adjusts the height of the picture frame of the current problem point 1 to fully display the on-site picture 1-3 in the intermediate report form. The replaced intermediate report form is as follows: Fig.15 shown.

[0146] In an optional embodiment, when the expert needs to add other on-site pictures in the optional picture window to the picture grid, the expert can click on a certain on-site picture in the optional picture window and drag it outside the range in the optional picture window to select the on-site picture and add it to the corresponding picture grid; wherein other on-site pictures refer to on-site pictures other than those already displayed in the picture grid. For example, since the expert jumps to the shadow interface through the on-site picture 1-1, when the expert needs to add the on-site picture 1-2 to the picture grid where the on-site picture 1-1 is located, the expert can click on the on-site picture 1-2 in the optional picture window and drag it outside the range in the optional picture window, then the shadow interface of the embodiment of the present invention disappears, and the expert returns to the interface of the intermediate report table, and at the same time obtains the on-site picture 1-2 (or obtains the index of the on-site picture 1-2, etc.), and then adds the on-site picture 1-2 to the picture grid after the on-site picture 1-1, and adaptively adjusts the height of the picture grid of the current problem point 1 to fully display the on-site picture 1-2 in the intermediate report table, and the intermediate report table after addition is as shown in FIG. Fig.16 shown.

[0147] Step 205c: Adaptively adjust the picture frame according to the text frame height occupied by the information to be rectified to obtain a corresponding target report form.

[0148] Specifically, in order to explain the process of adjusting the picture frame, as shown in FIG. Fig.17 As shown, step 205c includes:

[0149] Step 2051: Determine the height of the text box occupied by the information to be rectified in the intermediate report form.

[0150] Step 2052: According to the order of the on-site pictures in the intermediate report form, determine at least one on-site picture that can be accommodated by the height of the text box.

[0151] like Fig.18 The figure shows a specific example of an intermediate report form after the expert adds or replaces the on-site pictures. The order of the on-site pictures in the intermediate report form is: on-site picture 1-1, on-site picture 1-2 and on-site picture 1-3. Since the order is specified by the expert, there is no need to refer to the current display priority of each on-site picture, and only the order currently displayed in the picture grid is obtained; the embodiment of the present invention needs to calculate the picture grid height adapted to the text frame height according to the text frame height and the order in which each on-site picture is currently displayed in the picture grid.

[0152] In an optional embodiment, the height m occupied by the scene picture 1-1 is calculated, the height n occupied by the scene picture 1-1 and the scene picture 1-2 is calculated, and the height o occupied by the scene picture 1-1, the scene picture 1-2 and the scene picture 1-3 is calculated; from the height m, the height n and the height o, at least one scene picture that is less than or equal to the text box height and closest to the text box height is determined, for example, when the height m is less than or equal to the text box height, and the height n is greater than the text box height, it is determined to display the scene picture 1-1 in the scene picture column. Since the scene pictures in the embodiments of the present invention are often of the same size, it is also possible to directly obtain the number of scene pictures that can be accommodated by the text box height by dividing the height of the scene picture, and then select a corresponding number of scene pictures in the scene picture column starting from the first picture according to the arrangement order of the scene pictures in the scene picture column as the scene pictures displayed in the scene picture column.

[0153] Step 2053: In the picture frame, only the at least one live picture that can be accommodated is displayed.

[0154] like Fig.19 As shown, the question frame of the current problem point 1 in the target report table is obtained. In the case where the displayed on-site picture is selected and / or adjusted by the expert, in an optional embodiment, a function key can be set within the corresponding question frame range, and the function key can realize one-key expansion of the undisplayed on-site picture. The expanded question frame is as shown in FIG. Fig. 20 As shown; when not expanded, the function key displays a plus sign; after expansion, the function key displays a minus sign;

[0155] The target report form of the embodiment of the present invention refers to an electronic form, and in actual use, it is often necessary to print it as a paper form; in an optional embodiment, the plus sign of the function key is also displayed in the paper form, thereby improving the convenience of relevant personnel in reading the form. When relevant personnel are flipping through the paper form, they can know from the plus sign at the function key position that not all on-site pictures are displayed here, and then they can use the electronic form to view all on-site pictures of the current problem point.

[0156] In an optional embodiment, since there may be a situation where the text box height of some information columns to be rectified is smaller than the height of any on-site picture; at this time, the embodiment of the present invention can use the target detection model to first extract the features in each on-site picture that best reflect the current problem point, and then use the similarity model and / or classification model, etc. to compare the degree of difference in the reflection of the same current problem point by each on-site picture in the same multi-perspective picture set, so as to determine the longitudinal coordinates of the image area that best reflects the current problem point in the on-site picture to be displayed; and according to the longitudinal coordinates, the on-site picture to be displayed is vertically cropped, so that the cropped on-site picture can adapt to the text box height as much as possible.

[0157] like Fig.21 As shown, the steel enterprise safety management system improvement of the embodiment of the present invention also provides a "1+2+3+N" safety management standard process. Among them, "1" refers to the establishment of a safety expert team. "2" refers to the construction of a digital safety management platform for the metallurgical industry and a digital safety risk management platform for steel enterprises; the digital safety management platform for the metallurgical industry can include a safety regulations and standards resource database, a safety accident case database, an electronic training course and assessment resource database, a hazard analysis example resource database, a hidden danger investigation and treatment standard clause basis database, and a comprehensive safety management system tool / module resource database; the digital safety risk management platform for steel enterprises is mainly based on the national regulatory requirements such as the metallurgical industry's safety production laws and regulations, technical standards, etc., focusing on the entire production process of steel enterprises, with the full process safety production management elements as the main body, to build a safety risk management platform covering safety production information management, key process equipment operation monitoring data, key equipment and key area monitoring, regional safety risk dynamic assessment and early warning, and operator violation monitoring and alarm as the characteristics, providing a kind of intelligent means of safety risk management for steel enterprises. "3" refers to 3 application tools, based on intelligent technology to design safety development index evaluation tools, all-staff safety performance evaluation tools and employee behavior safety evaluation tools. "N" means using the aforementioned three application tools to analyze in N special safety management modules whether the project site meets the requirements of production safety standardization; special safety management modules may include production safety standardization module, stakeholder safety module, team safety standardization module, environmental protection facility safety module, etc.

[0158] Embodiment 2:

[0159] like Fig. 22 , is a schematic diagram of the structure of the steel enterprise safety management system improvement device according to an embodiment of the present invention. The steel enterprise safety management system improvement device according to this embodiment includes one or more processors 21 and a memory 22. Fig. 22 A processor 21 is taken as an example.

[0160] The processor 21 and the memory 22 may be connected via a bus or other means. Fig. 22 The example of connecting through bus is taken in the following.

[0161] The memory 22 is a non-volatile computer-readable storage medium that can be used to store non-volatile software programs and non-volatile computer executable programs, such as the method for improving the safety management system of a steel enterprise in this embodiment. The processor 21 executes the method for improving the safety management system of a steel enterprise by running the non-volatile software programs and instructions stored in the memory 22.

[0162] The memory 22 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage devices. In some embodiments, the memory 22 may optionally include a memory remotely arranged relative to the processor 21, and these remote memories may be connected to the processor 21 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0163] The program instructions / modules are stored in the memory 22, and when executed by the one or more processors 21, the method for improving the safety management system of a steel enterprise in the above embodiment is executed, for example, the method described above is executed. Figure 1 , Figure 3-Figure 4 , Figure 6-Figure 7 , Figure 11-Figure 12 and Fig.17 The steps shown.

[0164] An embodiment of the present invention further provides a non-volatile computer storage medium, wherein the computer storage medium stores computer executable instructions, and the computer executable instructions are executed by one or more processors, such as Fig. 22 A processor 21 can enable the above one or more processors to execute the steel enterprise safety management system improvement method in the specific embodiment of the present invention, for example, to execute the above described Figure 1 , Figure 3-Figure 4 , Figure 6-Figure 7 , Figure 11-Figure 12 and Fig.17 The steps shown can also be implemented Fig. 22 The various modules and units described above; or the method for improving the safety management system of a steel enterprise in a specific embodiment of the present invention, for example, the method described above Figure 1 , Figure 3-Figure 4 , Figure 6-Figure 7 , Figure 11-Figure 12 and Fig.17 The steps shown can also be implemented Fig. 22 The various modules and units described.

[0165] It is worth noting that the information interaction, execution process, etc. between the modules and units within the above-mentioned devices and systems are based on the same concept as the processing method embodiment of the present invention. The specific contents can be found in the description of the method embodiment of the present invention and will not be repeated here.

[0166] A person skilled in the art may understand that all or part of the steps in the various methods of the embodiments may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, and the storage medium may include: a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, etc.

[0167] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for improving the safety management system of a steel enterprise, characterized in that: Organize experts to identify at least one current problem point on site in advance according to safety standards, and collect a collection of multi-view pictures of each current problem point; Then, for the at least one current problem point, the method for improving the safety management system of a steel enterprise includes: Generate an initial report table according to the optimal viewing angle picture in the multi-view picture set; Obtain the information to be rectified for each current problem point filled in by the expert in the initial report form according to the safety standard, and obtain a target report form, so as to rectify the at least one current problem point according to the target report form.

2. The method for improving the safety management system of a steel enterprise according to claim 1, characterized in that: Before generating an initial report table according to the optimal view picture in the multi-view picture set, the method includes: Pre-acquire a set of historical pictures of historical problem points; wherein the set of historical pictures includes at least three historical pictures with different viewing angles; The priority mapping relationship between the historical display priority of the historical picture and the historical problem point is learned to obtain a priority model, so as to use the priority model to determine the optimal viewing angle picture.

3. The method for improving the safety management system of a steel enterprise according to claim 2, characterized in that: The generating an initial report table according to the optimal view picture in the multi-view picture set comprises: Determine the problem sequence number of the at least one current problem point; store the multi-view picture set of the at least one current problem point respectively according to the corresponding problem sequence number; wherein the multi-view picture set includes at least three scene pictures of different perspectives; Using the priority model, determining the current display priority of each live picture in the multi-view picture set; determining the live picture with the highest current display priority in the multi-view picture set as the optimal view picture; A corresponding question frame is constructed for each current question point according to the question sequence number, and an optimal viewing angle picture corresponding to the question sequence number is displayed in the question frame to obtain an initial report form.

4. The method for improving the safety management system of a steel enterprise according to claim 1, characterized in that: Before obtaining the information to be rectified for each current problem point filled in by the expert in the initial report form according to the safety standard to obtain the target report form, the following steps are included: Obtain in advance the safety standards violated by the historical problem points, as well as the historical rectification information of the historical problem points; The keyword mapping relationship between the historical keywords of the historical rectification information and the safety standards violated by the historical problem points is learned to obtain a keyword model so that the keyword model can be used to prompt the expert with optional safety standards when the expert fills in the information to be rectified.

5. The method for improving the safety management system of a steel enterprise according to claim 4, characterized in that: The target report form obtained by obtaining the information to be rectified for each current problem point filled in the initial report form by the expert according to the safety standard includes: When the expert fills in the problem description of the information to be rectified in the initial report form, extracting at least one current keyword from the problem description; Using the keyword model to match the current keyword to obtain at least one first candidate standard; and / or using the current keyword to match the security standard to obtain at least one second candidate standard; Displaying the at least one first candidate standard and / or the at least one second candidate standard, so that the expert can refer to the at least one first candidate standard and / or the at least one second candidate standard, fill in the information to be rectified, and obtain an intermediate report form; According to the information to be rectified and the multi-view picture set, other on-site pictures are selectively added to the intermediate report form, or other on-site pictures are not added to the intermediate report form to obtain a target report form.

6. The method for improving the safety management system of a steel enterprise according to claim 5, characterized in that: The selectively adding other on-site pictures to the intermediate report form, or not adding other on-site pictures to the intermediate report form, to obtain a target report form includes: When the expert has completed filling in the information to be rectified, determining the height of the text box occupied by the information to be rectified in the intermediate report form; When the height of the text box is less than or equal to the picture height occupied by the optimal viewing angle picture, no other on-site pictures are added to the intermediate report form to obtain a corresponding target report form; When the height of the text box is greater than the picture height occupied by the optimal viewing angle picture, add a corresponding number of other on-site pictures to the intermediate report form according to the current display priority, and ensure that the height of the text box is greater than or equal to the picture height of all on-site pictures in the target report form to obtain the corresponding target report form.

7. The method for improving the safety management system of a steel enterprise according to claim 1, characterized in that: The target report form obtained by obtaining the information to be rectified for each current problem point filled in the initial report form by the expert according to the safety standard includes: When the expert completes filling in the information to be rectified of the current problem point in the initial report form, an intermediate report form is generated; wherein the intermediate report form includes a problem grid of the at least one current problem point, each of the problem grids includes a corresponding picture grid, and the picture grid is used to display the on-site picture added to the intermediate report form; When the expert clicks on any on-site picture in the picture frame of the current problem point in the intermediate report form, a shadow interface pops up and is displayed in the form of an interface covering the intermediate report form; an optional picture window and a magnified window are displayed on the shadow interface; Acquire a multi-view picture set corresponding to the scene picture clicked in the picture frame; display all the scene pictures in the multi-view picture set in the optional picture window; when the expert clicks on any scene picture in the optional picture window, display the corresponding scene picture in an enlarged form in the enlarged window; When the expert selects any on-site picture in the optional picture window, the expert returns to the interface of the intermediate report form from the shadow interface, obtains the on-site picture selected in the optional picture window, and replaces the on-site picture clicked in the picture frame with the obtained on-site picture; and / or, when the expert selects any on-site picture in the optional picture window and drags it out of the range of the optional picture window, the expert returns to the interface of the intermediate report form from the shadow interface, obtains the dragged on-site picture, and adds the obtained on-site picture to the picture frame; According to the height of the text frame occupied by the information to be rectified, the picture frame is adaptively adjusted to obtain a corresponding target report form.

8. The method for improving the safety management system of a steel enterprise according to claim 7, characterized in that: According to the height of the text frame occupied by the information to be rectified, the picture frame is adaptively adjusted to obtain the corresponding target report form including: Determine the height of the text box occupied by the information to be rectified in the intermediate report form; According to the order of the on-site pictures in the intermediate report form, determining at least one on-site picture that can be accommodated by the height of the text box; In the picture frame, only the at least one live picture that can be accommodated is displayed.

9. A steel enterprise safety management system lifting device, characterized in that: The device for improving the safety management system of an iron and steel enterprise comprises at least one processor and a memory, wherein the at least one processor and the memory are connected via a data bus, and the memory stores instructions executable by the at least one processor, and after being executed by the processor, the instructions are used to implement the method for improving the safety management system of an iron and steel enterprise as described in any one of claims 1-8.

10. A non-volatile computer storage medium, characterized in that: The computer storage medium stores computer executable instructions, and the computer executable instructions are executed by one or more processors to complete the method for improving the safety management system of a steel enterprise as described in any one of claims 1-8.

Images