CN115866290A - Video dotting method, device, equipment and storage medium - Google Patents
Video dotting method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN115866290A CN115866290A CN202210610692.6A CN202210610692A CN115866290A CN 115866290 A CN115866290 A CN 115866290A CN 202210610692 A CN202210610692 A CN 202210610692A CN 115866290 A CN115866290 A CN 115866290A
- Authority
- CN
- China
- Prior art keywords
- video
- dotting
- information
- node
- audio
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 205
- 238000001514 detection method Methods 0.000 claims description 34
- 238000004590 computer program Methods 0.000 claims description 20
- 238000004422 calculation algorithm Methods 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 10
- 238000004891 communication Methods 0.000 description 6
- 238000007689 inspection Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000008034 disappearance Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 230000002996 emotional effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 230000005236 sound signal Effects 0.000 description 1
Images
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a video dotting method, a video dotting device, video dotting equipment and a storage medium. The video dotting method comprises the following steps: acquiring a video file to be dotted, and extracting an audio file to be identified from the video file to be dotted; performing voice recognition on the audio file to be recognized to obtain an audio recognition result; matching the audio recognition result through a process state matcher to obtain process anchor point information; and determining to obtain video dotting information according to the process anchor point information, and dotting the video to be dotted according to the video dotting information. The invention can realize intelligent dotting of the video and improve the dotting efficiency of the video.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a video dotting method, a video dotting device, video dotting equipment and a storage medium.
Background
The double recording (namely, the sound recording and the video recording) is a hard regulation of a bank prison, on one hand, the phenomena of false commitment and illegal cost protection and publicity in the process of communicating with a client by a trust company or a three-party financing sales staff are avoided, on the other hand, the double recording (namely, the sound recording and the video recording) is also a re-reminding for the risk bearing capacity and the product risk awareness of an investor, and the original intention is still to protect the investor.
However, since the financial market is a market with a huge audience population, any company cannot finish the sales of all financial products through its own dedicated channel, and in order to increase the market share, almost all parties or security officers will sell the same product in multiple channels by adopting a self-supporting and partner distribution mode, and a compliance problem is faced in this cooperation mode, namely: if the customer purchases financing or insurance products through a self-operated channel, the trade is carried out through an online system of a bank or a security department, and the process can carry out sound recording and video recording strictly according to a compliance flow and carry out compliance detection in real time. But the selling channels of the partners face different situations, due to the technical reserve and cost problems of the partners, the real-time compliance recording capability cannot be provided for the customers, the videos can be uploaded to a system of a security department or a bank party only in a mode of video recording under a line after the transaction is completed, and the part of business faces great compliance risks.
In the off-line quality inspection system of two recordings, because the compliance video is that the third party sales channel transmitted, the information of dotting of each node of video is the disappearance, consequently needs the artifical dotting of operating personnel, and its efficiency is very low, consequently, need a set of intelligence that provides to the video in the off-line compliance detection scene promptly to make things convenient for artifical reinspection can fix a position the node of the non-compliance in the video fast.
Disclosure of Invention
The invention mainly aims to provide a video dotting method, a video dotting device, video dotting equipment and a storage medium, and aims to realize intelligent dotting of videos and improve video dotting efficiency.
In order to achieve the above object, the present invention provides a video dotting method, including:
acquiring a video file to be doted, and extracting an audio file to be identified from the video file to be doted;
carrying out voice recognition on the audio file to be recognized to obtain an audio recognition result;
matching the audio recognition result through a process state matcher to obtain process anchor point information;
and determining to obtain video dotting information according to the process anchor point information, and dotting the video to be dotted according to the video dotting information.
Preferably, before the step of matching the audio recognition result by the process state matcher to obtain process anchor point information, the video dotting method further includes:
acquiring service flow information, wherein the service flow information comprises a node number of each service flow node, a service flow dialect, a keyword and a service flow sequence;
and respectively constructing the keywords of each service process node into a state tree of the finite state machine according to a finite state machine algorithm, and obtaining the process state matcher based on the service process node numbers, the service process sequence and the state tree.
Preferably, the step of matching the audio recognition result through the process state matcher to obtain process anchor point information includes:
matching the keywords in the state tree of the process state matcher with the audio recognition result to obtain a matching result;
and determining to obtain process anchor point information according to the matching result, wherein the process anchor point information comprises the corresponding starting time and ending time of each service process node in the audio file to be identified.
Preferably, the step of determining to obtain video dotting information according to the process anchor point information includes:
determining video dotting positions of the service process nodes according to corresponding starting time and ending time of the service process nodes in the process anchor point information in the audio file to be identified;
and acquiring a node title corresponding to each service flow node, and acquiring video dotting information according to the video dotting position and the node title.
Preferably, before the step of obtaining the video dotting information according to the video dotting position and the node title, the video dotting method further includes:
acquiring a compliance detection result of each service process node corresponding to the video to be doted, and determining dotting color information corresponding to each video dotting position according to the compliance detection result;
the step of obtaining video dotting information according to the video dotting position and the node title comprises the following steps:
and obtaining video dotting information according to the video dotting position, the dotting color information and the node title.
Preferably, the step of dotting the video to be dotted according to the video dotting information includes:
and drawing the video dotting information on a progress bar of a video player plug-in to realize dotting processing of the video to be dotted.
In addition, to achieve the above object, the present invention further provides a video dotting apparatus, including:
the file acquisition module is used for acquiring a video file to be dotted and extracting an audio file to be identified from the video file to be dotted;
the voice recognition module is used for carrying out voice recognition on the audio file to be recognized to obtain an audio recognition result;
the information matching module is used for matching the audio identification result through the process state matcher to obtain process anchor point information;
and the video dotting module is used for determining to obtain video dotting information according to the process anchor point information and dotting the video to be dotted according to the video dotting information.
In addition, to achieve the above object, the present invention also provides a video dotting apparatus, including: a memory, a processor and a computer program stored on the memory and executable on the processor, the computer program, when executed by the processor, implementing the steps of the video dotting method as described above.
Furthermore, to achieve the above object, the present invention further provides a computer readable storage medium, having a computer program stored thereon, where the computer program is executed by a processor to implement the steps of the video dotting method as described above.
The invention provides a video dotting method, a video dotting device, video dotting equipment and a storage medium, wherein a video file to be dotted is obtained first, and an audio file to be identified is extracted from the video file to be dotted; then, carrying out voice recognition on the audio file to be recognized to obtain an audio recognition result; then, matching the audio recognition result through a process state matcher to obtain process anchor point information; and then determining to obtain video dotting information according to the process anchor point information, and dotting the video to be dotted according to the video dotting information. Through the mode, the intelligent dotting of videos can be realized, and compared with a manual dotting mode, the efficiency of dotting of videos can be greatly improved. In addition, after the video is dotted, the position where the video compliance detection fails can be quickly positioned in the process of manual rechecking, and the manual quality inspection efficiency is further improved.
Drawings
Fig. 1 is a schematic device structure diagram of a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating a video dotting method according to a first embodiment of the present invention;
fig. 3 is a functional block diagram of a video dotting device according to a first embodiment of the invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1, fig. 1 is a schematic device structure diagram of a hardware operating environment according to an embodiment of the present invention.
The video dotting device in the embodiment of the present invention may be a server, or may also be a terminal device such as a PC (Personal Computer), a tablet Computer, or a portable Computer.
As shown in fig. 1, the video dotting apparatus may include: a processor 1001, such as a CPU, a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., a Wi-Fi interface). The memory 1005 may be a high-speed RAM memory or a non-volatile memory (e.g., a magnetic disk memory). The memory 1005 may alternatively be a storage device separate from the processor 1001.
Those skilled in the art will appreciate that the video dotting device structure shown in fig. 1 does not constitute a limitation of the video dotting device, and may include more or fewer components than shown, or some components may be combined, or a different arrangement of components.
As shown in fig. 1, a memory 1005, which is a kind of computer storage medium, may include therein an operating system, a network communication module, a user interface module, and a computer program.
In the terminal shown in fig. 1, the network interface 1004 is mainly used for connecting to a backend server and performing data communication with the backend server; the user interface 1003 is mainly used for connecting a client and performing data communication with the client; and the processor 1001 may be configured to invoke the computer program stored in the memory 1005 and perform the following operations:
acquiring a video file to be dotted, and extracting an audio file to be identified from the video file to be dotted;
carrying out voice recognition on the audio file to be recognized to obtain an audio recognition result;
matching the audio recognition result through a process state matcher to obtain process anchor point information;
and determining to obtain video dotting information according to the process anchor point information, and dotting the video to be dotted according to the video dotting information.
Further, the processor 1001 may call the computer program stored in the memory 1005, and also perform the following operations:
acquiring service flow information, wherein the service flow information comprises a node number of each service flow node, a service flow dialect, a keyword and a service flow sequence;
and respectively constructing the keywords of each service process node into a state tree of the finite state machine according to a finite state machine algorithm, and obtaining the process state matcher based on the service process node numbers, the service process sequence and the state tree.
Further, the processor 1001 may call the computer program stored in the memory 1005, and also perform the following operations:
matching the keywords in the state tree of the process state matcher with the audio recognition result to obtain a matching result;
and determining to obtain process anchor point information according to the matching result, wherein the process anchor point information comprises the corresponding starting time and ending time of each service process node in the audio file to be identified.
Further, the processor 1001 may call the computer program stored in the memory 1005, and also perform the following operations:
determining video dotting positions of the service process nodes according to corresponding starting time and ending time of the service process nodes in the process anchor point information in the audio file to be identified;
and acquiring a node title corresponding to each service flow node, and acquiring video dotting information according to the video dotting position and the node title.
Further, the processor 1001 may call the computer program stored in the memory 1005, and also perform the following operations:
acquiring a compliance detection result of each service process node corresponding to the video to be doted, and determining dotting color information corresponding to each video dotting position according to the compliance detection result;
the step of obtaining video dotting information according to the video dotting position and the node title comprises the following steps:
and obtaining video dotting information according to the video dotting position, the dotting color information and the node title.
Further, the processor 1001 may call the computer program stored in the memory 1005, and also perform the following operations:
and drawing the video dotting information on a progress bar of a video player plug-in to realize dotting processing on the video to be dotted.
Based on the hardware structure, the invention provides various embodiments of the video dotting method.
The invention provides a video dotting method.
Referring to fig. 2, fig. 2 is a flowchart illustrating a video dotting method according to a first embodiment of the present invention.
In this embodiment, the video dotting method includes:
step S10, obtaining a video file to be doted, and extracting an audio file to be identified from the video file to be doted;
the video dotting method of the embodiment is implemented by a video dotting device, which may be a server, or a terminal device such as a PC (Personal Computer), a tablet Computer, or a portable Computer.
In this embodiment, a video file to be dotted is obtained first, where the video file to be dotted is a video file recorded in an intelligent dual-recording quality inspection scene, and the video file to be dotted includes a video file and an audio file, so that an audio part of a video to be dotted needs to be extracted and divided first to obtain an audio file to be identified, and specifically, the audio file in the video to be dotted can be extracted through Fast Forward Mpeg (multimedia video processing tool) and converted into an audio format and a code rate required by a subsequent speech recognition algorithm to obtain an audio to be identified.
FFMPEG is a set of open source computer programs that can be used to record, convert digital audio, video, and convert them into streams, using LGPL or GPL licenses. It provides a complete solution for recording, converting and streaming audio and video.
Step S20, carrying out voice recognition on the audio file to be recognized to obtain an audio recognition result;
after the audio file to be recognized is obtained, voice recognition is carried out on the audio file to be recognized, and an audio recognition result is obtained. During Speech Recognition, an ASR (Automatic Speech Recognition) algorithm may be used for Recognition, and a corresponding interface may be called for Speech Recognition, and certainly, during specific implementation, the audio file to be recognized may also be sent to a corresponding professional platform for Speech Recognition, and then an audio Recognition result returned by the professional platform is received.
The audio recognition results include, but are not limited to: channel _ ID (track ID to which the sentence belongs), begin _ time (start time offset of the sentence in milliseconds), end _ time (end time offset of the sentence in milliseconds), text (recognized text result of the sentence), emotion _ value (emotional energy value 1-10, the higher the value is), silence _ duration (silence duration between the sentence and the previous sentence in seconds), and average speech rate of the speech _ rate sentence in words per minute).
And step S30, matching the audio identification result through a process state matcher to obtain process anchor point information.
After performing voice recognition to obtain an audio recognition result, matching the audio recognition result through a process state matcher to obtain process anchor point information, where the process state matcher is pre-constructed, and a specific construction process may refer to the following second embodiment, which is not described herein again, and the process anchor point information includes start time and end time corresponding to each service process node in the audio file to be recognized.
The process of acquiring the flow anchor point information is as follows: matching the keywords in the state tree of the process state matcher with the audio recognition result, namely recognizing the keywords configured by each service process node through the state tree, finally calculating the recognition total score of each service process node, wherein if the recognition total score exceeds a preset threshold value, the recognition total score is hit, and the calculation formula of the recognition total score is as follows: score (total identification) = T (set number of keywords)/R (identified number of keywords) × 100%, and then, according to the matching result, the corresponding time points (including the start time and the end time) of each service process node in the audio identification result, that is, the process anchor information, can be determined.
And S40, determining to obtain video dotting information according to the process anchor point information, and dotting the video to be dotted according to the video dotting information.
After the process anchor point information is obtained, video dotting information is determined and obtained according to the process anchor point information, wherein the video dotting information at least comprises video dotting positions and node titles corresponding to the service process nodes, and dotting color information corresponding to the video dotting positions can be further included.
Specifically, the video dotting position of each service flow node can be determined according to the corresponding start time and end time of each service flow node in the flow anchor point information in the audio file to be identified, then, the node title corresponding to each service flow node is obtained, and the video dotting information is obtained according to the video dotting position and the node title.
Furthermore, a compliance detection result of each service process node corresponding to the video to be doted can be obtained, dotting color information corresponding to each video dotting position is determined according to the compliance detection result, and then video dotting information is obtained according to the video dotting position, the dotting color information and the node title.
For a specific process of acquiring video dotting information, reference may be made to the following third embodiment, which is not described herein again.
Further, the step of performing dotting processing on the video to be dotted according to the video dotting information comprises the following steps:
and drawing the video dotting information on a progress bar of a video player plug-in to realize dotting processing of the video to be dotted.
In this embodiment, after the video dotting information is acquired, dotting processing is performed on the video to be dotted according to the video dotting information, and specifically, the video dotting information is drawn on a progress bar of a video player plug-in to implement dotting processing on the video to be dotted. By video dotting, when a user moves a mouse to a small point on a video playing bar, the video content corresponding to the small point is displayed in a toast (a simple message prompt box) prompt box mode.
The embodiment of the invention provides a video dotting method, which comprises the steps of firstly obtaining a video file to be dotted, and extracting an audio file to be identified from the video file to be dotted; then, carrying out voice recognition on the audio file to be recognized to obtain an audio recognition result; then, matching the audio recognition result through a process state matcher to obtain process anchor point information; and then determining to obtain video dotting information according to the process anchor point information, and dotting the video to be dotted according to the video dotting information. Through the mode, the intelligent dotting of videos can be realized, and compared with a manual dotting mode, the efficiency of dotting of videos can be greatly improved. In addition, after the video is dotted, the position of failure in video compliance detection can be quickly positioned in the process of manual review, and the efficiency of manual quality inspection is further improved.
Further, based on the first embodiment, a second embodiment of the video dotting method according to the present invention is provided.
In this embodiment, before the step S30, the video dotting method further includes:
step A, acquiring service flow information, wherein the service flow information comprises a node number of each service flow node, a service flow conversation, a keyword and a service flow sequence;
and step B, respectively constructing the keywords of each service process node into a state tree of the finite state machine according to a finite state machine algorithm, and obtaining the process state matcher based on the service process node numbers, the service process sequence and the state tree.
In this embodiment, the service flow information is obtained, where the service flow information includes a node number (nodeId), a service flow technology (Speech), a Keyword (Keyword), and a service flow sequence (detailSort) of each service flow node, and the service flow information may further include: the expression mode of the node title and the business process information is mostly message data in a json format. The intelligent double-record quality inspection service in the sales process of a financial product is taken as an example for explanation.
The business process information may be:
after the business process information is obtained, keywords of all business process nodes are respectively constructed into a state tree of the finite state machine according to a finite state machine algorithm, and then a process state matcher is obtained based on the serial number of the business process nodes, the business process sequence and the state tree. Among them, the Finite state machine (DFA) refers to a tool for performing object behavior modeling, which is used to describe the sequence of states that an object experiences in its lifecycle and how to respond to various events from the outside world, and converts from one state to another state through a series of events, namely state- > event- > state.
Further, step S30 may include:
step a31, matching keywords in a state tree of the process state matcher with the audio recognition result to obtain a matching result;
step a32, determining to obtain process anchor point information according to the matching result, wherein the process anchor point information comprises the corresponding starting time and ending time of each service process node in the audio file to be identified.
In this embodiment, when performing a process anchor based on an audio recognition result obtained by speech recognition, the specific process is as follows: matching the keywords in the state tree of the process state matcher with the audio recognition result, namely recognizing the keywords configured by each service process node through the state tree, and finally calculating the recognition total score of each service process node, wherein if the recognition total score exceeds a preset threshold value, the recognition total score is hit, and the calculation formula of the recognition total score is as follows: score (total identification) = T (set number of keywords)/R (identified number of keywords) × 100%, and then, according to the matching result, the corresponding time point (including the start time and the end time) of each business process node in the audio identification result can be determined.
In this embodiment, the keyword to be matched is constructed as a state tree by using a finite state machine algorithm, and further constructed as a process state matcher, so that the audio recognition result is subsequently matched by using the process state matcher, and process anchor point information, that is, the corresponding time point of each service process node in the audio file to be recognized, is obtained. The matching identification of the business process is completed in a finite state machine mode, compared with the existing identification method adopting an NLP intention identification algorithm, the accuracy and the precision of the business process identification can be greatly improved, meanwhile, relevant rules do not need to be configured manually, the process complexity can be greatly simplified, and the identification efficiency is improved.
Further, based on the second embodiment, a third embodiment of the video dotting method according to the present invention is provided.
In this embodiment, the step of "determining to obtain video dotting information according to the flow anchor information" may include:
step a41, determining the video dotting position of each service process node according to the corresponding start time and end time of each service process node in the audio file to be identified in the process anchor point information;
and a42, acquiring a node title corresponding to each service flow node, and acquiring video dotting information according to the video dotting position and the node title.
In this embodiment, the video dotting information is obtained as follows:
and determining the video dotting position of each service flow node according to the corresponding starting time and ending time of each service flow node in the flow anchor point information in the audio file to be identified, wherein the video dotting position of each service flow node specifically comprises a starting dotting position and an ending dotting position, the starting dotting position corresponds to the position of the starting time in the video to be dotted, and the ending dotting position corresponds to the position of the ending time in the video to be dotted. And then, acquiring a node title corresponding to each service flow node, and obtaining video dotting information according to the video dotting position and the node title.
Further, before the step "determining to obtain video dotting information according to the process anchor point information", the video dotting method may further include:
step a43, acquiring a compliance detection result of each service process node corresponding to the video to be doted, and determining dotting color information corresponding to each video dotting position according to the compliance detection result;
in this case, the step of "obtaining video dotting information according to the video dotting position and the node title" may include:
and obtaining video dotting information according to the video dotting position, the dotting color information and the node title.
In this embodiment, the video dotting information may be further refined by combining the compliance detection result of the video to be dotted, specifically, while the video dotting position and the node title are obtained, the compliance detection result of each business process node corresponding to the video to be dotted may be further obtained, and the dotting color information corresponding to each video dotting position is determined according to the compliance detection result, for example, if the compliance detection result is pass, the dotting color information may be represented by red, and if the compliance detection result is fail, the dotting color information may be represented by white. And then, obtaining video dotting information according to the video dotting position, the dotting color information and the node title. The video dotting information can be expressed as follows:
wherein beginTime represents the starting time offset of the sentence, and the unit is millisecond; endTime the end time offset of the sentence in milliseconds; subject represents a node title; pointColor indicates dotted color; emsg denotes error prompt; detailSort represents the flow sequence.
Further, based on the first to third embodiments, a fourth embodiment of the video dotting method according to the present invention is provided.
In this embodiment, before the step S20, the video dotting method further includes:
step C, performing VAD detection on the audio file to be identified to obtain a detection result;
in this embodiment, after the audio file to be recognized is obtained, before the algorithm is called to perform Voice recognition, VAD (Voice Activity Detection) Detection is performed on the audio file to be recognized to obtain a Detection result, so as to recognize a silence segment from the audio signal stream.
Step D, judging whether the audio file to be identified is blank audio according to the detection result;
if the audio file to be identified is not a blank audio, executing step S20: and carrying out voice recognition on the audio file to be recognized to obtain an audio recognition result.
After the VAD detection result is obtained, whether the audio file to be identified is blank audio or not is judged according to the detection result, namely whether the total duration of the silent segment of the audio file to be identified is greater than or equal to the product value of the total duration and a preset proportion (which can be specifically set according to actual needs) or not is detected according to the detection result, and if the total duration of the silent segment is greater than or equal to the product value, the audio file to be identified is judged to be blank audio; and if the total duration of the silent segments is less than the product value, judging that the audio file to be identified is not blank audio.
Further, if the audio file to be identified is not a blank audio, continuing to execute the following steps: and carrying out voice recognition on the audio file to be recognized to obtain an audio recognition result. For a specific implementation process, reference may be made to the first embodiment, which is not described herein again.
Further, if the audio file to be identified is blank audio, the subsequent steps are stopped to be executed, and error prompt information is generated to prompt that the audio file to be identified is blank audio, so that detection is not needed, and algorithm resources are prevented from being wasted.
In this embodiment, by performing VAD detection on the audio file to be recognized, subsequent detection is not performed when blank audio is detected, and subsequent detection is performed only when it is detected that the audio file to be recognized is not blank audio.
Further, based on the fourth embodiment, a fifth embodiment of the video dotting method according to the present invention is proposed.
In this embodiment, before the step S20, the video dotting method further includes:
step E, judging whether a silent segment exists at the beginning and/or the end of the audio file to be identified according to the detection result;
in this embodiment, after obtaining the VAD detection result and detecting the blank audio, if the audio file to be identified is not the blank audio, further, whether a silence segment exists at the beginning and/or the end of the audio file to be identified may be determined according to the detection result.
Step F, if a silent segment exists at the beginning and/or the end of the audio file to be identified, determining to obtain a silent period according to the detection result;
step G, intercepting the audio file to be identified according to the silent time period to obtain a target audio file;
at this time, step S20 may include:
and carrying out voice recognition on the target recognition audio file to obtain an audio recognition result.
If the beginning and/or the end of the audio file to be identified has the silent segment, determining to obtain a silent time period according to the detection result, namely the time period corresponding to the beginning silent segment and/or the end silent segment. And then, intercepting the audio file to be identified according to the silent time period, namely removing the silent segments at the beginning and/or the end and reserving the non-silent segments at the middle part to obtain the target audio file. Further, the target recognition audio file is subjected to speech recognition to obtain an audio recognition result, and further subsequent steps are performed, and the specific execution process may refer to the first embodiment, which is not described herein again.
By the method, whether the beginning and/or the end of the audio file to be recognized have the silent segments or not is detected, and if the silent segments exist, the silent segments are segmented out, so that the waste of part of algorithm resources is further avoided, the waste of expense for calling the voice recognition algorithm by an enterprise is further avoided, and the enterprise cost can be saved.
The invention also provides a video dotting device.
Referring to fig. 3, fig. 3 is a functional module diagram of a video dotting device according to a first embodiment of the present invention.
As shown in fig. 3, the video dotting apparatus includes:
the file acquisition module 10 is configured to acquire a video file to be doted, and extract an audio file to be identified from the video file to be doted;
the voice recognition module 20 is configured to perform voice recognition on the audio file to be recognized to obtain an audio recognition result;
the information matching module 30 is configured to match the audio recognition result through a process state matcher, so as to obtain process anchor point information;
and the video dotting module 40 is configured to determine to obtain video dotting information according to the process anchor point information, and perform dotting processing on the video to be dotted according to the video dotting information.
Further, the video dotting device further comprises:
the information acquisition module is used for acquiring business process information, wherein the business process information comprises the node number of each business process node, a business process strategy, a keyword and a business process sequence;
and the matcher constructing module is used for respectively constructing the keywords of each service process node into a state tree of the finite state machine according to a finite state machine algorithm, and obtaining the process state matcher based on the service process node numbers, the service process sequence and the state tree.
Further, the information matching module 30 includes:
the information matching unit is used for matching the keywords in the state tree of the process state matcher with the audio recognition result to obtain a matching result;
and the information determining unit is used for determining and obtaining process anchor point information according to the matching result, wherein the process anchor point information comprises the corresponding starting time and ending time of each service process node in the audio file to be identified.
Further, the video dotting module 40 includes:
a dotting position determining unit, configured to determine a video dotting position of each service process node according to a start time and an end time, corresponding to each service process node in the audio file to be identified, in the process anchor point information;
and the dotting information determining unit is used for acquiring node titles corresponding to the service flow nodes and obtaining video dotting information according to the video dotting positions and the node titles.
Further, the video dotting module 40 further includes:
the result acquisition unit is used for acquiring the compliance detection result of each service process node corresponding to the video to be doted and determining dotting color information corresponding to each video dotting position according to the compliance detection result;
and the dotting information determining unit is also used for obtaining video dotting information according to the video dotting position, the dotting color information and the node title.
Further, the video dotting module 40 further includes:
and the video dotting unit is used for drawing the video dotting information on a progress bar of a video player plug-in so as to realize dotting processing of the video to be doted.
The function implementation of each module in the video dotting device corresponds to each step in the video dotting method embodiment, and the function and implementation process are not described in detail herein.
The present invention further provides a computer-readable storage medium, on which a computer program is stored, which, when executed by a processor, implements the steps of the video dotting method according to any one of the above embodiments.
The specific embodiment of the computer-readable storage medium of the present invention is substantially the same as the embodiments of the video dotting method described above, and is not described herein again.
The invention also provides a computer program product comprising a computer program which, when executed by a processor, carries out the steps of the video dotting method as claimed in any one of the above.
The specific embodiment of the computer program product of the present invention is substantially the same as the embodiments of the video dotting method described above, and will not be described herein again.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system 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 system. Without further limitation, an element defined by the phrases "comprising a," "8230," "8230," or "comprising" does not exclude the presence of other like elements in a process, method, article, or system comprising the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) as described above and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (9)
1. A video dotting method is characterized by comprising the following steps:
acquiring a video file to be dotted, and extracting an audio file to be identified from the video file to be dotted;
carrying out voice recognition on the audio file to be recognized to obtain an audio recognition result;
matching the audio recognition result through a process state matcher to obtain process anchor point information;
and determining to obtain video dotting information according to the process anchor point information, and dotting the video to be dotted according to the video dotting information.
2. The video dotting method according to claim 1, wherein before the step of matching the audio recognition result by the process state matcher to obtain process anchor point information, the video dotting method further comprises:
acquiring service flow information, wherein the service flow information comprises a node number of each service flow node, a service flow dialect, a keyword and a service flow sequence;
and respectively constructing the keywords of each service process node into a state tree of the finite state machine according to a finite state machine algorithm, and obtaining the process state matcher based on the service process node numbers, the service process sequence and the state tree.
3. The video dotting method according to claim 2, wherein the step of matching the audio recognition result by the process state matcher to obtain process anchor information comprises:
matching the keywords in the state tree of the process state matcher with the audio recognition result to obtain a matching result;
and determining to obtain process anchor point information according to the matching result, wherein the process anchor point information comprises the corresponding starting time and ending time of each service process node in the audio file to be identified.
4. The video dotting method according to claim 3, wherein the step of determining to obtain video dotting information according to the process anchor point information comprises:
determining video dotting positions of the service process nodes according to corresponding starting time and ending time of the service process nodes in the process anchor point information in the audio file to be identified;
and acquiring a node title corresponding to each service flow node, and acquiring video dotting information according to the video dotting position and the node title.
5. The video dotting method according to claim 4, wherein before the step of obtaining video dotting information based on the video dotting position and the node title, the video dotting method further comprises:
acquiring a compliance detection result of each service process node corresponding to the video to be dotted, and determining dotting color information corresponding to each video dotting position according to the compliance detection result;
the step of obtaining video dotting information according to the video dotting position and the node title comprises the following steps:
and obtaining video dotting information according to the video dotting position, the dotting color information and the node title.
6. The video dotting method according to any one of claims 1 to 5, wherein said step of dotting the video to be dotted according to the video dotting information comprises:
and drawing the video dotting information on a progress bar of a video player plug-in to realize dotting processing on the video to be dotted.
7. A video dotting apparatus, characterized in that the video dotting apparatus comprises:
the file acquisition module is used for acquiring a video file to be dotted and extracting an audio file to be identified from the video file to be dotted;
the voice recognition module is used for carrying out voice recognition on the audio file to be recognized to obtain an audio recognition result;
the information matching module is used for matching the audio recognition result through the process state matcher to obtain process anchor point information;
and the video dotting module is used for determining to obtain video dotting information according to the process anchor point information and dotting the video to be dotted according to the video dotting information.
8. A video dotting apparatus, characterized in that the video dotting apparatus comprises: memory, processor and computer program stored on the memory and executable on the processor, the computer program when executed by the processor implementing the steps of the video dotting method according to any one of claims 1 to 6.
9. A computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium, which computer program, when being executed by a processor, carries out the steps of the video dotting method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210610692.6A CN115866290B (en) | 2022-05-31 | 2022-05-31 | Video dotting method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210610692.6A CN115866290B (en) | 2022-05-31 | 2022-05-31 | Video dotting method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115866290A true CN115866290A (en) | 2023-03-28 |
| CN115866290B CN115866290B (en) | 2024-10-25 |
Family
ID=85660147
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210610692.6A Active CN115866290B (en) | 2022-05-31 | 2022-05-31 | Video dotting method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115866290B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116886992A (en) * | 2023-09-06 | 2023-10-13 | 北京中关村科金技术有限公司 | Video data processing method and device, electronic equipment and storage medium |
| CN118377812A (en) * | 2024-06-25 | 2024-07-23 | 宁波菊风系统软件有限公司 | Dual-recording video file quality inspection method and computer readable storage medium |
| CN119025702A (en) * | 2024-10-28 | 2024-11-26 | 深圳星网信通科技股份有限公司 | Control method, device and storage medium of recording management system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013049077A1 (en) * | 2011-09-26 | 2013-04-04 | Limelight Networks, Inc. | Methods and systems for generating automated tags for video files and indentifying intra-video features of interest |
| CN106571137A (en) * | 2016-10-28 | 2017-04-19 | 努比亚技术有限公司 | Terminal voice dotting control device and method |
| CN109743624A (en) * | 2018-12-14 | 2019-05-10 | 深圳壹账通智能科技有限公司 | Video cutting method, device, computer equipment and storage medium |
| CN109831677A (en) * | 2018-12-14 | 2019-05-31 | 平安科技（深圳）有限公司 | Video desensitization method, device, computer equipment and storage medium |
| CN113095202A (en) * | 2021-04-07 | 2021-07-09 | 中国工商银行股份有限公司 | Data segmentation method and device in double-record data quality inspection |
| CN113723767A (en) * | 2021-08-10 | 2021-11-30 | 上海浦东发展银行股份有限公司 | Business process quality inspection method and device based on voice interaction data |
-
2022
- 2022-05-31 CN CN202210610692.6A patent/CN115866290B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013049077A1 (en) * | 2011-09-26 | 2013-04-04 | Limelight Networks, Inc. | Methods and systems for generating automated tags for video files and indentifying intra-video features of interest |
| CN106571137A (en) * | 2016-10-28 | 2017-04-19 | 努比亚技术有限公司 | Terminal voice dotting control device and method |
| CN109743624A (en) * | 2018-12-14 | 2019-05-10 | 深圳壹账通智能科技有限公司 | Video cutting method, device, computer equipment and storage medium |
| CN109831677A (en) * | 2018-12-14 | 2019-05-31 | 平安科技（深圳）有限公司 | Video desensitization method, device, computer equipment and storage medium |
| CN113095202A (en) * | 2021-04-07 | 2021-07-09 | 中国工商银行股份有限公司 | Data segmentation method and device in double-record data quality inspection |
| CN113723767A (en) * | 2021-08-10 | 2021-11-30 | 上海浦东发展银行股份有限公司 | Business process quality inspection method and device based on voice interaction data |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116886992A (en) * | 2023-09-06 | 2023-10-13 | 北京中关村科金技术有限公司 | Video data processing method and device, electronic equipment and storage medium |
| CN116886992B (en) * | 2023-09-06 | 2023-12-01 | 北京中关村科金技术有限公司 | Video data processing method and device, electronic equipment and storage medium |
| CN118377812A (en) * | 2024-06-25 | 2024-07-23 | 宁波菊风系统软件有限公司 | Dual-recording video file quality inspection method and computer readable storage medium |
| CN118377812B (en) * | 2024-06-25 | 2024-09-27 | 宁波菊风系统软件有限公司 | Dual-recording video file quality inspection method and computer readable storage medium |
| CN119025702A (en) * | 2024-10-28 | 2024-11-26 | 深圳星网信通科技股份有限公司 | Control method, device and storage medium of recording management system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115866290B (en) | 2024-10-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110147726B (en) | Service quality inspection method and device, storage medium and electronic device | |
| CN111741356B (en) | Quality inspection method, device and equipment for double-recording video and readable storage medium | |
| CN115866290A (en) | Video dotting method, device, equipment and storage medium | |
| US7596498B2 (en) | Monitoring, mining, and classifying electronically recordable conversations | |
| CN109660744A (en) | The double recording methods of intelligence, equipment, storage medium and device based on big data | |
| CN110533288A (en) | Business handling process detection method, device, computer equipment and storage medium | |
| CN112233690B (en) | Double recording method, device, terminal and storage medium | |
| CN109474843A (en) | The method of speech control terminal, client, server | |
| CN111599359A (en) | Man-machine interaction method, server, client and storage medium | |
| CN113095204A (en) | Double-recording data quality inspection method, device and system | |
| WO2020135756A1 (en) | Video segment extraction method, apparatus and device, and computer-readable storage medium | |
| CN113315979A (en) | Data processing method and device, electronic equipment and storage medium | |
| CN114786035A (en) | Compliance quality inspection and interactive question-answering system and method for live scene | |
| US20230394854A1 (en) | Video-based chapter generation for a communication session | |
| CN110378190B (en) | Video content detection system and detection method based on subject recognition | |
| JP7123448B1 (en) | Information processing method, computer program and information processing device | |
| WO2023272833A1 (en) | Data detection method, apparatus and device and readable storage medium | |
| CN118540427A (en) | Video recording and video file processing method, device, equipment and storage medium | |
| CN114095738A (en) | Video and live broadcast processing method, live broadcast system, electronic device, terminal and medium | |
| CN117408624A (en) | Content life cycle management method and system based on artificial intelligence | |
| CN114727138B (en) | Commodity information processing method, commodity information processing device and computer equipment | |
| US20230326454A1 (en) | Dynamic chapter generation for a communication session | |
| CN109101964A (en) | Determine the method, equipment and storage medium in head and the tail region in multimedia file | |
| TWM578858U (en) | Cross-channel artificial intelligence dialogue platform | |
| CN117319701A (en) | Multimedia data processing method, apparatus and computer readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |