A face recognition device and memory cleaning method thereof

Abstract

An embodiment of the present invention provides a face recognition device and a memory cleaning method thereof, which relate to the field of memory cleaning technology. Among them, this face recognition device can execute steps S1 to S6 to clean the memory: S1, the processor controls the clock chip to send an electrical signal of a preset frequency. S2, after receiving the electrical signal of the preset frequency, the communication module sends a memory query command to the processor, S3, obtains the usage of a specified area in the memory, and performs judgment and processing based on the usage. S4, when it is judged that the usage is above the first preset value and less than the second preset value, a memory cleaning request is sent to the back-end platform server. S5, when it is judged that the usage is above the second preset value, or when a memory cleaning command sent by the back-end platform server is received, the communication module sends an electrical signal of a preset frequency to the processor. S6, the processor receives the electrical signal of the preset frequency, and then performs memory cleaning on the specified area of ​​the memory.

Description

Technical Field

[0001] The present invention relates to the field of memory cleaning technology, and in particular to a face recognition device and a memory cleaning method thereof. Background Art

[0002] With the rapid development of the intelligent era, facial recognition smart terminal devices are increasingly used in people's lives, such as smart gate control and smart attendance.

[0003] To query raw data, facial recognition smart terminal devices typically save the captured image data to their own memory during the facial recognition image acquisition process, making it easier for administrators to query the raw data later. For example, in smart attendance applications, if the backend server does not save the data sent remotely by the smart terminal device, if you need to continue querying data for that period, you can query the raw data in the smart terminal device's memory in real time.

[0004] Because smart terminal devices store image data in their memory after each facial recognition session, this can lead to insufficient memory space over time. A typical solution is for management personnel to clear unnecessary memory space on-site. However, by the time the management personnel can manually clear the memory, the smart terminal device is already unable to perform normal facial recognition due to insufficient memory space, leaving the device unusable for a period of time.

[0005] Furthermore, if managers need to manage multiple facial recognition terminals at the same time, they have to go on site to clean up the memory data of each device. In addition, the time when the memory space of each device is insufficient is uncertain. This is not only troublesome, but also wastes time and increases maintenance costs.

[0006] In view of this, the applicant filed this application after studying the existing technology. Summary of the Invention

[0007] The present invention provides a face recognition device and a memory clearing method thereof to improve at least one of the above-mentioned technical problems.

[0008] First,

[0009] An embodiment of the present invention provides a facial recognition device comprising a processor, a memory, a communication module, and a clock chip. The processor and the communication module are connected via USB and / or serial communication. The processor and the communication module are each electrically connected to the clock chip. The processor is electrically connected to the memory. The facial recognition device can execute steps S1 to S6 to clear the memory:

[0010] S1. The processor controls the clock chip to send out an electrical signal of a preset frequency.

[0011] S2. After receiving the electrical signal of the preset frequency, the communication module sends a memory query command to the processor.

[0012] S3. Obtain the usage of the specified area in the memory, and perform judgment and processing based on the usage.

[0013] S4. When it is determined that the usage is greater than the first preset value and less than the second preset value, a memory cleanup request is sent to the backend platform server.

[0014] S5. When it is determined that the usage is above the second preset value, or when a memory cleanup command is received from the background platform server, the communication module sends an electrical signal of a preset frequency to the processor.

[0015] S6. The processor receives the electrical signal of the preset frequency and then performs memory clearing on the designated area of ​​the memory.

[0016] Second aspect,

[0017] An embodiment of the present invention provides a memory clearing method for a face recognition device, which is performed from the communication module side and includes steps A1 to A4.

[0018] A1. Receive an electrical signal of a preset frequency and then issue a memory query command. The electrical signal of the preset frequency is issued by a clock chip configured by the processor.

[0019] A2. Receive the usage of the specified area in the memory and perform judgment and processing based on the usage.

[0020] A3. When it is determined that the usage is greater than the first preset value and less than the second preset value, a memory cleanup request is sent to the backend platform server.

[0021] A4. When it is determined that the usage is above the second preset value, or when a memory cleanup command is received from the background platform server, an electrical signal of a preset frequency is sent so that the processor can receive the electrical signal of the preset frequency and perform memory cleanup on the designated area in the memory.

[0022] Thirdly,

[0023] An embodiment of the present invention provides a memory clearing method for a face recognition device, which is written from the processor side and includes steps B1 to B3.

[0024] B1. Send a control signal so that the clock chip sends an electrical signal of a preset frequency after receiving the control signal.

[0025] B2. Receive a memory query command, then query and return the usage of a specified memory area. The memory query command is issued by the communication module after receiving an electrical signal of a preset frequency.

[0026] B3. Receive an electrical signal of a preset frequency and perform memory cleanup on a designated area of ​​the memory. The electrical signal of the preset frequency is issued when the communication module determines that the usage is above a second preset value or receives a memory cleanup command from a backend platform server.

[0027] By adopting the above technical solution, the present invention can achieve the following technical effects:

[0028] The facial recognition device of the present invention can automatically and remotely clean the memory, eliminating the hassle of manual on-site cleaning and saving corresponding maintenance costs. It offers the advantages of low cost, ease of use, automatic detection and control, and both remote and automatic cleaning. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0030] Figure 1 This is a flowchart of a memory clearing method for a face recognition device.

[0031] Figure 2 This is the circuit diagram of a face recognition device.

[0032] Figure 3 This is a logic diagram of the processor side of the memory cleaning method of the face recognition device.

[0033] Figure 4 This is a logic diagram of the communication device side of the memory cleaning method of the face recognition device. DETAILED DESCRIPTION

[0034] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0035] Example 1

[0036] See also Figures 1 to 4 A first embodiment of the present invention provides a face recognition device, comprising a processor U1, a memory U5, a communication module U2, and a clock chip U3. The processor U1 and the communication module U2 are connected via a USB and / or serial port. The processor U1 and the communication module U2 are each electrically connected to the clock chip U3. The processor U1 is electrically connected to the memory U5.

[0037] Specifically, the face recognition terminal device can exchange data with the back-end management platform center (referred to as the back-end platform server) through the 4G communication module U2.

[0038] In actual use, memory U5 is rationally partitioned. One portion is used for system and app storage, while another is dedicated to storing the image data needed for face recognition (this data is saved in a specific file format to facilitate subsequent recognition and cleaning). This storage space is represented by the folder DATA. The designated area in this article refers to this folder, and the content to be cleaned in this article is the relevant image data in this folder.

[0039] The face recognition device can perform steps S1 to S6 to clear the memory:

[0040] S1. Processor U1 controls clock chip U3 to send out an electrical signal of a preset frequency.

[0041] Specifically, when the processor is working normally, the clock chip U3 and the real-time clock chip U3 related registers are configured through I2C so that the frequency output by the CLKOUT pin of the clock chip U3 is F.

[0042] S2, after receiving the electrical signal of the preset frequency, the communication module U2 sends a memory query command to the processor U1.

[0043] S3. Obtain the usage of the specified area in the memory U5, and perform judgment and processing based on the usage.

[0044] On the basis of the above embodiment, in an optional embodiment of the present invention, step S3 specifically includes steps S31 to S34.

[0045] S31. Obtain the usage of the specified area in the memory U5 and upload it to the backend platform server.

[0046] S32: Determine whether the usage is less than a first preset value.

[0047] S33: When the usage is less than the first preset value, continue to send memory query commands to the processor U1 to update the acquired usage. Otherwise, determine whether the usage is greater than the first preset value and less than the second preset value.

[0048] S34. When it is determined that the usage amount is not less than the second preset value, determine whether the usage amount is greater than the second preset value.

[0049] In this embodiment, the usage of a specified area is expressed as a percentage of the used storage. Assume that the storage capacity of DATA is M. M0, M1, and M2 are M multiplied by a certain percentage. Here, M>M2>M1. The usage is M0 / M=P0, M1 / M=P1, and M2 / M=P2. P0 is the percentage of DATA's used capacity in real time and is a variable. P1 is the memory overage threshold 1. P2 is the memory overage threshold 2.

[0050] In other embodiments, an unused percentage, unused storage amount, or used storage amount that is equal to the used percentage may be used. These equivalent alternative technical solutions should all fall within the scope of protection of the present invention.

[0051] S4. When it is determined that the usage is greater than the first preset value and less than the second preset value, a memory cleanup request is sent to the backend platform server.

[0052] S5. When it is determined that the usage is above the second preset value, or when a memory cleanup command is received from the background platform server, the communication module U2 sends an electrical signal of a preset frequency to the processor U1.

[0053] S6. The processor U1 receives the electrical signal of the preset frequency, and then clears the memory of the designated area of ​​the memory U5.

[0054] Specifically, the core system composed of processor U1 and memory U5 has been installed with an automatic memory cleaning APP. When an electrical signal of a preset frequency is received, the APP will be called to automatically clean the contents of the DATA file.

[0055] like Figure 3 and Figure 4 As shown, the embodiment of the present invention specifically includes the following steps:

[0056] Step 1: When the device is working normally, the processor U1 configures the relevant registers of the clock chip U3 through I2C, so that the CLKOUT pin of the clock chip U3 outputs the frequency of the F waveform.

[0057] Step 2: The communication module U2 detects a signal with a frequency of F on GPIO2. The communication module U2 sends a related query command to the processor U1 through the serial port, reads the space capacity percentage P0 of the DATA in the memory U5, and uploads the P0 data to the back-end platform server for display, and performs judgment processing at the same time.

[0058] Step 3: When P0 < P1, the communication module U2 does not send a remote memory cleaning request command to the backend platform server, and the communication module U2 continues to read and update the uploaded P0.

[0059] Step 4: When P1 ≤ P0 < P2, the communication module U2 sends a remote memory cleaning request command to the backend platform server. If the backend management personnel agree to this request command, the backend platform server will send a command agreeing to memory cleaning to the communication module U2. After the communication module U2 analyzes it, it will output (forward the signal input by GPIO2) a signal with a frequency of F to the IO1 port of the processor U1 through the GPIO1 port.

[0060] At this time, after detecting a waveform with a frequency of F on the IO1 of the processor U1, the processor U1 believes that an automatic cleaning operation will be performed, and the processor U1 will call the automatic cleaning APP to delete the content under the DATA file.

[0061] Step 5: If the backend management personnel do not agree to send the memory cleaning command due to some special reasons, as the face data continues to increase, P0 will also continue to increase. Until P0 ≥ P2, the communication module U2 will forcibly output (forward the signal input by GPIO2) a signal with a frequency of F to the IO1 port of the processor U1 through the GPIO1 port. At this time, after detecting a waveform with a frequency of F on the IO1 of the processor U1, the processor U1 believes that an automatic cleaning operation will be performed, and the processor U1 will call the automatic cleaning APP to delete the content under the DATA file.

[0062] Through Step 1 to Step 6, the automatic cleaning and remote control cleaning of the memory of the face recognition intelligent terminal device are finally realized.

[0063] The face recognition device of the embodiment of the present invention can realize automatic cleaning and remote control cleaning of the memory. It avoids the trouble brought by manual on-site cleaning and saves the corresponding maintenance costs. It has the advantages of low cost, convenient application, automatic detection and control, and at the same time has the advantages of remote control cleaning and automatic control cleaning.

[0064] As Figure 2 shown, on the basis of the above embodiment, in an optional embodiment of the present invention, the memory U5 is an EMMC. The processor U1 is an MPU. The communication module U2 is a 4G communication module U2. Specifically, the communication module U2 is a 4G module adopting the OPEN scheme, and it can execute the pre-stored program. For example: EC20 of Shanghai Quectel.

[0065] In this embodiment, the processor and memory U5 form the core system. The processor internally includes a PMIC, CPU, DDR3, etc., has audio and video codec functions, and includes a MIPI_DSI interface, a USB interface, and a combination circuit containing Wi-Fi, Bluetooth, Ethernet, etc. In practice, it runs on the Android platform. IO1 is the processor's GPIO port and IO1 is an input port. The other power conversion circuits of this combination are not shown in the diagram. The processor and memory U5 communicate via the SDIO interface.

[0066] GPIO1 is the output port of communication module U2, and GPIO2 is the input port of communication module U2. The processor and communication module U2 communicate via USB and serial ports to exchange data. Specifically, the facial recognition device also includes a common-mode inductor U6 and a level conversion chip U7. Communication module U2 is connected to the USB interface of processor U1 via common-mode inductor U6. The serial port of communication module U2 and the serial port of processor U1 are electrically connected via level conversion chip U7.

[0067] Specifically, the common mode inductor U6 integrates electrostatic protection. The level conversion chip U7 is used to match the serial communication levels of the processor and the communication module U2.

[0068] like Figure 2 As shown, based on the above embodiment, in an optional embodiment of the present invention, the processor U1 is connected to the memory U5 via the SDIO interface. The processor U1 is connected to the clock chip U3 via the I2C bus.

[0069] In this embodiment, only after the processor operates normally and the clock chip U3 is controlled to output a fixed frequency, the entire system will enter the memory automatic cleaning detection mechanism. This operation is not performed in the sleep state.

[0070] like Figure 2 As shown, based on the above embodiment, in an optional embodiment of the present invention, the face recognition device further includes a display screen U4 with a touch screen. The processor U1 is electrically connected to the display screen U4 via a MIPI interface.

[0071] like Figure 2As shown, based on the above embodiment, in an optional embodiment of the present invention, the face recognition device further includes a first transistor Q1, a first resistor R1, and a second resistor R2. The first resistor R1 and the second resistor R2 are pull-up resistors. The CLKOUT output pin of the clock chip U3 is electrically connected to the base of the first transistor Q1 and the first end of the first resistor R1. The second end of the first resistor R1 is connected to the first power supply VDD. The emitter of the first transistor Q1 is grounded. The collector of the first transistor Q1 is electrically connected to the GPIO2 input port of the communication module U2 and the first end of the second resistor R2. The second end of the second resistor R2 is connected to the second power supply VCC.

[0072] Preferably, the facial recognition device further includes a third resistor R3, a fourth resistor R4, a fifth resistor R5, a sixth resistor R6, a second transistor Q2, and a third transistor Q3. The sixth resistor R6 is a pull-up resistor. The third resistor R3, the fourth resistor R4, and the fifth resistor R5 are current-limiting resistors. The GPIO1 output port of the communication module U2 is electrically connected to the first end of the fourth resistor R4. The second end of the fourth resistor R4 is electrically connected to the base of the second transistor Q2. The emitter of the second transistor Q2 is grounded. The collector of the second transistor Q2 is electrically connected to the first end of the third resistor R3, the first end of the fifth resistor R5, and the base of the third transistor Q3. The second end of the third resistor R3 is connected to the first power supply VDD. The second end of the fifth resistor R5 is grounded. The emitter of the third transistor Q3 is grounded. The collector of the third transistor Q3 is electrically connected to the I01 input port of the processor U1 and the first end of the sixth resistor R6. The second end of the sixth resistor R6 is connected to the first power supply VDD.

[0073] Specifically, the first transistor Q1, the second transistor Q2, and the third transistor Q3 are all NPN transistors. The first power supply VDD is the power supply for the internal IO port of the processor U1. The second power supply VCC is the power supply for the IO port of the communication module U2.

[0074] This embodiment of the present invention utilizes the frequency characteristics of the real-time clock chip U3 and the switching characteristics of an electronic switch. It also employs automatic I / O port detection and control technology, 4G wireless communication, and I2C communication technology to implement a memory clearing method for a facial recognition device.

[0075] When the processor is working normally, the relevant registers of the real-time clock chip U3 are configured through I2C, so that the frequency output by the CLKOUT pin of the real-time clock chip U3 is F. At this time, the communication module U2 will detect a waveform with a frequency of F on GPIO2. The communication module U2 sends a relevant query command to the processor through the serial port to read the space capacity percentage P0 of the DATA under the memory U5;

[0076] The communication module U2 uploads the P0 data to the backend platform server for display and simultaneously performs judgment and processing. When P0 < P1, the communication module U2 does not send a remote memory cleaning request command to the backend platform server; when P1 ≤ P0 < P2, the communication module U2 sends a remote memory cleaning request command to the backend platform server. The data of the occupied ratio of a specific memory space is uploaded to the backend platform server, enabling the management personnel to intuitively understand the remaining memory space of the current device.

[0077] If the backend management personnel approve the request command, the backend platform server will send a command to approve the memory cleaning to the communication module U2. After the communication module U2 analyzes it, it will output a signal with a frequency of F to the IO1 port of the processor through the GPIO1 port (forwarding the signal input by the GPIO2 port). When the processor detects a waveform with a frequency of F on the IO1, the processor believes that an automatic cleaning operation will be performed, and the processor will call the automatic cleaning APP to delete the content under the DATA file.

[0078] If the backend management personnel do not approve the memory cleaning command for some special reasons, as the face data continues to increase, P0 also continues to increase. Until P0 ≥ P2, the communication module U2 will forcibly output a signal with a frequency of F to the IO1 port of the processor through the GPIO1 port (forwarding the signal input by the GPIO2). When the processor detects a waveform with a frequency of F on the IO1, the processor believes that an automatic cleaning operation will be performed, and the processor will call the automatic cleaning APP to delete the content under the DATA file. In this way, the automatic cleaning and remote control cleaning of the memory of the face recognition intelligent terminal device are finally realized.

[0079] The circuit structure of the face recognition device in the embodiment of the present invention is simple and easy to implement, with the advantages of low cost, convenient application, automatic detection, control, remote control cleaning and automatic cleaning. It is actually applied to the face recognition intelligent terminal device to realize the automatic cleaning and remote control cleaning of the memory of the face recognition intelligent terminal device; thus avoiding the trouble brought by manual on-site cleaning and saving the corresponding maintenance costs.

[0080] Embodiment 2

[0081] Please refer to Figure 3 , the second embodiment of the present invention provides a method for cleaning the memory of a face recognition device, which is written from the perspective of the communication module and includes steps A1 to A4.

[0082] A1. Receive an electrical signal with a preset frequency, and then issue a memory query command. Among them, the electrical signal with a preset frequency is issued by a clock chip configured by the processor.

[0083] A2. Receive the usage of the specified area in the memory and perform judgment and processing based on the usage.

[0084] A3. When it is determined that the usage is greater than the first preset value and less than the second preset value, a memory cleanup request is sent to the backend platform server.

[0085] A4. When it is determined that the usage is above the second preset value, or when a memory cleanup command is received from the background platform server, an electrical signal of a preset frequency is sent so that the processor can receive the electrical signal of the preset frequency and perform memory cleanup on the designated area in the memory.

[0086] Based on the above embodiment, in an optional embodiment of the present invention, step A2 specifically includes:

[0087] A21. Obtain the usage of the specified area in the storage and upload it to the backend platform server.

[0088] A22. Determine whether the usage is less than a first preset value.

[0089] A23. When the usage is less than the first preset value, continue to send memory query commands to the processor to update the acquired usage. Otherwise, determine whether the usage is greater than the first preset value and less than a second preset value.

[0090] A24. When it is determined that the usage amount is not less than the second preset value, determine whether the usage amount is greater than the second preset value.

[0091] Example 3:

[0092] See also Figure 4 The third embodiment of the present invention provides a memory cleaning method for a face recognition device, which is written from the processor side and includes steps B1 to B3.

[0093] B1. Send a control signal so that the clock chip sends an electrical signal of a preset frequency after receiving the control signal.

[0094] B2. Receive a memory query command, then query and return the usage of a specified memory area. The memory query command is issued by the communication module after receiving an electrical signal of a preset frequency.

[0095] B3. Receive an electrical signal of a preset frequency and perform memory cleanup on a designated area of ​​the memory. The electrical signal of the preset frequency is issued when the communication module determines that the usage is above a second preset value or receives a memory cleanup command from a backend platform server.

[0096] In the several embodiments provided in the embodiments of the present invention, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device and method embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions, and operations of the devices, methods, and computer program products according to multiple embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or part of the code, which contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the boxes can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, as well as the combination of boxes in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified functions or actions, or can be implemented using a combination of dedicated hardware and computer instructions.

[0097] In addition, the functional modules in the various embodiments of the present invention may be integrated together to form an independent part, or each module may exist independently, or two or more modules may be integrated to form an independent part.

[0098] If the functions are implemented in the form of software modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, electronic device, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage media include various media that can store program code, such as USB flash drives, mobile hard drives, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks. It should be noted that, in this document, the terms "comprise," "include," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or device that includes a series of elements includes not only those elements but also other elements not explicitly listed, or also includes elements inherent to such process, method, article, or device. Without further constraints, an element defined by the phrase "comprises a..." does not preclude the existence of additional identical elements in the process, method, article or apparatus that includes the element.

[0099] The terms used in the embodiments of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The singular forms "a", "an", "the" and "the" used in the embodiments of the present invention and the appended claims are also intended to include plural forms unless the context clearly indicates otherwise.

[0100] It should be understood that the term "and / or" as used herein is merely a description of the relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " in this document generally indicates that the associated objects are in an "or" relationship.

[0101] The word "if," as used herein, may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to the determination" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)," depending on the context.

[0102] The "first" and "second" mentioned in the embodiments are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It is understood that the specific order or precedence of "first" and "second" can be interchanged where appropriate. It should be understood that the objects distinguished by "first" and "second" can be interchanged where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein.

[0103] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be within the scope of protection of the present invention.

Claims

1. A face recognition device, characterized in that: The device comprises a processor, a memory, a communication module, and a clock chip; the processor and the communication module are connected via USB and / or serial communication; the processor and the communication module are electrically connected to the clock chip, respectively; the processor is electrically connected to the memory; and the face recognition device can perform the following steps to clear the memory: The processor controls the clock chip to send out an electrical signal of a preset frequency; After receiving the electrical signal of the preset frequency, the communication module sends a memory query command to the processor to obtain the usage of the specified area in the memory and perform judgment and processing based on the usage; when it is determined that the usage is greater than the first preset value and less than the second preset value, a memory cleanup request is sent to the backend platform server; when it is determined that the usage is greater than the second preset value, or when a memory cleanup command is received from the backend platform server, the communication module sends an electrical signal of the preset frequency to the processor; The processor receives an electrical signal of a preset frequency and then performs memory cleanup on a designated area of ​​the memory; The face recognition device further includes a first transistor, a first resistor and a second resistor; the first resistor and the second resistor are pull-up resistors; The CLKOUT output pin of the clock chip is electrically connected to the base of the first transistor and the first end of the first resistor; the second end of the first resistor is connected to the first power supply; the emitter of the first transistor is grounded; the collector of the first transistor is electrically connected to the GPIO2 input port of the communication module and the first end of the second resistor; the second end of the second resistor is connected to the second power supply; The face recognition device further includes a third resistor, a fourth resistor, a fifth resistor, a sixth resistor, a second transistor and a third transistor; the sixth resistor is a pull-up resistor; the third resistor, the fourth resistor and the fifth resistor are current-limiting resistors; The GPIO1 output port of the communication module is electrically connected to the first end of the fourth resistor; the second end of the fourth resistor is electrically connected to the base of the second transistor; the emitter of the second transistor is grounded; the collector of the second transistor is electrically connected to the first end of the third resistor, the first end of the fifth resistor and the base of the third transistor; the second end of the third resistor is connected to the first power supply; the second end of the fifth resistor is grounded; the emitter of the third transistor is grounded; the collector of the third transistor is electrically connected to the I01 input port of the processor and the first end of the sixth resistor; and the second end of the sixth resistor is connected to the first power supply.

2. The face recognition device according to claim 1, characterized in that Get the usage of a specified area in the memory and make judgments and processes based on the usage, including: Get the usage of the specified area in the storage and upload it to the backend platform server; Determining whether the usage is less than a first preset value; When the usage is less than the first preset value, continuously sending memory query commands to the processor to update the acquired usage; otherwise, determining whether the usage is greater than the first preset value and less than a second preset value; When it is determined that the usage amount is not less than the second preset value, it is determined whether the usage amount is greater than the second preset value.

3. The face recognition device according to claim 1 or 2, characterized in that: The face recognition device also includes a common-mode inductor and a level conversion chip; the communication module is communicatively connected to the USB interface of the processor via the common-mode inductor; the serial port of the communication module and the serial port of the processor are electrically connected via the level conversion chip.

4. The face recognition device according to claim 1 or 2, characterized in that: The processor is connected to the memory via an SDIO interface; the processor is connected to the clock chip via an I2C bus.

5. The face recognition device according to claim 1 or 2, characterized in that: The memory is EMMC; the processor is MPU; and the communication module is a 4G communication module.

6. A memory cleaning method for a face recognition device, characterized in that: Used to control a face recognition device according to any one of claims 1 to 5; The memory cleaning method includes: Receive an electrical signal of a preset frequency and then issue a memory query command; wherein the electrical signal of the preset frequency is issued by a clock chip configured by the processor; Receive the usage of a specified area in the memory and make judgments and processes based on the usage; When it is determined that the usage is greater than the first preset value and less than the second preset value, a memory cleanup request is sent to the backend platform server; When it is determined that the usage is above the second preset value, or when a memory cleanup command is received from the background platform server, an electrical signal of a preset frequency is sent so that the processor can receive the electrical signal of the preset frequency and perform memory cleanup on the designated area in the memory.

7. The memory cleaning method according to claim 6, characterized in that: Receive the usage of a specified area in the memory and perform judgment and processing based on the usage, including: Get the usage of the specified area in the storage and upload it to the backend platform server; Determining whether the usage is less than a first preset value; When the usage is less than the first preset value, continuously sending memory query commands to the processor to update the acquired usage; otherwise, determining whether the usage is greater than the first preset value and less than a second preset value; When it is determined that the usage amount is not less than the second preset value, it is determined whether the usage amount is greater than the second preset value.

8. A memory cleaning method for a face recognition device, characterized in that: Used to control a face recognition device according to any one of claims 1 to 5; The memory cleaning method includes: Sending a control signal so that the clock chip sends an electrical signal of a preset frequency after receiving the control signal; Receive a memory query command, and then query and return the usage of a specified area of ​​the memory; wherein the memory query command is issued by the communication module after receiving an electrical signal of a preset frequency; Receive an electrical signal of a preset frequency and perform memory cleaning on a specified area of ​​the memory; wherein, the electrical signal of the preset frequency is issued when the communication module determines that the usage is above a second preset value, or receives a memory cleaning command sent by a background platform server.

Images