Conference room patrol method and device, server and storage medium
By regularly obtaining conference room monitoring images and using graphic and text dialogue models to analyze, the problem of timely update in the conference room reservation system is solved, the utilization rate of conference rooms is improved, and the effective use of conference rooms is ensured.
Patent Information
- Application Number
- CN202411165591.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-22
- Publication Date
- 2024-12-27
AI Technical Summary
The use of the conference room is not updated in time in the conference room reservation system, resulting in low utilization of the conference room. Especially when the meeting is cancelled or the ended early, the user does not actively cancel the reservation, resulting in the actual idle conference room being unable to be booked.
By obtaining the monitoring image of the conference room at every preset time, analyzing the current usage information using the graphic and text dialogue model, and updating the status identifier in the conference reservation system when determining that the conference room is in a non-conference state, indicating that the conference room is idle, thus Update the usage of the conference room in a timely manner.
It realizes accurate and timely updates of conference rooms usage, improves the utilization rate of conference rooms, and enables cancelled or early ending meeting rooms to be re-booked.
Smart Images
Figure CN119204989A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of artificial intelligence technology, and in particular to a conference room inspection method, device, server and storage medium. Background Art
[0002] Companies in the fields of finance, insurance or technology have set up more meeting rooms for internal staff to better carry out their work, so as to facilitate receiving customers or exchanging technology. At present, in order to avoid time conflicts in the use of meeting rooms, major financial, insurance or technology companies have developed meeting room reservation systems to record the use of meeting rooms. However, when the meeting is cancelled or ends early, the user who reserved the meeting room will not actively cancel the meeting room reservation, resulting in the inability to update the meeting room usage recorded in the meeting room reservation system in a timely manner, making it impossible to book the actually idle meeting rooms, resulting in low utilization of the meeting rooms. Summary of the invention
[0003] The embodiments of the present application provide a conference room inspection method, device, server and storage medium, which are intended to accurately and timely update the conference room usage recorded in a conference reservation system to improve the utilization rate of the conference room.
[0004] In a first aspect, an embodiment of the present application provides a conference room inspection method, comprising:
[0005] Acquire a monitoring image currently collected by a target monitoring device at a preset time interval, wherein the target monitoring device is installed in a target conference room, and the target conference room is a conference room in a meeting state;
[0006] Inputting the monitoring image and the preset question command into the target graphic-text dialogue model, so that the target graphic-text dialogue model analyzes the monitoring image based on the preset question command to answer the current usage information of the target conference room;
[0007] When it is determined according to the current use information that the target conference room is in a non-conference state, the state identifier of the target conference room in the conference reservation system is updated to a first identifier, where the first identifier is used to indicate that the target conference room is in an idle state.
[0008] In a second aspect, an embodiment of the present application further provides a conference room inspection device, which is applied to a server, and the conference room inspection device includes:
[0009] An image polling module, used to obtain the monitoring image currently collected by the target monitoring device at a preset time interval, wherein the target monitoring device is installed in a target conference room, and the target conference room is a conference room in a meeting state;
[0010] A model calling module, used for inputting the monitoring image and the preset question command into the target graphic-text dialogue model, so that the target graphic-text dialogue model analyzes the monitoring image based on the preset question command to answer the current usage information of the target conference room;
[0011] The information updating module is used to update the state identifier of the target conference room in the conference reservation system to a first identifier when it is determined according to the current usage information that the target conference room is in a non-conference state, wherein the first identifier is used to indicate that the target conference room is in an idle state.
[0012] In a third aspect, an embodiment of the present application further provides a server, comprising a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, the steps of the conference room inspection method described in the first aspect are implemented.
[0013] In a fourth aspect, an embodiment of the present application further provides a storage medium for computer-readable storage, wherein a computer program is stored on the storage medium, wherein when the computer program is executed by a processor, the steps of the conference room inspection method described in the first aspect are implemented.
[0014] The embodiments of the present application provide a conference room inspection method, device, server and storage medium. The embodiments of the present application obtain surveillance images of a conference room in a meeting state at preset time intervals, and input the surveillance images and preset question commands into a target text-graphic dialogue model, so that the target text-graphic dialogue model analyzes the surveillance images based on the preset question commands to answer current usage information of the conference room in a meeting state, and then when it is determined that the target conference room is in a non-meeting state according to the current usage information, the status identifier of the corresponding conference room in the conference reservation system is updated to a first identifier indicating an idle state, so that when the meeting is cancelled or the meeting ends early, the conference room usage recorded in the conference reservation system can be accurately and timely updated, so that the conference room whose meeting is cancelled or the meeting ends early can be reserved, thereby effectively improving the utilization rate of the conference room. BRIEF DESCRIPTION OF THE DRAWINGS
[0015] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0016] Figure 1 This is a schematic diagram of a scenario for implementing the conference room inspection method provided in an embodiment of the present application;
[0017] Figure 2 This is a schematic diagram of the steps of a conference room inspection method provided in an embodiment of the present application;
[0018] Figure 3 It is a schematic diagram of the steps of another conference room inspection method provided in an embodiment of the present application;
[0019] Figure 4 is a schematic block diagram of a conference room inspection device provided in an embodiment of the present application;
[0020] Figure 5 It is a schematic block diagram of the structure of a server provided in an embodiment of the present application.
[0021] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION
[0022] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0023] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.
[0024] Companies in the fields of finance, insurance or technology have set up more meeting rooms for internal staff to better carry out their work, so as to facilitate receiving customers or exchanging technology. At present, in order to avoid time conflicts in the use of meeting rooms, major financial, insurance or technology companies have developed meeting room reservation systems to record the use of meeting rooms. However, when the meeting is cancelled or ends early, the user who reserved the meeting room will not actively cancel the meeting room reservation, resulting in the inability to update the meeting room usage recorded in the meeting room reservation system in a timely manner, making it impossible to book the actually idle meeting rooms, resulting in low utilization of the meeting rooms.
[0025] To solve the above problems, the embodiments of the present application provide a conference room inspection method, device, server and storage medium. The embodiments of the present application obtain surveillance images of conference rooms in a meeting state at preset time intervals, and input the surveillance images and preset question commands into a target graphic dialogue model, so that the target graphic dialogue model analyzes the surveillance images based on the preset question commands to answer the current usage information of the conference room in the meeting state, and then when it is determined that the target conference room is in a non-meeting state according to the current usage information, the state identifier of the corresponding conference room in the conference reservation system is updated to a first identifier indicating an idle state, so that when the meeting is cancelled or the meeting ends early, the conference room usage recorded in the conference reservation system can be accurately and timely updated, so that the conference room that is cancelled or the meeting ends early can be reserved, effectively improving the utilization rate of the conference room.
[0026] In conjunction with the accompanying drawings, some embodiments of the present application are described in detail below. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.
[0027] See also Figure 1 , Figure 1 It is a schematic diagram of a scenario for implementing the conference room inspection method provided in an embodiment of the present application.
[0028] like Figure 1 As shown, the server 100 is connected to multiple monitoring devices 200 in communication, and the server 100 is also connected to the conference reservation system 300 in communication. The monitoring device 200 is installed in the conference room and is used to collect monitoring images of the conference room. A conference room is installed with at least one monitoring device 200. The server 100 can be connected to multiple monitoring devices 200 in communication via wired or wireless means. Similarly, the server 100 can also be connected to the conference reservation system 300 in communication via wired or wireless means.
[0029] In some implementations, the server 100 obtains the monitoring image currently collected by the target monitoring device (any one or more of the multiple monitoring devices 200) at preset time intervals, the target monitoring device is installed in the target conference room, and the target conference room is a conference room in a meeting state; the monitoring image and the preset question command are input into the target graphic dialogue model, so that the target graphic dialogue model analyzes the monitoring image based on the preset question command to answer the current usage information of the target conference room; when it is determined that the target conference room is in a non-meeting state according to the current usage information, the state identifier of the target conference room in the conference reservation system is updated to a first identifier, and the first identifier is used to indicate that the target conference room is in an idle state. For example, when it is determined that the target conference room is in a non-meeting state according to the current usage information, the server 100 sends a state update instruction to the conference reservation system 300, so that the conference reservation system 300 updates the state identifier of the target conference room to the first identifier according to the state update instruction to indicate that the target conference room is in an idle state, thereby updating the conference room usage recorded in the conference reservation system 300.
[0030] Among them, the monitoring device 200 may include a fisheye camera, a wide-angle camera or an infrared camera, etc. The conference reservation system 300 may be a subsystem in the server 100, or may be another independent server, which is not specifically limited in this application. The server 100 may be an independent server, or may be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms.
[0031] The following will be combined Figure 1 The scenario in the present application provides a detailed introduction to the conference room inspection method provided in the present application embodiment. Figure 1 The scenario is only used to explain the conference room inspection method provided in the embodiment of the present application, but does not constitute a limitation on the application scenario of the conference room inspection method provided in the embodiment of the present application.
[0032] See also Figure 2 , Figure 2 The figure is a schematic diagram of the steps of a conference room inspection method provided in an embodiment of the present application. The conference room inspection method is applied to a server.
[0033] like Figure 2 As shown, the conference room inspection method includes steps S101 to S103.
[0034] Step S101: acquiring a monitoring image currently collected by a target monitoring device at a preset time interval, wherein the target monitoring device is installed in a target conference room, and the target conference room is a conference room in a meeting state.
[0035] In this embodiment, the conference room is in the meeting state means that the meeting scheduled time of the conference room has arrived, and the meeting scheduled time is still remaining. For example, the meeting scheduled time of conference room A is 14:00-15:00, then when the time reaches 14:00, the state of conference room A changes from the scheduled state to the meeting state, and in the time period of 14:00-15:00, conference room A is always in the meeting state.
[0036] Among them, the preset time can be set based on the actual situation, and the embodiments of the present application do not make specific limitations on this. For example, the preset time is 5 minutes or 3 minutes. The server obtains the monitoring image currently collected by the target monitoring device every 5 minutes or 3 minutes. For example, the conference rooms in the meeting state include Conference Room A, Conference Room B and Conference Room C, and the monitoring device M1 is installed in Conference Room A, the monitoring device M2 is installed in Conference Room B, and the monitoring device M3 is installed in Conference Room C. Then the server obtains the monitoring image Image1 currently collected by the monitoring device M1, the monitoring image Image2 currently collected by the monitoring device M2, and the monitoring image Image3 currently collected by the monitoring device M3 every 5 minutes or 3 minutes.
[0037] In some embodiments, acquiring the monitoring image currently collected by the target monitoring device may include: sending an image acquisition instruction to the target monitoring device, so that the target monitoring device sends the currently collected monitoring image to the server according to the image acquisition instruction; and the server receives the monitoring image sent by the target monitoring device based on the image acquisition instruction. This embodiment can ensure that the monitoring image obtained by the server is the latest, so that the conference room can be inspected accurately and timely, improving the efficiency and accuracy of conference room inspection.
[0038] For example, the conference rooms in the meeting state include Conference Room A, Conference Room B and Conference Room C, and the monitoring device M1 is installed in Conference Room A, the monitoring device M2 is installed in Conference Room B, and the monitoring device M3 is installed in Conference Room C. Then the server sends image acquisition instructions to the monitoring devices M1, M2 and M3 every 5 minutes or 3 minutes. When the monitoring device M1 receives the image acquisition instruction, it collects the monitoring image Image1 of Conference Room A and sends the monitoring image Image1 of Conference Room A to the server. When the monitoring device M2 receives the image acquisition instruction, it collects the monitoring image Image2 of Conference Room B and sends the monitoring image Image2 of Conference Room B to the server. When the monitoring device M3 receives the image acquisition instruction, it collects the monitoring image Image3 of Conference Room C and sends the monitoring image Image3 of Conference Room C to the server. The server receives the monitoring image Image1 sent by the monitoring device M1, receives the monitoring image Image2 sent by the monitoring device M2, and receives the monitoring image Image3 sent by the monitoring device M3.
[0039] In some embodiments, before step S101, it also includes: obtaining conference room status information sent by the conference reservation system, the conference room status information includes the conference room identifier of each conference room and the status identifier of each conference room; determining the conference room identifier corresponding to the second identifier as the target conference room identifier, the second identifier is used to indicate that the conference room is in a meeting state; determining the monitoring device corresponding to the monitoring device identifier bound to the target conference room identifier as the target monitoring device. This embodiment can accurately determine the conference room in the meeting state through the conference room status information in the conference reservation system, so as to facilitate timely inspection of the conference room in the meeting state.
[0040] In some embodiments, the conference room identifier is used to uniquely identify the conference room, the conference room identifier may be the conference room name, and the status identifier may include a first identifier, a second identifier, or a third identifier, the first identifier is used to indicate that the conference room is idle, the second identifier is used to indicate that the conference room is in a meeting, and the third identifier is used to indicate that the conference room is in a scheduled state. The scheduled state refers to the state in which the conference room is reserved but the time has not yet arrived at the scheduled meeting time.
[0041] In some embodiments, when the conference room reservation system obtains the conference room reservation request sent by the terminal device, it parses the conference room reservation request to obtain the conference room identifier and meeting reservation time of the conference room to be reserved. When it is determined that the conference room to be reserved is idle at the meeting reservation time according to the current conference room status information and the conference room identifier of the conference room to be reserved, the state identifier of the conference room to be reserved at the meeting reservation time is updated to a third identifier, and a conference room reservation success message is sent to the terminal device; when it is determined that the conference room to be reserved is in a reserved state or in a meeting state at the meeting reservation time according to the current conference room status information and the conference room identifier of the conference room to be reserved, a conference room reservation failure prompt is sent to the terminal device. Among them, the conference room reservation request also carries information such as the meeting theme and the number of participants.
[0042] Step S102: input the monitoring image and the preset question command into the target text-graphic dialogue model, so that the target text-graphic dialogue model analyzes the monitoring image based on the preset question command to output the current usage information of the target conference room.
[0043] In this embodiment, the preset question command can be set based on the actual situation, and the embodiment of the present application does not specifically limit this. For example, the preset question is named: Please answer the following questions after parsing the image content: [Are the people in the picture in a meeting? How many people are there? ], and reply using the following format: [{In the meeting: "Yes / No", number of people:}]. For another example, the preset question is named: Please answer the following questions after parsing the image content: [Are the people in the picture in a meeting? How many people are there? ], and if the people in the picture are not in a meeting, reply using the following format: [{Meeting status identifier: first preset identifier, number of people:}], and if the people in the picture are in a meeting, reply using the following format: [{Meeting status identifier: second preset identifier, number of people:}].
[0044] In some embodiments, the target text-image dialogue model is obtained by fine-tuning a preset text-image dialogue model in advance based on a plurality of training samples, the training samples include conference room monitoring images and conference room usage information, the conference room usage information includes a conference room status identifier and the number of participants, the conference room status identifier includes a first preset identifier or a second preset identifier, the first preset identifier is used to indicate that the conference room corresponding to the conference room monitoring image is in a non-meeting state, and the second preset identifier is used to indicate that the conference room corresponding to the conference room monitoring image is in a meeting state. Among them, the preset text-image dialogue model includes VisualGLM-6B, ChatGPT or LLaMA, etc.
[0045] In some embodiments, after step S102, the method further includes: deleting the monitoring image. In this embodiment, by deleting the monitoring image, the target text-graphic dialogue model will not store the monitoring image, thereby preventing the confidential meeting content or secret meeting content from being leaked.
[0046] When it is determined according to the current usage information that the target conference room is in a non-conference state, step S103 is executed to update the state identifier of the target conference room in the conference reservation system to a first identifier, where the first identifier is used to indicate that the target conference room is in an idle state.
[0047] In this embodiment, when the current use information includes the word "No", it is determined that the target conference room is in a non-meeting state, and when the current use information includes the word "Yes", it is determined that the target conference room is in a meeting state. Alternatively, when the meeting state identifier in the current use information is a first preset identifier, it is determined that the target conference room is in a non-meeting state, and when the meeting state identifier in the current use information is a second preset identifier, it is determined that the target conference room is in a meeting state. When it is determined that the target conference room is in a meeting state according to the current use information, the current number of meeting persons in the target conference room is updated to the number of meeting persons in the current use information.
[0048] In some embodiments, Figure 3 As shown, after step S102, the following steps are also included:
[0049] Step S104: when it is determined according to the current usage information that the target conference room is in a non-conference state, a reservation cancellation prompt message of the target conference room is pushed to the subscriber of the target conference room.
[0050] In this embodiment, the reservation cancellation prompt information is used to prompt the booker to cancel the reservation of the target conference room. When it is determined that the target conference room is in a non-meeting state according to the current usage information, the reservation cancellation prompt information of the target conference room can be sent to the email address of the booker of the target conference room, or the reservation cancellation prompt information of the target conference room can be pushed to the booker of the target conference room in the form of a text message, or the reservation cancellation prompt information of the target conference room can be sent to the mobile terminal of the booker of the target conference room. When the mobile terminal receives the reservation cancellation prompt information, it displays a reservation cancellation prompt pop-up window containing the reservation cancellation prompt information.
[0051] When a reservation cancellation instruction of the target conference room triggered by the booker is detected, step S103 is executed to update the state identifier of the target conference room in the conference reservation system to a first identifier, where the first identifier is used to indicate that the target conference room is in an idle state.
[0052] This embodiment pushes reservation cancellation prompt information of the target conference room to the person who has made the reservation of the target conference room when it is determined that the target conference room is in a non-meeting state, so as to prompt the person who has made the reservation to cancel the reservation of the target conference room. Then, when the reservation cancellation instruction is detected, the state identifier of the target conference room in the conference reservation system is updated to the first identifier. This avoids the situation where the conference room is updated to an idle state due to an incorrect result output by the target graphic dialogue model, and provides a better user experience.
[0053] In some embodiments, when a reservation reservation instruction of a target conference room triggered by a booker is detected, the state identifier of the target conference room in the conference reservation system is maintained as a second identifier, and the second identifier is used to indicate that the target conference room is in a conference state.
[0054] In some embodiments, after step S103, it also includes: determining the monitoring image and the current usage information as candidate training samples; sending the candidate training samples to the data annotation terminal for display, so that the data annotator updates or confirms the displayed candidate training samples; when the sample confirmation instruction sent by the data annotation terminal is obtained, determining the candidate training samples as target training samples; when the sample update instruction sent by the data annotation terminal is obtained, the current usage information in the candidate training samples is updated according to the sample update instruction to obtain the target training samples; when the number of target training samples reaches a preset number, the target image-text dialogue model is optimized and trained according to the preset number of target training samples. In this embodiment, by sending the candidate training samples to the data annotation terminal for display, so that the data annotator updates or confirms the displayed candidate training samples, the updated or confirmed candidate training samples are determined as target training samples, which can ensure the accuracy of the samples. In this way, according to the accurate target training samples, the target image-text dialogue model is optimized and trained, so that a more accurate target image-text dialogue model can be obtained to improve the accuracy of the target image-text dialogue model.
[0055] In some embodiments, determining the surveillance image and the current usage information as candidate training samples may include: performing a desensitization operation on one or more sensitive areas in the surveillance image to obtain a desensitized image, and determining the desensitized image and the current usage information as candidate training samples. The sensitive area is the area where the text in the surveillance image is located, and the desensitization operation includes mosaicing or blurring the sensitive area so that the sensitive area cannot be seen, thereby obtaining a desensitized image. This embodiment can effectively prevent the leakage of confidential meeting content or secret meeting content by desensitizing the surveillance image and then storing it as a candidate training sample.
[0056] See also Figure 4 , Figure 4 It is a schematic block diagram of another conference room inspection device provided in an embodiment of the present application.
[0057] like Figure 4 As shown, the conference room inspection device 110 includes:
[0058] An image polling module 111 is used to obtain the monitoring image currently collected by the target monitoring device at a preset time interval, wherein the target monitoring device is installed in a target conference room, and the target conference room is a conference room in a meeting state;
[0059] The model calling module 112 is used to input the monitoring image and the preset question command into the target graphic-text dialogue model, so that the target graphic-text dialogue model analyzes the monitoring image based on the preset question command to answer the current usage information of the target conference room;
[0060] The information updating module 113 is used to update the state identifier of the target conference room in the conference reservation system to a first identifier when it is determined according to the current usage information that the target conference room is in a non-conference state, wherein the first identifier is used to indicate that the target conference room is in an idle state.
[0061] In some embodiments, the image polling module 111 is further configured to:
[0062] Sending an image acquisition instruction to the target monitoring device, so that the target monitoring device sends the currently collected monitoring image to the server according to the image acquisition instruction;
[0063] Receive the monitoring image sent by the target monitoring device based on the image acquisition instruction.
[0064] In some embodiments, the conference room inspection device 110 further includes a determination module, wherein the determination module is used to:
[0065] Acquire conference room status information sent by the conference reservation system, wherein the conference room status information includes a conference room identifier of each conference room and a status identifier of each conference room;
[0066] Determine the conference room identifier corresponding to the second identifier of the state identifier as the target conference room identifier, wherein the second identifier is used to indicate that the conference room is in a meeting state;
[0067] The monitoring device corresponding to the monitoring device identifier bound to the target conference room identifier is determined as the target monitoring device.
[0068] In some embodiments, the conference room inspection device 110 further includes:
[0069] A deletion module is used to delete the monitoring image.
[0070] In some embodiments, the conference room inspection device 110 further includes:
[0071] An information push module, configured to push reservation cancellation prompt information of the target conference room to a booker of the target conference room when it is determined according to the current usage information that the target conference room is in a non-conference state;
[0072] The information updating module 113 is further configured to update the state identifier of the target conference room in the conference reservation system to a first identifier when detecting a reservation cancellation instruction of the target conference room triggered by the booker.
[0073] In some embodiments, the conference room inspection device 110 further includes:
[0074] A sample determination module, used to determine the monitoring image and the current usage information as candidate training samples;
[0075] A sending module, used for sending the candidate training samples to a data annotation terminal for display, so that the data annotator can update or confirm the displayed candidate training samples;
[0076] The sample determination module is further configured to determine the candidate training sample as a target training sample when a sample confirmation instruction sent by the data annotation terminal is obtained;
[0077] The sample determination module is further configured to update the current usage information in the candidate training samples according to the sample update instruction when the sample update instruction sent by the data annotation terminal is obtained, so as to obtain the target training samples;
[0078] The model optimization module is used to optimize the training of the target text-image dialogue model according to the preset number of target training samples when the number of the target training samples reaches a preset number.
[0079] In some embodiments, the sample determination module is further used to:
[0080] A desensitization operation is performed on one or more sensitive areas in the monitoring image to obtain a desensitized image, and the desensitized image and the current usage information are determined as the candidate training samples.
[0081] It should be noted that technicians in the relevant field can clearly understand that for the convenience and simplicity of description, the specific working process of the above-described device and each module and unit can refer to the corresponding process in the aforementioned conference room inspection method embodiment, and will not be repeated here.
[0082] The apparatus provided in the above embodiment may be implemented in the form of a computer program. The computer program may be Figure 5Run on the server shown.
[0083] See also Figure 5 , Figure 5 It is a schematic block diagram of the structure of a server provided in an embodiment of the present application.
[0084] like Figure 5 As shown, the server includes a processor, a memory, and a network interface connected via a system bus, wherein the memory may include a storage medium and an internal memory.
[0085] The storage medium can store an operating system and a computer program. The computer program includes program instructions, and when the program instructions are executed, the processor can execute any conference room inspection method.
[0086] The processor is used to provide computing and control capabilities to support the operation of the entire server.
[0087] The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art will appreciate that Figure 5 The structure shown in the figure is only a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the server to which the solution of the present application is applied. The specific server may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.
[0088] It should be understood that the processor may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.
[0089] In one embodiment, the processor is used to run a computer program stored in the memory to implement the following steps:
[0090] Acquire a monitoring image currently collected by a target monitoring device at a preset time interval, wherein the target monitoring device is installed in a target conference room, and the target conference room is a conference room in a meeting state;
[0091] Inputting the monitoring image and the preset question command into the target graphic-text dialogue model, so that the target graphic-text dialogue model analyzes the monitoring image based on the preset question command to answer the current usage information of the target conference room;
[0092] When it is determined according to the current use information that the target conference room is in a non-conference state, the state identifier of the target conference room in the conference reservation system is updated to a first identifier, where the first identifier is used to indicate that the target conference room is in an idle state.
[0093] In some embodiments, when acquiring the monitoring image currently collected by the target monitoring device, the processor is used to implement:
[0094] Sending an image acquisition instruction to the target monitoring device, so that the target monitoring device sends the currently collected monitoring image to the server according to the image acquisition instruction;
[0095] Receive the monitoring image sent by the target monitoring device based on the image acquisition instruction.
[0096] In some embodiments, before acquiring the monitoring image currently collected by the target monitoring device at every preset time, the processor is further used to implement:
[0097] Acquire conference room status information sent by the conference reservation system, wherein the conference room status information includes a conference room identifier of each conference room and a status identifier of each conference room;
[0098] Determine the conference room identifier corresponding to the second identifier of the state identifier as the target conference room identifier, wherein the second identifier is used to indicate that the conference room is in a meeting state;
[0099] The monitoring device corresponding to the monitoring device identifier bound to the target conference room identifier is determined as the target monitoring device.
[0100] In some embodiments, after inputting the monitoring image and the preset question command into the target graphic-text dialogue model, the processor is further configured to implement:
[0101] Delete the monitoring image.
[0102] In some embodiments, after inputting the monitoring image and the preset question command into the target text-graphic dialogue model so that the target text-graphic dialogue model analyzes the monitoring image based on the preset question command to output the current usage information of the target conference room, the processor is further configured to implement:
[0103] When it is determined according to the current usage information that the target conference room is in a non-meeting state, pushing a reservation cancellation prompt message of the target conference room to a booker of the target conference room;
[0104] When the reservation cancellation instruction of the target conference room triggered by the booker is detected, the step of updating the state identifier of the target conference room in the conference reservation system to the first identifier is performed.
[0105] In some embodiments, after the processor updates the state identifier of the target conference room in the conference reservation system to the first identifier when determining that the target conference room is in a non-conference state according to the current usage information, the processor is further configured to implement:
[0106] Determining the monitoring image and the current usage information as candidate training samples;
[0107] Sending the candidate training samples to a data annotation terminal for display, so that the data annotator can update or confirm the displayed candidate training samples;
[0108] When a sample confirmation instruction sent by the data annotation terminal is obtained, determining the candidate training sample as a target training sample;
[0109] When a sample update instruction sent by the data annotation terminal is obtained, the current usage information in the candidate training sample is updated according to the sample update instruction to obtain a target training sample;
[0110] When the number of the target training samples reaches a preset number, the target text-image dialogue model is optimized and trained according to the preset number of target training samples.
[0111] In some embodiments, when determining the surveillance image and the current usage information as candidate training samples, the processor is used to implement:
[0112] A desensitization operation is performed on one or more sensitive areas in the monitoring image to obtain a desensitized image, and the desensitized image and the current usage information are determined as the candidate training samples.
[0113] It should be noted that those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the server described above can refer to the corresponding process in the aforementioned conference room inspection method embodiment, and will not be repeated here.
[0114] It can be known from the description of the above implementation methods that those skilled in the art can clearly understand that the present application can be implemented by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present application can be essentially or partly contributed to the prior art in the form of a software product, which can be stored in a storage medium such as ROM / RAM, a disk, an optical disk, etc., including several instructions for enabling a server (which can be a personal computer, a server, or a network server, etc.) to execute the methods described in the various embodiments of the present application or certain parts of the embodiments.
[0115] An embodiment of the present application further provides a storage medium, on which a computer program is stored. The computer program includes program instructions. The method implemented when the program instructions are executed can refer to the various embodiments of the conference room inspection method of the present application.
[0116] The storage medium may be volatile or non-volatile. The storage medium may be an internal storage unit of the server described in the foregoing embodiment, such as a hard disk or memory of the server. The storage medium may also be an external storage server of the server, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc., equipped on the server.
[0117] Furthermore, the storage medium may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function, etc.; the data storage area may store data created according to the use of the blockchain node, etc.
[0118] The blockchain referred to in this application is a new application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, platform product service layer, and application service layer.
[0119] It should be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in this application specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.
[0120] It should also be understood that the term "and / or" used in the specification of this application and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, including these combinations. It should be noted that, in this article, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including 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 system. In the absence of further restrictions, an element defined by the sentence "including a..." does not exclude the presence of other identical elements in the process, method, article or system including the element.
[0121] The serial numbers of the embodiments of the present application are for description only and do not represent the advantages and disadvantages of the embodiments. The above description is only a specific implementation mode of the present application, but the protection scope of the present application 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 in the present application, and these modifications or replacements should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.
Claims
1. A conference room inspection method, characterized in that: Applied to a server, the method comprises: Acquire a monitoring image currently collected by a target monitoring device at a preset time interval, wherein the target monitoring device is installed in a target conference room, and the target conference room is a conference room in a meeting state; Inputting the monitoring image and the preset question command into the target graphic-text dialogue model, so that the target graphic-text dialogue model analyzes the monitoring image based on the preset question command to answer the current usage information of the target conference room; When it is determined according to the current use information that the target conference room is in a non-conference state, the state identifier of the target conference room in the conference reservation system is updated to a first identifier, where the first identifier is used to indicate that the target conference room is in an idle state.
2. The conference room inspection method according to claim 1, characterized in that: The step of obtaining the monitoring image currently collected by the target monitoring device includes: Sending an image acquisition instruction to the target monitoring device, so that the target monitoring device sends the currently collected monitoring image to the server according to the image acquisition instruction; Receive the monitoring image sent by the target monitoring device based on the image acquisition instruction.
3. The conference room inspection method according to claim 1, characterized in that: Before acquiring the monitoring image currently collected by the target monitoring device at a preset time interval, the method further includes: Acquire conference room status information sent by the conference reservation system, wherein the conference room status information includes a conference room identifier of each conference room and a status identifier of each conference room; Determine the conference room identifier corresponding to the second identifier of the state identifier as the target conference room identifier, wherein the second identifier is used to indicate that the conference room is in a meeting state; The monitoring device corresponding to the monitoring device identifier bound to the target conference room identifier is determined as the target monitoring device.
4. The conference room inspection method according to claim 1, characterized in that: After the monitoring image and the preset question command are input into the target text-graphic dialogue model, the method further includes: Delete the monitoring image.
5. The conference room inspection method according to claim 1, characterized in that: After the monitoring image and the preset question command are input into the target text-graphic dialogue model so that the target text-graphic dialogue model analyzes the monitoring image based on the preset question command to output the current usage information of the target conference room, the method further includes: When it is determined according to the current usage information that the target conference room is in a non-meeting state, pushing a reservation cancellation prompt message of the target conference room to a booker of the target conference room; When the reservation cancellation instruction of the target conference room triggered by the booker is detected, the step of updating the state identifier of the target conference room in the conference reservation system to the first identifier is performed.
6. The conference room inspection method according to any one of claims 1 to 5, characterized in that: When it is determined according to the current usage information that the target conference room is in a non-conference state, after updating the state identifier of the target conference room in the conference reservation system to a first identifier, the method further includes: Determining the monitoring image and the current usage information as candidate training samples; Sending the candidate training samples to a data annotation terminal for display, so that the data annotator can update or confirm the displayed candidate training samples; When a sample confirmation instruction sent by the data annotation terminal is obtained, determining the candidate training sample as a target training sample; When a sample update instruction sent by the data annotation terminal is obtained, the current usage information in the candidate training sample is updated according to the sample update instruction to obtain a target training sample; When the number of the target training samples reaches a preset number, the target text-image dialogue model is optimized and trained according to the preset number of target training samples.
7. The conference room inspection method according to claim 6, characterized in that: The step of determining the monitoring image and the current usage information as candidate training samples includes: A desensitization operation is performed on one or more sensitive areas in the monitoring image to obtain a desensitized image, and the desensitized image and the current usage information are determined as the candidate training samples.
8. A conference room inspection device, characterized in that: Applied to a server, the conference room inspection device comprises: An image polling module, used to obtain the monitoring image currently collected by the target monitoring device at a preset time interval, wherein the target monitoring device is installed in a target conference room, and the target conference room is a conference room in a meeting state; A model calling module, used for inputting the monitoring image and the preset question command into the target graphic-text dialogue model, so that the target graphic-text dialogue model analyzes the monitoring image based on the preset question command to answer the current usage information of the target conference room; The information updating module is used to update the state identifier of the target conference room in the conference reservation system to a first identifier when it is determined according to the current usage information that the target conference room is in a non-conference state, wherein the first identifier is used to indicate that the target conference room is in an idle state.
9. A server, characterized in that: The server includes a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, the steps of the conference room inspection method according to any one of claims 1 to 7 are implemented.
10. A storage medium for computer-readable storage, characterized in that: The storage medium stores a computer program, wherein when the computer program is executed by the processor, the steps of the conference room inspection method according to any one of claims 1 to 7 are implemented.