Detection method and device suitable for detecting whether people exist in elevator or not and electronic equipment

Abstract

The invention provides a detection method and device suitable for detecting whether a person exists in an elevator or not and electronic equipment, and can be applied to the technical field of Internet of Things and artificial intelligence. The method comprises the steps that data filtering is conducted on a sensor data set detected by a sensor which is arranged in an elevator car and suitable for detecting the human body, and a filtered data set is obtained; under the condition that the data size of the filtering data set is larger than the first preset data size, filtering data equal to the first preset data size is selected from the filtering data set, and an effective data set is obtained; determining a prediction data group according to the effective data group; according to a preset weight, performing weighted summation on the prediction data set to obtain detection data; and according to the detection data, whether people exist in the car is determined.

Description

Technical Field

[0001] The present disclosure relates to the technical fields of the Internet of Things and artificial intelligence, and particularly to a detection method, device, and electronic device suitable for detecting whether there is a person in an elevator. Background Art

[0002] At present, elevators are widely used in various places. Due to the large number of users, complex scenarios, and frequent use of elevators, it is inevitable that failures will occur and people will be trapped, threatening the safety of passengers. Therefore, it is necessary to timely monitor the elevator status and the conditions of the people in the elevator to rescue the trapped people in time after the elevator fails and ensure the safety of passengers' lives.

[0003] Related technologies usually set up cameras in the elevator carriages and monitor the situations inside the elevators through logistics personnel to ensure timely grasp of elevator accident problems. However, monitoring through camera images has the problem of infringing on the privacy of the people inside the elevator, and the installation and wiring steps of the cameras inside the elevator are cumbersome, increasing the cost. Summary of the Invention

[0004] In view of the above problems, the present disclosure provides a detection method, device, and electronic device suitable for detecting whether there is a person in an elevator.

[0005] According to a first aspect of the present disclosure, there is provided a detection method suitable for detecting whether there is a person in an elevator, including: filtering sensor data groups detected by sensors suitable for detecting the human body provided in the elevator car to remove incorrect data that appears in the data groups due to vibrations generated after the car door closes, so as to obtain filtered data groups; in the case where the data volume of the filtered data groups is greater than a first preset data volume, selecting filtered data equal to the first preset data volume from the filtered data groups to obtain valid data groups; determining predicted data groups according to the valid data groups; performing weighted summation on the predicted data groups according to preset weights to obtain detection data, where the preset weight corresponding to the i-th valid data in the predicted data groups is determined by taking a preset base greater than 1 as the base and i as the exponent; and determining whether there is a person in the car according to the detection data.

[0006] According to an embodiment of the present disclosure, filtering the sensor data groups detected by sensors suitable for detecting the human body provided in the elevator car includes: performing sampling analysis on the data groups to determine an error-prone time range of the influence of the car door closing on the sensors; and filtering the sensor data within the error-prone time range in the data groups to obtain filtered data groups. Preferably, the error-prone time range is 3-8 seconds after receiving the car door closed in-place signal.

[0007] According to an embodiment of the present disclosure, a detection method applicable to detecting whether there is a person in an elevator further includes: when the data volume of the filtered data group is less than a second preset data volume, completing the filtered data group so that the data volume after completion is equal to the second preset data volume, to obtain an effective data group, where a first preset data volume is greater than the second preset data volume.

[0008] According to an embodiment of the present disclosure, completing the filtered data group so that the data volume after completion is equal to the second preset data volume includes: using a logistic regression model to predict the next filtered data of the filtered data group to obtain supplementary data; supplementing the supplementary data to the filtered data group to obtain a completed data group; and when the data volume of the completed data group is greater than the second preset data volume, replacing the filtered data group with the completed data group.

[0009] According to an embodiment of the present disclosure, using a logistic regression model to predict the next filtered data of the filtered data group to obtain supplementary data includes: training the logistic regression model h θ (x) using formula (1):

[0010]

[0011] where x represents a vector composed of the filtered data in the filtered data group, and θ T represents the predicted parameter obtained by training; supplementing 0 to the filtered data group to obtain a verification data group; calculating the verification data group using the logistic regression model to obtain a verification result; when the verification result is greater than 0.5, determining the supplementary data as 0; and when the verification result is less than 0.5, determining the supplementary data as 1.

[0012] According to an embodiment of the present disclosure, the effective data group consists of 0 and 1, where 0 indicates that there is no person in the car and 1 indicates that there is a person in the car. According to the effective data group, determining a predicted data group includes: using -1 as the base and the i-th effective data minus 1 as the exponent to calculate the predicted data corresponding to the i-th effective data; and determining the predicted data group according to multiple predicted data and the positions of the multiple predicted data corresponding to the effective data in the effective data group.

[0013] According to an embodiment of the present disclosure, using -1 as the base and the i-th effective data minus 1 as the exponent to calculate the predicted data corresponding to the i-th effective data includes: calculating the predicted data P i corresponding to the i-th effective data using formula (2):

[0014]

[0015] where x i represents the value of the i-th effective data.

[0016] According to an embodiment of the present disclosure, determining whether there is a person in the car based on detection data includes: determining that there is a person in the car when the detection data is greater than 0; and determining that there is no person in the car when the detection data is less than 0.

[0017] According to an embodiment of the present disclosure, the detection method applicable to detecting whether there is a person in an elevator further includes: performing real-time calculation based on the sensor data collected in real time after the car door is closed to obtain an updated detection result of human body detection; and updating the detection result with the updated detection result when the updated detection result is different from the detection result.

[0018] According to an embodiment of the present disclosure, when the data volume of the sensor filtered data group is greater than a first preset data volume, selecting the first preset data volume of sensor filtered data from the sensor filtered data group to obtain an effective data group, including: selecting the latest first preset data volume of sensor filtered data from the sensor filtered data group according to the time sequence to obtain an effective data group.

[0019] According to an embodiment of the present disclosure, the sensor includes an infrared sensor and a microwave sensor, and is used to sense the presence of a human body through the limb movement, breathing, heartbeat, etc. of the human body in a static environment.

[0020] A second aspect of the present disclosure provides a detection device applicable to detecting whether there is a person in an elevator, including:

[0021] A data filtering module, applicable to filtering the sensor data group detected by the sensor applicable to detecting the human body provided in the elevator car to remove the error data appearing in the data group caused by the vibration generated after the car door is closed, and obtaining a filtered data group;

[0022] A data selection module, applicable to selecting the filtered data equal to the first preset data volume from the filtered data group when the data volume of the filtered data group is greater than the first preset data volume to obtain an effective data group;

[0023] A data determination module, applicable to determining a prediction data group according to the effective data group;

[0024] A data summation module, applicable to performing weighted summation on the prediction data group according to a preset weight to obtain detection data, where the preset weight corresponding to the i-th effective data in the prediction data group is determined by using a preset base greater than 1 as the base and i as the exponent; and

[0025] A judgment module, applicable to determining whether there is a person in the car according to the detection data.

[0026] According to an embodiment of the present disclosure, the data filtering module is further adapted to sample and analyze a data group to determine an error-prone time range of the influence on the sensor after the car door is closed; and filter the sensor data within the error-prone time range in the data group to obtain a filtered data group. Preferably, the error-prone time range is 3 to 8 seconds after receiving the car door closed in-place signal.

[0027] According to an embodiment of the present disclosure, a detection device adapted to detect whether there is a person in an elevator further includes:

[0028] A data completion module, adapted to, when the amount of data in the filtered data group is less than a second preset amount of data, complete the filtered data group so that the amount of data after completion is equal to the second preset amount of data to obtain a valid data group.

[0029] According to an embodiment of the present disclosure, the data completion module is further adapted to use a logistic regression model to predict the next filtered data of the filtered data group to obtain supplementary data; supplement the supplementary data to the filtered data group to obtain a completed data group; and when the amount of data in the completed data group is greater than the second preset amount of data, replace the filtered data group with the completed data group.

[0030] According to an embodiment of the present disclosure, the valid data group consists of 0 and 1. Among them, 0 indicates that there is no person in the car, and 1 indicates that there is a person in the car. According to the valid data group, determining a predicted data group includes: calculating the predicted data corresponding to the i-th valid data with -1 as the base and the i-th valid data - 1 as the exponent; and determining the predicted data group according to multiple predicted data and the positions of the multiple predicted data corresponding to the valid data in the valid data group.

[0031] According to an embodiment of the present disclosure, the sensor includes an infrared sensor and a microwave sensor, and is used to sense the presence of a person through the limb movement, breathing, heartbeat, etc. of the person in a static environment.

[0032] A third aspect of the present disclosure provides an electronic device, including: one or more processors; a memory for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors are caused to execute the above method.

[0033] A fourth aspect of the present disclosure further provides a computer-readable storage medium, on which an executable instruction is stored, and when the instruction is executed by a processor, the processor is caused to execute the above method.

[0034] A fifth aspect of the present disclosure further provides a computer program product, including a computer program, and when the computer program is executed by a processor, the above method is implemented.

[0035] According to an embodiment of the present disclosure, error data in a data group detected by a sensor is removed through data filtering to obtain a filtered data group, which can avoid the influence of error data caused by the vibration generated when the elevator car door closes on the detection result. According to the comparison result between the data volume of the filtered data group and a first preset data volume, it is determined to select part of the data from the filtered data group to obtain a valid data group. The predicted data group obtained from the valid data group is weighted and summed using a preset weight to determine the detection data. Since the preset weight is determined with a preset base greater than 1 as the base and the position of the predicted data in the predicted data group as the exponent, it can be ensured that the predicted data at the later position in the predicted data group has a greater weight on the result of the detection data, thereby ensuring the correctness of the detection data and improving the detection accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Through the following description of the embodiments of the present disclosure with reference to the accompanying drawings, the above content and other objects, features, and advantages of the present disclosure will become clearer. In the drawings:

[0037] Figure 1 FIG. schematically shows an application scenario diagram of a detection method, device, and electronic device suitable for detecting whether there is someone in an elevator according to an embodiment of the present disclosure;

[0038] Figure 2 FIG. schematically shows a simple three-dimensional diagram inside an elevator car according to an embodiment of the present disclosure;

[0039] Figure 3 FIG. schematically shows a flowchart of a detection method suitable for detecting whether there is someone in an elevator according to an embodiment of the present disclosure;

[0040] Figure 4 FIG. schematically shows a structural block diagram of a detection device suitable for detecting whether there is someone in an elevator according to an embodiment of the present disclosure; and

[0041] Figure 5 FIG. schematically shows a block diagram of an electronic device suitable for implementing a detection method for detecting whether there is someone in an elevator according to an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0042] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are merely exemplary and are not intended to limit the scope of the present disclosure. In the following detailed description, for the purpose of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, obviously, one or more embodiments can also be implemented without these specific details. In addition, in the following description, descriptions of well-known structures and technologies are omitted to avoid unnecessarily confusing the concepts of the present disclosure.

[0043] The terms used herein are for describing specific embodiments only and are not intended to limit the present disclosure. The terms "including", "comprising" and the like used herein indicate the presence of the described features, steps, operations and / or components, but do not preclude the presence or addition of one or more other features, steps, operations or components.

[0044] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those of ordinary skill in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification, and should not be interpreted in an idealized or overly rigid manner.

[0045] In cases where expressions such as "at least one of A, B, and C" are used, generally, it should be interpreted according to the meaning commonly understood by those of ordinary skill in the art (for example, "a system having at least one of A, B, and C" should include, but not be limited to, a system having only A, only B, only C, having A and B, having A and C, having B and C, and / or having A, B, and C).

[0046] In the technical solution of the present invention, the user information involved (including but not limited to user image information, user device information, such as location information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) are all information and data authorized by the user or fully authorized by all parties. Moreover, the processing of relevant data, such as collection, storage, use, processing, transmission, provision, disclosure, and application, all comply with the relevant laws, regulations, and standards of the relevant countries and regions, adopt necessary confidentiality measures, do not violate public order and good customs, and provide corresponding operation entrances for users to choose to authorize or reject.

[0047] In the process of implementing the present disclosure, it is found that in related technologies, infrared sensors, microwave sensors, radar sensors, etc. can be installed in the elevator car to detect whether there is anyone in the elevator. However, radar sensors and microwave sensors are easily affected by the vibration during the operation of the elevator itself, and the accuracy of the detection results is not high. Infrared sensors are easily affected by the environment and are insensitive to the induction of the human body in summer, which is likely to cause false alarms.

[0048] Embodiments of the present disclosure provide a detection method applicable to detecting whether there is a person in an elevator, including: filtering sensor data groups detected by sensors applicable to detecting the human body provided in an elevator car to remove error data that appears in the data groups due to vibrations generated after the car door closes, obtaining a filtered data group; in a case where the amount of data in the filtered data group is greater than a first preset amount of data, selecting filtered data equal to the first preset amount of data from the filtered data group to obtain a valid data group; determining a predicted data group according to the valid data group; performing weighted summation on the predicted data group according to a preset weight to obtain detection data, where the preset weight corresponding to the i-th valid data in the predicted data group is determined by using a preset base greater than 1 as the base and i as the exponent; and determining whether there is a person in the car according to the detection data.

[0049] Figure 1 FIG. schematically shows an application scenario diagram of a detection method, device, and electronic device applicable to detecting whether there is a person in an elevator according to an embodiment of the present disclosure.

[0050] As Figure 1 shown, the application scenario 100 according to this embodiment may include a first elevator 101, a second elevator 102, a third elevator 103, a network 104, and a server 105. The network 104 is used as a medium for providing a communication link between the first elevator 101, the second elevator 102, the third elevator 103, and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, etc.

[0051] Sensors may be installed on the first elevator 101, the second elevator 102, and the third elevator 103. Users may ride in at least one of the first elevator 101, the second elevator 102, and the third elevator 103 and interact with the server 105 through the network 104 to send sensor data and the like.

[0052] The first elevator 101, the second elevator 102, and the third elevator 103 may be elevators of any brand installed in various places.

[0053] The server 105 may be a server for processing data, such as processing sensor data of passengers riding in the first elevator 101, the second elevator 102, and the third elevator 103.

[0054] Note that the detection method provided by the embodiments of the present disclosure for detecting whether there is a person in an elevator can generally be executed by the server 105. Correspondingly, the detection device provided by the embodiments of the present disclosure for detecting whether there is a person in an elevator can generally be disposed in the server 105. The detection method provided by the embodiments of the present disclosure for detecting whether there is a person in an elevator can also be executed by a server or a server cluster different from the server 105 and capable of communicating with the first elevator 101, the second elevator 102, the third elevator 103, and / or the server 105. Correspondingly, the detection device provided by the embodiments of the present disclosure for detecting whether there is a person in an elevator can also be disposed in a server or a server cluster different from the server 105 and capable of communicating with the first elevator 101, the second elevator 102, the third elevator 103, and / or the server 105.

[0055] It should be understood that Figure 1 the numbers of elevators, networks, and servers in

[0056] are merely illustrative. According to the implementation requirements, any number of elevators, networks, and servers can be provided. Figure 1 Based on the scenario described below Figures 2 to 3 the detection method provided by the embodiments of the present disclosure for detecting whether there is a person in an elevator will be described in detail through

[0057] Figure 2 A schematic three-dimensional diagram of the interior of an elevator car according to an embodiment of the present disclosure is schematically shown.

[0058] As Figure 2 shown, any one of the first elevator 101, the second elevator 102, and the third elevator 103 includes an elevator car 1, a sensor 2 disposed above the elevator car 1, including an infrared sensor and a microwave sensor, for sensing the presence of a person through the limb movement, breathing, heartbeat, etc. of the person in a static environment, and a non-metal plate 3.

[0059] Figure 3 A flowchart of the detection method provided by the embodiments of the present disclosure for detecting whether there is a person in an elevator is schematically shown.

[0060] As Figure 3 shown, the detection method provided by this embodiment for detecting whether there is a person in an elevator includes operations S310 to S350.

[0061] In operation S310, the sensor data set detected by the sensor for detecting a person disposed in the elevator car is filtered to remove the error data appearing in the data set caused by the vibration generated after the car door is closed, and a filtered data set is obtained.

[0062] In operation S320, when the data volume of the filtered data group is greater than the first preset data volume, filtered data equal to the first preset data volume is selected from the filtered data group to obtain a valid data group.

[0063] In operation S330, a predicted data group is determined according to the valid data group.

[0064] In operation S340, weighted summation is performed on the predicted data group according to preset weights to obtain detection data, where the preset weight corresponding to the i-th valid data in the predicted data group is determined by taking a preset base greater than 1 as the base and i as the exponent.

[0065] In operation S350, it is determined whether there is someone in the elevator car according to the detection data.

[0066] According to an embodiment of the present disclosure, as Figure 2 shown, the sensor 2 can be arranged on the top of the elevator car 1 or can be hidden and installed behind the non-metal plate 3, where the non-metal plate 3 can be an acrylic plate for the interior of the elevator car, etc. The sensor can sense vibrations, so the vibrations generated during the opening and closing of the elevator car door and during operation will affect the accuracy of the sensor data detected by the sensor. Through data filtering, the error data caused by the vibrations generated after the car door is closed can be removed. The data group can include the data collected starting from after the elevator car door is closed. The filtered data group can be obtained after removing the error data in the data group.

[0067] According to an embodiment of the present disclosure, when the data volume of the filtered data group is greater than the first preset data volume, since the data volume is too large, it will lead to an excessive calculation amount, thereby reducing the detection efficiency. Therefore, a valid data group can be obtained by selecting filtered data equal to the first preset data volume from the filtered data group.

[0068] According to an embodiment of the present disclosure, according to the value of the valid data in the valid data group, the sign of the predicted data at the corresponding position in the predicted data group can be determined. The preset weight is set according to the position of the predicted data in the preset data group. For example, the preset base greater than 1 can be taken as 1.19, and the preset weight corresponding to the i-th valid data in the predicted data group is 1.19 i . After determining the preset weight, weighted summation can be performed according to the predicted data and the preset weight at each position to determine the detection data.

[0069] According to an embodiment of the present disclosure, it can be determined whether there is someone in the elevator car according to the value of the detection data. When there is someone in the elevator car, it is possible to determine whether to contact the car by voice, whether to alarm, etc. according to the duration of someone in the car, so as to ensure that the elevator car is discovered in time in case of entrapment and ensure the safety of the elevator.

[0070] According to an embodiment of the present disclosure, error data in the data group detected by the sensor is removed through data filtering to obtain a filtered data group, which can avoid the influence of error data caused by the vibration generated when the car door closes on the detection result. According to the comparison result between the data volume of the filtered data group and the first preset data volume, it is determined to select part of the data from the filtered data group to obtain a valid data group. The predicted data group obtained according to the valid data group is weighted and summed using a preset weight to determine the detection data. Since the preset weight is determined by using a preset base greater than 1 as the base and the position of the predicted data in the predicted data group as the exponent, it can be ensured that the predicted data at the end of the predicted data group has a greater weight on the result of the detection data, thereby ensuring the correctness of the detection data and improving the detection accuracy.

[0071] According to an embodiment of the present disclosure, data filtering of the sensor data group detected by the sensor applicable to detecting the human body provided in the elevator car includes: performing sampling analysis on the data group to determine the error-prone time range of the influence on the sensor after the car door closes; and filtering the sensor data within the error-prone time range in the data group to obtain a filtered data group. Preferably, the error-prone time range is 3 - 8 seconds after receiving the car door closing in-place signal.

[0072] According to an embodiment of the present disclosure, sensor data groups detected by sensors applicable to detecting the human body in multiple scenarios can be collected, as shown in Table 1 - Table 2.

[0073] Table 1

[0074]

[0075] Table 2

[0076]

[0077]

[0078] According to an embodiment of the present disclosure, the error-prone time range can be the time range prone to error data caused by the vibration generated after the car door closes. Table 1 shows the sensor data group when the elevator door is open, no one enters, and the elevator runs after the door closes. Table 2 shows the sensor data group when the elevator door is open, someone enters, and the elevator runs after the door closes. Since no one will be trapped in the elevator when the door is open, it is only necessary to detect whether there is someone in the elevator through a detection method after the elevator door closes. By comparing the data readings in the data group with the actual situation of whether there is someone in the elevator, the error-prone time range of the influence of the vibration generated by the door closing on the sensor after the car door closes can be determined. Among them, the car door closing signal is used to indicate that the elevator car door has been closed. Therefore, when the car door closing in-place signal is received, it can be determined that the car door has closed, and the sensor data can be analyzed.

[0079] According to an embodiment of the present disclosure, the bolded data represents error data where a detection error occurs. Through analysis, it can be determined that the probability of error data occurring within 6 seconds after the elevator door closes is the highest. Therefore, the error - prone time range can be selected as 6 seconds. Among them, the error - prone time range of elevators of different brands and different specifications can be determined according to specific sampling and analysis. Since the error - prone time range is 6 seconds after closing the door and the time is short, there will be no danger caused by trapping people due to elevator failures during this period. Therefore, the filtering operation can be to delete the sensor data within the error - prone time range, which will not affect the detection data.

[0080] According to an embodiment of the present disclosure, by judging the error - prone time range of the sensor after the elevator door closes and deleting the sensor data within the error - prone time range, it can be ensured that a large amount of error data will not appear in the data used to detect whether there is someone in the elevator, thereby improving the accuracy of the detection data.

[0081] According to an embodiment of the present disclosure, the detection method applicable to detecting whether there is someone in the elevator further includes: when the data volume of the filtered data group is less than the second preset data volume, complementing the filtered data group so that the data volume after complementing is equal to the second preset data volume to obtain an effective data group, where the first preset data volume is greater than the second preset data volume.

[0082] According to an embodiment of the present disclosure, as Figure 1 shown, sensor 1 can be set to collect data once per second. When the data volume of the filtered data group is less than the second preset data volume, it is difficult to judge the error data through the filtered data in the filtered data group. For example, when the elevator car 2 closes the door and then opens the door after running one floor, after filtering out the error data through data filtering, the data volume in the filtered data group may be less than the second preset data volume. The filtered data group can be complemented so that the data volume after complementing is equal to the second preset data volume to obtain an effective data group. When the data volume of the filtered data group is less than or equal to the first preset data volume and greater than or equal to the second preset data volume, the filtered data group can be used as the effective data group.

[0083] According to an embodiment of the present disclosure, when the data volume of the filtered data group is less than the second preset data volume, obtaining an effective data group through data complementation can provide sufficient data for subsequent detection of whether there is someone in the elevator to ensure the correctness of the detection result.

[0084] According to an embodiment of the present disclosure, complementing the filtered data group so that the data volume after complementing is equal to the second preset data volume includes: using a logistic regression model to predict the next filtered data of the filtered data group to obtain supplementary data; supplementing the supplementary data to the filtered data group to obtain a complemented data group; and when the data volume of the complemented data group is greater than the second preset data volume, replacing the filtered data group with the complemented data group.

[0085] According to an embodiment of the present disclosure, data filtering is completed to obtain a filtered data set. In the case where there is incorrect data in the filtered data set, if the amount of data in the filtered data set is too small, the incorrect data is likely to affect the detection data. If the amount of data in the filtered data set is sufficient, the influence of the incorrect data on the detection data is reduced, and it is not easy for a small amount of incorrect data to affect the correctness of the detection data.

[0086] According to an embodiment of the present disclosure, the next filtered data can be predicted through a logistic regression model and supplemented to the filtered data set to obtain a completed data set. In the case where the amount of data in the completed data set is less than a second preset amount of data, the next filtered data is predicted using the logistic regression model and supplemented to the completed data set to update the completed data set. Until the amount of data in the completed data set is greater than the second preset amount of data, the completed data set is used to replace the filtered data set.

[0087] According to an embodiment of the present disclosure, by setting the second preset amount of data, in the case where the amount of data in the filtered data set is less than the second preset amount of data, the filtered data set is completed to ensure that the amount of data is sufficient and reduce the possibility that the correctness of the detection data is affected by a small amount of incorrect data.

[0088] According to an embodiment of the present disclosure, using a logistic regression model to predict the next filtered data of the filtered data set to obtain supplementary data, including: training the logistic regression model h θ (x) with formula (1):

[0089]

[0090] where x represents the vector composed of the filtered data in the filtered data set, and θ T represents the predicted parameter obtained through training; 0 is supplemented to the filtered data set to obtain a verification data set; the verification data set is calculated using the logistic regression model to obtain a verification result; in the case where the verification result is greater than 0.5, the supplementary data is determined to be 0; and in the case where the verification result is less than 0.5, the supplementary data is determined to be 1.

[0091] According to an embodiment of the present disclosure, the linear regression formula is as shown in formula (3):

[0092] z = θ0 + θ1x1 + θ2x2 + … + θ n x n = θ T x (3),

[0093] Among them, z is a function obtained by linear regression fitting. Logistic regression belongs to the generalized linear regression model, as shown in formula (1). By training the logistic regression model with (1), the next digit of the filtered data set is supplemented with 0 and input into the logistic regression model. The verification result output by the logistic regression model is the correct probability. For a binary classification task, when the verification result is greater than 0.5, it indicates that the probability that the next digit of the filtered data set is 0 is greater than the probability that the next digit is 1. Therefore, the supplementary data can be determined to be 0. When the verification result is less than 0.5, it indicates that the probability that the next digit of the filtered data set is 0 is less than the probability that the next digit is 1. Therefore, the supplementary data can be determined to be 1.

[0094] For example, set the second preset data volume to 5. After completing the training of the logistic regression model, for the filtered data set [0, 0, 1, 0], predicting the next supplementary data, the probability that the supplementary data is 0 is 0.6666746771329081, and the probability that it is 1 is 0.33332532286709093. Therefore, it can be determined that the supplementary data is 0, and the completed data set [0, 0, 1, 0, 1] is used to replace the filtered data set. For the filtered data set [0, 1, 1, 1], the probability that the supplementary data is 0 is 0.05455904931317135, and the probability that it is 1 is 0.9454409506868287. Therefore, it can be determined that the supplementary data is 1, and the completed data set [0, 1, 1, 1, 1] is used to replace the filtered data set.

[0095] According to an embodiment of the present disclosure, the valid data set consists of 0 and 1. Among them, 0 indicates that there is no one in the car, and 1 indicates that there is someone in the car. According to the valid data set, determining the predicted data set includes: using -1 as the base and the i-th valid data - 1 as the exponent to calculate the predicted data corresponding to the i-th valid data; and determining the predicted data set according to multiple predicted data and the positions of the multiple predicted data corresponding to the valid data in the valid data set.

[0096] According to an embodiment of the present disclosure, in the absence of external interference, the sensor data being 0 indicates that there is no one in the car, and the sensor data being 1 indicates that there is someone in the car.

[0097] According to an embodiment of the present disclosure, using -1 as the base and the i-th valid data - 1 as the exponent to calculate the predicted data corresponding to the i-th valid data includes: calculating the predicted data P corresponding to the i-th valid data using formula (2) i :

[0098]

[0099] Among them, x i represents the value of the i-th said valid data.

[0100] According to an embodiment of the present disclosure, with -1 as the base number and the numerical value of the valid data -1 as the exponent, that is, when the sensor data is 0, the exponent is -1, and the corresponding predicted data is -1. When the sensor data is 1, the exponent is 0, and the corresponding predicted data is 1. According to the position of the valid data corresponding to the predicted data, determine the predicted data group corresponding to the valid data group.

[0101] According to an embodiment of the present disclosure, by calculating the predicted data, converting 0 of the valid data to -1 and 1 of the valid data to 1, and then performing subsequent calculations, it is possible to more clearly distinguish the state of someone in the car from the state of no one, thereby improving the correctness of the detection data.

[0102] According to an embodiment of the present disclosure, when determining each predicted data in the predicted data group, perform weighted summation on the predicted data group through a preset weight to obtain the detection data. Wherein, when the preset base number is 1.19, the preset weight corresponding to the i-th valid data in the predicted data group is 1.19 i The i-th detection data component Q in the predicted data group can be calculated by formula (4) i :

[0103] Q i = P i × 1.19 i (4),

[0104] When there are N predicted data in the predicted data group, summing the N detection data components can obtain the detection data Q, as shown in formula (5):

[0105]

[0106] According to an embodiment of the present disclosure, determine whether there is someone in the car according to the detection data, including: when the detection data is greater than 0, determine that there is someone in the car; and when the detection data is less than 0, determine that there is no one in the car.

[0107] According to an embodiment of the present disclosure, since 0 and 1 of the sensor data in the valid data are respectively converted to -1 and 1 through formula (2). When there is no one in the elevator car, excluding external interference, all the predicted data are -1, and the detection data obtained after weighted summation is less than 0. When there is someone in the elevator car, excluding external interference, all the predicted data are 1, and the detection data obtained after weighted summation is greater than 0. Therefore, when the detection data is greater than 0, it can be determined that there is someone in the car, and when the detection data is less than 0, it can be determined that there is no one in the car.

[0108] According to an embodiment of the present disclosure, the detection method applicable to detecting whether there is a person in the elevator further includes: performing real-time calculation based on the sensor data collected in real time after the car door is closed to obtain an updated detection result of human body detection; and updating the detection result with the updated detection result in the case where the updated detection result is different from the detection result.

[0109] According to an embodiment of the present disclosure, the updated detection result can be calculated using the sensor data collected in real time by the same calculation method as the detection result. In the case where the updated detection result is the same as the detection result, there is no need to change the detection result. In the case where the updated detection result is different from the detection result, the detection result is updated with the updated detection result to complete the real-time monitoring of whether there is a person in the elevator.

[0110] According to an embodiment of the present disclosure, in the case where the data volume of the sensor filtered data group is greater than the first preset data volume, selecting the first preset data volume of sensor filtered data from the sensor filtered data group to obtain an effective data group, including: selecting the latest first preset data volume of sensor filtered data from the sensor filtered data group according to the time sequence to obtain an effective data group.

[0111] According to an embodiment of the present disclosure, in the sensor filtered data group, the sensor filtered data is arranged from left to right according to the time sequence, and the latest data is at the rightmost of the sensor filtered data group. Therefore, the first preset data volume of sensor filtered data can be selected from the rightmost to obtain an effective data group.

[0112] According to an embodiment of the present disclosure, obtaining a filtered data group through data filtering can ensure a relatively high data accuracy rate. In special cases, when there are incorrect data in the filtered data group, the effective data group obtained from the filtered data group can be weighted and calculated to obtain detection data, and it is determined whether there is a person in the car according to the detection data to ensure the detection accuracy rate.

[0113] For example, the first preset data volume is set to 8. In the case where the effective data group is [1, 1, 1, 1, 0, 1, 0, 0], the predicted data group can be obtained as [1, 1, 1, 1, -1, 1, -1, -1]. According to the preset weight, the detection data components can be determined to be (1.19) 1 , (1.19) 2 , (1.19) 3 , (1.19) 4 , -(1.19) 5 , (1.19) 6 , -(1.19) 7 , -(1.19) 8。The sum of the detected data components gives a detected data of -0.6506953595668121, which is less than 0. Therefore, it is determined that there is no one in the elevator. When the valid data group is [1, 0, 1, 0, 0, 1, 1, 1], the predicted data group can be obtained as [1, -1, 1, -1, -1, 1, 1, 1]. According to the preset weights, the detected data components can be determined to be (1.19) 1 , -(1.19) 2 , (1.19) 3 , -(1.19) 4 , -(1.19) 5 , (1.19) 6 , (1.19) 7 , (1.19) 8 。The sum of the detected data components gives a detected data of 7.307827750328812, which is greater than 0. Therefore, it is determined that there is someone in the elevator.

[0114] In the extreme case, when the valid data group is [1, 0, 1, 0, 0, 1, 1, 0], the predicted data group can be obtained as [1, -1, 1, -1, -1, 1, 1, -1]. According to the preset weights, the detected data components can be determined to be (1.19) 1 , -(1.19) 2 , (1.19) 3 , -(1.19) 4 , -(1.19) 5 , (1.19) 6 , (1.19) 7 , -(1.19) 8 。The sum of the detected data components gives a detected data of -0.7349429439980337, which is less than 0. Therefore, it is determined that there is no one in the elevator.

[0115] When the valid data group is [1, 0, 1, 0, 0, 1, 0, 1], the predicted data group can be obtained as [1, -1, 1, -1, -1, 1, -1, 1]. According to the preset weights, the detected data components can be determined to be (1.19) 1 , -(1.19) 2 , (1.19) 3 , -(1.19) 4 , -(1.19) 5 , (1.19) 6 , -(1.19) 7 , (1.19) 8 。The sum of the detected data components gives a detected data of 0.5491969147600342, which is greater than 0. Therefore, it is determined that there is someone in the elevator.

[0116] When the valid data group is [1, 0, 1, 1, 1, 0, 0, 1], the predicted data group can be obtained as [1, -1, 1, 1, 1, -1, -1, 1]. According to the preset weights, the detected data components can be determined to be (1.19) 1 , -(1.19) 2 , (1.19) 3 ,(1.19) 4 , (1.19) 5 , -(1.19) 6 , -(1.19) 7 ,(1.19) 8 . The sum of the detected data components gives a detected data of 3.6530609439980335, which is greater than 0. Therefore, it is determined that there is someone in the elevator.

[0117] According to an embodiment of the present disclosure, by selecting the sensor filtering data of the latest first preset data volume to obtain a valid data group and using the valid data group for calculation, the amount of calculation can be reduced. At the same time, since the earlier sensor data has little reference significance for the detected data of whether there is someone in the current car, removing the earlier sensor data has little impact on the detected data and will not affect the correctness of the monitoring data.

[0118] According to an embodiment of the present disclosure, the sensor includes an infrared sensor and a microwave sensor, which are used to sense the presence of a human body through limb movements, breathing, heartbeat, etc. in a static environment.

[0119] According to an embodiment of the present disclosure, using an infrared sensor and a microwave sensor as sensors can accurately sense the presence of a human body in a static environment, but it is easily affected by the opening and closing of the elevator car door and the vibration generated during elevator operation, resulting in incorrect data. Through a detection method applicable to detecting whether there is someone in the elevator, the influence of incorrect data on the detection result of whether there is someone can be reduced, and the detection accuracy can be improved. At the same time, compared with using a camera to monitor the situation in the elevator car, the infrared sensor and the microwave sensor do not collect images, so there is no risk of leakage of the privacy of elevator passengers.

[0120] According to an embodiment of the present disclosure, the effectiveness of the detection method applicable to detecting whether there is someone in the elevator can be verified by comparing the detection result obtained by the detection method applicable to detecting whether there is someone in the elevator with the actual occupancy status of the actual data group, as shown in Table 3.

[0121] Table 3

[0122]

[0123] According to an embodiment of the present disclosure, the actual states corresponding to the first and third data groups are that there is a person, and the detection result obtained by a detection method applicable to detecting whether there is a person in the elevator is that there is a person. The actual states corresponding to the second and fourth data groups are that there is no person, and the detection result obtained by a detection method applicable to detecting whether there is a person in the elevator is that there is no person. Thus, it is verified that the detection method of the present disclosure applicable to detecting whether there is a person in the elevator has a high detection result accuracy.

[0124] Based on the above detection method applicable to detecting whether there is a person in the elevator, the present disclosure further provides a detection device applicable to detecting whether there is a person in the elevator. The following will be combined with Figure 3 to describe this device in detail.

[0125] Figure 4 The structural block diagram of the detection device applicable to detecting whether there is a person in the elevator according to an embodiment of the present disclosure is schematically shown.

[0126] As Figure 4 shown, the detection device 400 applicable to detecting whether there is a person in the elevator in this embodiment includes a data filtering module 410, a data selection module 420, a data determination module 430, a data summation module 440, and a judgment module 450.

[0127] The data filtering module 410 is used to filter the sensor data group detected by the sensor applicable to detecting the human body provided in the elevator car to remove the error data that appears in the data group due to the vibration generated after the car door is closed, and obtain a filtered data group.

[0128] The data selection module 420 is used to select the filtered data equal to the first preset data volume from the filtered data group when the data volume of the filtered data group is greater than the first preset data volume, and obtain an effective data group.

[0129] The data determination module 430 is used to determine a predicted data group according to the effective data group.

[0130] The data summation module 440 is used to perform weighted summation on the predicted data group according to a preset weight to obtain detection data, where the preset weight corresponding to the i-th effective data in the predicted data group is determined by using a preset base greater than 1 as the base and i as the exponent.

[0131] The judgment module 450 is used to determine whether there is a person in the car according to the detection data.

[0132] According to an embodiment of the present disclosure, the data filtering module 410 includes a sampling analysis unit and a data filtering unit.

[0133] The sampling analysis unit is used to perform sampling analysis on the data group to determine the error-prone time range of the influence of the car door closing on the sensor.

[0134] The data filtering unit is used to filter the sensor data within the error-prone time range in the data group to obtain a filtered data group.

[0135] Preferably, the error-prone time range is 3 - 8 seconds after receiving the signal that the car door is closed in place.

[0136] According to an embodiment of the present disclosure, the detection device 400 applicable to detecting whether there is a person in the elevator further includes a data completion module.

[0137] The data completion module is used to complete the filtered data group when the data volume of the filtered data group is less than the second preset data volume, so that the data volume after completion is equal to the second preset data volume, and an effective data group is obtained.

[0138] According to an embodiment of the present disclosure, the data completion module includes a data prediction unit, a data completion unit, and a data substitution unit.

[0139] The data prediction unit is used to use a logistic regression model to predict the next filtered data of the filtered data group to obtain supplementary data.

[0140] The data completion unit is used to supplement the supplementary data to the filtered data group to obtain a completed data group.

[0141] The data substitution unit is used to replace the filtered data group with the completed data group when the data volume of the completed data group is greater than the second preset data volume.

[0142] According to an embodiment of the present disclosure, the data prediction unit includes a model training subunit, a data supplementation subunit, a data calculation subunit, a first data determination subunit, and a second data determination subunit.

[0143] The model training subunit is used to train the logistic regression model h θ (x) using formula (1).

[0144] The data supplementation subunit is used to supplement 0 to the filtered data group to obtain a verification data group.

[0145] The data calculation subunit is used to calculate the verification data group using the logistic regression model to obtain a verification result.

[0146] The first data determination subunit is used to determine the supplementary data as 0 when the verification result is greater than 0.5.

[0147] The second data determination subunit is used to determine the supplementary data as 1 when the verification result is less than 0.5.

[0148] According to an embodiment of the present disclosure, the valid data group consists of 0 and 1, where 0 indicates that there is no one in the car and 1 indicates that there is someone in the car. The data determination module 440 includes a predicted data calculation unit and a data determination unit.

[0149] The predicted data calculation unit is used to calculate the predicted data corresponding to the i-th valid data with -1 as the base and the i-th valid data - 1 as the exponent.

[0150] The data determination unit is used to determine the predicted data group according to multiple predicted data and the positions of the valid data corresponding to the multiple predicted data in the valid data group.

[0151] According to an embodiment of the present disclosure, the predicted data calculation unit includes a predicted data calculation subunit.

[0152] The predicted data calculation subunit is used to calculate the predicted data P corresponding to the i-th valid data by using formula (2). i 。

[0153] According to an embodiment of the present disclosure, the judgment module 450 includes a first result determination unit and a second result determination unit.

[0154] The first result determination unit is used to determine that there is someone in the car when the detection data is greater than 0.

[0155] The second result determination unit is used to determine that there is no one in the car when the detection data is less than 0.

[0156] According to an embodiment of the present disclosure, the detection device 400 applicable to detecting whether there is someone in the elevator further includes a real-time calculation module and a result update module.

[0157] The real-time calculation module is used to perform real-time calculation according to the sensor data collected in real time after the car door is closed to obtain an updated detection result of human body detection.

[0158] The result update module is used to update the detection result with the updated detection result when the updated detection result is different from the detection result.

[0159] According to an embodiment of the present disclosure, the data selection module 420 includes a data selection unit.

[0160] The data selection unit is used to select the latest first preset amount of sensor filtered data from the sensor filtered data group according to the time sequence to obtain the valid data group.

[0161] According to an embodiment of the present disclosure, the sensor includes an infrared sensor and a microwave sensor, and is used to sense the presence of a human body through the limb movement, breathing, heartbeat, etc. of the human body in a static environment.

[0162] According to an embodiment of the present disclosure, any multiple modules among the data filtering module 410, the data selection module 420, the data determination module 430, the data summation module 440, and the judgment module 450 may be combined and implemented in one module, or any one of them may be split into multiple modules. Alternatively, at least part of the functions of one or more of these modules may be combined with at least part of the functions of other modules and implemented in one module. According to an embodiment of the present disclosure, at least one of the data filtering module 410, the data selection module 420, the data determination module 430, the data summation module 440, and the judgment module 450 may be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on chip, a system on substrate, a system on package, an application specific integrated circuit (ASIC), or may be implemented by any other reasonable means such as hardware or firmware through circuit integration or packaging, or may be implemented in any one of the three implementation manners of software, hardware, and firmware, or in any appropriate combination of several of them. Alternatively, at least one of the data filtering module 410, the data selection module 420, the data determination module 430, the data summation module 440, and the judgment module 450 may be at least partially implemented as a computer program module, and when the computer program module is run, it can execute corresponding functions.

[0163] Figure 5 A block diagram of an electronic device suitable for implementing a detection method applicable to detecting whether there is a person in an elevator according to an embodiment of the present disclosure is schematically shown.

[0164] As Figure 5 shown, the electronic device 500 according to an embodiment of the present disclosure includes a processor 501, which can perform various appropriate actions and processes according to a program stored in a read only memory (ROM) 502 or a program loaded from a storage section 508 into a random access memory (RAM) 503. The processor 501 may include, for example, a general microprocessor (such as a CPU), an instruction set processor, and / or a related chipset, and / or a dedicated microprocessor (such as an application specific integrated circuit (ASIC)), etc. The processor 501 may also include on-board memory for caching purposes. The processor 501 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0165] In the RAM 503, various programs and data required for the operation of the electronic device 500 are stored. The processor 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. The processor 501 performs various operations of the method flow according to the embodiments of the present disclosure by executing the programs in the ROM 502 and / or the RAM 503. It should be noted that the programs may also be stored in one or more memories other than the ROM 502 and the RAM 503. The processor 501 may also perform various operations of the method flow according to the embodiments of the present disclosure by executing the programs stored in the one or more memories.

[0166] According to an embodiment of the present disclosure, the electronic device 500 may further include an input / output (I / O) interface 505, and the input / output (I / O) interface 505 is also connected to the bus 504. The electronic device 500 may further include one or more of the following components connected to the input / output (I / O) interface 505: an input portion 506 including a keyboard, a mouse, etc.; an output portion 507 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc. and a speaker, etc.; a storage portion 508 including a hard disk, etc.; and a communication portion 509 including a network interface card such as a LAN card, a modem, etc. The communication portion 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the input / output (I / O) interface 505 as needed. A removable medium 511, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 510 as needed so that a computer program read therefrom is installed into the storage portion 508 as needed.

[0167] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or may exist separately without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the one or more programs are executed, the method according to the embodiments of the present disclosure is implemented.

[0168] According to an embodiment of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, which may include, for example, but is not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In the present disclosure, the computer-readable storage medium may be any tangible medium that contains or stores a program, and this program can be used by or in combination with an instruction execution system, apparatus, or device. For example, according to an embodiment of the present disclosure, the computer-readable storage medium may include the above-described ROM 502 and / or RAM 503 and / or one or more memories other than ROM 502 and RAM 503.

[0169] An embodiment of the present disclosure further includes a computer program product, which includes a computer program that contains program code for executing the method shown in the flowchart. When the computer program product runs in a computer system, the program code is used to enable the computer system to implement the detection method provided by the embodiment of the present disclosure applicable to detecting whether there is a person in an elevator.

[0170] When the computer program is executed by the processor 501, it executes the above functions defined in the system / apparatus of the embodiment of the present disclosure. According to an embodiment of the present disclosure, the above-described systems, apparatuses, modules, units, etc. can be implemented by computer program modules.

[0171] In one embodiment, the computer program may rely on tangible storage media such as optical storage devices and magnetic storage devices. In another embodiment, the computer program may also be transmitted and distributed in the form of a signal on a network medium, and be downloaded and installed through the communication part 509, and / or be installed from the removable medium 511. The program code contained in the computer program can be transmitted by any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0172] In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 509, and / or be installed from the removable medium 511. When the computer program is executed by the processor 501, it executes the above functions defined in the system of the embodiment of the present disclosure. According to an embodiment of the present disclosure, the above-described systems, devices, apparatuses, modules, units, etc. can be implemented by computer program modules.

[0173] According to embodiments of the present disclosure, program code for executing the computer programs provided by the embodiments of the present disclosure may be written in any combination of one or more programming languages. Specifically, these computing programs may be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. The programming languages include, but are not limited to, such as Java, C++, Python, the "C" language, or similar programming languages. The program code may be executed entirely on the user's computing device, partially on the user's device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device may be connected to the user's computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., by connecting through the Internet using an Internet service provider).

[0174] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code that contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram or flowchart, and combinations of blocks in the block diagram or flowchart, may be implemented by a dedicated hardware-based system for performing the specified functions or operations, or may be implemented by a combination of dedicated hardware and computer instructions.

[0175] Those skilled in the art can understand that the features recited in the various embodiments and / or claims of the present disclosure can be combined or / and combined in various ways, even if such combinations or combinations are not explicitly recited in the present disclosure. In particular, without departing from the spirit and teachings of the present disclosure, the features recited in the various embodiments and / or claims of the present disclosure can be combined and / or combined in various ways. All such combinations and / or combinations fall within the scope of the present disclosure.

[0176] The embodiments of the present disclosure have been described above. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of the present disclosure. Although the embodiments have been described separately above, this does not mean that the measures in each embodiment cannot be used advantageously in combination. The scope of the present disclosure is defined by the appended claims and their equivalents. Without departing from the scope of the present disclosure, those skilled in the art can make various substitutions and modifications, and these substitutions and modifications should fall within the scope of the present disclosure.

Claims

1. A detection method applicable to detecting whether there is someone in an elevator, including: Data filtering is performed on a set of sensor data detected by a sensor suitable for detecting a human body disposed in an elevator car to remove error data that appears in the set of data due to vibrations generated after the car door closes, obtaining a filtered data set; In the case where the amount of data in the filtered data set is greater than a first preset amount of data, filtered data equal to the first preset amount of data is selected from the filtered data set to obtain the valid data set; Based on the valid data set, a predicted data set is determined; According to a preset weight, weighted summation is performed on the predicted data set to obtain detection data, where the preset weight corresponding to the i-th valid data in the predicted data set is determined with a preset base greater than 1 as the base and i as the exponent; And Based on the detection data, it is determined whether there is someone in the car.

2. The method according to claim 1, wherein, The data filtering of the set of sensor data detected by the sensor suitable for detecting a human body disposed in the elevator car includes: Performing sampling analysis on the set of data to determine an error-prone time range of the influence on the sensor after the car door closes; and Filtering the sensor data in the set of data that is within the error-prone time range to obtain the filtered data set, Preferably, the error-prone time range is 3 - 8 seconds after receiving the car door closed signal.

3. The method according to claim 1, further including: In the case where the amount of data in the filtered data set is less than a second preset amount of data, the filtered data set is supplemented so that the amount of data after supplementation is equal to the second preset amount of data, obtaining a valid data set, where the first preset amount of data is greater than the second preset amount of data.

4. The method according to claim 3, wherein, The supplementing the filtered data set so that the amount of data after supplementation is equal to the second preset amount of data includes: Using a logistic regression model to predict the next filtered data of the filtered data set to obtain supplementary data; Supplementing the supplementary data to the filtered data set to obtain a supplemented data set; and In the case where the amount of data in the supplemented data set is greater than the second preset amount of data, replacing the filtered data set with the supplemented data set.

5. The method according to claim 4, wherein, The using a logistic regression model to predict the next filtered data of the filtered data set to obtain supplementary data includes: Train the logistic regression model h θ (x) using formula (1): where x represents the vector formed by the filtering data in the filtering data group, and θ T represents the prediction parameter obtained through training; Supplementing 0 to the filtered data set to obtain a verification data set; Calculating the verification data set using the logistic regression model to obtain a verification result; In the case where the verification result is greater than 0.5, determining the supplementary data as 0; and In the case where the verification result is less than 0.5, determining the supplementary data as 1.

6. The method according to claim 1, wherein, The valid data set consists of 0 and 1, where 0 indicates that there is no one in the car and 1 indicates that there is someone in the car, The determining a predicted data set based on the valid data set includes: Calculating the predicted data corresponding to the i-th valid data with -1 as the base and the i-th valid data - 1 as the exponent; and Based on multiple predicted data and the positions of the multiple predicted data corresponding to the valid data in the valid data set, determining the predicted data set.

7. The method according to claim 6, wherein, The calculating the predicted data corresponding to the i-th valid data with -1 as the base and the i-th valid data - 1 as the exponent includes: Calculate the predicted data P corresponding to the i-th said valid data by using formula (2) i :[[-END]] Among them, x i represents the value of the i-th said valid data.

8. The method according to claim 6, wherein, Determining whether there is anyone in the car based on the detected data includes: When the detected data is greater than 0, determining that there is someone in the car; and When the detected data is less than 0, determining that there is no one in the car.

9. The method according to claim 1, further comprising: Performing real-time calculation based on the sensor data collected in real time after the car door is closed to obtain an updated detection result of the human body detection; And When the updated detection result is different from the detection result, using the updated detection result to update the detection result.

10. The method according to claim 1, wherein When the data volume of the sensor filtered data group is greater than a first preset data volume, selecting the sensor filtered data of the first preset data volume from the sensor filtered data group to obtain an effective data group, including: Selecting the latest sensor filtered data of the first preset data volume from the sensor filtered data group according to the time sequence to obtain the effective data group.

11. The method according to claim 1, wherein The sensor includes an infrared sensor and a microwave sensor, and is used to sense the presence of a human body through the limb movement, breathing, heartbeat, etc. of the human body in a static environment.

12. A detection device adapted to detect whether there is a person in an elevator, comprising: A data filtering module, which is applicable to filter a sensor data group detected by a sensor applicable to detecting a human body provided in an elevator car to remove error data appearing in the data group caused by vibrations generated after the car door is closed, so as to obtain a filtered data group; A data selection module, which is applicable to select filtered data equal to the first preset data volume from the filtered data group when the data volume of the filtered data group is greater than the first preset data volume to obtain the effective data group, wherein the first preset data volume is greater than the second preset data volume; A data determination module, which is applicable to determine a predicted data group according to the effective data group; A data summation module, which is applicable to perform weighted summation on the predicted data group according to a preset weight to obtain detected data, wherein the preset weight corresponding to the i-th effective data in the predicted data group is determined by using a preset base greater than 1 as the base and i as the exponent; and A judgment module, which is applicable to determine whether there is anyone in the car according to the detected data.

13. The detection device according to claim 12, wherein The data filtering module is further applicable to perform sampling analysis on the data group to determine an error-prone time range of the influence on the sensor after the car door is closed; and Filtering the sensor data in the data group within the error-prone time range to obtain the filtered data group, Preferably, the error-prone time range is 3-8 seconds after receiving the car door closed in-place signal.

14. The device according to claim 12, further comprising: A data completion module, which is applicable to complete the filtered data group when the data volume of the filtered data group is less than the second preset data volume so that the data volume after completion is equal to the second preset data volume to obtain an effective data group.

15. The detection device according to claim 14, wherein The data completion module is further applicable to use a logistic regression model to predict the next filtered data of the filtered data group to obtain supplementary data; Supplementary the supplementary data to the filtered data group to obtain a completed data group; And In the case where the data volume of the complement data group is greater than the second preset data volume, replace the filtered data group with the complement data group.

16. The detection device according to claim 12, wherein The valid data group consists of 0s and 1s, where 0 indicates that there is no one in the car and 1 indicates that there is someone in the car. Determining the prediction data group according to the valid data group includes: Using -1 as the base and the i-th valid data - 1 as the exponent to calculate the prediction data corresponding to the i-th valid data; and Determining the prediction data group according to a plurality of the prediction data and the positions of the plurality of the prediction data in the valid data group corresponding to the valid data.

17. The detection device according to claim 12, wherein The sensor includes an infrared sensor and a microwave sensor, and is used to sense the presence of a human body through the limb movement, breathing, heartbeat, etc. of the human body in a static environment.

18. An electronic device, comprising: One or more processors; A storage device for storing one or more programs. Wherein, when the one or more programs are executed by the one or more processors, the one or more processors are caused to execute the method according to any one of claims 1 to 11.

19. A computer-readable storage medium having executable instructions stored thereon, which when executed by a processor cause the processor to execute the method according to any one of claims 1 to 11.

Images