Commercial lighting system and lighting method based on AIoT and sensor network

Abstract

The embodiment of the present invention discloses a commercial lighting system and lighting method based on AIoT and sensor network, the method includes obtaining image data of goods and the environment in which the goods are located; adjusting the light according to the image data; obtaining environmental images including customers and goods; estimating regional heat maps and product heat map data according to the environmental images; and displaying regional heat maps and product heat map data. The AI ​​smart lamp of the present invention can use imaging sensors to automatically perceive shopping mall environmental information and target product information, and after reasoning and analysis, it can realize automatic adjustment of parameters such as brightness, color temperature and color. The AI ​​smart box uses integrated imaging sensors to realize functions such as customer detection and product heat analysis, as well as other additional commercial applications, such as regional heat maps, product heat maps, scene control, security, store entry reminders, energy saving and other functions, and is rich in functions.

Description

Technical Field

[0001] The present invention relates to the field of lighting technology, and more specifically to a commercial lighting system and a lighting method based on AIoT and a sensor network. Background Art

[0002] At present, the brightness, color temperature and color parameters of traditional commercial lighting LED lamps are generally fixed and cannot be adjusted automatically. Although some can be adjusted, they are limited to controlling the corresponding lighting mode through switches. There are few types of these lighting modes, and they are not convenient to adjust. They are limited in use and have poor user experience. In addition, some applications with commercial added value, such as regional heat maps, product heat maps, scene control, store entry reminders, security and other applications, must be implemented using other special systems, and the functions are relatively simple. Summary of the invention

[0003] The purpose of the present invention is to overcome the deficiencies of the prior art and provide a commercial lighting system and a lighting method based on AIoT and a sensor network.

[0004] To achieve the above object, the present invention adopts the following technical solutions:

[0005] On the one hand, commercial lighting systems based on AIoT and sensor networks include:

[0006] server;

[0007] At least one AI smart light, connected to the server;

[0008] At least one AI smart box, communicating with the AI ​​smart light and the server;

[0009] An intelligent electronic device is communicatively connected with the AI ​​smart light, the AI ​​smart box and the server.

[0010] Its further technical solution is: the AI ​​smart light includes an LED light, a first imaging sensor, a first wireless communication network, a first gateway, a first AI processor and a controller; the first wireless communication network is used to establish a network connection with the AI ​​smart box, and the first gateway is used to establish a communication connection with the server and the intelligent electronic device; the first imaging sensor is used to collect image data of the product and the environment in which the product is located, and the first AI processor is used to process the image data collected by the first imaging sensor and set a spectral scheme to send to the controller, and the controller is used to control the LED light to perform corresponding light adjustments according to the spectral scheme.

[0011] Its further technical solution is: the AI ​​smart box includes a second imaging sensor, a second wireless communication network, a second gateway and a second AI processor; the second wireless communication network is used to establish a network connection with the AI ​​smart light, the second gateway is used to establish a communication connection with the server and the smart electronic device, the second imaging sensor is used to collect environmental images including customers and products, the second AI processor processes the environmental images to obtain product information and customer flow information, and the second gateway is used to send the information processed by the second AI processor to the server to generate regional heat maps and product heat maps.

[0012] On the other hand, the lighting methods of commercial lighting systems based on AIoT and sensor networks include:

[0013] Acquire image data of the product and the environment in which the product is located;

[0014] Adjust lighting based on image data;

[0015] Acquire environmental images including customers and products;

[0016] Estimate regional heat map and product heat map data based on environmental images;

[0017] Displays regional heat map and product heat map data.

[0018] A further technical solution is: the light adjustment according to the image data includes:

[0019] Perform inference analysis on image data to obtain product information;

[0020] Searching for a pre-stored spectral formula corresponding to the product information according to the product information;

[0021] Adjust the light according to the spectrum recipe.

[0022] A further technical solution is: the product information includes product location information, category information, color information and style information.

[0023] A further technical solution is: the method of estimating the regional heat map and the commodity heat map data according to the environmental image includes:

[0024] Count the number of customers in the environment image;

[0025] Calculate the location information of each customer in the environment venue;

[0026] With the location of the target product in the environment as the center, set a circular area that affects the target product;

[0027] Generate a product heat map based on the number of valid people in the circular area.

[0028] A further technical solution is: after setting a circular area affecting the target product with the location of the target product in the environment as the center, the method further includes:

[0029] Calculate the dwell time of each customer in the circular area;

[0030] If the residence time is greater than the set threshold, the customer is determined to be a valid customer attracted by the target product.

[0031] A further technical solution thereof is: after generating the commodity heat map according to the effective number of people in the circular area, it also includes:

[0032] Set the scene heat area with the center of the environment site as the center of the circle;

[0033] Generate a regional heat map for the crowd density in the scene heat area.

[0034] Compared with the prior art, the present invention has the following beneficial effects: the present invention forms an IoT network through AI smart lights and AI smart boxes, and forms an intelligent commercial lighting system with servers and intelligent electronic devices. AI smart lights can use imaging sensors to automatically sense the mall environment information and target product information, and after reasoning and analysis, realize automatic adjustment of parameters such as brightness, color temperature and color. The AI ​​smart box uses integrated imaging sensors to realize functions such as customer detection and product heat analysis, as well as other additional commercial applications, such as regional heat maps, product heat maps, scene control, security, store entry reminders, energy saving and other functions, with rich functions.

[0035] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the following preferred embodiments are specifically cited and described in detail as follows. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying any creative work.

[0037] Figure 1 A system architecture diagram of a commercial lighting system based on AIoT and sensor network provided in a specific embodiment of the present invention;

[0038] Figure 2A functional architecture diagram of an AI smart light in a commercial lighting system based on AIoT and sensor networks provided by a specific embodiment of the present invention;

[0039] Figure 3 A functional architecture diagram of an AI smart box in a commercial lighting system based on AIoT and sensor networks provided by a specific embodiment of the present invention;

[0040] Figure 4 A flowchart of a lighting method for a commercial lighting system of AIoT and sensor network provided in a specific embodiment of the present invention. DETAILED DESCRIPTION

[0041] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0042] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0043] It should also be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0044] It should be further understood that the term "and / or" used in the present description and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0045] like Figure 1 As shown in the figure, the commercial lighting system based on AIoT and sensor network includes:

[0046] server;

[0047] At least one AI smart lamp 100, connected to the server for communication;

[0048] At least one AI smart box 200, connected to the AI ​​smart light 100 and the server;

[0049] The intelligent electronic device is connected to the AI ​​smart lamp 100, the AI ​​smart box 200 and the server for communication.

[0050] In this embodiment, Figure 1 In the figure, the cloud service system refers to the server, and the APP unit refers to the APP software of the smart electronic device. The IoT network is formed by multiple AI smart lights 100 and multiple AI smart boxes 200, and the server and smart electronic devices form a smart commercial lighting system.

[0051] The data collected by the AI ​​smart lamp 100 and the AI ​​smart box 200 can be transmitted to the server for aggregation and calculation to realize various commercial functions, such as product heat map, regional heat map, scene control, security, store entry reminder, energy saving, etc. The APP on the smart electronic device can configure, manually control and intervene in the commercial lighting system.

[0052] In one embodiment, if Figure 2 As shown, the AI ​​smart lamp 100 includes an LED lamp 160, a first imaging sensor 150, a first wireless communication network 120, a first gateway 110, a first AI processor 140 and a controller 130; the first wireless communication network 120 is used to establish a network connection with the AI ​​smart box 200, and the first gateway 110 is used to establish a communication connection with the server and the smart electronic device; the first imaging sensor 150 is used to collect image data of the product and the environment in which the product is located, and the first AI processor 140 is used to process the image data collected by the first imaging sensor 150 and set the spectral scheme to send to the controller 130, and the controller 130 is used to control the LED lamp 160 to perform corresponding light adjustments according to the spectral scheme.

[0053] Specifically, the LED lamp 160 can be a lighting lamp such as a track light, a downlight, a spotlight, etc. The first imaging sensor 150, the first wireless communication network 120, the first gateway 110, the first AI processor 140 and the controller 130 can be integrated on the LED lamp 160 or not.

[0054] In this embodiment, the first imaging sensor 150 is a camera, the first wireless communication network 120 is a Bluetooth mesh network, and the first gateway 110 is a WiFi gateway.

[0055] In one embodiment, if Figure 3As shown, the AI ​​smart box 200 includes a second imaging sensor 240, a second wireless communication network 220, a second gateway 210 and a second AI processor 230; the second wireless communication network 220 is used to establish a network connection with the AI ​​smart lamp 100, the second gateway 210 is used to establish a communication connection with the server and the smart electronic device, the second imaging sensor 240 is used to collect environmental images including customers and products, the second AI processor 230 processes the environmental images to obtain product information and customer flow information, and the second gateway 210 is used to send the information processed by the second AI processor 230 to the server to generate a regional heat map and a product heat map.

[0056] In this embodiment, the second imaging sensor 240 is a camera, the second wireless communication network 220 is a Bluetooth mesh network, and the second gateway 210 is a WiFi gateway.

[0057] Specifically, the first AI processor 140 and the second AI processor 230 are both transplanted with a trained deep learning model, and the required target object information can be inferred and analyzed using the deep learning model. The deep learning model is transplanted to the first AI processor 140 and the second AI processor 230 after training.

[0058] In this embodiment, the training process of the deep learning model uses an imaging sensor to collect a large number of images of scenes illuminated by smart lights, and then classifies and annotates the images as training data sets, verification data sets, and test data sets for the deep learning model. The deep learning model is established and trained, verified, and tested. This training process is generally completed on a workstation or server, rather than in the AI ​​processor of the AI ​​smart light 100 and the AI ​​smart box 200. After the training is completed, the trained deep learning model is transplanted to the AI ​​processor of the AI ​​smart light 100 and the AI ​​smart box 200. The reasoning process of deep learning is completed in the AI ​​processor. The reasoning process of the deep learning model is to first use the imaging sensor integrated on the AI ​​smart light 100 and the AI ​​smart box 200 to capture the image, and then use the deep learning model that has been transplanted to the AI ​​processor of the smart light to perform reasoning analysis on the image to obtain the identification, classification, and positioning information of the illuminated object for light matching and color matching. For the AI ​​smart box 200, the number of customers in the image and the thermal value of the product are obtained.

[0059] like Figure 4 As shown, an embodiment of the present invention further provides a lighting method using the above-mentioned commercial lighting system based on AIoT and sensor network, and the method includes the following steps: S10-S50.

[0060] S10: Obtain image data of the commodity and the environment in which the commodity is located.

[0061] In this embodiment, the AI ​​smart light 100 can utilize the first imaging sensor 150 to collect image data of the photographed goods and the environment in which the goods are located.

[0062] S20: Adjust the lighting according to the image data.

[0063] In one embodiment, step S20 specifically includes the following steps: S201 - S203 .

[0064] S201: Perform inference analysis on image data to obtain product information.

[0065] In this embodiment, the deep learning model of the first AI processor 140 can be used to perform inference analysis on the image data to obtain product information, which includes product location information, category information, color information, and style information.

[0066] S202: Search for a pre-stored spectral formula corresponding to the product information according to the product information.

[0067] In this embodiment, a spectral formula is pre-stored in the internal storage space Flash of the AI ​​smart lamp 100. The spectral formula is configured in advance by an optical engineer based on attributes such as the category, color, and style of the product. Different spectral formulas can be configured for different product information.

[0068] S203, adjusting the lighting according to the spectrum formula.

[0069] In this embodiment, after finding the spectrum formula corresponding to the product information in the storage space Flash, the controller 130 will adjust the light of the LED lamp 160 according to the spectrum formula.

[0070] S30: Acquire an environment image including customers and products.

[0071] In this embodiment, the AI ​​smart box 200 can utilize the second imaging sensor 240 to photograph the environment to obtain an environment image.

[0072] S40: Estimate regional heat map and product heat map data based on the environment image.

[0073] In this embodiment, step S40 specifically includes the following steps:

[0074] S401: Count the number of customers in the environment image.

[0075] In this embodiment, the deep learning model of the second AI processor 230 can identify customers and the number of customers in the environmental image.

[0076] S402: Calculate the location information of each customer in the environment.

[0077] S403: Taking the location of the target product in the environment as the center of the circle, set a circular area that affects the target product.

[0078] Specifically, the radius of the circular area can be determined according to actual conditions, and only customers located in the circular area can be used as elements for generating a product heat map.

[0079] S404: Generate a commodity heat map according to the number of valid people in the circular area.

[0080] In this embodiment, different heat gradient areas can be designed within the circular area, and corresponding pixel colors are assigned to different heat gradient areas to generate the heat map of the product. For example, red represents a higher heat value for the product, and blue represents a lower heat value for the product. The heat maps of all products in the mall can be integrated together to generate the heat map of all products in the mall.

[0081] In one embodiment, in order to improve the accuracy of calculation, the following steps are further included after step S403:

[0082] S4035. Calculate the residence time of each customer in the circular area.

[0083] S4036: If the dwell time is greater than the set threshold, the customer is determined to be a valid customer attracted by the target product.

[0084] Specifically, in actual scenarios, there may be customers who just pass through the circular area and do not stay because they are attracted by the goods. In this case, such customers are not effective customers attracted by the goods and need to be excluded. By setting the stay time, effective customers attracted by the goods can be screened out.

[0085] In one embodiment, step S404 further includes the following steps:

[0086] S405, setting a scene heat area with the center of the environment site as the center of the circle.

[0087] S406: Generate a regional heat map for the crowd density in the scene heat area.

[0088] Specifically, the scene heat area is set according to the needs, and the corresponding pixel color can be assigned according to the density of people in the heat area to generate a regional heat map. For example, red represents a high heat value in the area, and blue represents a low heat value in the area. By integrating all the regional heat maps in the mall, a regional heat map of the entire mall can be generated.

[0089] S50: Displaying regional heat map and product heat map data.

[0090] In this embodiment, the regional heat map and the commodity heat map can be displayed through a display device for relevant personnel to perform data analysis and retrieval.

[0091] In one embodiment, the environmental image obtained by the AI ​​smart box 200 also has other functional effects, such as scene control, store entry reminder / security, energy saving, etc.

[0092] Specifically, scene control is based on the environmental images collected by the AI ​​smart box 200, and determines how to turn on the lights based on factors such as customer flow, product color, ambient light, time, etc., and realizes group control of lights through the IoT network to create the best environmental lighting effect for customers.

[0093] The store entry reminder / security is based on the environmental images collected by the AI ​​smart box 200. When someone enters the store, if it is business hours, the salesperson will be reminded on the smart electronic device APP that a customer has entered the store to shop. If it is non-business hours, an alarm message will be issued on the smart electronic device APP to remind people of intrusion.

[0094] Energy saving is based on the environmental image collected by the AI ​​Smart Box 200. When a customer is detected entering the store, the lights in the customer area are adjusted to 100% brightness to facilitate customers to purchase goods. If no customer is detected within the set time, the lights are automatically dimmed to save energy.

[0095] The present invention forms an IoT network through AI smart lights and AI smart boxes, and forms an intelligent commercial lighting system with servers and intelligent electronic devices. The AI ​​smart lights can use imaging sensors to automatically perceive shopping mall environment information and target product information, and through reasoning and analysis, realize automatic adjustment of parameters such as brightness, color temperature and color. The AI ​​smart box uses integrated imaging sensors to realize functions such as customer detection and product heat analysis, as well as other additional commercial applications, such as regional heat maps, product heat maps, scene control, security, store entry reminders, energy saving and other functions, with rich functions.

[0096] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. Commercial lighting system based on AI oT and sensor network, characterized by: include: server; At least one AI smart light, connected to the server; At least one AI smart box, communicating with the AI ​​smart light and the server; An intelligent electronic device, which is communicatively connected with the AI ​​smart light, the AI ​​smart box and the server; The AI ​​smart light includes an LED light, a first imaging sensor, a first wireless communication network, a first gateway, a first AI processor and a controller; the first wireless communication network is used to establish a network connection with the AI ​​smart box, and the first gateway is used to establish a communication connection with the server and the smart electronic device; the first imaging sensor is used to collect image data of the commodity and the environment in which the commodity is located, the first AI processor is used to process the image data collected by the first imaging sensor and set a spectrum scheme to send to the controller, and the controller is used to control the LED light to perform corresponding light adjustment according to the spectrum scheme; the AI ​​smart box includes a second imaging sensor, a second wireless communication network, a second gateway and a second AI processor; the second wireless communication network is used to establish a network connection with the AI ​​smart light, the second gateway is used to establish a communication connection with the server and the smart electronic device, the second imaging sensor is used to collect environmental images including customers and commodities, the second AI processor processes the environmental images to obtain commodity information and passenger flow information, and the second gateway is used to send the information processed by the second AI processor to the server to generate a regional heat map and a commodity heat map.

2. The lighting method of the commercial lighting system based on AI oT and sensor network as claimed in claim 1, characterized in that: include: Acquire image data of the product and the environment in which the product is located; Adjust lighting based on image data; Acquire environmental images including customers and products; Estimate regional heat map and product heat map data based on environmental images; Displays regional heat map and product heat map data.

3. The lighting method of the commercial lighting system based on AI oT and sensor network according to claim 2 is characterized in that: The step of adjusting the lighting according to the image data includes: Perform inference analysis on image data to obtain product information; Searching for a pre-stored spectral formula corresponding to the product information according to the product information; Adjust the light according to the spectrum recipe.

4. The lighting method of the commercial lighting system based on AI oT and sensor network according to claim 3 is characterized in that: The product information includes product location information, category information, color information and style information.

5. The lighting method of the commercial lighting system based on AI oT and sensor network according to claim 2, characterized in that: The estimating of the regional heat map and the commodity heat map data according to the environment image includes: Count the number of customers in the environment image; Calculate the location information of each customer in the environment venue; With the location of the target product in the environment as the center, set a circular area that affects the target product; Generate a product heat map based on the number of valid people in the circular area.

6. The lighting method of the commercial lighting system based on AI oT and sensor network according to claim 5, characterized in that: After setting a circular area affecting the target product with the location of the target product in the environment as the center, the method further includes: Calculate the dwell time of each customer in the circular area; If the residence time is greater than the set threshold, the customer is determined to be a valid customer attracted by the target product.

7. The lighting method of the commercial lighting system based on AI oT and sensor network according to claim 5, characterized in that: After generating the commodity heat map according to the effective number of people in the circular area, the method further includes: Set the scene heat area with the center of the environment site as the center of the circle; Generate a regional heat map for the crowd density in the scene heat area.

Images