A management method for automatic seat selection and related equipment

Abstract

The present invention provides a management method and related equipment for automatic seat selection, which are applied to the field of data processing technology. The present application obtains target user information, a target event set matching the target user information, target place information and a training sample set; pre-processes the training sample set to generate a training sample set with target feature data; processes a preset seat pre-arrangement management model based on the training sample set with target feature data to generate a target seat pre-arrangement management model; processes the target user information to generate physiological parameter information of the target user; processes the target event set to generate a seat pre-arrangement influencing factor; processes the target place information based on the target seat pre-arrangement management model to generate attribute information of the target place; processes the attribute information of the target place, the physiological parameter information of the target user and the seat pre-arrangement influencing factor based on the target seat pre-arrangement management model to generate the seat pre-arrangement information of the target place.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a management method for automatic seat selection and related equipment. Background Art

[0002] When users use the application in the terminal device to help reserve seats, they often need to go through the following process: first enter the ticket booking application in the terminal device, then select the show to be watched, select the venue, such as selecting the number of the theater, then select the seat in the venue, and finally make payment and exchange. In each venue, the quality of the seat is affected by many factors such as the size of the screen, the position and volume of the sound, the difference between the front and back rows, etc., and the viewing effect of different seats in different venues is often different. In the traditional processing process, since users cannot predict the best viewing seat among the remaining seats in unfamiliar venues, they can only rely on past experience when choosing seats, and as a result, they often miss the best viewing position in the venue. In addition, if a satisfactory seat cannot be found in the current venue, the user can only return to the previous steps to select the show, venue, etc. again, resulting in a waste of user time.

[0003] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0004] The purpose of this application is to provide a management method and related equipment for automatic seat selection, which at least to some extent overcomes the problems existing in the prior art, by obtaining information on target users, events, places and training sample sets, preprocessing the training sample sets to generate target feature data, obtaining a preset model and processing it to obtain a target seat pre-arrangement management model. The target user information is processed to obtain physiological parameter information, and the target event set is processed to obtain seat pre-arrangement influencing factors. The target place information is processed using the model to generate attribute information, including seat classification. Finally, the attribute information, physiological parameter information and influencing factors are processed separately to obtain the first and second seat pre-arrangement values, and the seat pre-arrangement information is comprehensively generated to provide users with accurate seat selection suggestions and improve the scientificity and rationality of seat allocation.

[0005] Other features and advantages of the present application will become apparent from the following detailed description, or may be learned in part by the practice of the present invention.

[0006] According to one aspect of the present application, a method for managing automatic seat selection is provided, comprising: obtaining target user information, a target event set matching the target user information, target venue information and a training sample set, wherein the target venue information comprises location information within the target venue, and the training sample set comprises historical environmental factor information of the target venue and real-time environmental factor information of other venues adjacent to the target venue; preprocessing the training sample set to generate a training sample set with target feature data, wherein the target feature data is used to characterize risk factors affecting venue seat pre-arrangement; obtaining a preset seat pre-arrangement management model, wherein the preset seat pre-arrangement management model is generated based on historical environmental factor information of other venues. The method comprises the following steps: processing the preset seat pre-arrangement management model based on the training sample set with target feature data to generate a target seat pre-arrangement management model; processing the target user information to generate physiological parameter information of the target user; processing the target event set matching the target user information to generate a seat pre-arrangement influencing factor; processing the target place information based on the target seat pre-arrangement management model to generate attribute information of the target place, wherein the attribute information of the target place includes classification information of seats; processing the attribute information of the target place, the physiological parameter information of the target user and the seat pre-arrangement influencing factor based on the target seat pre-arrangement management model to generate seat pre-arrangement information of the target place.

[0007] Another aspect of the present application is a management device for automatic seat selection, characterized in that it includes: an acquisition module, used to acquire target user information, a target event set matching the target user information, target venue information and a training sample set, wherein the target venue information includes location information within the target venue, and the training sample set includes historical environmental factor information of the target venue and real-time environmental factor information of other venues adjacent to the target venue; acquiring a preset seat pre-arrangement management model, wherein the preset seat pre-arrangement management model is generated based on historical environmental factor information of other venues; a processing module, used to pre-process the training sample set to generate a training sample set with target feature data, wherein the target feature data is used to characterize the influencing venue risk factors for seat pre-arrangement; processing the preset seat pre-arrangement management model based on the training sample set with target feature data to generate a target seat pre-arrangement management model; processing the target user information to generate physiological parameter information of the target user; processing the target event set matching the target user information to generate seat pre-arrangement influencing factors; processing the target venue information based on the target seat pre-arrangement management model to generate attribute information of the target venue, wherein the attribute information of the target venue includes classification information of seats; processing the attribute information of the target venue, the physiological parameter information of the target user and the seat pre-arrangement influencing factors based on the target seat pre-arrangement management model to generate seat pre-arrangement information for the target venue.

[0008] According to another aspect of the present application, an electronic device is characterized in that it includes: a first processor; and a memory for storing executable instructions of the first processor; wherein the first processor is configured to execute the above-mentioned automatic seat selection management method by executing the executable instructions.

[0009] According to another aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a second processor, the above-mentioned automatic seat selection management method is implemented.

[0010] According to another aspect of the present application, a computer program product is provided, including a computer program, characterized in that when the computer program is executed by a third processor, the above-mentioned automatic seat selection management method is implemented.

[0011] The present application provides an automatic seat selection management method and related equipment, in which a server obtains information about target users, events, places and training sample sets, pre-processes the training sample sets to generate target feature data, obtains a preset model and obtains a target seat pre-arrangement management model after processing. The target user information is processed to obtain physiological parameter information, and the target event set is processed to obtain seat pre-arrangement influencing factors. The model is used to process the target place information to generate attribute information, including seat classification. Finally, the attribute information, physiological parameter information and influencing factors are processed separately to obtain the first and second seat pre-arrangement values, and the seat pre-arrangement information is comprehensively generated to provide users with accurate seat selection suggestions and improve the scientificity and rationality of seat allocation.

[0012] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 A flowchart showing a method for managing automatic seat selection provided by an embodiment of the present application is shown;

[0014] Figure 2 A schematic diagram of the structure of an automatic seat selection management device provided by an embodiment of the present application is shown;

[0015] Figure 3 A schematic diagram of the structure of an electronic device provided by an embodiment of the present application is shown;

[0016] Figure 4 A schematic diagram of a storage medium provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0017] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0018] Combine the following Figure 1 To describe the management method of automatic seat selection according to an exemplary embodiment of the present application. It should be noted that the following application scenarios are only shown to facilitate understanding of the spirit and principle of the present application, and the implementation of the present application is not limited in this regard. On the contrary, the implementation of the present application can be applied to any applicable scenario.

[0019] In one implementation, the present application also proposes a management method and related equipment for automatic seat selection. Figure 1 The flowchart of a method for managing automatic seat selection according to an embodiment of the present application is schematically shown. Figure 1 As shown, the method is applied to a server, comprising:

[0020] S101, obtaining target user information, a target event set matching the target user information, target location information, and a training sample set.

[0021] In one implementation, assuming that the target user is a new employee named Xiao Li, the target user information may include the following: Basic information: Name is Xiao Li, age is 25, gender is female, and department is sales department. Training demand information: Hope to improve his sales skills and communication skills through this training. Xiao Li has a high requirement for the comfort of the seat because he is a little tired recently. Learning style information: Xiao Li prefers interactive learning methods and hopes that the seat can facilitate communication with the lecturer and other trainees. The target event set matching Xiao Li's information may include: The company is about to carry out a three-day sales skills training, and the training location is in the target venue. This event will affect Xiao Li's choice of seat. For example, she may want to choose a seat that is close to the lecturer and can clearly see the projected content. There may be group discussions during the training, and Xiao Li hopes to choose a seat that is convenient for communicating with group members.

[0022] The target location is assumed to be a company's training conference room, and its location information can be described as: located on the fifth floor of the company's office building, the conference room has an area of ​​150 square meters and a total of 80 seats. The layout of the conference room is roughly as follows: there is a podium and projection screen in the front, rows of tables and chairs in the middle, and some temporary chairs in the back.

[0023] The training sample set includes the historical environmental factor information of the target location and the real-time environmental factor information of other locations adjacent to the target location. Among them, the historical environmental factor information of the target location: the temperature of the conference room at different time periods in the past few training sessions, for example, the temperature in the morning is relatively suitable, and it may become a bit stuffy in the afternoon due to direct sunlight. The degree of wear of some seats, such as the seats near the door are often dragged by people, and the bottom of the seats are worn to a certain extent. There was a slight water leak in a corner during the last training. Although it has been repaired, it may still affect the trainees' choice of seats in this area. The sight of different seats, the front seats in the middle have the best sight, and can clearly see the lecturer and the projected content, while the seats near the window may be affected by direct sunlight. The distance between each seat and the entrance and the bathroom, for example, seat A10 is only 3 meters away from the nearest entrance, and seat B15 is about 8 meters away from the bathroom.

[0024] Real-time environmental factor information of other places adjacent to the target place: An important meeting is taking place in the office adjacent to the training conference room, and the sound may interfere with the seats on the side of the conference room close to the office. A small tea party is being held in the company's lounge area, and there are certain activity sounds, but it is far away from the target place and the impact is relatively small.

[0025] S102, preprocessing the training sample set to generate a training sample set with target feature data.

[0026] In one implementation, feature extraction is performed on the training sample set to determine the original feature library. The training sample set includes historical environmental factor information of the target training venue and real-time environmental factor information of other venues adjacent to the target venue. For historical environmental factors: extract temperature features, such as the average temperature, maximum temperature, and minimum temperature of the conference room at different time periods during past training. Extract seat wear features, which are divided into different levels such as slight wear, moderate wear, and severe wear. Extract water leakage features to record whether there is a water leak and the severity of the water leak. Extract line of sight features, such as good, general, poor, etc. Extract distance features from entrances and exits and toilets, and record them in specific meters. For real-time environmental factors of adjacent venues: extract sound intensity features of adjacent office meetings, which can be expressed in decibel values. Extract sound intensity features of activities in the rest area, also recorded in decibel values. In this way, the original feature library is determined, which contains various features related to the pre-arrangement of seats in the training venue.

[0027] The original feature library is divided into various feature data sets to generate training sets and validation sets. Assume that there are 100 sample data in the original feature library. 70 of them can be randomly selected as training sets for model training; the remaining 30 are used as validation sets to evaluate the performance of the model. For example, the training set may contain environmental factor data from the past five training sessions, while the validation set contains environmental factor data from the most recent training session.

[0028] Based on the classifier, the original feature library is divided into various validation sets for prediction and the prediction results are determined. Use a classifier, such as a decision tree classifier. Input the feature data in the validation set into the classifier, and the classifier predicts each sample based on the learned rules. Assume that the classification goal is to predict the popularity of seats, which are divided into three levels: high, medium, and low. After the classifier predicts each sample in the validation set, a series of prediction results are obtained, such as predicting that the popularity of a certain seat is medium.

[0029] Based on the preset algorithm, the original feature library is divided into various training sets for training to obtain the validation set class prediction results. The preset algorithm, such as the random forest algorithm, is used for training on the training set. During the training process, the algorithm will continuously adjust the model parameters according to the feature data and corresponding labels (such as the seat popularity level) in the training set to improve the accuracy of the prediction. After the training is completed, the data of the validation set is input into the trained model to obtain the validation set class prediction results. This result is the model's prediction of the samples in the validation set, which is also the seat popularity level prediction.

[0030] The prediction results and the validation set prediction results are processed to generate target feature data, which is used to characterize the risk factors that affect the venue seat pre-arrangement. The prediction results obtained by the classifier are compared and analyzed with the validation set prediction results obtained by the model. If the prediction results of the two are relatively consistent, it means that the corresponding features have a strong characterization ability for the risk factors of seat pre-arrangement. For example, if a seat is considered to be less popular in both predictions, and its characteristics are severe wear and tear and far from the bathroom, then these features can be used as risk factors that affect the venue seat pre-arrangement, that is, target feature data. If the prediction results of the two are inconsistent, the reasons can be further analyzed. It may be that the feature extraction is not comprehensive or the model needs to be further optimized. Through continuous adjustment and improvement, more accurate target feature data can be generated for subsequent seat pre-arrangement management models.

[0031] S103, obtaining a preset seat pre-arrangement management model.

[0032] In one implementation, the preset seat pre-arrangement management model is generated based on the historical environmental factor information of other places. Assume that an enterprise has multiple training places, including large conference rooms, small training rooms, etc. Now, it is necessary to perform seat pre-arrangement management for one of the specific training rooms (target place). Obtain the preset seat pre-arrangement management model, and specifically, collect the historical environmental factor information of other places. For example, for another large conference room of the enterprise, record the various environmental factors during different training activities in the past year. Including temperature changes, such as the indoor temperature is higher during summer training and relatively lower in winter; the use and wear of seats, some seats have obvious wear on the surface due to frequent use; whether there is a water leak, such as after a heavy rain, there is a slight water leak in a corner of the conference room; sight factor, seats near the window may be affected by direct sunlight and affect the sight, while seats in the middle position have relatively good sight; distance from the entrance and exit and the bathroom, some seats are very close to the entrance and exit, which is convenient for trainees to enter and exit, while some seats are far from the bathroom, etc.

[0033] Based on these historical environmental factors, a machine learning algorithm is used to generate a preset seat pre-arrangement management model. For example, a neural network algorithm can be used to take different environmental factors as input features and the use of seats (whether they are selected, how often they are selected, etc.) as output labels. By learning from a large amount of historical data, the model gradually grasps the relationship between different environmental factors and seat selection. For example, after training, the model found that when the temperature is moderate, the seat is not worn, the line of sight is good, and the distance to the entrance and toilet is close, the probability of the seat being selected is high. On the contrary, when the temperature is too high or too low, the seat is severely worn, the line of sight is blocked, or it is far from the entrance and toilet, the probability of the seat being selected is low. In this way, a preset seat pre-arrangement management model generated based on the historical environmental factor information of other places is obtained, which can provide a reference and basis for the pre-arrangement of seats in the target training venue.

[0034] S104, processing the preset seat pre-arrangement management model based on the training sample set with target feature data to generate a target seat pre-arrangement management model.

[0035] In one implementation, the preset seat pre-arrangement management model is processed based on the training sample set with target feature data to generate a target seat pre-arrangement management model. Assume that the target training venue is a medium-sized training classroom of the company. The target feature data in the training sample set include the following aspects: Historical temperature data of the training classroom: In the past few training sessions, the temperature changes of the classroom in different time periods are recorded. For example, the temperature is usually between 22-24 degrees Celsius during morning training, and it may rise to 25-27 degrees Celsius in the afternoon, especially when the temperature is directly exposed to sunlight. Due to frequent use, the leather surface of some seats has been worn, which is divided into light wear, medium wear and heavy wear levels. There was a water leakage problem in a corner of the classroom. Although it has been repaired, the seats in this position may still be of concern to the trainees. The seats near the window will have a poor view when the sun is strong, while the seats in the middle and front have a good view and can clearly see the podium and projection screen. Some seats are close to the entrance and exit, which is convenient for trainees to enter and exit, but may be disturbed by external noise; other seats are close to the bathroom and may be affected by odor.

[0036] The preset seat pre-arrangement management model is generated based on the historical environmental factor information of other training venues in the company. For example, from the historical data of another large training room, the model learned the influence of factors such as temperature, seat wear, and line of sight on seat selection. The training sample set with the target feature data is input into the preset seat pre-arrangement management model. The model will further learn and adjust according to the input data. For example, if it is found in the historical data of the target training classroom that even if the temperature is moderate, as long as the seat is close to the toilet, few students will choose this seat. The preset model may not fully consider the influence of this factor. At this time, the model will adjust the parameters according to the new training sample set and increase the weight of the feature of distance from the toilet. For another example, for seats with a history of water leakage, even after repair, students still tend to avoid choosing them. The model will adjust the way of handling the water leakage feature according to this situation, so that the actual selection tendency of students can be more accurately reflected when predicting the popularity of seats.

[0037] After learning and adjusting the training sample set, a target seat pre-arrangement management model suitable for the target training classroom is finally generated. This model can more accurately predict the popularity of different seats based on the specific environmental factors of the target classroom, and provide more precise guidance for seat pre-arrangement. For example, when a new training activity is scheduled, this model can recommend the most suitable seats for trainees based on factors such as the expected temperature of the day, the current state of the seats, and whether there are special activities that affect the line of sight, or provide training organizers with seat pre-arrangement plans to improve the training effect and trainee satisfaction.

[0038] S105: Process the target user information to generate physiological parameter information of the target user.

[0039] In one implementation, the target user information is processed to generate initial facial image information and target user identity information, wherein the initial facial image information is the facial information of the target user within a preset time period. Assume that the target user is Xiao Wang, an employee who is participating in training. When signing in for training, Xiao Wang's facial information within a preset time period (for example, within one minute before and after signing in) is collected through a camera installed at the entrance of the training venue. This is the initial facial image information. At the same time, Xiao Wang signs in using an employee card, and the system reads the information in the card to determine Xiao Wang's identity information, including name, department, position, etc.

[0040] Process the initial facial image information to generate the influencing factors of the target user's facial expression features. Analyze Xiao Wang's initial facial image information. For example, detect Xiao Wang's facial expressions, including the shape of his eyebrows, the size and degree of squinting of his eyes, and the upturn or drooping of his mouth corners. If Xiao Wang's eyebrows are slightly wrinkled, his eyes are slightly squinting, and his mouth corners are not obviously upturned or drooped, these features can be used as influencing factors of facial expression features. At the same time, consider the environmental factors when collecting facial images, such as light intensity, background noise, etc. If the light is dim, it may affect Xiao Wang's facial expression, which is also recorded as an influencing factor of facial expression features.

[0041] The influencing factors of the target user's facial expression characteristics are processed to generate the target user's emotional information, where the target user's emotional information is used to characterize the target user's facial expression change information. Xiao Wang's emotional information is inferred based on his facial expression characteristics influencing factors. For example, if the eyebrows are wrinkled, the eyes are squinting, and the light is dim, it may mean that Xiao Wang is a little nervous or tired. This is the target user's emotional information, which is used to characterize Xiao Wang's facial expression change information at this specific moment. If Xiao Wang's facial image is collected again during the training process, it is found that his expression gradually changes from nervous to relaxed, and the corners of his mouth are slightly raised, which means that his emotions have changed, and his emotional information is further updated.

[0042] The target user's identity information is processed to generate the target user's real-time vital signs information. Using Xiao Wang's identity information, his real-time vital signs information is obtained from the company's health management system. For example, if Xiao Wang wears a smart bracelet, the data uploaded by the bracelet shows that his current heart rate is 75 beats per minute, blood pressure is 120 / 80 mmHg, sleep time is 7 hours, etc. If Xiao Wang has a recent record of being sick, the system will also include this information in the real-time vital signs information. For example, if he has a cold, he may have symptoms such as coughing and fatigue.

[0043] Based on the real-time vital signs information of the target user and the influencing factors of the target user's facial expression characteristics, the physiological parameter information of the target user is generated. Based on Xiao Wang's real-time vital signs information and the influencing factors of facial expression characteristics, his physiological parameter information is generated. For example, if Xiao Wang's heart rate and blood pressure are normal, but his expression shows a little fatigue, then the physiological parameter information may indicate that he is in basically good physical condition, but may need more rest or a comfortable seating environment. These physiological parameter information can be used in the seat pre-arrangement management model. If Xiao Wang needs more rest, the model may recommend a relatively quiet seat close to the entrance and exit so that he can go out to rest at any time. If his eyesight is not very good, the model will consider arranging a seat for him that is close to the podium and has a good line of sight.

[0044] S106, processing the target event set matching the target user information to generate a seat pre-arrangement influencing factor.

[0045] In one implementation, the target event set that matches the target user information is processed to generate the type information of the target event, wherein the type information of the target event is used to characterize the warning level of the target event for seat selection. Assume that the target user is Xiao Li, an employee who is participating in training. The target event set that matches Xiao Li's information may include an important upcoming training course, a group discussion session during the training, and renovations being carried out near the training classroom. These target events are processed to determine the type information of the target event. For example, an important training course can be classified as a high-priority event, and the warning level for seat selection is high, because the trainees may want to choose a seat that can clearly see the podium and projection and is not disturbed; the group discussion session may be a medium-priority event, and the trainees may prefer to choose a seat that is convenient for communicating with group members; and nearby decoration is a low-priority event, but it may cause some noise interference to the seats near the decoration area.

[0046] The type information of the target event is processed to generate user historical seat pre-arrangement information, wherein the user historical seat pre-arrangement information is used to characterize the seat information assigned to different users when they experience the target event of this type. The type information of the target event is processed to query the user historical seat pre-arrangement information. For example, for an important training course event with high priority, query the seat information assigned to different users in similar training courses in the past. It may be found that in previous important trainings, some students chose the middle seats in the front row, which have good sight lines and are close to the lecturer; while other students chose the corner seats at the back, probably to avoid being overly noticed.

[0047] Process the user's historical seat pre-arrangement information to generate seat selection influencing factors and weight information corresponding to the seat selection influencing factors. Analyze the user's historical seat pre-arrangement information to extract seat selection influencing factors. For example, for important training course events, influencing factors may include sight factors, distance from the instructor, quietness, etc. At the same time, according to the frequency of occurrence of different factors in historical data and their importance to seat selection, determine the weight information corresponding to the seat selection influencing factors. For example, the weight of the sight factor may be high because most trainees hope to see the training content clearly; while the weight of quietness may be relatively low, but it may also affect seat selection in some cases.

[0048] Based on the preset seat selection influencing feature set, the seat selection influencing factor and the weight information corresponding to the seat selection influencing factor are processed to generate the seat pre-arrangement influencing factor. Based on the preset seat selection influencing feature set, the seat selection influencing factor and the corresponding weight information are processed to generate the seat pre-arrangement influencing factor. The preset seat selection influencing feature set can be a series of features and rules pre-set according to the characteristics of the training venue and general user needs. For example, if the preset feature set stipulates that seats with good sight and close to the lecturer have a higher priority, then in the processing process, the sight factor and the influence factor and weight of the distance from the lecturer will be adjusted and comprehensively calculated according to this rule, and finally a seat pre-arrangement influencing factor that can reflect the degree of influence of the target event on the seat pre-arrangement is obtained. In this way, by gradually processing the target event set that matches the target user information, the seat pre-arrangement influencing factor is generated, which provides an important basis for the seat pre-arrangement management of the training venue.

[0049] S107: Process the target location information based on the target seat pre-arrangement management model to generate attribute information of the target location.

[0050] In one implementation, the target location information is processed based on the target seat pre-arrangement management model to generate monitoring point information, wherein the monitoring point information is the seat information located in the target location. Assume that the target location is a classroom in a large training center. The target seat pre-arrangement management model processes the target location information and first generates monitoring point information, where the monitoring points are the seats in the classroom. Each seat has its own unique position and characteristics, for example, seat A1 is located in the front row of the classroom by the window, seat B10 is located in the middle of the back row of the classroom, etc.

[0051] The monitoring point information is processed in groups to generate several group information, wherein the group information includes the monitoring point information at different distances from the training area. The monitoring point information is processed in groups according to the different distances from the training area (usually the podium area). It can be divided into three groups: the near area (0-3 meters from the podium), the middle area (3-6 meters from the podium) and the far area (more than 6 meters from the podium). In this way, seat A1 may be classified into the near area, and seat B10 may be classified into the far area.

[0052] Perform feature extraction on the group information to generate feature data sets for different groups. Perform feature extraction on each group information to generate feature data sets for different groups. For near-zone seats, possible features include excellent sight, easy interaction with the lecturer, and possible influence of the lecturer's movement; for mid-zone seats, features may include good sight, moderate noise, and relatively quiet; for far-zone seats, features may be relatively quiet, less disturbed, but with poor sight.

[0053] Process the feature data sets of different groups to obtain abnormal seat features and correlation co-occurrence frequencies. Process the feature data sets of different groups to identify abnormal seat features. For example, a damaged chair is found in the near area, which is an abnormal seat feature. At the same time, count the frequency of different features appearing simultaneously in each group, that is, the correlation co-occurrence frequency. For example, in the middle area seats, the probability of the two features of good sight and moderate noise appearing simultaneously is high.

[0054] The abnormal seat features and the correlation co-occurrence frequency are processed to generate correlation information, wherein the correlation information is used to characterize the correlation between the seat features at different distances from the training area and the actual situation of the seats in the target location. The abnormal seat features and the correlation co-occurrence frequency are processed to generate correlation information. This information is used to characterize the correlation between the seat features at different distances from the training area and the actual situation of the seats in the target location. For example, it is found that among the seats in the near area, seats with good sight lines are usually more likely to be selected by trainees, indicating that the feature of good sight lines is strongly correlated with the actual use of seats.

[0055] Based on the correlation information, the feature data sets of different groups are processed to generate the attribute information of the target place, and the attribute information of the target place includes the classification information of the seats. Based on the correlation information, the feature data sets of different groups are further processed to generate the attribute information of the target place. These attribute information include the classification information of the seats, for example, they can be divided into high-quality seats (good sight, no abnormalities, moderate distance from the podium), ordinary seats (relatively average characteristics in all aspects) and problem seats (damaged or greatly disturbed, etc.). In this way, when pre-arranging seats, more suitable seat selection suggestions can be provided to students based on these attribute information.

[0056] S108: Process the attribute information of the target place, the physiological parameter information of the target user and the seat pre-arrangement influencing factor based on the target seat pre-arrangement management model to generate seat pre-arrangement information of the target place.

[0057] In one implementation, the attribute information of the target venue is processed based on the target seat pre-arrangement management model to generate a first seat pre-arrangement value for the target seat. Assume that the target venue is a large conference room in a corporate training center. The target seat pre-arrangement management model processes the attribute information of the target venue. The conference room is divided into different areas, such as the front row area close to the podium, the middle area, and the back row area. Each area has different seat characteristics. For example, the front row area has a good view but may be greatly affected by the movement of the lecturer, the middle area is more balanced, and the back row area is relatively quiet but the view may be slightly worse. Assume that there are three groups (m=3), each with a different number of seats ( , , For each group of features, assume there are three features (k=3), namely, line of sight ( ), interference degree ( ) and comfort ( ). Each feature has a corresponding weight ( , , ), these weights can be determined by analyzing previous training data or expert evaluation. Calculate the value of a single seat pre-arrangement: Take a seat in the middle area as an example, assuming that the values ​​of the seat on the three features are =Good, =Medium, = better, the corresponding weight is =0.4, =0.3, =0.3. According to the formula , the pre-arrangement value of the seat in the middle area is =0.4×good+0.3×medium+0.3×better.

[0058] Calculate the overall first seat reservation value: perform similar calculations for all seats in all groups, and then use the formula , we can get the first seat pre-arrangement value of the target seats in the entire conference room. For example, if there are 20 seats in the front row area, 30 seats in the middle area, and 25 seats in the back row area, calculate the sum of the seat pre-arrangement values ​​of each area, and then divide it by the total number of seats 75 to get the first seat pre-arrangement value .

[0059] ;

[0060] ;

[0061] P represents the comprehensive seat reservation value of the target venue or some index value related to seat reservation.

[0062] m represents the number of seat groups in the target venue. For example, if the target venue is divided into three groups: the area near the podium, the middle area, and the back area, then m=3.

[0063] n represents the number of seats in each group. For example, if there are n seats in a group.

[0064] Represents the pre-ranking value of the lth seat in the ith group. This value is calculated by considering the value of the seat on each feature and the corresponding feature weight.

[0065] k represents the number of seat features in each group. For example, if we consider the three features of seat sight, interference and comfort, then k=3.

[0066] is the weight of the jth feature in the ith group. This weight reflects the importance of the feature in seat pre-arrangement and can be determined by data analysis, expert evaluation, etc.

[0067] represents the value of the jth feature for the lth seat in the ith group. For example, if j represents the sight line, then It may be different values ​​such as "good", "medium", "poor", etc.

[0068] Based on the target seat pre-arrangement management model, the target user's physiological parameter information and seat pre-arrangement influencing factors are processed to generate the second seat pre-arrangement value of the target seat. Assume that the target user is Xiao Zhang, an employee who is participating in the training. Xiao Zhang's physiological parameter information This may include physical fatigue level (mild fatigue), vision condition (mild myopia), etc. This may include the importance of the training course (high), the weather conditions of the day (hot, which may affect the choice of a seat near the air conditioner), etc. Assume that physiological parameter information affects the weight =0.6, weight of seat pre-arrangement influencing factor =0.4. According to the formula , assuming that Xiao Zhang's physiological parameter information and seat pre-arrangement influencing factors are quantified, =0.7 (indicates the degree of demand for seats after comprehensive consideration of physiological parameters), =0.8 (indicates the degree of demand for seats after comprehensive consideration of the factors affecting seat pre-arrangement). Then the second seat pre-arrangement value =0.6×0.7+0.4×0.8=0.42+0.32=0.74.

[0069] ;in, The second seat reservation value representing the target seat.

[0070] Represents the target user's physiological parameter information influence weight. It reflects the importance of the target user's physiological parameter information in calculating the second seat reservation value.

[0071] Physiological parameter information representing the target user, such as physical fatigue level, vision condition, etc., which will affect the user's demand for seats.

[0072] Represents the weight of the seat pre-arrangement influence factor. It reflects the relative importance of the seat pre-arrangement influence factor in calculating the second seat pre-arrangement value.

[0073] Represents the factors affecting seat pre-arrangement. For example, it may include the importance of the training course, the weather conditions of the day, etc. These factors will also affect the choice of seats.

[0074] The first seat pre-arrangement value of the target seat and the second seat pre-arrangement value of the target seat are processed to generate the seat pre-arrangement information of the target venue. The first seat pre-arrangement value and the second seat pre-arrangement value of the target seat are processed to generate the seat pre-arrangement information of the target venue. For example, if the seat with a higher first seat pre-arrangement value is in the middle of the front row of the conference room, and the second seat pre-arrangement value shows that Xiao Zhang is more suitable for a seat close to the entrance and exit with a better line of sight due to physical fatigue and vision problems, after comprehensive consideration, a seat that meets both the overall seat quality and personal needs can be recommended to Xiao Zhang. In this way, through the processing of different information by the target seat pre-arrangement management model, the seat pre-arrangement information of the target venue is finally generated, providing scientific and reasonable seat arrangement suggestions for training organizers and trainees.

[0075] This automatic seat selection management method aims to provide users of the target venue with a more scientific and reasonable seat pre-arrangement plan. First, obtain the target user information, target event set, target venue information and training sample set. The target venue information includes location information, and the training sample set covers the historical environmental factors of the target venue and the real-time environmental factors of adjacent venues. These factors include activity conditions, seat wear, water leakage, sight, and distance from the entrance or toilet. Then, preprocess the training sample set. The original feature library is determined by feature extraction, and the training set and validation set are divided. The classifier is used to predict the validation set and combined with the preset algorithm to train the training set to obtain the prediction results and the validation set class prediction results, and then generate the target feature data that characterizes the risk factors affecting seat pre-arrangement.

[0076] After obtaining the preset seat pre-arrangement management model generated based on historical environmental factors of other places, the model is processed with the training sample set with target feature data to obtain the target seat pre-arrangement management model. For the processing of target user information, the initial face image information and identity information are first obtained, and then the expression feature influencing factors and emotional information are generated, and the real-time vital sign information generated by the identity information is combined to finally obtain the target user's physiological parameter information. For the processing of the target event set, the target event type information is first determined to characterize the warning level, and then the user's historical seat pre-arrangement information is generated, and the seat selection influencing factors and weight information are obtained, and then the seat pre-arrangement influencing factors are generated based on the preset seat selection influencing feature set.

[0077] The target seat pre-arrangement management model is used to process the target venue information, generate monitoring point information, i.e. seat information, and extract features after grouping to obtain feature data sets of different groups. The abnormal seat features and correlation co-occurrence frequency are obtained, and correlation information is generated to characterize the correlation between seat features and seat actual conditions, thereby generating the attribute information of the target venue including seat classification information. Finally, based on the target seat pre-arrangement management model, the target venue attribute information, target user physiological parameter information, and seat pre-arrangement influencing factors are processed respectively to obtain the first seat pre-arrangement value and the second seat pre-arrangement value of the target seat. The two are processed comprehensively to generate the seat pre-arrangement information of the target venue, providing users with more accurate seat selection suggestions.

[0078] In one embodiment, if Figure 2 As shown, the present application also provides a management device for automatic seat selection, including:

[0079] The acquisition module 201 is used to acquire target user information, a target event set matching the target user information, target venue information and a training sample set, wherein the target venue information includes location information within the target venue, and the training sample set includes historical environmental factor information of the target venue and real-time environmental factor information of other venues adjacent to the target venue; acquire a preset seat pre-arrangement management model, wherein the preset seat pre-arrangement management model is generated based on the historical environmental factor information of other venues;

[0080] The processing module 202 is used to pre-process the training sample set to generate a training sample set with target feature data, wherein the target feature data is used to characterize the risk factors that affect the venue seat pre-arrangement; based on the training sample set with target feature data, the preset seat pre-arrangement management model is processed to generate a target seat pre-arrangement management model; the target user information is processed to generate physiological parameter information of the target user; the target event set matching the target user information is processed to generate seat pre-arrangement influencing factors; based on the target seat pre-arrangement management model, the target venue information is processed to generate attribute information of the target venue, wherein the attribute information of the target venue includes classification information of seats; based on the target seat pre-arrangement management model, the attribute information of the target venue, the physiological parameter information of the target user and the seat pre-arrangement influencing factors are processed to generate seat pre-arrangement information of the target venue.

[0081] The present application embodiment provides an electronic device, such as Figure 3As shown, the electronic device 3 includes a first processor 300, a memory 301, a bus 302 and a communication interface 303. The first processor 300, the communication interface 303 and the memory 301 are connected via the bus 302. The memory 301 stores a computer program that can be run on the first processor 300. When the first processor 300 runs the computer program, the automatic seat selection management method provided in any of the aforementioned embodiments of the present application is executed.

[0082] The memory 301 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk memory. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 303 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used.

[0083] The bus 302 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The memory 301 is used to store a program, and the first processor 300 executes the program after receiving an execution instruction. The automatic seat selection management method disclosed in any implementation of the embodiment of the present application may be applied to the first processor 300, or implemented by the first processor 300.

[0084] The first processor 300 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the first processor 300. The above-mentioned first processor 300 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a readily available programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be embodied as being executed by a hardware decoding processor, or by a combination of hardware and software modules in a decoding processor. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 301, and the first processor 300 reads the information in the memory 301 and completes the steps of the above method in combination with its hardware.

[0085] The electronic device provided in the above-mentioned embodiments of the present application and the automatic seat selection management method provided in the embodiments of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.

[0086] The present application embodiment provides a computer-readable storage medium, such as Figure 4 As shown, the computer-readable storage medium 401 stores a computer program, and when the computer program is read and executed by the second processor 402, the automatic seat selection management method as described above is implemented.

[0087] The technical solution of the embodiment of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling an electronic device (which may be an air conditioner, a refrigeration device, a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the method described in the embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.

[0088] The computer-readable storage medium provided in the above-mentioned embodiments of the present application and the automatic seat selection management method provided in the embodiments of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.

[0089] An embodiment of the present application provides a computer program product, including a computer program, wherein the computer program is executed by a third processor to implement the method described above.

[0090] The computer program product provided in the above-mentioned embodiments of the present application and the automatic seat selection management method provided in the embodiments of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.

[0091] It should be noted that, in this application, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or still includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise one..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0092] Each embodiment in the present application is described in a related manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the management method, electronic device, electronic device, and readable storage medium embodiment for evaluating automatic seat selection, since they are basically similar to the above-mentioned management method embodiment for automatic seat selection, the description is relatively simple, and the relevant parts can be referred to the partial description of the above-mentioned management method embodiment for automatic seat selection.

[0093] Although the present application is disclosed as above, the present application is not limited thereto. Any person skilled in the art can make various changes and modifications without departing from the spirit and scope of the present application. Therefore, the protection scope of the present application shall be subject to the scope defined by the claims.

Claims

1. A method for managing automatic seat selection, characterized in that: include: Acquire target user information, a target event set matching the target user information, target place information, and a training sample set, wherein the target place information includes location information of the target place, and the training sample set includes historical environmental factor information of the target place and real-time environmental factor information of other places adjacent to the target place; Preprocessing the training sample set to generate a training sample set with target feature data, wherein the target feature data is used to characterize risk factors that affect venue seat pre-arrangement; Acquire a preset seat pre-arrangement management model, wherein the preset seat pre-arrangement management model is generated based on historical environmental factor information of other places; Processing the preset seat pre-arrangement management model based on the training sample set with target feature data to generate a target seat pre-arrangement management model; Processing the target user information to generate physiological parameter information of the target user; Process the target event set that matches the target user information to generate seat pre-arrangement influencing factors; Processing the target location information based on the target seat pre-arrangement management model to generate attribute information of the target location, wherein the attribute information of the target location includes classification information of seats; Processing the attribute information of the target place, the physiological parameter information of the target user and the seat pre-arrangement influencing factor based on the target seat pre-arrangement management model to generate seat pre-arrangement information of the target place; Processing the target user information to generate physiological parameter information of the target user, including: processing the target user information to generate initial facial image information and identity information of the target user, wherein the initial facial image information is facial information of the target user within a preset time period; processing the initial facial image information to generate expression feature influencing factors of the target user; processing the expression feature influencing factors of the target user to generate emotional information of the target user, wherein the emotional information of the target user is used to characterize expression change information of the target user; processing the identity information of the target user to generate real-time vital sign information of the target user; processing based on the real-time vital sign information of the target user and the expression feature influencing factors of the target user to generate physiological parameter information of the target user; Processing a target event set that matches target user information to generate a seat pre-arrangement influence factor, including: processing the target event set that matches target user information to generate type information of the target event, wherein the type information of the target event is used to characterize the warning level of the target event on seat selection; processing the type information of the target event to generate user historical seat pre-arrangement information, wherein the user historical seat pre-arrangement information is used to characterize the seat information allocated to different users when they experience the target event of this type; processing the user historical seat pre-arrangement information to generate a seat selection influence factor and weight information corresponding to the seat selection influence factor; processing the seat selection influence factor and the weight information corresponding to the seat selection influence factor based on a preset seat selection influence feature set to generate a seat pre-arrangement influence factor; The target venue information is processed based on the target seat pre-arrangement management model to generate attribute information of the target venue, including: processing the target venue information based on the target seat pre-arrangement management model to generate monitoring point information, wherein the monitoring point information is seat information located in the target venue; grouping the monitoring point information to generate a plurality of grouping information, wherein the grouping information includes monitoring point information at different distances from a training area; performing feature extraction on the grouping information to generate feature data sets of different groups; processing the feature data sets of different groups to obtain abnormal seat features and correlation co-occurrence frequencies; processing the abnormal seat features and the correlation co-occurrence frequencies to generate correlation information, wherein the correlation information is used to characterize the correlation between seat features at different distances from a training area and the actual situation of seats in the target venue; processing the feature data sets of different groups based on the correlation information to generate attribute information of the target venue.

2. The method according to claim 1, characterized in that Preprocessing the training sample set to generate a training sample set with target feature data includes: Extract features from the training sample set and determine the original feature library; Dividing the original feature library into various feature data sets to generate a training set and a validation set; Based on the classifier, the original feature library is divided into various verification sets for prediction, and the prediction results are determined; Based on the preset algorithm, the original feature library is divided into various training sets for training, and the prediction results of the validation set are obtained; The prediction results and the validation set prediction results are processed to generate target feature data, where the target feature data is used to characterize risk factors that affect venue seat pre-arrangement.

3. The method according to claim 1, characterized in that The target seat pre-arrangement management model is used to process the attribute information of the target place, the physiological parameter information of the target user, and the seat pre-arrangement influencing factor to generate seat pre-arrangement information of the target place, including: Processing the attribute information of the target place based on the target seat pre-arrangement management model to generate a first seat pre-arrangement value of the target seat; Processing the physiological parameter information of the target user and the seat reservation influencing factor based on the target seat reservation management model to generate a second seat reservation value for the target seat; The first seat pre-arrangement value of the target seat and the second seat pre-arrangement value of the target seat are processed to generate seat pre-arrangement information of the target place.

4. The method according to claim 3, characterized in that The method further comprises: processing the attribute information of the target place, the physiological parameter information of the target user and the seat pre-arrangement influencing factor based on the target seat pre-arrangement management model to generate seat pre-arrangement information of the target place; The target seat pre-arrangement management model also includes a calculation formula for obtaining a first seat pre-arrangement value, and the calculation formula includes: ； ； Wherein, P represents the comprehensive seat pre-arrangement value of the target venue; m represents the number of seat groups in the target venue; n represents the number of seats in each group; represents the pre-arranged value of the lth seat in the ith group; k represents the number of seat features in each group; is the weight of the jth feature in the i-th group; represents the value of the lth seat in the i-th group on the j-th feature; The target seat pre-arrangement management model also includes a calculation formula for obtaining a second seat pre-arrangement value, and the calculation formula includes: ； in, is the impact factor of the target user's physiological parameter information on the seat, The impact factor for seat pre-arrangement is is the weight of physiological parameter information, Pre-arrange the weights of influencing factors for seats.

5. An automatic seat selection management device, characterized in that: The device comprises: an acquisition module, used to acquire target user information, a target event set matching the target user information, target venue information and a training sample set, wherein the target venue information includes location information of the target venue, and the training sample set includes historical environmental factor information of the target venue and real-time environmental factor information of other venues adjacent to the target venue; and acquire a preset seat pre-arrangement management model, wherein the preset seat pre-arrangement management model is generated based on the historical environmental factor information of other venues; A processing module is used to pre-process the training sample set to generate a training sample set with target feature data, wherein the target feature data is used to characterize risk factors that affect venue seat pre-arrangement; based on the training sample set with target feature data, the preset seat pre-arrangement management model is processed to generate a target seat pre-arrangement management model; the target user information is processed to generate physiological parameter information of the target user; the target event set matching the target user information is processed to generate seat pre-arrangement influencing factors; based on the target seat pre-arrangement management model, the target venue information is processed to generate attribute information of the target venue, wherein the attribute information of the target venue includes classification information of seats; based on the target seat pre-arrangement management model, the attribute information of the target venue, the physiological parameter information of the target user and the seat pre-arrangement influencing factors are processed to generate seat pre-arrangement information of the target venue; Processing the target user information to generate physiological parameter information of the target user, including: processing the target user information to generate initial facial image information and identity information of the target user, wherein the initial facial image information is facial information of the target user within a preset time period; processing the initial facial image information to generate expression feature influencing factors of the target user; processing the expression feature influencing factors of the target user to generate emotional information of the target user, wherein the emotional information of the target user is used to characterize expression change information of the target user; processing the identity information of the target user to generate real-time vital sign information of the target user; processing based on the real-time vital sign information of the target user and the expression feature influencing factors of the target user to generate physiological parameter information of the target user; Processing a target event set that matches target user information to generate a seat pre-arrangement influence factor, including: processing the target event set that matches target user information to generate type information of the target event, wherein the type information of the target event is used to characterize the warning level of the target event on seat selection; processing the type information of the target event to generate user historical seat pre-arrangement information, wherein the user historical seat pre-arrangement information is used to characterize the seat information allocated to different users when they experience the target event of this type; processing the user historical seat pre-arrangement information to generate a seat selection influence factor and weight information corresponding to the seat selection influence factor; processing the seat selection influence factor and the weight information corresponding to the seat selection influence factor based on a preset seat selection influence feature set to generate a seat pre-arrangement influence factor; The target venue information is processed based on the target seat pre-arrangement management model to generate attribute information of the target venue, including: processing the target venue information based on the target seat pre-arrangement management model to generate monitoring point information, wherein the monitoring point information is seat information located in the target venue; grouping the monitoring point information to generate a plurality of grouping information, wherein the grouping information includes monitoring point information at different distances from a training area; performing feature extraction on the grouping information to generate feature data sets of different groups; processing the feature data sets of different groups to obtain abnormal seat features and correlation co-occurrence frequencies; processing the abnormal seat features and the correlation co-occurrence frequencies to generate correlation information, wherein the correlation information is used to characterize the correlation between seat features at different distances from a training area and the actual situation of seats in the target venue; processing the feature data sets of different groups based on the correlation information to generate attribute information of the target venue.

6. An electronic device, characterized in that: include: a first processor; and a memory for storing executable instructions of the first processor; The first processor is configured to execute the automatic seat selection management method according to any one of claims 1 to 4 by executing the executable instructions.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the second processor, the automatic seat selection management method according to any one of claims 1 to 4 is implemented.

Images