Personalized highway operation safety propaganda and education information pushing method based on artificial intelligence

Abstract

The invention discloses a highway operation safety propaganda and education information personalized pushing method based on artificial intelligence, and relates to the field of operation highway safety production management, and the method comprises the steps: obtaining the operation information of a pushing region, and determining the main information of at least one construction unit in the pushing region; acquiring demand information of a plurality of construction individuals according to the main body information of each construction unit; and formulating at least one personalized push information packet according to the main body information of each construction unit and the operation information of the push area in combination with the demand information of the plurality of construction individuals. According to the method, the information of each construction unit and the demand information of the constructors in the pushing area are obtained in advance, the corresponding personalized pushing content is formulated in advance, then the feedback condition of the pushing content of the constructors in the pushing area is continuously collected, the personalized pushing content is optimized, and the pushing efficiency is improved. The push content in the push area is enabled to be matched with the requirements of the construction personnel, and the construction personnel can effectively receive the push content.

Description

Technical Field

[0001] The present invention relates to the field of highway operation safety production management, and in particular to an artificial intelligence-based personalized push method for highway operation safety publicity and education information. Background Art

[0002] In the process of highway operation, production safety is an important guarantee to ensure the safety of personnel and property. Studies have shown that production safety publicity and education is an important means to enhance employees' safety awareness and reduce the incidence of accidents. Through scientific publicity and education, employees can be effectively reminded of the importance of production safety, so that they can maintain a high degree of vigilance in their minds, so that they can consciously abide by safety regulations in actual operations and reduce accidents caused by improper operation or negligence. In addition, safety publicity and education can also help employees identify and deal with potential safety hazards in a timely manner and improve their ability to respond in emergency situations. Therefore, in highway operations, carrying out comprehensive and systematic safety publicity and education is not only a necessary measure to ensure the safety of employees and the public, but also an important foundation for achieving long-term development of the enterprise.

[0003] In recent years, with the rapid development of information technology, the use of modern information technology to carry out safety production publicity and education has become a popular and effective way. Pushing the latest safety information and precautions to employees in real time through text messages, emails, mobile applications, etc. can greatly improve the coverage and timeliness of publicity and education. However, most of the current push content is fixed, lacking personalized and accurate push for employees in different departments, responsibilities and working environments. This "one-size-fits-all" push method may not only cause information fatigue to employees in various positions when facing safety information that is not related to their responsibilities and working environment, and then ignore or even resist these push contents, but also may cause excessive interference to employees' work due to a large amount of information push. Therefore, realizing personalized and accurate push of publicity and education information and ensuring that each employee receives safety information closely related to their actual work has become the key to further improving the effectiveness of safety education. Summary of the invention

[0004] The purpose of the present invention is to solve the shortcoming in the prior art that the pushed content is not highly correlated with the receiving user, and to propose a personalized push method for highway operation safety education information based on artificial intelligence.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions: In a first aspect, the present invention provides a method for personalized push of highway operation safety education information based on artificial intelligence, comprising: Obtaining the operation information of the push area and determining the main information of at least one construction unit in the push area; According to the main information of each construction unit, the demand information of multiple construction individuals is collected; Formulate at least one personalized push information package based on the main information of each construction unit and the operation information of the push area, and in combination with the demand information of multiple construction individuals; Send at least one personalized push information package to the push area for content push, and collect emotional feedback characteristics of construction individuals in the push area in real time to determine content push quality information in the push area; According to the content push quality information of the push area, the existing push content in the push area is adjusted, and the push theme of the construction individuals in the push area is determined.

[0006] In some feasible solutions, the method for formulating at least one personalized push information package includes: Determine push content classification information in the push area according to the job information of the push area; According to the demand information of multiple construction individuals, content push matching is performed with the push content classification information in the push area, and push content matching information of multiple construction individuals is determined respectively; According to the push content matching information of each construction individual, a personalized push information package is formulated according to the push requirements.

[0007] In some feasible solutions, the push content classification information in the push area includes: One or a combination of accident prevention, laws and regulations, emergency response, safety training, and weather warning.

[0008] In some feasible solutions, the method for collecting and pushing emotional feedback characteristics of construction individuals in the area in real time includes: Pre-set the content push sampling range of the push area according to the operation information of the push area; According to the content push sampling range of the push area, micro-motion capture information of multiple construction individuals is collected in real time within the content push sampling range to determine feedback action information of the multiple construction individuals; According to the feedback action information of multiple construction individuals, the emotional feedback characteristics of the construction individuals in the content push sampling range of the push area are determined.

[0009] In some feasible solutions, the method for determining the emotional feedback characteristics of construction individuals in the content push sampling range of the push area includes: Suppose that there is a content push sampling range in the push area If there are individual construction units, then: Formula 1; In formula 1, is the overall sentiment score, ranging from , used to measure employees’ overall sentiment towards push content; is the total number of employees who participated in the feedback; The emotional types of employees are divided into three categories: Employees with positive emotions received a score of 1; Employees with neutral emotions received a score of 0; Employees with negative emotions scored .

[0010] In some feasible solutions, the method for determining feedback action information of multiple construction individuals includes: In the content push sampling range of the push area, image information of multiple continuous time segments is collected; Perform image analysis on the image information of multiple continuous time segments respectively, and determine the action changes of multiple construction individuals in different image information respectively; According to the temporal features in different image information, the action changes of multiple construction individuals in different image information are marked, and the feedback action information of the multiple construction individuals is determined.

[0011] In some feasible solutions, respectively determining the motion changes of multiple construction individuals in different image information includes: According to the time sequence features in the image information of the plurality of continuous time sequence segments, the image information of the first time sequence segment is selected as the original reference image, and the content push position in the original reference image is determined; The content push position in the original reference image is used as a coordinate reference point, and the reference contour coordinates of the heads of multiple construction individuals in the original reference image are determined respectively; According to the time sequence features in the image information of multiple continuous time sequence segments, the head contour coordinates of multiple construction individuals in different image information are extracted in turn to determine the movement changes of the multiple construction individuals in different image information.

[0012] In some feasible solutions, the method for determining the emotional feedback characteristics of construction individuals in the content push sampling range of the push area also includes: Assume that the head contour coordinates of any construction individual exist in the image information of multiple continuous time segments for: , , ,.... are the horizontal coordinates of the head contour of any construction individual in the image information of multiple continuous time series segments; , ,.... are respectively the vertical coordinates of the head contour of any construction individual in the image information of a plurality of continuous time series segments; At this time, the vertical position change of the head contour is used to detect the construction personnel's head raising and lowering movements. Then: Formula 2; In formula 2, is the vertical coordinate of the head contour of the construction individual in the current reference image, is the vertical coordinate of the head outline of the construction individual in the next reference image; Among them, if , it indicates a head-up action, and the construction individual is judged as an employee with positive emotions; like , it means the action of lowering the head, and the construction individual is judged as an employee with negative emotions.

[0013] In some feasible solutions, the push method further includes: According to the coordinate reference point of the content push location, respectively determine the facial region coordinate information of multiple construction individuals in the image information of at least one continuous time sequence segment; According to the facial region coordinate information of multiple construction individuals, the facial feature information of the construction individuals in the image information of each continuous time sequence segment is extracted respectively; According to the facial feature information of the construction individuals in the image information of each continuous time sequence segment, the emotional feedback features of the construction individuals in the content push sampling range of the push area are determined respectively.

[0014] The beneficial effects of the present invention are: The present invention obtains the information of each construction unit and the demand information of the construction personnel in the push area in advance, formulates the corresponding personalized push content in advance, and then continues to collect the push content feedback of the construction personnel in the push area, optimizes the personalized push content, so that the push content in the push area matches the needs of the construction personnel, and enables the construction personnel to effectively receive the push content. That is, it effectively solves the disadvantage of the above-mentioned prior art that the push content is not highly associated with the receiving user. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a schematic diagram of the overall process of a personalized push method for highway operation safety education information based on artificial intelligence provided in an embodiment of the present invention; Figure 2 A partial flow chart of a method for personalized push of highway operation safety education information based on artificial intelligence provided in an embodiment of the present invention; Figure 3A schematic diagram of formulating a personalized push information package for a personalized push method for highway operation safety education information based on artificial intelligence provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0016] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0017] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0018] In the present invention, unless otherwise clearly specified and limited, the terms "connection", "fixation", etc. should be understood in a broad sense. For example, "fixation" can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements, unless otherwise clearly defined. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0019] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present invention, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the meaning of "and / or" appearing in the full text includes three parallel schemes. Taking "A and / or B" as an example, it includes scheme A, or scheme B, or a scheme that satisfies both A and B. In addition, the technical solutions between the various embodiments can be combined with each other, but it must be based on the ability of ordinary technicians in the field to implement. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0020] Reference Figures 1 to 3In order to solve the shortcoming of the above-mentioned prior art that the push content is not highly correlated with the receiving user, the present invention provides a personalized push method for highway operation safety education information based on artificial intelligence. The push method obtains the information of each construction unit and the demand information of the construction personnel in the push area in advance, formulates the corresponding personalized push content in advance, and then continues to collect the push content feedback of the construction personnel in the push area, optimizes the personalized push content, so that the push content in the push area matches the needs of the construction personnel, and enables the construction personnel to effectively receive the push content. That is, it effectively solves the shortcoming of the above-mentioned prior art that the push content is not highly correlated with the receiving user.

[0021] Specifically, the present invention provides a personalized push method for highway operation safety education information based on artificial intelligence, which includes: obtaining operation information in the push area, and determining the main information of at least one construction unit in the push area (such as operation type, personnel type, etc.); then collecting the demand information of multiple construction individuals (i.e., individual employees) according to the main information of each construction unit; here, by building a database of individual construction employees, a comprehensive database including employee personal attributes (such as age, length of service, job responsibilities, etc.) and work conditions (such as attendance records, safety training conditions, etc.) can be established to comprehensively record and manage individual employee information, such as using the data modeling tool Apache Hive to build a data model according to analysis needs, as shown in the following formula:

[0022] in, The data model representing employee i is constructed from multiple dimensions, including personal attributes ( )、Work attributes( ), environmental attributes ( ); specifically, For employees The data model, is the employee's age, Employee length of service, The department where the employee works. For employees' positions and responsibilities, For the personal characteristics of employees (such as hobbies, habits, personality), For employee attendance, Keep records of employee safety training, Recording of employee work events, The weather conditions of the environment where the employees are located. The geographical information of employees, The geological disaster risk situation where the employee is located. That is, the needs of individual construction personnel can be determined according to the type of work, hobby characteristics, work location, etc. of individual employees in the main body of the construction unit. Then, according to the main body information of each construction unit and the operation information of the push area, combined with the demand information of multiple construction individuals, at least one personalized push information package can be formulated (such as the push theme: accident prevention (such as information on how to identify and avoid potential risks), laws and regulations (such as the latest traffic regulations and safety regulations update), emergency handling (such as emergency handling procedures and precautions after an accident), safety training (such as relevant safety training courses and materials), weather warning (such as safety tips under severe weather conditions), etc.). Then, at least one personalized push information package is sent to the push area for content push, and at this time, the emotional feedback characteristics of the construction individuals in the push area are collected in real time to determine the content push quality information of the push area; that is, here, by collecting the feedback actions of each construction individual in the push area on the push content, it is judged whether the content push in the push area fits the needs of the construction individual, so as to determine the content push quality of the push area. Then, according to the content push quality information of the push area, the existing push content in the push area can be adjusted, and then the push theme of the construction individual in the push area can be finally determined. That is, according to the feedback from multiple construction individuals on the push content of the original configuration, the push content of the original configuration can be adjusted to make the push content more relevant to the needs of the construction individuals.

[0023] Reference Figure 3In this embodiment, in order to facilitate understanding of how to pre-formulate a personalized push information package, the following explanation is given here. Specifically, the method for formulating at least one personalized push information package includes: according to the operation information of the push area, the push content classification information in the push area can be determined; that is, according to the work requirements of the push area, the types of different push contents can be pre-configured in advance, and then according to the demand information of multiple construction individuals, the content push is matched with the push content classification information in the push area, and the push content matching information of multiple construction individuals is determined respectively; then, according to the push content matching information of each construction individual, a personalized push information package is formulated according to the push requirements. Here, in order to facilitate understanding of how to determine the push content matching information of multiple construction individuals separately, the following example is given: suppose there are individual construction positions such as road safety managers, dispatchers, electromechanical operation and maintenance personnel, road maintenance personnel, bridge maintenance personnel, toll collectors, and inspectors in the push area. At this time, according to the above-mentioned database of individual construction employees, the content matching degree of the individual construction positions of road safety managers, dispatchers, electromechanical operation and maintenance personnel, road maintenance personnel, bridge maintenance personnel, toll collectors, and inspectors can be allocated in advance (the specific content matching degree value can be adjusted according to the actual situation). Then, according to the push theme, the corresponding content template can be selected, including content structure, format and style, which can help to quickly generate consistent and high-quality push content to meet the needs of different individual construction positions. That is, the needs of construction individuals in the push area are different, so push content with high adaptability to the needs of construction individuals can be configured. That is, the number of cycles of different push content themes can be determined according to the type of construction individual operations in the push area. Figure 3 As shown, taking the push time of road safety guards as an example, the value of 0.5 for accident prevention can be: in the first 1 minute of the overall push content, the accident prevention time accounts for 30 seconds. The value of 0.5 for laws and regulations can be: in the second 1 minute of the overall push content, the laws and regulations time accounts for 30 seconds. The value of 0.4 for emergency handling can be: in the third 1 minute of the overall push content, the emergency handling time accounts for 24 seconds. The value of 0.4 for safety training can be: in the fourth 1 minute of the overall push content, the safety training time accounts for 24 seconds. The value of 0.4 for weather warning can be: in the fifth 1 minute of the overall push content, the weather warning time accounts for 24 seconds. It should be noted that in Figure 3 The content matching degree for different construction individuals can be used as a reference Figure 3 The data in the content can be adjusted for different construction entities (such as different enterprises) according to the individual construction work needs, that is, the push time or push frequency of the push topic can be increased or decreased according to the actual situation of the content push area.

[0024] In this embodiment, in order to facilitate understanding of how to collect the emotional feedback characteristics of the construction individuals in the push area for the pre-set push content, the following description is made here. Specifically, the method for collecting the emotional feedback characteristics of the construction individuals in the push area in real time includes: presetting the content push sampling range of the push area according to the operation information of the push area; then collecting the micro-motion capture information (such as raising the head, lowering the head, etc.) of multiple construction individuals in the content push sampling range in real time according to the content push sampling range of the push area, and determining the feedback action information of multiple construction individuals; then determining the emotional feedback characteristics of the construction individuals in the content push sampling range of the push area according to the feedback action information of multiple construction individuals. In this embodiment, in order to facilitate rapid determination of the data information of the construction individuals in the content push sampling range of the push area, face punching can be set in the content push sampling range of the push area, that is, the existence of construction individuals in the content push sampling range of the push area can be known in advance through face punching, and then the employee information and action characteristics of the construction individuals in the content push sampling range of the push area can be quickly matched.

[0025] Specifically, the method for determining the emotional feedback characteristics of construction individuals in the content push sampling range of the push area includes: Suppose that there is a content push sampling range in the push area If there are individual construction units, then: Formula 1; In formula 1, is the overall sentiment score, ranging from , used to measure employees’ overall sentiment towards push content; is the total number of employees who participated in the feedback; The emotional types of employees are divided into three categories: Employees with positive emotions received a score of 1; Employees with neutral emotions received a score of 0; Employees with negative emotions scored .

[0026] That is, the feedback of multiple construction individuals in the content push sampling range of the push area on the pre-defined push content (such as active interest, neutral non-rejection, and negative disinterest) can be used to determine the compatibility of the existing push content with the push of multiple construction individuals in the content push sampling range, and then the existing push content can be adjusted according to the different adaptability.

[0027] In this embodiment, in order to facilitate understanding of how to collect feedback from multiple construction individuals receiving pushed content within the content push sampling range, the following description is given here. The method for determining the feedback action information of multiple construction individuals includes: collecting image information of multiple continuous time segments within the content push sampling range of the push area; that is, collecting image information of multiple continuous times within the content push sampling range (such as collecting multiple continuous content push sampling range images of several seconds), and then performing image analysis on the image information of the multiple continuous time segments, respectively, to determine the action changes of multiple construction individuals in different image information; At the same time, according to the time series features in different image information, the action changes of multiple construction individuals in different image information are marked, and then the feedback action information of multiple construction individuals is determined. It should be noted that in this embodiment, since the position of the construction individual in the push area changes as the work is completed, in order to more quickly mark the identity information of the construction individual in the push area, it may change. Therefore, the identity of the construction individual in the push area can be pre-marked according to the construction individual employee database and face punching in advance.

[0028] More specifically, the step of respectively determining the motion changes of multiple construction individuals in different image information includes: According to the timing features in the image information of multiple continuous time segments, the image information of the first time segment is selected as the original reference image, and the content push position in the original reference image is determined; then the content push position in the original reference image is used as the coordinate reference point, and the reference contour coordinates of the heads of multiple construction individuals in the original reference image are determined respectively; according to the timing features in the image information of multiple continuous time segments, the head contour coordinates of multiple construction individuals in different image information are extracted in turn to determine the movement changes of multiple construction individuals in different image information. Here, in order to facilitate understanding of how to determine the movement changes of construction individuals through the head contour coordinates of multiple construction individuals in different image information, the following example is given. Specifically, the method for determining the emotional feedback characteristics of construction individuals in the content push sampling range of the push area also includes: Assume that the head contour coordinates of any construction individual exist in the image information of multiple continuous time segments for: , , ,.... are the horizontal coordinates of the head contour of any construction individual in the image information of multiple continuous time series segments; , ,.... are respectively the vertical coordinates of the head contour of any construction individual in the image information of a plurality of continuous time series segments; At this time, the vertical position change of the head contour is used to detect the construction personnel's head raising and lowering movements. Then: Formula 2; In formula 2, is the vertical coordinate of the head contour of the construction individual in the current reference image, is the vertical coordinate of the head contour of the construction individual in the next reference image; , it indicates a head-up action, and at this time the construction individual can be judged as an employee with positive emotions; if , it indicates a head-down action. At this time, the construction individual can be judged as an employee with negative emotions. At the same time, if the vertical coordinate change of the construction individual's head contour is "0", it can be judged as neutral and not rejecting.

[0029] In this embodiment, in order to more accurately identify the emotional feedback characteristics of the construction individuals to the pushed content in the push area, the push method further includes: according to the coordinate reference point of the content push position, respectively determining the facial area coordinate information of multiple construction individuals in the image information of at least one continuous time segment; that is, since the content push position in the image information of multiple continuous time segments is unchanged, the coordinate reference point of the content push position constructs a coordinate system for the image information of each continuous time segment, and the facial area coordinate information of multiple construction individuals (such as the eye coordinates, nose bridge coordinates, lip coordinates, etc. of the construction individual) can be respectively extracted, and then the facial feature information of the construction individuals in the image information of each continuous time segment can be respectively extracted according to the facial area coordinate information of the multiple construction individuals; and then finally, according to the facial feature information of the construction individuals in the image information of each continuous time segment, the emotional feedback characteristics of the construction individuals in the content push sampling range of the push area can be respectively determined. Specifically, in order to facilitate understanding of how to extract the facial feature information of the construction individuals according to the facial area coordinate information of multiple construction individuals, gridded area extraction is adopted here with eye coordinates and nose bridge coordinates. Specifically, let the binocular coordinates of any construction individual in the image information of any continuous time sequence be and , the coordinates of the bridge of the nose are , then construct individual facial features for: Formula 3; The facial features of the construction individual are calculated by formula 3 After that, you can set the emotion judgment threshold according to the content push location ,like , then the construction individual is judged as an employee with positive emotions; if , then the construction individual is judged as a neutral and non-rejecting employee; if , then the construction individual is judged as an employee with negative emotions. Among them, the emotion judgment threshold It can be set according to the actual situation. That is, here, by using the coordinate reference point of the content push location, the facial features of the construction individual (that is, the area formed by the eyes and the bridge of the nose) are obtained respectively, and the emotional feedback of the construction individual to the pushed content is judged according to the size of the area formed by the eyes and the bridge of the nose, that is, by knowing the facial orientation area of ​​the construction individual and the content push location, the construction individual's interest in the pushed content is judged. It should be noted that in this embodiment, on the other hand, eye coordinates and lip coordinates can also be used, but this method is limited by the communication errors when the construction individual communicates with people, so the eye coordinates and nose bridge coordinates are used as examples here. In addition, in order to reduce the pressure on image processing, when any point of the eye coordinates, nose bridge coordinates or lip coordinates of any construction individual cannot be obtained, it can be directly determined that the construction individual is an employee with negative emotions.

[0030] In the second aspect, the present invention also provides a personalized push system for highway operation safety education information based on artificial intelligence, which adopts a personalized push method for highway operation safety education information based on artificial intelligence as described in any one of the first aspects, and the push system also includes: an image acquisition module, an image marking module, and an image analysis module. The image acquisition module is used to collect image information in the content push sampling range of the push area; the image marking module is used to perform image marking on the image information in the push sampling range; and the image analysis module is used to perform image analysis on the image information in the push sampling range.

[0031] In some embodiments, the push system can communicate using any currently known or future developed network protocol such as HTTP (Hyper Text Transfer Protocol), and can be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0032] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0033] The third aspect of the present invention provides a computer-readable medium having a computer program stored thereon, wherein when the program is executed by a processor, a personalized push method for highway operation safety education information based on artificial intelligence as described in any one of the first aspects is implemented. The computer-readable medium in this embodiment can be written in one or more programming languages ​​or a combination thereof to write computer program codes for performing the operations of some embodiments of the present disclosure, and the above-mentioned programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, C++, and also include conventional procedural programming languages ​​such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0034] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0035] In particular, according to some embodiments of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, some embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer readable medium, and the computer program includes a program code for executing the method shown in the flowchart.

[0036] The fourth aspect of the present invention provides an electronic device, comprising: one or more processors; a storage device having one or more programs stored thereon; when the one or more programs are executed by the one or more processors, the one or more processors implement a method for personalized push of highway operation safety education information based on artificial intelligence as described in the first aspect. The above-mentioned computer-readable medium may be included in the above-mentioned electronic device; or it may exist separately, that is, it is not assembled in the electronic device. The above-mentioned computer-readable medium carries one or more programs, and when the above-mentioned one or more programs are executed by the electronic device, the electronic device can implement a method for personalized push of highway operation safety education information based on artificial intelligence as described in the first aspect.

[0037] A fifth aspect of the present invention provides a computer program product, including a computer program, which, when executed by a processor, implements a personalized push method for highway operation safety education information based on artificial intelligence as described in the first aspect.

[0038] The above descriptions are only some preferred embodiments of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above inventive concept. For example, the above features are replaced with (but not limited to) technical features with similar functions disclosed in the embodiments of the present disclosure.

Claims

1. A personalized push method for highway operation safety education information based on artificial intelligence, It is characterized in that include: Obtaining the operation information of the push area and determining the main information of at least one construction unit in the push area; According to the main information of each construction unit, the demand information of multiple construction individuals is collected; Formulate at least one personalized push information package based on the main information of each construction unit and the operation information of the push area, and in combination with the demand information of multiple construction individuals; Send at least one personalized push information package to the push area for content push, and collect emotional feedback characteristics of construction individuals in the push area in real time to determine content push quality information in the push area; According to the content push quality information of the push area, the existing push content in the push area is adjusted, and the push theme of the construction individuals in the push area is determined.

2. According to claim 1, a personalized push method for highway operation safety education information based on artificial intelligence is characterized in that: The method for formulating at least one personalized push information package comprises: Determine push content classification information in the push area according to the job information of the push area; According to the demand information of multiple construction individuals, content push matching is performed with the push content classification information in the push area, and push content matching information of multiple construction individuals is determined respectively; According to the push content matching information of each construction individual, a personalized push information package is formulated according to the push requirements.

3. The method for personalized push of highway operation safety education information based on artificial intelligence according to claim 2 is characterized in that: The push content classification information in the push area includes: One or a combination of accident prevention, laws and regulations, emergency response, safety training, and weather warning.

4. The method for personalized push of highway operation safety education information based on artificial intelligence according to claim 1 is characterized in that: The method for collecting and pushing emotional feedback features of construction individuals in the area in real time includes: Pre-set the content push sampling range of the push area according to the operation information of the push area; According to the content push sampling range of the push area, micro-motion capture information of multiple construction individuals is collected in real time within the content push sampling range to determine feedback action information of the multiple construction individuals; According to the feedback action information of multiple construction individuals, the emotional feedback characteristics of the construction individuals in the content push sampling range of the push area are determined.

5. The method for personalized push of highway operation safety education information based on artificial intelligence according to claim 4 is characterized in that: The method for determining the emotional feedback characteristics of construction individuals in the content push sampling range of the push area includes: Suppose that there is a content push sampling range in the push area If there are individual construction units, then: Formula 1; In formula 1, is the overall sentiment score, ranging from , used to measure employees’ overall sentiment towards push content; is the total number of employees who participated in the feedback; The emotional types of employees are divided into three categories: Employees with positive emotions received a score of 1; Employees with neutral emotions received a score of 0; Employees with negative emotions scored .

6. The method for personalized push of highway operation safety education information based on artificial intelligence according to claim 5 is characterized in that: The method for determining feedback action information of multiple construction individuals includes: In the content push sampling range of the push area, image information of multiple continuous time segments is collected; Perform image analysis on the image information of multiple continuous time segments respectively, and determine the action changes of multiple construction individuals in different image information respectively; According to the temporal features in different image information, the action changes of multiple construction individuals in different image information are marked, and the feedback action information of the multiple construction individuals is determined.

7. The method for personalized push of highway operation safety education information based on artificial intelligence according to claim 6, characterized in that: The step of respectively determining the movement changes of multiple construction individuals in different image information includes: According to the time sequence features in the image information of the plurality of continuous time sequence segments, the image information of the first time sequence segment is selected as the original reference image, and the content push position in the original reference image is determined; The content push position in the original reference image is used as a coordinate reference point, and the reference contour coordinates of the heads of multiple construction individuals in the original reference image are determined respectively; According to the time sequence features in the image information of multiple continuous time sequence segments, the head contour coordinates of multiple construction individuals in different image information are extracted in turn to determine the movement changes of the multiple construction individuals in different image information.

8. The method for personalized push of highway operation safety education information based on artificial intelligence according to claim 7 is characterized in that: The method for determining the emotional feedback characteristics of construction individuals in the content push sampling range of the push area also includes: Assume that the head contour coordinates of any construction individual exist in the image information of multiple continuous time segments for: , , ,.... are the horizontal coordinates of the head contour of any construction individual in the image information of multiple continuous time series segments; , ,.... are respectively the vertical coordinates of the head contour of any construction individual in the image information of a plurality of continuous time series segments; At this time, the vertical position change of the head contour is used to detect the construction personnel's head raising and lowering movements. Then: Formula 2; In formula 2, is the vertical coordinate of the head contour of the construction individual in the current reference image, is the vertical coordinate of the head outline of the construction individual in the next reference image; Among them, if , it indicates a head-up action, and the construction individual is judged as an employee with positive emotions; like , it means the action of lowering the head, and the construction individual is judged as an employee with negative emotions.

9. The method for personalized push of highway operation safety education information based on artificial intelligence according to claim 8, characterized in that: The push method also includes: According to the coordinate reference point of the content push location, respectively determine the facial region coordinate information of multiple construction individuals in the image information of at least one continuous time sequence segment; According to the facial region coordinate information of multiple construction individuals, the facial feature information of the construction individuals in the image information of each continuous time sequence segment is extracted respectively; According to the facial feature information of the construction individuals in the image information of each continuous time sequence segment, the emotional feedback features of the construction individuals in the content push sampling range of the push area are determined respectively.

Images