Internet of Things platform data management system

Abstract

The invention relates to the field of Internet of Things management, in particular to an Internet of Things platform data management system which is provided with an input module used for shooting personnel information of a plurality of targets to be monitored and generating personnel data, a screening module used for screening the personnel data and distinguishing the personnel data, and a process module. The data preprocessing module is used for preprocessing common personnel data and non-common personnel data and forming corresponding common preprocessed data and non-common preprocessed data, the main learning module is used for generating a common route map according to the common preprocessed data, the secondary learning model is used for learning the non-common preprocessed data and generating a temporary route map, and the interaction module is used for interacting with the common personnel data and the non-common personnel data. The method and the device are used for displaying a common route map and a temporary route map, the problem of basement congestion is solved to a certain extent, the utilization rate of parking spaces is improved, the problem that the parking spaces cannot be found due to factors such as forgetting routes is reduced, the identification accuracy of an Internet of Things platform is improved, and the actual experience of users is improved.

Description

Technical Field

[0001] The present invention relates to the field of Internet of Things management, and in particular to an Internet of Things platform data management system. Background Art

[0002] IoT platform data management is applicable to a variety of scenarios, such as commercial complexes, large communities, smart parks, smart hospitals, etc. In these scenarios, the garage route indication system can greatly improve parking efficiency and management level, provide car owners with a convenient and efficient parking experience, and realize real-time monitoring of parking space status in the garage, intelligent guidance of parking space information, and automated management of vehicle access.

[0003] China Patent Authorization Announcement No.: CN216697528U discloses a parking space induction sensing system, including a ground parking garage, a parking area is set on the ground parking garage, parking spaces are set on the parking areas, and geomagnetic parking space detectors are set on the parking spaces. A mobile phone sensing device is set at the entrance of the ground parking garage, a central processing unit is set inside the mobile phone sensing device, a wireless network module is electrically connected to the central processing unit, and an arrow indicator light is set on the upper side of the ground parking garage. The utility model geomagnetic parking space detector transmits information about whether there is a vehicle in each parking space to the central processing unit. When the user parks, the mobile phone establishes a communication connection with the NFC sensing module, and the driver can park the car at the designated location according to the guidance of the arrow indicator light, without the need to frequently search for parking spaces. All vehicles can be parked in an orderly manner without chaos, thereby improving the convenience and safety of use.

[0004] Chinese Patent Authorization Announcement No.: CN218384274U discloses a video parking space detection device and a car search system. The device includes: a base, a shell, a camera module, a processing circuit, a communication circuit, a control circuit and an indicator light assembly. The base is fixed on the garage bridge. The shell is detachably connected to the base. The camera module is mounted on the shell, including a camera for capturing an image of the parking space. The processing circuit signal is connected to the camera, and the state of the parking space is analyzed based on the image information of the parking space acquired by the camera. The communication circuit signal is connected to the background processing module to obtain the navigation information sent by the background processing module. The control circuit signal is connected to the communication circuit. The indicator light assembly is mounted on the shell, including a first indicator light electrically connected to the processing circuit and a second indicator light electrically connected to the control circuit. The processing circuit controls the display state of the first indicator light according to the analyzed state of the parking space, and the control circuit controls the display state of the second indicator light according to the navigation information acquired by the communication circuit.

[0005] However, the above method has the following problems: it is impossible to monitor and query the parking route in real time, which leads to reduced management efficiency. Summary of the invention

[0006] To this end, the present invention provides an Internet of Things platform data management system to overcome the problem in the prior art that parking routes cannot be monitored and queried in real time, thereby reducing management efficiency.

[0007] To achieve the above object, the present invention provides an Internet of Things platform data management system, which is characterized by comprising: An input module is used to capture the personnel information of several targets to be monitored and generate corresponding personnel data; A screening module, which is connected to the input module, is used to screen the personnel data, distinguish whether the target to be monitored is a frequent person or an infrequent person, and divide the personnel data into frequent person data and infrequent person data; A process module, connected to the screening module, for preprocessing the frequently used personnel data and the infrequently used personnel data, and forming corresponding frequently used preprocessed data and infrequently used preprocessed data; A main learning module, which is connected to the screening module and the process module, and is used to generate a corresponding common route map according to the common pre-processing data; A secondary learning model, which is connected to the process module, is used to learn the infrequently used pre-processed data according to the indicator characteristics and generate a corresponding temporary roadmap; An interactive module, connected to the primary learning module and the secondary learning model, for receiving and displaying the common route map and the temporary route map; Wherein, the personnel information includes the face information and license plate information of the target to be monitored; The frequently used personnel are personnel whose frequency of appearance within a preset period is greater than a frequency threshold; The non-common personnel are personnel whose appearance frequency within the preset period is less than the frequency threshold; The main learning module is provided with a common route learning model; The common route learning model is generated by training based on all common personnel data within the preset period; The secondary learning module is provided with a temporary route learning model; The temporary route learning model is generated by training based on all non-common personnel data within the preset period.

[0008] Furthermore, the input module includes: A sensor, used to issue a shooting command when sensing the target to be monitored; An image sensor connected to the sensor to receive the shooting command and shoot face information and license plate information corresponding to a number of the monitored targets; a converter, connected to the image sensor, for receiving the personnel information and converting the personnel information into the personnel data for output, Wherein, the image sensor is provided with a camera with adjustable shooting angle.

[0009] Furthermore, the screening module comprises: A database for storing all personnel data monitored within the preset period; A timer is used to issue screening commands at fixed intervals; A filter, connected to the database and the timer, for filtering the personnel data upon receiving the filtering command; A classifier is connected to the filter and is used to mark the filtered personnel data as commonly used personnel data and uncommon personnel data.

[0010] Furthermore, the process module includes: A receiver, for receiving the frequently used personnel data and the infrequently used personnel data; A personnel fitter, connected to the receiver, for performing personnel fitting on the frequently used personnel data and the infrequently used personnel data; A preprocessor is connected to the personnel fitter and is used to preprocess the frequently used personnel data and the infrequently used personnel data and generate corresponding frequently used preprocessed data and infrequently used preprocessed data.

[0011] Furthermore, the sensor detects the target to be monitored and issues the shooting command. The image sensor changes the position of the camera in the horizontal or vertical direction according to the shooting command to adjust the angle of the shooting picture and capture the personnel information. The converter performs operational amplification on it to generate corresponding personnel data.

[0012] Furthermore, when receiving the filtering command, the filter queries the database to determine the occurrence frequency of the target to be monitored and filters the personnel data and marks the filtered personnel data through the classifier.

[0013] Furthermore, the personnel fitting device performs data cleaning on the frequently used personnel data and the infrequently used personnel data to generate corresponding personnel fitting data; The preprocessor selects several index features of the personnel fitting data and generates several commonly used preprocessed data and uncommon preprocessed data with a sampling rate of a standard sampling rate. Wherein, the indicator characteristics include the frequency of occurrence and / or the remaining space in the basement; The standard sampling rate is a sampling rate that can be recognized by the common route learning model and the temporary route learning model, and for a single sampling, the corresponding standard sampling rate is a single sampling rate.

[0014] Furthermore, the common route learning model annotates the common preprocessed data, queries the database and extracts the common routes corresponding to the common personnel, and generates the common route map.

[0015] Furthermore, the temporary route learning model labels the uncommon preprocessed data according to the indicator characteristics, plans and extracts temporary routes, and generates a corresponding temporary route map.

[0016] Furthermore, the interactive module is provided with an interactive interface for receiving the commonly used route map and the temporary route map, and backing them up as searchable items. When the non-common personnel are unable to return along the original route of the temporary route map when leaving the basement, they can click on the interactive interface and enter the license plate number to query the corresponding searchable item and display the temporary route map.

[0017] Compared with the prior art, the present invention is provided with an input module for capturing the personnel information of several targets to be monitored and generating personnel data, a screening module for screening and distinguishing the personnel data, a process module for preprocessing commonly used personnel data and uncommon personnel data and forming corresponding commonly used preprocessed data and uncommon preprocessed data, a main learning module for generating a commonly used route map according to the commonly used preprocessed data, a secondary learning model for learning the uncommon preprocessed data and generating a temporary route map, and an interactive module for displaying the commonly used route map and the temporary route map. To a certain extent, the congestion problem of the basement is solved, the utilization rate of the parking space is improved, the problem of not being able to find the parking space due to forgetting the route and other factors is reduced, the accuracy of the recognition of the Internet of Things platform is improved, and the actual experience of the user is improved.

[0018] Furthermore, by setting a converter in the input module, personnel information is converted into personnel data, which facilitates the learning of the preprocessed data by the machine learning model and improves the recognition accuracy of the Internet of Things platform.

[0019] Furthermore, by screening and classifying the personnel data in the screening module, the common route map and the temporary route map are output and displayed separately, thereby improving the utilization rate of the parking space.

[0020] Furthermore, by setting frequency thresholds, frequent and infrequent personnel can be quickly distinguished, solving the congestion problem in the basement to a certain extent.

[0021] Furthermore, by preprocessing the frequently used personnel data and the infrequently used personnel data, the corresponding preprocessed data is obtained, and the recognition efficiency of the machine learning model is used to quickly select the effective features of the preprocessed data, thereby further improving the management efficiency of the system.

[0022] Furthermore, by setting up an interactive interface, the frequently used route maps and temporary route maps are backed up as searchable items, allowing non-frequently used personnel to return along the original route along the temporary route map, reducing the problem of not being able to find a parking space due to factors such as forgetting the route, and improving the user's actual experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 This is a structural diagram of an Internet of Things platform data management system of the present invention; Figure 2 It is a structural schematic diagram of the input module of the present invention; Figure 3 It is a structural schematic diagram of the screening module of the present invention; Figure 4 It is a structural schematic diagram of the process module of the present invention. DETAILED DESCRIPTION

[0024] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0025] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0026] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is merely for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0027] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0028] See also Figure 1 As shown, it is a structural diagram of an Internet of Things platform data management system of the present invention, including: An input module is used to capture the personnel information of several targets to be monitored and generate corresponding personnel data; A screening module, which is connected to the input module, is used to screen the personnel data, distinguish whether the monitored target is a regular person or an irregular person, and divide the personnel data into regular person data and irregular person data; A process module, which is connected to the screening module, is used to pre-process the frequently used personnel data and the infrequently used personnel data, and form corresponding frequently used pre-processed data and infrequently used pre-processed data; The main learning module is connected with the screening module and the process module to generate corresponding common route maps according to common pre-processing data; The secondary learning model is connected to the process module and is used to learn the uncommon preprocessed data according to the indicator characteristics and generate the corresponding temporary roadmap; An interactive module, which is connected to the main learning module and the secondary learning model, and is used to receive and display the common route map and the temporary route map; Among them, personnel information includes facial information and license plate information of the target to be monitored; Frequently used personnel are those whose frequency of appearance in a preset period is greater than the frequency threshold; Non-usual personnel are those whose frequency of appearance within a preset period is less than the frequency threshold; The main learning module has a common route learning model; The common route learning model is trained and generated based on all the common personnel data within a preset period; A temporary route learning model is provided in the secondary learning module; The temporary route learning model is trained and generated based on all non-common personnel data within a preset period.

[0029] An input module is provided to capture the personnel information of several targets to be monitored and generate personnel data, a screening module is used to screen and distinguish personnel data, a process module is used to preprocess commonly used personnel data and uncommon personnel data and form corresponding commonly used preprocessed data and uncommon preprocessed data, a main learning module is used to generate a commonly used route map based on the commonly used preprocessed data, a secondary learning model is used to learn the uncommon preprocessed data and generate a temporary route map, and an interactive module is used to display the commonly used route map and the temporary route map. To a certain extent, the congestion problem in the basement is solved, the utilization rate of parking spaces is improved, the problem of being unable to find parking spaces due to forgetting routes and other factors is reduced, the accuracy of recognition of the Internet of Things platform is improved, and the actual experience of users is improved.

[0030] See also Figure 2 As shown, it is a schematic diagram of the structure of the input module of the present invention, including: A sensor is used to issue a shooting command when a target to be monitored is sensed; An image sensor is connected to the sensor to receive a shooting command and capture facial information and license plate information corresponding to a number of monitored targets; A converter is connected to the image sensor to receive personnel information and convert the personnel information into personnel data for output. Among them, a camera with adjustable shooting angle is provided on the image sensor.

[0031] By setting a converter in the input module, personnel information is converted into personnel data, which facilitates the machine learning model to learn the preprocessed data and improves the recognition accuracy of the IoT platform.

[0032] See also Figure 3 As shown, it is a schematic diagram of the structure of the screening module of the present invention, comprising: A database to store all personnel data monitored within a preset period; A timer is used to issue screening commands at fixed intervals; A filter, which is connected to a database and a timer, and is used to filter the personnel data when a filtering command is received; The classifier is connected to the filter and is used to mark the filtered personnel data as common personnel data and uncommon personnel data.

[0033] In specific implementations, setting the fixed time length to 10 seconds is usually the best for screening personnel data.

[0034] By screening and classifying personnel data in the screening module, the common route map and temporary route map can be output and displayed separately, thereby improving the utilization rate of parking spaces.

[0035] By setting frequency thresholds, frequent and infrequent personnel can be quickly distinguished, solving the congestion problem in the basement to a certain extent.

[0036] In practice, the frequency threshold is generally set to 55%-65%, and preferably 60%.

[0037] See also Figure 4 As shown, it is a structural schematic diagram of the process module of the present invention, including: A receiver, for receiving data of commonly used personnel and data of infrequently used personnel; A personnel fitter, connected to the receiver, for fitting the frequently used personnel data and the infrequently used personnel data; The preprocessor is connected to the personnel fitter and is used to preprocess the commonly used personnel data and the infrequently used personnel data and generate corresponding commonly used preprocessed data and infrequently used preprocessed data.

[0038] By preprocessing the data of frequently used personnel and infrequently used personnel, the corresponding preprocessed data is obtained. With the recognition efficiency of the machine learning model, the effective features of the preprocessed data can be quickly selected, thereby further improving the management efficiency of the system.

[0039] Specifically, the sensor detects the target to be monitored and issues a shooting command. The image sensor changes the horizontal or vertical position of the camera according to the shooting command to adjust the angle of the shooting picture and capture the personnel information. The converter performs operational amplification on it to generate corresponding personnel data.

[0040] Embodiment 1: photograph the facial information and license plate information of target A to be monitored, the converter performs computational amplification on the facial information pixels, performs text recognition on the license plate information, and outputs the personnel data as: "pixels 112px*112px, Tianjin A12138".

[0041] Specifically, when receiving a filtering command, the filter queries the database to determine the frequency of occurrence of the target to be monitored, filters the personnel data, and marks the filtered personnel data through the classifier.

[0042] Example 2: Assuming the frequency threshold is 60%, the preset period is 30 days, and the monitored target B appears 6 times within the preset period, the frequency of occurrence is 20%, which is less than the frequency threshold, and the monitored target B is marked as an infrequent person.

[0043] Example 3: Assuming the frequency threshold is 60%, the preset period is 30 days, and the target C to be monitored appears 24 times within the preset period, the frequency of occurrence is 80%, which is greater than the frequency threshold, and the target C to be monitored is marked as a frequent person.

[0044] In a specific implementation, when the frequency of occurrence of the target to be monitored is greater than the frequency threshold, the corresponding temporary route is automatically converted to a common route.

[0045] Specifically, the personnel fitter performs data cleaning on the frequently used personnel data and the infrequently used personnel data to generate corresponding personnel fitting data; The preprocessor selects several indicator features of the personnel fitting data and generates several commonly used preprocessed data and uncommon preprocessed data with a standard sampling rate. Among them, the indicator characteristics include the frequency of occurrence and / or the remaining space in the basement; The standard sampling rate is a sampling rate that can be recognized by the common route learning model and the temporary route learning model, and for a single sampling, the corresponding standard sampling rate is a single sampling rate.

[0046] Preferably, setting the sampling rate to 10 per second has a better learning effect on the preprocessed data, and for the system described in this application, the corresponding learning effect is optimal.

[0047] Specifically, the common route learning model annotates the common preprocessed data, queries the database and extracts the common routes corresponding to common personnel, and generates a common route map.

[0048] Specifically, the temporary route learning model labels the uncommon preprocessed data according to the indicator characteristics, plans and extracts temporary routes, and generates the corresponding temporary route map.

[0049] Specifically, the interactive module is provided with an interactive interface for receiving common route maps and temporary route maps, and backing them up as searchable items. When non-common personnel are unable to return along the original route along the temporary route map when leaving the basement, they can click on the interactive interface and enter the license plate number to query the corresponding searchable item and display the temporary route map.

[0050] Example 4: The license plate number of the non-common personnel D is "Jin A12138". When he enters the basement, the temporary route learning model generates the F temporary route map, and the interactive module backs up the F temporary route map. When the non-common personnel D forgets the route when leaving the basement, he clicks on the interactive interface and enters "Jin A12138", and the interactive interface displays the F temporary route map.

[0051] By setting up an interactive interface, frequently used route maps and temporary route maps are backed up as searchable items, allowing non-frequently used personnel to return along the original route along the temporary route map, reducing the problem of not being able to find a parking space due to factors such as forgetting the route, and improving the actual user experience.

[0052] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0053] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An Internet of Things platform data management system, characterized in that: include: An input module is used to capture the personnel information of several targets to be monitored and generate corresponding personnel data; A screening module, which is connected to the input module, is used to screen the personnel data, distinguish whether the target to be monitored is a frequent person or an infrequent person, and divide the personnel data into frequent person data and infrequent person data; A process module, connected to the screening module, for preprocessing the frequently used personnel data and the infrequently used personnel data, and forming corresponding frequently used preprocessed data and infrequently used preprocessed data; A main learning module, which is connected to the screening module and the process module, and is used to generate a corresponding common route map according to the common pre-processing data; A secondary learning model, which is connected to the process module, is used to learn the non-common pre-processed data according to the indicator characteristics and generate a corresponding temporary roadmap; An interactive module, connected to the primary learning module and the secondary learning model, for receiving and displaying the common route map and the temporary route map; Wherein, the personnel information includes the face information and license plate information of the target to be monitored; The frequently used personnel are personnel whose frequency of appearance within a preset period is greater than a frequency threshold; The non-common personnel are personnel whose appearance frequency within the preset period is less than the frequency threshold; The main learning module is provided with a common route learning model; The common route learning model is generated by training based on all common personnel data within the preset period; The secondary learning module is provided with a temporary route learning model; The temporary route learning model is generated by training based on all non-common personnel data within the preset period.

2. The Internet of Things platform data management system according to claim 1, characterized in that: The input module comprises: A sensor, used to issue a shooting command when sensing the target to be monitored; An image sensor connected to the sensor to receive the shooting command and shoot face information and license plate information corresponding to a number of the monitored targets; a converter, connected to the image sensor, for receiving the personnel information and converting the personnel information into the personnel data for output, Wherein, the image sensor is provided with a camera with adjustable shooting angle.

3. The Internet of Things platform data management system according to claim 2, characterized in that: The screening module comprises: A database for storing all personnel data monitored within the preset period; A timer is used to issue screening commands at fixed intervals; A filter, connected to the database and the timer, for filtering the personnel data upon receiving the filtering command; A classifier is connected to the filter and is used to mark the filtered personnel data as commonly used personnel data and uncommon personnel data.

4. The Internet of Things platform data management system according to claim 3, characterized in that: The process module comprises: A receiver, for receiving the frequently used personnel data and the infrequently used personnel data; A personnel fitter, connected to the receiver, for performing personnel fitting on the frequently used personnel data and the infrequently used personnel data; A preprocessor is connected to the personnel fitter and is used to preprocess the frequently used personnel data and the infrequently used personnel data and generate corresponding frequently used preprocessed data and infrequently used preprocessed data.

5. The Internet of Things platform data management system according to claim 4, characterized in that: The sensor detects the target to be monitored and issues the shooting command. The image sensor changes the position of the camera in the horizontal or vertical direction according to the shooting command to adjust the angle of the shooting picture and shoot the personnel information. The converter performs operational amplification on it to generate corresponding personnel data.

6. The Internet of Things platform data management system according to claim 5, characterized in that: When receiving the filtering command, the filter queries the database, determines the occurrence frequency of the target to be monitored, filters the personnel data, and marks the filtered personnel data through the classifier.

7. The Internet of Things platform data management system according to claim 6, characterized in that: The personnel fitting device performs data cleaning on the frequently used personnel data and the infrequently used personnel data to generate corresponding personnel fitting data; The preprocessor selects several index features of the personnel fitting data and generates several commonly used preprocessed data and uncommonly used preprocessed data with a sampling rate of a standard sampling rate. Wherein, the indicator characteristics include the frequency of occurrence and / or the remaining space in the basement; The standard sampling rate is a sampling rate that can be recognized by the common route learning model and the temporary route learning model, and for a single sampling, the corresponding standard sampling rate is a single sampling rate.

8. The Internet of Things platform data management system according to claim 7, characterized in that: The commonly used route learning model annotates the commonly used pre-processed data, queries the database and extracts the commonly used routes corresponding to the frequently used personnel, and generates the commonly used route map.

9. The Internet of Things platform data management system according to claim 8, characterized in that: The temporary route learning model labels the uncommon preprocessed data according to the indicator characteristics, plans and extracts temporary routes, and generates a corresponding temporary route map.

10. The Internet of Things platform data management system according to claim 9, characterized in that: The interactive module is provided with an interactive interface for receiving the commonly used route map and the temporary route map, and backing them up as searchable items. When the non-common personnel cannot return along the original route of the temporary route map when leaving the basement, they can click on the interactive interface and enter the license plate number to query the corresponding searchable item and display the temporary route map.

Images