Unmanned retail cabinet control system and method, computer readable storage medium and unmanned retail cabinet

Abstract

The invention discloses an unmanned retail cabinet control system and method, a computer readable storage medium and an unmanned retail cabinet, and the system comprises a signal obtaining module which is used for obtaining video signals and / or sound signals around the unmanned retail cabinet; the information processing module is used for receiving the signal input by the signal acquisition module and generating an execution instruction, and the execution instruction at least comprises an abnormal response instruction; and the execution module is used for receiving the execution instruction issued by the information processing module and executing a corresponding response program, and the execution module comprises a warning terminal and / or a communication terminal. Surrounding video and sound signals are captured in real time through the signal acquisition module, and judgment and response of the information processing module to abnormal events are combined, so that the limitation that a traditional unmanned retail cabinet only focuses on commodity theft prevention is broken through. When a consumer encounters personal safety events such as robbery and sudden diseases, the system can automatically trigger warning, record field information and even establish communication connection, equipment functions extend from commodity guarding to safety guarantee for the consumer, and the blank of the industry in the field of personal safety protection is filled.

Description

Technical Field

[0001] This invention relates to the field of unmanned retail cabinet technology, and more specifically, to a control system, method, computer-readable storage medium, and unmanned retail cabinet. Background Technology

[0002] In recent years, unmanned retail lockers have rapidly become widespread in the fresh and frozen food sector. However, traditional solutions either completely lack security features or concentrate technological resources on anti-theft modules, essentially treating consumers as potential targets rather than those requiring protection. This design logic causes the devices to completely fail in real-life personal safety incidents—when consumers encounter robbery, sudden illness, or violence from third parties, the anti-theft system cannot provide basic assistance.

[0003] In view of this, the present invention is proposed. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to overcome the shortcomings of the prior art and provide a control system, method, computer-readable storage medium and unmanned retail cabinet.

[0005] To achieve the above objectives, the technical solution of the present invention is as follows: In a first aspect, the present invention provides a control system for an unmanned retail cabinet, comprising: The signal acquisition module is used to acquire video and / or audio signals from the vicinity of the unmanned retail cabinet. The information processing module is used to receive the signal input from the signal acquisition module and generate an execution instruction, wherein the execution instruction includes at least an exception response instruction; An execution module is used to receive execution instructions issued by the information processing module and execute the corresponding response program. The execution module includes an alert terminal and / or a communication terminal.

[0006] Secondly, the present invention provides a control method for an unmanned retail cabinet, comprising: The information processing module of the unmanned retail cabinet determines whether an abnormal event has occurred based on the input signal. When an abnormal event occurs, the information processing module generates and sends an abnormal response instruction to the execution module, and the execution module executes the abnormal response program. After the information processing module issues an abnormal termination command, the execution module stops executing the abnormal response program.

[0007] In a preferred embodiment, an anomaly index is calculated based on the input signal, and when the anomaly index exceeds a set threshold, an abnormal event is determined to have occurred.

[0008] In a preferred embodiment, in n1 consecutive calculations, when the number of times the calculated abnormal index exceeds the set threshold is greater than or equal to m1, an abnormal event is determined to have occurred, where m1≤n1.

[0009] In a preferred embodiment, after an abnormal event occurs, if the number of times the calculated abnormal index exceeds the set threshold is less than m2 in n2 consecutive calculations, the abnormal event is determined to be resolved, and the information processing module issues an abnormal termination command, where m2≤n2.

[0010] In a preferred embodiment, after executing the exception response procedure, the execution module enters a first-level response state and alerts the terminal.

[0011] In a preferred embodiment, if the execution module does not receive an abnormal termination instruction within a first set time during the first-level response state, the execution module enters the second-level response state and starts recording on-site video / or audio.

[0012] In a preferred embodiment, if the execution module does not receive an abnormal termination instruction within a second set time during the second response state, the execution module enters the third response state and activates the communication terminal to establish a communication connection.

[0013] Thirdly, the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the control method described above.

[0014] Fourthly, the present invention provides an unmanned retail cabinet, including the control system described above, or employing the control method described above, or including the computer-readable storage medium described above.

[0015] Compared with the prior art, the beneficial effects of the present invention are reflected in: 1. Enhanced security protection, upgrading from merchandise theft prevention to personal protection: This invention uses a signal acquisition module to capture surrounding video and sound signals in real time, combined with an information processing module to judge and respond to abnormal events, breaking the limitations of traditional unmanned retail cabinets that only focus on merchandise theft prevention. When consumers encounter personal safety incidents such as robbery or sudden illness, the system can automatically trigger alarms, record on-site information, and even establish communication connections, extending the device's function from merchandise protection to consumer safety assurance, filling a gap in the industry in the field of personal safety protection.

[0016] 2. Reduce the probability of false positives and improve the accuracy of system response: This invention introduces an anomaly index calculation and multi-round verification mechanism, effectively avoiding the problem of false positives caused by a single signal trigger. This design ensures both the keen capture of real abnormal events and reduces unnecessary responses caused by non-abnormal situations such as accidental noise and brief interference, making the system operation more reliable.

[0017] 3. Tiered response mechanism optimizes resource allocation and balances protection effectiveness and cost: The system sets up a tiered response status of Level 1 (alarms), Level 2 (video / audio recording), and Level 3 (communication connection), with each level escalating gradually according to a set time. This design avoids ineffective resource consumption—minor anomalies only trigger basic alerts, while sustained anomalies only utilize higher-cost resources such as recording and communication. This ensures security while achieving a reasonable allocation of technical resources, reducing the daily operation and maintenance costs of the equipment.

[0018] 4. Enhance core competitiveness and expand commercial value boundaries: Compared to traditional unmanned retail cabinets that only have basic sales functions, this invention endows the equipment with security protection capabilities. This not only reduces equipment damage and merchandise loss caused by security incidents, but also enhances user trust by protecting consumer safety. This shift from "passive theft prevention" to "active protection" gives unmanned retail cabinets a differentiated advantage in market competition, bringing operators higher user retention rates and commercial value. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments are described clearly and completely below. The following embodiments are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0020] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0021] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0022] [Example 1] This embodiment provides a control system for an unmanned retail cabinet, which includes a signal acquisition module, an information processing module, and an execution module. The signal acquisition module acquires video and / or audio signals from the vicinity of the unmanned retail cabinet; the information processing module receives signals input from the signal acquisition module and generates execution instructions, which at least include an exception response instruction; the execution module receives the execution instructions from the information processing module and executes the corresponding response program, and the execution module includes an alert terminal and / or a communication terminal.

[0023] For example, The signal acquisition module includes: High-definition camera: Installed on the top and front of the unmanned retail cabinet, it can rotate 360 ​​degrees and collect video signals within a certain range around the cabinet, such as 5 meters. Sound sensor: Installed on the front of the unmanned retail cabinet, it can collect sound signals within a certain range around the cabinet, such as 5 meters; Infrared sensor: Used to detect if anyone is approaching the retail counter. When human activity is detected, the high-definition camera and sound sensor are automatically activated and put into operation.

[0024] The information processing module employs an embedded artificial intelligence computing platform, possessing image and sound recognition capabilities. It includes a built-in abnormal behavior recognition algorithm, capable of identifying abnormal behaviors such as violent physical conflict, sudden collapse, loud cries for help, and equipment damage. A built-in abnormal sound recognition algorithm can identify abnormal sounds such as screams, breaking glass, fighting sounds, and cries for help. Furthermore, the sound recognition algorithm can also recognize and respond to preset keywords.

[0025] Furthermore, the information processing module is equipped with a local storage unit, which can temporarily store processed information and instructions.

[0026] The execution module includes: Warning terminal: includes an audible alarm and a flashing warning light.

[0027] Communication terminal: Includes network module and call module, can be connected to remote monitoring platform and preset emergency contacts, and can dial alarm when necessary.

[0028] Storage unit: Can store video and audio recordings. Furthermore, it includes cloud storage functionality, allowing video and audio recordings to be uploaded to the cloud for safekeeping.

[0029] Interactive terminal: Includes touch screen and microphone, can integrate product selection function of unmanned retail cabinet, and realize two-way communication with remote personnel.

[0030] The modules are connected via an internal bus to ensure sufficient signal transmission rate and guarantee real-time performance and reliability.

[0031] [Example 2] This embodiment provides a control method for unmanned retail cabinets, implemented based on the control system of the aforementioned embodiment. The control method includes: The information processing module of the unmanned retail cabinet determines whether an abnormal event has occurred based on the input signals. When an abnormal event occurs, the information processing module generates and sends an abnormal response command to the execution module, which then executes the abnormal response program. After the information processing module issues an abnormal termination command, the execution module stops executing the abnormal response program.

[0032] An anomaly index is calculated based on the input signal. When the anomaly index exceeds a set threshold, an anomaly event is determined to have occurred.

[0033] In n1 consecutive calculations, if the calculated abnormal index exceeds the set threshold more than or equal to m1 times, an abnormal event is determined to have occurred, where m1 ≤ n1. After an abnormal event occurs, in n2 consecutive calculations, if the calculated abnormal index exceeds the set threshold less than m2 times, the abnormal event is determined to have been resolved, and the information processing module issues an abnormal termination command, where m2 ≤ n2.

[0034] In a preferred embodiment, after executing the exception response procedure, the execution module enters a Level 1 response state, alerting the terminal to issue an alarm. In the Level 1 response state, if the execution module does not receive an exception termination command within a first predetermined time, it enters a Level 2 response state and initiates on-site video and / or audio recording. In the Level 2 response state, if the execution module does not receive an exception termination command within a second predetermined time, it enters a Level 3 response state and activates the communication terminal to establish a communication connection.

[0035] A specific example is as follows: After the unmanned retail cabinet is powered on, the system performs a self-test to check whether each module is working properly.

[0036] The initial anomaly index threshold is set to 60 (range 0-100), n1=5, m1=3, n2=5, m2=1. The first set time is set to 30 seconds, and the second set time is set to 60 seconds. The system enters standby mode, with only the infrared sensor active and other modules in low-power mode.

[0037] When the infrared sensor detects a person approaching, the wake-up signal acquisition module starts working.

[0038] A high-definition camera captures one image frame every 2 seconds, while a sound sensor continuously collects sound signals. The information processing module analyzes the captured image and sound signals to calculate an anomaly index: for image signals, anomalies are identified and assigned a score from 0 to 100; for sound signals, anomalies are identified and assigned a score from 0 to 100. The anomaly index is a weighted average of the image and sound scores; for example, the weights are 0.6 and 0.4, respectively.

[0039] In five consecutive calculations (n1=5), an abnormal event is determined to have occurred when the abnormality index exceeds the threshold of 60 three or more times (m1=3).

[0040] Then, the information processing module generates an exception response instruction and sends it to the execution module.

[0041] After receiving the instruction, the execution module enters the first-level response state: it activates the high-decibel alarm and flashing warning light, emitting an audible and visual alarm that lasts for 10 seconds with 2-second intervals.

[0042] In the first-level response state, if no abnormal termination command is received within the first set time (e.g., 30 seconds), the execution module enters the second-level response state: the high-definition camera starts to record video continuously, the frame rate is increased to 60fps, the sound sensor starts to record sound continuously, and the recorded audio and video files are stored in the local storage unit in real time and / or uploaded to the cloud server synchronously.

[0043] In the Level 2 response state, if no abnormal termination command is received within the second set time (e.g., 60 seconds), the execution module enters the Level 3 response state: the communication terminal connects to the remote monitoring platform via the 4G module and uploads real-time audio and video streams; it automatically dials the preset emergency contact number (e.g., shopping mall security guard, nearby police station) and sends a text message containing the device location; and it activates the interactive terminal to facilitate two-way communication between on-site personnel and remote personnel.

[0044] During the abnormal event handling process, the information processing module continuously calculates the abnormality index.

[0045] If, in five consecutive calculations (n²=5), the anomaly index exceeds the threshold less than once (m²=1), the anomaly is considered resolved. The information processing module issues an anomaly termination command, the execution module stops executing the anomaly response program, and the system returns to normal operation.

[0046] In some implementations, the resolution of abnormal events can also be carried out through manual intervention, such as by setting a release control button on the unmanned retail cabinet, or by voice, touch or other operations, or by issuing commands remotely. This facilitates the quick resolution of the abnormal response status of the unmanned retail cabinet after manual confirmation that the abnormal event has been resolved or that the system has given a false alarm.

[0047] In some implementations, the abnormal response of unmanned retail cabinets can also be operated through manual intervention, such as by setting an "alarm" button on the unmanned retail cabinet, or by voice, touch and other operations. When a user encounters an emergency, the system can respond quickly and directly enter the abnormal response state, or directly enter a high-level abnormal response state, in order to achieve the fastest response and ensure the user's personal safety.

[0048] The following is a specific application scenario example of this embodiment: An elderly customer suddenly fainted while selecting items at an unmanned retail vending machine. The camera in the signal acquisition module captured the image of the person collapsing, and the anomaly index was calculated to be 85. Four out of five calculations showed the anomaly index exceeding the threshold, prompting the system to determine an abnormal event. The execution module entered a Level 1 response state, issuing an audible and visual alarm. If no termination command was received after 30 seconds, it entered a Level 2 response state, beginning to record video and audio of the scene. If no termination command was received after 60 seconds, it entered a Level 3 response state, contacting the remote monitoring platform and emergency contacts. After medical personnel arrived and provided assistance, the abnormal situation was resolved, and the system returned to normal.

[0049] The following is another specific application scenario example of this embodiment: A group of children were playing and laughing near the unmanned retail kiosks, making quite a bit of noise. The sound sensor detected the high-decibel sound, and the anomaly index was calculated to be 65. However, in five consecutive calculations, only two exceeded the threshold, failing to meet the condition m1=3, and the system did not classify it as an abnormal event. This avoided false alarms caused by normal playfulness.

[0050] [Example 3] This embodiment provides a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the control method provided in the foregoing embodiment.

[0051] [Example 4] This embodiment provides an unmanned retail cabinet, including the control system, control method, or computer-readable storage medium provided in the foregoing embodiments.

[0052] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0053] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-described technical content to create equivalent embodiments without departing from the scope of the present invention. The implementation schemes in the above embodiments can also be further combined or replaced. Any simple modifications, equivalent changes and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. A control system for an unmanned retail cabinet, characterized in that, include: The signal acquisition module is used to acquire video and / or audio signals around the unmanned retail cabinet; The information processing module is used to receive the signal input from the signal acquisition module and generate an execution instruction, wherein the execution instruction includes at least an exception response instruction; An execution module is used to receive execution instructions issued by the information processing module and execute the corresponding response program. The execution module includes an alert terminal and / or a communication terminal.

2. A control method for an unmanned retail cabinet, characterized in that, include: The information processing module of the unmanned retail cabinet determines whether an abnormal event has occurred based on the input signal. When an abnormal event occurs, the information processing module generates and sends an abnormal response instruction to the execution module, and the execution module executes the abnormal response program. After the information processing module issues an abnormal termination command, the execution module stops executing the abnormal response program.

3. The control method for unmanned retail cabinets as described in claim 2, characterized in that: An anomaly index is calculated based on the input signal. When the anomaly index exceeds a set threshold, an anomaly event is determined to have occurred.

4. The control method for unmanned retail cabinets as described in claim 3, characterized in that: In n1 consecutive calculations, if the calculated abnormality index exceeds the set threshold more than or equal to m1 times, an abnormal event is determined to have occurred, where m1≤n1.

5. The control method for unmanned retail cabinets as described in claim 4, characterized in that: After an abnormal event occurs, if the number of times the calculated abnormal index exceeds the set threshold is less than m2 in n2 consecutive calculations, the abnormal event is determined to be resolved, and the information processing module issues an abnormal termination command, where m2≤n2.

6. The control method for unmanned retail cabinets as described in claim 2, characterized in that: After the execution module executes the exception response procedure, it enters the first-level response state and issues an alarm to the warning terminal.

7. The control method for unmanned retail cabinets as described in claim 6, characterized in that: In the first-level response state, if the execution module does not receive an abnormal termination instruction within the first set time, the execution module enters the second-level response state and starts on-site video / or audio recording.

8. The control method for unmanned retail cabinets as described in claim 7, characterized in that: In the Level 2 response state, if the execution module does not receive an abnormal termination instruction within the second set time, the execution module enters the Level 3 response state and activates the communication terminal to establish a communication connection.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by the processor, it performs the control method according to any one of claims 2-8.

10. An unmanned retail cabinet, characterized in that: It includes the control system as described in claim 1, or the control method as described in any one of claims 2-8, or the computer-readable storage medium as described in claim 9.