Fume hood control method and system based on regional human body sensing

Abstract

The present invention discloses a fume hood control method and system based on regional human body sensing, the method comprising: obtaining historical sensing records of a target area obtained by sensors arranged at multiple positions; identifying human activity records in the historical sensing records based on a sensing data recognition algorithm; analyzing pedestrian activity patterns corresponding to the target area according to the human activity records and corresponding recording times; and determining the ventilation area and ventilation time of the fume hood in the target area according to the pedestrian activity patterns. It can be seen that the present invention can effectively improve the intelligent degree of fume hood control, achieve safer laboratory ventilation effects, and reduce safety accidents.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a fume hood control method and system based on regional human body sensing. Background Art

[0002] Fume hoods, also known as exhaust hoods, smoke hoods, exhaust hoods, fume cupboards, smoke hoods or fume cupboards, are large equipment in laboratories, especially chemical laboratories. Their purpose is to reduce the contact between experimenters and harmful gases. The working principle is to extract the harmful gases generated during the experiment through an exhaust fan. The intelligence level of fume hoods in the prior art has begun to improve, and sensor technology has also begun to be applied to improve ventilation effects. However, when applying sensor technology, the prior art does not make full use of human behavior recognition in historical sensor records to adjust the laboratory ventilation strategy accordingly. Therefore, the control efficiency is low and the ventilation effect is lacking. It can be seen that the prior art has defects that need to be solved urgently. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide a fume hood control method and system based on regional human body sensing, which can effectively improve the intelligence level of fume hood control, achieve safer laboratory ventilation effects, and reduce safety accidents.

[0004] In order to solve the above technical problems, the first aspect of the present invention discloses a fume hood control method based on regional human body sensing, the method comprising:

[0005] Acquiring historical sensing records of a target area obtained by sensors disposed at a plurality of locations;

[0006] Based on the sensor data recognition algorithm, identifying the human activity records in the historical sensor records;

[0007] Analyzing pedestrian activity patterns corresponding to the target area according to the human activity records and corresponding recording times;

[0008] The ventilation area and ventilation time of the fume hood in the target area are determined according to the pedestrian activity pattern.

[0009] As an optional implementation, in the first aspect of the present invention, the sensor is an infrared sensor; and the position is a ceiling position, a wall position, a cabinet outer position, a cabinet inner position or a floor position.

[0010] As an optional implementation, in the first aspect of the present invention, the identifying of the human activity records in the historical sensor records based on the sensor data recognition algorithm includes:

[0011] Based on a preset data location distance rule, a plurality of sensor records in the historical sensor records are grouped to obtain a plurality of record groups; the location distance between the record locations of any two sensor records in the record group is less than a preset distance threshold;

[0012] For each of the record groups, determining the probability that the record group belongs to human activity and the corresponding user characteristics according to the neural network algorithm;

[0013] All the record groups and corresponding user features whose probabilities are greater than a preset probability threshold are determined as human activity records.

[0014] As an optional implementation, in the first aspect of the present invention, determining the probability that the record group belongs to human activity and the corresponding user characteristics according to the neural network algorithm includes:

[0015] The sensor record values ​​and record positions corresponding to all sensor records in the record group are input as input data to a trained probability prediction neural network to obtain the probability that the record group belongs to a human activity; the probability prediction neural network is trained by a training data set including a plurality of training record groups and corresponding human activity annotations;

[0016] The vector data obtained after the probability prediction neural network vectorizes the input data is input into the trained feature extraction neural network to obtain the user features corresponding to the record group.

[0017] As an optional implementation, in the first aspect of the present invention, the probability prediction neural network is a classifier algorithm model; the feature extraction neural network includes multiple transformer modules.

[0018] As an optional implementation, in the first aspect of the present invention, analyzing the pedestrian activity pattern corresponding to the target area according to the human activity record and the corresponding recording time includes:

[0019] Grouping all sensor records in the human activity record to obtain a plurality of user record groups;

[0020] Determine the user record group including a total number of all sensor records greater than a preset number threshold as a target user record group;

[0021] For each target user record group, connecting the record positions corresponding to the sensor records in the target user record group according to the corresponding record time to obtain a record position line corresponding to the target user record group;

[0022] Calculate the vector average of the user features corresponding to all the sensing records in the target user record group to obtain the corresponding record group user features.

[0023] As an optional implementation, in the first aspect of the present invention, a vector distance between the user features corresponding to any two sensing records in the user record group is less than a preset vector distance threshold.

[0024] As an optional embodiment, in the first aspect of the present invention, determining the ventilation area and ventilation time of the fume hood in the target area according to the pedestrian activity pattern includes:

[0025] Calculate the intersections of all the recorded position lines to obtain a plurality of intersection areas; each of the intersection areas is a circular area with the intersection point of any at least two of the recorded position lines as the center and a radius as a preset value;

[0026] For each intersection area, the average value of the user importance corresponding to the record group user features corresponding to all the record position lines corresponding to the intersection area is calculated to obtain the importance weight corresponding to the intersection area; the user importance is obtained by inputting the record group user features into a preset classifier model to obtain an output user type, and determining the importance of the user type according to the preset correspondence between the type and importance; the user type is a student user, an assistant user, a teacher user, a cleaning staff user or a school supervisor user;

[0027] Calculate the product of the total number of all the record position lines corresponding to the intersection area and the importance weight to obtain the area parameter corresponding to the intersection area;

[0028] Determine the intersection area where the area parameter is greater than a preset parameter threshold as a core ventilation area;

[0029] When the fume hood in the target area is ventilated, each of the core ventilation areas is ventilated first, and the ventilation time of each of the core ventilation areas is greater than that of other areas.

[0030] A second aspect of an embodiment of the present invention discloses a fume hood control system based on regional human body sensing, the system comprising:

[0031] An acquisition module, used for acquiring historical sensing records of a target area acquired by sensors arranged at multiple locations;

[0032] An identification module, used for identifying human activity records in the historical sensor records based on a sensor data identification algorithm;

[0033] An analysis module, used for analyzing the pedestrian activity patterns corresponding to the target area according to the human activity records and the corresponding recording time;

[0034] The determination module is used to determine the ventilation area and ventilation time of the fume hood in the target area according to the pedestrian activity pattern.

[0035] As an optional implementation, in the second aspect of the present invention, the sensor is an infrared sensor; the position is a ceiling position, a wall position, a cabinet outer position, a cabinet inner position or a floor position.

[0036] As an optional implementation, in the second aspect of the present invention, the identification module identifies the specific manner of the human activity record in the historical sensor record based on the sensor data identification algorithm, including:

[0037] Based on a preset data location distance rule, a plurality of sensor records in the historical sensor records are grouped to obtain a plurality of record groups; the location distance between the record locations of any two sensor records in the record group is less than a preset distance threshold;

[0038] For each of the record groups, determining the probability that the record group belongs to human activity and the corresponding user characteristics according to the neural network algorithm;

[0039] All the record groups and corresponding user features whose probabilities are greater than a preset probability threshold are determined as human activity records.

[0040] As an optional implementation, in the second aspect of the present invention, the identification module determines the probability that the record group belongs to human activity and the specific manner of the corresponding user characteristics according to the neural network algorithm, including:

[0041] The sensor record values ​​and record positions corresponding to all sensor records in the record group are input as input data to a trained probability prediction neural network to obtain the probability that the record group belongs to a human activity; the probability prediction neural network is trained by a training data set including a plurality of training record groups and corresponding human activity annotations;

[0042] The vector data obtained after the probability prediction neural network vectorizes the input data is input into the trained feature extraction neural network to obtain the user features corresponding to the record group.

[0043] As an optional implementation, in the second aspect of the present invention, the probability prediction neural network is a classifier algorithm model; the feature extraction neural network includes multiple transformer modules.

[0044] As an optional implementation, in the second aspect of the present invention, the specific manner in which the analysis module analyzes the pedestrian activity pattern corresponding to the target area according to the human activity record and the corresponding recording time includes:

[0045] Grouping all sensor records in the human activity record to obtain a plurality of user record groups;

[0046] Determine the user record group including a total number of all sensor records greater than a preset number threshold as a target user record group;

[0047] For each target user record group, connecting the record positions corresponding to the sensor records in the target user record group according to the corresponding record time to obtain a record position line corresponding to the target user record group;

[0048] Calculate the vector average of the user features corresponding to all the sensing records in the target user record group to obtain the corresponding record group user features.

[0049] As an optional implementation, in the second aspect of the present invention, a vector distance between the user features corresponding to any two sensing records in the user record group is less than a preset vector distance threshold.

[0050] As an optional embodiment, in the second aspect of the present invention, the specific manner in which the determination module determines the ventilation area and ventilation time of the fume hood in the target area according to the pedestrian activity pattern includes:

[0051] Calculate the intersections of all the recorded position lines to obtain a plurality of intersection areas; each of the intersection areas is a circular area with the intersection point of any at least two of the recorded position lines as the center and a radius as a preset value;

[0052] For each intersection area, the average value of the user importance corresponding to the record group user features corresponding to all the record position lines corresponding to the intersection area is calculated to obtain the importance weight corresponding to the intersection area; the user importance is obtained by inputting the record group user features into a preset classifier model to obtain an output user type, and determining the importance of the user type according to the preset correspondence between the type and importance; the user type is a student user, an assistant user, a teacher user, a cleaning staff user or a school supervisor user;

[0053] Calculate the product of the total number of all the record position lines corresponding to the intersection area and the importance weight to obtain the area parameter corresponding to the intersection area;

[0054] Determine the intersection area where the area parameter is greater than a preset parameter threshold as a core ventilation area;

[0055] When the fume hood in the target area is ventilated, each of the core ventilation areas is ventilated first, and the ventilation time of each of the core ventilation areas is greater than that of other areas.

[0056] The third aspect of the present invention discloses another fume hood control system based on regional human body sensing, the system comprising:

[0057] A memory storing executable program code;

[0058] a processor coupled to the memory;

[0059] The processor calls the executable program code stored in the memory to execute part or all of the steps in the fume hood control method based on regional human body sensing disclosed in the first aspect of the present invention.

[0060] The fourth aspect of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute some or all of the steps in the fume hood control method based on regional human body sensing disclosed in the first aspect of the present invention.

[0061] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0062] The present invention can obtain historical sensing records of the target area through sensors arranged at multiple positions, and then identify human activity records based on the historical sensing records to analyze the activity patterns of pedestrians, so as to determine the ventilation area and ventilation time of the fume hood in a targeted manner, thereby effectively improving the intelligence level of fume hood control, achieving safer laboratory ventilation effects, and reducing safety accidents. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0064] Figure 1 It is a flow chart of a fume hood control method based on regional human body sensing disclosed in an embodiment of the present invention.

[0065] Figure 2 It is a structural schematic diagram of a fume hood control system based on regional human body sensing disclosed in an embodiment of the present invention.

[0066] Figure 3It is a structural schematic diagram of another fume hood control system based on regional human body sensing disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0067] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings 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.

[0068] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, device, product or equipment that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or equipment.

[0069] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0070] The present invention discloses a fume hood control method and system based on regional human body sensing, which can obtain historical sensing records of the target area through sensors set at multiple positions, and then identify human activity records based on the historical sensing records to analyze the pedestrian activity patterns, so as to determine the ventilation area and ventilation time of the fume hood in a targeted manner, thereby effectively improving the intelligent degree of fume hood control, achieving a safer laboratory ventilation effect, and reducing safety accidents. The following are detailed descriptions.

[0071] Embodiment 1

[0072] See also Figure 1 , Figure 1 is a flow chart of a fume hood control method based on regional human body sensing disclosed in an embodiment of the present invention. Figure 1The fume hood control method based on regional human body sensing described above can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 1 As shown, the fume hood control method based on regional human body sensing may include the following operations:

[0073] 101. Obtain historical sensing records of a target area obtained by sensors set at multiple locations.

[0074] 102. Based on the sensor data recognition algorithm, human activity records in historical sensor records are identified.

[0075] 103. According to the human activity records and the corresponding recording time, analyze the pedestrian activity patterns corresponding to the target area.

[0076] 104. Determine the ventilation area and ventilation time of the fume hood in the target area based on the pedestrian activity patterns.

[0077] It can be seen that the above-mentioned embodiments of the invention can obtain historical sensor records of the target area through sensors set at multiple positions, and then identify human activity records based on the historical sensor records to analyze the patterns of pedestrian activities, so as to determine the ventilation area and ventilation time of the fume hood in a targeted manner, thereby effectively improving the intelligence level of fume hood control, achieving safer laboratory ventilation effects, and reducing safety accidents.

[0078] As an optional embodiment, in the above steps, the sensor is an infrared sensor; the position is a ceiling position, a wall position, a cabinet outer position, a cabinet inner position or a floor position.

[0079] It can be seen that through the above optional embodiments, the details of the sensor type and setting location are clarified, which facilitates the sensor records to accurately characterize the movement patterns of objects in the area, so as to accurately identify human activity records in the subsequent period, facilitate the subsequent analysis of pedestrian activity patterns and determination of ventilation strategies, and assist in improving the intelligence level of fume hood control, achieving safer laboratory ventilation effects, and reducing safety accidents.

[0080] As an optional embodiment, in the above step, identifying the human activity records in the historical sensor records based on the sensor data recognition algorithm includes:

[0081] Based on a preset data location distance rule, multiple sensor records in the historical sensor records are grouped to obtain multiple record groups; optionally, the location distance between the record locations of any two sensor records in the record group is less than a preset distance threshold;

[0082] For each record group, determine the probability that the record group belongs to human activity and the corresponding user characteristics according to the neural network algorithm;

[0083] All record groups and corresponding user features with probabilities greater than a preset probability threshold are determined as human activity records.

[0084] It can be seen that through the above-mentioned optional embodiments, multiple sensor records in the historical sensor records can be grouped according to distance rules, and then the probability that the record group belongs to human activity and the corresponding user characteristics can be determined through a neural network algorithm to accurately identify human activity records, which is convenient for subsequent analysis of pedestrian activity patterns and determination of ventilation strategies, and assists in improving the intelligence level of fume hood control, achieving safer laboratory ventilation effects, and reducing safety accidents.

[0085] As an optional embodiment, in the above steps, determining the probability that the record group belongs to human activity and the corresponding user characteristics according to the neural network algorithm includes:

[0086] The sensor record values ​​and record positions corresponding to all sensor records in the record group are input as input data to a trained probability prediction neural network to obtain the probability that the record group belongs to a human activity; optionally, the probability prediction neural network is trained by a training data set including a plurality of training record groups and corresponding human activity annotations;

[0087] The vector data obtained by vectorizing the input data through the probability prediction neural network is input into the trained feature extraction neural network to obtain the user features corresponding to the record group.

[0088] It can be seen that through the above-mentioned optional embodiments, it is possible to predict the probability that the record group belongs to human activity and the corresponding user characteristics according to the sensor record values ​​and record positions corresponding to all the sensor records in the record group through the probability prediction neural network and the feature extraction neural network, so as to accurately identify the human activity records in the subsequent time, facilitate the subsequent analysis of pedestrian activity patterns and determination of ventilation strategies, and assist in improving the intelligence level of fume hood control, achieving safer laboratory ventilation effects, and reducing safety accidents.

[0089] As an optional embodiment, in the above steps, the probability prediction neural network is a classifier algorithm model; the feature extraction neural network includes multiple transformer modules.

[0090] It can be seen that through the above optional embodiments, the details of the probability prediction neural network and the feature extraction neural network are clarified, which is convenient for subsequent use to accurately predict the probability that the record group belongs to human activities and the corresponding user characteristics, so as to accurately identify the human activity records in the subsequent period, facilitate the subsequent use to analyze the patterns of pedestrian activities and determine ventilation strategies, and assist in improving the intelligence level of fume hood control, achieving safer laboratory ventilation effects, and reducing safety accidents.

[0091] As an optional embodiment, in the above step, analyzing the pedestrian activity pattern corresponding to the target area according to the human activity records and the corresponding recording time includes:

[0092] Grouping all sensor records in the human activity record to obtain a plurality of user record groups;

[0093] A user record group including a total number of all sensor records greater than a preset number threshold is determined as a target user record group;

[0094] For each target user record group, the record positions corresponding to the sensor records in the target user record group are connected according to the corresponding record time to obtain a record position line corresponding to the target user record group;

[0095] Calculate the vector average of the user features corresponding to all the sensor records in the target user record group to obtain the corresponding record group user features.

[0096] It can be seen that through the above optional embodiments, all sensor records in the human activity records can be grouped and the record quantity can be screened to obtain the target user record group, and then the record position line and record group user characteristics corresponding to each target user record group can be obtained by connecting the record positions and calculating the vector average of the user characteristics, so as to facilitate the subsequent determination of the ventilation strategy, assist in improving the intelligence level of the fume hood control, achieve safer laboratory ventilation effects, and reduce safety accidents.

[0097] As an optional embodiment, in the above steps, the vector distance between the user features corresponding to any two sensing records in the user record group is less than a preset vector distance threshold.

[0098] It can be seen that through the above optional embodiments, the grouping threshold details of the user record group are clarified, which is convenient for the subsequent accurate screening and calculation of the record position lines and record group user characteristics corresponding to the target user record group, and is convenient for the subsequent determination of the ventilation strategy, thereby assisting in improving the intelligence level of fume hood control, achieving safer laboratory ventilation effects, and reducing safety accidents.

[0099] As an optional embodiment, in the above steps, determining the ventilation area and ventilation time of the fume hood in the target area according to the pedestrian activity pattern includes:

[0100] Calculate the intersections of all the recorded position lines to obtain a plurality of intersection areas; optionally, each intersection area is a circular area with the intersection point of any at least two recorded position lines as the center and a radius as a preset value;

[0101] For each intersection area, the average value of the user importance corresponding to the record group user features corresponding to all the record position lines corresponding to the intersection area is calculated to obtain the importance weight corresponding to the intersection area; optionally, the user importance is obtained by inputting the record group user features into a preset classifier model to obtain the output user type, and determining the importance of the user type according to the preset correspondence between the type and importance; the user type is a student user, an assistant user, a teacher user, a cleaning staff user or a school supervisor user;

[0102] Calculate the product of the total number of all record position lines corresponding to the intersection area and the importance weight to obtain the area parameter corresponding to the intersection area;

[0103] The intersection area whose regional parameters are greater than a preset parameter threshold is determined as a core ventilation area;

[0104] When ventilating the fume hoods in the target area, each core ventilation area shall be ventilated first, and the ventilation time of each core ventilation area shall be greater than that of other areas.

[0105] It can be seen that through the above optional embodiments, it is possible to determine the intersection area of ​​the recorded position lines and calculate the regional parameters according to the weight rules, and screen the core ventilation areas based on the regional parameters to determine the ventilation strategy, thereby improving the intelligence level of fume hood control, achieving safer laboratory ventilation effects, and reducing safety accidents.

[0106] Embodiment 2

[0107] See also Figure 2 , Figure 2 : is a schematic diagram of a fume hood control system based on regional human body sensing disclosed in an embodiment of the present invention. Figure 2 The fume hood control system based on regional human body sensing described above can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 2 As shown, the fume hood control system based on regional human body sensing may include:

[0108] The acquisition module 201 is used to acquire historical sensing records of a target area obtained by sensors arranged at multiple locations.

[0109] The identification module 202 is used to identify human activity records in historical sensor records based on a sensor data identification algorithm.

[0110] The analysis module 203 is used to analyze the pedestrian activity patterns corresponding to the target area according to the human activity records and the corresponding recording time.

[0111] The determination module 204 is used to determine the ventilation area and ventilation time of the fume hood in the target area according to the pedestrian activity pattern.

[0112] It can be seen that the above-mentioned embodiments of the invention can obtain historical sensor records of the target area through sensors set at multiple positions, and then identify human activity records based on the historical sensor records to analyze the patterns of pedestrian activities, so as to determine the ventilation area and ventilation time of the fume hood in a targeted manner, thereby effectively improving the intelligence level of fume hood control, achieving safer laboratory ventilation effects, and reducing safety accidents.

[0113] As an optional embodiment, the sensor is an infrared sensor; the location is a ceiling location, a wall location, a cabinet outer location, a cabinet inner location or a floor location.

[0114] It can be seen that through the above optional embodiments, the details of the sensor type and setting location are clarified, which facilitates the sensor records to accurately characterize the movement patterns of objects in the area, so as to accurately identify human activity records in the subsequent period, facilitate the subsequent analysis of pedestrian activity patterns and determination of ventilation strategies, and assist in improving the intelligence level of fume hood control, achieving safer laboratory ventilation effects, and reducing safety accidents.

[0115] As an optional embodiment, the identification module identifies the specific manner of human activity records in historical sensor records based on the sensor data identification algorithm, including:

[0116] Based on a preset data location distance rule, multiple sensor records in the historical sensor records are grouped to obtain multiple record groups; optionally, the location distance between the record locations of any two sensor records in the record group is less than a preset distance threshold;

[0117] For each record group, determine the probability that the record group belongs to human activity and the corresponding user characteristics according to the neural network algorithm;

[0118] All record groups and corresponding user features with probabilities greater than a preset probability threshold are determined as human activity records.

[0119] It can be seen that through the above-mentioned optional embodiments, multiple sensor records in the historical sensor records can be grouped according to distance rules, and then the probability that the record group belongs to human activity and the corresponding user characteristics can be determined through a neural network algorithm to accurately identify human activity records, which is convenient for subsequent analysis of pedestrian activity patterns and determination of ventilation strategies, and assists in improving the intelligence level of fume hood control, achieving safer laboratory ventilation effects, and reducing safety accidents.

[0120] As an optional embodiment, the identification module determines the probability that the record group belongs to human activity and the specific manner of the corresponding user characteristics according to the neural network algorithm, including:

[0121] The sensor record values ​​and record positions corresponding to all sensor records in the record group are input as input data to a trained probability prediction neural network to obtain the probability that the record group belongs to a human activity; optionally, the probability prediction neural network is trained by a training data set including a plurality of training record groups and corresponding human activity annotations;

[0122] The vector data obtained by vectorizing the input data through the probability prediction neural network is input into the trained feature extraction neural network to obtain the user features corresponding to the record group.

[0123] It can be seen that through the above-mentioned optional embodiments, it is possible to predict the probability that the record group belongs to human activity and the corresponding user characteristics according to the sensor record values ​​and record positions corresponding to all the sensor records in the record group through the probability prediction neural network and the feature extraction neural network, so as to accurately identify the human activity records in the subsequent time, facilitate the subsequent analysis of pedestrian activity patterns and determination of ventilation strategies, and assist in improving the intelligence level of fume hood control, achieving safer laboratory ventilation effects, and reducing safety accidents.

[0124] As an optional embodiment, the probability prediction neural network is a classifier algorithm model; the feature extraction neural network includes multiple transformer modules.

[0125] It can be seen that through the above optional embodiments, the details of the probability prediction neural network and the feature extraction neural network are clarified, which is convenient for subsequent use to accurately predict the probability that the record group belongs to human activities and the corresponding user characteristics, so as to accurately identify the human activity records in the subsequent period, facilitate the subsequent use to analyze the patterns of pedestrian activities and determine ventilation strategies, and assist in improving the intelligence level of fume hood control, achieving safer laboratory ventilation effects, and reducing safety accidents.

[0126] As an optional embodiment, the specific manner in which the analysis module analyzes the pedestrian activity pattern corresponding to the target area according to the human activity records and the corresponding recording time includes:

[0127] Grouping all sensor records in the human activity record to obtain a plurality of user record groups;

[0128] A user record group including a total number of all sensor records greater than a preset number threshold is determined as a target user record group;

[0129] For each target user record group, the record positions corresponding to the sensor records in the target user record group are connected according to the corresponding record time to obtain a record position line corresponding to the target user record group;

[0130] Calculate the vector average of the user features corresponding to all the sensor records in the target user record group to obtain the corresponding record group user features.

[0131] It can be seen that through the above optional embodiments, all sensor records in the human activity records can be grouped and the record quantity can be screened to obtain the target user record group, and then the record position line and record group user characteristics corresponding to each target user record group can be obtained by connecting the record positions and calculating the vector average of the user characteristics, so as to facilitate the subsequent determination of the ventilation strategy, assist in improving the intelligence level of the fume hood control, achieve safer laboratory ventilation effects, and reduce safety accidents.

[0132] As an optional embodiment, a vector distance between the user features corresponding to any two sensing records in the user record group is less than a preset vector distance threshold.

[0133] It can be seen that through the above optional embodiments, the grouping threshold details of the user record group are clarified, which is convenient for the subsequent accurate screening and calculation of the record position lines and record group user characteristics corresponding to the target user record group, and is convenient for the subsequent determination of the ventilation strategy, thereby assisting in improving the intelligence level of fume hood control, achieving safer laboratory ventilation effects, and reducing safety accidents.

[0134] As an optional embodiment, the specific method of determining the ventilation area and ventilation time of the fume hood in the target area according to the pedestrian activity pattern by the determination module includes:

[0135] Calculate the intersections of all the recorded position lines to obtain a plurality of intersection areas; optionally, each intersection area is a circular area with the intersection point of any at least two recorded position lines as the center and a radius as a preset value;

[0136] For each intersection area, the average value of the user importance corresponding to the record group user features corresponding to all the record position lines corresponding to the intersection area is calculated to obtain the importance weight corresponding to the intersection area; optionally, the user importance is obtained by inputting the record group user features into a preset classifier model to obtain the output user type, and determining the importance of the user type according to the preset correspondence between the type and importance; the user type is a student user, an assistant user, a teacher user, a cleaning staff user or a school supervisor user;

[0137] Calculate the product of the total number of all record position lines corresponding to the intersection area and the importance weight to obtain the area parameter corresponding to the intersection area;

[0138] The intersection area whose regional parameters are greater than a preset parameter threshold is determined as a core ventilation area;

[0139] When ventilating the fume hoods in the target area, each core ventilation area shall be ventilated first, and the ventilation time of each core ventilation area shall be greater than that of other areas.

[0140] It can be seen that through the above optional embodiments, it is possible to determine the intersection area of ​​the recorded position lines and calculate the regional parameters according to the weight rules, and screen the core ventilation areas based on the regional parameters to determine the ventilation strategy, thereby improving the intelligence level of fume hood control, achieving safer laboratory ventilation effects, and reducing safety accidents.

[0141] Embodiment 3

[0142] See also Figure 3 , Figure 3 Another fume hood control system based on regional human body sensing disclosed in an embodiment of the present invention. Figure 3 The fume hood control system based on regional human body sensing is applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 3 As shown, the fume hood control system based on regional human body sensing may include:

[0143] A memory 301 storing executable program codes;

[0144] a processor 302 coupled to the memory 301;

[0145] The processor 302 calls the executable program code stored in the memory 301 to execute the steps of the fume hood control method based on regional human body sensing described in the first embodiment.

[0146] Embodiment 4

[0147] An embodiment of the present invention discloses a computer-readable storage medium storing a computer program for electronic data exchange, wherein the computer program enables a computer to execute the steps of the fume hood control method based on regional human body sensing described in the first embodiment.

[0148] Embodiment 5

[0149] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute the steps of the fume hood control method based on regional human body sensing described in Example 1.

[0150] The above describes specific embodiments of the present specification, and other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily have to be performed in the specific order or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0151] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0152] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0153] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification may be in the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the embodiments of this specification may be in the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0154] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0155] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0156] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0157] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0158] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0159] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0160] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0161] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0162] Each embodiment in this specification is described in a progressive 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 system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0163] Finally, it should be noted that the fume hood control method and system based on regional human body sensing disclosed in the embodiment of the present invention discloses only the preferred embodiments of the present invention, which are only used to illustrate the technical scheme of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, it should be understood by those skilled in the art that the technical schemes described in the aforementioned embodiments can still be modified, or some of the technical features therein can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical schemes from the spirit and scope of the technical schemes of the various embodiments of the present invention.

Claims

1. A fume hood control method based on regional human body sensing, characterized in that: The method comprises: Acquiring historical sensing records of a target area obtained by sensors disposed at a plurality of locations; Based on the sensor data recognition algorithm, human activity records in the historical sensor records are identified, including: Based on a preset data location distance rule, a plurality of sensor records in the historical sensor records are grouped to obtain a plurality of record groups; the location distance between the record locations of any two sensor records in the record group is less than a preset distance threshold; For each of the record groups, determining the probability that the record group belongs to human activity and the corresponding user characteristics according to the neural network algorithm; Determine all the record groups and corresponding user features whose probabilities are greater than a preset probability threshold as human activity records; Analyzing pedestrian activity patterns corresponding to the target area according to the human activity records and corresponding recording times, including: Grouping all sensor records in the human activity record to obtain a plurality of user record groups; Determine the user record group including a total number of all sensor records greater than a preset number threshold as a target user record group; For each target user record group, connecting the record positions corresponding to the sensor records in the target user record group according to the corresponding record time to obtain a record position line corresponding to the target user record group; Calculate the vector average of the user features corresponding to all sensor records in the target user record group to obtain the corresponding record group user features; Determining the ventilation area and ventilation time of the fume hood in the target area according to the pedestrian activity pattern includes: Calculate the intersections of all the recorded position lines to obtain a plurality of intersection areas; each of the intersection areas is a circular area with the intersection point of any at least two of the recorded position lines as the center and a radius as a preset value; For each intersection area, the average value of the user importance corresponding to the record group user features corresponding to all the record position lines corresponding to the intersection area is calculated to obtain the importance weight corresponding to the intersection area; the user importance is obtained by inputting the record group user features into a preset classifier model to obtain an output user type, and determining the importance of the user type according to the preset correspondence between the type and importance; the user type is a student user, an assistant user, a teacher user, a cleaning staff user or a school supervisor user; Calculate the product of the total number of all the record position lines corresponding to the intersection area and the importance weight to obtain the area parameter corresponding to the intersection area; Determine the intersection area where the area parameter is greater than a preset parameter threshold as a core ventilation area; When the fume hood in the target area is ventilated, each of the core ventilation areas is ventilated first, and the ventilation time of each of the core ventilation areas is greater than that of other areas.

2. The fume hood control method based on regional human body sensing according to claim 1 is characterized in that: The sensor is an infrared sensor; the position is a ceiling position, a wall position, a cabinet outer position, a cabinet inner position or a floor position.

3. The fume hood control method based on regional human body sensing according to claim 1 is characterized in that: Determining the probability that the record group belongs to human activity and the corresponding user characteristics according to the neural network algorithm includes: The sensor record values ​​and record positions corresponding to all sensor records in the record group are input as input data to a trained probability prediction neural network to obtain the probability that the record group belongs to a human activity; the probability prediction neural network is trained by a training data set including a plurality of training record groups and corresponding human activity annotations; The vector data obtained after the probability prediction neural network vectorizes the input data is input into the trained feature extraction neural network to obtain the user features corresponding to the record group.

4. The fume hood control method based on regional human body sensing according to claim 3 is characterized in that: The probability prediction neural network is a classifier algorithm model; the feature extraction neural network includes multiple transformer modules.

5. The fume hood control method based on regional human body sensing according to claim 1 is characterized in that: A vector distance between the user features corresponding to any two sensing records in the user record group is less than a preset vector distance threshold.

6. A fume hood control system based on regional human body sensing, characterized in that: The system comprises: An acquisition module, used for acquiring historical sensing records of a target area acquired by sensors arranged at multiple locations; The recognition module is used to recognize the human activity records in the historical sensing records based on the sensing data recognition algorithm, including: Based on a preset data location distance rule, a plurality of sensor records in the historical sensor records are grouped to obtain a plurality of record groups; the location distance between the record locations of any two sensor records in the record group is less than a preset distance threshold; For each of the record groups, determining the probability that the record group belongs to human activity and the corresponding user characteristics according to the neural network algorithm; Determine all the record groups and corresponding user features whose probabilities are greater than a preset probability threshold as human activity records; The analysis module is used to analyze the pedestrian activity pattern corresponding to the target area according to the human activity records and the corresponding recording time, including: Grouping all sensor records in the human activity record to obtain a plurality of user record groups; Determine the user record group including a total number of all sensor records greater than a preset number threshold as a target user record group; For each target user record group, connecting the record positions corresponding to the sensor records in the target user record group according to the corresponding record time to obtain a record position line corresponding to the target user record group; Calculate the vector average of the user features corresponding to all sensor records in the target user record group to obtain the corresponding record group user features; A determination module, used to determine the ventilation area and ventilation time of the fume hood in the target area according to the pedestrian activity pattern, including: Calculate the intersections of all the recorded position lines to obtain a plurality of intersection areas; each of the intersection areas is a circular area with the intersection point of any at least two of the recorded position lines as the center and a radius as a preset value; For each intersection area, the average value of the user importance corresponding to the record group user features corresponding to all the record position lines corresponding to the intersection area is calculated to obtain the importance weight corresponding to the intersection area; the user importance is obtained by inputting the record group user features into a preset classifier model to obtain an output user type, and determining the importance of the user type according to the preset correspondence between the type and importance; the user type is a student user, an assistant user, a teacher user, a cleaning staff user or a school supervisor user; Calculate the product of the total number of all the record position lines corresponding to the intersection area and the importance weight to obtain the area parameter corresponding to the intersection area; Determine the intersection area where the area parameter is greater than a preset parameter threshold as a core ventilation area; When the fume hood in the target area is ventilated, each of the core ventilation areas is ventilated first, and the ventilation time of each of the core ventilation areas is greater than that of other areas.

7. A fume hood control system based on regional human body sensing, characterized in that: The system comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the fume hood control method based on regional human body sensing as described in any one of claims 1 to 5.

Images