Time Calibration Method, Device, Computer Equipment and Storage Medium

Abstract

The present invention relates to the field of intelligent security, and discloses a time calibration method, device, computer device and storage medium. The method includes: receiving a heartbeat result returned by an image data platform, where the heartbeat result includes a time credibility field; if the value of the time credibility field is unavailable, sending a time calibration request to a time calibration server; receiving a time calibration result returned by the time calibration server in response to the time calibration request; and performing calibration processing on the set time of the current shooting device according to the time calibration result. The present invention can reduce the time calibration frequency of the shooting device and improve the temporal accuracy of the image data obtained by the shooting device.

Description

Technical Field

[0001] The present invention relates to the field of intelligent security, and particularly to a time calibration method, device, computer device and storage medium. Background Art

[0002] With the development of society, the number of installed security cameras is increasing. According to incomplete statistics, there are hundreds of thousands of security cameras installed in a large city. These security cameras regularly upload image data to an image data platform. Since each security camera has its own time setting, there are some time settings that are different from those of the image data platform. For those security cameras with time settings different from the image data platform, there is a large error between the image acquisition time and the real time (here it is considered that the time setting of the image data platform is correct).

[0003] The existing solution is that the security camera itself continuously sends a time calibration request to the time calibration interface of the time calibration server. However, most of the time calibration requests are unnecessary, overly relying on the time calibration server, which increases the service pressure on the time calibration server. Summary of the Invention

[0004] Based on this, it is necessary to provide a time calibration method, device, computer device and storage medium for the above technical problems to reduce the time calibration frequency of security cameras.

[0005] A time calibration method, characterized by comprising:

[0006] Receiving a heartbeat keep-alive request and image data sent by a shooting device;

[0007] Analyzing the image data to generate a time accuracy analysis result;

[0008] Setting a time credibility field of a heartbeat result according to the time accuracy analysis result; the heartbeat result is used to respond to the heartbeat keep-alive request;

[0009] Returning the heartbeat result to the shooting device so that the shooting device calibrates its own set time according to the time credibility field.

[0010] A time calibration method, characterized by comprising:

[0011] Receiving a heartbeat result returned by an image data platform, the heartbeat result including a time credibility field;

[0012] If the value of the time credibility field is unavailable, sending a time calibration request to a time calibration server;

[0013] Receive the time calibration result in response to the time calibration request returned by the time calibration server;

[0014] Calibrate the set time of the imaging device according to the time calibration result.

[0015] A time calibration device, comprising:

[0016] A receiving device data module, configured to receive a heartbeat keep-alive request and image data sent by an imaging device;

[0017] A time accuracy analysis module, configured to analyze the image data to generate a time accuracy analysis result;

[0018] A heartbeat field setting module, configured to set a time credibility field of a heartbeat result according to the time accuracy analysis result; the heartbeat result is used to respond to the heartbeat keep-alive request;

[0019] A calibrated set time module, configured to return the heartbeat result to the imaging device, so that the imaging device calibrates its own set time according to the time credibility field.

[0020] A time calibration device, comprising:

[0021] A receiving heartbeat data module, configured to receive a heartbeat result returned by an image data platform, where the heartbeat result includes a time credibility field;

[0022] A time calibration request module, configured to send a time calibration request to a time calibration server if the value of the time credibility field is unavailable;

[0023] A receiving time calibration result, configured to receive the time calibration result in response to the time calibration request returned by the time calibration server;

[0024] A time calibration module, configured to calibrate the set time of the current imaging device according to the time calibration result.

[0025] A computer device, comprising a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor, where the processor implements the above time calibration method when executing the computer-readable instructions.

[0026] One or more readable storage media storing computer-readable instructions, where when the computer-readable instructions are executed by one or more processors, the one or more processors execute the time calibration method as described above.

[0027] The present invention analyzes the image data sent by a photographing device to generate a time accuracy analysis result; sets the time credibility field of a heartbeat result according to the time accuracy analysis result; the heartbeat result is used to respond to the heartbeat keep-alive request of the photographing device; returns the heartbeat result to the photographing device, so that the photographing device can calibrate its set time according to the time credibility field, such that the photographing device does not need to frequently send time calibration requests to a time calibration server for time calibration, can reduce the frequency of the photographing device sending time calibration requests to the time calibration server for time calibration, and improve the time accuracy of the image data obtained by the photographing device. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description in the embodiments of the present invention. Obviously, the drawings in the following description are only some embodiments of the present invention, and for those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0029] Figure 1 is a schematic diagram of an application environment of a time calibration method in an embodiment of the present invention;

[0030] Figure 2 is a schematic flowchart of a time calibration method in an embodiment of the present invention;

[0031] Figure 3 is a time prediction trend curve generated based on a prediction result in an embodiment of the present invention;

[0032] Figure 4 is a schematic flowchart of a time calibration method in an embodiment of the present invention;

[0033] Figure 5 is a schematic structural diagram of a time calibration device in an embodiment of the present invention;

[0034] Figure 6 is a schematic structural diagram of a time calibration device in an embodiment of the present invention;

[0035] Figure 7 is a schematic diagram of a computer device in an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0036] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0037] The time calibration method provided in this embodiment can be applied in an application environment such as Figure 1 , where the client communicates with the server. Among them, the client can be a shooting device, such as a security camera. The server can be an image data platform for storing the image data uploaded by the security camera. The server can be implemented by an independent server or a server cluster composed of multiple servers.

[0038] In one embodiment, as Figure 2 shown, a time calibration method is provided. Taking the server in Figure 1 as an example, the following steps S10 - S40 are included.

[0039] S10. Receive the heartbeat keep - alive request and image data sent by the shooting device.

[0040] Understandably, the execution subject of the time calibration method provided in this embodiment can be an image data platform. The image data platform can be connected to multiple shooting devices, receive the heartbeat keep - alive requests and image data sent by each shooting device. The image data platform includes an image database. This image database can store the image data received from the shooting devices. Here, the heartbeat keep - alive request is used to maintain the connection between the shooting device and the image data platform.

[0041] S20. Analyze the image data to generate a time accuracy analysis result.

[0042] Understandably, after receiving the image data, the image data platform can analyze the image data to generate a time accuracy analysis result. Here, the image data platform can have an in - built or external data analysis platform. The data analysis platform analyzes the image data, and then the time accuracy analysis result is obtained from the data analysis platform. Here, the data analysis platform is set with a trained prediction model, which can perform intelligent prediction on the input image data and output the time accuracy analysis result. For example, when the generation time of the image data is within the prediction range of the prediction model, "OK" is output; otherwise, "unvalid" is output.

[0043] S30. Set the time credibility field of the heartbeat result according to the time accuracy analysis result; the heartbeat result is used to respond to the heartbeat keep - alive request.

[0044] Understandably, the heartbeat result refers to the feedback result of the image data platform responding to the heartbeat keep - alive request of the shooting device. The heartbeat result also sets a time credibility field, which can feedback the time credibility of the image data submitted by the shooting device.

[0045] After the image data platform receives the time accuracy analysis result, it can set the value of the time credibility field in the heartbeat result according to the time accuracy analysis result. It should be noted that here, the time accuracy analysis result used to set the value of the time credibility field does not necessarily need to be sent synchronously with the heartbeat keep-alive request. When generating the heartbeat result, the latest generated time accuracy analysis result corresponding to the current shooting device can be used.

[0046] The presentation form of the value of the time credibility field can be set according to actual needs. In one example, when the time accuracy analysis result is "OK", the value of the time credibility field can be "0"; when the time accuracy analysis result is "unvalid", the value of the time credibility field can be "1".

[0047] S40. Return the heartbeat result to the shooting device so that the shooting device can calibrate its set time according to the time credibility field.

[0048] Understandably, the shooting device can determine whether to calibrate its set time according to the time credibility field. For example, if the time credibility field is 0 (indicating that the set time of the shooting device is credible), the shooting device does not need to calibrate its set time. If the time credibility field is 1 (indicating that the set time of the shooting device is not credible), the shooting device needs to calibrate its set time.

[0049] A time calibration server can be set up, and the time calibration server provides calibration services to the shooting device. Here, since the shooting device can pre-judge whether its set time is credible, the number of requests for calibration from the time calibration server can be greatly reduced, reducing the processing pressure on the time calibration server.

[0050] The time calibration method provided in this embodiment analyzes the image data sent by the shooting device to generate a time accuracy analysis result; sets the time credibility field of the heartbeat result according to the time accuracy analysis result; the heartbeat result is used to respond to the heartbeat keep-alive request of the shooting device; returns the heartbeat result to the shooting device so that the shooting device can calibrate its set time according to the time credibility field, enabling the shooting device to not need to frequently send time calibration requests to the time calibration server for time calibration, reducing the frequency of the shooting device sending time calibration requests to the time calibration server for time calibration, and improving the temporal accuracy of the image data obtained by the shooting device.

[0051] Optionally, step S20, that is, analyzing the image data to generate a time accuracy analysis result, includes:

[0052] S201. Extract features from the image data to generate time series data;

[0053] S202. Generate an actual time trend curve based on the time series data; process the time series data through a time series prediction model to generate a predicted time trend curve.

[0054] S203. Compare the actual time trend curve and the predicted time trend curve to generate the time accuracy analysis result.

[0055] Understandably, time series data refers to data within a time period, which is used to describe the situation of things in an image changing over time. Such data can reflect the state or degree of change of a certain thing or phenomenon over time. In some examples, a data analysis platform can use the Prophet framework (an open-source framework provided by Facebook), which can be used for future prediction, missing value supplementation, or anomaly detection.

[0056] In a specific example, a certain camera can extract several feature data as shown in Table 1.

[0057] Table 1 Feature data extracted from image data

[0058]

[0059] In Table 1, the total duration of the image data is 5 minutes. A 128-dimensional feature vector can be extracted from the image data at each moment (every 5 seconds). By splicing these feature vectors, time series data can be obtained.

[0060] The above time series data can be input into the Prophet framework. The Prophet framework consists of two columns, namely 'ds' and 'y', where 'ds' represents the timestamp and 'y' represents the value of the time series (vector value). The column names in the data structure (such as pd.dataframe) in the framework can be changed according to actual needs. For example, if the original two column names are 'timestamp' and 'value', the labels of the above two columns can be changed using a renaming function (such as df.rename), and after modification, they are 'ds' and 'y' respectively.

[0061] In some examples, the time series data needs to be normalized. A normalization algorithm can be selected according to actual needs. For example, the average normalization algorithm can be adopted.

[0062] After completing the normalization of the time series data, the Prophet framework can be initialized, then the model can be fitted, and the time series can be predicted to obtain the predicted value. Before obtaining the predicted value, the number of prediction points of the predicted value and the frequency of the time series need to be set.

[0063] After the prediction operation is performed, a prediction graph can be drawn based on the prediction result, and the components of the time series can be drawn.

[0064] As Figure 3 shown, a time prediction trend curve can be generated according to the preset result (including three curves, namely the prediction line (predict), the upper prediction boundary line (upper), and the lower prediction boundary line (lower)), and a time actual trend curve (true) can be generated according to the time series data. If the time actual trend curve is between the upper prediction boundary line and the lower prediction boundary line, the time accuracy analysis result is "OK"; if the time actual trend curve is not between the upper prediction boundary line and the lower prediction boundary line, the time accuracy analysis result is "unvalid".

[0065] In one embodiment, as Figure 4 shown, a time calibration method is provided. Taking the application of this method in the Figure 1 client as an example for illustration, it includes the following steps S01 - S04.

[0066] S01. Receive the heartbeat result returned by the image data platform, where the heartbeat result includes a time credibility field.

[0067] Understandably, for the time calibration method provided in this embodiment, its execution entity can be a shooting device, such as a security camera. The shooting device is connected to the image data platform. The image data platform includes an image database. This image database can store a large amount of structured image data. The image data platform can process the image data stored in the image database to generate the security data required by users. The image data platform can be connected to multiple shooting devices and send their respective heartbeat results to each shooting device. By receiving the heartbeat result, the validity of the connection between the shooting device and the image data platform can be confirmed. In particular, here, the heartbeat result also sets a time credibility field, and this field can feedback the time credibility of the image data submitted by the shooting device.

[0068] S02. If the value of the time credibility field is unavailable, send a time calibration request to the time calibration server.

[0069] Understandably, the time credibility field can include two values, namely available (represented by available OK) and unavailable (represented by unvalid). If the value of the time credibility field is available, it means that the set time of the shooting device is normal and there is no need to correct the time. If the value of the time credibility field is unavailable, a time calibration request needs to be sent to the time calibration server. There can be several time calibration servers, and the shooting device can send a time calibration request to one of the time calibration servers. Here, the time calibration server refers to a server that provides time calibration services.

[0070] S03. Receive the time calibration result in response to the time calibration request returned by the time calibration server.

[0071] Understandably, after receiving the time calibration request, the time calibration server can return the time calibration result to the imaging device that sent the time calibration request. The time calibration result contains accurate time data.

[0072] S04. Calibrate the set time of the imaging device according to the time calibration result.

[0073] Understandably, the current imaging device may refer to the imaging device that sent the time calibration request. After receiving the time calibration result, the current imaging device can calibrate its own set time according to the time calibration result. In one example, the set time of the imaging device was originally 8:00:01 and after calibration it is 12:22:16.

[0074] In steps S01 - S04, receive the heartbeat result returned by the image data platform, where the heartbeat result includes a time credibility field, to determine whether to send a time calibration request to the time calibration server according to the time credibility field. If the value of the time credibility field is unavailable, send a time calibration request to the time calibration server to obtain accurate time data. Receive the time calibration result in response to the time calibration request returned by the time calibration server to obtain accurate time data. Calibrate the set time of the imaging device according to the time calibration result to achieve synchronization of the device set time. The time calibration method provided in this embodiment can reduce the time calibration frequency of the imaging device and improve the temporal accuracy of the image data obtained by the imaging device.

[0075] Optionally, before step S01, that is, before receiving the heartbeat result returned by the image data platform, where the heartbeat result includes a time credibility field, further includes:

[0076] S011. Send the heartbeat keep - alive request and the image data to the image data platform so that the image data platform generates the heartbeat result according to the heartbeat keep - alive request;

[0077] S012. Obtain the time accuracy analysis result of the image data so that the image data platform sets the value of the time credibility field according to the time accuracy analysis result.

[0078] Understandably, before receiving the heartbeat result, the imaging device needs to send a heartbeat keep - alive request to the image data platform and at the same time transmit the image data collected by itself to the image data platform.

[0079] After receiving the image data, the image data platform can analyze the image data to generate a time accuracy analysis result. Here, the image data platform can have an in-built or external data analysis platform. The data analysis platform analyzes the image data, and then the time accuracy analysis result is obtained from the data analysis platform. Here, the data analysis platform is provided with a trained prediction model, which can perform intelligent prediction on the input image data and output the time accuracy analysis result. For example, when the generation time of the image data is within the prediction range of the prediction model, "OK" is output; otherwise, "unvalid" is output.

[0080] After the image data platform receives the time accuracy analysis result, it can set the value of the time credibility field in the heartbeat result according to the time accuracy analysis result. It should be noted that here, the time accuracy analysis result used to set the value of the time credibility field is not necessarily sent synchronously with the heartbeat keep-alive request. When generating the heartbeat result, the latest generated time accuracy analysis result corresponding to the current shooting device can be used.

[0081] The display form of the value of the time credibility field can be set according to actual needs. In one example, when the time accuracy analysis result is "OK", the value of the time credibility field can be "0"; when the time accuracy analysis result is "unvalid", the value of the time credibility field can be "1".

[0082] Optionally, in step S012, that is, obtaining the time accuracy analysis result of the image data, includes:

[0083] S0121. Extract features from the image data to generate time series data;

[0084] S0122. Generate an actual time trend curve according to the time series data; process the time series data through a time series prediction model stored in the data analysis platform to generate a predicted time trend curve;

[0085] S0123. Compare the actual time trend curve and the predicted time trend curve to generate the time accuracy analysis result.

[0086] Understandably, for the specific steps of this embodiment, reference can be made to the above steps S201 to S203, which will not be elaborated here. Optionally, after step S10, that is, receiving the heartbeat result returned by the image data platform, and the heartbeat result includes the time credibility field, it further includes:

[0087] S21. If the value of the time credibility field is available, do not send a time calibration request to the time calibration server.

[0088] Understandably, if the value of the time credibility field is available, a time calibration request is not sent to the time calibration server. This can reduce the frequency of time calibration requests.

[0089] Optionally, after step S04, after calibrating the set time of the current imaging device according to the time calibration result, the following steps are further included:

[0090] S051. If the heartbeat connection with the image data platform is unavailable, generate time trend data based on the image data;

[0091] S052. Compare the time trend data with the previously stored prior prediction trend data to generate a comparison result;

[0092] S053. Determine whether to send a time calibration request to the time calibration server according to the comparison result.

[0093] In some special cases (such as network failures, etc.), the imaging device cannot maintain a heartbeat connection with the image data platform. Therefore, before the special case occurs, the image data platform can transmit the time trend data generated by the data analysis platform to the imaging device and store it in the local memory of the imaging device. The time trend data can refer to time prediction data for a future period (such as the next three months).

[0094] The imaging device can process the current image data to generate time trend data. Then, it is determined whether the time trend data is within the prediction allowable range of the corresponding time prediction data to generate a comparison result. The comparison result includes "OK" and "invalid". If "OK", a time calibration request does not need to be sent to the time calibration server. If "invalid", a time calibration request needs to be sent to the time calibration server.

[0095] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0096] In one embodiment, a time calibration device is provided, and the time calibration device corresponds one-to-one to the time calibration method in the above embodiment. As Figure 5 shown, the time calibration device includes a receiving device data module 10, a time accuracy analysis module 20, a heartbeat field setting module 30, and a calibrated set time module 40. The detailed descriptions of each functional module are as follows:

[0097] The receiving device data module 10 is configured to receive a heartbeat keep-alive request and image data sent by the imaging device;

[0098] A time accuracy analysis module 20, configured to analyze the image data to generate a time accuracy analysis result;

[0099] A heartbeat field setting module 30, configured to set a time credibility field of a heartbeat result according to the time accuracy analysis result; the heartbeat result is used to respond to the heartbeat keep-alive request;

[0100] A calibration setting time module 40, configured to return the heartbeat result to the shooting device, so that the shooting device calibrates its set time according to the time credibility field.

[0101] Optionally, the time accuracy analysis module 20 includes:

[0102] A generated sequence data unit, configured to perform feature extraction on the image data to generate time series data;

[0103] A trend curve unit, configured to generate an actual time trend curve according to the time series data; process the time series data through a time series prediction model to generate a predicted time trend curve;

[0104] A curve comparison unit, configured to compare the actual time trend curve and the predicted time trend curve to generate the time accuracy analysis result.

[0105] In an embodiment, a time calibration device is provided, and this time calibration device corresponds one-to-one with the time calibration method in the above embodiment. As Figure 6 shown, this time calibration device includes a heartbeat data receiving module 01, a time calibration request module 02, a received time calibration result 03, and a time calibration module 04. The detailed description of each functional module is as follows:

[0106] The heartbeat data receiving module 01 is configured to receive the heartbeat result returned by the image data platform, and the heartbeat result includes a time credibility field;

[0107] The time calibration request module 02 is configured to send a time calibration request to the time calibration server if the value of the time credibility field is unavailable;

[0108] The received time calibration result 03 is configured to receive the time calibration result returned by the time calibration server in response to the time calibration request;

[0109] The time calibration module 04 is configured to calibrate the set time of the current shooting device according to the time calibration result.

[0110] Optionally, the time calibration device further includes:

[0111] A sending module, configured to send a heartbeat keep-alive request and image data to the image data platform, so that the image data platform generates the heartbeat result according to the heartbeat keep-alive request;

[0112] A field setting module, configured to obtain the time accuracy analysis result of the image data, so that the image data platform sets the value of the time credibility field according to the time accuracy analysis result.

[0113] Optionally, the field setting module includes:

[0114] A feature extraction unit, configured to extract features from the image data to generate time series data;

[0115] A curve generation unit, configured to generate an actual time trend curve according to the time series data; process the time series data through a time series prediction model stored in a data analysis platform to generate a predicted time trend curve;

[0116] A comparison unit, configured to compare the actual time trend curve and the predicted time trend curve to generate the time accuracy analysis result.

[0117] Optionally, the time calibration device further includes:

[0118] A non-sending time calibration request module, configured to not send a time calibration request to a time calibration server if the value of the time credibility field is available.

[0119] Optionally, the time calibration device further includes:

[0120] A local trend data generation module, configured to generate time trend data according to image data if the heartbeat connection with the image data platform is unavailable;

[0121] A local comparison module, configured to compare the time trend data with previously stored prior predicted trend data to generate a comparison result;

[0122] A local time calibration judgment module, configured to determine whether to send a time calibration request to the time calibration server according to the comparison result.

[0123] For the specific limitations of the time calibration device, reference may be made to the limitations of the time calibration method in the foregoing text, which will not be elaborated herein. Each module in the foregoing time calibration device may be implemented in whole or in part by software, hardware, and their combination. The foregoing modules may be embedded in or independent of a processor in a computer device in the form of hardware, or may be stored in a memory in the computer device in the form of software, so as to facilitate the processor to call and execute the operations corresponding to the foregoing modules.

[0124] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in Figure 7 . The computer device includes a processor, a memory, a network interface, and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a readable storage medium and an internal memory. The readable storage medium stores an operating system, computer-readable instructions, and a database. The internal memory provides an environment for the operation of the operating system and computer-readable instructions in the readable storage medium. The database of the computer device is used to store the data involved in the time calibration method. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer-readable instructions are executed by the processor, a time calibration method is implemented. The readable storage medium provided in this embodiment includes a non-volatile readable storage medium and a volatile readable storage medium.

[0125] In one embodiment, a computer device is provided, including a memory, a processor, and computer-readable instructions stored on the memory and executable on the processor. When the processor executes the computer-readable instructions, the following steps are implemented:

[0126] Receive a heartbeat keep-alive request and image data sent by a shooting device;

[0127] Analyze the image data to generate a time accuracy analysis result;

[0128] Set the time credibility field of the heartbeat result according to the time accuracy analysis result; the heartbeat result is used to respond to the heartbeat keep-alive request;

[0129] Return the heartbeat result to the shooting device so that the shooting device can perform calibration processing on its own set time according to the time credibility field.

[0130] Alternatively, when the above processor executes the computer-readable instructions, the following steps may also be implemented:

[0131] Receive a heartbeat result returned by an image data platform, where the heartbeat result includes a time credibility field;

[0132] If the value of the time credibility field is unavailable, send a time calibration request to a time calibration server;

[0133] Receive a time calibration result returned by the time calibration server in response to the time calibration request;

[0134] Calibrate the set time of the current shooting device according to the time calibration result.

[0135] In one embodiment, one or more computer-readable storage media storing computer-readable instructions are provided. The readable storage media provided in this embodiment include non-volatile readable storage media and volatile readable storage media. Computer-readable instructions are stored on the readable storage media. When the computer-readable instructions are executed by one or more processors, the following steps are implemented:

[0136] Receive a heartbeat keep-alive request and image data sent by a shooting device;

[0137] Analyze the image data to generate a time accuracy analysis result;

[0138] Set the time credibility field of the heartbeat result according to the time accuracy analysis result; the heartbeat result is used to respond to the heartbeat keep-alive request;

[0139] Return the heartbeat result to the shooting device so that the shooting device can perform a calibration process on its set time according to the time credibility field.

[0140] Alternatively, when the above computer-readable instructions are executed by one or more processors, the following steps are implemented:

[0141] Receive a heartbeat result returned by an image data platform, where the heartbeat result includes a time credibility field;

[0142] If the value of the time credibility field is unavailable, send a time calibration request to a time calibration server;

[0143] Receive a time calibration result returned by the time calibration server in response to the time calibration request;

[0144] Calibrate the set time of the current shooting device according to the time calibration result.

[0145] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through computer-readable instructions. The computer-readable instructions can be stored in a non-volatile readable storage medium or a volatile readable storage medium. When the computer-readable instructions are executed, they can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided in the present application can include non-volatile and / or volatile memories. Non-volatile memories can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memories can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0146] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, only the above division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0147] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A time calibration method, characterized in that, applied to an image data platform, includes: Receiving a heartbeat keep-alive request and image data sent by a shooting device; Analyzing the image data to generate a time accuracy analysis result; Setting a time credibility field of a heartbeat result according to the time accuracy analysis result; the heartbeat result is used to respond to the heartbeat keep-alive request; Returning the heartbeat result to the shooting device, so that the shooting device calibrates its set time according to the time credibility field; Analyzing the image data to generate a time accuracy analysis result, including: Extracting features from the image data to generate time series data; Generating an actual time trend curve according to the time series data; processing the time series data through a time series prediction model to generate a predicted time trend curve; Comparing the actual time trend curve and the predicted time trend curve to generate the time accuracy analysis result.

2. A time calibration method, characterized in that, applied to a shooting device, includes: Receiving a heartbeat result returned by an image data platform, the heartbeat result includes a time credibility field; If the value of the time credibility field is unavailable, sending a time calibration request to a time calibration server; Receiving a time calibration result returned by the time calibration server in response to the time calibration request; Calibrating the set time of the shooting device according to the time calibration result; Before receiving the heartbeat result returned by the image data platform, further includes: Sending a heartbeat keep-alive request and image data to the image data platform, so that the image data platform generates the heartbeat result according to the heartbeat keep-alive request; Obtaining a time accuracy analysis result of the image data, so that the image data platform sets the value of the time credibility field according to the time accuracy analysis result; The obtaining a time accuracy analysis result of the image data, includes: Extracting features from the image data to generate time series data; Generating an actual time trend curve according to the time series data; processing the time series data through a time series prediction model to generate a predicted time trend curve; Comparing the actual time trend curve and the predicted time trend curve to generate the time accuracy analysis result.

3. The time calibration method according to claim 2, characterized in that, after calibrating the set time of the current shooting device according to the time calibration result, further includes: If the heartbeat connection with the image data platform is unavailable, generating time trend data according to the image data; Comparing the time trend data with pre-stored prior predicted trend data to generate a comparison result; Determining whether to send a time calibration request to the time calibration server according to the comparison result.

4. A time calibration device, characterized in that, applied to an image data platform, includes: A receiving device data module, configured to receive a heartbeat keep-alive request and image data sent by a shooting device; A time accuracy analysis module, configured to analyze the image data to generate a time accuracy analysis result; A heartbeat field setting module, configured to set a time credibility field of a heartbeat result according to the time accuracy analysis result; the heartbeat result is used to respond to the heartbeat keep-alive request; A calibration setting time module, configured to return the heartbeat result to the shooting device, so that the shooting device calibrates its set time according to the time credibility field; The time accuracy analysis module includes: A generated sequence data unit, configured to perform feature extraction on the image data to generate time series data; A trend curve unit, configured to generate an actual time trend curve according to the time series data; process the time series data through a time series prediction model to generate a predicted time trend curve; A curve comparison unit, configured to compare the actual time trend curve and the predicted time trend curve to generate the time accuracy analysis result.

5. A time calibration device, characterized in that, applied to a shooting device, including: A receiving heartbeat data module, configured to receive a heartbeat result returned by an image data platform, the heartbeat result including a time credibility field; A time calibration request module, configured to send a time calibration request to a time calibration server if the value of the time credibility field is unavailable; A receiving time calibration result, configured to receive a time calibration result returned by the time calibration server in response to the time calibration request; A time calibration module, configured to calibrate the set time of the current shooting device according to the time calibration result; The time calibration device further includes: A sending module, configured to send a heartbeat keep-alive request and image data to the image data platform, so that the image data platform generates the heartbeat result according to the heartbeat keep-alive request; A field setting module, configured to obtain a time accuracy analysis result of the image data, so that the image data platform sets the value of the time credibility field according to the time accuracy analysis result; The field setting module includes: A feature extraction unit, configured to perform feature extraction on the image data to generate time series data; A curve generation unit, configured to generate an actual time trend curve according to the time series data; process the time series data through a time series prediction model stored in a data analysis platform to generate a predicted time trend curve; A comparison unit, configured to compare the actual time trend curve and the predicted time trend curve to generate the time accuracy analysis result.

6. A computer device, including a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor, characterized in that, when the processor executes the computer-readable instructions, the time calibration method according to any one of claims 1 to 3 is implemented.

7. One or more readable storage media storing computer-readable instructions, when the computer-readable instructions are executed by one or more processors, cause the one or more processors to execute the time calibration method according to any one of claims 1 to 3.

Images