CN111666453A

CN111666453A - Video management method, video retrieval method, video management device, video retrieval device, electronic equipment and storage medium

Info

Publication number: CN111666453A
Application number: CN201910173319.7A
Authority: CN
Inventors: 张晓奇
Original assignee: Hangzhou Hikvision Digital Technology Co Ltd
Current assignee: Hangzhou Hikvision Digital Technology Co Ltd
Priority date: 2019-03-07
Filing date: 2019-03-07
Publication date: 2020-09-15
Anticipated expiration: 2039-03-07
Also published as: CN111666453B

Abstract

The embodiment of the invention provides a video management method, a video retrieval method, a video management device, a video retrieval device, electronic equipment and a storage medium. The video management method is applied to an ATM host, and comprises the following steps: receiving a target command sent by client equipment; judging whether the target command is one of at least one preset command or not; any predetermined command is a command generated by the client device when detecting that a user performs a predetermined transaction operation on the client device; different predetermined transaction operations correspond to different predetermined commands; if yes, acquiring transaction parameters formed by the preset transaction operation corresponding to the target command, and searching a target image frame from the real-time monitoring video of the client equipment, wherein the target image frame is an image frame representing the preset transaction operation corresponding to the target command; and establishing an incidence relation between the transaction parameters and the target image frame. The embodiment of the invention can realize intelligent management of the monitoring video stored in the ATM host, thereby providing a retrieval basis for intelligent video retrieval.

Description

Video management method, video retrieval method, video management device, video retrieval device, electronic equipment and storage medium

Technical Field

The present invention relates to the field of network technologies, and in particular, to a method and an apparatus for video management and retrieval, an electronic device, and a storage medium.

Background

The ATM host is a special high-definition digital hard disk video recorder in the financial industry, and can realize high-definition coding and video recording. The ATM host supports the access of an analog camera and the access of a digital camera, and can also perform network access and networking so as to meet the requirements of digitization, networking and high-definition video monitoring. Therefore, the ATM host has been widely used for video and audio monitoring of scenes such as an ATM (Automatic Teller Machine), a bank counter, and the like. In particular, the ATM host stores video and audio content relating to the performance of transaction operations by users at ATMs, transaction devices at bank counters, and the like.

In practical application, it is sometimes necessary to search a video corresponding to specific transaction information from a large amount of monitoring videos stored in the ATM host. For example, a video corresponding to a certain bank card number needs to be retrieved from a large amount of monitoring videos stored by the ATM host.

However, the existing ATM host only stores video and audio data of the surveillance video for the surveillance video collected by the audio/video collecting device. Because only the video and audio data of the surveillance video are stored in the ATM host, when the video corresponding to a specific transaction information needs to be retrieved, the comparison retrieval is usually performed manually in the surveillance video stored in the ATM host, which results in lower retrieval efficiency of video retrieval. Therefore, how to intelligently manage the mass monitoring videos in the ATM host so as to provide a retrieval basis for intelligent video retrieval is an urgent problem to be solved.

Disclosure of Invention

Embodiments of the present invention provide a video management method, a video retrieval method, a video management apparatus, an electronic device, and a storage medium, so as to implement intelligent management on a surveillance video stored in an ATM host, thereby providing a retrieval basis for intelligent video retrieval. The specific technical scheme is as follows:

in a first aspect, the present invention provides a video management method, applied to an ATM host, where the ATM host is in communication connection with a client device, and the method includes:

receiving a target command sent by the client device;

judging whether the target command is one of at least one preset command or not; any preset command is a command generated by the client device when the client device detects that a user performs a preset transaction operation on the client device; different predetermined transaction operations correspond to different predetermined commands;

when the judgment result is yes, acquiring transaction parameters formed by the preset transaction operation corresponding to the target command, and searching a target image frame from the real-time monitoring video corresponding to the client device, wherein the target image frame can represent the image frame of the preset transaction operation corresponding to the target command;

and establishing an incidence relation between the transaction parameters and the target image frame.

Optionally, the frame type of the target image frame is an I frame;

the searching the target image frame from the real-time monitoring video corresponding to the client device comprises:

searching an I frame with a timestamp closest to a target time point from a real-time monitoring video corresponding to the client device to serve as a target image frame; and the target time point is the time point of acquiring the transaction parameters.

Optionally, the at least one predetermined command comprises: the client device generates a first command when detecting that the user performs a transaction starting operation, and generates a second command when detecting that the user performs a transaction ending operation;

the method further comprises the following steps:

when the target command is the first command, after searching a target image frame from a real-time monitoring video corresponding to the client device, marking the target image frame as an initial image frame, wherein the initial image frame is an image frame representing the starting of a transaction;

when the target command is the second command, after searching a target image frame from the real-time monitoring video corresponding to the client device, marking the target image frame as a termination image frame, wherein the termination image frame is an image frame representing the end of a transaction.

Optionally, the establishing of the association relationship between the transaction parameter and the target image frame includes:

and correspondingly storing the transaction parameters and the frame identification of the target image frame into a hard disk of the ATM host or a storage device connected with the ATM host.

Optionally, after the association relationship between the transaction parameter and the target image frame is established, the method further includes:

adding the transaction parameter to a plurality of consecutive image frames of the real-time surveillance video, a first frame of the plurality of consecutive image frames being the target image frame.

In a second aspect, the present invention provides a video retrieval method applied to an ATM host, where the method includes:

receiving a retrieval instruction, wherein the retrieval instruction carries: a target transaction parameter;

determining a first target image frame corresponding to a target transaction parameter based on a pre-established association relation between the transaction parameter and the target image frame, wherein the first target image frame is a target image frame containing the target transaction parameter in the corresponding transaction parameter; the association relation between the transaction parameters and the target image frames is established according to the video management method of the first aspect;

and searching video data containing the first target image frame in the stored monitoring video, and determining the searched video data as a retrieval result.

Optionally, after searching for a video including the first target image frame in the stored monitoring videos and determining the searched video as a search result, the method further includes:

adding the target transaction parameter to a plurality of consecutive image frames of the video as the retrieval result, a first frame of the plurality of consecutive image frames being the first target image frame.

In a third aspect, the present invention provides a video management apparatus for an ATM host, where the ATM host is in communication connection with a client device, the apparatus including:

the first receiving module is used for receiving a target command sent by the client device;

the judging module is used for judging whether the target command is one of at least one preset command; any preset command is a command generated by the client device when the client device detects that a user performs a preset transaction operation on the client device; different predetermined transaction operations correspond to different predetermined commands;

the acquisition module is used for acquiring transaction parameters formed by the preset transaction operation corresponding to the target command and searching a target image frame from the real-time monitoring video corresponding to the client equipment, wherein the target image frame can represent the image frame of the preset transaction operation corresponding to the target command;

and the establishing module is used for establishing the incidence relation between the transaction parameters and the target image frame.

Optionally, the frame type of the target image frame is an I frame;

the acquisition module is specifically configured to search, from the real-time monitoring video corresponding to the client device, an I frame having a timestamp closest to a target time point as a target image frame; and the target time point is the time point of acquiring the transaction parameters.

the device further comprises:

the first control module is used for marking the target image frame as an initial image frame after the acquisition module searches a target image frame from a real-time monitoring video corresponding to the client device when the target command is the first command, wherein the initial image frame is an image frame representing the starting of a transaction;

and the second control module is used for marking the target image frame as a termination image frame after the acquisition module searches the target image frame from the real-time monitoring video corresponding to the client equipment when the target command is the second command, wherein the termination image frame is an image frame representing the end of the transaction.

Optionally, the establishing module is specifically configured to correspondingly store the transaction parameter and the frame identifier of the target image frame in a hard disk of the ATM host or a storage device connected to the ATM host.

Optionally, the apparatus further comprises:

the first adding module is used for adding the transaction parameters into a plurality of continuous image frames of the real-time monitoring video after the establishing module establishes the association relationship between the transaction parameters and the target image frame, wherein the first frame of the plurality of continuous image frames is the target image frame.

In a fourth aspect, the present invention provides a video retrieval apparatus for use with an ATM host, the apparatus comprising:

a second receiving module, configured to receive a retrieval instruction, where the retrieval instruction carries: a target transaction parameter;

the determining module is used for determining a first target image frame corresponding to the target transaction parameter based on a pre-established association relation between the transaction parameter and a target image frame, wherein the first target image frame is a target image frame of the corresponding transaction parameter, and the target image frame comprises the target transaction parameter; the association relationship between the transaction parameters and the target image frames is established by the video management device of the third aspect;

and the searching module is used for searching the video data containing the first target image frame in the stored monitoring video and determining the searched video data as a retrieval result.

Optionally, the apparatus further comprises:

the second adding module is used for searching the video containing the first target image frame in the stored monitoring video, determining the searched video as a searching result, and then adding the target transaction parameter into a plurality of continuous image frames of the video serving as the searching result, wherein the first frame of the plurality of continuous image frames is the first target image frame.

In a fifth aspect, the present invention provides an electronic device, which is an ATM host, and includes a processor, a communication interface, a memory, and a communication bus, where the processor, the communication interface, and the memory complete communication with each other through the communication bus;

a memory for storing a computer program;

a processor for implementing the steps of the video management method according to the first aspect when executing the program stored in the memory.

In a sixth aspect, the present invention provides an electronic device, which is an ATM host, and includes a processor, a communication interface, a memory, and a communication bus, where the processor, the communication interface, and the memory complete communication with each other through the communication bus;

a memory for storing a computer program;

a processor, configured to implement the steps of the video retrieval method according to the second aspect when executing the program stored in the memory.

In a seventh aspect, the present invention provides a computer-readable storage medium, in which a computer program is stored, and the computer program, when executed by a processor, implements the steps of the video management method according to the first aspect.

In an eighth aspect, the present invention provides a computer-readable storage medium, in which a computer program is stored, and the computer program, when executed by a processor, implements the steps of the video retrieval method according to the second aspect.

As can be seen from the above, with the video management method provided by the embodiment of the present invention, after receiving a target command sent by a client device, an ATM host determines whether the target command is one of at least one predetermined command; and when the judgment result is yes, acquiring a transaction parameter formed by a preset transaction operation corresponding to the target command, searching a target image frame from a real-time monitoring video corresponding to the client equipment, and then establishing an association relation between the transaction parameter and the target image frame. Therefore, the video management method can realize intelligent management of the monitoring video stored by the ATM host, thereby providing a retrieval basis for intelligent video retrieval.

In addition, based on the video management method provided by the embodiment of the invention, compared with the manual retrieval in the prior art, the video retrieval method provided by the embodiment of the invention can quickly and effectively retrieve the video corresponding to the specific transaction information.

Of course, it is not necessary for any product or method of practicing the invention to achieve all of the above-described advantages at the same time.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.

Fig. 1 is a schematic flow chart of a video management method according to an embodiment of the present invention;

fig. 2 is a schematic flow chart of another video management method according to an embodiment of the present invention;

fig. 3 is a schematic flow chart of a video retrieval method according to an embodiment of the present invention;

FIG. 4 is a schematic flow chart of another video retrieval method according to an embodiment of the present invention;

fig. 5 is a schematic structural diagram of a video management apparatus according to an embodiment of the present invention;

fig. 6 is a schematic structural diagram of a video retrieval apparatus according to an embodiment of the present invention;

fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present invention;

fig. 8 is a schematic structural diagram of another electronic device according to an embodiment of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

The ATM host is a special high-definition digital hard disk video recorder in the financial industry, is communicated with an automatic teller machine, transaction equipment at a bank counter and the like, can be used as a back-end server of the automatic teller machine, the transaction equipment at the bank counter and the like, and can realize high-definition coding and video recording. The existing ATM host only stores video and audio data of monitoring videos collected by the audio and video collecting device. Because only the video and audio data of the surveillance video are stored in the ATM host, when the video corresponding to a specific transaction information needs to be retrieved, the comparison retrieval is usually performed manually in the surveillance video stored in the ATM host, which results in lower retrieval efficiency of video retrieval. Therefore, how to intelligently manage the mass monitoring videos in the ATM host so as to provide a retrieval basis for intelligent video retrieval is an urgent problem to be solved.

In order to solve the above technical problem, an embodiment of the present invention provides a video management method.

It should be noted that the video management method provided by the embodiment of the present invention can be applied to an ATM host. The ATM host may store surveillance video of a transaction performed by a user at a client device. The client device may be an ATM, a transaction device at a bank counter, etc., among others. In the embodiment of the present invention, there may be one or more client devices.

It can be understood that, because the embodiment of the present invention provides a video management method, the ATM host needs to be able to obtain a surveillance video corresponding to a client device, where the surveillance video specifically includes: and audio and video data corresponding to the client device. In the monitoring video corresponding to the client device, the process that the user executes the transaction operation on the client device can be monitored.

In specific application, the monitoring video corresponding to the client device can be acquired by the audio and video acquisition device corresponding to the client device. In one mode, the audio/video capture device corresponding to the client device may be the client device itself, and at this time, the client device may actively or passively upload the captured audio/video data to the ATM host or another storage device in communication with the ATM host. In another mode, the audio/video capture device corresponding to the client device may be an audio/video capture device installed near the client device, and at this time, the audio/video capture device may actively or passively upload the captured audio/video data to the ATM host or another storage device in communication with the ATM host. Whether the client device or the audio and video acquisition device installed near the client device, the acquired audio and video data are as follows: and monitoring the process of the transaction operation executed by the user on the client device to obtain the audio and video data.

In addition, it is emphasized that when the audio-video data corresponding to the client device is uploaded to another storage device, the ATM host may request to obtain the audio-video data corresponding to the client device from the another storage device. Moreover, the client device itself or the audio/video acquisition device installed near the client device can acquire the audio/video data corresponding to the client device in real time all the time, and can also start to acquire the audio/video data corresponding to the client device when detecting that the user or the user performs the transaction starting operation, which is reasonable.

A video management method according to an embodiment of the present invention is described below with reference to the accompanying drawings.

Fig. 1 is a flowchart illustrating a video management method according to an embodiment of the present invention. As shown in fig. 1, a video management method provided in an embodiment of the present invention may include the following steps:

s101, receiving a target command sent by the client device.

When any user performs a transaction operation at a client device, the client device may detect the transaction operation and generate a target command corresponding to the transaction operation. In turn, the client device may send the target command to the ATM host to inform the ATM host that a user is currently performing a transaction operation on the client device. Specifically, in this embodiment, the ATM host may previously enter into an agreement with the client device: when the client device detects that a user executes a transaction operation on the client device, the client device generates a target command corresponding to the transaction operation and sends the target command to the ATM host. Specifically, when the target command is transmitted, the target command may be transmitted by wired communication or wireless communication.

The transaction operations described above may include, but are not limited to: inserting cards, inquiring, withdrawing money, depositing money, modifying passwords, transferring accounts, inquiring without cards, depositing money without cards, fetching cards and the like.

It will be appreciated that a transaction operation may form a corresponding transaction parameter. The transaction parameters may include, but are not limited to, the transaction operation: transaction time, transaction operation type, transaction card number, transaction amount, and the like.

Therefore, the target command can carry transaction parameters formed by the corresponding transaction operation, so that the ATM host can obtain the transaction parameters. Of course, the target command may not carry these transaction parameters, but merely inform the ATM host by sending the target command: there are currently users performing transaction operations on client devices.

S102, judging whether the target command is one of at least one preset command.

Any predetermined command is a command generated by the client device when the client device detects that a user performs a predetermined transaction operation on the client device. In this embodiment, different predefined transaction operations correspond to different predefined commands. It is understood that, by determining whether the target command is one of the at least one predetermined command, it is determined whether the transaction operation currently performed by the user is a predetermined transaction operation.

The predetermined transaction operation may be a predefined standard or canonical transaction operation. For example, the predetermined transaction operations may include, but are not limited to: inserting cards, inquiring, withdrawing money, depositing money, modifying passwords, transferring accounts, inquiring without cards, depositing money without cards, fetching cards and the like. Thus, each predetermined command is a command generated by a user when performing a transaction operation of a certain standard or specification. Moreover, a transaction operation corresponds to a predetermined command.

In a specific application, for each predetermined command, a check code corresponding to the predetermined command may be predefined. When the target command is received, the ATM host may determine whether the target command is one of the at least one predetermined command by determining whether a check code of the target command is a check code of one of the at least one predetermined command. Of course, there may be various ways to determine whether the target command is one of the at least one predetermined command, which is not limited in the present invention.

S103, when the judgment result is yes, acquiring a transaction parameter formed by a preset transaction operation corresponding to the target command, and searching a target image frame from a real-time monitoring video corresponding to the client device.

Wherein, the target image frame is an image frame capable of representing a predetermined transaction operation corresponding to the target command.

And when the judgment result is yes, the target command passes the correctness check, and the target command is one of at least one preset command. That is, the transaction operation corresponding to the target command is a predetermined transaction operation. Then, the ATM host may obtain transaction parameters formed by a predetermined transaction operation corresponding to the target command, and search for a target image frame from the real-time monitoring video corresponding to the client device. Since the target image frame is an image frame capable of representing a predetermined transaction operation corresponding to the target command, the association relationship between the acquired transaction parameter and the searched target image frame can be further established.

The transaction parameters formed by the predetermined transaction operation corresponding to the target command may include, but are not limited to: transaction time, transaction operation type, transaction card number, transaction amount, and the like.

As described in step S101, in one case, the target command may carry a transaction parameter formed by the corresponding transaction operation. In this case, then, the ATM host may parse the packet of the target command after receiving the target command, and extract from the packet: and the target command corresponds to a transaction parameter formed by a predetermined transaction operation.

In another case, the target command may not carry the transaction parameters formed by the corresponding transaction operation. In this case, then, the ATM host may send a transaction parameter acquisition request to the client device, the receiving client device sending in response to the request: and the target command corresponds to a transaction parameter formed by a predetermined transaction operation.

In this embodiment, the ATM host may obtain a real-time monitoring video corresponding to the client device, and search for the target image frame from the real-time monitoring video. The frame type of the target image frame may be an I frame, i.e., a key frame. Specifically, the ATM host may send an acquisition instruction to the audio/video acquisition device to acquire a monitoring video acquired by the audio/video acquisition device corresponding to the client device in real time. The specific process of the ATM host obtaining the monitoring video acquired by the audio/video acquisition device in real time may be as follows: the method comprises the steps that audio and video signals are collected by audio and video collection equipment, after an acquisition instruction is received, the collected audio and video signals are coded into audio and video code streams through a coder, and the audio and video code streams are sent to an ATM host; the ATM host writes the received audio and video code stream into a pre-allocated code stream cache, reads the audio and video code stream from the code stream cache, and writes the read audio and video code stream into a pre-allocated video partition of a hard disk of the ATM host. The audio and video code stream is the real-time monitoring video corresponding to the client device.

The embodiment of the present invention does not limit the video encoding format for encoding the video signal, and any video encoding format capable of encoding the video signal may be applied to the present application. Similarly, the embodiment of the present invention also does not limit the audio encoding format for encoding the audio signal, and any audio encoding format capable of encoding the audio signal may be applied to the present application.

Optionally, when the frame type of the target image frame is an I frame, in an implementation, searching for the target image frame from the real-time monitoring video corresponding to the client device may include:

searching an I frame with the timestamp closest to the target time point from the real-time monitoring video corresponding to the client equipment to serve as a target image frame; wherein the target time point is the time point of obtaining the transaction parameters.

In this implementation, the timestamp of one I frame refers to: the acquisition time of the frame. Since the transaction parameter is formed by the predetermined transaction operation corresponding to the target command, the I frame with the timestamp closest to the time point of acquiring the transaction parameter is used as the target image frame, and the target image frame can be used as the image frame representing the predetermined transaction operation corresponding to the target command executed by the user. That is, the target image frame may be an image frame when the user performs the predetermined transaction operation.

The method for searching the target image frame in the real-time monitoring video corresponding to the client device is not limited. Any one of the existing methods can search the target image frame from the real-time monitoring video corresponding to the client device, and can be applied to the invention.

For example: in other implementations, the time point when the ATM host receives the target command may be used as the target time point, so that one I frame with the timestamp closest to the target time point is searched from the real-time monitoring video corresponding to the client device as the target image frame. Since the target command is generated and sent to the ATM host when the client device detects that the user performs a predetermined transaction operation at the client device, an I frame having a timestamp closest to a time point at which the ATM host receives the target command is used as the target image frame, and the target image frame may be used as an image frame representing that the user performs the predetermined transaction operation corresponding to the target command. That is, the target image frame may be an image frame when the user performs the predetermined transaction operation.

Another example is: searching an I frame with a timestamp which is behind the target time point and is closest to the target time point from the real-time monitoring video corresponding to the client equipment as a target image frame; or searching an I frame with the timestamp being before and closest to the target time point from the real-time monitoring video corresponding to the client device as the target image frame. Wherein the target time point may be a time point of acquiring transaction parameters or a time point of receiving a target command by the ATM host.

And S104, establishing an association relation between the transaction parameters and the target image frame.

After acquiring the transaction parameters formed by the predetermined transaction operation corresponding to the target command and searching the target image frame from the real-time monitoring video corresponding to the client device, the ATM host can establish the association relationship between the transaction parameters and the target image frame.

Optionally, in an implementation, the establishing of the association relationship between the transaction parameter and the target image frame may include:

In this implementation, the frame identification of the target image frame may be: a timestamp of the target image frame. The time stamp of the target image frame refers to: the acquisition time of the target image frame. In this embodiment, the ATM host may store the real-time monitoring video corresponding to the client device in a local hard disk, and then the frame identifier of the target image frame may also be: offset address of the target image frame in the corresponding hard disk partition. The corresponding hard disk partition refers to: and the hard disk of the ATM host stores the hard disk partition of the real-time monitoring video corresponding to the client device.

Specifically, the ATM host may write the acquired transaction parameters into a transaction parameter cache allocated in advance, and at the same time, read the transaction parameters from the transaction parameter cache, and write the read transaction parameters into a transaction parameter partition of a hard disk of the ATM host allocated in advance. When the transaction parameters are written into the transaction parameter partition, the frame identification of the target image frame is also written into the transaction parameter partition, so that the transaction parameters and the frame identification of the target image frame are correspondingly stored in a hard disk of the ATM host.

Of course, the transaction parameters and the frame identifier of the target image frame may also be correspondingly stored in: in a storage device connected to an ATM host. The storage device connected to the ATM host may specifically be: a network disk or other type of storage device connected to an ATM host.

The correlation between the transaction parameters established by the ATM host and the target image frames can provide a retrieval basis for intelligent video retrieval. Namely: the video corresponding to the specific transaction information can be retrieved from the massive monitoring videos stored by the ATM host based on the incidence relation between the transaction parameters and the target image frames established by the ATM host.

Optionally, in an implementation manner, in the embodiment shown in fig. 1, the at least one predetermined command may include: the method comprises the steps that a first command is generated when the client device detects that a user performs a transaction starting operation, and a second command is generated when the client device detects that the user performs a transaction ending operation;

correspondingly, the method may further include:

when the target command is a first command, after searching a target image frame from a real-time monitoring video corresponding to the client device, marking the target image frame as an initial image frame, wherein the initial image frame is an image frame representing the starting of transaction;

and when the target command is a second command, after searching the target image frame from the real-time monitoring video corresponding to the client equipment, marking the target image frame as a termination image frame, wherein the termination image frame is an image frame representing the end of the transaction.

In this implementation, the above-mentioned transaction starting operation may be: and (4) card insertion operation. It will be appreciated that the card insertion operation is typically the first transaction operation performed by the user during the entire transaction performed by the client device. When the user performs the card insertion operation, it means that the user starts a transaction at the client device. Then, when the target command is the first command, the ATM host may mark the target image frame as a start image frame after searching for the target image frame from the real-time monitoring video corresponding to the client device, the start image frame being an image frame indicating that the transaction is opened. That is, the starting image frame is: an image frame representing a user starting a transaction process at a client.

When video retrieval is performed in a large amount of monitoring videos stored by an ATM host, a target transaction parameter is often given, and a video segment of a transaction process corresponding to the target transaction parameter is expected to be retrieved. For example, given a target transaction parameter a generated by a user when performing a predetermined transaction operation b, and a transaction process c including the transaction operation b, it is often desirable to retrieve a video segment of the transaction process c. Based on this, when the target command is the above-mentioned first command, marking the target image frame as the start image frame after searching the target image frame may facilitate: and determining the initial position of the video segment of the transaction process corresponding to the target transaction parameter. The starting position may be represented by a starting image frame.

In this implementation, the transaction ending operation may be: and (5) card taking operation. It will be appreciated that, throughout the course of a transaction performed by a user at a client device, typically, the card-removal operation is the last transaction performed by the user. When the user performs a card-pickup operation, it means that the user has finished the transaction at the client device. Then, when the target command is the second command, the ATM host may mark the target image frame as a termination image frame after searching for the target image frame from the real-time monitoring video corresponding to the client device, the termination image frame being an image frame indicating that the transaction is terminated. That is, the termination image frame is: an image frame representing a user ending a transaction at a client.

As described above, when performing video retrieval in a large amount of surveillance videos stored in the ATM host, a target transaction parameter is often given, and it is desirable to retrieve a video segment of a transaction process corresponding to the target transaction parameter. Based on this, when the target command is the above-described second command, marking the target image frame as the termination image frame after searching for the target image frame may facilitate: and determining the end position of the video segment of the transaction process corresponding to the target transaction parameter. The end position may be represented by a termination image frame.

Therefore, by the implementation mode, when the video segment of the transaction process corresponding to the target transaction parameter needs to be retrieved, the marked starting image frame and the marked ending image frame can be respectively utilized to determine the starting position and the ending position of the video segment, so that the video segment is determined.

Specifically, when the target image frame is marked as the start image frame, the marking may be performed by way 1 and way 2. Mode 1: and adding a starting identifier for the target image frame, wherein the starting identifier is an identifier for representing the start of the transaction. Mode 2: the frame identifier of the target image frame is recorded as a start identifier, which is an identifier characterizing the start of the transaction. Also, when the target image frame is marked as the termination image frame, the marking may be performed by the manner 3 and the manner 4. Mode 3: and adding an ending mark for the target image frame, wherein the ending mark is a mark for representing the end of the transaction. Mode 4: and recording the frame identifier of the target image frame as an end identifier, wherein the end identifier is an identifier for representing the end of the transaction. Of course, the above is merely an example, in practical applications, there are various ways to mark the target image frame as the start image frame/the end image frame, and the marking way is not limited by the embodiment of the present invention.

Fig. 2 is a flowchart illustrating another video management method according to an embodiment of the present invention. As shown in fig. 2, on the basis of the embodiment shown in fig. 1, after step S104, the following steps may be further included:

and S105, adding the transaction parameters into a plurality of continuous image frames of the real-time monitoring video, wherein the first frame of the plurality of continuous image frames is a target image frame.

After the association relationship between the transaction parameter and the target image frame is established, the transaction parameter may be further added to a plurality of consecutive image frames in the real-time monitoring video, which take the target image frame as the first frame. The added transaction parameters here refer to: the transaction parameters are displayed in a plurality of consecutive image frames, starting with the target image frame. That is, the transaction parameters are displayed in the image frames for a period of time from the target image frame, so that the transaction parameters formed when the user performs the predetermined transaction operation are visually displayed in the image frames representing the predetermined transaction operation. The number of the consecutive image frames can be set according to the requirement, for example: the consecutive plurality of image frames is 120 consecutive image frames.

In the present embodiment, the transaction parameter may be added in a plurality of consecutive image frames by an OSD (On-Screen Display) method, for example. By displaying the transaction parameters in the image frame through the method, the transaction parameters can be displayed in a post-overlapping mode. The post-overlay is different from the prior display mode of displaying the transaction parameters by integrating the transaction parameters into the audio and video code stream of the monitoring video. The display mode of the post-superposition is as follows: when the user sends a transaction parameter display instruction at the ATM host, the transaction parameters are obtained, and the display of the transaction parameters is controlled through a single thread. Specifically, the target transaction parameters are displayed for a period of time from the target image frame by control of the separate thread. That is to say, the transaction parameters can be displayed according to the requirements of the user, and because the transaction parameters are not incorporated into the audio/video code stream of the monitoring video, the transaction information can be prevented from being leaked.

As can be seen from the above, with the video management method provided by the embodiment of the present invention, after receiving a target command sent by a client device, an ATM host determines whether the target command is one of at least one predetermined command; and when the judgment result is yes, acquiring a transaction parameter formed by a preset transaction operation corresponding to the target command, searching a target image frame from a real-time monitoring video corresponding to the client equipment, and then establishing an association relation between the transaction parameter and the target image frame. Therefore, the video management method can realize intelligent management of the monitoring video stored by the ATM host, thereby providing a retrieval basis for intelligent video retrieval. Moreover, by adding the transaction parameters to a plurality of continuous image frames taking the target image frame as the first frame in the real-time monitoring video, the transaction parameters formed when the user performs the predetermined transaction operation can be intuitively displayed in the image frame representing the predetermined transaction operation.

In practical applications, it is increasingly necessary to retrieve videos corresponding to specific transaction information from a large number of monitoring videos stored in an ATM host. For example, a video corresponding to a certain bank card number needs to be retrieved from a large amount of monitoring videos stored by the ATM host.

However, the existing ATM host only stores video and audio data of the surveillance video for the surveillance video collected by the audio/video collecting device. Because only the video and audio data of the surveillance video are stored in the ATM host, when the video corresponding to a specific transaction information needs to be retrieved, the comparison retrieval is usually performed manually in the surveillance video stored in the ATM host, which results in lower retrieval efficiency of video retrieval. In order to solve the above technical problem, an embodiment of the present invention provides a video retrieval method.

It should be noted that the video retrieval method provided by the embodiment of the present invention can be applied to an ATM host.

Next, a video retrieval method provided by an embodiment of the present invention is described.

Fig. 3 is a flowchart illustrating a video retrieval method according to an embodiment of the present invention. The method is applied to the ATM host. As shown in fig. 3, the method may include the steps of:

s301, receiving a retrieval instruction, wherein the retrieval instruction carries: a target transaction parameter.

When any user needs to retrieve the video corresponding to the specific transaction information in the ATM host, the user can send a retrieval instruction to the ATM host, and the specific transaction information can be used as a target transaction parameter and contained in the retrieval instruction. Illustratively, the user may enter the target transaction parameters in a predetermined interface of the ATM host, click a decision or search button, and issue a search command.

The target transaction parameters may include one or more of, for example, one or more of transaction time, transaction operation type, transaction card number, transaction amount, and the like. The target transaction parameter is expressed as a specific value of the corresponding kind of transaction parameter. For example, when the target trading parameter is trading time, the target trading parameter is represented by a specific numerical value of trading time, such as: year 2018, month 5, day 1, 10: 00.

S302, determining a first target image frame corresponding to a target transaction parameter based on a pre-established incidence relation between the transaction parameter and a target image frame, wherein the first target image frame is the target image frame containing the target transaction parameter in the corresponding transaction parameter; the association relationship between the transaction parameters and the target image frames is established according to the video management method shown in fig. 1 or fig. 2.

After receiving the retrieval instruction, the ATM host may determine a first target image frame corresponding to the target transaction parameter based on the association relationship between the transaction parameter and the target image frame established according to the video management method shown in fig. 1 or fig. 2. It is understood that the type of the transaction parameter corresponding to any target image frame is uncertain, and may be one or more, which is related to the predetermined transaction operation performed by the user. Therefore, in this embodiment, the first target image frame is a target image frame of the corresponding transaction parameter that includes the target transaction parameter. That is, when the target transaction parameters are one or more, the transaction parameters corresponding to the first target image frame should include the one or more target transaction parameters. The inclusion here means: the first target image frame is the specific numerical value of the corresponding transaction parameter, and the specific numerical value of the target transaction parameter is included in the first target image frame.

It is understood that, in practical applications, the determined first target image frame may be one frame or multiple frames.

Due to the relationship between the transaction parameters and the target image frames established by the video management method shown in fig. 1 or fig. 2, the relationship between the transaction parameters formed when the user performs the predetermined transaction operation and the image frames representing the predetermined transaction operation is substantially the relationship. Therefore, the first target image frame determined in this step is: when a user performs a predetermined transaction operation to form a target transaction parameter, a target image frame of the predetermined transaction operation can be characterized.

S303, searching the video data containing the first target image frame in the stored monitoring video, and determining the searched video data as a search result.

The stored monitoring videos may specifically be monitoring videos corresponding to each client device. The client device may be an ATM cash dispenser, a bank counter device, or the like. That is, the user may perform a transaction operation on the client device.

Generally, the monitoring video stored by the ATM host can be stored in the ATM host in segments. Therefore, in this embodiment, a video segment in which the first target image frame is located, that is, video data including the first target image frame, may be determined according to the frame identifier of the first target image frame, and the determined video segment may be used as a retrieval result. Wherein the frame identification of the first target image frame may be: a timestamp of the first target image frame. The timestamp of the first target image frame may refer to: the acquisition time of the first target image frame. In this embodiment, the ATM host may store the monitoring video in a local hard disk, and then, the frame identifier of the first target image frame may also be: offset address of the first target image frame in the corresponding hard disk partition. The corresponding hard disk partition refers to: and the hard disk partition of the monitoring video is stored in the hard disk of the ATM host.

It can be understood that, for the case that the first target image frame is a plurality of frames, when the surveillance video segments of some of the plurality of frames are the same, it is not necessary to repeatedly use the surveillance video segment multiple times as the retrieval result.

In order to retrieve the video data more accurately, the starting image frame and the ending image frame marked in the embodiment of fig. 1 or fig. 2 may also be used to determine the video data of the transaction process corresponding to the target transaction parameter, that is, determine the sub-segment of the transaction process containing the first target image frame from the video segment. Specifically, after the video segment including the first target image frame is determined, the start image frame and the end image frame marked in the embodiment of fig. 1 or fig. 2 may be used to determine the start position and the end position of the sub-segment of the transaction process corresponding to the target transaction parameter, so as to determine the sub-segment from the video segment including the first target image frame, where the sub-segment is the video data including the first target image frame. When the first target image frame is not the start image frame and the end image frame, a frame of start image frame closest to the first target image frame may be used as the start position of the transaction process, and a frame of end image frame closest to the first target image frame may be used as the end position of the transaction process; when the first target image frame is a starting image frame, taking the first target image frame as the starting position of the transaction process, and taking a frame ending image frame which is the latest frame after the first target image frame as the ending position of the transaction process; when the first target image frame is the termination image frame, taking a frame starting image frame which is the nearest frame before the first target image frame as the starting position of the transaction process, and taking the first target image frame as the ending position of the transaction process.

For example, every 30 minutes of the surveillance video is taken as a video clip. The video segment is 8:00-8:30,8:30-9:00 and the like, and the sub-segment containing the first target image frame is determined based on the starting image frame, the ending image frame and the first target image frame; if the determined sub-segment is 8:10-8:20, which indicates that the first target image frame is also in the video segment, using the video data of 8:10-8:20 as a retrieval result; if the determined sub-segments are 8:20-8:40 and the timestamp of the first target image frame is 8:25, taking video data of 8:20-8:30 as a retrieval result; if the determined sub-segment is 8:20-8:40 and the timestamp of the first target image frame is 8:35, then the video data of 8:30-8:40 is used as the retrieval result.

As can be seen from the above, according to the scheme provided by the embodiment of the present invention, the ATM host determines the video corresponding to the target transaction parameter from the stored surveillance video based on the pre-established association relationship between the transaction parameter and the target image frame. Compared with the manual retrieval in the prior art, the video corresponding to the specific transaction information can be quickly and effectively retrieved.

Fig. 4 is a flowchart illustrating another video retrieval method according to an embodiment of the present invention. As shown in fig. 4, on the basis of the embodiment shown in fig. 3, after step S303, the following steps may be further included:

s304, adding the target transaction parameter into a plurality of continuous image frames of the video as a retrieval result, wherein the first frame of the plurality of continuous image frames is the first target image frame.

In the stored monitoring video, a video including a first target image frame is searched, and after the searched video is determined as a search result, a target transaction parameter may be further added to a plurality of consecutive image frames in the video as the search result, the first target image frame being a first frame. The adding of the target transaction parameters refers to: the target transaction parameter is displayed in a consecutive plurality of image frames, starting with a first target image frame. That is, starting from the first target image frame, the target transaction parameter is displayed in the image frame for a period of time, so that the target transaction parameter formed when the user performs the certain predetermined transaction operation is visually displayed in the image frame representing the certain predetermined transaction operation. The number of the consecutive image frames can be set according to the requirement, for example: the consecutive plurality of image frames is 120 consecutive image frames.

In the present embodiment, the target transaction parameter may be added in a plurality of consecutive image frames by an OSD (On-Screen Display) method, for example. By displaying the target transaction parameters in the image frame through the method, the target transaction parameters can be displayed in a 'post-superposition' mode. The post-superposition is different from the prior display mode of displaying the target transaction parameter by integrating the target transaction parameter into the audio/video code stream of the monitoring video. The display mode of the post-superposition is as follows: when a user sends a target transaction parameter display instruction at the ATM host, the target transaction parameter is obtained, and the display of the target transaction parameter is controlled through a single thread. Specifically, the target transaction parameters are displayed for a period of time starting from the first target image frame, controlled by the separate thread. That is to say, the target transaction parameters can be displayed according to the requirements of the user, and because the target transaction parameters are not merged into the audio/video code stream of the monitoring video, the transaction information can be prevented from being leaked.

As can be seen from the above, according to the scheme provided by the embodiment of the present invention, the ATM host determines the video corresponding to the target transaction parameter from the stored surveillance video based on the pre-established association relationship between the transaction parameter and the target image frame. Compared with the manual retrieval in the prior art, the video corresponding to the specific transaction information can be quickly and effectively retrieved. Moreover, by adding the target transaction parameter to a plurality of consecutive image frames in the stored monitoring video, the first target image frame being the first frame, the target transaction parameter formed when the user performs the certain predetermined transaction operation can be intuitively displayed in the image frame representing the certain predetermined transaction operation.

Corresponding to the video management method provided by the embodiment of the invention, the embodiment of the invention also provides a video management device. The video management device is applied to an ATM host which is in communication connection with a client device.

Fig. 5 is a video management apparatus according to an embodiment of the present invention, and as shown in fig. 5, the apparatus may include the following modules:

a first receiving module 501, configured to receive a target command sent by the client device;

a determining module 502, configured to determine whether the target command is one of at least one predetermined command; any preset command is a command generated by the client device when the client device detects that a user performs a preset transaction operation on the client device; different predetermined transaction operations correspond to different predetermined commands;

an obtaining module 503, configured to, when a determination result is yes, obtain a transaction parameter formed by a predetermined transaction operation corresponding to the target command, and search a target image frame from a real-time monitoring video corresponding to the client device, where the target image frame is an image frame capable of representing the predetermined transaction operation corresponding to the target command;

an establishing module 504, configured to establish an association relationship between the transaction parameter and the target image frame.

As can be seen from the above, with the video management apparatus provided in the embodiment of the present invention, after receiving a target command sent by a client device, an ATM host determines whether the target command is one of at least one predetermined command; and when the judgment result is yes, acquiring a transaction parameter formed by a preset transaction operation corresponding to the target command, searching a target image frame from a real-time monitoring video corresponding to the client equipment, and then establishing an association relation between the transaction parameter and the target image frame. Therefore, the video management method can realize intelligent management of the monitoring video stored by the ATM host, thereby providing a retrieval basis for intelligent video retrieval.

As an implementation manner of the embodiment of the present invention, the frame type of the target image frame is an I frame;

the obtaining module 503 is specifically configured to search, from the real-time monitoring video corresponding to the client device, an I frame whose timestamp is closest to a target time point, as a target image frame; and the target time point is the time point of acquiring the transaction parameters.

As an implementation manner of the embodiment of the present invention, the at least one predetermined command includes: the client device generates a first command when detecting that the user performs a transaction starting operation, and generates a second command when detecting that the user performs a transaction ending operation;

the device further comprises:

a first control module, configured to, when the target command is the first command, mark the target image frame as an initial image frame after the obtaining module 503 searches for the target image frame from the real-time monitoring video corresponding to the client device, where the initial image frame is an image frame representing that a transaction is started;

a second control module, configured to, when the target command is the second command, mark the target image frame as a termination image frame after the acquisition module 503 searches for the target image frame from the real-time monitoring video corresponding to the client device, where the termination image frame is an image frame that represents that a transaction is terminated.

As an implementation manner of the embodiment of the present invention, the establishing module 504 is specifically configured to correspondingly store the transaction parameter and the frame identifier of the target image frame in a hard disk of the ATM host or a storage device connected to the ATM host.

As an implementation manner of the embodiment of the present invention, the apparatus further includes:

a first adding module, configured to add the transaction parameter to consecutive image frames of the real-time surveillance video after the establishing module 504 establishes an association relationship between the transaction parameter and the target image frame, where a first frame of the consecutive image frames is the target image frame.

Corresponding to the video retrieval method provided by the embodiment of the invention, the embodiment of the invention also provides a video retrieval device. The video retrieval device is applied to an ATM host.

Fig. 6 is a video retrieval apparatus according to an embodiment of the present invention, and as shown in fig. 6, the apparatus may include the following modules:

a second receiving module 601, configured to receive a retrieval instruction, where the retrieval instruction carries: a target transaction parameter;

a determining module 602, configured to determine, based on a pre-established association relationship between a transaction parameter and a target image frame, a first target image frame corresponding to the target transaction parameter, where the first target image frame is a target image frame of the corresponding transaction parameter that includes the target transaction parameter; the association relationship between the transaction parameters and the target image frame is established by the video management device shown in fig. 5;

the searching module 603 is configured to search the stored surveillance video for video data including the first target image frame, and determine the searched video data as a search result.

a second adding module, configured to, after the searching module 603 searches for a video including the first target image frame in the stored surveillance video, and determines the found video as a search result, add the target transaction parameter to a plurality of consecutive image frames of the video serving as the search result, where a first frame of the plurality of consecutive image frames is the first target image frame.

An embodiment of the present invention further provides an electronic device, which is an ATM host, as shown in fig. 7, and includes a processor 701, a communication interface 702, a memory 703 and a communication bus 704, where the processor 701, the communication interface 702, and the memory 703 complete mutual communication through the communication bus 704,

a memory 703 for storing a computer program;

the processor 701 is configured to implement the video management method according to the embodiment of the present invention when executing the program stored in the memory 703, so as to obtain the same technical effect.

The communication bus mentioned in the electronic device may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.

The communication interface is used for communication between the electronic equipment and other equipment.

The Memory may include a Random Access Memory (RAM) or a non-volatile Memory (non-volatile Memory), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the processor.

The Processor may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the device can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, or a discrete hardware component.

The embodiment of the present invention further provides another electronic device, which is an ATM host, as shown in fig. 8, and includes a processor 801, a communication interface 802, a memory 803, and a communication bus 804, where the processor 801, the communication interface 802, and the memory 803 complete mutual communication via the communication bus 804,

a memory 803 for storing a computer program;

the processor 801 is configured to implement the video retrieval method according to the embodiment of the present invention when executing the program stored in the memory 803, so as to obtain the same technical effect.

In yet another embodiment of the present invention, there is further provided a computer-readable storage medium having stored therein instructions, which when run on a computer, cause the computer to execute the video management method of any one of the above embodiments to obtain the same technical effect.

In another embodiment of the present invention, there is provided another computer-readable storage medium, which stores instructions that, when executed on a computer, cause the computer to execute the video retrieval method of any one of the above embodiments to obtain the same technical effect.

In a further embodiment provided by the present invention, there is also provided a computer program product containing instructions which, when run on a computer, cause the computer to perform the video management method of any of the above embodiments to achieve the same technical effect.

In yet another embodiment of the present invention, there is provided another computer program product containing instructions, which when run on a computer, causes the computer to execute the video retrieval method of any of the above embodiments to achieve the same technical effect.

In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. The procedures or functions according to the embodiments of the invention are brought about in whole or in part when the computer program instructions are loaded and executed on a computer. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wire (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wirelessly (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.

It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.

All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the device/ATM host/storage medium/computer program product embodiment, since it is substantially similar to the method embodiment, the description is relatively simple, and reference may be made to the partial description of the method embodiment for the relevant points.

The above description is only for the preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention shall fall within the protection scope of the present invention.

Claims

1. A video management method for use with an ATM host communicatively coupled to a client device, the method comprising:

receiving a target command sent by the client device;

2. The method of claim 1, wherein the frame type of the target image frame is an I-frame;

3. The method of claim 1, wherein the at least one predetermined command comprises: the client device generates a first command when detecting that the user performs a transaction starting operation, and generates a second command when detecting that the user performs a transaction ending operation;

the method further comprises the following steps:

4. The method according to any one of claims 1-3, wherein said associating said transaction parameter with said target image frame comprises:

5. The method of any of claims 1-3, wherein after establishing the association of the transaction parameter with the target image frame, the method further comprises:

6. A video retrieval method for use with an ATM host, the method comprising:

determining a first target image frame corresponding to a target transaction parameter based on a pre-established association relation between the transaction parameter and the target image frame, wherein the first target image frame is a target image frame containing the target transaction parameter in the corresponding transaction parameter; the association relation between the transaction parameters and the target image frames is established according to the video management method of any one of claims 1 to 5;

7. A video management apparatus for use with an ATM host communicatively coupled to a client device, the apparatus comprising:

8. A video retrieval device for use with an ATM host, said device comprising:

the determining module is used for determining a first target image frame corresponding to the target transaction parameter based on a pre-established association relation between the transaction parameter and a target image frame, wherein the first target image frame is a target image frame of the corresponding transaction parameter, and the target image frame comprises the target transaction parameter; the association relation between the transaction parameter and the target image frame is established by the video management device of claim 7;

9. An electronic device is characterized in that the electronic device is an ATM host and comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus;

a memory for storing a computer program;

a processor for implementing the method steps of any one of claims 1 to 6 when executing a program stored in the memory.

10. A computer-readable storage medium, characterized in that a computer program is stored in the computer-readable storage medium, which computer program, when being executed by a processor, carries out the method steps of any one of claims 1-6.